Merge branch 'upstream-fixes'

19 files changed, 366 insertions, 297 deletions

diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index d17c97d07c8..675bd256829 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -1442,13 +1442,15 @@ ssize_t cifs_user_read(struct file *file, char __user *read_data,
 					 &bytes_read, &smb_read_data,
 					 &buf_type);
 			pSMBr = (struct smb_com_read_rsp *)smb_read_data;
-			if (copy_to_user(current_offset, 
-					 smb_read_data + 4 /* RFC1001 hdr */
-					 + le16_to_cpu(pSMBr->DataOffset), 
-					 bytes_read)) {
-				rc = -EFAULT;
-			}
 			if (smb_read_data) {
+				if (copy_to_user(current_offset,
+						smb_read_data +
+						4 /* RFC1001 length field */ +
+						le16_to_cpu(pSMBr->DataOffset),
+						bytes_read)) {
+					rc = -EFAULT;
+				}
+
 				if(buf_type == CIFS_SMALL_BUFFER)
 					cifs_small_buf_release(smb_read_data);
 				else if(buf_type == CIFS_LARGE_BUFFER)
diff --git a/fs/compat.c b/fs/compat.c
index 70c5af4cc27..a2ba78bdf7f 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -1751,11 +1751,15 @@ asmlinkage long compat_sys_select(int n, compat_ulong_t __user *inp,
 	ret = compat_core_sys_select(n, inp, outp, exp, &timeout);
 
 	if (tvp) {
+		struct compat_timeval rtv;
+
 		if (current->personality & STICKY_TIMEOUTS)
 			goto sticky;
-		tv.tv_usec = jiffies_to_usecs(do_div((*(u64*)&timeout), HZ));
-		tv.tv_sec = timeout;
-		if (copy_to_user(tvp, &tv, sizeof(tv))) {
+		rtv.tv_usec = jiffies_to_usecs(do_div((*(u64*)&timeout), HZ));
+		rtv.tv_sec = timeout;
+		if (compat_timeval_compare(&rtv, &tv) < 0)
+			rtv = tv;
+		if (copy_to_user(tvp, &rtv, sizeof(rtv))) {
 sticky:
 			/*
 			 * If an application puts its timeval in read-only
@@ -1822,13 +1826,17 @@ asmlinkage long compat_sys_pselect7(int n, compat_ulong_t __user *inp,
 	} while (!ret && !timeout && tsp && (ts.tv_sec || ts.tv_nsec));
 
 	if (tsp && !(current->personality & STICKY_TIMEOUTS)) {
-		ts.tv_sec += timeout / HZ;
-		ts.tv_nsec += (timeout % HZ) * (1000000000/HZ);
-		if (ts.tv_nsec >= 1000000000) {
-			ts.tv_sec++;
-			ts.tv_nsec -= 1000000000;
+		struct compat_timespec rts;
+
+		rts.tv_sec = timeout / HZ;
+		rts.tv_nsec = (timeout % HZ) * (NSEC_PER_SEC/HZ);
+		if (rts.tv_nsec >= NSEC_PER_SEC) {
+			rts.tv_sec++;
+			rts.tv_nsec -= NSEC_PER_SEC;
 		}
-		(void)copy_to_user(tsp, &ts, sizeof(ts));
+		if (compat_timespec_compare(&rts, &ts) < 0)
+			rts = ts;
+		copy_to_user(tsp, &rts, sizeof(rts));
 	}
 
 	if (ret == -ERESTARTNOHAND) {
@@ -1918,12 +1926,17 @@ asmlinkage long compat_sys_ppoll(struct pollfd __user *ufds,
 		sigprocmask(SIG_SETMASK, &sigsaved, NULL);
 
 	if (tsp && timeout >= 0) {
+		struct compat_timespec rts;
+
 		if (current->personality & STICKY_TIMEOUTS)
 			goto sticky;
 		/* Yes, we know it's actually an s64, but it's also positive. */
-		ts.tv_nsec = jiffies_to_usecs(do_div((*(u64*)&timeout), HZ)) * 1000;
-		ts.tv_sec = timeout;
-		if (copy_to_user(tsp, &ts, sizeof(ts))) {
+		rts.tv_nsec = jiffies_to_usecs(do_div((*(u64*)&timeout), HZ)) *
+					1000;
+		rts.tv_sec = timeout;
+		if (compat_timespec_compare(&rts, &ts) < 0)
+			rts = ts;
+		if (copy_to_user(tsp, &rts, sizeof(rts))) {
 sticky:
 			/*
 			 * If an application puts its timeval in read-only
diff --git a/fs/exec.c b/fs/exec.c
index 055378d2513..0e1c95074d4 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1403,7 +1403,7 @@ static void zap_threads (struct mm_struct *mm)
 		do_each_thread(g,p) {
 			if (mm == p->mm && p != tsk &&
 			    p->ptrace && p->parent->mm == mm) {
-				__ptrace_unlink(p);
+				__ptrace_detach(p, 0);
 			}
 		} while_each_thread(g,p);
 		write_unlock_irq(&tasklist_lock);
diff --git a/fs/jbd/checkpoint.c b/fs/jbd/checkpoint.c
index e6265a0b56b..543ed543d1e 100644
--- a/fs/jbd/checkpoint.c
+++ b/fs/jbd/checkpoint.c
@@ -24,75 +24,29 @@
 #include <linux/slab.h>
 
 /*
- * Unlink a buffer from a transaction checkpoint list.
+ * Unlink a buffer from a transaction.
  *
  * Called with j_list_lock held.
  */
 
