Revision a742994aa2e271eb8cd8e043d276515ec858ed73 authored by Filipe Manana on 13 February 2015, 16:56:14 UTC, committed by Chris Mason on 14 February 2015, 16:22:49 UTC
If we are recording in the tree log that an inode has new names (new hard links were added), we would drop items, belonging to the inode, that we shouldn't: 1) When the flag BTRFS_INODE_COPY_EVERYTHING is set in the inode's runtime flags, we ended up dropping all the extent and xattr items that were previously logged. This was done only in memory, since logging a new name doesn't imply syncing the log; 2) When the flag BTRFS_INODE_COPY_EVERYTHING is set in the inode's runtime flags, we ended up dropping all the xattr items that were previously logged. Like the case before, this was done only in memory because logging a new name doesn't imply syncing the log. This led to some surprises in scenarios such as the following: 1) write some extents to an inode; 2) fsync the inode; 3) truncate the inode or delete/modify some of its xattrs 4) add a new hard link for that inode 5) fsync some other file, to force the log tree to be durably persisted 6) power failure happens The next time the fs is mounted, the fsync log replay code is executed, and the resulting file doesn't have the content it had when the last fsync against it was performed, instead if has a content matching what it had when the last transaction commit happened. So change the behaviour such that when a new name is logged, only the inode item and reference items are processed. This is easy to reproduce with the test I just made for xfstests, whose main body is: _scratch_mkfs >> $seqres.full 2>&1 _init_flakey _mount_flakey # Create our test file with some data. $XFS_IO_PROG -f -c "pwrite -S 0xaa -b 8K 0 8K" \ $SCRATCH_MNT/foo | _filter_xfs_io # Make sure the file is durably persisted. sync # Append some data to our file, to increase its size. $XFS_IO_PROG -f -c "pwrite -S 0xcc -b 4K 8K 4K" \ $SCRATCH_MNT/foo | _filter_xfs_io # Fsync the file, so from this point on if a crash/power failure happens, our # new data is guaranteed to be there next time the fs is mounted. $XFS_IO_PROG -c "fsync" $SCRATCH_MNT/foo # Now shrink our file to 5000 bytes. $XFS_IO_PROG -c "truncate 5000" $SCRATCH_MNT/foo # Now do an expanding truncate to a size larger than what we had when we last # fsync'ed our file. This is just to verify that after power failure and # replaying the fsync log, our file matches what it was when we last fsync'ed # it - 12Kb size, first 8Kb of data had a value of 0xaa and the last 4Kb of # data had a value of 0xcc. $XFS_IO_PROG -c "truncate 32K" $SCRATCH_MNT/foo # Add one hard link to our file. This made btrfs drop all of our file's # metadata from the fsync log, including the metadata relative to the # extent we just wrote and fsync'ed. This change was made only to the fsync # log in memory, so adding the hard link alone doesn't change the persisted # fsync log. This happened because the previous truncates set the runtime # flag BTRFS_INODE_NEEDS_FULL_SYNC in the btrfs inode structure. ln $SCRATCH_MNT/foo $SCRATCH_MNT/foo_link # Now make sure the in memory fsync log is durably persisted. # Creating and fsync'ing another file will do it. # After this our persisted fsync log will no longer have metadata for our file # foo that points to the extent we wrote and fsync'ed before. touch $SCRATCH_MNT/bar $XFS_IO_PROG -c "fsync" $SCRATCH_MNT/bar # As expected, before the crash/power failure, we should be able to see a file # with a size of 32Kb, with its first 5000 bytes having the value 0xaa and all # the remaining bytes with value 0x00. echo "File content before:" od -t x1 $SCRATCH_MNT/foo # Simulate a crash/power loss. _load_flakey_table $FLAKEY_DROP_WRITES _unmount_flakey _load_flakey_table $FLAKEY_ALLOW_WRITES _mount_flakey # After mounting the fs again, the fsync log was replayed. # The expected result is to see a file with a size of 12Kb, with its first 8Kb # of data having the value 0xaa and its last 4Kb of data having a value of 0xcc. # The btrfs bug used to leave the file as it used te be as of the last # transaction commit - that is, with a size of 8Kb with all bytes having a # value of 0xaa. echo "File content after:" od -t x1 $SCRATCH_MNT/foo The test case for xfstests follows soon. Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Chris Mason <clm@fb.com>
1 parent 1a4bcf4
atomic.h
#ifndef _ASM_GENERIC_BITOPS_ATOMIC_H_
#define _ASM_GENERIC_BITOPS_ATOMIC_H_
#include <asm/types.h>
#include <linux/irqflags.h>
#ifdef CONFIG_SMP
#include <asm/spinlock.h>
#include <asm/cache.h> /* we use L1_CACHE_BYTES */
/* Use an array of spinlocks for our atomic_ts.
* Hash function to index into a different SPINLOCK.
* Since "a" is usually an address, use one spinlock per cacheline.
