57 files changed, 3224 insertions, 2222 deletions
diff --git a/kernel/Makefile b/kernel/Makefile
index 7c9b0a585502..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
@@ -95,7 +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);
+                len = 0;
-                if (err)
+                if (audit_sig_sid) {
-                        return err;
+                        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);
+                if (audit_sig_sid) {
-                security_release_secctx(ctx, len);
+                        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..7ccba4bc5e3b 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
+static void __put_css_set(struct css_set *cg, int taskexit)
- * 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)
 {
        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();
+        /* This css_set is dead. unlink it and release cgroup refcounts */
-        for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
+        hlist_del(&cg->hlist);
-                struct cgroup *cgrp = rcu_dereference(cg->subsys[i]->cgroup);
+        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) {
-                if (!memcmp(template, cg->subsys, sizeof(cg->subsys))) {
+                if (!compare_css_sets(cg, oldcg, cgrp, template))
-                        /* All subsystems matched */
+                        continue;
-                        return cg;
-                }
+                /* This css_set matches what we need */
+                return cg;
        }
        /* No existing cgroup group matched */
@@ -435,8 +508,14 @@ static void link_css_set(struct list_head *tmp_cg_links,
        link = list_first_entry(tmp_cg_links, struct cg_cgroup_link,
                                cgrp_link_list);
        link->cg = cg;
+        link->cgrp = cgrp;
+        atomic_inc(&cgrp->count);
        list_move(&link->cgrp_link_list, &cgrp->css_sets);
-        list_add(&link->cg_link_list, &cg->cg_links);
+        /*
+         * Always add links to the tail of the list so that the list
+         * is sorted by order of hierarchy creation
+         */
+        list_add_tail(&link->cg_link_list, &cg->cg_links);
 }
 /*
@@ -451,11 +530,11 @@ static struct css_set *find_css_set(
 {
        struct css_set *res;
        struct cgroup_subsys_state *template[CGROUP_SUBSYS_COUNT];
-        int i;
        struct list_head tmp_cg_links;
        struct hlist_head *hhead;
+        struct cg_cgroup_link *link;
        /* First see if we already have a cgroup group that matches
         * the desired set */
@@ -489,20 +568,12 @@ static struct css_set *find_css_set(
        write_lock(&css_set_lock);
        /* Add reference counts and links from the new css_set. */
-        for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
+        list_for_each_entry(link, &oldcg->cg_links, cg_link_list) {
-                struct cgroup *cgrp = res->subsys[i]->cgroup;
+                struct cgroup *c = link->cgrp;
-                struct cgroup_subsys *ss = subsys[i];
+                if (c->root == cgrp->root)
-                atomic_inc(&cgrp->count);
+                        c = cgrp;
-                /*
+                link_css_set(&tmp_cg_links, res, c);
-                 * We want to add a link once per cgroup, so we
-                 * only do it for the first subsystem in each
-                 * hierarchy
-                 */
-                if (ss->root->subsys_list.next == &ss->sibling)
-                        link_css_set(&tmp_cg_links, res, cgrp);
        }
-        if (list_empty(&rootnode.subsys_list))
-                link_css_set(&tmp_cg_links, res, dummytop);
        BUG_ON(!list_empty(&tmp_cg_links));
@@ -518,6 +589,41 @@ static struct css_set *find_css_set(
 }
 /*
+ * Return the cgroup for "task" from the given hierarchy. Must be
+ * called with cgroup_mutex held.
+ */
+static struct cgroup *task_cgroup_from_root(struct task_struct *task,
+                                            struct cgroupfs_root *root)
+{
+        struct css_set *css;
+        struct cgroup *res = NULL;
+        BUG_ON(!mutex_is_locked(&cgroup_mutex));
+        read_lock(&css_set_lock);
+        /*
+         * No need to lock the task - since we hold cgroup_mutex the
+         * task can't change groups, so the only thing that can happen
+         * is that it exits and its css is set back to init_css_set.
+         */
+        css = task->cgroups;
+        if (css == &init_css_set) {
+                res = &root->top_cgroup;
+        } else {
+                struct cg_cgroup_link *link;
+                list_for_each_entry(link, &css->cg_links, cg_link_list) {
+                        struct cgroup *c = link->cgrp;
+                        if (c->root == root) {
+                                res = c;
+                                break;
+                        }
+                }
+        }
+        read_unlock(&css_set_lock);
+        BUG_ON(!res);
+        return res;
+}
+/*
 * There is one global cgroup mutex. We also require taking
 * task_lock() when dereferencing a task's cgroup subsys pointers.
 * See "The task_lock() exception", at the end of this comment.
@@ -596,7 +702,7 @@ void cgroup_unlock(void)
 static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, int mode);
 static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry);
 static int cgroup_populate_dir(struct cgroup *cgrp);
-static struct inode_operations cgroup_dir_inode_operations;
+static const struct inode_operations cgroup_dir_inode_operations;
 static struct file_operations proc_cgroupstats_operations;
 static struct backing_dev_info cgroup_backing_dev_info = {
@@ -677,6 +783,12 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode)
                 */
                deactivate_super(cgrp->root->sb);
+                /*
+                 * if we're getting rid of the cgroup, refcount should ensure
+                 * that there are no pidlists left.
+                 */
+                BUG_ON(!list_empty(&cgrp->pidlists));
                call_rcu(&cgrp->rcu_head, free_cgroup_rcu);
        }
        iput(inode);
@@ -841,6 +953,8 @@ static int cgroup_show_options(struct seq_file *seq, struct vfsmount *vfs)
                seq_puts(seq, ",noprefix");
        if (strlen(root->release_agent_path))
                seq_printf(seq, ",release_agent=%s", root->release_agent_path);
+        if (strlen(root->name))
+                seq_printf(seq, ",name=%s", root->name);
        mutex_unlock(&cgroup_mutex);
        return 0;
 }
@@ -849,6 +963,12 @@ struct cgroup_sb_opts {
        unsigned long subsys_bits;
        unsigned long flags;
        char *release_agent;
+        char *name;
+        /* User explicitly requested empty subsystem */
+        bool none;
+        struct cgroupfs_root *new_root;
 };
 /* Convert a hierarchy specifier into a bitmask of subsystems and
@@ -863,9 +983,7 @@ static int parse_cgroupfs_options(char *data,
        mask = ~(1UL << cpuset_subsys_id);
 #endif
-        opts->subsys_bits = 0;
+        memset(opts, 0, sizeof(*opts));
-        opts->flags = 0;
-        opts->release_agent = NULL;
        while ((token = strsep(&o, ",")) != NULL) {
                if (!*token)
@@ -879,17 +997,42 @@ static int parse_cgroupfs_options(char *data,
                                if (!ss->disabled)
                                        opts->subsys_bits |= 1ul << i;
                        }
+                } else if (!strcmp(token, "none")) {
+                        /* Explicitly have no subsystems */
+                        opts->none = true;
                } else if (!strcmp(token, "noprefix")) {
                        set_bit(ROOT_NOPREFIX, &opts->flags);
                } else if (!strncmp(token, "release_agent=", 14)) {
                        /* Specifying two release agents is forbidden */
                        if (opts->release_agent)
                                return -EINVAL;
-                        opts->release_agent = kzalloc(PATH_MAX, GFP_KERNEL);
+                        opts->release_agent =
+                                kstrndup(token + 14, PATH_MAX, GFP_KERNEL);
                        if (!opts->release_agent)
                                return -ENOMEM;
-                        strncpy(opts->release_agent, token + 14, PATH_MAX - 1);
+                } else if (!strncmp(token, "name=", 5)) {
-                        opts->release_agent[PATH_MAX - 1] = 0;
+                        int i;
+                        const char *name = token + 5;
+                        /* Can't specify an empty name */
+                        if (!strlen(name))
+                                return -EINVAL;
+                        /* Must match [\w.-]+ */
+                        for (i = 0; i < strlen(name); i++) {
+                                char c = name[i];
+                                if (isalnum(c))
+                                        continue;
+                                if ((c == '.') || (c == '-') || (c == '_'))
+                                        continue;
+                                return -EINVAL;
+                        }
+                        /* Specifying two names is forbidden */
+                        if (opts->name)
+                                return -EINVAL;
+                        opts->name = kstrndup(name,
+                                              MAX_CGROUP_ROOT_NAMELEN,
+                                              GFP_KERNEL);
+                        if (!opts->name)
+                                return -ENOMEM;
                } else {
                        struct cgroup_subsys *ss;
                        int i;
@@ -906,6 +1049,8 @@ static int parse_cgroupfs_options(char *data,
                }
        }
+        /* Consistency checks */
        /*
         * Option noprefix was introduced just for backward compatibility
         * with the old cpuset, so we allow noprefix only if mounting just
@@ -915,8 +1060,16 @@ static int parse_cgroupfs_options(char *data,
            (opts->subsys_bits & mask))
                return -EINVAL;
-        /* We can't have an empty hierarchy */
-        if (!opts->subsys_bits)
+        /* Can't specify "none" and some subsystems */
+        if (opts->subsys_bits && opts->none)
+                return -EINVAL;
+        /*
+         * We either have to specify by name or by subsystems. (So all
+         * empty hierarchies must have a name).
+         */
+        if (!opts->subsys_bits && !opts->name)
                return -EINVAL;
        return 0;
@@ -944,6 +1097,12 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data)
                goto out_unlock;
        }
+        /* Don't allow name to change at remount */
+        if (opts.name && strcmp(opts.name, root->name)) {
+                ret = -EINVAL;
+                goto out_unlock;
+        }
        ret = rebind_subsystems(root, opts.subsys_bits);
        if (ret)
                goto out_unlock;
@@ -955,13 +1114,14 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data)
                strcpy(root->release_agent_path, opts.release_agent);
 out_unlock:
        kfree(opts.release_agent);
+        kfree(opts.name);
        mutex_unlock(&cgroup_mutex);
        mutex_unlock(&cgrp->dentry->d_inode->i_mutex);
        unlock_kernel();
        return ret;
 }
-static struct super_operations cgroup_ops = {
+static const struct super_operations cgroup_ops = {
        .statfs = simple_statfs,
        .drop_inode = generic_delete_inode,
        .show_options = cgroup_show_options,
@@ -974,9 +1134,10 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp)
        INIT_LIST_HEAD(&cgrp->children);
        INIT_LIST_HEAD(&cgrp->css_sets);
        INIT_LIST_HEAD(&cgrp->release_list);
-        INIT_LIST_HEAD(&cgrp->pids_list);
+        INIT_LIST_HEAD(&cgrp->pidlists);
-        init_rwsem(&cgrp->pids_mutex);
+        mutex_init(&cgrp->pidlist_mutex);
 }
 static void init_cgroup_root(struct cgroupfs_root *root)
 {
        struct cgroup *cgrp = &root->top_cgroup;
@@ -988,33 +1149,106 @@ static void init_cgroup_root(struct cgroupfs_root *root)
        init_cgroup_housekeeping(cgrp);
 }
+static bool init_root_id(struct cgroupfs_root *root)
+{
+        int ret = 0;
+        do {
+                if (!ida_pre_get(&hierarchy_ida, GFP_KERNEL))
+                        return false;
+                spin_lock(&hierarchy_id_lock);
+                /* Try to allocate the next unused ID */
+                ret = ida_get_new_above(&hierarchy_ida, next_hierarchy_id,
+                                        &root->hierarchy_id);
+                if (ret == -ENOSPC)
+                        /* Try again starting from 0 */
+                        ret = ida_get_new(&hierarchy_ida, &root->hierarchy_id);
+                if (!ret) {
+                        next_hierarchy_id = root->hierarchy_id + 1;
+                } else if (ret != -EAGAIN) {
+                        /* Can only get here if the 31-bit IDR is full ... */
+                        BUG_ON(ret);
+                }
+                spin_unlock(&hierarchy_id_lock);
+        } while (ret);
+        return true;
+}
 static int cgroup_test_super(struct super_block *sb, void *data)
 {
-        struct cgroupfs_root *new = data;
+        struct cgroup_sb_opts *opts = data;
        struct cgroupfs_root *root = sb->s_fs_info;
-        /* First check subsystems */
+        /* If we asked for a name then it must match */
-        if (new->subsys_bits != root->subsys_bits)
+        if (opts->name && strcmp(opts->name, root->name))
-            return 0;
+                return 0;
-        /* Next check flags */
+        /*
-        if (new->flags != root->flags)
+         * If we asked for subsystems (or explicitly for no
+         * subsystems) then they must match
+         */
+        if ((opts->subsys_bits || opts->none)
+            && (opts->subsys_bits != root->subsys_bits))
                return 0;
        return 1;
 }
+static struct cgroupfs_root *cgroup_root_from_opts(struct cgroup_sb_opts *opts)
+{
+        struct cgroupfs_root *root;
+        if (!opts->subsys_bits && !opts->none)
+                return NULL;
+        root = kzalloc(sizeof(*root), GFP_KERNEL);
+        if (!root)
+                return ERR_PTR(-ENOMEM);
+        if (!init_root_id(root)) {
+                kfree(root);
+                return ERR_PTR(-ENOMEM);
+        }
+        init_cgroup_root(root);
+        root->subsys_bits = opts->subsys_bits;
+        root->flags = opts->flags;
+        if (opts->release_agent)
+                strcpy(root->release_agent_path, opts->release_agent);
+        if (opts->name)
+                strcpy(root->name, opts->name);
+        return root;
+}
+static void cgroup_drop_root(struct cgroupfs_root *root)
+{
+        if (!root)
+                return;
+        BUG_ON(!root->hierarchy_id);
+        spin_lock(&hierarchy_id_lock);
+        ida_remove(&hierarchy_ida, root->hierarchy_id);
+        spin_unlock(&hierarchy_id_lock);
+        kfree(root);
+}
 static int cgroup_set_super(struct super_block *sb, void *data)
 {
        int ret;
-        struct cgroupfs_root *root = data;
+        struct cgroup_sb_opts *opts = data;
+        /* If we don't have a new root, we can't set up a new sb */
+        if (!opts->new_root)
+                return -EINVAL;
+        BUG_ON(!opts->subsys_bits && !opts->none);
        ret = set_anon_super(sb, NULL);
        if (ret)
                return ret;
-        sb->s_fs_info = root;
+        sb->s_fs_info = opts->new_root;
-        root->sb = sb;
+        opts->new_root->sb = sb;
        sb->s_blocksize = PAGE_CACHE_SIZE;
        sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
@@ -1051,48 +1285,43 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
                         void *data, struct vfsmount *mnt)
 {
        struct cgroup_sb_opts opts;
+        struct cgroupfs_root *root;
        int ret = 0;
        struct super_block *sb;
-        struct cgroupfs_root *root;
+        struct cgroupfs_root *new_root;
-        struct list_head tmp_cg_links;
        /* First find the desired set of subsystems */
        ret = parse_cgroupfs_options(data, &opts);
-        if (ret) {
+        if (ret)
-                kfree(opts.release_agent);
+                goto out_err;
-                return ret;
-        }
-        root = kzalloc(sizeof(*root), GFP_KERNEL);
-        if (!root) {
-                kfree(opts.release_agent);
-                return -ENOMEM;
-        }
-        init_cgroup_root(root);
+        /*
-        root->subsys_bits = opts.subsys_bits;
+         * Allocate a new cgroup root. We may not need it if we're
-        root->flags = opts.flags;
+         * reusing an existing hierarchy.
-        if (opts.release_agent) {
+         */
-                strcpy(root->release_agent_path, opts.release_agent);
+        new_root = cgroup_root_from_opts(&opts);
-                kfree(opts.release_agent);
+        if (IS_ERR(new_root)) {
+                ret = PTR_ERR(new_root);
+                goto out_err;
        }
+        opts.new_root = new_root;
-        sb = sget(fs_type, cgroup_test_super, cgroup_set_super, root);
+        /* Locate an existing or new sb for this hierarchy */
+        sb = sget(fs_type, cgroup_test_super, cgroup_set_super, &opts);
        if (IS_ERR(sb)) {
-                kfree(root);
+                ret = PTR_ERR(sb);
-                return PTR_ERR(sb);
+                cgroup_drop_root(opts.new_root);
+                goto out_err;
        }
-        if (sb->s_fs_info != root) {
+        root = sb->s_fs_info;
-                /* Reusing an existing superblock */
+        BUG_ON(!root);
-                BUG_ON(sb->s_root == NULL);
+        if (root == opts.new_root) {
-                kfree(root);
+                /* We used the new root structure, so this is a new hierarchy */
-                root = NULL;
+                struct list_head tmp_cg_links;
-        } else {
-                /* New superblock */
                struct cgroup *root_cgrp = &root->top_cgroup;
                struct inode *inode;
+                struct cgroupfs_root *existing_root;
                int i;
                BUG_ON(sb->s_root != NULL);
@@ -1105,6 +1334,18 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
                mutex_lock(&inode->i_mutex);
                mutex_lock(&cgroup_mutex);
+                if (strlen(root->name)) {
+                        /* Check for name clashes with existing mounts */
+                        for_each_active_root(existing_root) {
+                                if (!strcmp(existing_root->name, root->name)) {
+                                        ret = -EBUSY;
+                                        mutex_unlock(&cgroup_mutex);
+                                        mutex_unlock(&inode->i_mutex);
+                                        goto drop_new_super;
+                                }
+                        }
+                }
                /*
                 * We're accessing css_set_count without locking
                 * css_set_lock here, but that's OK - it can only be
@@ -1123,7 +1364,8 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
                if (ret == -EBUSY) {
                        mutex_unlock(&cgroup_mutex);
                        mutex_unlock(&inode->i_mutex);
-                        goto free_cg_links;
+                        free_cg_links(&tmp_cg_links);
+                        goto drop_new_super;
                }
                /* EBUSY should be the only error here */
@@ -1155,17 +1397,27 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
                BUG_ON(root->number_of_cgroups != 1);
                cgroup_populate_dir(root_cgrp);
-                mutex_unlock(&inode->i_mutex);
                mutex_unlock(&cgroup_mutex);
+                mutex_unlock(&inode->i_mutex);
+        } else {
+                /*
+                 * We re-used an existing hierarchy - the new root (if
+                 * any) is not needed
+                 */
+                cgroup_drop_root(opts.new_root);
        }
        simple_set_mnt(mnt, sb);
+        kfree(opts.release_agent);
+        kfree(opts.name);
        return 0;
- free_cg_links:
-        free_cg_links(&tmp_cg_links);
 drop_new_super:
        deactivate_locked_super(sb);
+ out_err:
+        kfree(opts.release_agent);
+        kfree(opts.name);
        return ret;
 }
@@ -1211,7 +1463,7 @@ static void cgroup_kill_sb(struct super_block *sb) {
        mutex_unlock(&cgroup_mutex);
        kill_litter_super(sb);
-        kfree(root);
+        cgroup_drop_root(root);
 }
 static struct file_system_type cgroup_fs_type = {
@@ -1276,27 +1528,6 @@ int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen)
        return 0;
 }
-/*
- * Return the first subsystem attached to a cgroup's hierarchy, and
- * its subsystem id.