-static void __buffer_unlink_first(struct journal_head *jh)
+static inline void __buffer_unlink(struct journal_head *jh)
 {
 	transaction_t *transaction;
 
 	transaction = jh->b_cp_transaction;
+	jh->b_cp_transaction = NULL;
 
 	jh->b_cpnext->b_cpprev = jh->b_cpprev;
 	jh->b_cpprev->b_cpnext = jh->b_cpnext;
-	if (transaction->t_checkpoint_list == jh) {
+	if (transaction->t_checkpoint_list == jh)
 		transaction->t_checkpoint_list = jh->b_cpnext;
-		if (transaction->t_checkpoint_list == jh)
-			transaction->t_checkpoint_list = NULL;
-	}
-}
-
-/*
- * Unlink a buffer from a transaction checkpoint(io) list.
- *
- * Called with j_list_lock held.
- */
-
-static inline void __buffer_unlink(struct journal_head *jh)
-{
-	transaction_t *transaction;
-
-	transaction = jh->b_cp_transaction;
-
-	__buffer_unlink_first(jh);
-	if (transaction->t_checkpoint_io_list == jh) {
-		transaction->t_checkpoint_io_list = jh->b_cpnext;
-		if (transaction->t_checkpoint_io_list == jh)
-			transaction->t_checkpoint_io_list = NULL;
-	}
-}
-
-/*
- * Move a buffer from the checkpoint list to the checkpoint io list
- *
- * Called with j_list_lock held
- */
-
-static inline void __buffer_relink_io(struct journal_head *jh)
-{
-	transaction_t *transaction;
-
-	transaction = jh->b_cp_transaction;
-	__buffer_unlink_first(jh);
-
-	if (!transaction->t_checkpoint_io_list) {
-		jh->b_cpnext = jh->b_cpprev = jh;
-	} else {
-		jh->b_cpnext = transaction->t_checkpoint_io_list;
-		jh->b_cpprev = transaction->t_checkpoint_io_list->b_cpprev;
-		jh->b_cpprev->b_cpnext = jh;
-		jh->b_cpnext->b_cpprev = jh;
-	}
-	transaction->t_checkpoint_io_list = jh;
+	if (transaction->t_checkpoint_list == jh)
+		transaction->t_checkpoint_list = NULL;
 }
 
 /*
  * Try to release a checkpointed buffer from its transaction.
- * Returns 1 if we released it and 2 if we also released the
- * whole transaction.
- *
+ * Returns 1 if we released it.
  * Requires j_list_lock
  * Called under jbd_lock_bh_state(jh2bh(jh)), and drops it
  */
@@ -103,11 +57,12 @@ static int __try_to_free_cp_buf(struct journal_head *jh)
 
 	if (jh->b_jlist == BJ_None && !buffer_locked(bh) && !buffer_dirty(bh)) {
 		JBUFFER_TRACE(jh, "remove from checkpoint list");
-		ret = __journal_remove_checkpoint(jh) + 1;
+		__journal_remove_checkpoint(jh);
 		jbd_unlock_bh_state(bh);
 		journal_remove_journal_head(bh);
 		BUFFER_TRACE(bh, "release");
 		__brelse(bh);
+		ret = 1;
 	} else {
 		jbd_unlock_bh_state(bh);
 	}
@@ -162,53 +117,83 @@ static void jbd_sync_bh(journal_t *journal, struct buffer_head *bh)
 }
 
 /*
- * Clean up transaction's list of buffers submitted for io.
- * We wait for any pending IO to complete and remove any clean
- * buffers. Note that we take the buffers in the opposite ordering
- * from the one in which they were submitted for IO.
+ * Clean up a transaction's checkpoint list.
+ *
+ * We wait for any pending IO to complete and make sure any clean
+ * buffers are removed from the transaction.
+ *
+ * Return 1 if we performed any actions which might have destroyed the
+ * checkpoint.  (journal_remove_checkpoint() deletes the transaction when
+ * the last checkpoint buffer is cleansed)
  *
  * Called with j_list_lock held.
  */
-
-static void __wait_cp_io(journal_t *journal, transaction_t *transaction)
+static int __cleanup_transaction(journal_t *journal, transaction_t *transaction)
 {
-	struct journal_head *jh;
+	struct journal_head *jh, *next_jh, *last_jh;
 	struct buffer_head *bh;
-	tid_t this_tid;
-	int released = 0;
-
-	this_tid = transaction->t_tid;
-restart:
-	/* Didn't somebody clean up the transaction in the meanwhile */
-	if (journal->j_checkpoint_transactions != transaction ||
-		transaction->t_tid != this_tid)
-		return;
-	while (!released && transaction->t_checkpoint_io_list) {
-		jh = transaction->t_checkpoint_io_list;
+	int ret = 0;
+
+	assert_spin_locked(&journal->j_list_lock);
+	jh = transaction->t_checkpoint_list;
+	if (!jh)
+		return 0;
+
+	last_jh = jh->b_cpprev;
+	next_jh = jh;
+	do {
+		jh = next_jh;
 		bh = jh2bh(jh);
-		if (!jbd_trylock_bh_state(bh)) {
-			jbd_sync_bh(journal, bh);
-			spin_lock(&journal->j_list_lock);
-			goto restart;
-		}
 		if (buffer_locked(bh)) {
 			atomic_inc(&bh->b_count);
 			spin_unlock(&journal->j_list_lock);
-			jbd_unlock_bh_state(bh);
 			wait_on_buffer(bh);
 			/* the journal_head may have gone by now */
 			BUFFER_TRACE(bh, "brelse");
 			__brelse(bh);
-			spin_lock(&journal->j_list_lock);
-			goto restart;
+			goto out_return_1;
 		}
+
 		/*
-		 * Now in whatever state the buffer currently is, we know that
-		 * it has been written out and so we can drop it from the list
+		 * This is foul
 		 */
-		released = __journal_remove_checkpoint(jh);
-		jbd_unlock_bh_state(bh);
-	}
+		if (!jbd_trylock_bh_state(bh)) {
+			jbd_sync_bh(journal, bh);
+			goto out_return_1;
+		}
+
+		if (jh->b_transaction != NULL) {
+			transaction_t *t = jh->b_transaction;
+			tid_t tid = t->t_tid;
+
+			spin_unlock(&journal->j_list_lock);
+			jbd_unlock_bh_state(bh);
+			log_start_commit(journal, tid);
+			log_wait_commit(journal, tid);
+			goto out_return_1;
+		}
+
+		/*
+		 * AKPM: I think the buffer_jbddirty test is redundant - it
+		 * shouldn't have NULL b_transaction?
+		 */
+		next_jh = jh->b_cpnext;
+		if (!buffer_dirty(bh) && !buffer_jbddirty(bh)) {
+			BUFFER_TRACE(bh, "remove from checkpoint");
+			__journal_remove_checkpoint(jh);
+			jbd_unlock_bh_state(bh);
+			journal_remove_journal_head(bh);
+			__brelse(bh);
+			ret = 1;
+		} else {
+			jbd_unlock_bh_state(bh);
+		}
+	} while (jh != last_jh);
+
+	return ret;
+out_return_1:
+	spin_lock(&journal->j_list_lock);
+	return 1;
 }
 
