The locking policy is such that the erase_complete_block spinlock is
nested within the alloc_sem mutex. This fixes a case in which the
acquisition order was erroneously reversed. This issue was caught by
the following lockdep splat:
=======================================================
[ INFO: possible circular locking dependency detected ]
3.0.5 #1
-------------------------------------------------------
jffs2_gcd_mtd6/299 is trying to acquire lock:
(&c->alloc_sem){+.+.+.}, at: [<c01f7714>] jffs2_garbage_collect_pass+0x314/0x890
but task is already holding lock:
(&(&c->erase_completion_lock)->rlock){+.+...}, at: [<c01f7708>] jffs2_garbage_collect_pass+0x308/0x890
which lock already depends on the new lock.
the existing dependency chain (in reverse order) is:
-> #1 (&(&c->erase_completion_lock)->rlock){+.+...}:
[<c008bec4>] validate_chain+0xe6c/0x10bc
[<c008c660>] __lock_acquire+0x54c/0xba4
[<c008d240>] lock_acquire+0xa4/0x114
[<c046780c>] _raw_spin_lock+0x3c/0x4c
[<c01f744c>] jffs2_garbage_collect_pass+0x4c/0x890
[<c01f937c>] jffs2_garbage_collect_thread+0x1b4/0x1cc
[<c0071a68>] kthread+0x98/0xa0
[<c000f264>] kernel_thread_exit+0x0/0x8
-> #0 (&c->alloc_sem){+.+.+.}:
[<c008ad2c>] print_circular_bug+0x70/0x2c4
[<c008c08c>] validate_chain+0x1034/0x10bc
[<c008c660>] __lock_acquire+0x54c/0xba4
[<c008d240>] lock_acquire+0xa4/0x114
[<c0466628>] mutex_lock_nested+0x74/0x33c
[<c01f7714>] jffs2_garbage_collect_pass+0x314/0x890
[<c01f937c>] jffs2_garbage_collect_thread+0x1b4/0x1cc
[<c0071a68>] kthread+0x98/0xa0
[<c000f264>] kernel_thread_exit+0x0/0x8
other info that might help us debug this:
Possible unsafe locking scenario:
CPU0 CPU1
---- ----
lock(&(&c->erase_completion_lock)->rlock);
lock(&c->alloc_sem);
lock(&(&c->erase_completion_lock)->rlock);
lock(&c->alloc_sem);
*** DEADLOCK ***
1 lock held by jffs2_gcd_mtd6/299:
#0: (&(&c->erase_completion_lock)->rlock){+.+...}, at: [<c01f7708>] jffs2_garbage_collect_pass+0x308/0x890
stack backtrace:
[<c00155dc>] (unwind_backtrace+0x0/0x100) from [<c0463dc0>] (dump_stack+0x20/0x24)
[<c0463dc0>] (dump_stack+0x20/0x24) from [<c008ae84>] (print_circular_bug+0x1c8/0x2c4)
[<c008ae84>] (print_circular_bug+0x1c8/0x2c4) from [<c008c08c>] (validate_chain+0x1034/0x10bc)
[<c008c08c>] (validate_chain+0x1034/0x10bc) from [<c008c660>] (__lock_acquire+0x54c/0xba4)
[<c008c660>] (__lock_acquire+0x54c/0xba4) from [<c008d240>] (lock_acquire+0xa4/0x114)
[<c008d240>] (lock_acquire+0xa4/0x114) from [<c0466628>] (mutex_lock_nested+0x74/0x33c)
[<c0466628>] (mutex_lock_nested+0x74/0x33c) from [<c01f7714>] (jffs2_garbage_collect_pass+0x314/0x890)
[<c01f7714>] (jffs2_garbage_collect_pass+0x314/0x890) from [<c01f937c>] (jffs2_garbage_collect_thread+0x1b4/0x1cc)
[<c01f937c>] (jffs2_garbage_collect_thread+0x1b4/0x1cc) from [<c0071a68>] (kthread+0x98/0xa0)
[<c0071a68>] (kthread+0x98/0xa0) from [<c000f264>] (kernel_thread_exit+0x0/0x8)
This was introduce in '81cfc9f jffs2: Fix serious write stall due to erase'.
