Merge branch 'linus' into sched/core

Conflicts:
	fs/proc/array.c

Merge reason: resolve conflict and queue up dependent patch.

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

97 files changed, 8993 insertions, 8402 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index 3d9c7e27e3f9..b8d4cd8ac0b9 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -58,7 +58,6 @@ obj-$(CONFIG_KEXEC) += kexec.o
 obj-$(CONFIG_BACKTRACE_SELF_TEST) += backtracetest.o
 obj-$(CONFIG_COMPAT) += compat.o
 obj-$(CONFIG_CGROUPS) += cgroup.o
-obj-$(CONFIG_CGROUP_DEBUG) += cgroup_debug.o
 obj-$(CONFIG_CGROUP_FREEZER) += cgroup_freezer.o
 obj-$(CONFIG_CPUSETS) += cpuset.o
 obj-$(CONFIG_CGROUP_NS) += ns_cgroup.o
@@ -87,7 +86,6 @@ obj-$(CONFIG_RELAY) += relay.o
 obj-$(CONFIG_SYSCTL) += utsname_sysctl.o
 obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o
 obj-$(CONFIG_TASKSTATS) += taskstats.o tsacct.o
-obj-$(CONFIG_MARKERS) += marker.o
 obj-$(CONFIG_TRACEPOINTS) += tracepoint.o
 obj-$(CONFIG_LATENCYTOP) += latencytop.o
 obj-$(CONFIG_FUNCTION_TRACER) += trace/
@@ -96,7 +94,7 @@ obj-$(CONFIG_X86_DS) += trace/
 obj-$(CONFIG_RING_BUFFER) += trace/
 obj-$(CONFIG_SMP) += sched_cpupri.o
 obj-$(CONFIG_SLOW_WORK) += slow-work.o
-obj-$(CONFIG_PERF_COUNTERS) += perf_counter.o
+obj-$(CONFIG_PERF_EVENTS) += perf_event.o
 
 ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
 # According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is
diff --git a/kernel/audit.c b/kernel/audit.c
index defc2e6f1e3b..5feed232be9d 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -855,18 +855,24 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 		break;
 	}
 	case AUDIT_SIGNAL_INFO:
-		err = security_secid_to_secctx(audit_sig_sid, &ctx, &len);
-		if (err)
-			return err;
+		len = 0;
+		if (audit_sig_sid) {
+			err = security_secid_to_secctx(audit_sig_sid, &ctx, &len);
+			if (err)
+				return err;
+		}
 		sig_data = kmalloc(sizeof(*sig_data) + len, GFP_KERNEL);
 		if (!sig_data) {
-			security_release_secctx(ctx, len);
+			if (audit_sig_sid)
+				security_release_secctx(ctx, len);
 			return -ENOMEM;
 		}
 		sig_data->uid = audit_sig_uid;
 		sig_data->pid = audit_sig_pid;
-		memcpy(sig_data->ctx, ctx, len);
-		security_release_secctx(ctx, len);
+		if (audit_sig_sid) {
+			memcpy(sig_data->ctx, ctx, len);
+			security_release_secctx(ctx, len);
+		}
 		audit_send_reply(NETLINK_CB(skb).pid, seq, AUDIT_SIGNAL_INFO,
 				0, 0, sig_data, sizeof(*sig_data) + len);
 		kfree(sig_data);
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index 0e96dbc60ea9..cc7e87936cbc 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -45,8 +45,8 @@
 
 struct audit_watch {
 	atomic_t		count;	/* reference count */
-	char			*path;	/* insertion path */
 	dev_t			dev;	/* associated superblock device */
+	char			*path;	/* insertion path */
 	unsigned long		ino;	/* associated inode number */
 	struct audit_parent	*parent; /* associated parent */
 	struct list_head	wlist;	/* entry in parent->watches list */
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 68d3c6a0ecd6..267e484f0198 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -168,12 +168,12 @@ struct audit_context {
 	int		    in_syscall;	/* 1 if task is in a syscall */
 	enum audit_state    state, current_state;
 	unsigned int	    serial;     /* serial number for record */
-	struct timespec	    ctime;      /* time of syscall entry */
 	int		    major;      /* syscall number */
+	struct timespec	    ctime;      /* time of syscall entry */
 	unsigned long	    argv[4];    /* syscall arguments */
-	int		    return_valid; /* return code is valid */
 	long		    return_code;/* syscall return code */
 	u64		    prio;
+	int		    return_valid; /* return code is valid */
 	int		    name_count;
 	struct audit_names  names[AUDIT_NAMES];
 	char *		    filterkey;	/* key for rule that triggered record */
@@ -198,8 +198,8 @@ struct audit_context {
 	char		    target_comm[TASK_COMM_LEN];
 
 	struct audit_tree_refs *trees, *first_trees;
-	int tree_count;
 	struct list_head killed_trees;
+	int tree_count;
 
 	int type;
 	union {
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index c7ece8f027f2..ca83b73fba19 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -23,6 +23,7 @@
  */
 