 #define NR_BATCH	64
@@ -218,7 +203,9 @@ __flush_batch(journal_t *journal, struct buffer_head **bhs, int *batch_count)
 {
 	int i;
 
+	spin_unlock(&journal->j_list_lock);
 	ll_rw_block(SWRITE, *batch_count, bhs);
+	spin_lock(&journal->j_list_lock);
 	for (i = 0; i < *batch_count; i++) {
 		struct buffer_head *bh = bhs[i];
 		clear_buffer_jwrite(bh);
@@ -234,46 +221,19 @@ __flush_batch(journal_t *journal, struct buffer_head **bhs, int *batch_count)
  * Return 1 if something happened which requires us to abort the current
  * scan of the checkpoint list.  
  *
- * Called with j_list_lock held and drops it if 1 is returned
+ * Called with j_list_lock held.
  * Called under jbd_lock_bh_state(jh2bh(jh)), and drops it
  */
-static int __process_buffer(journal_t *journal, struct journal_head *jh,
-			struct buffer_head **bhs, int *batch_count)
+static int __flush_buffer(journal_t *journal, struct journal_head *jh,
+			struct buffer_head **bhs, int *batch_count,
+			int *drop_count)
 {
 	struct buffer_head *bh = jh2bh(jh);
 	int ret = 0;
 
-	if (buffer_locked(bh)) {
-		get_bh(bh);
-		spin_unlock(&journal->j_list_lock);
-		jbd_unlock_bh_state(bh);
-		wait_on_buffer(bh);
-		/* the journal_head may have gone by now */
-		BUFFER_TRACE(bh, "brelse");
-		put_bh(bh);
-		ret = 1;
-	}
-	else if (jh->b_transaction != NULL) {
-		transaction_t *t = jh->b_transaction;
-		tid_t tid = t->t_tid;
+	if (buffer_dirty(bh) && !buffer_locked(bh) && jh->b_jlist == BJ_None) {
+		J_ASSERT_JH(jh, jh->b_transaction == NULL);
 
-		spin_unlock(&journal->j_list_lock);
-		jbd_unlock_bh_state(bh);
-		log_start_commit(journal, tid);
-		log_wait_commit(journal, tid);
-		ret = 1;
-	}
-	else if (!buffer_dirty(bh)) {
-		J_ASSERT_JH(jh, !buffer_jbddirty(bh));
-		BUFFER_TRACE(bh, "remove from checkpoint");
-		__journal_remove_checkpoint(jh);
-		spin_unlock(&journal->j_list_lock);
-		jbd_unlock_bh_state(bh);
-		journal_remove_journal_head(bh);
-		put_bh(bh);
-		ret = 1;
-	}
-	else {
 		/*
 		 * Important: we are about to write the buffer, and
 		 * possibly block, while still holding the journal lock.
@@ -286,30 +246,45 @@ static int __process_buffer(journal_t *journal, struct journal_head *jh,
 		J_ASSERT_BH(bh, !buffer_jwrite(bh));
 		set_buffer_jwrite(bh);
 		bhs[*batch_count] = bh;
-		__buffer_relink_io(jh);
 		jbd_unlock_bh_state(bh);
 		(*batch_count)++;
 		if (*batch_count == NR_BATCH) {
-			spin_unlock(&journal->j_list_lock);
 			__flush_batch(journal, bhs, batch_count);
 			ret = 1;
 		}
+	} else {
+		int last_buffer = 0;
+		if (jh->b_cpnext == jh) {
+			/* We may be about to drop the transaction.  Tell the
+			 * caller that the lists have changed.
+			 */
+			last_buffer = 1;
+		}
+		if (__try_to_free_cp_buf(jh)) {
+			(*drop_count)++;
+			ret = last_buffer;
+		}
 	}
 	return ret;
 }
 
 /*
- * Perform an actual checkpoint. We take the first transaction on the
- * list of transactions to be checkpointed and send all its buffers
- * to disk. We submit larger chunks of data at once.
+ * Perform an actual checkpoint.  We don't write out only enough to
+ * satisfy the current blocked requests: rather we submit a reasonably
+ * sized chunk of the outstanding data to disk at once for
+ * efficiency.  __log_wait_for_space() will retry if we didn't free enough.
  * 
+ * However, we _do_ take into account the amount requested so that once
+ * the IO has been queued, we can return as soon as enough of it has
+ * completed to disk.
+ *
  * The journal should be locked before calling this function.
  */
 int log_do_checkpoint(journal_t *journal)
 {
-	transaction_t *transaction;
-	tid_t this_tid;
 	int result;
+	int batch_count = 0;
+	struct buffer_head *bhs[NR_BATCH];
 
 	jbd_debug(1, "Start checkpoint\n");
 
@@ -324,70 +299,79 @@ int log_do_checkpoint(journal_t *journal)
 		return result;
 
