Merge 'Linux v3.0' into Litmus

Some notes:
* Litmus^RT scheduling class is the topmost scheduling class
  (above stop_sched_class).
* scheduler_ipi() function (e.g., in smp_reschedule_interrupt())
  may increase IPI latencies.
* Added path into schedule() to quickly re-evaluate scheduling
  decision without becoming preemptive again. This used to be
  a standard path before the removal of BKL.

Conflicts:
	Makefile
	arch/arm/kernel/calls.S
	arch/arm/kernel/smp.c
	arch/x86/include/asm/unistd_32.h
	arch/x86/kernel/smp.c
	arch/x86/kernel/syscall_table_32.S
	include/linux/hrtimer.h
	kernel/printk.c
	kernel/sched.c
	kernel/sched_fair.c

1 files changed, 26 insertions, 51 deletions

diff --git a/fs/jbd/commit.c b/fs/jbd/commit.c
index 95d8c11c929e..72ffa974b0b8 100644
--- a/fs/jbd/commit.c
+++ b/fs/jbd/commit.c
@@ -20,6 +20,7 @@
 #include <linux/mm.h>
 #include <linux/pagemap.h>
 #include <linux/bio.h>
+#include <linux/blkdev.h>
 
 /*
  * Default IO end handler for temporary BJ_IO buffer_heads.
@@ -137,34 +138,10 @@ static int journal_write_commit_record(journal_t *journal,
         JBUFFER_TRACE(descriptor, "write commit block");
         set_buffer_dirty(bh);
 
-        if (journal->j_flags & JFS_BARRIER) {
-                ret = __sync_dirty_buffer(bh, WRITE_SYNC | WRITE_BARRIER);
-
-                /*
-                 * Is it possible for another commit to fail at roughly
-                 * the same time as this one?  If so, we don't want to
-                 * trust the barrier flag in the super, but instead want
-                 * to remember if we sent a barrier request
-                 */
-                if (ret == -EOPNOTSUPP) {
-                        char b[BDEVNAME_SIZE];
-
-                        printk(KERN_WARNING
-                                "JBD: barrier-based sync failed on %s - "
-                                "disabling barriers\n",
-                                bdevname(journal->j_dev, b));
-                        spin_lock(&journal->j_state_lock);
-                        journal->j_flags &= ~JFS_BARRIER;
-                        spin_unlock(&journal->j_state_lock);
-
-                        /* And try again, without the barrier */
-                        set_buffer_uptodate(bh);
-                        set_buffer_dirty(bh);
-                        ret = sync_dirty_buffer(bh);
-                }
-        } else {
+        if (journal->j_flags & JFS_BARRIER)
+                ret = __sync_dirty_buffer(bh, WRITE_SYNC | WRITE_FLUSH_FUA);
+        else
                 ret = sync_dirty_buffer(bh);
-        }
 
         put_bh(bh);             /* One for getblk() */
         journal_put_journal_head(descriptor);
@@ -318,19 +295,13 @@ void journal_commit_transaction(journal_t *journal)
         int first_tag = 0;
         int tag_flag;
         int i;
-        int write_op = WRITE;
+        struct blk_plug plug;
 
         /*
          * First job: lock down the current transaction and wait for
          * all outstanding updates to complete.
          */
 
-#ifdef COMMIT_STATS
-        spin_lock(&journal->j_list_lock);
-        summarise_journal_usage(journal);
-        spin_unlock(&journal->j_list_lock);
-#endif
-
         /* Do we need to erase the effects of a prior journal_flush? */
         if (journal->j_flags & JFS_FLUSHED) {
                 jbd_debug(3, "super block updated\n");
@@ -351,13 +322,6 @@ void journal_commit_transaction(journal_t *journal)
         spin_lock(&journal->j_state_lock);
         commit_transaction->t_state = T_LOCKED;
 