Cc: stable@kernel.org [2.6.37+]
Signed-off-by: Josh Cartwright <joshc@linux.com>
Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Use pr_fmt to prefix KBUILD_MODNAME to appropriate logging messages.
Remove now unnecessary internal prefixes from formats.
Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Use the more current logging style.
Coalesce formats, align arguments.
Convert uses of embedded function names to %s, __func__.
A couple of long line checkpatch errors I don't care about exist.
Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
D1 and D2 macros are mostly uses to emit debugging messages.
Convert the logging uses of D1 & D2 to jffs2_dbg(level, fmt, ...)
to be a bit more consistent style with the rest of the kernel.
All jffs2_dbg output is now at KERN_DEBUG where some of
the previous uses were emitted at various KERN_<LEVEL>s.
Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Drop the alloc_sem before erasing flash in
jffs2_garbage_collect_pass().
Otherwise writes are put on hold until the erase
has finised.
Signed-off-by: Joakim Tjernlund <Joakim.Tjernlund@transmode.se>
Signed-off-by: Artem Bityutskiy <Artem.Bityutskiy@nokia.com>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
jffs2_garbage_collect_pass() would previously return -EAGAIN if it
couldn't find anything to garbage collect from, and there were blocks on
the erase_pending_list. If the blocks were actually in the process of
being erased, though, then they wouldn't be on that list. Check for
nr_erasing_blocks being non-zero instead.
Fix jffs2_reserve_space() to wait for the in-progress erases to
complete, when jffs2_garbage_collect_pass() returns -EAGAIN.
And fix jffs2_erase_succeeded() to actually wake up the erase_wait wq
that jffs2_reserve_space() is now using.
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Ever since jffs2_garbage_collect_metadata() was first half-written in
February 2001, it's been broken on architectures where 'char' is signed.
When garbage collecting a symlink with target length above 127, the payload
length would end up negative, causing interesting and bad things to happen.
Cc: stable@kernel.org
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
To support NFS export, we need to know the parent inode of directories.
Rather than growing the jffs2_inode_cache structure, share space with
the nlink field -- which was always set to 1 for directories anyway.
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
We don't actually care about nlink; we only care whether the inode in
question is unlinked or not.
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
When _all_ the blocks were on the erase_pending_list, we could't find a
block to GC from but there was no _actually_ free space, and
jffs2_reserve_space() would get a little unhappy.
Handle this case by returning -EAGAIN from jffs2_garbage_collect_pass().
There are two callers of that function -- jffs2_flush_wbuf_gc(), which
will interpret it as an error and flush the writebuffer by other means,
and jffs2_reserve_space(), which we modify to respond to -EAGAIN with an
immediate call to jffs2_erase_pending_blocks() and another run round the
loop.
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
fs/jffs2/gc.c:1147:29: warning: symbol 'jeb' shadows an earlier one
fs/jffs2/gc.c:1084:89: originally declared here
fs/jffs2/gc.c:1197:29: warning: symbol 'jeb' shadows an earlier one
fs/jffs2/gc.c:1084:89: originally declared here
Rename the unused 'jeb' argument to avoid this. We could potentially
remove the argument, but GCC should be doing that anyway.
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
In three places: summary scan, normal scan, REF_PRISTINE GC.
Just truncate at the NUL, since that was the correct thing to do in the
only case where this (inexplicable) breakage has been seen.
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
In OLPC trac #4184 we found a case where a corrupted node didn't
actually get obsoleted when we tried to garbage-collect it. So we wrote
out many million copies of it, in repeated attempts to obsolete it,
until the flash became full. Don't Do That.
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
In particular, remove the bit in the LICENCE file about contacting
Red Hat for alternative arrangements. Their errant IS department broke
that arrangement a long time ago -- the policy of collecting copyright
assignments from contributors came to an end when the plug was pulled on
the servers hosting the project, without notice or reason.
