2008-07-14 16:08:37 +00:00
|
|
|
|
/*
|
|
|
|
|
* This file is part of UBIFS.
|
|
|
|
|
*
|
|
|
|
|
* Copyright (C) 2006-2008 Nokia Corporation.
|
|
|
|
|
*
|
|
|
|
|
* This program is free software; you can redistribute it and/or modify it
|
|
|
|
|
* under the terms of the GNU General Public License version 2 as published by
|
|
|
|
|
* the Free Software Foundation.
|
|
|
|
|
*
|
|
|
|
|
* This program is distributed in the hope that it will be useful, but WITHOUT
|
|
|
|
|
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
|
|
|
|
|
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
|
|
|
|
|
* more details.
|
|
|
|
|
*
|
|
|
|
|
* You should have received a copy of the GNU General Public License along with
|
|
|
|
|
* this program; if not, write to the Free Software Foundation, Inc., 51
|
|
|
|
|
* Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
|
|
|
|
|
*
|
|
|
|
|
* Authors: Adrian Hunter
|
|
|
|
|
* Artem Bityutskiy (Битюцкий Артём)
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* This file implements functions that manage the running of the commit process.
|
|
|
|
|
* Each affected module has its own functions to accomplish their part in the
|
|
|
|
|
* commit and those functions are called here.
|
|
|
|
|
*
|
|
|
|
|
* The commit is the process whereby all updates to the index and LEB properties
|
|
|
|
|
* are written out together and the journal becomes empty. This keeps the
|
|
|
|
|
* file system consistent - at all times the state can be recreated by reading
|
|
|
|
|
* the index and LEB properties and then replaying the journal.
|
|
|
|
|
*
|
|
|
|
|
* The commit is split into two parts named "commit start" and "commit end".
|
|
|
|
|
* During commit start, the commit process has exclusive access to the journal
|
|
|
|
|
* by holding the commit semaphore down for writing. As few I/O operations as
|
|
|
|
|
* possible are performed during commit start, instead the nodes that are to be
|
|
|
|
|
* written are merely identified. During commit end, the commit semaphore is no
|
|
|
|
|
* longer held and the journal is again in operation, allowing users to continue
|
|
|
|
|
* to use the file system while the bulk of the commit I/O is performed. The
|
|
|
|
|
* purpose of this two-step approach is to prevent the commit from causing any
|
|
|
|
|
* latency blips. Note that in any case, the commit does not prevent lookups
|
|
|
|
|
* (as permitted by the TNC mutex), or access to VFS data structures e.g. page
|
|
|
|
|
* cache.
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
#include <linux/freezer.h>
|
|
|
|
|
#include <linux/kthread.h>
|
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files. percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.
percpu.h -> slab.h dependency is about to be removed. Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability. As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.
http://userweb.kernel.org/~tj/misc/slabh-sweep.py
The script does the followings.
* Scan files for gfp and slab usages and update includes such that
only the necessary includes are there. ie. if only gfp is used,
gfp.h, if slab is used, slab.h.
* When the script inserts a new include, it looks at the include
blocks and try to put the new include such that its order conforms
to its surrounding. It's put in the include block which contains
core kernel includes, in the same order that the rest are ordered -
alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
doesn't seem to be any matching order.
* If the script can't find a place to put a new include (mostly
because the file doesn't have fitting include block), it prints out
an error message indicating which .h file needs to be added to the
file.
The conversion was done in the following steps.
1. The initial automatic conversion of all .c files updated slightly
over 4000 files, deleting around 700 includes and adding ~480 gfp.h
and ~3000 slab.h inclusions. The script emitted errors for ~400
files.
2. Each error was manually checked. Some didn't need the inclusion,
some needed manual addition while adding it to implementation .h or
embedding .c file was more appropriate for others. This step added
inclusions to around 150 files.
3. The script was run again and the output was compared to the edits
from #2 to make sure no file was left behind.
4. Several build tests were done and a couple of problems were fixed.
e.g. lib/decompress_*.c used malloc/free() wrappers around slab
APIs requiring slab.h to be added manually.
5. The script was run on all .h files but without automatically
editing them as sprinkling gfp.h and slab.h inclusions around .h
files could easily lead to inclusion dependency hell. Most gfp.h
inclusion directives were ignored as stuff from gfp.h was usually
wildly available and often used in preprocessor macros. Each
slab.h inclusion directive was examined and added manually as
necessary.
6. percpu.h was updated not to include slab.h.
7. Build test were done on the following configurations and failures
were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my
distributed build env didn't work with gcov compiles) and a few
more options had to be turned off depending on archs to make things
build (like ipr on powerpc/64 which failed due to missing writeq).
* x86 and x86_64 UP and SMP allmodconfig and a custom test config.
* powerpc and powerpc64 SMP allmodconfig
* sparc and sparc64 SMP allmodconfig
* ia64 SMP allmodconfig
* s390 SMP allmodconfig
* alpha SMP allmodconfig
* um on x86_64 SMP allmodconfig
8. percpu.h modifications were reverted so that it could be applied as
a separate patch and serve as bisection point.
Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.
Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 08:04:11 +00:00
|
|
|
|
#include <linux/slab.h>
|
2008-07-14 16:08:37 +00:00
|
|
|
|
#include "ubifs.h"
|
|
|
|
|
|
2011-01-16 17:22:02 +00:00
|
|
|
|
/*
|
|
|
|
|
* nothing_to_commit - check if there is nothing to commit.
|
|
|
|
|
* @c: UBIFS file-system description object
|
|
|
|
|
*
|
|
|
|
|
* This is a helper function which checks if there is anything to commit. It is
|
|
|
|
|
* used as an optimization to avoid starting the commit if it is not really
|
|
|
|
|
* necessary. Indeed, the commit operation always assumes flash I/O (e.g.,
|
|
|
|
|
* writing the commit start node to the log), and it is better to avoid doing
|
|
|
|
|
* this unnecessarily. E.g., 'ubifs_sync_fs()' runs the commit, but if there is
|
|
|
|
|
* nothing to commit, it is more optimal to avoid any flash I/O.
|
|
|
|
|
*
|
|
|
|
|
* This function has to be called with @c->commit_sem locked for writing -
|
|
|
|
|
* this function does not take LPT/TNC locks because the @c->commit_sem
|
|
|
|
|
* guarantees that we have exclusive access to the TNC and LPT data structures.
|
|
|
|
|
*
|
|
|
|
|
* This function returns %1 if there is nothing to commit and %0 otherwise.
|
|
|
|
|
*/
|
|
|
|
|
static int nothing_to_commit(struct ubifs_info *c)
|
|
|
|
|
{
|
|
|
|
|
/*
|
|
|
|
|
* During mounting or remounting from R/O mode to R/W mode we may
|
|
|
|
|
* commit for various recovery-related reasons.
|
|
|
|
|
*/
|
|
|
|
|
if (c->mounting || c->remounting_rw)
|
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* If the root TNC node is dirty, we definitely have something to
|
|
|
|
|
* commit.
|
|
|
|
|
*/
|
2011-05-30 11:45:30 +00:00
|
|
|
|
if (c->zroot.znode && ubifs_zn_dirty(c->zroot.znode))
|
2011-01-16 17:22:02 +00:00
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Even though the TNC is clean, the LPT tree may have dirty nodes. For
|
|
|
|
|
* example, this may happen if the budgeting subsystem invoked GC to
|
|
|
|
|
* make some free space, and the GC found an LEB with only dirty and
|
|
|
|
|
* free space. In this case GC would just change the lprops of this
|
|
|
|
|
* LEB (by turning all space into free space) and unmap it.
|
|
|
|
|
*/
|
|
|
|
|
if (c->nroot && test_bit(DIRTY_CNODE, &c->nroot->flags))
|
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
|
|
ubifs_assert(atomic_long_read(&c->dirty_zn_cnt) == 0);
|
|
|
|
|
ubifs_assert(c->dirty_pn_cnt == 0);
|
|
|
|
|
ubifs_assert(c->dirty_nn_cnt == 0);
|
|
|
|
|
|
|
|
|
|
return 1;
|
|
|
|
|
}
|
|
|
|
|
|
2008-07-14 16:08:37 +00:00
|
|
|
|
/**
|
|
|
|
|
* do_commit - commit the journal.
|
|
|
|
|
* @c: UBIFS file-system description object
|
|
|
|
|
*
|
|
|
|
|
* This function implements UBIFS commit. It has to be called with commit lock
|
|
|
|
|
* locked. Returns zero in case of success and a negative error code in case of
|
|
|
|
|
* failure.
|
|
|
|
|
*/
|
|
|
|
|
static int do_commit(struct ubifs_info *c)
|
|
|
|
|
{
|
|
|
|
|
int err, new_ltail_lnum, old_ltail_lnum, i;
|
|
|
|
|
struct ubifs_zbranch zroot;
|
|
|
|
|
struct ubifs_lp_stats lst;
|
|
|
|
|
|
|
|
|
|
dbg_cmt("start");
|
2010-09-19 15:34:26 +00:00
|
|
|
|
ubifs_assert(!c->ro_media && !c->ro_mount);
|
UBIFS: introduce new flag for RO due to errors
The R/O state may have various reasons:
1. The UBI volume is R/O
2. The FS is mounted R/O
3. The FS switched to R/O mode because of an error
However, in UBIFS we have only one variable which represents cases
1 and 3 - 'c->ro_media'. Indeed, we set this to 1 if we switch to
R/O mode due to an error, and then we test it in many places to
make sure that we stop writing as soon as the error happens.
But this is very unclean. One consequence of this, for example, is
that in 'ubifs_remount_fs()' we use 'c->ro_media' to check whether
we are in R/O mode because on an error, and we print a message
in this case. However, if we are in R/O mode because the media
is R/O, our message is bogus.
This patch introduces new flag - 'c->ro_error' which is set when
we switch to R/O mode because of an error. It also changes all
"if (c->ro_media)" checks to "if (c->ro_error)" checks, because
this is what the checks actually mean. We do not need to check
for 'c->ro_media' because if the UBI volume is in R/O mode, we
do not allow R/W mounting, and now writes can happen. This is
guaranteed by VFS. But it is good to double-check this, so this
patch also adds many "ubifs_assert(!c->ro_media)" checks.
In the 'ubifs_remount_fs()' function this patch makes a bit more
changes - it fixes the error messages as well.