- */
-static void get_first_subsys(const struct cgroup *cgrp,
-                        struct cgroup_subsys_state **css, int *subsys_id)
-{
-        const struct cgroupfs_root *root = cgrp->root;
-        const struct cgroup_subsys *test_ss;
-        BUG_ON(list_empty(&root->subsys_list));
-        test_ss = list_entry(root->subsys_list.next,
-                             struct cgroup_subsys, sibling);
-        if (css) {
-                *css = cgrp->subsys[test_ss->subsys_id];
-                BUG_ON(!*css);
-        }
-        if (subsys_id)
-                *subsys_id = test_ss->subsys_id;
-}
 /**
 * cgroup_attach_task - attach task 'tsk' to cgroup 'cgrp'
 * @cgrp: the cgroup the task is attaching to
@@ -1313,18 +1544,15 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
        struct css_set *cg;
        struct css_set *newcg;
        struct cgroupfs_root *root = cgrp->root;
-        int subsys_id;
-        get_first_subsys(cgrp, NULL, &subsys_id);
        /* Nothing to do if the task is already in that cgroup */
-        oldcgrp = task_cgroup(tsk, subsys_id);
+        oldcgrp = task_cgroup_from_root(tsk, root);
        if (cgrp == oldcgrp)
                return 0;
        for_each_subsys(root, ss) {
                if (ss->can_attach) {
-                        retval = ss->can_attach(ss, cgrp, tsk);
+                        retval = ss->can_attach(ss, cgrp, tsk, false);
                        if (retval)
                                return retval;
                }
@@ -1362,7 +1590,7 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
        for_each_subsys(root, ss) {
                if (ss->attach)
-                        ss->attach(ss, cgrp, oldcgrp, tsk);
+                        ss->attach(ss, cgrp, oldcgrp, tsk, false);
        }
        set_bit(CGRP_RELEASABLE, &oldcgrp->flags);
        synchronize_rcu();
@@ -1423,15 +1651,6 @@ static int cgroup_tasks_write(struct cgroup *cgrp, struct cftype *cft, u64 pid)
        return ret;
 }
-/* The various types of files and directories in a cgroup file system */
-enum cgroup_filetype {
-        FILE_ROOT,
-        FILE_DIR,
-        FILE_TASKLIST,
-        FILE_NOTIFY_ON_RELEASE,
-        FILE_RELEASE_AGENT,
-};
 /**
 * cgroup_lock_live_group - take cgroup_mutex and check that cgrp is alive.
 * @cgrp: the cgroup to be checked for liveness
@@ -1711,7 +1930,7 @@ static struct file_operations cgroup_file_operations = {
        .release = cgroup_file_release,
 };
-static struct inode_operations cgroup_dir_inode_operations = {
+static const struct inode_operations cgroup_dir_inode_operations = {
        .lookup = simple_lookup,
        .mkdir = cgroup_mkdir,
        .rmdir = cgroup_rmdir,
@@ -1876,7 +2095,7 @@ int cgroup_task_count(const struct cgroup *cgrp)
 * the start of a css_set
 */
 static void cgroup_advance_iter(struct cgroup *cgrp,
-                                          struct cgroup_iter *it)
+                                struct cgroup_iter *it)
 {
        struct list_head *l = it->cg_link;
        struct cg_cgroup_link *link;
@@ -2129,7 +2348,7 @@ int cgroup_scan_tasks(struct cgroup_scanner *scan)
 }
 /*
- * Stuff for reading the 'tasks' file.
+ * Stuff for reading the 'tasks'/'procs' files.
 *
 * Reading this file can return large amounts of data if a cgroup has
 * *lots* of attached tasks. So it may need several calls to read(),
@@ -2139,27 +2358,196 @@ int cgroup_scan_tasks(struct cgroup_scanner *scan)
 */
 /*
- * Load into 'pidarray' up to 'npids' of the tasks using cgroup
+ * The following two functions "fix" the issue where there are more pids
- * 'cgrp'.  Return actual number of pids loaded.  No need to
+ * than kmalloc will give memory for; in such cases, we use vmalloc/vfree.
- * task_lock(p) when reading out p->cgroup, since we're in an RCU
+ * TODO: replace with a kernel-wide solution to this problem
- * read section, so the css_set can't go away, and is
+ */
- * immutable after creation.
+#define PIDLIST_TOO_LARGE(c) ((c) * sizeof(pid_t) > (PAGE_SIZE * 2))
+static void *pidlist_allocate(int count)
+{
+        if (PIDLIST_TOO_LARGE(count))
+                return vmalloc(count * sizeof(pid_t));
+        else
+                return kmalloc(count * sizeof(pid_t), GFP_KERNEL);
+}
+static void pidlist_free(void *p)
+{
+        if (is_vmalloc_addr(p))
+                vfree(p);
+        else
+                kfree(p);
+}
+static void *pidlist_resize(void *p, int newcount)
+{
+        void *newlist;
+        /* note: if new alloc fails, old p will still be valid either way */
+        if (is_vmalloc_addr(p)) {
+                newlist = vmalloc(newcount * sizeof(pid_t));
+                if (!newlist)
+                        return NULL;
+                memcpy(newlist, p, newcount * sizeof(pid_t));
+                vfree(p);
+        } else {
+                newlist = krealloc(p, newcount * sizeof(pid_t), GFP_KERNEL);
+        }
+        return newlist;
+}
+/*
+ * pidlist_uniq - given a kmalloc()ed list, strip out all duplicate entries
+ * If the new stripped list is sufficiently smaller and there's enough memory
+ * to allocate a new buffer, will let go of the unneeded memory. Returns the
+ * number of unique elements.
+ */
+/* is the size difference enough that we should re-allocate the array? */
+#define PIDLIST_REALLOC_DIFFERENCE(old, new) ((old) - PAGE_SIZE >= (new))
+static int pidlist_uniq(pid_t **p, int length)
+{
+        int src, dest = 1;
+        pid_t *list = *p;
+        pid_t *newlist;
+        /*
+         * we presume the 0th element is unique, so i starts at 1. trivial
+         * edge cases first; no work needs to be done for either
+         */
+        if (length == 0 || length == 1)
+                return length;
+        /* src and dest walk down the list; dest counts unique elements */
+        for (src = 1; src < length; src++) {
+                /* find next unique element */
+                while (list[src] == list[src-1]) {
+                        src++;
+                        if (src == length)
+                                goto after;
+                }
+                /* dest always points to where the next unique element goes */
+                list[dest] = list[src];
+                dest++;
+        }
+after:
+        /*
+         * if the length difference is large enough, we want to allocate a
+         * smaller buffer to save memory. if this fails due to out of memory,
+         * we'll just stay with what we've got.
+         */
+        if (PIDLIST_REALLOC_DIFFERENCE(length, dest)) {
+                newlist = pidlist_resize(list, dest);
+                if (newlist)
+                        *p = newlist;
+        }
+        return dest;
+}
+static int cmppid(const void *a, const void *b)
+{
+        return *(pid_t *)a - *(pid_t *)b;
+}
+/*
+ * find the appropriate pidlist for our purpose (given procs vs tasks)
+ * returns with the lock on that pidlist already held, and takes care
+ * of the use count, or returns NULL with no locks held if we're out of
+ * memory.
 */
-static int pid_array_load(pid_t *pidarray, int npids, struct cgroup *cgrp)
+static struct cgroup_pidlist *cgroup_pidlist_find(struct cgroup *cgrp,
+                                                  enum cgroup_filetype type)
 {
-        int n = 0, pid;
+        struct cgroup_pidlist *l;
+        /* don't need task_nsproxy() if we're looking at ourself */
+        struct pid_namespace *ns = get_pid_ns(current->nsproxy->pid_ns);
+        /*
+         * We can't drop the pidlist_mutex before taking the l->mutex in case
+         * the last ref-holder is trying to remove l from the list at the same
+         * time. Holding the pidlist_mutex precludes somebody taking whichever
+         * list we find out from under us - compare release_pid_array().
+         */
+        mutex_lock(&cgrp->pidlist_mutex);
+        list_for_each_entry(l, &cgrp->pidlists, links) {
+                if (l->key.type == type && l->key.ns == ns) {
+                        /* found a matching list - drop the extra refcount */
+                        put_pid_ns(ns);
+                        /* make sure l doesn't vanish out from under us */
+                        down_write(&l->mutex);
+                        mutex_unlock(&cgrp->pidlist_mutex);
+                        l->use_count++;
+                        return l;
+                }
+        }
+        /* entry not found; create a new one */
+        l = kmalloc(sizeof(struct cgroup_pidlist), GFP_KERNEL);
+        if (!l) {
+                mutex_unlock(&cgrp->pidlist_mutex);
+                put_pid_ns(ns);
+                return l;
+        }
+        init_rwsem(&l->mutex);
+        down_write(&l->mutex);
+        l->key.type = type;
+        l->key.ns = ns;
+        l->use_count = 0; /* don't increment here */
+        l->list = NULL;
+        l->owner = cgrp;
+        list_add(&l->links, &cgrp->pidlists);
+        mutex_unlock(&cgrp->pidlist_mutex);
+        return l;
+}
+/*
+ * Load a cgroup's pidarray with either procs' tgids or tasks' pids
+ */
+static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type,
+                              struct cgroup_pidlist **lp)
+{
+        pid_t *array;
+        int length;
+        int pid, n = 0; /* used for populating the array */
        struct cgroup_iter it;
        struct task_struct *tsk;
+        struct cgroup_pidlist *l;
+        /*
+         * If cgroup gets more users after we read count, we won't have
+         * enough space - tough.  This race is indistinguishable to the
+         * caller from the case that the additional cgroup users didn't
+         * show up until sometime later on.
+         */
+        length = cgroup_task_count(cgrp);
+        array = pidlist_allocate(length);
+        if (!array)
+                return -ENOMEM;
+        /* now, populate the array */
        cgroup_iter_start(cgrp, &it);
        while ((tsk = cgroup_iter_next(cgrp, &it))) {
-                if (unlikely(n == npids))
+                if (unlikely(n == length))
                        break;
-                pid = task_pid_vnr(tsk);
+                /* get tgid or pid for procs or tasks file respectively */
-                if (pid > 0)
+                if (type == CGROUP_FILE_PROCS)
-                        pidarray[n++] = pid;
+                        pid = task_tgid_vnr(tsk);
+                else
+                        pid = task_pid_vnr(tsk);
+                if (pid > 0) /* make sure to only use valid results */
+                        array[n++] = pid;
        }
        cgroup_iter_end(cgrp, &it);
-        return n;
+        length = n;
+        /* now sort & (if procs) strip out duplicates */
+        sort(array, length, sizeof(pid_t), cmppid, NULL);
+        if (type == CGROUP_FILE_PROCS)
+                length = pidlist_uniq(&array, length);
+        l = cgroup_pidlist_find(cgrp, type);
+        if (!l) {
+                pidlist_free(array);
+                return -ENOMEM;
+        }
+        /* store array, freeing old if necessary - lock already held */
+        pidlist_free(l->list);
+        l->list = array;
+        l->length = length;
+        l->use_count++;
+        up_write(&l->mutex);
+        *lp = l;
+        return 0;
 }
 /**
@@ -2216,37 +2604,14 @@ err:
        return ret;
 }
-/*
- * Cache pids for all threads in the same pid namespace that are
- * opening the same "tasks" file.
- */
-struct cgroup_pids {
-        /* The node in cgrp->pids_list */
-        struct list_head list;
-        /* The cgroup those pids belong to */
-        struct cgroup *cgrp;
-        /* The namepsace those pids belong to */
-        struct pid_namespace *ns;
-        /* Array of process ids in the cgroup */
-        pid_t *tasks_pids;
-        /* How many files are using the this tasks_pids array */
-        int use_count;
-        /* Length of the current tasks_pids array */
-        int length;
-};
-static int cmppid(const void *a, const void *b)
-{
-        return *(pid_t *)a - *(pid_t *)b;
-}
 /*
- * seq_file methods for the "tasks" file. The seq_file position is the
+ * seq_file methods for the tasks/procs files. The seq_file position is the
 * next pid to display; the seq_file iterator is a pointer to the pid
- * in the cgroup->tasks_pids array.
+ * in the cgroup->l->list array.
 */
-static void *cgroup_tasks_start(struct seq_file *s, loff_t *pos)
+static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos)
 {
        /*
         * Initially we receive a position value that corresponds to
@@ -2254,48 +2619,45 @@ static void *cgroup_tasks_start(struct seq_file *s, loff_t *pos)
         * after a seek to the start). Use a binary-search to find the
         * next pid to display, if any
         */
-        struct cgroup_pids *cp = s->private;
+        struct cgroup_pidlist *l = s->private;
-        struct cgroup *cgrp = cp->cgrp;
        int index = 0, pid = *pos;
        int *iter;
-        down_read(&cgrp->pids_mutex);
+        down_read(&l->mutex);
        if (pid) {
-                int end = cp->length;
+                int end = l->length;
                while (index < end) {
                        int mid = (index + end) / 2;
-                        if (cp->tasks_pids[mid] == pid) {
+                        if (l->list[mid] == pid) {
                                index = mid;
                                break;
-                        } else if (cp->tasks_pids[mid] <= pid)
+                        } else if (l->list[mid] <= pid)
                                index = mid + 1;
                        else
                                end = mid;
                }
        }
        /* If we're off the end of the array, we're done */
-        if (index >= cp->length)
+        if (index >= l->length)
                return NULL;
        /* Update the abstract position to be the actual pid that we found */
-        iter = cp->tasks_pids + index;
+        iter = l->list + index;
        *pos = *iter;
        return iter;
 }
-static void cgroup_tasks_stop(struct seq_file *s, void *v)
+static void cgroup_pidlist_stop(struct seq_file *s, void *v)
 {
-        struct cgroup_pids *cp = s->private;
+        struct cgroup_pidlist *l = s->private;
-        struct cgroup *cgrp = cp->cgrp;
+        up_read(&l->mutex);
-        up_read(&cgrp->pids_mutex);
 }
-static void *cgroup_tasks_next(struct seq_file *s, void *v, loff_t *pos)
+static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos)
 {
-        struct cgroup_pids *cp = s->private;
+        struct cgroup_pidlist *l = s->private;
-        int *p = v;
+        pid_t *p = v;
-        int *end = cp->tasks_pids + cp->length;
+        pid_t *end = l->list + l->length;
        /*
         * Advance to the next pid in the array. If this goes off the
         * end, we're done
@@ -2309,124 +2671,107 @@ static void *cgroup_tasks_next(struct seq_file *s, void *v, loff_t *pos)
        }
 }
-static int cgroup_tasks_show(struct seq_file *s, void *v)
+static int cgroup_pidlist_show(struct seq_file *s, void *v)
 {
        return seq_printf(s, "%d\n", *(int *)v);
 }
-static struct seq_operations cgroup_tasks_seq_operations = {
+/*
-        .start = cgroup_tasks_start,
+ * seq_operations functions for iterating on pidlists through seq_file -
-        .stop = cgroup_tasks_stop,
+ * independent of whether it's tasks or procs
-        .next = cgroup_tasks_next,
+ */
-        .show = cgroup_tasks_show,
+static const struct seq_operations cgroup_pidlist_seq_operations = {
+        .start = cgroup_pidlist_start,
+        .stop = cgroup_pidlist_stop,
+        .next = cgroup_pidlist_next,
+        .show = cgroup_pidlist_show,
 };
-static void release_cgroup_pid_array(struct cgroup_pids *cp)
+static void cgroup_release_pid_array(struct cgroup_pidlist *l)
 {
-        struct cgroup *cgrp = cp->cgrp;
+        /*
+         * the case where we're the last user of this particular pidlist will
-        down_write(&cgrp->pids_mutex);
+         * have us remove it from the cgroup's list, which entails taking the
-        BUG_ON(!cp->use_count);
+         * mutex. since in pidlist_find the pidlist->lock depends on cgroup->
-        if (!--cp->use_count) {
+         * pidlist_mutex, we have to take pidlist_mutex first.
-                list_del(&cp->list);
+         */
-                put_pid_ns(cp->ns);
+        mutex_lock(&l->owner->pidlist_mutex);
-                kfree(cp->tasks_pids);
+        down_write(&l->mutex);
-                kfree(cp);
+        BUG_ON(!l->use_count);
+        if (!--l->use_count) {
+                /* we're the last user if refcount is 0; remove and free */
+                list_del(&l->links);
+                mutex_unlock(&l->owner->pidlist_mutex);
+                pidlist_free(l->list);
+                put_pid_ns(l->key.ns);
+                up_write(&l->mutex);
+                kfree(l);
+                return;
        }
-        up_write(&cgrp->pids_mutex);
+        mutex_unlock(&l->owner->pidlist_mutex);
+        up_write(&l->mutex);
 }
-static int cgroup_tasks_release(struct inode *inode, struct file *file)
+static int cgroup_pidlist_release(struct inode *inode, struct file *file)
 {
-        struct seq_file *seq;
+        struct cgroup_pidlist *l;
-        struct cgroup_pids *cp;
        if (!(file->f_mode & FMODE_READ))
                return 0;
+        /*
-        seq = file->private_data;
+         * the seq_file will only be initialized if the file was opened for
-        cp = seq->private;
+         * reading; hence we check if it's not null only in that case.
+         */
-        release_cgroup_pid_array(cp);
+        l = ((struct seq_file *)file->private_data)->private;
+        cgroup_release_pid_array(l);
        return seq_release(inode, file);
 }
-static struct file_operations cgroup_tasks_operations = {
+static const struct file_operations cgroup_pidlist_operations = {
        .read = seq_read,
        .llseek = seq_lseek,
        .write = cgroup_file_write,
-        .release = cgroup_tasks_release,
+        .release = cgroup_pidlist_release,
 };
 /*
- * Handle an open on 'tasks' file.  Prepare an array containing the
+ * The following functions handle opens on a file that displays a pidlist
- * process id's of tasks currently attached to the cgroup being opened.
+ * (tasks or procs). Prepare an array of the process/thread IDs of whoever's
+ * in the cgroup.
 */
+/* helper function for the two below it */
-static int cgroup_tasks_open(struct inode *unused, struct file *file)
+static int cgroup_pidlist_open(struct file *file, enum cgroup_filetype type)
 {
        struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent);
-        struct pid_namespace *ns = current->nsproxy->pid_ns;
+        struct cgroup_pidlist *l;
-        struct cgroup_pids *cp;
-        pid_t *pidarray;
-        int npids;
        int retval;
        /* Nothing to do for write-only files */
        if (!(file->f_mode & FMODE_READ))
                return 0;
-        /*
+        /* have the array populated */
-         * If cgroup gets more users after we read count, we won't have
+        retval = pidlist_array_load(cgrp, type, &l);
-         * enough space - tough.  This race is indistinguishable to the
+        if (retval)
-         * caller from the case that the additional cgroup users didn't
+                return retval;
-         * show up until sometime later on.