 	/*
-	 * OK, we need to start writing disk blocks.  Take one transaction
-	 * and write it.
+	 * OK, we need to start writing disk blocks.  Try to free up a
+	 * quarter of the log in a single checkpoint if we can.
 	 */
-	spin_lock(&journal->j_list_lock);
-	if (!journal->j_checkpoint_transactions)
-		goto out;
-	transaction = journal->j_checkpoint_transactions;
-	this_tid = transaction->t_tid;
-restart:
 	/*
-	 * If someone cleaned up this transaction while we slept, we're
-	 * done (maybe it's a new transaction, but it fell at the same
-	 * address).
+	 * AKPM: check this code.  I had a feeling a while back that it
+	 * degenerates into a busy loop at unmount time.
 	 */
- 	if (journal->j_checkpoint_transactions == transaction &&
-			transaction->t_tid == this_tid) {
-		int batch_count = 0;
-		struct buffer_head *bhs[NR_BATCH];
-		struct journal_head *jh;
-		int retry = 0;
-
-		while (!retry && transaction->t_checkpoint_list) {
+	spin_lock(&journal->j_list_lock);
+	while (journal->j_checkpoint_transactions) {
+		transaction_t *transaction;
+		struct journal_head *jh, *last_jh, *next_jh;
+		int drop_count = 0;
+		int cleanup_ret, retry = 0;
+		tid_t this_tid;
+
+		transaction = journal->j_checkpoint_transactions;
+		this_tid = transaction->t_tid;
+		jh = transaction->t_checkpoint_list;
+		last_jh = jh->b_cpprev;
+		next_jh = jh;
+		do {
 			struct buffer_head *bh;
 
-			jh = transaction->t_checkpoint_list;
+			jh = next_jh;
+			next_jh = jh->b_cpnext;
 			bh = jh2bh(jh);
 			if (!jbd_trylock_bh_state(bh)) {
 				jbd_sync_bh(journal, bh);
+				spin_lock(&journal->j_list_lock);
 				retry = 1;
 				break;
 			}
-			retry = __process_buffer(journal, jh, bhs,
-						&batch_count);
-			if (!retry &&
-			    lock_need_resched(&journal->j_list_lock)) {
-				spin_unlock(&journal->j_list_lock);
+			retry = __flush_buffer(journal, jh, bhs, &batch_count, &drop_count);
+			if (cond_resched_lock(&journal->j_list_lock)) {
 				retry = 1;
 				break;
 			}
-		}
+		} while (jh != last_jh && !retry);
 
 		if (batch_count) {
-			if (!retry) {
-				spin_unlock(&journal->j_list_lock);
-				retry = 1;
-			}
 			__flush_batch(journal, bhs, &batch_count);
+			retry = 1;
 		}
 
-		if (retry) {
-			spin_lock(&journal->j_list_lock);
-			goto restart;
-		}
 		/*
-		 * Now we have cleaned up the first transaction's checkpoint
-		 * list.  Let's clean up the second one.
+		 * If someone cleaned up this transaction while we slept, we're
+		 * done
+		 */
+		if (journal->j_checkpoint_transactions != transaction)
+			break;
+		if (retry)
+			continue;
+		/*
+		 * Maybe it's a new transaction, but it fell at the same
+		 * address
 		 */
-		__wait_cp_io(journal, transaction);
+		if (transaction->t_tid != this_tid)
+			continue;
+		/*
+		 * We have walked the whole transaction list without
+		 * finding anything to write to disk.  We had better be
+		 * able to make some progress or we are in trouble.
+		 */
+		cleanup_ret = __cleanup_transaction(journal, transaction);
+		J_ASSERT(drop_count != 0 || cleanup_ret != 0);
+		if (journal->j_checkpoint_transactions != transaction)
+			break;
 	}
-out:
 	spin_unlock(&journal->j_list_lock);
 	result = cleanup_journal_tail(journal);
 	if (result < 0)
 		return result;
+
 	return 0;
 }
 
@@ -472,91 +456,52 @@ int cleanup_journal_tail(journal_t *journal)
 /* Checkpoint list management */
 
 /*
- * journal_clean_one_cp_list
- *
- * Find all the written-back checkpoint buffers in the given list and release them.
- *
- * Called with the journal locked.
- * Called with j_list_lock held.
- * Returns number of bufers reaped (for debug)
- */
-
-static int journal_clean_one_cp_list(struct journal_head *jh, int *released)
-{
-	struct journal_head *last_jh;
-	struct journal_head *next_jh = jh;
-	int ret, freed = 0;
-
-	*released = 0;
-	if (!jh)
-		return 0;
-
- 	last_jh = jh->b_cpprev;
-	do {
-		jh = next_jh;
-		next_jh = jh->b_cpnext;
-		/* Use trylock because of the ranking */
-		if (jbd_trylock_bh_state(jh2bh(jh))) {
-			ret = __try_to_free_cp_buf(jh);
-			if (ret) {
-				freed++;
-				if (ret == 2) {
-					*released = 1;
-					return freed;
-				}
-			}
-		}
-		/*
-		 * This function only frees up some memory if possible so we
-		 * dont have an obligation to finish processing. Bail out if
-		 * preemption requested:
-		 */
-		if (need_resched())
-			return freed;
-	} while (jh != last_jh);
-
-	return freed;
-}
-
-/*
  * journal_clean_checkpoint_list
  *
  * Find all the written-back checkpoint buffers in the journal and release them.
  *
  * Called with the journal locked.
  * Called with j_list_lock held.
- * Returns number of buffers reaped (for debug)
+ * Returns number of bufers reaped (for debug)
  */
 
 int __journal_clean_checkpoint_list(journal_t *journal)
 {
 	transaction_t *transaction, *last_transaction, *next_transaction;
-	int ret = 0, released;
+	int ret = 0;
 
 	transaction = journal->j_checkpoint_transactions;
-	if (!transaction)
+	if (transaction == 0)
 		goto out;
 