Signed-off-by: Artem Bityutskiy <Artem.Bityutskiy@nokia.com>
2010-09-17 13:44:28 +00:00
|
|
|
|
|
|
|
|
|
if (c->ro_error) {
|
2008-07-14 16:08:37 +00:00
|
|
|
|
err = -EROFS;
|
|
|
|
|
goto out_up;
|
|
|
|
|
}
|
|
|
|
|
|
2011-01-16 17:22:02 +00:00
|
|
|
|
if (nothing_to_commit(c)) {
|
|
|
|
|
up_write(&c->commit_sem);
|
|
|
|
|
err = 0;
|
|
|
|
|
goto out_cancel;
|
|
|
|
|
}
|
|
|
|
|
|
2008-07-14 16:08:37 +00:00
|
|
|
|
/* Sync all write buffers (necessary for recovery) */
|
|
|
|
|
for (i = 0; i < c->jhead_cnt; i++) {
|
|
|
|
|
err = ubifs_wbuf_sync(&c->jheads[i].wbuf);
|
|
|
|
|
if (err)
|
|
|
|
|
goto out_up;
|
|
|
|
|
}
|
|
|
|
|
|
2008-07-21 14:14:29 +00:00
|
|
|
|
c->cmt_no += 1;
|
2008-07-14 16:08:37 +00:00
|
|
|
|
err = ubifs_gc_start_commit(c);
|
|
|
|
|
if (err)
|
|
|
|
|
goto out_up;
|
|
|
|
|
err = dbg_check_lprops(c);
|
|
|
|
|
if (err)
|
|
|
|
|
goto out_up;
|
|
|
|
|
err = ubifs_log_start_commit(c, &new_ltail_lnum);
|
|
|
|
|
if (err)
|
|
|
|
|
goto out_up;
|
|
|
|
|
err = ubifs_tnc_start_commit(c, &zroot);
|
|
|
|
|
if (err)
|
|
|
|
|
goto out_up;
|
|
|
|
|
err = ubifs_lpt_start_commit(c);
|
|
|
|
|
if (err)
|
|
|
|
|
goto out_up;
|
|
|
|
|
err = ubifs_orphan_start_commit(c);
|
|
|
|
|
if (err)
|
|
|
|
|
goto out_up;
|
|
|
|
|
|
|
|
|
|
ubifs_get_lp_stats(c, &lst);
|
|
|
|
|
|
|
|
|
|
up_write(&c->commit_sem);
|
|
|
|
|
|
|
|
|
|
err = ubifs_tnc_end_commit(c);
|
|
|
|
|
if (err)
|
|
|
|
|
goto out;
|
|
|
|
|
err = ubifs_lpt_end_commit(c);
|
|
|
|
|
if (err)
|
|
|
|
|
goto out;
|
|
|
|
|
err = ubifs_orphan_end_commit(c);
|
|
|
|
|
if (err)
|
|
|
|
|
goto out;
|
|
|
|
|
old_ltail_lnum = c->ltail_lnum;
|
|
|
|
|
err = ubifs_log_end_commit(c, new_ltail_lnum);
|
|
|
|
|
if (err)
|
|
|
|
|
goto out;
|
|
|
|
|
err = dbg_check_old_index(c, &zroot);
|
|
|
|
|
if (err)
|
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
|
|
mutex_lock(&c->mst_mutex);
|
2008-07-21 14:14:29 +00:00
|
|
|
|
c->mst_node->cmt_no = cpu_to_le64(c->cmt_no);
|
2008-07-14 16:08:37 +00:00
|
|
|
|
c->mst_node->log_lnum = cpu_to_le32(new_ltail_lnum);
|
|
|
|
|
c->mst_node->root_lnum = cpu_to_le32(zroot.lnum);
|
|
|
|
|
c->mst_node->root_offs = cpu_to_le32(zroot.offs);
|
|
|
|
|
c->mst_node->root_len = cpu_to_le32(zroot.len);
|
|
|
|
|
c->mst_node->ihead_lnum = cpu_to_le32(c->ihead_lnum);
|
|
|
|
|
c->mst_node->ihead_offs = cpu_to_le32(c->ihead_offs);
|
2011-03-29 15:04:05 +00:00
|
|
|
|
c->mst_node->index_size = cpu_to_le64(c->bi.old_idx_sz);
|
2008-07-14 16:08:37 +00:00
|
|
|
|
c->mst_node->lpt_lnum = cpu_to_le32(c->lpt_lnum);
|
|
|
|
|
c->mst_node->lpt_offs = cpu_to_le32(c->lpt_offs);
|
|
|
|
|
c->mst_node->nhead_lnum = cpu_to_le32(c->nhead_lnum);
|
|
|
|
|
c->mst_node->nhead_offs = cpu_to_le32(c->nhead_offs);
|
|
|
|
|
c->mst_node->ltab_lnum = cpu_to_le32(c->ltab_lnum);
|
|
|
|
|
c->mst_node->ltab_offs = cpu_to_le32(c->ltab_offs);
|
|
|
|
|
c->mst_node->lsave_lnum = cpu_to_le32(c->lsave_lnum);
|
|
|
|
|
c->mst_node->lsave_offs = cpu_to_le32(c->lsave_offs);
|
|
|
|
|
c->mst_node->lscan_lnum = cpu_to_le32(c->lscan_lnum);
|
|
|
|
|
c->mst_node->empty_lebs = cpu_to_le32(lst.empty_lebs);
|
|
|
|
|
c->mst_node->idx_lebs = cpu_to_le32(lst.idx_lebs);
|
|
|
|
|
c->mst_node->total_free = cpu_to_le64(lst.total_free);
|
|
|
|
|
c->mst_node->total_dirty = cpu_to_le64(lst.total_dirty);
|
|
|
|
|
c->mst_node->total_used = cpu_to_le64(lst.total_used);
|
|
|
|
|
c->mst_node->total_dead = cpu_to_le64(lst.total_dead);
|
|
|
|
|
c->mst_node->total_dark = cpu_to_le64(lst.total_dark);
|
|
|
|
|
if (c->no_orphs)
|
|
|
|
|
c->mst_node->flags |= cpu_to_le32(UBIFS_MST_NO_ORPHS);
|
|
|
|
|
else
|
|
|
|
|
c->mst_node->flags &= ~cpu_to_le32(UBIFS_MST_NO_ORPHS);
|
|
|
|
|
err = ubifs_write_master(c);
|
|
|
|
|
mutex_unlock(&c->mst_mutex);
|
|
|
|
|
if (err)
|
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
|
|
err = ubifs_log_post_commit(c, old_ltail_lnum);
|
|
|
|
|
if (err)
|
|
|
|
|
goto out;
|
|
|
|
|
err = ubifs_gc_end_commit(c);
|
|
|
|
|
if (err)
|
|
|
|
|
goto out;
|
|
|
|
|
err = ubifs_lpt_post_commit(c);
|
|
|
|
|
if (err)
|
|
|
|
|
goto out;
|
|
|
|
|
|
2011-01-16 17:22:02 +00:00
|
|
|
|
out_cancel:
|
2008-07-14 16:08:37 +00:00
|
|
|
|
spin_lock(&c->cs_lock);
|
|
|
|
|
c->cmt_state = COMMIT_RESTING;
|
|
|
|
|
wake_up(&c->cmt_wq);
|
|
|
|
|
dbg_cmt("commit end");
|
|
|
|
|
spin_unlock(&c->cs_lock);
|
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
|
|
out_up:
|
|
|
|
|
up_write(&c->commit_sem);
|
|
|
|
|
out:
|
|
|
|
|
ubifs_err("commit failed, error %d", err);
|
|
|
|
|
spin_lock(&c->cs_lock);
|
|
|
|
|
c->cmt_state = COMMIT_BROKEN;
|
|
|
|
|
wake_up(&c->cmt_wq);
|
|
|
|
|
spin_unlock(&c->cs_lock);
|
|
|
|
|
ubifs_ro_mode(c, err);
|
|
|
|
|
return err;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* run_bg_commit - run background commit if it is needed.