+        /* configure file information */
-         */
+        file->f_op = &cgroup_pidlist_operations;
-        npids = cgroup_task_count(cgrp);
-        pidarray = kmalloc(npids * sizeof(pid_t), GFP_KERNEL);
-        if (!pidarray)
-                return -ENOMEM;
-        npids = pid_array_load(pidarray, npids, cgrp);
-        sort(pidarray, npids, sizeof(pid_t), cmppid, NULL);
-        /*
-         * Store the array in the cgroup, freeing the old
-         * array if necessary
-         */
-        down_write(&cgrp->pids_mutex);
-        list_for_each_entry(cp, &cgrp->pids_list, list) {
-                if (ns == cp->ns)
-                        goto found;
-        }
-        cp = kzalloc(sizeof(*cp), GFP_KERNEL);
-        if (!cp) {
-                up_write(&cgrp->pids_mutex);
-                kfree(pidarray);
-                return -ENOMEM;
-        }
-        cp->cgrp = cgrp;
-        cp->ns = ns;
-        get_pid_ns(ns);
-        list_add(&cp->list, &cgrp->pids_list);
-found:
-        kfree(cp->tasks_pids);
-        cp->tasks_pids = pidarray;
-        cp->length = npids;
-        cp->use_count++;
-        up_write(&cgrp->pids_mutex);
-        file->f_op = &cgroup_tasks_operations;
-        retval = seq_open(file, &cgroup_tasks_seq_operations);
+        retval = seq_open(file, &cgroup_pidlist_seq_operations);
        if (retval) {
-                release_cgroup_pid_array(cp);
+                cgroup_release_pid_array(l);
                return retval;
        }
-        ((struct seq_file *)file->private_data)->private = cp;
+        ((struct seq_file *)file->private_data)->private = l;
        return 0;
 }
+static int cgroup_tasks_open(struct inode *unused, struct file *file)
+{
+        return cgroup_pidlist_open(file, CGROUP_FILE_TASKS);
+}
+static int cgroup_procs_open(struct inode *unused, struct file *file)
+{
+        return cgroup_pidlist_open(file, CGROUP_FILE_PROCS);
+}
 static u64 cgroup_read_notify_on_release(struct cgroup *cgrp,
                                            struct cftype *cft)
@@ -2449,21 +2794,27 @@ static int cgroup_write_notify_on_release(struct cgroup *cgrp,
 /*
 * for the common functions, 'private' gives the type of file
 */
+/* for hysterical raisins, we can't put this on the older files */
+#define CGROUP_FILE_GENERIC_PREFIX "cgroup."
 static struct cftype files[] = {
        {
                .name = "tasks",
                .open = cgroup_tasks_open,
                .write_u64 = cgroup_tasks_write,
-                .release = cgroup_tasks_release,
+                .release = cgroup_pidlist_release,
-                .private = FILE_TASKLIST,
                .mode = S_IRUGO | S_IWUSR,
        },
+        {
+                .name = CGROUP_FILE_GENERIC_PREFIX "procs",
+                .open = cgroup_procs_open,
+                /* .write_u64 = cgroup_procs_write, TODO */
+                .release = cgroup_pidlist_release,
+                .mode = S_IRUGO,
+        },
        {
                .name = "notify_on_release",
                .read_u64 = cgroup_read_notify_on_release,
                .write_u64 = cgroup_write_notify_on_release,
-                .private = FILE_NOTIFY_ON_RELEASE,
        },
 };
@@ -2472,7 +2823,6 @@ static struct cftype cft_release_agent = {
        .read_seq_string = cgroup_release_agent_show,
        .write_string = cgroup_release_agent_write,
        .max_write_len = PATH_MAX,
-        .private = FILE_RELEASE_AGENT,
 };
 static int cgroup_populate_dir(struct cgroup *cgrp)
@@ -2879,6 +3229,7 @@ int __init cgroup_init_early(void)
        init_task.cgroups = &init_css_set;
        init_css_set_link.cg = &init_css_set;
+        init_css_set_link.cgrp = dummytop;
        list_add(&init_css_set_link.cgrp_link_list,
                 &rootnode.top_cgroup.css_sets);
        list_add(&init_css_set_link.cg_link_list,
@@ -2933,7 +3284,7 @@ int __init cgroup_init(void)
        /* Add init_css_set to the hash table */
        hhead = css_set_hash(init_css_set.subsys);
        hlist_add_head(&init_css_set.hlist, hhead);
+        BUG_ON(!init_root_id(&rootnode));
        err = register_filesystem(&cgroup_fs_type);
        if (err < 0)
                goto out;
@@ -2986,15 +3337,16 @@ static int proc_cgroup_show(struct seq_file *m, void *v)
        for_each_active_root(root) {
                struct cgroup_subsys *ss;
                struct cgroup *cgrp;
-                int subsys_id;
                int count = 0;
-                seq_printf(m, "%lu:", root->subsys_bits);
+                seq_printf(m, "%d:", root->hierarchy_id);
                for_each_subsys(root, ss)
                        seq_printf(m, "%s%s", count++ ? "," : "", ss->name);
+                if (strlen(root->name))
+                        seq_printf(m, "%sname=%s", count ? "," : "",
+                                   root->name);
                seq_putc(m, ':');
-                get_first_subsys(&root->top_cgroup, NULL, &subsys_id);
+                cgrp = task_cgroup_from_root(tsk, root);
-                cgrp = task_cgroup(tsk, subsys_id);
                retval = cgroup_path(cgrp, buf, PAGE_SIZE);
                if (retval < 0)
                        goto out_unlock;
@@ -3033,8 +3385,8 @@ static int proc_cgroupstats_show(struct seq_file *m, void *v)
        mutex_lock(&cgroup_mutex);
        for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
                struct cgroup_subsys *ss = subsys[i];
-                seq_printf(m, "%s\t%lu\t%d\t%d\n",
+                seq_printf(m, "%s\t%d\t%d\t%d\n",
-                           ss->name, ss->root->subsys_bits,
+                           ss->name, ss->root->hierarchy_id,
                           ss->root->number_of_cgroups, !ss->disabled);
        }
        mutex_unlock(&cgroup_mutex);
@@ -3320,13 +3672,11 @@ int cgroup_is_descendant(const struct cgroup *cgrp, struct task_struct *task)
 {
        int ret;
        struct cgroup *target;
-        int subsys_id;
        if (cgrp == dummytop)
                return 1;
-        get_first_subsys(cgrp, NULL, &subsys_id);
+        target = task_cgroup_from_root(task, cgrp->root);
-        target = task_cgroup(task, subsys_id);
        while (cgrp != target && cgrp!= cgrp->top_cgroup)
                cgrp = cgrp->parent;
        ret = (cgrp == target);
@@ -3693,3 +4043,154 @@ css_get_next(struct cgroup_subsys *ss, int id,
        return ret;
 }
+#ifdef CONFIG_CGROUP_DEBUG
+static struct cgroup_subsys_state *debug_create(struct cgroup_subsys *ss,
+                                                   struct cgroup *cont)
+{
+        struct cgroup_subsys_state *css = kzalloc(sizeof(*css), GFP_KERNEL);
+        if (!css)
+                return ERR_PTR(-ENOMEM);
+        return css;
+}
+static void debug_destroy(struct cgroup_subsys *ss, struct cgroup *cont)
+{
+        kfree(cont->subsys[debug_subsys_id]);
+}
+static u64 cgroup_refcount_read(struct cgroup *cont, struct cftype *cft)
+{
+        return atomic_read(&cont->count);
+}
+static u64 debug_taskcount_read(struct cgroup *cont, struct cftype *cft)
+{
+        return cgroup_task_count(cont);
+}
+static u64 current_css_set_read(struct cgroup *cont, struct cftype *cft)
+{
+        return (u64)(unsigned long)current->cgroups;
+}
+static u64 current_css_set_refcount_read(struct cgroup *cont,
+                                           struct cftype *cft)
+{
+        u64 count;
+        rcu_read_lock();
+        count = atomic_read(&current->cgroups->refcount);
+        rcu_read_unlock();
+        return count;
+}
+static int current_css_set_cg_links_read(struct cgroup *cont,
+                                         struct cftype *cft,
+                                         struct seq_file *seq)
+{
+        struct cg_cgroup_link *link;
+        struct css_set *cg;
+        read_lock(&css_set_lock);
+        rcu_read_lock();
+        cg = rcu_dereference(current->cgroups);
+        list_for_each_entry(link, &cg->cg_links, cg_link_list) {
+                struct cgroup *c = link->cgrp;
+                const char *name;
+                if (c->dentry)
+                        name = c->dentry->d_name.name;
+                else
+                        name = "?";
+                seq_printf(seq, "Root %d group %s\n",
+                           c->root->hierarchy_id, name);
+        }
+        rcu_read_unlock();
+        read_unlock(&css_set_lock);
+        return 0;
+}
+#define MAX_TASKS_SHOWN_PER_CSS 25
+static int cgroup_css_links_read(struct cgroup *cont,
+                                 struct cftype *cft,
+                                 struct seq_file *seq)
+{
+        struct cg_cgroup_link *link;
+        read_lock(&css_set_lock);
+        list_for_each_entry(link, &cont->css_sets, cgrp_link_list) {
+                struct css_set *cg = link->cg;
+                struct task_struct *task;
+                int count = 0;
+                seq_printf(seq, "css_set %p\n", cg);
+                list_for_each_entry(task, &cg->tasks, cg_list) {
+                        if (count++ > MAX_TASKS_SHOWN_PER_CSS) {
+                                seq_puts(seq, "  ...\n");
+                                break;
+                        } else {
+                                seq_printf(seq, "  task %d\n",
+                                           task_pid_vnr(task));
+                        }
+                }
+        }
+        read_unlock(&css_set_lock);
+        return 0;
+}
+static u64 releasable_read(struct cgroup *cgrp, struct cftype *cft)
+{
+        return test_bit(CGRP_RELEASABLE, &cgrp->flags);
+}
+static struct cftype debug_files[] =  {
+        {
+                .name = "cgroup_refcount",
+                .read_u64 = cgroup_refcount_read,
+        },
+        {
+                .name = "taskcount",
+                .read_u64 = debug_taskcount_read,
+        },
+        {
+                .name = "current_css_set",
+                .read_u64 = current_css_set_read,
+        },
+        {
+                .name = "current_css_set_refcount",
+                .read_u64 = current_css_set_refcount_read,
+        },
+        {
+                .name = "current_css_set_cg_links",
+                .read_seq_string = current_css_set_cg_links_read,
+        },
+        {
+                .name = "cgroup_css_links",
+                .read_seq_string = cgroup_css_links_read,
+        },
+        {
+                .name = "releasable",
+                .read_u64 = releasable_read,
+        },
+};
+static int debug_populate(struct cgroup_subsys *ss, struct cgroup *cont)
+{
+        return cgroup_add_files(cont, ss, debug_files,
+                                ARRAY_SIZE(debug_files));
+}
+struct cgroup_subsys debug_subsys = {
+        .name = "debug",
+        .create = debug_create,
+        .destroy = debug_destroy,
+        .populate = debug_populate,
+        .subsys_id = debug_subsys_id,
+};
+#endif /* CONFIG_CGROUP_DEBUG */
diff --git a/kernel/cgroup_debug.c b/kernel/cgroup_debug.c
deleted file mode 100644
index 0c92d797baa6..000000000000
--- a/kernel/cgroup_debug.c
+++ /dev/null
@@ -1,105 +0,0 @@
-/*
- * kernel/cgroup_debug.c - Example cgroup subsystem that
- * exposes debug info
- *
- * Copyright (C) Google Inc, 2007
- *
- * Developed by Paul Menage (menage@google.com)
- *
- */
-#include <linux/cgroup.h>
-#include <linux/fs.h>
-#include <linux/slab.h>
-#include <linux/rcupdate.h>
-#include <asm/atomic.h>
-static struct cgroup_subsys_state *debug_create(struct cgroup_subsys *ss,
-                                                   struct cgroup *cont)
-{
-        struct cgroup_subsys_state *css = kzalloc(sizeof(*css), GFP_KERNEL);
-        if (!css)
-                return ERR_PTR(-ENOMEM);
-        return css;
-}
-static void debug_destroy(struct cgroup_subsys *ss, struct cgroup *cont)
-{
-        kfree(cont->subsys[debug_subsys_id]);
-}
-static u64 cgroup_refcount_read(struct cgroup *cont, struct cftype *cft)
-{
-        return atomic_read(&cont->count);
-}
-static u64 taskcount_read(struct cgroup *cont, struct cftype *cft)
-{
-        u64 count;
-        count = cgroup_task_count(cont);
-        return count;
-}
-static u64 current_css_set_read(struct cgroup *cont, struct cftype *cft)
-{
-        return (u64)(long)current->cgroups;
-}
-static u64 current_css_set_refcount_read(struct cgroup *cont,
-                                           struct cftype *cft)
-{
-        u64 count;
-        rcu_read_lock();
-        count = atomic_read(&current->cgroups->refcount);
-        rcu_read_unlock();
-        return count;
-}
-static u64 releasable_read(struct cgroup *cgrp, struct cftype *cft)
-{
-        return test_bit(CGRP_RELEASABLE, &cgrp->flags);
-}
-static struct cftype files[] =  {
-        {
-                .name = "cgroup_refcount",
-                .read_u64 = cgroup_refcount_read,
-        },
-        {
-                .name = "taskcount",
-                .read_u64 = taskcount_read,
-        },
-        {
-                .name = "current_css_set",
-                .read_u64 = current_css_set_read,
-        },
-        {
-                .name = "current_css_set_refcount",
-                .read_u64 = current_css_set_refcount_read,
-        },
-        {
-                .name = "releasable",
-                .read_u64 = releasable_read,
-        },
-};
-static int debug_populate(struct cgroup_subsys *ss, struct cgroup *cont)
-{
-        return cgroup_add_files(cont, ss, files, ARRAY_SIZE(files));
-}
-struct cgroup_subsys debug_subsys = {
-        .name = "debug",
-        .create = debug_create,
-        .destroy = debug_destroy,
-        .populate = debug_populate,
-        .subsys_id = debug_subsys_id,
-};
diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c
index fb249e2bcada..59e9ef6aab40 100644
--- a/kernel/cgroup_freezer.c
+++ b/kernel/cgroup_freezer.c
@@ -159,7 +159,7 @@ static bool is_task_frozen_enough(struct task_struct *task)
 */
 static int freezer_can_attach(struct cgroup_subsys *ss,
                              struct cgroup *new_cgroup,
-                              struct task_struct *task)
+                              struct task_struct *task, bool threadgroup)
 {
        struct freezer *freezer;
@@ -177,6 +177,19 @@ static int freezer_can_attach(struct cgroup_subsys *ss,
        if (freezer->state == CGROUP_FROZEN)
                return -EBUSY;
+        if (threadgroup) {
+                struct task_struct *c;
+                rcu_read_lock();
+                list_for_each_entry_rcu(c, &task->thread_group, thread_group) {
+                        if (is_task_frozen_enough(c)) {
+                                rcu_read_unlock();
+                                return -EBUSY;
+                        }
+                }
+                rcu_read_unlock();
+        }
        return 0;
 }
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 7e75a41bd508..b5cb469d2545 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1324,9 +1324,10 @@ static int fmeter_getrate(struct fmeter *fmp)
 static cpumask_var_t cpus_attach;
 /* Called by cgroups to determine if a cpuset is usable; cgroup_mutex held */
-static int cpuset_can_attach(struct cgroup_subsys *ss,
+static int cpuset_can_attach(struct cgroup_subsys *ss, struct cgroup *cont,
-                             struct cgroup *cont, struct task_struct *tsk)
+                             struct task_struct *tsk, bool threadgroup)
 {
+        int ret;
        struct cpuset *cs = cgroup_cs(cont);
        if (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed))
@@ -1343,18 +1344,51 @@ static int cpuset_can_attach(struct cgroup_subsys *ss,
        if (tsk->flags & PF_THREAD_BOUND)
                return -EINVAL;
-        return security_task_setscheduler(tsk, 0, NULL);
+        ret = security_task_setscheduler(tsk, 0, NULL);
+        if (ret)
+                return ret;
+        if (threadgroup) {
+                struct task_struct *c;
+                rcu_read_lock();
+                list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) {
+                        ret = security_task_setscheduler(c, 0, NULL);
+                        if (ret) {
+                                rcu_read_unlock();
+                                return ret;
+                        }
+                }
+                rcu_read_unlock();
+        }
+        return 0;
+}
+static void cpuset_attach_task(struct task_struct *tsk, nodemask_t *to,
+                               struct cpuset *cs)
+{
+        int err;
+        /*
+         * can_attach beforehand should guarantee that this doesn't fail.
+         * TODO: have a better way to handle failure here
+         */
+        err = set_cpus_allowed_ptr(tsk, cpus_attach);
+        WARN_ON_ONCE(err);
+        task_lock(tsk);
+        cpuset_change_task_nodemask(tsk, to);
+        task_unlock(tsk);
+        cpuset_update_task_spread_flag(cs, tsk);
 }
-static void cpuset_attach(struct cgroup_subsys *ss,
+static void cpuset_attach(struct cgroup_subsys *ss, struct cgroup *cont,
-                          struct cgroup *cont, struct cgroup *oldcont,
+                          struct cgroup *oldcont, struct task_struct *tsk,
-                          struct task_struct *tsk)
+                          bool threadgroup)
 {
        nodemask_t from, to;
        struct mm_struct *mm;
        struct cpuset *cs = cgroup_cs(cont);
        struct cpuset *oldcs = cgroup_cs(oldcont);
-        int err;
        if (cs == &top_cpuset) {
                cpumask_copy(cpus_attach, cpu_possible_mask);
@@ -1363,15 +1397,19 @@ static void cpuset_attach(struct cgroup_subsys *ss,
                guarantee_online_cpus(cs, cpus_attach);
                guarantee_online_mems(cs, &to);
        }
-        err = set_cpus_allowed_ptr(tsk, cpus_attach);
-        if (err)
-                return;
-        task_lock(tsk);
+        /* do per-task migration stuff possibly for each in the threadgroup */
-        cpuset_change_task_nodemask(tsk, &to);
+        cpuset_attach_task(tsk, &to, cs);
-        task_unlock(tsk);
+        if (threadgroup) {
-        cpuset_update_task_spread_flag(cs, tsk);
+                struct task_struct *c;
+                rcu_read_lock();
+                list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) {
+                        cpuset_attach_task(c, &to, cs);
+                }
+                rcu_read_unlock();
+        }
+        /* change mm; only needs to be done once even if threadgroup */
        from = oldcs->mems_allowed;
        to = cs->mems_allowed;
        mm = get_task_mm(tsk);
diff --git a/kernel/cred.c b/kernel/cred.c
index d7f7a01082eb..dd76cfe5f5b0 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -782,6 +782,25 @@ EXPORT_SYMBOL(set_create_files_as);
 #ifdef CONFIG_DEBUG_CREDENTIALS
+bool creds_are_invalid(const struct cred *cred)
+{
+        if (cred->magic != CRED_MAGIC)
+                return true;
+        if (atomic_read(&cred->usage) < atomic_read(&cred->subscribers))
+                return true;
+#ifdef CONFIG_SECURITY_SELINUX
+        if (selinux_is_enabled()) {
+                if ((unsigned long) cred->security < PAGE_SIZE)
+                        return true;
+                if ((*(u32 *)cred->security & 0xffffff00) ==
+                    (POISON_FREE << 24 | POISON_FREE << 16 | POISON_FREE << 8))
+                        return true;
+        }
+#endif
+        return false;
+}
+EXPORT_SYMBOL(creds_are_invalid);
 /*
 * dump invalid credentials
 */
diff --git a/kernel/exit.c b/kernel/exit.c
index ae5d8660ddff..5859f598c951 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -47,7 +47,7 @@
 #include <linux/tracehook.h>
 #include <linux/fs_struct.h>
 #include <linux/init_task.h>
-#include <linux/perf_counter.h>
+#include <linux/perf_event.h>
 #include <trace/events/sched.h>
 #include <asm/uaccess.h>
@@ -154,8 +154,8 @@ static void delayed_put_task_struct(struct rcu_head *rhp)
 {
        struct task_struct *tsk = container_of(rhp, struct task_struct, rcu);
-#ifdef CONFIG_PERF_COUNTERS
+#ifdef CONFIG_PERF_EVENTS
-        WARN_ON_ONCE(tsk->perf_counter_ctxp);
+        WARN_ON_ONCE(tsk->perf_event_ctxp);
 #endif
        trace_sched_process_free(tsk);
        put_task_struct(tsk);
@@ -359,8 +359,10 @@ void __set_special_pids(struct pid *pid)
 {
        struct task_struct *curr = current->group_leader;
-        if (task_session(curr) != pid)
+        if (task_session(curr) != pid) {
                change_pid(curr, PIDTYPE_SID, pid);
+                proc_sid_connector(curr);
+        }
        if (task_pgrp(curr) != pid)
                change_pid(curr, PIDTYPE_PGID, pid);
@@ -945,6 +947,8 @@ NORET_TYPE void do_exit(long code)
        if (group_dead) {
                hrtimer_cancel(&tsk->signal->real_timer);
                exit_itimers(tsk->signal);
+                if (tsk->mm)
+                        setmax_mm_hiwater_rss(&tsk->signal->maxrss, tsk->mm);
        }
        acct_collect(code, group_dead);
        if (group_dead)
@@ -972,8 +976,6 @@ NORET_TYPE void do_exit(long code)
                disassociate_ctty(1);
        module_put(task_thread_info(tsk)->exec_domain->module);
-        if (tsk->binfmt)
-                module_put(tsk->binfmt->module);
        proc_exit_connector(tsk);
@@ -981,7 +983,7 @@ NORET_TYPE void do_exit(long code)
         * Flush inherited counters to the parent - before the parent
         * gets woken up by child-exit notifications.