 #include <linux/cgroup.h>
+#include <linux/ctype.h>
 #include <linux/errno.h>
 #include <linux/fs.h>
 #include <linux/kernel.h>
@@ -48,6 +49,8 @@
 #include <linux/namei.h>
 #include <linux/smp_lock.h>
 #include <linux/pid_namespace.h>
+#include <linux/idr.h>
+#include <linux/vmalloc.h> /* TODO: replace with more sophisticated array */
 
 #include <asm/atomic.h>
 
@@ -60,6 +63,8 @@ static struct cgroup_subsys *subsys[] = {
 #include <linux/cgroup_subsys.h>
 };
 
+#define MAX_CGROUP_ROOT_NAMELEN 64
+
 /*
  * A cgroupfs_root represents the root of a cgroup hierarchy,
  * and may be associated with a superblock to form an active
@@ -74,6 +79,9 @@ struct cgroupfs_root {
 	 */
 	unsigned long subsys_bits;
 
+	/* Unique id for this hierarchy. */
+	int hierarchy_id;
+
 	/* The bitmask of subsystems currently attached to this hierarchy */
 	unsigned long actual_subsys_bits;
 
@@ -94,6 +102,9 @@ struct cgroupfs_root {
 
 	/* The path to use for release notifications. */
 	char release_agent_path[PATH_MAX];
+
+	/* The name for this hierarchy - may be empty */
+	char name[MAX_CGROUP_ROOT_NAMELEN];
 };
 
 /*
@@ -141,6 +152,10 @@ struct css_id {
 static LIST_HEAD(roots);
 static int root_count;
 
+static DEFINE_IDA(hierarchy_ida);
+static int next_hierarchy_id;
+static DEFINE_SPINLOCK(hierarchy_id_lock);
+
 /* dummytop is a shorthand for the dummy hierarchy's top cgroup */
 #define dummytop (&rootnode.top_cgroup)
 
@@ -201,6 +216,7 @@ struct cg_cgroup_link {
 	 * cgroup, anchored on cgroup->css_sets
 	 */
 	struct list_head cgrp_link_list;
+	struct cgroup *cgrp;
 	/*
 	 * List running through cg_cgroup_links pointing at a
 	 * single css_set object, anchored on css_set->cg_links
@@ -227,8 +243,11 @@ static int cgroup_subsys_init_idr(struct cgroup_subsys *ss);
 static DEFINE_RWLOCK(css_set_lock);
 static int css_set_count;
 
-/* hash table for cgroup groups. This improves the performance to
- * find an existing css_set */
+/*
+ * hash table for cgroup groups. This improves the performance to find
+ * an existing css_set. This hash doesn't (currently) take into
+ * account cgroups in empty hierarchies.
+ */
 #define CSS_SET_HASH_BITS	7
 #define CSS_SET_TABLE_SIZE	(1 << CSS_SET_HASH_BITS)
 static struct hlist_head css_set_table[CSS_SET_TABLE_SIZE];
@@ -248,48 +267,22 @@ static struct hlist_head *css_set_hash(struct cgroup_subsys_state *css[])
 	return &css_set_table[index];
 }
 
+static void free_css_set_rcu(struct rcu_head *obj)
+{
+	struct css_set *cg = container_of(obj, struct css_set, rcu_head);
+	kfree(cg);
+}
+
 /* We don't maintain the lists running through each css_set to its
  * task until after the first call to cgroup_iter_start(). This
  * reduces the fork()/exit() overhead for people who have cgroups
  * compiled into their kernel but not actually in use */
 static int use_task_css_set_links __read_mostly;
 
-/* When we create or destroy a css_set, the operation simply
- * takes/releases a reference count on all the cgroups referenced
- * by subsystems in this css_set. This can end up multiple-counting
- * some cgroups, but that's OK - the ref-count is just a
- * busy/not-busy indicator; ensuring that we only count each cgroup
- * once would require taking a global lock to ensure that no
- * subsystems moved between hierarchies while we were doing so.
- *
- * Possible TODO: decide at boot time based on the number of
- * registered subsystems and the number of CPUs or NUMA nodes whether
- * it's better for performance to ref-count every subsystem, or to
- * take a global lock and only add one ref count to each hierarchy.
- */
-
-/*
- * unlink a css_set from the list and free it
- */
-static void unlink_css_set(struct css_set *cg)
+static void __put_css_set(struct css_set *cg, int taskexit)
 {
 	struct cg_cgroup_link *link;
 	struct cg_cgroup_link *saved_link;
-
-	hlist_del(&cg->hlist);
-	css_set_count--;
-
-	list_for_each_entry_safe(link, saved_link, &cg->cg_links,
-				 cg_link_list) {
-		list_del(&link->cg_link_list);
-		list_del(&link->cgrp_link_list);
-		kfree(link);
-	}
-}
-
-static void __put_css_set(struct css_set *cg, int taskexit)
-{
-	int i;
 	/*
 	 * Ensure that the refcount doesn't hit zero while any readers
 	 * can see it. Similar to atomic_dec_and_lock(), but for an
@@ -302,21 +295,28 @@ static void __put_css_set(struct css_set *cg, int taskexit)
 		write_unlock(&css_set_lock);
 		return;
 	}
-	unlink_css_set(cg);
-	write_unlock(&css_set_lock);
 