|
|
|
|
|
* @c: UBIFS file-system description object
|
|
|
|
|
*
|
|
|
|
|
* This function runs background commit if it is needed. Returns zero in case
|
|
|
|
|
* of success and a negative error code in case of failure.
|
|
|
|
|
*/
|
|
|
|
|
static int run_bg_commit(struct ubifs_info *c)
|
|
|
|
|
{
|
|
|
|
|
spin_lock(&c->cs_lock);
|
|
|
|
|
/*
|
|
|
|
|
* Run background commit only if background commit was requested or if
|
|
|
|
|
* commit is required.
|
|
|
|
|
*/
|
|
|
|
|
if (c->cmt_state != COMMIT_BACKGROUND &&
|
|
|
|
|
c->cmt_state != COMMIT_REQUIRED)
|
|
|
|
|
goto out;
|
|
|
|
|
spin_unlock(&c->cs_lock);
|
|
|
|
|
|
|
|
|
|
down_write(&c->commit_sem);
|
|
|
|
|
spin_lock(&c->cs_lock);
|
|
|
|
|
if (c->cmt_state == COMMIT_REQUIRED)
|
|
|
|
|
c->cmt_state = COMMIT_RUNNING_REQUIRED;
|
|
|
|
|
else if (c->cmt_state == COMMIT_BACKGROUND)
|
|
|
|
|
c->cmt_state = COMMIT_RUNNING_BACKGROUND;
|
|
|
|
|
else
|
|
|
|
|
goto out_cmt_unlock;
|
|
|
|
|
spin_unlock(&c->cs_lock);
|
|
|
|
|
|
|
|
|
|
return do_commit(c);
|
|
|
|
|
|
|
|
|
|
out_cmt_unlock:
|
|
|
|
|
up_write(&c->commit_sem);
|
|
|
|
|
out:
|
|
|
|
|
spin_unlock(&c->cs_lock);
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* ubifs_bg_thread - UBIFS background thread function.
|
|
|
|
|
* @info: points to the file-system description object
|
|
|
|
|
*
|
|
|
|
|
* This function implements various file-system background activities:
|
|
|
|
|
* o when a write-buffer timer expires it synchronizes the appropriate
|
|
|
|
|
* write-buffer;
|
|
|
|
|
* o when the journal is about to be full, it starts in-advance commit.
|
|
|
|
|
*
|
|
|
|
|
* Note, other stuff like background garbage collection may be added here in
|
|
|
|
|
* future.
|
|
|
|
|
*/
|
|
|
|
|
int ubifs_bg_thread(void *info)
|
|
|
|
|
{
|
|
|
|
|
int err;
|
|
|
|
|
struct ubifs_info *c = info;
|
|
|
|
|
|
2008-10-21 09:56:31 +00:00
|
|
|
|
dbg_msg("background thread \"%s\" started, PID %d",
|
|
|
|
|
c->bgt_name, current->pid);
|
2008-07-14 16:08:37 +00:00
|
|
|
|
set_freezable();
|
|
|
|
|
|
|
|
|
|
while (1) {
|
|
|
|
|
if (kthread_should_stop())
|
|
|
|
|
break;
|
|
|
|
|
|
|
|
|
|
if (try_to_freeze())
|
|
|
|
|
continue;
|
|
|
|
|
|
|
|
|
|
set_current_state(TASK_INTERRUPTIBLE);
|
|
|
|
|
/* Check if there is something to do */
|
|
|
|
|
if (!c->need_bgt) {
|
|
|
|
|
/*
|
|
|
|
|
* Nothing prevents us from going sleep now and
|
|
|
|
|
* be never woken up and block the task which
|
|
|
|
|
* could wait in 'kthread_stop()' forever.
|
|
|
|
|
*/
|
|
|
|
|
if (kthread_should_stop())
|
|
|
|
|
break;
|
|
|
|
|
schedule();
|
|
|
|
|
continue;
|
|
|
|
|
} else
|
|
|
|
|
__set_current_state(TASK_RUNNING);
|
|
|
|
|
|
|
|
|
|
c->need_bgt = 0;
|
|
|
|
|
err = ubifs_bg_wbufs_sync(c);
|
|
|
|
|
if (err)
|
|
|
|
|
ubifs_ro_mode(c, err);
|
|
|
|
|
|
|
|
|
|
run_bg_commit(c);
|
|
|
|
|
cond_resched();
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
dbg_msg("background thread \"%s\" stops", c->bgt_name);
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* ubifs_commit_required - set commit state to "required".