         */
-        perf_counter_exit_task(tsk);
+        perf_event_exit_task(tsk);
        exit_notify(tsk, group_dead);
 #ifdef CONFIG_NUMA
@@ -1093,28 +1095,28 @@ struct wait_opts {
        int __user              *wo_stat;
        struct rusage __user    *wo_rusage;
+        wait_queue_t            child_wait;
        int                     notask_error;
 };
-static struct pid *task_pid_type(struct task_struct *task, enum pid_type type)
+static inline
+struct pid *task_pid_type(struct task_struct *task, enum pid_type type)
 {
-        struct pid *pid = NULL;
+        if (type != PIDTYPE_PID)
-        if (type == PIDTYPE_PID)
+                task = task->group_leader;
-                pid = task->pids[type].pid;
+        return task->pids[type].pid;
-        else if (type < PIDTYPE_MAX)
-                pid = task->group_leader->pids[type].pid;
-        return pid;
 }
-static int eligible_child(struct wait_opts *wo, struct task_struct *p)
+static int eligible_pid(struct wait_opts *wo, struct task_struct *p)
 {
-        int err;
+        return  wo->wo_type == PIDTYPE_MAX ||
+                task_pid_type(p, wo->wo_type) == wo->wo_pid;
-        if (wo->wo_type < PIDTYPE_MAX) {
+}
-                if (task_pid_type(p, wo->wo_type) != wo->wo_pid)
-                        return 0;
-        }
+static int eligible_child(struct wait_opts *wo, struct task_struct *p)
+{
+        if (!eligible_pid(wo, p))
+                return 0;
        /* Wait for all children (clone and not) if __WALL is set;
         * otherwise, wait for clone children *only* if __WCLONE is
         * set; otherwise, wait for non-clone children *only*.  (Note:
@@ -1124,10 +1126,6 @@ static int eligible_child(struct wait_opts *wo, struct task_struct *p)
            && !(wo->wo_flags & __WALL))
                return 0;
-        err = security_task_wait(p);
-        if (err)
-                return err;
        return 1;
 }
@@ -1140,18 +1138,20 @@ static int wait_noreap_copyout(struct wait_opts *wo, struct task_struct *p,
        put_task_struct(p);
        infop = wo->wo_info;
-        if (!retval)
+        if (infop) {
-                retval = put_user(SIGCHLD, &infop->si_signo);
+                if (!retval)
-        if (!retval)
+                        retval = put_user(SIGCHLD, &infop->si_signo);
-                retval = put_user(0, &infop->si_errno);
+                if (!retval)
-        if (!retval)
+                        retval = put_user(0, &infop->si_errno);
-                retval = put_user((short)why, &infop->si_code);
+                if (!retval)
-        if (!retval)
+                        retval = put_user((short)why, &infop->si_code);
-                retval = put_user(pid, &infop->si_pid);
+                if (!retval)
-        if (!retval)
+                        retval = put_user(pid, &infop->si_pid);
-                retval = put_user(uid, &infop->si_uid);
+                if (!retval)
-        if (!retval)
+                        retval = put_user(uid, &infop->si_uid);
-                retval = put_user(status, &infop->si_status);
+                if (!retval)
+                        retval = put_user(status, &infop->si_status);
+        }
        if (!retval)
                retval = pid;
        return retval;
@@ -1208,6 +1208,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
        if (likely(!traced) && likely(!task_detached(p))) {
                struct signal_struct *psig;
                struct signal_struct *sig;
+                unsigned long maxrss;
                /*
                 * The resource counters for the group leader are in its
@@ -1256,6 +1257,9 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
                psig->coublock +=
                        task_io_get_oublock(p) +
                        sig->oublock + sig->coublock;
+                maxrss = max(sig->maxrss, sig->cmaxrss);
+                if (psig->cmaxrss < maxrss)
+                        psig->cmaxrss = maxrss;
                task_io_accounting_add(&psig->ioac, &p->ioac);
                task_io_accounting_add(&psig->ioac, &sig->ioac);
                spin_unlock_irq(&p->real_parent->sighand->siglock);
@@ -1477,13 +1481,14 @@ static int wait_task_continued(struct wait_opts *wo, struct task_struct *p)
 * then ->notask_error is 0 if @p is an eligible child,
 * or another error from security_task_wait(), or still -ECHILD.
 */
-static int wait_consider_task(struct wait_opts *wo, struct task_struct *parent,
+static int wait_consider_task(struct wait_opts *wo, int ptrace,
-                                int ptrace, struct task_struct *p)
+                                struct task_struct *p)
 {
        int ret = eligible_child(wo, p);
        if (!ret)
                return ret;
+        ret = security_task_wait(p);
        if (unlikely(ret < 0)) {
                /*
                 * If we have not yet seen any eligible child,
@@ -1545,7 +1550,7 @@ static int do_wait_thread(struct wait_opts *wo, struct task_struct *tsk)
                 * Do not consider detached threads.
                 */
                if (!task_detached(p)) {
-                        int ret = wait_consider_task(wo, tsk, 0, p);
+                        int ret = wait_consider_task(wo, 0, p);
                        if (ret)
                                return ret;
                }
@@ -1559,7 +1564,7 @@ static int ptrace_do_wait(struct wait_opts *wo, struct task_struct *tsk)
        struct task_struct *p;
        list_for_each_entry(p, &tsk->ptraced, ptrace_entry) {
-                int ret = wait_consider_task(wo, tsk, 1, p);
+                int ret = wait_consider_task(wo, 1, p);
                if (ret)
                        return ret;
        }
@@ -1567,15 +1572,38 @@ static int ptrace_do_wait(struct wait_opts *wo, struct task_struct *tsk)
        return 0;
 }
+static int child_wait_callback(wait_queue_t *wait, unsigned mode,
+                                int sync, void *key)
+{
+        struct wait_opts *wo = container_of(wait, struct wait_opts,
+                                                child_wait);
+        struct task_struct *p = key;
+        if (!eligible_pid(wo, p))
+                return 0;
+        if ((wo->wo_flags & __WNOTHREAD) && wait->private != p->parent)
+                return 0;
+        return default_wake_function(wait, mode, sync, key);
+}
+void __wake_up_parent(struct task_struct *p, struct task_struct *parent)
+{
+        __wake_up_sync_key(&parent->signal->wait_chldexit,
+                                TASK_INTERRUPTIBLE, 1, p);
+}
 static long do_wait(struct wait_opts *wo)
 {
-        DECLARE_WAITQUEUE(wait, current);
        struct task_struct *tsk;
        int retval;
        trace_sched_process_wait(wo->wo_pid);
-        add_wait_queue(&current->signal->wait_chldexit,&wait);
+        init_waitqueue_func_entry(&wo->child_wait, child_wait_callback);
+        wo->child_wait.private = current;
+        add_wait_queue(&current->signal->wait_chldexit, &wo->child_wait);
 repeat:
        /*
         * If there is nothing that can match our critiera just get out.
@@ -1616,32 +1644,7 @@ notask:
        }
 end:
        __set_current_state(TASK_RUNNING);
-        remove_wait_queue(&current->signal->wait_chldexit,&wait);
+        remove_wait_queue(&current->signal->wait_chldexit, &wo->child_wait);
-        if (wo->wo_info) {
-                struct siginfo __user *infop = wo->wo_info;
-                if (retval > 0)
-                        retval = 0;
-                else {
-                        /*
-                         * For a WNOHANG return, clear out all the fields
-                         * we would set so the user can easily tell the
-                         * difference.
-                         */
-                        if (!retval)
-                                retval = put_user(0, &infop->si_signo);
-                        if (!retval)
-                                retval = put_user(0, &infop->si_errno);
-                        if (!retval)
-                                retval = put_user(0, &infop->si_code);
-                        if (!retval)
-                                retval = put_user(0, &infop->si_pid);
-                        if (!retval)
-                                retval = put_user(0, &infop->si_uid);
-                        if (!retval)
-                                retval = put_user(0, &infop->si_status);
-                }
-        }
        return retval;
 }
@@ -1686,6 +1689,29 @@ SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *,
        wo.wo_stat      = NULL;
        wo.wo_rusage    = ru;
        ret = do_wait(&wo);
+        if (ret > 0) {
+                ret = 0;
+        } else if (infop) {
+                /*
+                 * For a WNOHANG return, clear out all the fields
+                 * we would set so the user can easily tell the
+                 * difference.
+                 */
+                if (!ret)
+                        ret = put_user(0, &infop->si_signo);
+                if (!ret)
+                        ret = put_user(0, &infop->si_errno);
+                if (!ret)
+                        ret = put_user(0, &infop->si_code);
+                if (!ret)
+                        ret = put_user(0, &infop->si_pid);
+                if (!ret)
+                        ret = put_user(0, &infop->si_uid);
+                if (!ret)
+                        ret = put_user(0, &infop->si_status);
+        }
        put_pid(pid);
        /* avoid REGPARM breakage on x86: */
diff --git a/kernel/fork.c b/kernel/fork.c
index bfee931ee3fb..266c6af6ef1b 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -49,6 +49,7 @@
 #include <linux/ftrace.h>
 #include <linux/profile.h>
 #include <linux/rmap.h>
+#include <linux/ksm.h>
 #include <linux/acct.h>
 #include <linux/tsacct_kern.h>
 #include <linux/cn_proc.h>
@@ -61,7 +62,8 @@
 #include <linux/blkdev.h>
 #include <linux/fs_struct.h>
 #include <linux/magic.h>
-#include <linux/perf_counter.h>
+#include <linux/perf_event.h>
+#include <linux/posix-timers.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -136,9 +138,17 @@ struct kmem_cache *vm_area_cachep;
 /* SLAB cache for mm_struct structures (tsk->mm) */
 static struct kmem_cache *mm_cachep;
+static void account_kernel_stack(struct thread_info *ti, int account)
+{
+        struct zone *zone = page_zone(virt_to_page(ti));
+        mod_zone_page_state(zone, NR_KERNEL_STACK, account);
+}
 void free_task(struct task_struct *tsk)
 {
        prop_local_destroy_single(&tsk->dirties);
+        account_kernel_stack(tsk->stack, -1);
        free_thread_info(tsk->stack);
        rt_mutex_debug_task_free(tsk);
        ftrace_graph_exit_task(tsk);
@@ -253,6 +263,9 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
        tsk->btrace_seq = 0;
 #endif
        tsk->splice_pipe = NULL;
+        account_kernel_stack(ti, 1);
        return tsk;
 out:
@@ -288,6 +301,9 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
        rb_link = &mm->mm_rb.rb_node;
        rb_parent = NULL;
        pprev = &mm->mmap;
+        retval = ksm_fork(mm, oldmm);
+        if (retval)
+                goto out;
        for (mpnt = oldmm->mmap; mpnt; mpnt = mpnt->vm_next) {
                struct file *file;
@@ -418,22 +434,30 @@ __setup("coredump_filter=", coredump_filter_setup);
 #include <linux/init_task.h>
+static void mm_init_aio(struct mm_struct *mm)
+{
+#ifdef CONFIG_AIO
+        spin_lock_init(&mm->ioctx_lock);
+        INIT_HLIST_HEAD(&mm->ioctx_list);
+#endif
+}
 static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p)
 {
        atomic_set(&mm->mm_users, 1);
        atomic_set(&mm->mm_count, 1);
        init_rwsem(&mm->mmap_sem);
        INIT_LIST_HEAD(&mm->mmlist);
-        mm->flags = (current->mm) ? current->mm->flags : default_dump_filter;
+        mm->flags = (current->mm) ?
+                (current->mm->flags & MMF_INIT_MASK) : default_dump_filter;
        mm->core_state = NULL;
        mm->nr_ptes = 0;
        set_mm_counter(mm, file_rss, 0);
        set_mm_counter(mm, anon_rss, 0);
        spin_lock_init(&mm->page_table_lock);
-        spin_lock_init(&mm->ioctx_lock);
-        INIT_HLIST_HEAD(&mm->ioctx_list);
        mm->free_area_cache = TASK_UNMAPPED_BASE;
        mm->cached_hole_size = ~0UL;
+        mm_init_aio(mm);
        mm_init_owner(mm, p);
        if (likely(!mm_alloc_pgd(mm))) {
@@ -485,6 +509,7 @@ void mmput(struct mm_struct *mm)
        if (atomic_dec_and_test(&mm->mm_users)) {
                exit_aio(mm);
+                ksm_exit(mm);
                exit_mmap(mm);
                set_mm_exe_file(mm, NULL);
                if (!list_empty(&mm->mmlist)) {
@@ -493,6 +518,8 @@ void mmput(struct mm_struct *mm)
                        spin_unlock(&mmlist_lock);
                }
                put_swap_token(mm);
+                if (mm->binfmt)
+                        module_put(mm->binfmt->module);
                mmdrop(mm);
        }
 }
@@ -618,9 +645,14 @@ struct mm_struct *dup_mm(struct task_struct *tsk)
        mm->hiwater_rss = get_mm_rss(mm);
        mm->hiwater_vm = mm->total_vm;
+        if (mm->binfmt && !try_module_get(mm->binfmt->module))
+                goto free_pt;
        return mm;
 free_pt:
+        /* don't put binfmt in mmput, we haven't got module yet */
+        mm->binfmt = NULL;
        mmput(mm);
 fail_nomem:
@@ -788,10 +820,10 @@ static void posix_cpu_timers_init_group(struct signal_struct *sig)
        thread_group_cputime_init(sig);
        /* Expiration times and increments. */
-        sig->it_virt_expires = cputime_zero;
+        sig->it[CPUCLOCK_PROF].expires = cputime_zero;
-        sig->it_virt_incr = cputime_zero;
+        sig->it[CPUCLOCK_PROF].incr = cputime_zero;
-        sig->it_prof_expires = cputime_zero;
+        sig->it[CPUCLOCK_VIRT].expires = cputime_zero;
-        sig->it_prof_incr = cputime_zero;
+        sig->it[CPUCLOCK_VIRT].incr = cputime_zero;
        /* Cached expiration times. */
        sig->cputime_expires.prof_exp = cputime_zero;
@@ -849,6 +881,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
        sig->nvcsw = sig->nivcsw = sig->cnvcsw = sig->cnivcsw = 0;
        sig->min_flt = sig->maj_flt = sig->cmin_flt = sig->cmaj_flt = 0;
        sig->inblock = sig->oublock = sig->cinblock = sig->coublock = 0;
+        sig->maxrss = sig->cmaxrss = 0;
        task_io_accounting_init(&sig->ioac);
        sig->sum_sched_runtime = 0;
        taskstats_tgid_init(sig);
@@ -863,6 +896,8 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
        tty_audit_fork(sig);
+        sig->oom_adj = current->signal->oom_adj;
        return 0;
 }
@@ -958,6 +993,16 @@ static struct task_struct *copy_process(unsigned long clone_flags,
        if ((clone_flags & CLONE_SIGHAND) && !(clone_flags & CLONE_VM))
                return ERR_PTR(-EINVAL);
+        /*
+         * Siblings of global init remain as zombies on exit since they are
+         * not reaped by their parent (swapper). To solve this and to avoid
+         * multi-rooted process trees, prevent global and container-inits
+         * from creating siblings.
+         */
+        if ((clone_flags & CLONE_PARENT) &&
+                                current->signal->flags & SIGNAL_UNKILLABLE)
+                return ERR_PTR(-EINVAL);
        retval = security_task_create(clone_flags);
        if (retval)
                goto fork_out;
@@ -999,9 +1044,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
        if (!try_module_get(task_thread_info(p)->exec_domain->module))
                goto bad_fork_cleanup_count;
-        if (p->binfmt && !try_module_get(p->binfmt->module))
-                goto bad_fork_cleanup_put_domain;
        p->did_exec = 0;
        delayacct_tsk_init(p);  /* Must remain after dup_task_struct() */
        copy_flags(clone_flags, p);
@@ -1075,10 +1117,12 @@ static struct task_struct *copy_process(unsigned long clone_flags,
        p->bts = NULL;
+        p->stack_start = stack_start;
        /* Perform scheduler related setup. Assign this task to a CPU. */
        sched_fork(p, clone_flags);
-        retval = perf_counter_init_task(p);
+        retval = perf_event_init_task(p);
        if (retval)
                goto bad_fork_cleanup_policy;
@@ -1253,7 +1297,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
        write_unlock_irq(&tasklist_lock);
        proc_fork_connector(p);
        cgroup_post_fork(p);
-        perf_counter_fork(p);
+        perf_event_fork(p);
        return p;
 bad_fork_free_pid:
@@ -1280,16 +1324,13 @@ bad_fork_cleanup_semundo:
 bad_fork_cleanup_audit:
        audit_free(p);
 bad_fork_cleanup_policy:
-        perf_counter_free_task(p);
+        perf_event_free_task(p);
 #ifdef CONFIG_NUMA
        mpol_put(p->mempolicy);
 bad_fork_cleanup_cgroup:
 #endif
        cgroup_exit(p, cgroup_callbacks_done);
        delayacct_tsk_free(p);
-        if (p->binfmt)
-                module_put(p->binfmt->module);
-bad_fork_cleanup_put_domain:
        module_put(task_thread_info(p)->exec_domain->module);
 bad_fork_cleanup_count:
        atomic_dec(&p->cred->user->processes);
diff --git a/kernel/gcov/Kconfig b/kernel/gcov/Kconfig
index 654efd09f6a9..70a298d6da71 100644
--- a/kernel/gcov/Kconfig
+++ b/kernel/gcov/Kconfig
@@ -34,7 +34,7 @@ config GCOV_KERNEL
 config GCOV_PROFILE_ALL
        bool "Profile entire Kernel"
        depends on GCOV_KERNEL
-        depends on S390 || X86 || (PPC && EXPERIMENTAL)
+        depends on S390 || X86 || (PPC && EXPERIMENTAL) || MICROBLAZE
        default n
        ---help---
        This options activates profiling for the entire kernel.