We do still dual-license it for use with eCos, with the GPL+exception
licence approved by the FSF as being GPL-compatible. It's just that nobody
has the right to license it differently.
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
We should never find the unchecked size is non-zero after we've finished
checking all inodes. If it happens, used to BUG(), leaving the alloc_sem
held and deadlocking. Instead, just return -ENOSPC after complaining. The
GC thread will die, but read-only operation should be able to continue and
the file system should be unmountable.
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
We observe soft lockups when doing heavy test which creates
directory with a lot of direntries and deletes them. This
cycle is the reason fo this. Make it nicer and add cond_resched()
inside of it.
Signed-off-by: Artem Bityutskiy <dedekind@infradead.org>
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
If xattr_ref is associated with an orphan inode_cache
on filesystem mounting, those xattr_refs are not
released even if this inode_cache is released.
This patch enables to call jffs2_xattr_delete_inode()
for such a irregular inode_cachde too.
Signed-off-by: KaiGai Kohei <kaigai@ak.jp.nec.com>
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
- When xdatum is removed, a new xdatum with 'delete marker' is
written. (version==0xffffffff means 'delete marker')
- When xref is removed, a new xref with 'delete marker' is written.
(odd-numbered xseqno means 'delete marker')
- delete_xattr_(datum/xref)_delay() are new deletion functions
are added. We can only use them if we can detect the target
obsolete xdatum/xref as a orphan or errir one.
(e.g when inode deletion, or detecting crc error)
[1/3] jffs2-xattr-v6-01-delete_marker.patch
Signed-off-by: KaiGai Kohei <kaigai@ak.jp.nec.com>
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
As the first step towards eliminating the ref->next_phys member and saving
memory by using an _array_ of struct jffs2_raw_node_ref per eraseblock,
stop the write functions from allocating their own refs; have them just
_reserve_ the appropriate number instead. Then jffs2_link_node_ref() can
just fill them in.
Use a linked list of pre-allocated refs in the superblock, for now. Once
we switch to an array, it'll just be a case of extending that array.
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
We don't need the upper layers to deal with the physical offset. It's
_always_ c->nextblock->offset + c->sector_size - c->nextblock->free_size
so we might as well just let the actual write functions deal with that.
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Let's avoid the potential for forgetting to set ref->next_in_ino, by doing
it within jffs2_link_node_ref() instead.
This highlights the ugliness of what we're currently doing with
xattr_datum and xattr_ref structures -- we should find a nicer way of
dealing with that.
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
If __totlen is going away, we need to pass the length in separately.
Also stop callers from needlessly setting ref->next_phys to NULL,
since that's done for them... and since that'll also be going away soon.
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
We should preserve these when we come to garbage collect them, not let
them get erased. Use jffs2_garbage_collect_pristine() for this, and make
sure the summary code copes -- just refrain from writing a summary for any
block which contains a node we don't understand.
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Device node major/minor numbers are just stored in the payload of a single
data node. Just extend that to 4 bytes and use new_encode_dev() for it.
We only use the 4-byte format if we _need_ to, if !old_valid_dev(foo).
This preserves backwards compatibility with older code as much as
possible. If we do make devices with major or minor numbers above 255, and
then mount the file system with the old code, it'll just read the first
two bytes and get the numbers wrong. If it comes to garbage-collect it,
it'll then write back those wrong numbers. But that's about the best we
can expect.
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Remove jffs2_garbage_collect_xattr(c, ic).
jffs2_garbage_collect_xattr_datum/ref() are called from gc.c directly.
In original implementation, jffs2_garbage_collect_xattr(c, ic) returns
with holding a spinlock if 'ic' is inode_cache. But it returns after
releasing a spinlock if 'ic' is xattr_datum/ref.
It looks so confusable behavior. Thus, this patch makes caller manage
locking/unlocking.