|
|
|
|
|
* @c: UBIFS file-system description object
|
|
|
|
|
*
|
|
|
|
|
* This function is called if a commit is required but cannot be done from the
|
|
|
|
|
* calling function, so it is just flagged instead.
|
|
|
|
|
*/
|
|
|
|
|
void ubifs_commit_required(struct ubifs_info *c)
|
|
|
|
|
{
|
|
|
|
|
spin_lock(&c->cs_lock);
|
|
|
|
|
switch (c->cmt_state) {
|
|
|
|
|
case COMMIT_RESTING:
|
|
|
|
|
case COMMIT_BACKGROUND:
|
|
|
|
|
dbg_cmt("old: %s, new: %s", dbg_cstate(c->cmt_state),
|
|
|
|
|
dbg_cstate(COMMIT_REQUIRED));
|
|
|
|
|
c->cmt_state = COMMIT_REQUIRED;
|
|
|
|
|
break;
|
|
|
|
|
case COMMIT_RUNNING_BACKGROUND:
|
|
|
|
|
dbg_cmt("old: %s, new: %s", dbg_cstate(c->cmt_state),
|
|
|
|
|
dbg_cstate(COMMIT_RUNNING_REQUIRED));
|
|
|
|
|
c->cmt_state = COMMIT_RUNNING_REQUIRED;
|
|
|
|
|
break;
|
|
|
|
|
case COMMIT_REQUIRED:
|
|
|
|
|
case COMMIT_RUNNING_REQUIRED:
|
|
|
|
|
case COMMIT_BROKEN:
|
|
|
|
|
break;
|
|
|
|
|
}
|
|
|
|
|
spin_unlock(&c->cs_lock);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* ubifs_request_bg_commit - notify the background thread to do a commit.
|
|
|
|
|
* @c: UBIFS file-system description object
|
|
|
|
|
*
|
|
|
|
|
* This function is called if the journal is full enough to make a commit
|
|
|
|
|
* worthwhile, so background thread is kicked to start it.
|
|
|
|
|
*/
|
|
|
|
|
void ubifs_request_bg_commit(struct ubifs_info *c)
|
|
|
|
|
{
|
|
|
|
|
spin_lock(&c->cs_lock);
|
|
|
|
|
if (c->cmt_state == COMMIT_RESTING) {
|
|
|
|
|
dbg_cmt("old: %s, new: %s", dbg_cstate(c->cmt_state),
|
|
|
|
|
dbg_cstate(COMMIT_BACKGROUND));
|
|
|
|
|
c->cmt_state = COMMIT_BACKGROUND;
|
|
|
|
|
spin_unlock(&c->cs_lock);
|
|
|
|
|
ubifs_wake_up_bgt(c);
|
|
|
|
|
} else
|
|
|
|
|
spin_unlock(&c->cs_lock);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* wait_for_commit - wait for commit.
|
|
|
|
|
* @c: UBIFS file-system description object
|
|
|
|
|
*
|
|
|
|
|
* This function sleeps until the commit operation is no longer running.
|
|
|
|
|
*/
|
|
|
|
|
static int wait_for_commit(struct ubifs_info *c)
|
|
|
|
|
{
|
|
|
|
|
dbg_cmt("pid %d goes sleep", current->pid);
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* The following sleeps if the condition is false, and will be woken
|
|
|
|
|
* when the commit ends. It is possible, although very unlikely, that we
|
|
|
|
|
* will wake up and see the subsequent commit running, rather than the
|
|
|
|
|
* one we were waiting for, and go back to sleep. However, we will be
|
|
|
|
|
* woken again, so there is no danger of sleeping forever.
|
|
|
|
|
*/
|
|
|
|
|
wait_event(c->cmt_wq, c->cmt_state != COMMIT_RUNNING_BACKGROUND &&
|
|
|
|
|
c->cmt_state != COMMIT_RUNNING_REQUIRED);
|
|
|
|
|
dbg_cmt("commit finished, pid %d woke up", current->pid);
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* ubifs_run_commit - run or wait for commit.
|
|
|
|
|
* @c: UBIFS file-system description object
|
|
|
|
|
*
|
|
|
|
|
* This function runs commit and returns zero in case of success and a negative
|
|
|
|
|
* error code in case of failure.
|
|
|
|
|
*/
|
|
|
|
|
int ubifs_run_commit(struct ubifs_info *c)
|
|
|
|
|
{
|
|
|
|
|
int err = 0;
|
|
|
|
|
|
|
|
|
|
spin_lock(&c->cs_lock);
|
|
|
|
|
if (c->cmt_state == COMMIT_BROKEN) {
|
2011-05-26 13:57:14 +00:00
|
|
|
|
err = -EROFS;
|
2008-07-14 16:08:37 +00:00
|
|
|
|
goto out;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
if (c->cmt_state == COMMIT_RUNNING_BACKGROUND)
|
|
|
|
|
/*
|
|
|
|
|
* We set the commit state to 'running required' to indicate
|
|
|
|
|
* that we want it to complete as quickly as possible.