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index c03f221fee44..e5d98ce50f89 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -48,6 +48,8 @@
 #include <asm/uaccess.h>
+#include <trace/events/timer.h>
 /*
 * The timer bases:
 *
@@ -442,6 +444,26 @@ static inline void debug_hrtimer_activate(struct hrtimer *timer) { }
 static inline void debug_hrtimer_deactivate(struct hrtimer *timer) { }
 #endif
+static inline void
+debug_init(struct hrtimer *timer, clockid_t clockid,
+           enum hrtimer_mode mode)
+{
+        debug_hrtimer_init(timer);
+        trace_hrtimer_init(timer, clockid, mode);
+}
+static inline void debug_activate(struct hrtimer *timer)
+{
+        debug_hrtimer_activate(timer);
+        trace_hrtimer_start(timer);
+}
+static inline void debug_deactivate(struct hrtimer *timer)
+{
+        debug_hrtimer_deactivate(timer);
+        trace_hrtimer_cancel(timer);
+}
 /* High resolution timer related functions */
 #ifdef CONFIG_HIGH_RES_TIMERS
@@ -798,7 +820,7 @@ static int enqueue_hrtimer(struct hrtimer *timer,
        struct hrtimer *entry;
        int leftmost = 1;
-        debug_hrtimer_activate(timer);
+        debug_activate(timer);
        /*
         * Find the right place in the rbtree:
@@ -884,7 +906,7 @@ remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base)
                 * reprogramming happens in the interrupt handler. This is a
                 * rare case and less expensive than a smp call.
                 */
-                debug_hrtimer_deactivate(timer);
+                debug_deactivate(timer);
                timer_stats_hrtimer_clear_start_info(timer);
                reprogram = base->cpu_base == &__get_cpu_var(hrtimer_bases);
                __remove_hrtimer(timer, base, HRTIMER_STATE_INACTIVE,
@@ -1117,7 +1139,7 @@ static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
 void hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
                  enum hrtimer_mode mode)
 {
-        debug_hrtimer_init(timer);
+        debug_init(timer, clock_id, mode);
        __hrtimer_init(timer, clock_id, mode);
 }
 EXPORT_SYMBOL_GPL(hrtimer_init);
@@ -1141,7 +1163,7 @@ int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp)
 }
 EXPORT_SYMBOL_GPL(hrtimer_get_res);
-static void __run_hrtimer(struct hrtimer *timer)
+static void __run_hrtimer(struct hrtimer *timer, ktime_t *now)
 {
        struct hrtimer_clock_base *base = timer->base;
        struct hrtimer_cpu_base *cpu_base = base->cpu_base;
@@ -1150,7 +1172,7 @@ static void __run_hrtimer(struct hrtimer *timer)
        WARN_ON(!irqs_disabled());
-        debug_hrtimer_deactivate(timer);
+        debug_deactivate(timer);
        __remove_hrtimer(timer, base, HRTIMER_STATE_CALLBACK, 0);
        timer_stats_account_hrtimer(timer);
        fn = timer->function;
@@ -1161,7 +1183,9 @@ static void __run_hrtimer(struct hrtimer *timer)
         * the timer base.
         */
        spin_unlock(&cpu_base->lock);
+        trace_hrtimer_expire_entry(timer, now);
        restart = fn(timer);
+        trace_hrtimer_expire_exit(timer);
        spin_lock(&cpu_base->lock);
        /*
@@ -1272,7 +1296,7 @@ void hrtimer_interrupt(struct clock_event_device *dev)
                                break;
                        }
-                        __run_hrtimer(timer);
+                        __run_hrtimer(timer, &basenow);
                }
                base++;
        }
@@ -1394,7 +1418,7 @@ void hrtimer_run_queues(void)
                                        hrtimer_get_expires_tv64(timer))
                                break;
-                        __run_hrtimer(timer);
+                        __run_hrtimer(timer, &base->softirq_time);
                }
                spin_unlock(&cpu_base->lock);
        }
@@ -1571,7 +1595,7 @@ static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base,
        while ((node = rb_first(&old_base->active))) {
                timer = rb_entry(node, struct hrtimer, node);
                BUG_ON(hrtimer_callback_running(timer));
-                debug_hrtimer_deactivate(timer);
+                debug_deactivate(timer);
                /*
                 * Mark it as STATE_MIGRATE not INACTIVE otherwise the
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index 022a4927b785..d4e841747400 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -171,12 +171,12 @@ static unsigned long timeout_jiffies(unsigned long timeout)
 * Process updating of timeout sysctl
 */
 int proc_dohung_task_timeout_secs(struct ctl_table *table, int write,
-                                  struct file *filp, void __user *buffer,
+                                  void __user *buffer,
                                  size_t *lenp, loff_t *ppos)
 {
        int ret;
-        ret = proc_doulongvec_minmax(table, write, filp, buffer, lenp, ppos);
+        ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
        if (ret || !write)
                goto out;
diff --git a/kernel/itimer.c b/kernel/itimer.c
index 58762f7077ec..b03451ede528 100644
--- a/kernel/itimer.c
+++ b/kernel/itimer.c
@@ -12,6 +12,7 @@
 #include <linux/time.h>
 #include <linux/posix-timers.h>
 #include <linux/hrtimer.h>
+#include <trace/events/timer.h>
 #include <asm/uaccess.h>
@@ -41,10 +42,43 @@ static struct timeval itimer_get_remtime(struct hrtimer *timer)
        return ktime_to_timeval(rem);
 }
+static void get_cpu_itimer(struct task_struct *tsk, unsigned int clock_id,
+                           struct itimerval *const value)
+{
+        cputime_t cval, cinterval;
+        struct cpu_itimer *it = &tsk->signal->it[clock_id];
+        spin_lock_irq(&tsk->sighand->siglock);
+        cval = it->expires;
+        cinterval = it->incr;
+        if (!cputime_eq(cval, cputime_zero)) {
+                struct task_cputime cputime;
+                cputime_t t;
+                thread_group_cputimer(tsk, &cputime);
+                if (clock_id == CPUCLOCK_PROF)
+                        t = cputime_add(cputime.utime, cputime.stime);
+                else
+                        /* CPUCLOCK_VIRT */
+                        t = cputime.utime;
+                if (cputime_le(cval, t))
+                        /* about to fire */
+                        cval = cputime_one_jiffy;
+                else
+                        cval = cputime_sub(cval, t);
+        }
+        spin_unlock_irq(&tsk->sighand->siglock);
+        cputime_to_timeval(cval, &value->it_value);
+        cputime_to_timeval(cinterval, &value->it_interval);
+}
 int do_getitimer(int which, struct itimerval *value)
 {
        struct task_struct *tsk = current;
-        cputime_t cinterval, cval;
        switch (which) {
        case ITIMER_REAL:
@@ -55,44 +89,10 @@ int do_getitimer(int which, struct itimerval *value)
                spin_unlock_irq(&tsk->sighand->siglock);
                break;
        case ITIMER_VIRTUAL:
-                spin_lock_irq(&tsk->sighand->siglock);
+                get_cpu_itimer(tsk, CPUCLOCK_VIRT, value);
-                cval = tsk->signal->it_virt_expires;
-                cinterval = tsk->signal->it_virt_incr;
-                if (!cputime_eq(cval, cputime_zero)) {
-                        struct task_cputime cputime;
-                        cputime_t utime;
-                        thread_group_cputimer(tsk, &cputime);
-                        utime = cputime.utime;
-                        if (cputime_le(cval, utime)) { /* about to fire */
-                                cval = jiffies_to_cputime(1);
-                        } else {
-                                cval = cputime_sub(cval, utime);
-                        }
-                }
-                spin_unlock_irq(&tsk->sighand->siglock);
-                cputime_to_timeval(cval, &value->it_value);
-                cputime_to_timeval(cinterval, &value->it_interval);
                break;
        case ITIMER_PROF:
-                spin_lock_irq(&tsk->sighand->siglock);
+                get_cpu_itimer(tsk, CPUCLOCK_PROF, value);
-                cval = tsk->signal->it_prof_expires;
-                cinterval = tsk->signal->it_prof_incr;
-                if (!cputime_eq(cval, cputime_zero)) {
-                        struct task_cputime times;
-                        cputime_t ptime;
-                        thread_group_cputimer(tsk, &times);
-                        ptime = cputime_add(times.utime, times.stime);
-                        if (cputime_le(cval, ptime)) { /* about to fire */
-                                cval = jiffies_to_cputime(1);
-                        } else {
-                                cval = cputime_sub(cval, ptime);
-                        }
-                }
-                spin_unlock_irq(&tsk->sighand->siglock);
-                cputime_to_timeval(cval, &value->it_value);
-                cputime_to_timeval(cinterval, &value->it_interval);
                break;
        default:
                return(-EINVAL);
@@ -123,11 +123,62 @@ enum hrtimer_restart it_real_fn(struct hrtimer *timer)
        struct signal_struct *sig =
                container_of(timer, struct signal_struct, real_timer);
+        trace_itimer_expire(ITIMER_REAL, sig->leader_pid, 0);
        kill_pid_info(SIGALRM, SEND_SIG_PRIV, sig->leader_pid);
        return HRTIMER_NORESTART;
 }
+static inline u32 cputime_sub_ns(cputime_t ct, s64 real_ns)
+{
+        struct timespec ts;
+        s64 cpu_ns;
+        cputime_to_timespec(ct, &ts);
+        cpu_ns = timespec_to_ns(&ts);
+        return (cpu_ns <= real_ns) ? 0 : cpu_ns - real_ns;
+}
+static void set_cpu_itimer(struct task_struct *tsk, unsigned int clock_id,
+                           const struct itimerval *const value,
+                           struct itimerval *const ovalue)
+{
+        cputime_t cval, nval, cinterval, ninterval;
+        s64 ns_ninterval, ns_nval;
+        struct cpu_itimer *it = &tsk->signal->it[clock_id];
+        nval = timeval_to_cputime(&value->it_value);
+        ns_nval = timeval_to_ns(&value->it_value);
+        ninterval = timeval_to_cputime(&value->it_interval);
+        ns_ninterval = timeval_to_ns(&value->it_interval);
+        it->incr_error = cputime_sub_ns(ninterval, ns_ninterval);
+        it->error = cputime_sub_ns(nval, ns_nval);
+        spin_lock_irq(&tsk->sighand->siglock);
+        cval = it->expires;
+        cinterval = it->incr;
+        if (!cputime_eq(cval, cputime_zero) ||
+            !cputime_eq(nval, cputime_zero)) {
+                if (cputime_gt(nval, cputime_zero))
+                        nval = cputime_add(nval, cputime_one_jiffy);
+                set_process_cpu_timer(tsk, clock_id, &nval, &cval);
+        }
+        it->expires = nval;
+        it->incr = ninterval;
+        trace_itimer_state(clock_id == CPUCLOCK_VIRT ?
+                           ITIMER_VIRTUAL : ITIMER_PROF, value, nval);
+        spin_unlock_irq(&tsk->sighand->siglock);
+        if (ovalue) {
+                cputime_to_timeval(cval, &ovalue->it_value);
+                cputime_to_timeval(cinterval, &ovalue->it_interval);
+        }
+}
 /*
 * Returns true if the timeval is in canonical form
 */
@@ -139,7 +190,6 @@ int do_setitimer(int which, struct itimerval *value, struct itimerval *ovalue)
        struct task_struct *tsk = current;
        struct hrtimer *timer;
        ktime_t expires;
-        cputime_t cval, cinterval, nval, ninterval;
        /*
         * Validate the timevals in value.
@@ -171,51 +221,14 @@ again:
                } else
                        tsk->signal->it_real_incr.tv64 = 0;
+                trace_itimer_state(ITIMER_REAL, value, 0);
                spin_unlock_irq(&tsk->sighand->siglock);
                break;
        case ITIMER_VIRTUAL:
-                nval = timeval_to_cputime(&value->it_value);
+                set_cpu_itimer(tsk, CPUCLOCK_VIRT, value, ovalue);
-                ninterval = timeval_to_cputime(&value->it_interval);
-                spin_lock_irq(&tsk->sighand->siglock);
-                cval = tsk->signal->it_virt_expires;
-                cinterval = tsk->signal->it_virt_incr;
-                if (!cputime_eq(cval, cputime_zero) ||
-                    !cputime_eq(nval, cputime_zero)) {
-                        if (cputime_gt(nval, cputime_zero))
-                                nval = cputime_add(nval,
-                                                   jiffies_to_cputime(1));
-                        set_process_cpu_timer(tsk, CPUCLOCK_VIRT,
-                                              &nval, &cval);
-                }
-                tsk->signal->it_virt_expires = nval;
-                tsk->signal->it_virt_incr = ninterval;
-                spin_unlock_irq(&tsk->sighand->siglock);
-                if (ovalue) {
-                        cputime_to_timeval(cval, &ovalue->it_value);
-                        cputime_to_timeval(cinterval, &ovalue->it_interval);
-                }
                break;
        case ITIMER_PROF:
-                nval = timeval_to_cputime(&value->it_value);
+                set_cpu_itimer(tsk, CPUCLOCK_PROF, value, ovalue);
-                ninterval = timeval_to_cputime(&value->it_interval);
-                spin_lock_irq(&tsk->sighand->siglock);
-                cval = tsk->signal->it_prof_expires;
-                cinterval = tsk->signal->it_prof_incr;
-                if (!cputime_eq(cval, cputime_zero) ||
-                    !cputime_eq(nval, cputime_zero)) {
-                        if (cputime_gt(nval, cputime_zero))
-                                nval = cputime_add(nval,
-                                                   jiffies_to_cputime(1));
-                        set_process_cpu_timer(tsk, CPUCLOCK_PROF,
-                                              &nval, &cval);
-                }
-                tsk->signal->it_prof_expires = nval;
-                tsk->signal->it_prof_incr = ninterval;
-                spin_unlock_irq(&tsk->sighand->siglock);
-                if (ovalue) {
-                        cputime_to_timeval(cval, &ovalue->it_value);
-                        cputime_to_timeval(cinterval, &ovalue->it_interval);
-                }
                break;
        default:
                return -EINVAL;
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index 3a29dbe7898e..8b6b8b697c68 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -59,7 +59,8 @@ static inline int is_kernel_inittext(unsigned long addr)
 static inline int is_kernel_text(unsigned long addr)
 {
-        if (addr >= (unsigned long)_stext && addr <= (unsigned long)_etext)
+        if ((addr >= (unsigned long)_stext && addr <= (unsigned long)_etext) ||
+            arch_is_kernel_text(addr))
                return 1;
        return in_gate_area_no_task(addr);
 }
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index ef177d653b2c..cfadc1291d0b 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1321,7 +1321,7 @@ static int __kprobes show_kprobe_addr(struct seq_file *pi, void *v)
        return 0;
 }
-static struct seq_operations kprobes_seq_ops = {
+static const struct seq_operations kprobes_seq_ops = {
        .start = kprobe_seq_start,
        .next  = kprobe_seq_next,
        .stop  = kprobe_seq_stop,
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index f74d2d7aa605..3815ac1d58b2 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -578,6 +578,9 @@ static int static_obj(void *obj)
        if ((addr >= start) && (addr < end))
                return 1;
+        if (arch_is_kernel_data(addr))
+                return 1;
 #ifdef CONFIG_SMP
        /*
         * percpu var?