[5/10] jffs2-xattr-v5.1-05-update_xattr_gc.patch
Signed-off-by: KaiGai Kohei <kaigai@ak.jp.nec.com>
This attached patches provide xattr support including POSIX-ACL and
SELinux support on JFFS2 (version.5).
There are some significant differences from previous version posted
at last December.
The biggest change is addition of EBS(Erase Block Summary) support.
Currently, both kernel and usermode utility (sumtool) can recognize
xattr nodes which have JFFS2_NODETYPE_XATTR/_XREF nodetype.
In addition, some bugs are fixed.
- A potential race condition was fixed.
- Unexpected fail when updating a xattr by same name/value pair was fixed.
- A bug when removing xattr name/value pair was fixed.
The fundamental structures (such as using two new nodetypes and exclusion
mechanism by rwsem) are unchanged. But most of implementation were reviewed
and updated if necessary.
Espacially, we had to change several internal implementations related to
load_xattr_datum() to avoid a potential race condition.
[1/2] xattr_on_jffs2.kernel.version-5.patch
[2/2] xattr_on_jffs2.utils.version-5.patch
Signed-off-by: KaiGai Kohei <kaigai@ak.jp.nec.com>
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
For a while now, we've postponed CRC-checking of data nodes to be done
by the GC thread, instead of being done while the user is waiting for
mount to finish. The GC thread would iterate through all the inodes on
the system and check each of their data nodes. It would skip over inodes
which had already been used or were already being read in by
read_inode(), because their data nodes would have been examined anyway.
However, we could sometimes reach the end of the for-each-inode loop and
still have some unchecked space left, if an inode we'd skipped was
_still_ in the process of being read. This fixes that race by actually
waiting for read_inode() to finish rather than just moving on.
Thanks to Ladislav Michl for coming up with a reproducible test case and
helping to track it down.
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
The goal of summary is to speed up the mount time. Erase block summary (EBS)
stores summary information at the end of every (closed) erase block. It is
no longer necessary to scan all nodes separetly (and read all pages of them)
just read this "small" summary, where every information is stored which is
needed at mount time.
This summary information is stored in a JFFS2_FEATURE_RWCOMPAT_DELETE. During
the mount process if there is no summary info the orignal scan process will
be executed. EBS works with NAND and NOR flashes, too.
There is a user space tool called sumtool to generate this summary
information for a JFFS2 image.
Signed-off-by: Ferenc Havasi <havasi@inf.u-szeged.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
From: David Woodhouse <dwmw2@infradead.org>
Signed-off-by: Artem B. Bityutskiy <dedekind@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Various simplifiactions. printk format corrections.
Convert more code to use the new debug functions.
Signed-off-by: Artem B. Bityutskiy <dedekind@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
If debugging is disabled, define debugging functions as empty macros, instead
of using Dx() explicitly.
Signed-off-by: Artem B. Bityutskiy <dedekind@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Move debug functions into a seperate source file
Signed-off-by: Artem B. Bityutskiy <dedekind@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Make sure the erase_pending_wbuf_list's blocks are taken into account
when picking the block to GC.
Signed-off-by: Artem B. Bityuckiy <dedekind@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
DataFlash page-sizes are not a power of two (they're multiples of 528
bytes). There are a few places in JFFS2 code where sector_size is used
as a bitmask. A new macro (SECTOR_ADDR) was defined to calculate these
sector addresses. For non-DataFlash devices, the original (faster)
bitmask operation is still used.
In scan.c, the EMPTY_SCAN_SIZE was a constant of 1024.
Since this could be larger than the sector size of the DataFlash, this
is now basically set to MIN(sector_size, 1024).
Addition of a jffs2_is_writebuffered() macro.
Signed-off-by: Andrew Victor <andrew@sanpeople.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Initial git repository build. I'm not bothering with the full history,
even though we have it. We can create a separate "historical" git
archive of that later if we want to, and in the meantime it's about
3.2GB when imported into git - space that would just make the early
git days unnecessarily complicated, when we don't have a lot of good
infrastructure for it.
Let it rip!