|
|
|
|
|
*/
|
|
|
|
|
c->cmt_state = COMMIT_RUNNING_REQUIRED;
|
|
|
|
|
|
|
|
|
|
if (c->cmt_state == COMMIT_RUNNING_REQUIRED) {
|
|
|
|
|
spin_unlock(&c->cs_lock);
|
|
|
|
|
return wait_for_commit(c);
|
|
|
|
|
}
|
|
|
|
|
spin_unlock(&c->cs_lock);
|
|
|
|
|
|
|
|
|
|
/* Ok, the commit is indeed needed */
|
|
|
|
|
|
|
|
|
|
down_write(&c->commit_sem);
|
|
|
|
|
spin_lock(&c->cs_lock);
|
|
|
|
|
/*
|
|
|
|
|
* Since we unlocked 'c->cs_lock', the state may have changed, so
|
|
|
|
|
* re-check it.
|
|
|
|
|
*/
|
|
|
|
|
if (c->cmt_state == COMMIT_BROKEN) {
|
2011-05-26 13:57:14 +00:00
|
|
|
|
err = -EROFS;
|
2008-07-14 16:08:37 +00:00
|
|
|
|
goto out_cmt_unlock;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
if (c->cmt_state == COMMIT_RUNNING_BACKGROUND)
|
|
|
|
|
c->cmt_state = COMMIT_RUNNING_REQUIRED;
|
|
|
|
|
|
|
|
|
|
if (c->cmt_state == COMMIT_RUNNING_REQUIRED) {
|
|
|
|
|
up_write(&c->commit_sem);
|
|
|
|
|
spin_unlock(&c->cs_lock);
|
|
|
|
|
return wait_for_commit(c);
|
|
|
|
|
}
|
|
|
|
|
c->cmt_state = COMMIT_RUNNING_REQUIRED;
|
|
|
|
|
spin_unlock(&c->cs_lock);
|
|
|
|
|
|
|
|
|
|
err = do_commit(c);
|
|
|
|
|
return err;
|
|
|
|
|
|
|
|
|
|
out_cmt_unlock:
|
|
|
|
|
up_write(&c->commit_sem);
|
|
|
|
|
out:
|
|
|
|
|
spin_unlock(&c->cs_lock);
|
|
|
|
|
return err;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* ubifs_gc_should_commit - determine if it is time for GC to run commit.
|
|
|
|
|
* @c: UBIFS file-system description object
|
|
|
|
|
*
|
|
|
|
|
* This function is called by garbage collection to determine if commit should
|
|
|
|
|
* be run. If commit state is @COMMIT_BACKGROUND, which means that the journal
|
|
|
|
|
* is full enough to start commit, this function returns true. It is not
|
|
|
|
|
* absolutely necessary to commit yet, but it feels like this should be better
|
|
|
|
|
* then to keep doing GC. This function returns %1 if GC has to initiate commit
|
|
|
|
|
* and %0 if not.
|
|
|
|
|
*/
|
|
|
|
|
int ubifs_gc_should_commit(struct ubifs_info *c)
|
|
|
|
|
{
|
|
|
|
|
int ret = 0;
|
|
|
|
|
|
|
|
|
|
spin_lock(&c->cs_lock);
|
|
|
|
|
if (c->cmt_state == COMMIT_BACKGROUND) {
|
|
|
|
|
dbg_cmt("commit required now");
|
|
|
|
|
c->cmt_state = COMMIT_REQUIRED;
|
|
|
|
|
} else
|
|
|
|
|
dbg_cmt("commit not requested");
|
|
|
|
|
if (c->cmt_state == COMMIT_REQUIRED)
|
|
|
|
|
ret = 1;
|
|
|
|
|
spin_unlock(&c->cs_lock);
|
|
|
|
|
return ret;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#ifdef CONFIG_UBIFS_FS_DEBUG
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* struct idx_node - hold index nodes during index tree traversal.
|
|
|
|
|
* @list: list
|
|
|
|
|
* @iip: index in parent (slot number of this indexing node in the parent
|
|
|
|
|
* indexing node)
|
|
|
|
|
* @upper_key: all keys in this indexing node have to be less or equivalent to
|
|
|
|
|
* this key
|
|
|
|
|
* @idx: index node (8-byte aligned because all node structures must be 8-byte
|
|
|
|
|
* aligned)
|
|
|
|
|
*/
|
|
|
|
|
struct idx_node {
|
|
|
|
|
struct list_head list;
|
|
|
|
|
int iip;
|
|
|
|
|
union ubifs_key upper_key;
|
|
|
|
|
struct ubifs_idx_node idx __attribute__((aligned(8)));
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* dbg_old_index_check_init - get information for the next old index check.
|
|
|
|
|
* @c: UBIFS file-system description object
|
|
|
|
|
* @zroot: root of the index
|
|
|
|
|
*
|
|
|
|
|
* This function records information about the index that will be needed for the
|
|
|
|
|
* next old index check i.e. 'dbg_check_old_index()'.
|
|
|
|
|
*
|
|
|
|
|
* This function returns %0 on success and a negative error code on failure.
|
|
|
|
|
*/
|
|
|
|
|
int dbg_old_index_check_init(struct ubifs_info *c, struct ubifs_zbranch *zroot)
|
|
|
|
|
{
|
|
|
|
|
struct ubifs_idx_node *idx;
|
|
|
|
|
int lnum, offs, len, err = 0;
|
2008-10-17 10:31:39 +00:00
|
|
|
|
struct ubifs_debug_info *d = c->dbg;
|
2008-07-14 16:08:37 +00:00
|
|
|
|
|
2008-10-17 10:31:39 +00:00
|
|
|
|
d->old_zroot = *zroot;
|
|
|
|
|
lnum = d->old_zroot.lnum;
|
|
|
|
|
offs = d->old_zroot.offs;
|
|
|
|
|
len = d->old_zroot.len;
|
2008-07-14 16:08:37 +00:00
|
|
|
|
|
|
|
|
|
idx = kmalloc(c->max_idx_node_sz, GFP_NOFS);
|
|
|
|
|
if (!idx)
|
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
|
|
err = ubifs_read_node(c, idx, UBIFS_IDX_NODE, len, lnum, offs);
|
|
|
|
|
if (err)
|
|
|
|
|
goto out;
|
|
|
|
|
|
2008-10-17 10:31:39 +00:00
|
|
|
|
d->old_zroot_level = le16_to_cpu(idx->level);
|
|
|
|
|
d->old_zroot_sqnum = le64_to_cpu(idx->ch.sqnum);
|
2008-07-14 16:08:37 +00:00
|
|
|
|
out:
|
|
|
|
|
kfree(idx);
|
|
|
|
|
return err;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* dbg_check_old_index - check the old copy of the index.