diff --git a/kernel/lockdep_proc.c b/kernel/lockdep_proc.c
index d4b3dbc79fdb..d4aba4f3584c 100644
--- a/kernel/lockdep_proc.c
+++ b/kernel/lockdep_proc.c
@@ -594,7 +594,7 @@ static int ls_show(struct seq_file *m, void *v)
        return 0;
 }
-static struct seq_operations lockstat_ops = {
+static const struct seq_operations lockstat_ops = {
        .start  = ls_start,
        .next   = ls_next,
        .stop   = ls_stop,
diff --git a/kernel/module.c b/kernel/module.c
index b6ee424245dd..fe748a86d452 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -47,6 +47,7 @@
 #include <linux/rculist.h>
 #include <asm/uaccess.h>
 #include <asm/cacheflush.h>
+#include <asm/mmu_context.h>
 #include <linux/license.h>
 #include <asm/sections.h>
 #include <linux/tracepoint.h>
@@ -1535,6 +1536,10 @@ static void free_module(struct module *mod)
        /* Finally, free the core (containing the module structure) */
        module_free(mod, mod->module_core);
+#ifdef CONFIG_MPU
+        update_protections(current->mm);
+#endif
 }
 void *__symbol_get(const char *symbol)
@@ -1792,6 +1797,17 @@ static void setup_modinfo(struct module *mod, Elf_Shdr *sechdrs,
        }
 }
+static void free_modinfo(struct module *mod)
+{
+        struct module_attribute *attr;
+        int i;
+        for (i = 0; (attr = modinfo_attrs[i]); i++) {
+                if (attr->free)
+                        attr->free(mod);
+        }
+}
 #ifdef CONFIG_KALLSYMS
 /* lookup symbol in given range of kernel_symbols */
@@ -1857,13 +1873,93 @@ static char elf_type(const Elf_Sym *sym,
        return '?';
 }
+static bool is_core_symbol(const Elf_Sym *src, const Elf_Shdr *sechdrs,
+                           unsigned int shnum)
+{
+        const Elf_Shdr *sec;
+        if (src->st_shndx == SHN_UNDEF
+            || src->st_shndx >= shnum
+            || !src->st_name)
+                return false;
+        sec = sechdrs + src->st_shndx;
+        if (!(sec->sh_flags & SHF_ALLOC)
+#ifndef CONFIG_KALLSYMS_ALL
+            || !(sec->sh_flags & SHF_EXECINSTR)
+#endif
+            || (sec->sh_entsize & INIT_OFFSET_MASK))
+                return false;
+        return true;
+}
+static unsigned long layout_symtab(struct module *mod,
+                                   Elf_Shdr *sechdrs,
+                                   unsigned int symindex,
+                                   unsigned int strindex,
+                                   const Elf_Ehdr *hdr,
+                                   const char *secstrings,
+                                   unsigned long *pstroffs,
+                                   unsigned long *strmap)
+{
+        unsigned long symoffs;
+        Elf_Shdr *symsect = sechdrs + symindex;
+        Elf_Shdr *strsect = sechdrs + strindex;
+        const Elf_Sym *src;
+        const char *strtab;
+        unsigned int i, nsrc, ndst;
+        /* Put symbol section at end of init part of module. */
+        symsect->sh_flags |= SHF_ALLOC;
+        symsect->sh_entsize = get_offset(mod, &mod->init_size, symsect,
+                                         symindex) | INIT_OFFSET_MASK;
+        DEBUGP("\t%s\n", secstrings + symsect->sh_name);
+        src = (void *)hdr + symsect->sh_offset;
+        nsrc = symsect->sh_size / sizeof(*src);
+        strtab = (void *)hdr + strsect->sh_offset;
+        for (ndst = i = 1; i < nsrc; ++i, ++src)
+                if (is_core_symbol(src, sechdrs, hdr->e_shnum)) {
+                        unsigned int j = src->st_name;
+                        while(!__test_and_set_bit(j, strmap) && strtab[j])
+                                ++j;
+                        ++ndst;
+                }
+        /* Append room for core symbols at end of core part. */
+        symoffs = ALIGN(mod->core_size, symsect->sh_addralign ?: 1);
+        mod->core_size = symoffs + ndst * sizeof(Elf_Sym);
+        /* Put string table section at end of init part of module. */
+        strsect->sh_flags |= SHF_ALLOC;
+        strsect->sh_entsize = get_offset(mod, &mod->init_size, strsect,
+                                         strindex) | INIT_OFFSET_MASK;
+        DEBUGP("\t%s\n", secstrings + strsect->sh_name);
+        /* Append room for core symbols' strings at end of core part. */
+        *pstroffs = mod->core_size;
+        __set_bit(0, strmap);
+        mod->core_size += bitmap_weight(strmap, strsect->sh_size);
+        return symoffs;
+}
 static void add_kallsyms(struct module *mod,
                         Elf_Shdr *sechdrs,
+                         unsigned int shnum,
                         unsigned int symindex,
                         unsigned int strindex,
-                         const char *secstrings)
+                         unsigned long symoffs,
+                         unsigned long stroffs,
+                         const char *secstrings,
+                         unsigned long *strmap)
 {
-        unsigned int i;
+        unsigned int i, ndst;
+        const Elf_Sym *src;
+        Elf_Sym *dst;
+        char *s;
        mod->symtab = (void *)sechdrs[symindex].sh_addr;
        mod->num_symtab = sechdrs[symindex].sh_size / sizeof(Elf_Sym);
@@ -1873,13 +1969,44 @@ static void add_kallsyms(struct module *mod,
        for (i = 0; i < mod->num_symtab; i++)
                mod->symtab[i].st_info
                        = elf_type(&mod->symtab[i], sechdrs, secstrings, mod);
+        mod->core_symtab = dst = mod->module_core + symoffs;
+        src = mod->symtab;
+        *dst = *src;
+        for (ndst = i = 1; i < mod->num_symtab; ++i, ++src) {
+                if (!is_core_symbol(src, sechdrs, shnum))
+                        continue;
+                dst[ndst] = *src;
+                dst[ndst].st_name = bitmap_weight(strmap, dst[ndst].st_name);
+                ++ndst;
+        }
+        mod->core_num_syms = ndst;
+        mod->core_strtab = s = mod->module_core + stroffs;
+        for (*s = 0, i = 1; i < sechdrs[strindex].sh_size; ++i)
+                if (test_bit(i, strmap))
+                        *++s = mod->strtab[i];
 }
 #else
+static inline unsigned long layout_symtab(struct module *mod,
+                                          Elf_Shdr *sechdrs,
+                                          unsigned int symindex,
+                                          unsigned int strindex,
+                                          const Elf_Hdr *hdr,
+                                          const char *secstrings,
+                                          unsigned long *pstroffs,
+                                          unsigned long *strmap)
+{
+}
 static inline void add_kallsyms(struct module *mod,
                                Elf_Shdr *sechdrs,
+                                unsigned int shnum,
                                unsigned int symindex,
                                unsigned int strindex,
-                                const char *secstrings)
+                                unsigned long symoffs,
+                                unsigned long stroffs,
+                                const char *secstrings,
+                                const unsigned long *strmap)
 {
 }
 #endif /* CONFIG_KALLSYMS */
@@ -1954,6 +2081,9 @@ static noinline struct module *load_module(void __user *umod,
        struct module *mod;
        long err = 0;
        void *percpu = NULL, *ptr = NULL; /* Stops spurious gcc warning */
+#ifdef CONFIG_KALLSYMS
+        unsigned long symoffs, stroffs, *strmap;
+#endif
        mm_segment_t old_fs;
        DEBUGP("load_module: umod=%p, len=%lu, uargs=%p\n",
@@ -2035,11 +2165,6 @@ static noinline struct module *load_module(void __user *umod,
        /* Don't keep modinfo and version sections. */
        sechdrs[infoindex].sh_flags &= ~(unsigned long)SHF_ALLOC;
        sechdrs[versindex].sh_flags &= ~(unsigned long)SHF_ALLOC;
-#ifdef CONFIG_KALLSYMS
-        /* Keep symbol and string tables for decoding later. */
-        sechdrs[symindex].sh_flags |= SHF_ALLOC;
-        sechdrs[strindex].sh_flags |= SHF_ALLOC;
-#endif
        /* Check module struct version now, before we try to use module. */
        if (!check_modstruct_version(sechdrs, versindex, mod)) {
@@ -2075,6 +2200,13 @@ static noinline struct module *load_module(void __user *umod,
                goto free_hdr;
        }
+        strmap = kzalloc(BITS_TO_LONGS(sechdrs[strindex].sh_size)
+                         * sizeof(long), GFP_KERNEL);
+        if (!strmap) {
+                err = -ENOMEM;
+                goto free_mod;
+        }
        if (find_module(mod->name)) {
                err = -EEXIST;
                goto free_mod;
@@ -2104,6 +2236,8 @@ static noinline struct module *load_module(void __user *umod,
           this is done generically; there doesn't appear to be any
           special cases for the architectures. */
        layout_sections(mod, hdr, sechdrs, secstrings);
+        symoffs = layout_symtab(mod, sechdrs, symindex, strindex, hdr,
+                                secstrings, &stroffs, strmap);
        /* Do the allocs. */
        ptr = module_alloc_update_bounds(mod->core_size);
@@ -2308,7 +2442,10 @@ static noinline struct module *load_module(void __user *umod,
        percpu_modcopy(mod->percpu, (void *)sechdrs[pcpuindex].sh_addr,
                       sechdrs[pcpuindex].sh_size);
-        add_kallsyms(mod, sechdrs, symindex, strindex, secstrings);
+        add_kallsyms(mod, sechdrs, hdr->e_shnum, symindex, strindex,
+                     symoffs, stroffs, secstrings, strmap);
+        kfree(strmap);
+        strmap = NULL;
        if (!mod->taints) {
                struct _ddebug *debug;
@@ -2380,13 +2517,14 @@ static noinline struct module *load_module(void __user *umod,
        synchronize_sched();
        module_arch_cleanup(mod);
 cleanup:
+        free_modinfo(mod);
        kobject_del(&mod->mkobj.kobj);
        kobject_put(&mod->mkobj.kobj);
 free_unload:
        module_unload_free(mod);
 #if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP)
- free_init:
        percpu_modfree(mod->refptr);
+ free_init:
 #endif
        module_free(mod, mod->module_init);
 free_core:
@@ -2397,6 +2535,7 @@ static noinline struct module *load_module(void __user *umod,
                percpu_modfree(percpu);
 free_mod:
        kfree(args);
+        kfree(strmap);
 free_hdr:
        vfree(hdr);
        return ERR_PTR(err);
@@ -2486,6 +2625,11 @@ SYSCALL_DEFINE3(init_module, void __user *, umod,
        /* Drop initial reference. */
        module_put(mod);
        trim_init_extable(mod);
+#ifdef CONFIG_KALLSYMS
+        mod->num_symtab = mod->core_num_syms;
+        mod->symtab = mod->core_symtab;
+        mod->strtab = mod->core_strtab;
+#endif
        module_free(mod, mod->module_init);
        mod->module_init = NULL;
        mod->init_size = 0;
@@ -2947,7 +3091,6 @@ void module_layout(struct module *mod,
                   struct modversion_info *ver,
                   struct kernel_param *kp,
                   struct kernel_symbol *ks,
-                   struct marker *marker,
                   struct tracepoint *tp)
 {
 }
diff --git a/kernel/ns_cgroup.c b/kernel/ns_cgroup.c
index 5aa854f9e5ae..2a5dfec8efe0 100644
--- a/kernel/ns_cgroup.c
+++ b/kernel/ns_cgroup.c
@@ -42,8 +42,8 @@ int ns_cgroup_clone(struct task_struct *task, struct pid *pid)
 *       (hence either you are in the same cgroup as task, or in an
 *        ancestor cgroup thereof)
 */
-static int ns_can_attach(struct cgroup_subsys *ss,
+static int ns_can_attach(struct cgroup_subsys *ss, struct cgroup *new_cgroup,
-                struct cgroup *new_cgroup, struct task_struct *task)
+                         struct task_struct *task, bool threadgroup)
 {
        if (current != task) {
                if (!capable(CAP_SYS_ADMIN))
@@ -56,6 +56,18 @@ static int ns_can_attach(struct cgroup_subsys *ss,
        if (!cgroup_is_descendant(new_cgroup, task))
                return -EPERM;
+        if (threadgroup) {
+                struct task_struct *c;
+                rcu_read_lock();
+                list_for_each_entry_rcu(c, &task->thread_group, thread_group) {
+                        if (!cgroup_is_descendant(new_cgroup, c)) {
+                                rcu_read_unlock();
+                                return -EPERM;
+                        }
+                }
+                rcu_read_unlock();
+        }
        return 0;
 }
diff --git a/kernel/panic.c b/kernel/panic.c
index 512ab73b0ca3..bcdef26e3332 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -177,7 +177,7 @@ static const struct tnt tnts[] = {
 *  'W' - Taint on warning.
 *  'C' - modules from drivers/staging are loaded.
 *
- *      The string is overwritten by the next call to print_taint().
+ *      The string is overwritten by the next call to print_tainted().
 */
 const char *print_tainted(void)
 {
diff --git a/kernel/params.c b/kernel/params.c
index 7f6912ced2ba..9da58eabdcb2 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -23,6 +23,7 @@
 #include <linux/device.h>
 #include <linux/err.h>
 #include <linux/slab.h>
+#include <linux/ctype.h>
 #if 0
 #define DEBUGP printk
@@ -87,7 +88,7 @@ static char *next_arg(char *args, char **param, char **val)
        }
        for (i = 0; args[i]; i++) {
-                if (args[i] == ' ' && !in_quote)
+                if (isspace(args[i]) && !in_quote)
                        break;
                if (equals == 0) {
                        if (args[i] == '=')
@@ -121,7 +122,7 @@ static char *next_arg(char *args, char **param, char **val)
                next = args + i;
        /* Chew up trailing spaces. */
-        while (*next == ' ')
+        while (isspace(*next))
                next++;
        return next;
 }
@@ -138,7 +139,7 @@ int parse_args(const char *name,
        DEBUGP("Parsing ARGS: %s\n", args);
        /* Chew leading spaces */
-        while (*args == ' ')
+        while (isspace(*args))
                args++;
        while (*args) {
diff --git a/kernel/perf_counter.c b/kernel/perf_event.c
index cc768ab81ac8..76ac4db405e9 100644
--- a/kernel/perf_counter.c
+++ b/kernel/perf_event.c
@@ -1,12 +1,12 @@
 /*
- * Performance counter core code
+ * Performance events core code:
 *
 *  Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de>
 *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
 *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
 *  Copyright  �  2009 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
 *
- *  For licensing details see kernel-base/COPYING
+ * For licensing details see kernel-base/COPYING
 */
 #include <linux/fs.h>
@@ -26,66 +26,66 @@
 #include <linux/syscalls.h>
 #include <linux/anon_inodes.h>
 #include <linux/kernel_stat.h>
-#include <linux/perf_counter.h>
+#include <linux/perf_event.h>
 #include <asm/irq_regs.h>
 /*
- * Each CPU has a list of per CPU counters:
+ * Each CPU has a list of per CPU events:
 */
 DEFINE_PER_CPU(struct perf_cpu_context, perf_cpu_context);
-int perf_max_counters __read_mostly = 1;
+int perf_max_events __read_mostly = 1;
 static int perf_reserved_percpu __read_mostly;
 static int perf_overcommit __read_mostly = 1;
-static atomic_t nr_counters __read_mostly;
+static atomic_t nr_events __read_mostly;
-static atomic_t nr_mmap_counters __read_mostly;
+static atomic_t nr_mmap_events __read_mostly;
-static atomic_t nr_comm_counters __read_mostly;
+static atomic_t nr_comm_events __read_mostly;
-static atomic_t nr_task_counters __read_mostly;
+static atomic_t nr_task_events __read_mostly;
 /*
- * perf counter paranoia level:
+ * perf event paranoia level:
 *  -1 - not paranoid at all
 *   0 - disallow raw tracepoint access for unpriv
- *   1 - disallow cpu counters for unpriv
+ *   1 - disallow cpu events for unpriv
 *   2 - disallow kernel profiling for unpriv
 */
-int sysctl_perf_counter_paranoid __read_mostly = 1;
+int sysctl_perf_event_paranoid __read_mostly = 1;
 static inline bool perf_paranoid_tracepoint_raw(void)
 {
-        return sysctl_perf_counter_paranoid > -1;
+        return sysctl_perf_event_paranoid > -1;
 }
 static inline bool perf_paranoid_cpu(void)
 {
-        return sysctl_perf_counter_paranoid > 0;
+        return sysctl_perf_event_paranoid > 0;
 }
 static inline bool perf_paranoid_kernel(void)
 {
-        return sysctl_perf_counter_paranoid > 1;
+        return sysctl_perf_event_paranoid > 1;
 }
-int sysctl_perf_counter_mlock __read_mostly = 512; /* 'free' kb per user */
+int sysctl_perf_event_mlock __read_mostly = 512; /* 'free' kb per user */
 /*
- * max perf counter sample rate
+ * max perf event sample rate
 */
-int sysctl_perf_counter_sample_rate __read_mostly = 100000;
+int sysctl_perf_event_sample_rate __read_mostly = 100000;
-static atomic64_t perf_counter_id;
+static atomic64_t perf_event_id;
 /*
- * Lock for (sysadmin-configurable) counter reservations:
+ * Lock for (sysadmin-configurable) event reservations:
 */
 static DEFINE_SPINLOCK(perf_resource_lock);
 /*
 * Architecture provided APIs - weak aliases:
 */
-extern __weak const struct pmu *hw_perf_counter_init(struct perf_counter *counter)
+extern __weak const struct pmu *hw_perf_event_init(struct perf_event *event)
 {
        return NULL;
 }
@@ -93,18 +93,18 @@ extern __weak const struct pmu *hw_perf_counter_init(struct perf_counter *counte
 void __weak hw_perf_disable(void)               { barrier(); }
 void __weak hw_perf_enable(void)                { barrier(); }
-void __weak hw_perf_counter_setup(int cpu)      { barrier(); }
+void __weak hw_perf_event_setup(int cpu)        { barrier(); }
-void __weak hw_perf_counter_setup_online(int cpu)       { barrier(); }
+void __weak hw_perf_event_setup_online(int cpu) { barrier(); }
 int __weak
-hw_perf_group_sched_in(struct perf_counter *group_leader,
+hw_perf_group_sched_in(struct perf_event *group_leader,
               struct perf_cpu_context *cpuctx,
-               struct perf_counter_context *ctx, int cpu)
+               struct perf_event_context *ctx, int cpu)
 {
        return 0;
 }
-void __weak perf_counter_print_debug(void)      { }
+void __weak perf_event_print_debug(void)        { }
 static DEFINE_PER_CPU(int, perf_disable_count);
@@ -130,20 +130,20 @@ void perf_enable(void)
                hw_perf_enable();
 }
-static void get_ctx(struct perf_counter_context *ctx)
+static void get_ctx(struct perf_event_context *ctx)
 {
        WARN_ON(!atomic_inc_not_zero(&ctx->refcount));
 }
 static void free_ctx(struct rcu_head *head)
 {
-        struct perf_counter_context *ctx;
+        struct perf_event_context *ctx;
-        ctx = container_of(head, struct perf_counter_context, rcu_head);
+        ctx = container_of(head, struct perf_event_context, rcu_head);
        kfree(ctx);
 }
-static void put_ctx(struct perf_counter_context *ctx)
+static void put_ctx(struct perf_event_context *ctx)
 {
        if (atomic_dec_and_test(&ctx->refcount)) {
                if (ctx->parent_ctx)
@@ -154,7 +154,7 @@ static void put_ctx(struct perf_counter_context *ctx)
        }
 }
-static void unclone_ctx(struct perf_counter_context *ctx)
+static void unclone_ctx(struct perf_event_context *ctx)
 {
        if (ctx->parent_ctx) {
                put_ctx(ctx->parent_ctx);
@@ -163,37 +163,37 @@ static void unclone_ctx(struct perf_counter_context *ctx)
 }
 /*
- * If we inherit counters we want to return the parent counter id
+ * If we inherit events we want to return the parent event id
 * to userspace.
 */
-static u64 primary_counter_id(struct perf_counter *counter)
+static u64 primary_event_id(struct perf_event *event)
 {
-        u64 id = counter->id;
+        u64 id = event->id;
-        if (counter->parent)
+        if (event->parent)
-                id = counter->parent->id;
+                id = event->parent->id;
        return id;
 }
 /*
- * Get the perf_counter_context for a task and lock it.
+ * Get the perf_event_context for a task and lock it.
 * This has to cope with with the fact that until it is locked,
 * the context could get moved to another task.
 */
-static struct perf_counter_context *
+static struct perf_event_context *
 perf_lock_task_context(struct task_struct *task, unsigned long *flags)
 {
-        struct perf_counter_context *ctx;
+        struct perf_event_context *ctx;
        rcu_read_lock();
 retry:
-        ctx = rcu_dereference(task->perf_counter_ctxp);
+        ctx = rcu_dereference(task->perf_event_ctxp);
        if (ctx) {
                /*
                 * If this context is a clone of another, it might
                 * get swapped for another underneath us by
-                 * perf_counter_task_sched_out, though the
+                 * perf_event_task_sched_out, though the
                 * rcu_read_lock() protects us from any context
                 * getting freed.  Lock the context and check if it
                 * got swapped before we could get the lock, and retry
@@ -201,7 +201,7 @@ perf_lock_task_context(struct task_struct *task, unsigned long *flags)
                 * can't get swapped on us any more.
                 */
                spin_lock_irqsave(&ctx->lock, *flags);
-                if (ctx != rcu_dereference(task->perf_counter_ctxp)) {
+                if (ctx != rcu_dereference(task->perf_event_ctxp)) {
                        spin_unlock_irqrestore(&ctx->lock, *flags);
                        goto retry;
                }
@@ -220,9 +220,9 @@ perf_lock_task_context(struct task_struct *task, unsigned long *flags)
 * can't get swapped to another task.  This also increments its
 * reference count so that the context can't get freed.
 */
-static struct perf_counter_context *perf_pin_task_context(struct task_struct *task)
+static struct perf_event_context *perf_pin_task_context(struct task_struct *task)
 {
-        struct perf_counter_context *ctx;
+        struct perf_event_context *ctx;
        unsigned long flags;
        ctx = perf_lock_task_context(task, &flags);
@@ -233,7 +233,7 @@ static struct perf_counter_context *perf_pin_task_context(struct task_struct *ta
        return ctx;
 }
-static void perf_unpin_context(struct perf_counter_context *ctx)
+static void perf_unpin_context(struct perf_event_context *ctx)
 {
        unsigned long flags;
@@ -244,123 +244,122 @@ static void perf_unpin_context(struct perf_counter_context *ctx)
 }
 /*
- * Add a counter from the lists for its context.
+ * Add a event from the lists for its context.
 * Must be called with ctx->mutex and ctx->lock held.