-        /*
-         * Use plugged writes here, since we want to submit several before
-         * we unplug the device. We don't do explicit unplugging in here,
-         * instead we rely on sync_buffer() doing the unplug for us.
-         */
-        if (commit_transaction->t_synchronous_commit)
-                write_op = WRITE_SYNC_PLUG;
         spin_lock(&commit_transaction->t_handle_lock);
         while (commit_transaction->t_updates) {
                 DEFINE_WAIT(wait);
@@ -392,7 +356,7 @@ void journal_commit_transaction(journal_t *journal)
          * we do not require it to remember exactly which old buffers it
          * has reserved.  This is consistent with the existing behaviour
          * that multiple journal_get_write_access() calls to the same
-         * buffer are perfectly permissable.
+         * buffer are perfectly permissible.
          */
         while (commit_transaction->t_reserved_list) {
                 jh = commit_transaction->t_reserved_list;
@@ -442,8 +406,10 @@ void journal_commit_transaction(journal_t *journal)
          * Now start flushing things to disk, in the order they appear
          * on the transaction lists.  Data blocks go first.
          */
+        blk_start_plug(&plug);
         err = journal_submit_data_buffers(journal, commit_transaction,
-                                          write_op);
+                                          WRITE_SYNC);
+        blk_finish_plug(&plug);
 
         /*
          * Wait for all previously submitted IO to complete.
@@ -504,7 +470,9 @@ void journal_commit_transaction(journal_t *journal)
                 err = 0;
         }
 
-        journal_write_revoke_records(journal, commit_transaction, write_op);
+        blk_start_plug(&plug);
+
+        journal_write_revoke_records(journal, commit_transaction, WRITE_SYNC);
 
         /*
          * If we found any dirty or locked buffers, then we should have
@@ -611,13 +579,13 @@ void journal_commit_transaction(journal_t *journal)
                 /* Bump b_count to prevent truncate from stumbling over
                    the shadowed buffer!  @@@ This can go if we ever get
                    rid of the BJ_IO/BJ_Shadow pairing of buffers. */
-                atomic_inc(&jh2bh(jh)->b_count);
+                get_bh(jh2bh(jh));
 
                 /* Make a temporary IO buffer with which to write it out
                    (this will requeue both the metadata buffer and the
                    temporary IO buffer). new_bh goes on BJ_IO*/
 
-                set_bit(BH_JWrite, &jh2bh(jh)->b_state);
+                set_buffer_jwrite(jh2bh(jh));
                 /*
                  * akpm: journal_write_metadata_buffer() sets
                  * new_bh->b_transaction to commit_transaction.
@@ -627,7 +595,7 @@ void journal_commit_transaction(journal_t *journal)
                 JBUFFER_TRACE(jh, "ph3: write metadata");
                 flags = journal_write_metadata_buffer(commit_transaction,
                                                       jh, &new_jh, blocknr);
-                set_bit(BH_JWrite, &jh2bh(new_jh)->b_state);
+                set_buffer_jwrite(jh2bh(new_jh));
                 wbuf[bufs++] = jh2bh(new_jh);
 
                 /* Record the new block's tag in the current descriptor
@@ -674,7 +642,7 @@ start_journal_io:
                                 clear_buffer_dirty(bh);
                                 set_buffer_uptodate(bh);
                                 bh->b_end_io = journal_end_buffer_io_sync;
-                                submit_bh(write_op, bh);
+                                submit_bh(WRITE_SYNC, bh);
                         }
                         cond_resched();
 
@@ -685,6 +653,8 @@ start_journal_io:
                 }
         }
 
+        blk_finish_plug(&plug);
+
         /* Lo and behold: we have just managed to send a transaction to
            the log.  Before we can commit it, wait for the IO so far to
            complete.  Control buffers being written are on the
@@ -737,7 +707,7 @@ wait_for_iobuf:
                    shadowed buffer */
                 jh = commit_transaction->t_shadow_list->b_tprev;
                 bh = jh2bh(jh);
-                clear_bit(BH_JWrite, &bh->b_state);
+                clear_buffer_jwrite(bh);
                 J_ASSERT_BH(bh, buffer_jbddirty(bh));
 
                 /* The metadata is now released for reuse, but we need
@@ -746,8 +716,13 @@ wait_for_iobuf:
                    required. */
                 JBUFFER_TRACE(jh, "file as BJ_Forget");
                 journal_file_buffer(jh, commit_transaction, BJ_Forget);
-                /* Wake up any transactions which were waiting for this
-                   IO to complete */
+                /*
+                 * Wake up any transactions which were waiting for this
+                 * IO to complete. The barrier must be here so that changes
+                 * by journal_file_buffer() take effect before wake_up_bit()
+                 * does the waitqueue check.
+                 */
+                smp_mb();
                 wake_up_bit(&bh->b_state, BH_Unshadow);
                 JBUFFER_TRACE(jh, "brelse shadowed buffer");
                 __brelse(bh);