 	last_transaction = transaction->t_cpprev;
 	next_transaction = transaction;
 	do {
+		struct journal_head *jh;
+
 		transaction = next_transaction;
 		next_transaction = transaction->t_cpnext;
-		ret += journal_clean_one_cp_list(transaction->
-				t_checkpoint_list, &released);
-		if (need_resched())
-			goto out;
-		if (released)
-			continue;
-		/*
-		 * It is essential that we are as careful as in the case of
-		 * t_checkpoint_list with removing the buffer from the list as
-		 * we can possibly see not yet submitted buffers on io_list
-		 */
-		ret += journal_clean_one_cp_list(transaction->
-				t_checkpoint_io_list, &released);
-		if (need_resched())
-			goto out;
+		jh = transaction->t_checkpoint_list;
+		if (jh) {
+			struct journal_head *last_jh = jh->b_cpprev;
+			struct journal_head *next_jh = jh;
+
+			do {
+				jh = next_jh;
+				next_jh = jh->b_cpnext;
+				/* Use trylock because of the ranknig */
+				if (jbd_trylock_bh_state(jh2bh(jh)))
+					ret += __try_to_free_cp_buf(jh);
+				/*
+				 * This function only frees up some memory
+				 * if possible so we dont have an obligation
+				 * to finish processing. Bail out if preemption
+				 * requested:
+				 */
+				if (need_resched())
+					goto out;
+			} while (jh != last_jh);
+		}
 	} while (transaction != last_transaction);
 out:
 	return ret;
@@ -571,22 +516,18 @@ out:
  * buffer updates committed in that transaction have safely been stored
  * elsewhere on disk.  To achieve this, all of the buffers in a
  * transaction need to be maintained on the transaction's checkpoint
- * lists until they have been rewritten, at which point this function is
+ * list until they have been rewritten, at which point this function is
  * called to remove the buffer from the existing transaction's
- * checkpoint lists.
- *
- * The function returns 1 if it frees the transaction, 0 otherwise.
+ * checkpoint list.
  *
  * This function is called with the journal locked.
  * This function is called with j_list_lock held.
- * This function is called with jbd_lock_bh_state(jh2bh(jh))
  */
 
-int __journal_remove_checkpoint(struct journal_head *jh)
+void __journal_remove_checkpoint(struct journal_head *jh)
 {
 	transaction_t *transaction;
 	journal_t *journal;
-	int ret = 0;
 
 	JBUFFER_TRACE(jh, "entry");
 
@@ -597,10 +538,8 @@ int __journal_remove_checkpoint(struct journal_head *jh)
 	journal = transaction->t_journal;
 
 	__buffer_unlink(jh);
-	jh->b_cp_transaction = NULL;
 
-	if (transaction->t_checkpoint_list != NULL ||
-	    transaction->t_checkpoint_io_list != NULL)
+	if (transaction->t_checkpoint_list != NULL)
 		goto out;
 	JBUFFER_TRACE(jh, "transaction has no more buffers");
 
@@ -626,10 +565,8 @@ int __journal_remove_checkpoint(struct journal_head *jh)
 	/* Just in case anybody was waiting for more transactions to be
            checkpointed... */
 	wake_up(&journal->j_wait_logspace);
-	ret = 1;
 out:
 	JBUFFER_TRACE(jh, "exit");
-	return ret;
 }
 
 /*
@@ -691,7 +628,6 @@ void __journal_drop_transaction(journal_t *journal, transaction_t *transaction)
 	J_ASSERT(transaction->t_shadow_list == NULL);
 	J_ASSERT(transaction->t_log_list == NULL);
 	J_ASSERT(transaction->t_checkpoint_list == NULL);
-	J_ASSERT(transaction->t_checkpoint_io_list == NULL);
 	J_ASSERT(transaction->t_updates == 0);
 	J_ASSERT(journal->j_committing_transaction != transaction);
 	J_ASSERT(journal->j_running_transaction != transaction);
diff --git a/fs/jbd/commit.c b/fs/jbd/commit.c
index 29e62d98bae..002ad2bbc76 100644
--- a/fs/jbd/commit.c
+++ b/fs/jbd/commit.c
@@ -829,8 +829,7 @@ restart_loop:
 	journal->j_committing_transaction = NULL;
 	spin_unlock(&journal->j_state_lock);
 
-	if (commit_transaction->t_checkpoint_list == NULL &&
-	    commit_transaction->t_checkpoint_io_list == NULL) {
+	if (commit_transaction->t_checkpoint_list == NULL) {
 		__journal_drop_transaction(journal, commit_transaction);
 	} else {
 		if (journal->j_checkpoint_transactions == NULL) {
diff --git a/fs/lockd/clntlock.c b/fs/lockd/clntlock.c
index 3eaf6e70108..da6354baa0b 100644
--- a/fs/lockd/clntlock.c
+++ b/fs/lockd/clntlock.c
@@ -111,9 +111,10 @@ long nlmclnt_block(struct nlm_rqst *req, long timeout)
 /*
  * The server lockd has called us back to tell us the lock was granted
  */
-u32
-nlmclnt_grant(struct nlm_lock *lock)
+u32 nlmclnt_grant(const struct sockaddr_in *addr, const struct nlm_lock *lock)
 {
+	const struct file_lock *fl = &lock->fl;
+	const struct nfs_fh *fh = &lock->fh;
 	struct nlm_wait	*block;
 	u32 res = nlm_lck_denied;
 