 */
 static void
-list_add_counter(struct perf_counter *counter, struct perf_counter_context *ctx)
+list_add_event(struct perf_event *event, struct perf_event_context *ctx)
 {
-        struct perf_counter *group_leader = counter->group_leader;
+        struct perf_event *group_leader = event->group_leader;
        /*
-         * Depending on whether it is a standalone or sibling counter,
+         * Depending on whether it is a standalone or sibling event,
-         * add it straight to the context's counter list, or to the group
+         * add it straight to the context's event list, or to the group
         * leader's sibling list:
         */
-        if (group_leader == counter)
+        if (group_leader == event)
-                list_add_tail(&counter->list_entry, &ctx->counter_list);
+                list_add_tail(&event->group_entry, &ctx->group_list);
        else {
-                list_add_tail(&counter->list_entry, &group_leader->sibling_list);
+                list_add_tail(&event->group_entry, &group_leader->sibling_list);
                group_leader->nr_siblings++;
        }
-        list_add_rcu(&counter->event_entry, &ctx->event_list);
+        list_add_rcu(&event->event_entry, &ctx->event_list);
-        ctx->nr_counters++;
+        ctx->nr_events++;
-        if (counter->attr.inherit_stat)
+        if (event->attr.inherit_stat)
                ctx->nr_stat++;
 }
 /*
- * Remove a counter from the lists for its context.
+ * Remove a event from the lists for its context.
 * Must be called with ctx->mutex and ctx->lock held.
 */
 static void
-list_del_counter(struct perf_counter *counter, struct perf_counter_context *ctx)
+list_del_event(struct perf_event *event, struct perf_event_context *ctx)
 {
-        struct perf_counter *sibling, *tmp;
+        struct perf_event *sibling, *tmp;
-        if (list_empty(&counter->list_entry))
+        if (list_empty(&event->group_entry))
                return;
-        ctx->nr_counters--;
+        ctx->nr_events--;
-        if (counter->attr.inherit_stat)
+        if (event->attr.inherit_stat)
                ctx->nr_stat--;
-        list_del_init(&counter->list_entry);
+        list_del_init(&event->group_entry);
-        list_del_rcu(&counter->event_entry);
+        list_del_rcu(&event->event_entry);
-        if (counter->group_leader != counter)
+        if (event->group_leader != event)
-                counter->group_leader->nr_siblings--;
+                event->group_leader->nr_siblings--;
        /*
-         * If this was a group counter with sibling counters then
+         * If this was a group event with sibling events then
-         * upgrade the siblings to singleton counters by adding them
+         * upgrade the siblings to singleton events by adding them
         * to the context list directly:
         */
-        list_for_each_entry_safe(sibling, tmp,
+        list_for_each_entry_safe(sibling, tmp, &event->sibling_list, group_entry) {
-                                 &counter->sibling_list, list_entry) {
-                list_move_tail(&sibling->list_entry, &ctx->counter_list);
+                list_move_tail(&sibling->group_entry, &ctx->group_list);
                sibling->group_leader = sibling;
        }
 }
 static void
-counter_sched_out(struct perf_counter *counter,
+event_sched_out(struct perf_event *event,
                  struct perf_cpu_context *cpuctx,
-                  struct perf_counter_context *ctx)
+                  struct perf_event_context *ctx)
 {
-        if (counter->state != PERF_COUNTER_STATE_ACTIVE)
+        if (event->state != PERF_EVENT_STATE_ACTIVE)
                return;
-        counter->state = PERF_COUNTER_STATE_INACTIVE;
+        event->state = PERF_EVENT_STATE_INACTIVE;
-        if (counter->pending_disable) {
+        if (event->pending_disable) {
-                counter->pending_disable = 0;
+                event->pending_disable = 0;
-                counter->state = PERF_COUNTER_STATE_OFF;
+                event->state = PERF_EVENT_STATE_OFF;
        }
-        counter->tstamp_stopped = ctx->time;
+        event->tstamp_stopped = ctx->time;
-        counter->pmu->disable(counter);
+        event->pmu->disable(event);
-        counter->oncpu = -1;
+        event->oncpu = -1;
-        if (!is_software_counter(counter))
+        if (!is_software_event(event))
                cpuctx->active_oncpu--;
        ctx->nr_active--;
-        if (counter->attr.exclusive || !cpuctx->active_oncpu)
+        if (event->attr.exclusive || !cpuctx->active_oncpu)
                cpuctx->exclusive = 0;
 }
 static void
-group_sched_out(struct perf_counter *group_counter,
+group_sched_out(struct perf_event *group_event,
                struct perf_cpu_context *cpuctx,
-                struct perf_counter_context *ctx)
+                struct perf_event_context *ctx)
 {
-        struct perf_counter *counter;
+        struct perf_event *event;
-        if (group_counter->state != PERF_COUNTER_STATE_ACTIVE)
+        if (group_event->state != PERF_EVENT_STATE_ACTIVE)
                return;
-        counter_sched_out(group_counter, cpuctx, ctx);
+        event_sched_out(group_event, cpuctx, ctx);
        /*
         * Schedule out siblings (if any):
         */
-        list_for_each_entry(counter, &group_counter->sibling_list, list_entry)
+        list_for_each_entry(event, &group_event->sibling_list, group_entry)
-                counter_sched_out(counter, cpuctx, ctx);
+                event_sched_out(event, cpuctx, ctx);
-        if (group_counter->attr.exclusive)
+        if (group_event->attr.exclusive)
                cpuctx->exclusive = 0;
 }
 /*
- * Cross CPU call to remove a performance counter
+ * Cross CPU call to remove a performance event
 *
- * We disable the counter on the hardware level first. After that we
+ * We disable the event on the hardware level first. After that we
 * remove it from the context list.
 */
-static void __perf_counter_remove_from_context(void *info)
+static void __perf_event_remove_from_context(void *info)
 {
        struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
-        struct perf_counter *counter = info;
+        struct perf_event *event = info;
-        struct perf_counter_context *ctx = counter->ctx;
+        struct perf_event_context *ctx = event->ctx;
        /*
         * If this is a task context, we need to check whether it is
@@ -373,22 +372,22 @@ static void __perf_counter_remove_from_context(void *info)
        spin_lock(&ctx->lock);
        /*
         * Protect the list operation against NMI by disabling the
-         * counters on a global level.
+         * events on a global level.
         */
        perf_disable();
-        counter_sched_out(counter, cpuctx, ctx);
+        event_sched_out(event, cpuctx, ctx);
-        list_del_counter(counter, ctx);
+        list_del_event(event, ctx);
        if (!ctx->task) {
                /*
-                 * Allow more per task counters with respect to the
+                 * Allow more per task events with respect to the
                 * reservation:
                 */
                cpuctx->max_pertask =
-                        min(perf_max_counters - ctx->nr_counters,
+                        min(perf_max_events - ctx->nr_events,
-                            perf_max_counters - perf_reserved_percpu);
+                            perf_max_events - perf_reserved_percpu);
        }
        perf_enable();
@@ -397,56 +396,56 @@ static void __perf_counter_remove_from_context(void *info)
 /*
- * Remove the counter from a task's (or a CPU's) list of counters.
+ * Remove the event from a task's (or a CPU's) list of events.
 *
 * Must be called with ctx->mutex held.
 *
- * CPU counters are removed with a smp call. For task counters we only
+ * CPU events are removed with a smp call. For task events we only
 * call when the task is on a CPU.
 *
- * If counter->ctx is a cloned context, callers must make sure that
+ * If event->ctx is a cloned context, callers must make sure that
- * every task struct that counter->ctx->task could possibly point to
+ * every task struct that event->ctx->task could possibly point to
 * remains valid.  This is OK when called from perf_release since
 * that only calls us on the top-level context, which can't be a clone.
- * When called from perf_counter_exit_task, it's OK because the
+ * When called from perf_event_exit_task, it's OK because the
 * context has been detached from its task.
 */
-static void perf_counter_remove_from_context(struct perf_counter *counter)
+static void perf_event_remove_from_context(struct perf_event *event)
 {
-        struct perf_counter_context *ctx = counter->ctx;
+        struct perf_event_context *ctx = event->ctx;
        struct task_struct *task = ctx->task;
        if (!task) {
                /*
-                 * Per cpu counters are removed via an smp call and
+                 * Per cpu events are removed via an smp call and
                 * the removal is always sucessful.
                 */
-                smp_call_function_single(counter->cpu,
+                smp_call_function_single(event->cpu,
-                                         __perf_counter_remove_from_context,
+                                         __perf_event_remove_from_context,
-                                         counter, 1);
+                                         event, 1);
                return;
        }
 retry:
-        task_oncpu_function_call(task, __perf_counter_remove_from_context,
+        task_oncpu_function_call(task, __perf_event_remove_from_context,
-                                 counter);
+                                 event);
        spin_lock_irq(&ctx->lock);
        /*
         * If the context is active we need to retry the smp call.
         */
-        if (ctx->nr_active && !list_empty(&counter->list_entry)) {
+        if (ctx->nr_active && !list_empty(&event->group_entry)) {
                spin_unlock_irq(&ctx->lock);
                goto retry;
        }
        /*
         * The lock prevents that this context is scheduled in so we
-         * can remove the counter safely, if the call above did not
+         * can remove the event safely, if the call above did not
         * succeed.
         */
-        if (!list_empty(&counter->list_entry)) {
+        if (!list_empty(&event->group_entry)) {
-                list_del_counter(counter, ctx);
+                list_del_event(event, ctx);
        }
        spin_unlock_irq(&ctx->lock);
 }
@@ -459,7 +458,7 @@ static inline u64 perf_clock(void)
 /*
 * Update the record of the current time in a context.
 */
-static void update_context_time(struct perf_counter_context *ctx)
+static void update_context_time(struct perf_event_context *ctx)
 {
        u64 now = perf_clock();
@@ -468,51 +467,51 @@ static void update_context_time(struct perf_counter_context *ctx)
 }
 /*
- * Update the total_time_enabled and total_time_running fields for a counter.
+ * Update the total_time_enabled and total_time_running fields for a event.
 */
-static void update_counter_times(struct perf_counter *counter)
+static void update_event_times(struct perf_event *event)
 {
-        struct perf_counter_context *ctx = counter->ctx;
+        struct perf_event_context *ctx = event->ctx;
        u64 run_end;
-        if (counter->state < PERF_COUNTER_STATE_INACTIVE ||
+        if (event->state < PERF_EVENT_STATE_INACTIVE ||
-            counter->group_leader->state < PERF_COUNTER_STATE_INACTIVE)
+            event->group_leader->state < PERF_EVENT_STATE_INACTIVE)
                return;
-        counter->total_time_enabled = ctx->time - counter->tstamp_enabled;
+        event->total_time_enabled = ctx->time - event->tstamp_enabled;
-        if (counter->state == PERF_COUNTER_STATE_INACTIVE)
+        if (event->state == PERF_EVENT_STATE_INACTIVE)
-                run_end = counter->tstamp_stopped;
+                run_end = event->tstamp_stopped;
        else
                run_end = ctx->time;
-        counter->total_time_running = run_end - counter->tstamp_running;
+        event->total_time_running = run_end - event->tstamp_running;
 }
 /*
- * Update total_time_enabled and total_time_running for all counters in a group.
+ * Update total_time_enabled and total_time_running for all events in a group.
 */
-static void update_group_times(struct perf_counter *leader)
+static void update_group_times(struct perf_event *leader)
 {
-        struct perf_counter *counter;
+        struct perf_event *event;
-        update_counter_times(leader);
+        update_event_times(leader);
-        list_for_each_entry(counter, &leader->sibling_list, list_entry)
+        list_for_each_entry(event, &leader->sibling_list, group_entry)
-                update_counter_times(counter);
+                update_event_times(event);
 }
 /*
- * Cross CPU call to disable a performance counter
+ * Cross CPU call to disable a performance event
 */
-static void __perf_counter_disable(void *info)
+static void __perf_event_disable(void *info)
 {
-        struct perf_counter *counter = info;
+        struct perf_event *event = info;
        struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
-        struct perf_counter_context *ctx = counter->ctx;
+        struct perf_event_context *ctx = event->ctx;
        /*
-         * If this is a per-task counter, need to check whether this
+         * If this is a per-task event, need to check whether this
-         * counter's task is the current task on this cpu.
+         * event's task is the current task on this cpu.
         */
        if (ctx->task && cpuctx->task_ctx != ctx)
                return;
@@ -520,57 +519,57 @@ static void __perf_counter_disable(void *info)
        spin_lock(&ctx->lock);
        /*
-         * If the counter is on, turn it off.
+         * If the event is on, turn it off.
         * If it is in error state, leave it in error state.
         */
-        if (counter->state >= PERF_COUNTER_STATE_INACTIVE) {
+        if (event->state >= PERF_EVENT_STATE_INACTIVE) {
                update_context_time(ctx);
-                update_group_times(counter);
+                update_group_times(event);
-                if (counter == counter->group_leader)
+                if (event == event->group_leader)
-                        group_sched_out(counter, cpuctx, ctx);
+                        group_sched_out(event, cpuctx, ctx);
                else
-                        counter_sched_out(counter, cpuctx, ctx);
+                        event_sched_out(event, cpuctx, ctx);
-                counter->state = PERF_COUNTER_STATE_OFF;
+                event->state = PERF_EVENT_STATE_OFF;
        }
        spin_unlock(&ctx->lock);
 }
 /*
- * Disable a counter.
+ * Disable a event.
 *
- * If counter->ctx is a cloned context, callers must make sure that
+ * If event->ctx is a cloned context, callers must make sure that
- * every task struct that counter->ctx->task could possibly point to
+ * every task struct that event->ctx->task could possibly point to
 * remains valid.  This condition is satisifed when called through
- * perf_counter_for_each_child or perf_counter_for_each because they
+ * perf_event_for_each_child or perf_event_for_each because they
- * hold the top-level counter's child_mutex, so any descendant that
+ * hold the top-level event's child_mutex, so any descendant that
- * goes to exit will block in sync_child_counter.
+ * goes to exit will block in sync_child_event.
- * When called from perf_pending_counter it's OK because counter->ctx
+ * When called from perf_pending_event it's OK because event->ctx
 * is the current context on this CPU and preemption is disabled,
- * hence we can't get into perf_counter_task_sched_out for this context.
+ * hence we can't get into perf_event_task_sched_out for this context.
 */
-static void perf_counter_disable(struct perf_counter *counter)
+static void perf_event_disable(struct perf_event *event)
 {
-        struct perf_counter_context *ctx = counter->ctx;
+        struct perf_event_context *ctx = event->ctx;
        struct task_struct *task = ctx->task;
        if (!task) {
                /*
-                 * Disable the counter on the cpu that it's on
+                 * Disable the event on the cpu that it's on
                 */
-                smp_call_function_single(counter->cpu, __perf_counter_disable,
+                smp_call_function_single(event->cpu, __perf_event_disable,
-                                         counter, 1);
+                                         event, 1);
                return;
        }
 retry:
-        task_oncpu_function_call(task, __perf_counter_disable, counter);
+        task_oncpu_function_call(task, __perf_event_disable, event);
        spin_lock_irq(&ctx->lock);
        /*
-         * If the counter is still active, we need to retry the cross-call.
+         * If the event is still active, we need to retry the cross-call.
         */
-        if (counter->state == PERF_COUNTER_STATE_ACTIVE) {
+        if (event->state == PERF_EVENT_STATE_ACTIVE) {
                spin_unlock_irq(&ctx->lock);
                goto retry;
        }
@@ -579,73 +578,73 @@ static void perf_counter_disable(struct perf_counter *counter)
         * Since we have the lock this context can't be scheduled
         * in, so we can change the state safely.
         */
-        if (counter->state == PERF_COUNTER_STATE_INACTIVE) {
+        if (event->state == PERF_EVENT_STATE_INACTIVE) {
-                update_group_times(counter);
+                update_group_times(event);
-                counter->state = PERF_COUNTER_STATE_OFF;
+                event->state = PERF_EVENT_STATE_OFF;
        }
        spin_unlock_irq(&ctx->lock);
 }
 static int
-counter_sched_in(struct perf_counter *counter,
+event_sched_in(struct perf_event *event,
                 struct perf_cpu_context *cpuctx,
-                 struct perf_counter_context *ctx,
+                 struct perf_event_context *ctx,
                 int cpu)
 {
-        if (counter->state <= PERF_COUNTER_STATE_OFF)
+        if (event->state <= PERF_EVENT_STATE_OFF)
                return 0;
-        counter->state = PERF_COUNTER_STATE_ACTIVE;
+        event->state = PERF_EVENT_STATE_ACTIVE;
-        counter->oncpu = cpu;   /* TODO: put 'cpu' into cpuctx->cpu */
+        event->oncpu = cpu;     /* TODO: put 'cpu' into cpuctx->cpu */
        /*
         * The new state must be visible before we turn it on in the hardware:
         */
        smp_wmb();
-        if (counter->pmu->enable(counter)) {
+        if (event->pmu->enable(event)) {
-                counter->state = PERF_COUNTER_STATE_INACTIVE;
+                event->state = PERF_EVENT_STATE_INACTIVE;
-                counter->oncpu = -1;
+                event->oncpu = -1;
                return -EAGAIN;
        }
-        counter->tstamp_running += ctx->time - counter->tstamp_stopped;
+        event->tstamp_running += ctx->time - event->tstamp_stopped;
-        if (!is_software_counter(counter))
+        if (!is_software_event(event))
                cpuctx->active_oncpu++;
        ctx->nr_active++;
-        if (counter->attr.exclusive)
+        if (event->attr.exclusive)
                cpuctx->exclusive = 1;
        return 0;
 }
 static int
-group_sched_in(struct perf_counter *group_counter,
+group_sched_in(struct perf_event *group_event,
               struct perf_cpu_context *cpuctx,
-               struct perf_counter_context *ctx,
+               struct perf_event_context *ctx,
               int cpu)
 {
-        struct perf_counter *counter, *partial_group;
+        struct perf_event *event, *partial_group;
        int ret;
-        if (group_counter->state == PERF_COUNTER_STATE_OFF)
+        if (group_event->state == PERF_EVENT_STATE_OFF)
                return 0;
-        ret = hw_perf_group_sched_in(group_counter, cpuctx, ctx, cpu);
+        ret = hw_perf_group_sched_in(group_event, cpuctx, ctx, cpu);
        if (ret)
                return ret < 0 ? ret : 0;
-        if (counter_sched_in(group_counter, cpuctx, ctx, cpu))
+        if (event_sched_in(group_event, cpuctx, ctx, cpu))
                return -EAGAIN;
        /*
         * Schedule in siblings as one group (if any):
         */
-        list_for_each_entry(counter, &group_counter->sibling_list, list_entry) {
+        list_for_each_entry(event, &group_event->sibling_list, group_entry) {
-                if (counter_sched_in(counter, cpuctx, ctx, cpu)) {
+                if (event_sched_in(event, cpuctx, ctx, cpu)) {
-                        partial_group = counter;
+                        partial_group = event;
                        goto group_error;
                }
        }
@@ -657,57 +656,57 @@ group_error:
         * Groups can be scheduled in as one unit only, so undo any
         * partial group before returning:
         */
-        list_for_each_entry(counter, &group_counter->sibling_list, list_entry) {
+        list_for_each_entry(event, &group_event->sibling_list, group_entry) {
-                if (counter == partial_group)
+                if (event == partial_group)
                        break;
-                counter_sched_out(counter, cpuctx, ctx);
+                event_sched_out(event, cpuctx, ctx);
        }
-        counter_sched_out(group_counter, cpuctx, ctx);
+        event_sched_out(group_event, cpuctx, ctx);
        return -EAGAIN;
 }
 /*
- * Return 1 for a group consisting entirely of software counters,
+ * Return 1 for a group consisting entirely of software events,
- * 0 if the group contains any hardware counters.
+ * 0 if the group contains any hardware events.