|
|
|
|
|
* @c: UBIFS file-system description object
|
|
|
|
|
* @zroot: root of the new index
|
|
|
|
|
*
|
|
|
|
|
* In order to be able to recover from an unclean unmount, a complete copy of
|
|
|
|
|
* the index must exist on flash. This is the "old" index. The commit process
|
|
|
|
|
* must write the "new" index to flash without overwriting or destroying any
|
|
|
|
|
* part of the old index. This function is run at commit end in order to check
|
|
|
|
|
* that the old index does indeed exist completely intact.
|
|
|
|
|
*
|
|
|
|
|
* This function returns %0 on success and a negative error code on failure.
|
|
|
|
|
*/
|
|
|
|
|
int dbg_check_old_index(struct ubifs_info *c, struct ubifs_zbranch *zroot)
|
|
|
|
|
{
|
|
|
|
|
int lnum, offs, len, err = 0, uninitialized_var(last_level), child_cnt;
|
|
|
|
|
int first = 1, iip;
|
2008-10-17 10:31:39 +00:00
|
|
|
|
struct ubifs_debug_info *d = c->dbg;
|
2009-07-15 02:19:03 +00:00
|
|
|
|
union ubifs_key uninitialized_var(lower_key), upper_key, l_key, u_key;
|
2008-07-14 16:08:37 +00:00
|
|
|
|
unsigned long long uninitialized_var(last_sqnum);
|
|
|
|
|
struct ubifs_idx_node *idx;
|
|
|
|
|
struct list_head list;
|
|
|
|
|
struct idx_node *i;
|
|
|
|
|
size_t sz;
|
|
|
|
|
|
2011-06-03 05:53:35 +00:00
|
|
|
|
if (!dbg_is_chk_index(c))
|
2011-03-25 16:33:57 +00:00
|
|
|
|
return 0;
|
2008-07-14 16:08:37 +00:00
|
|
|
|
|
|
|
|
|
INIT_LIST_HEAD(&list);
|
|
|
|
|
|
|
|
|
|
sz = sizeof(struct idx_node) + ubifs_idx_node_sz(c, c->fanout) -
|
|
|
|
|
UBIFS_IDX_NODE_SZ;
|
|
|
|
|
|
|
|
|
|
/* Start at the old zroot */
|
2008-10-17 10:31:39 +00:00
|
|
|
|
lnum = d->old_zroot.lnum;
|
|
|
|
|
offs = d->old_zroot.offs;
|
|
|
|
|
len = d->old_zroot.len;
|
2008-07-14 16:08:37 +00:00
|
|
|
|
iip = 0;
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Traverse the index tree preorder depth-first i.e. do a node and then
|
|
|
|
|
* its subtrees from left to right.
|
|
|
|
|
*/
|
|
|
|
|
while (1) {
|
|
|
|
|
struct ubifs_branch *br;
|
|
|
|
|
|
|
|
|
|
/* Get the next index node */
|
|
|
|
|
i = kmalloc(sz, GFP_NOFS);
|
|
|
|
|
if (!i) {
|
|
|
|
|
err = -ENOMEM;
|
|
|
|
|
goto out_free;
|
|
|
|
|
}
|
|
|
|
|
i->iip = iip;
|
|
|
|
|
/* Keep the index nodes on our path in a linked list */
|
|
|
|
|
list_add_tail(&i->list, &list);
|
|
|
|
|
/* Read the index node */
|
|
|
|
|
idx = &i->idx;
|
|
|
|
|
err = ubifs_read_node(c, idx, UBIFS_IDX_NODE, len, lnum, offs);
|
|
|
|
|
if (err)
|
|
|
|
|
goto out_free;
|
|
|
|
|
/* Validate index node */
|
|
|
|
|
child_cnt = le16_to_cpu(idx->child_cnt);
|
|
|
|
|
if (child_cnt < 1 || child_cnt > c->fanout) {
|
|
|
|
|
err = 1;
|
|
|
|
|
goto out_dump;
|
|
|
|
|
}
|
|
|
|
|
if (first) {
|
|
|
|
|
first = 0;
|
|
|
|
|
/* Check root level and sqnum */
|
2008-10-17 10:31:39 +00:00
|
|
|
|
if (le16_to_cpu(idx->level) != d->old_zroot_level) {
|
2008-07-14 16:08:37 +00:00
|
|
|
|
err = 2;
|
|
|
|
|
goto out_dump;
|
|
|
|
|
}
|
2008-10-17 10:31:39 +00:00
|
|
|
|
if (le64_to_cpu(idx->ch.sqnum) != d->old_zroot_sqnum) {
|
2008-07-14 16:08:37 +00:00
|
|
|
|
err = 3;
|
|
|
|
|
goto out_dump;
|
|
|
|
|
}
|
|
|
|
|
/* Set last values as though root had a parent */
|
|
|
|
|
last_level = le16_to_cpu(idx->level) + 1;
|
|
|
|
|
last_sqnum = le64_to_cpu(idx->ch.sqnum) + 1;
|
|
|
|
|
key_read(c, ubifs_idx_key(c, idx), &lower_key);
|
|
|
|
|
highest_ino_key(c, &upper_key, INUM_WATERMARK);
|
|
|
|
|
}
|
|
|
|
|
key_copy(c, &upper_key, &i->upper_key);
|
|
|
|
|
if (le16_to_cpu(idx->level) != last_level - 1) {
|
|
|
|
|
err = 3;
|
|
|
|
|
goto out_dump;
|
|
|
|
|
}
|
|
|
|
|
/*
|
|
|
|
|
* The index is always written bottom up hence a child's sqnum
|
|
|
|
|
* is always less than the parents.