@@ -122,14 +123,20 @@ nlmclnt_grant(struct nlm_lock *lock)
 	 * Warning: must not use cookie to match it!
 	 */
 	list_for_each_entry(block, &nlm_blocked, b_list) {
-		if (nlm_compare_locks(block->b_lock, &lock->fl)) {
-			/* Alright, we found a lock. Set the return status
-			 * and wake up the caller
-			 */
-			block->b_status = NLM_LCK_GRANTED;
-			wake_up(&block->b_wait);
-			res = nlm_granted;
-		}
+		struct file_lock *fl_blocked = block->b_lock;
+
+		if (!nlm_compare_locks(fl_blocked, fl))
+			continue;
+		if (!nlm_cmp_addr(&block->b_host->h_addr, addr))
+			continue;
+		if (nfs_compare_fh(NFS_FH(fl_blocked->fl_file->f_dentry->d_inode) ,fh) != 0)
+			continue;
+		/* Alright, we found a lock. Set the return status
+		 * and wake up the caller
+		 */
+		block->b_status = NLM_LCK_GRANTED;
+		wake_up(&block->b_wait);
+		res = nlm_granted;
 	}
 	return res;
 }
diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c
index 4063095d849..b10f913aa06 100644
--- a/fs/lockd/svc4proc.c
+++ b/fs/lockd/svc4proc.c
@@ -228,7 +228,7 @@ nlm4svc_proc_granted(struct svc_rqst *rqstp, struct nlm_args *argp,
 	resp->cookie = argp->cookie;
 
 	dprintk("lockd: GRANTED       called\n");
-	resp->status = nlmclnt_grant(&argp->lock);
+	resp->status = nlmclnt_grant(&rqstp->rq_addr, &argp->lock);
 	dprintk("lockd: GRANTED       status %d\n", ntohl(resp->status));
 	return rpc_success;
 }
diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c
index 3bc437e0cf5..35681d9cf1f 100644
--- a/fs/lockd/svcproc.c
+++ b/fs/lockd/svcproc.c
@@ -256,7 +256,7 @@ nlmsvc_proc_granted(struct svc_rqst *rqstp, struct nlm_args *argp,
 	resp->cookie = argp->cookie;
 
 	dprintk("lockd: GRANTED       called\n");
-	resp->status = nlmclnt_grant(&argp->lock);
+	resp->status = nlmclnt_grant(&rqstp->rq_addr, &argp->lock);
 	dprintk("lockd: GRANTED       status %d\n", ntohl(resp->status));
 	return rpc_success;
 }
diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h
index 42eb53b5293..23ceaa7127b 100644
--- a/fs/ocfs2/dlm/dlmcommon.h
+++ b/fs/ocfs2/dlm/dlmcommon.h
@@ -208,6 +208,9 @@ static inline void __dlm_set_joining_node(struct dlm_ctxt *dlm,
 #define DLM_LOCK_RES_IN_PROGRESS          0x00000010
 #define DLM_LOCK_RES_MIGRATING            0x00000020
 
+/* max milliseconds to wait to sync up a network failure with a node death */
+#define DLM_NODE_DEATH_WAIT_MAX (5 * 1000)
+
 #define DLM_PURGE_INTERVAL_MS   (8 * 1000)
 
 struct dlm_lock_resource
@@ -658,6 +661,7 @@ int dlm_launch_recovery_thread(struct dlm_ctxt *dlm);
 void dlm_complete_recovery_thread(struct dlm_ctxt *dlm);
 void dlm_wait_for_recovery(struct dlm_ctxt *dlm);
 int dlm_is_node_dead(struct dlm_ctxt *dlm, u8 node);
+int dlm_wait_for_node_death(struct dlm_ctxt *dlm, u8 node, int timeout);
 
 void dlm_put(struct dlm_ctxt *dlm);
 struct dlm_ctxt *dlm_grab(struct dlm_ctxt *dlm);
diff --git a/fs/ocfs2/dlm/dlmconvert.c b/fs/ocfs2/dlm/dlmconvert.c
index 6001b22a997..f66e2d818cc 100644
--- a/fs/ocfs2/dlm/dlmconvert.c
+++ b/fs/ocfs2/dlm/dlmconvert.c
@@ -392,6 +392,11 @@ static enum dlm_status dlm_send_remote_convert_request(struct dlm_ctxt *dlm,
 	} else {
 		mlog_errno(tmpret);
 		if (dlm_is_host_down(tmpret)) {
+			/* instead of logging the same network error over
+			 * and over, sleep here and wait for the heartbeat
+			 * to notice the node is dead.  times out after 5s. */
+			dlm_wait_for_node_death(dlm, res->owner, 
+						DLM_NODE_DEATH_WAIT_MAX);
 			ret = DLM_RECOVERING;
 			mlog(0, "node %u died so returning DLM_RECOVERING "
 			     "from convert message!\n", res->owner);
@@ -421,7 +426,7 @@ int dlm_convert_lock_handler(struct o2net_msg *msg, u32 len, void *data)
 	struct dlm_lockstatus *lksb;
 	enum dlm_status status = DLM_NORMAL;
 	u32 flags;
-	int call_ast = 0, kick_thread = 0;
+	int call_ast = 0, kick_thread = 0, ast_reserved = 0;
 
 	if (!dlm_grab(dlm)) {
 		dlm_error(DLM_REJECTED);
@@ -490,6 +495,7 @@ int dlm_convert_lock_handler(struct o2net_msg *msg, u32 len, void *data)
 	status = __dlm_lockres_state_to_status(res);
 	if (status == DLM_NORMAL) {
 		__dlm_lockres_reserve_ast(res);
+		ast_reserved = 1;
 		res->state |= DLM_LOCK_RES_IN_PROGRESS;
 		status = __dlmconvert_master(dlm, res, lock, flags,
 					     cnv->requested_type,
@@ -512,10 +518,10 @@ leave:
 	else
 		dlm_lock_put(lock);
 
-	/* either queue the ast or release it */
+	/* either queue the ast or release it, if reserved */
 	if (call_ast)
 		dlm_queue_ast(dlm, lock);
-	else
+	else if (ast_reserved)
 		dlm_lockres_release_ast(dlm, res);
 
 	if (kick_thread)
diff --git a/fs/ocfs2/dlm/dlmlock.c b/fs/ocfs2/dlm/dlmlock.c
index d1a0038557a..671d4ff222c 100644
--- a/fs/ocfs2/dlm/dlmlock.c
+++ b/fs/ocfs2/dlm/dlmlock.c
@@ -220,6 +220,17 @@ static enum dlm_status dlmlock_remote(struct dlm_ctxt *dlm,
 			dlm_error(status);
 		dlm_revert_pending_lock(res, lock);
 		dlm_lock_put(lock);
+	} else if (dlm_is_recovery_lock(res->lockname.name, 
+					res->lockname.len)) {
+		/* special case for the $RECOVERY lock.
+		 * there will never be an AST delivered to put
+		 * this lock on the proper secondary queue
+		 * (granted), so do it manually. */
+		mlog(0, "%s: $RECOVERY lock for this node (%u) is "
+		     "mastered by %u; got lock, manually granting (no ast)\n",
+		     dlm->name, dlm->node_num, res->owner);
+		list_del_init(&lock->list);
+		list_add_tail(&lock->list, &res->granted);
 	}
 	spin_unlock(&res->spinlock);
 