*/
# define ATOMIC_HASH_SIZE 4
# define ATOMIC_HASH(a) (&(__atomic_hash[ (((unsigned long) a)/L1_CACHE_BYTES) & (ATOMIC_HASH_SIZE-1) ]))
extern arch_spinlock_t __atomic_hash[ATOMIC_HASH_SIZE] __lock_aligned;
/* Can't use raw_spin_lock_irq because of #include problems, so
* this is the substitute */
#define _atomic_spin_lock_irqsave(l,f) do { \
arch_spinlock_t *s = ATOMIC_HASH(l); \
local_irq_save(f); \
arch_spin_lock(s); \
} while(0)
#define _atomic_spin_unlock_irqrestore(l,f) do { \
arch_spinlock_t *s = ATOMIC_HASH(l); \
arch_spin_unlock(s); \
local_irq_restore(f); \
} while(0)
#else
# define _atomic_spin_lock_irqsave(l,f) do { local_irq_save(f); } while (0)
# define _atomic_spin_unlock_irqrestore(l,f) do { local_irq_restore(f); } while (0)
#endif
/*
* NMI events can occur at any time, including when interrupts have been
* disabled by *_irqsave(). So you can get NMI events occurring while a
* *_bit function is holding a spin lock. If the NMI handler also wants
* to do bit manipulation (and they do) then you can get a deadlock
* between the original caller of *_bit() and the NMI handler.
*
* by Keith Owens
*/
/**
* set_bit - Atomically set a bit in memory
* @nr: the bit to set
* @addr: the address to start counting from
*
* This function is atomic and may not be reordered. See __set_bit()
* if you do not require the atomic guarantees.
*
* Note: there are no guarantees that this function will not be reordered
* on non x86 architectures, so if you are writing portable code,
* make sure not to rely on its reordering guarantees.
*
* Note that @nr may be almost arbitrarily large; this function is not
* restricted to acting on a single-word quantity.
*/
static inline void set_bit(int nr, volatile unsigned long *addr)
{
unsigned long mask = BIT_MASK(nr);
unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
unsigned long flags;
_atomic_spin_lock_irqsave(p, flags);
*p |= mask;
_atomic_spin_unlock_irqrestore(p, flags);
}
/**
* clear_bit - Clears a bit in memory
* @nr: Bit to clear
* @addr: Address to start counting from
*
* clear_bit() is atomic and may not be reordered. However, it does
* not contain a memory barrier, so if it is used for locking purposes,
* you should call smp_mb__before_atomic() and/or smp_mb__after_atomic()
* in order to ensure changes are visible on other processors.
*/
static inline void clear_bit(int nr, volatile unsigned long *addr)
{
unsigned long mask = BIT_MASK(nr);
unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
unsigned long flags;
_atomic_spin_lock_irqsave(p, flags);
*p &= ~mask;
_atomic_spin_unlock_irqrestore(p, flags);
}
/**
* change_bit - Toggle a bit in memory
* @nr: Bit to change
* @addr: Address to start counting from
*
* change_bit() is atomic and may not be reordered. It may be
* reordered on other architectures than x86.
* Note that @nr may be almost arbitrarily large; this function is not
* restricted to acting on a single-word quantity.
*/
static inline void change_bit(int nr, volatile unsigned long *addr)
{
unsigned long mask = BIT_MASK(nr);
unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
unsigned long flags;
_atomic_spin_lock_irqsave(p, flags);
*p ^= mask;
_atomic_spin_unlock_irqrestore(p, flags);
}
/**
* test_and_set_bit - Set a bit and return its old value
* @nr: Bit to set
* @addr: Address to count from
*
* This operation is atomic and cannot be reordered.
* It may be reordered on other architectures than x86.
* It also implies a memory barrier.
*/
static inline int test_and_set_bit(int nr, volatile unsigned long *addr)
{
unsigned long mask = BIT_MASK(nr);
unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
unsigned long old;
unsigned long flags;
_atomic_spin_lock_irqsave(p, flags);
old = *p;
*p = old | mask;
_atomic_spin_unlock_irqrestore(p, flags);
return (old & mask) != 0;
}
/**
* test_and_clear_bit - Clear a bit and return its old value
* @nr: Bit to clear
* @addr: Address to count from
*
* This operation is atomic and cannot be reordered.
* It can be reorderdered on other architectures other than x86.
* It also implies a memory barrier.
*/
static inline int test_and_clear_bit(int nr, volatile unsigned long *addr)
{
unsigned long mask = BIT_MASK(nr);
unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
unsigned long old;
unsigned long flags;
_atomic_spin_lock_irqsave(p, flags);
old = *p;
*p = old & ~mask;
_atomic_spin_unlock_irqrestore(p, flags);
return (old & mask) != 0;
}
/**
* test_and_change_bit - Change a bit and return its old value
* @nr: Bit to change
* @addr: Address to count from
*
* This operation is atomic and cannot be reordered.
* It also implies a memory barrier.
*/
static inline int test_and_change_bit(int nr, volatile unsigned long *addr)
{
unsigned long mask = BIT_MASK(nr);
unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
unsigned long old;
unsigned long flags;
_atomic_spin_lock_irqsave(p, flags);
old = *p;
*p = old ^ mask;
_atomic_spin_unlock_irqrestore(p, flags);
return (old & mask) != 0;
}
#endif /* _ASM_GENERIC_BITOPS_ATOMIC_H */
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...