Merge commit 'v2.6.39-rc4' into sched/core

Merge reason: Pick up upstream fixes.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

5 files changed, 29 insertions, 25 deletions

diff --git a/kernel/futex.c b/kernel/futex.c
index dfb924ffe65b..fe28dc282eae 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1886,7 +1886,7 @@ retry:
         restart->futex.val = val;
         restart->futex.time = abs_time->tv64;
         restart->futex.bitset = bitset;
-        restart->futex.flags = flags;
+        restart->futex.flags = flags | FLAGS_HAS_TIMEOUT;
 
         ret = -ERESTART_RESTARTBLOCK;
 
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 27960f114efd..8e81a9860a0d 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -364,6 +364,7 @@ void perf_cgroup_switch(struct task_struct *task, int mode)
                         }
 
                         if (mode & PERF_CGROUP_SWIN) {
+                                WARN_ON_ONCE(cpuctx->cgrp);
                                 /* set cgrp before ctxsw in to
                                  * allow event_filter_match() to not
                                  * have to pass task around
@@ -2423,6 +2424,14 @@ static void perf_event_enable_on_exec(struct perf_event_context *ctx)
         if (!ctx || !ctx->nr_events)
                 goto out;
 
+        /*
+         * We must ctxsw out cgroup events to avoid conflict
+         * when invoking perf_task_event_sched_in() later on
+         * in this function. Otherwise we end up trying to
+         * ctxswin cgroup events which are already scheduled
+         * in.
+         */
+        perf_cgroup_sched_out(current);
         task_ctx_sched_out(ctx, EVENT_ALL);
 
         raw_spin_lock(&ctx->lock);
@@ -2447,6 +2456,9 @@ static void perf_event_enable_on_exec(struct perf_event_context *ctx)
 
         raw_spin_unlock(&ctx->lock);
 
+        /*
+         * Also calls ctxswin for cgroup events, if any:
+         */
         perf_event_context_sched_in(ctx, ctx->task);
 out:
         local_irq_restore(flags);
diff --git a/kernel/pid.c b/kernel/pid.c
index 02f221274265..57a8346a270e 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -217,11 +217,14 @@ static int alloc_pidmap(struct pid_namespace *pid_ns)
         return -1;
 }
 
-int next_pidmap(struct pid_namespace *pid_ns, int last)
+int next_pidmap(struct pid_namespace *pid_ns, unsigned int last)
 {
         int offset;
         struct pidmap *map, *end;
 
+        if (last >= PID_MAX_LIMIT)
+                return -1;
+
         offset = (last + 1) & BITS_PER_PAGE_MASK;
         map = &pid_ns->pidmap[(last + 1)/BITS_PER_PAGE];
         end = &pid_ns->pidmap[PIDMAP_ENTRIES];
diff --git a/kernel/sched.c b/kernel/sched.c
index 27d3e73a2af6..30a29ad46eb1 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -4218,7 +4218,7 @@ need_resched:
                          */
                         if (blk_needs_flush_plug(prev)) {
                                 raw_spin_unlock(&rq->lock);
-                                blk_flush_plug(prev);
+                                blk_schedule_flush_plug(prev);
                                 raw_spin_lock(&rq->lock);
                         }
                 }
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 7aa40f8e182d..6957aa298dfa 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -850,29 +850,21 @@ static void blk_add_trace_plug(void *ignore, struct request_queue *q)
                 __blk_add_trace(bt, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL);
 }
 
-static void blk_add_trace_unplug_io(void *ignore, struct request_queue *q)
+static void blk_add_trace_unplug(void *ignore, struct request_queue *q,
+                                    unsigned int depth, bool explicit)
 {
         struct blk_trace *bt = q->blk_trace;
 
         if (bt) {
-                unsigned int pdu = q->rq.count[READ] + q->rq.count[WRITE];
-                __be64 rpdu = cpu_to_be64(pdu);
+                __be64 rpdu = cpu_to_be64(depth);
+                u32 what;
 
-                __blk_add_trace(bt, 0, 0, 0, BLK_TA_UNPLUG_IO, 0,
-                                sizeof(rpdu), &rpdu);
-        }
-}
-
-static void blk_add_trace_unplug_timer(void *ignore, struct request_queue *q)
-{
-        struct blk_trace *bt = q->blk_trace;
-
-        if (bt) {
-                unsigned int pdu = q->rq.count[READ] + q->rq.count[WRITE];
-                __be64 rpdu = cpu_to_be64(pdu);
+                if (explicit)
+                        what = BLK_TA_UNPLUG_IO;
+                else
+                        what = BLK_TA_UNPLUG_TIMER;
 
-                __blk_add_trace(bt, 0, 0, 0, BLK_TA_UNPLUG_TIMER, 0,
-                                sizeof(rpdu), &rpdu);
+                __blk_add_trace(bt, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu);
         }
 }
 
@@ -1015,9 +1007,7 @@ static void blk_register_tracepoints(void)
         WARN_ON(ret);
         ret = register_trace_block_plug(blk_add_trace_plug, NULL);
         WARN_ON(ret);
-        ret = register_trace_block_unplug_timer(blk_add_trace_unplug_timer, NULL);
-        WARN_ON(ret);
-        ret = register_trace_block_unplug_io(blk_add_trace_unplug_io, NULL);
+        ret = register_trace_block_unplug(blk_add_trace_unplug, NULL);
         WARN_ON(ret);
         ret = register_trace_block_split(blk_add_trace_split, NULL);
         WARN_ON(ret);
@@ -1032,8 +1022,7 @@ static void blk_unregister_tracepoints(void)
         unregister_trace_block_rq_remap(blk_add_trace_rq_remap, NULL);
         unregister_trace_block_bio_remap(blk_add_trace_bio_remap, NULL);
         unregister_trace_block_split(blk_add_trace_split, NULL);
-        unregister_trace_block_unplug_io(blk_add_trace_unplug_io, NULL);
-        unregister_trace_block_unplug_timer(blk_add_trace_unplug_timer, NULL);
+        unregister_trace_block_unplug(blk_add_trace_unplug, NULL);
         unregister_trace_block_plug(blk_add_trace_plug, NULL);
         unregister_trace_block_sleeprq(blk_add_trace_sleeprq, NULL);
         unregister_trace_block_getrq(blk_add_trace_getrq, NULL);