@@ -646,7 +657,19 @@ retry_lock:
 			mlog(0, "retrying lock with migration/"
 			     "recovery/in progress\n");
 			msleep(100);
-			dlm_wait_for_recovery(dlm);
+			/* no waiting for dlm_reco_thread */
+			if (recovery) {
+				if (status == DLM_RECOVERING) {
+					mlog(0, "%s: got RECOVERING "
+					     "for $REOCVERY lock, master "
+					     "was %u\n", dlm->name, 
+					     res->owner);
+					dlm_wait_for_node_death(dlm, res->owner, 
+							DLM_NODE_DEATH_WAIT_MAX);
+				}
+			} else {
+				dlm_wait_for_recovery(dlm);
+			}
 			goto retry_lock;
 		}
 
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index a3194fe173d..2e2e95e6949 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -2482,7 +2482,9 @@ top:
 				atomic_set(&mle->woken, 1);
 				spin_unlock(&mle->spinlock);
 				wake_up(&mle->wq);
-				/* final put will take care of list removal */
+				/* do not need events any longer, so detach 
+				 * from heartbeat */
+				__dlm_mle_detach_hb_events(dlm, mle);
 				__dlm_put_mle(mle);
 			}
 			continue;
@@ -2537,6 +2539,9 @@ top:
 			spin_unlock(&res->spinlock);
 			dlm_lockres_put(res);
 
+			/* about to get rid of mle, detach from heartbeat */
+			__dlm_mle_detach_hb_events(dlm, mle);
+
 			/* dump the mle */
 			spin_lock(&dlm->master_lock);
 			__dlm_put_mle(mle);
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index 186e9a76aa5..ed76bda1a53 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -278,6 +278,24 @@ int dlm_is_node_dead(struct dlm_ctxt *dlm, u8 node)
 	return dead;
 }
 
+int dlm_wait_for_node_death(struct dlm_ctxt *dlm, u8 node, int timeout)
+{
+	if (timeout) {
+		mlog(ML_NOTICE, "%s: waiting %dms for notification of "
+		     "death of node %u\n", dlm->name, timeout, node);
+		wait_event_timeout(dlm->dlm_reco_thread_wq,
+			   dlm_is_node_dead(dlm, node),
+			   msecs_to_jiffies(timeout));
+	} else {
+		mlog(ML_NOTICE, "%s: waiting indefinitely for notification "
+		     "of death of node %u\n", dlm->name, node);
+		wait_event(dlm->dlm_reco_thread_wq,
+			   dlm_is_node_dead(dlm, node));
+	}
+	/* for now, return 0 */
+	return 0;
+}
+
 /* callers of the top-level api calls (dlmlock/dlmunlock) should
  * block on the dlm->reco.event when recovery is in progress.
  * the dlm recovery thread will set this state when it begins
@@ -2032,6 +2050,30 @@ again:
 			     dlm->reco.new_master);
 			status = -EEXIST;
 		} else {
+			status = 0;
+
+			/* see if recovery was already finished elsewhere */
+			spin_lock(&dlm->spinlock);
+			if (dlm->reco.dead_node == O2NM_INVALID_NODE_NUM) {
+				status = -EINVAL;	
+				mlog(0, "%s: got reco EX lock, but "
+				     "node got recovered already\n", dlm->name);
+				if (dlm->reco.new_master != O2NM_INVALID_NODE_NUM) {
+					mlog(ML_ERROR, "%s: new master is %u "
+					     "but no dead node!\n", 
+					     dlm->name, dlm->reco.new_master);
+					BUG();
+				}
+			}
+			spin_unlock(&dlm->spinlock);
+		}
+
+		/* if this node has actually become the recovery master,
+		 * set the master and send the messages to begin recovery */
+		if (!status) {
+			mlog(0, "%s: dead=%u, this=%u, sending "
+			     "begin_reco now\n", dlm->name, 
+			     dlm->reco.dead_node, dlm->node_num);
 			status = dlm_send_begin_reco_message(dlm,
 				      dlm->reco.dead_node);
 			/* this always succeeds */
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index fa0bcac5cea..d329c9df90a 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -1584,10 +1584,9 @@ static int ocfs2_commit_thread(void *arg)
 	while (!(kthread_should_stop() &&
 		 atomic_read(&journal->j_num_trans) == 0)) {
 
-		wait_event_interruptible_timeout(osb->checkpoint_event,
-						 atomic_read(&journal->j_num_trans)
-						 || kthread_should_stop(),
-						 OCFS2_CHECKPOINT_INTERVAL);
+		wait_event_interruptible(osb->checkpoint_event,
+					 atomic_read(&journal->j_num_trans)
+					 || kthread_should_stop());
 
 		status = ocfs2_commit_cache(osb);
 		if (status < 0)
diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h
index 7d0a816184f..2f3a6acdac4 100644
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@@ -29,8 +29,6 @@
 #include <linux/fs.h>
 #include <linux/jbd.h>
 