|
|
|
|
|
*/
|
|
|
|
|
if (le64_to_cpu(idx->ch.sqnum) >= last_sqnum) {
|
|
|
|
|
err = 4;
|
|
|
|
|
goto out_dump;
|
|
|
|
|
}
|
|
|
|
|
/* Check key range */
|
|
|
|
|
key_read(c, ubifs_idx_key(c, idx), &l_key);
|
|
|
|
|
br = ubifs_idx_branch(c, idx, child_cnt - 1);
|
|
|
|
|
key_read(c, &br->key, &u_key);
|
|
|
|
|
if (keys_cmp(c, &lower_key, &l_key) > 0) {
|
|
|
|
|
err = 5;
|
|
|
|
|
goto out_dump;
|
|
|
|
|
}
|
|
|
|
|
if (keys_cmp(c, &upper_key, &u_key) < 0) {
|
|
|
|
|
err = 6;
|
|
|
|
|
goto out_dump;
|
|
|
|
|
}
|
|
|
|
|
if (keys_cmp(c, &upper_key, &u_key) == 0)
|
|
|
|
|
if (!is_hash_key(c, &u_key)) {
|
|
|
|
|
err = 7;
|
|
|
|
|
goto out_dump;
|
|
|
|
|
}
|
|
|
|
|
/* Go to next index node */
|
|
|
|
|
if (le16_to_cpu(idx->level) == 0) {
|
|
|
|
|
/* At the bottom, so go up until can go right */
|
|
|
|
|
while (1) {
|
|
|
|
|
/* Drop the bottom of the list */
|
|
|
|
|
list_del(&i->list);
|
|
|
|
|
kfree(i);
|
|
|
|
|
/* No more list means we are done */
|
|
|
|
|
if (list_empty(&list))
|
|
|
|
|
goto out;
|
|
|
|
|
/* Look at the new bottom */
|
|
|
|
|
i = list_entry(list.prev, struct idx_node,
|
|
|
|
|
list);
|
|
|
|
|
idx = &i->idx;
|
|
|
|
|
/* Can we go right */
|
|
|
|
|
if (iip + 1 < le16_to_cpu(idx->child_cnt)) {
|
|
|
|
|
iip = iip + 1;
|
|
|
|
|
break;
|
|
|
|
|
} else
|
|
|
|
|
/* Nope, so go up again */
|
|
|
|
|
iip = i->iip;
|
|
|
|
|
}
|
|
|
|
|
} else
|
|
|
|
|
/* Go down left */
|
|
|
|
|
iip = 0;
|
|
|
|
|
/*
|
|
|
|
|
* We have the parent in 'idx' and now we set up for reading the
|
|
|
|
|
* child pointed to by slot 'iip'.
|
|
|
|
|
*/
|
|
|
|
|
last_level = le16_to_cpu(idx->level);
|
|
|
|
|
last_sqnum = le64_to_cpu(idx->ch.sqnum);
|
|
|
|
|
br = ubifs_idx_branch(c, idx, iip);
|
|
|
|
|
lnum = le32_to_cpu(br->lnum);
|
|
|
|
|
offs = le32_to_cpu(br->offs);
|
|
|
|
|
len = le32_to_cpu(br->len);
|
|
|
|
|
key_read(c, &br->key, &lower_key);
|
|
|
|
|
if (iip + 1 < le16_to_cpu(idx->child_cnt)) {
|
|
|
|
|
br = ubifs_idx_branch(c, idx, iip + 1);
|
|
|
|
|
key_read(c, &br->key, &upper_key);
|
|
|
|
|
} else
|
|
|
|
|
key_copy(c, &i->upper_key, &upper_key);
|
|
|
|
|
}
|
|
|
|
|
out:
|
|
|
|
|
err = dbg_old_index_check_init(c, zroot);
|
|
|
|
|
if (err)
|
|
|
|
|
goto out_free;
|
|
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
|
|
out_dump:
|
|
|
|
|
dbg_err("dumping index node (iip=%d)", i->iip);
|
|
|
|
|
dbg_dump_node(c, idx);
|
|
|
|
|
list_del(&i->list);
|
|
|
|
|
kfree(i);
|
|
|
|
|
if (!list_empty(&list)) {
|
|
|
|
|
i = list_entry(list.prev, struct idx_node, list);
|
|
|
|
|
dbg_err("dumping parent index node");
|
|
|
|
|
dbg_dump_node(c, &i->idx);
|
|
|
|
|
}
|
|
|
|
|
out_free:
|
|
|
|
|
while (!list_empty(&list)) {
|
|
|
|
|
i = list_entry(list.next, struct idx_node, list);
|
|
|
|
|
list_del(&i->list);
|
|
|
|
|
kfree(i);
|
|
|
|
|
}
|
|
|
|
|
ubifs_err("failed, error %d", err);
|
|
|
|
|
if (err > 0)
|
|
|
|
|
err = -EINVAL;
|
|
|
|
|
return err;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#endif /* CONFIG_UBIFS_FS_DEBUG */
|