-	rcu_read_lock();
-	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
-		struct cgroup *cgrp = rcu_dereference(cg->subsys[i]->cgroup);
+	/* This css_set is dead. unlink it and release cgroup refcounts */
+	hlist_del(&cg->hlist);
+	css_set_count--;
+
+	list_for_each_entry_safe(link, saved_link, &cg->cg_links,
+				 cg_link_list) {
+		struct cgroup *cgrp = link->cgrp;
+		list_del(&link->cg_link_list);
+		list_del(&link->cgrp_link_list);
 		if (atomic_dec_and_test(&cgrp->count) &&
 		    notify_on_release(cgrp)) {
 			if (taskexit)
 				set_bit(CGRP_RELEASABLE, &cgrp->flags);
 			check_for_release(cgrp);
 		}
+
+		kfree(link);
 	}
-	rcu_read_unlock();
-	kfree(cg);
+
+	write_unlock(&css_set_lock);
+	call_rcu(&cg->rcu_head, free_css_set_rcu);
 }
 
 /*
@@ -338,6 +338,78 @@ static inline void put_css_set_taskexit(struct css_set *cg)
 }
 
 /*
+ * compare_css_sets - helper function for find_existing_css_set().
+ * @cg: candidate css_set being tested
+ * @old_cg: existing css_set for a task
+ * @new_cgrp: cgroup that's being entered by the task
+ * @template: desired set of css pointers in css_set (pre-calculated)
+ *
+ * Returns true if "cg" matches "old_cg" except for the hierarchy
+ * which "new_cgrp" belongs to, for which it should match "new_cgrp".
+ */
+static bool compare_css_sets(struct css_set *cg,
+			     struct css_set *old_cg,
+			     struct cgroup *new_cgrp,
+			     struct cgroup_subsys_state *template[])
+{
+	struct list_head *l1, *l2;
+
+	if (memcmp(template, cg->subsys, sizeof(cg->subsys))) {
+		/* Not all subsystems matched */
+		return false;
+	}
+
+	/*
+	 * Compare cgroup pointers in order to distinguish between
+	 * different cgroups in heirarchies with no subsystems. We
+	 * could get by with just this check alone (and skip the
+	 * memcmp above) but on most setups the memcmp check will
+	 * avoid the need for this more expensive check on almost all
+	 * candidates.
+	 */
+
+	l1 = &cg->cg_links;
+	l2 = &old_cg->cg_links;
+	while (1) {
+		struct cg_cgroup_link *cgl1, *cgl2;
+		struct cgroup *cg1, *cg2;
+
+		l1 = l1->next;
+		l2 = l2->next;
+		/* See if we reached the end - both lists are equal length. */
+		if (l1 == &cg->cg_links) {
+			BUG_ON(l2 != &old_cg->cg_links);
+			break;
+		} else {
+			BUG_ON(l2 == &old_cg->cg_links);
+		}
+		/* Locate the cgroups associated with these links. */
+		cgl1 = list_entry(l1, struct cg_cgroup_link, cg_link_list);
+		cgl2 = list_entry(l2, struct cg_cgroup_link, cg_link_list);
+		cg1 = cgl1->cgrp;
+		cg2 = cgl2->cgrp;
+		/* Hierarchies should be linked in the same order. */
+		BUG_ON(cg1->root != cg2->root);
+
+		/*
+		 * If this hierarchy is the hierarchy of the cgroup
+		 * that's changing, then we need to check that this
+		 * css_set points to the new cgroup; if it's any other
+		 * hierarchy, then this css_set should point to the
+		 * same cgroup as the old css_set.
+		 */
+		if (cg1->root == new_cgrp->root) {
+			if (cg1 != new_cgrp)
+				return false;
+		} else {
+			if (cg1 != cg2)
+				return false;
+		}
+	}
+	return true;
+}
+
+/*
  * find_existing_css_set() is a helper for
  * find_css_set(), and checks to see whether an existing
  * css_set is suitable.
@@ -378,10 +450,11 @@ static struct css_set *find_existing_css_set(
 
 	hhead = css_set_hash(template);
 	hlist_for_each_entry(cg, node, hhead, hlist) {