-#define OCFS2_CHECKPOINT_INTERVAL        (8 * HZ)
-
 enum ocfs2_journal_state {
 	OCFS2_JOURNAL_FREE = 0,
 	OCFS2_JOURNAL_LOADED,
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index ef5e5414e7a..d63da756eb4 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -1124,8 +1124,6 @@ static void handle_attrs(struct super_block *s)
 					 "reiserfs: cannot support attributes until flag is set in super-block");
 			REISERFS_SB(s)->s_mount_opt &= ~(1 << REISERFS_ATTRS);
 		}
-	} else if (le32_to_cpu(rs->s_flags) & reiserfs_attrs_cleared) {
-		REISERFS_SB(s)->s_mount_opt |= (1 << REISERFS_ATTRS);
 	}
 }
 
diff --git a/fs/reiserfs/xattr_acl.c b/fs/reiserfs/xattr_acl.c
index 43de3ba8333..ab8894c3b9e 100644
--- a/fs/reiserfs/xattr_acl.c
+++ b/fs/reiserfs/xattr_acl.c
@@ -228,7 +228,8 @@ struct posix_acl *reiserfs_get_acl(struct inode *inode, int type)
 		acl = ERR_PTR(retval);
 	} else {
 		acl = posix_acl_from_disk(value, retval);
-		*p_acl = posix_acl_dup(acl);
+		if (!IS_ERR(acl))
+			*p_acl = posix_acl_dup(acl);
 	}
 
 	kfree(value);
diff --git a/fs/select.c b/fs/select.c
index bc60a3e14ef..6ce68a9c897 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -398,11 +398,15 @@ asmlinkage long sys_select(int n, fd_set __user *inp, fd_set __user *outp,
 	ret = core_sys_select(n, inp, outp, exp, &timeout);
 
 	if (tvp) {
+		struct timeval rtv;
+
 		if (current->personality & STICKY_TIMEOUTS)
 			goto sticky;
-		tv.tv_usec = jiffies_to_usecs(do_div((*(u64*)&timeout), HZ));
-		tv.tv_sec = timeout;
-		if (copy_to_user(tvp, &tv, sizeof(tv))) {
+		rtv.tv_usec = jiffies_to_usecs(do_div((*(u64*)&timeout), HZ));
+		rtv.tv_sec = timeout;
+		if (timeval_compare(&rtv, &tv) < 0)
+			rtv = tv;
+		if (copy_to_user(tvp, &rtv, sizeof(rtv))) {
 sticky:
 			/*
 			 * If an application puts its timeval in read-only
@@ -460,11 +464,16 @@ asmlinkage long sys_pselect7(int n, fd_set __user *inp, fd_set __user *outp,
 	ret = core_sys_select(n, inp, outp, exp, &timeout);
 
 	if (tsp) {
+		struct timespec rts;
+
 		if (current->personality & STICKY_TIMEOUTS)
 			goto sticky;
-		ts.tv_nsec = jiffies_to_usecs(do_div((*(u64*)&timeout), HZ)) * 1000;
-		ts.tv_sec = timeout;
-		if (copy_to_user(tsp, &ts, sizeof(ts))) {
+		rts.tv_nsec = jiffies_to_usecs(do_div((*(u64*)&timeout), HZ)) *
+						1000;
+		rts.tv_sec = timeout;
+		if (timespec_compare(&rts, &ts) < 0)
+			rts = ts;
+		if (copy_to_user(tsp, &rts, sizeof(rts))) {
 sticky:
 			/*
 			 * If an application puts its timeval in read-only
@@ -758,12 +767,17 @@ asmlinkage long sys_ppoll(struct pollfd __user *ufds, unsigned int nfds,
 		sigprocmask(SIG_SETMASK, &sigsaved, NULL);
 
 	if (tsp && timeout >= 0) {
+		struct timespec rts;
+
 		if (current->personality & STICKY_TIMEOUTS)
 			goto sticky;
 		/* Yes, we know it's actually an s64, but it's also positive. */
-		ts.tv_nsec = jiffies_to_usecs(do_div((*(u64*)&timeout), HZ)) * 1000;
-		ts.tv_sec = timeout;
-		if (copy_to_user(tsp, &ts, sizeof(ts))) {
+		rts.tv_nsec = jiffies_to_usecs(do_div((*(u64*)&timeout), HZ)) *
+						1000;
+		rts.tv_sec = timeout;
+		if (timespec_compare(&rts, &ts) < 0)
+			rts = ts;
+		if (copy_to_user(tsp, &rts, sizeof(rts))) {
 		sticky:
 			/*
 			 * If an application puts its timeval in read-only
diff --git a/fs/stat.c b/fs/stat.c
index 24211b030f3..9948cc1685a 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -261,6 +261,7 @@ asmlinkage long sys_newlstat(char __user *filename, struct stat __user *statbuf)
 	return error;
 }
 
+#ifndef __ARCH_WANT_STAT64
 asmlinkage long sys_newfstatat(int dfd, char __user *filename,
 				struct stat __user *statbuf, int flag)
 {
@@ -281,6 +282,7 @@ asmlinkage long sys_newfstatat(int dfd, char __user *filename,
 out:
 	return error;
 }
+#endif
 
 asmlinkage long sys_newfstat(unsigned int fd, struct stat __user *statbuf)
 {
@@ -395,6 +397,26 @@ asmlinkage long sys_fstat64(unsigned long fd, struct stat64 __user * statbuf)
 	return error;
 }
 
+asmlinkage long sys_fstatat64(int dfd, char __user *filename,
+			       struct stat64 __user *statbuf, int flag)
+{
+	struct kstat stat;
+	int error = -EINVAL;
+
+	if ((flag & ~AT_SYMLINK_NOFOLLOW) != 0)
+		goto out;
+
+	if (flag & AT_SYMLINK_NOFOLLOW)
+		error = vfs_lstat_fd(dfd, filename, &stat);
+	else
+		error = vfs_stat_fd(dfd, filename, &stat);
+
+	if (!error)
+		error = cp_new_stat64(&stat, statbuf);
+
+out:
+	return error;
+}
 #endif /* __ARCH_WANT_STAT64 */
 
 void inode_add_bytes(struct inode *inode, loff_t bytes)