 */
-static int is_software_only_group(struct perf_counter *leader)
+static int is_software_only_group(struct perf_event *leader)
 {
-        struct perf_counter *counter;
+        struct perf_event *event;
-        if (!is_software_counter(leader))
+        if (!is_software_event(leader))
                return 0;
-        list_for_each_entry(counter, &leader->sibling_list, list_entry)
+        list_for_each_entry(event, &leader->sibling_list, group_entry)
-                if (!is_software_counter(counter))
+                if (!is_software_event(event))
                        return 0;
        return 1;
 }
 /*
- * Work out whether we can put this counter group on the CPU now.
+ * Work out whether we can put this event group on the CPU now.
 */
-static int group_can_go_on(struct perf_counter *counter,
+static int group_can_go_on(struct perf_event *event,
                           struct perf_cpu_context *cpuctx,
                           int can_add_hw)
 {
        /*
-         * Groups consisting entirely of software counters can always go on.
+         * Groups consisting entirely of software events can always go on.
         */
-        if (is_software_only_group(counter))
+        if (is_software_only_group(event))
                return 1;
        /*
         * If an exclusive group is already on, no other hardware
-         * counters can go on.
+         * events can go on.
         */
        if (cpuctx->exclusive)
                return 0;
        /*
         * If this group is exclusive and there are already
-         * counters on the CPU, it can't go on.
+         * events on the CPU, it can't go on.
         */
-        if (counter->attr.exclusive && cpuctx->active_oncpu)
+        if (event->attr.exclusive && cpuctx->active_oncpu)
                return 0;
        /*
         * Otherwise, try to add it if all previous groups were able
@@ -716,26 +715,26 @@ static int group_can_go_on(struct perf_counter *counter,
        return can_add_hw;
 }
-static void add_counter_to_ctx(struct perf_counter *counter,
+static void add_event_to_ctx(struct perf_event *event,
-                               struct perf_counter_context *ctx)
+                               struct perf_event_context *ctx)
 {
-        list_add_counter(counter, ctx);
+        list_add_event(event, ctx);
-        counter->tstamp_enabled = ctx->time;
+        event->tstamp_enabled = ctx->time;
-        counter->tstamp_running = ctx->time;
+        event->tstamp_running = ctx->time;
-        counter->tstamp_stopped = ctx->time;
+        event->tstamp_stopped = ctx->time;
 }
 /*
- * Cross CPU call to install and enable a performance counter
+ * Cross CPU call to install and enable a performance event
 *
 * Must be called with ctx->mutex held
 */
 static void __perf_install_in_context(void *info)
 {
        struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
-        struct perf_counter *counter = info;
+        struct perf_event *event = info;
-        struct perf_counter_context *ctx = counter->ctx;
+        struct perf_event_context *ctx = event->ctx;
-        struct perf_counter *leader = counter->group_leader;
+        struct perf_event *leader = event->group_leader;
        int cpu = smp_processor_id();
        int err;
@@ -744,7 +743,7 @@ static void __perf_install_in_context(void *info)
         * the current task context of this cpu. If not it has been
         * scheduled out before the smp call arrived.
         * Or possibly this is the right context but it isn't
-         * on this cpu because it had no counters.
+         * on this cpu because it had no events.
         */
        if (ctx->task && cpuctx->task_ctx != ctx) {
                if (cpuctx->task_ctx || ctx->task != current)
@@ -758,41 +757,41 @@ static void __perf_install_in_context(void *info)
        /*
         * Protect the list operation against NMI by disabling the
-         * counters on a global level. NOP for non NMI based counters.
+         * events on a global level. NOP for non NMI based events.
         */
        perf_disable();
-        add_counter_to_ctx(counter, ctx);
+        add_event_to_ctx(event, ctx);
        /*
-         * Don't put the counter on if it is disabled or if
+         * Don't put the event on if it is disabled or if
         * it is in a group and the group isn't on.
         */
-        if (counter->state != PERF_COUNTER_STATE_INACTIVE ||
+        if (event->state != PERF_EVENT_STATE_INACTIVE ||
-            (leader != counter && leader->state != PERF_COUNTER_STATE_ACTIVE))
+            (leader != event && leader->state != PERF_EVENT_STATE_ACTIVE))
                goto unlock;
        /*
-         * An exclusive counter can't go on if there are already active
+         * An exclusive event can't go on if there are already active
-         * hardware counters, and no hardware counter can go on if there
+         * hardware events, and no hardware event can go on if there
-         * is already an exclusive counter on.
+         * is already an exclusive event on.
         */
-        if (!group_can_go_on(counter, cpuctx, 1))
+        if (!group_can_go_on(event, cpuctx, 1))
                err = -EEXIST;
        else
-                err = counter_sched_in(counter, cpuctx, ctx, cpu);
+                err = event_sched_in(event, cpuctx, ctx, cpu);
        if (err) {
                /*
-                 * This counter couldn't go on.  If it is in a group
+                 * This event couldn't go on.  If it is in a group
                 * then we have to pull the whole group off.
-                 * If the counter group is pinned then put it in error state.
+                 * If the event group is pinned then put it in error state.
                 */
-                if (leader != counter)
+                if (leader != event)
                        group_sched_out(leader, cpuctx, ctx);
                if (leader->attr.pinned) {
                        update_group_times(leader);
-                        leader->state = PERF_COUNTER_STATE_ERROR;
+                        leader->state = PERF_EVENT_STATE_ERROR;
                }
        }
@@ -806,92 +805,92 @@ static void __perf_install_in_context(void *info)
 }
 /*
- * Attach a performance counter to a context
+ * Attach a performance event to a context
 *
- * First we add the counter to the list with the hardware enable bit
+ * First we add the event to the list with the hardware enable bit
- * in counter->hw_config cleared.
+ * in event->hw_config cleared.
 *
- * If the counter is attached to a task which is on a CPU we use a smp
+ * If the event is attached to a task which is on a CPU we use a smp
 * call to enable it in the task context. The task might have been
 * scheduled away, but we check this in the smp call again.
 *
 * Must be called with ctx->mutex held.
 */
 static void
-perf_install_in_context(struct perf_counter_context *ctx,
+perf_install_in_context(struct perf_event_context *ctx,
-                        struct perf_counter *counter,
+                        struct perf_event *event,
                        int cpu)
 {
        struct task_struct *task = ctx->task;
        if (!task) {
                /*
-                 * Per cpu counters are installed via an smp call and
+                 * Per cpu events are installed via an smp call and
                 * the install is always sucessful.
                 */
                smp_call_function_single(cpu, __perf_install_in_context,
-                                         counter, 1);
+                                         event, 1);
                return;
        }
 retry:
        task_oncpu_function_call(task, __perf_install_in_context,
-                                 counter);
+                                 event);
        spin_lock_irq(&ctx->lock);
        /*
         * we need to retry the smp call.
         */
-        if (ctx->is_active && list_empty(&counter->list_entry)) {
+        if (ctx->is_active && list_empty(&event->group_entry)) {
                spin_unlock_irq(&ctx->lock);
                goto retry;
        }
        /*
         * The lock prevents that this context is scheduled in so we
-         * can add the counter safely, if it the call above did not
+         * can add the event safely, if it the call above did not
         * succeed.
         */
-        if (list_empty(&counter->list_entry))
+        if (list_empty(&event->group_entry))
-                add_counter_to_ctx(counter, ctx);
+                add_event_to_ctx(event, ctx);
        spin_unlock_irq(&ctx->lock);
 }
 /*
- * Put a counter into inactive state and update time fields.
+ * Put a event into inactive state and update time fields.
 * Enabling the leader of a group effectively enables all
 * the group members that aren't explicitly disabled, so we
 * have to update their ->tstamp_enabled also.
 * Note: this works for group members as well as group leaders
 * since the non-leader members' sibling_lists will be empty.
 */
-static void __perf_counter_mark_enabled(struct perf_counter *counter,
+static void __perf_event_mark_enabled(struct perf_event *event,
-                                        struct perf_counter_context *ctx)
+                                        struct perf_event_context *ctx)
 {
-        struct perf_counter *sub;
+        struct perf_event *sub;
-        counter->state = PERF_COUNTER_STATE_INACTIVE;
+        event->state = PERF_EVENT_STATE_INACTIVE;
-        counter->tstamp_enabled = ctx->time - counter->total_time_enabled;
+        event->tstamp_enabled = ctx->time - event->total_time_enabled;
-        list_for_each_entry(sub, &counter->sibling_list, list_entry)
+        list_for_each_entry(sub, &event->sibling_list, group_entry)
-                if (sub->state >= PERF_COUNTER_STATE_INACTIVE)
+                if (sub->state >= PERF_EVENT_STATE_INACTIVE)
                        sub->tstamp_enabled =
                                ctx->time - sub->total_time_enabled;
 }
 /*
- * Cross CPU call to enable a performance counter
+ * Cross CPU call to enable a performance event
 */
-static void __perf_counter_enable(void *info)
+static void __perf_event_enable(void *info)
 {
-        struct perf_counter *counter = info;
+        struct perf_event *event = info;
        struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
-        struct perf_counter_context *ctx = counter->ctx;
+        struct perf_event_context *ctx = event->ctx;
-        struct perf_counter *leader = counter->group_leader;
+        struct perf_event *leader = event->group_leader;
        int err;
        /*
-         * If this is a per-task counter, need to check whether this
+         * If this is a per-task event, need to check whether this
-         * counter's task is the current task on this cpu.
+         * event's task is the current task on this cpu.
         */
        if (ctx->task && cpuctx->task_ctx != ctx) {
                if (cpuctx->task_ctx || ctx->task != current)
@@ -903,40 +902,40 @@ static void __perf_counter_enable(void *info)
        ctx->is_active = 1;
        update_context_time(ctx);
-        if (counter->state >= PERF_COUNTER_STATE_INACTIVE)
+        if (event->state >= PERF_EVENT_STATE_INACTIVE)
                goto unlock;
-        __perf_counter_mark_enabled(counter, ctx);
+        __perf_event_mark_enabled(event, ctx);
        /*
-         * If the counter is in a group and isn't the group leader,
+         * If the event is in a group and isn't the group leader,
         * then don't put it on unless the group is on.
         */
-        if (leader != counter && leader->state != PERF_COUNTER_STATE_ACTIVE)
+        if (leader != event && leader->state != PERF_EVENT_STATE_ACTIVE)
                goto unlock;
-        if (!group_can_go_on(counter, cpuctx, 1)) {
+        if (!group_can_go_on(event, cpuctx, 1)) {
                err = -EEXIST;
        } else {
                perf_disable();
-                if (counter == leader)
+                if (event == leader)
-                        err = group_sched_in(counter, cpuctx, ctx,
+                        err = group_sched_in(event, cpuctx, ctx,
                                             smp_processor_id());
                else
-                        err = counter_sched_in(counter, cpuctx, ctx,
+                        err = event_sched_in(event, cpuctx, ctx,
                                               smp_processor_id());
                perf_enable();
        }
        if (err) {
                /*
-                 * If this counter can't go on and it's part of a
+                 * If this event can't go on and it's part of a
                 * group, then the whole group has to come off.
                 */
-                if (leader != counter)
+                if (leader != event)
                        group_sched_out(leader, cpuctx, ctx);
                if (leader->attr.pinned) {
                        update_group_times(leader);
-                        leader->state = PERF_COUNTER_STATE_ERROR;
+                        leader->state = PERF_EVENT_STATE_ERROR;
                }
        }
@@ -945,98 +944,98 @@ static void __perf_counter_enable(void *info)
 }
 /*
- * Enable a counter.
+ * Enable a event.
 *
- * If counter->ctx is a cloned context, callers must make sure that
+ * If event->ctx is a cloned context, callers must make sure that
- * every task struct that counter->ctx->task could possibly point to
+ * every task struct that event->ctx->task could possibly point to
 * remains valid.  This condition is satisfied when called through
- * perf_counter_for_each_child or perf_counter_for_each as described
+ * perf_event_for_each_child or perf_event_for_each as described
- * for perf_counter_disable.
+ * for perf_event_disable.
 */
-static void perf_counter_enable(struct perf_counter *counter)
+static void perf_event_enable(struct perf_event *event)
 {
-        struct perf_counter_context *ctx = counter->ctx;
+        struct perf_event_context *ctx = event->ctx;
        struct task_struct *task = ctx->task;
        if (!task) {
                /*
-                 * Enable the counter on the cpu that it's on
+                 * Enable the event on the cpu that it's on
                 */
-                smp_call_function_single(counter->cpu, __perf_counter_enable,
+                smp_call_function_single(event->cpu, __perf_event_enable,
-                                         counter, 1);
+                                         event, 1);
                return;
        }
        spin_lock_irq(&ctx->lock);
-        if (counter->state >= PERF_COUNTER_STATE_INACTIVE)
+        if (event->state >= PERF_EVENT_STATE_INACTIVE)
                goto out;
        /*
-         * If the counter is in error state, clear that first.
+         * If the event is in error state, clear that first.
-         * That way, if we see the counter in error state below, we
+         * That way, if we see the event in error state below, we
         * know that it has gone back into error state, as distinct
         * from the task having been scheduled away before the
         * cross-call arrived.
         */
-        if (counter->state == PERF_COUNTER_STATE_ERROR)
+        if (event->state == PERF_EVENT_STATE_ERROR)
-                counter->state = PERF_COUNTER_STATE_OFF;
+                event->state = PERF_EVENT_STATE_OFF;
 retry:
        spin_unlock_irq(&ctx->lock);
-        task_oncpu_function_call(task, __perf_counter_enable, counter);
+        task_oncpu_function_call(task, __perf_event_enable, event);
        spin_lock_irq(&ctx->lock);
        /*
-         * If the context is active and the counter is still off,
+         * If the context is active and the event is still off,
         * we need to retry the cross-call.
         */
-        if (ctx->is_active && counter->state == PERF_COUNTER_STATE_OFF)
+        if (ctx->is_active && event->state == PERF_EVENT_STATE_OFF)
                goto retry;
        /*
         * Since we have the lock this context can't be scheduled
         * in, so we can change the state safely.
         */
-        if (counter->state == PERF_COUNTER_STATE_OFF)
+        if (event->state == PERF_EVENT_STATE_OFF)
-                __perf_counter_mark_enabled(counter, ctx);
+                __perf_event_mark_enabled(event, ctx);
 out:
        spin_unlock_irq(&ctx->lock);
 }
-static int perf_counter_refresh(struct perf_counter *counter, int refresh)
+static int perf_event_refresh(struct perf_event *event, int refresh)
 {
        /*
-         * not supported on inherited counters
+         * not supported on inherited events
         */
-        if (counter->attr.inherit)
+        if (event->attr.inherit)
                return -EINVAL;
-        atomic_add(refresh, &counter->event_limit);
+        atomic_add(refresh, &event->event_limit);
-        perf_counter_enable(counter);
+        perf_event_enable(event);
        return 0;
 }
-void __perf_counter_sched_out(struct perf_counter_context *ctx,
+void __perf_event_sched_out(struct perf_event_context *ctx,
                              struct perf_cpu_context *cpuctx)
 {
-        struct perf_counter *counter;
+        struct perf_event *event;
        spin_lock(&ctx->lock);
        ctx->is_active = 0;
-        if (likely(!ctx->nr_counters))
+        if (likely(!ctx->nr_events))
                goto out;
        update_context_time(ctx);
        perf_disable();
        if (ctx->nr_active) {
-                list_for_each_entry(counter, &ctx->counter_list, list_entry) {
+                list_for_each_entry(event, &ctx->group_list, group_entry) {
-                        if (counter != counter->group_leader)
+                        if (event != event->group_leader)
-                                counter_sched_out(counter, cpuctx, ctx);
+                                event_sched_out(event, cpuctx, ctx);
                        else
-                                group_sched_out(counter, cpuctx, ctx);
+                                group_sched_out(event, cpuctx, ctx);
                }
        }
        perf_enable();
@@ -1047,46 +1046,46 @@ void __perf_counter_sched_out(struct perf_counter_context *ctx,
 /*
 * Test whether two contexts are equivalent, i.e. whether they
 * have both been cloned from the same version of the same context
- * and they both have the same number of enabled counters.
+ * and they both have the same number of enabled events.
- * If the number of enabled counters is the same, then the set
+ * If the number of enabled events is the same, then the set
- * of enabled counters should be the same, because these are both
+ * of enabled events should be the same, because these are both
- * inherited contexts, therefore we can't access individual counters
+ * inherited contexts, therefore we can't access individual events
 * in them directly with an fd; we can only enable/disable all
- * counters via prctl, or enable/disable all counters in a family
+ * events via prctl, or enable/disable all events in a family
 * via ioctl, which will have the same effect on both contexts.
 */
-static int context_equiv(struct perf_counter_context *ctx1,
+static int context_equiv(struct perf_event_context *ctx1,
-                         struct perf_counter_context *ctx2)
+                         struct perf_event_context *ctx2)
 {
        return ctx1->parent_ctx && ctx1->parent_ctx == ctx2->parent_ctx
                && ctx1->parent_gen == ctx2->parent_gen
                && !ctx1->pin_count && !ctx2->pin_count;
 }
-static void __perf_counter_read(void *counter);
+static void __perf_event_read(void *event);
-static void __perf_counter_sync_stat(struct perf_counter *counter,
+static void __perf_event_sync_stat(struct perf_event *event,
-                                     struct perf_counter *next_counter)
+                                     struct perf_event *next_event)
 {
        u64 value;
-        if (!counter->attr.inherit_stat)
+        if (!event->attr.inherit_stat)
                return;
        /*
-         * Update the counter value, we cannot use perf_counter_read()
+         * Update the event value, we cannot use perf_event_read()
         * because we're in the middle of a context switch and have IRQs
         * disabled, which upsets smp_call_function_single(), however
-         * we know the counter must be on the current CPU, therefore we
+         * we know the event must be on the current CPU, therefore we
         * don't need to use it.
         */
-        switch (counter->state) {
+        switch (event->state) {
-        case PERF_COUNTER_STATE_ACTIVE:
+        case PERF_EVENT_STATE_ACTIVE:
-                __perf_counter_read(counter);
+                __perf_event_read(event);
                break;
-        case PERF_COUNTER_STATE_INACTIVE:
+        case PERF_EVENT_STATE_INACTIVE:
-                update_counter_times(counter);
+                update_event_times(event);
                break;
        default:
@@ -1094,73 +1093,73 @@ static void __perf_counter_sync_stat(struct perf_counter *counter,
        }
        /*
-         * In order to keep per-task stats reliable we need to flip the counter
+         * In order to keep per-task stats reliable we need to flip the event
         * values when we flip the contexts.
         */
-        value = atomic64_read(&next_counter->count);
+        value = atomic64_read(&next_event->count);
-        value = atomic64_xchg(&counter->count, value);
+        value = atomic64_xchg(&event->count, value);
-        atomic64_set(&next_counter->count, value);
+        atomic64_set(&next_event->count, value);
-        swap(counter->total_time_enabled, next_counter->total_time_enabled);
+        swap(event->total_time_enabled, next_event->total_time_enabled);
-        swap(counter->total_time_running, next_counter->total_time_running);
+        swap(event->total_time_running, next_event->total_time_running);
        /*
         * Since we swizzled the values, update the user visible data too.
         */
-        perf_counter_update_userpage(counter);
+        perf_event_update_userpage(event);
-        perf_counter_update_userpage(next_counter);
+        perf_event_update_userpage(next_event);
 }
 #define list_next_entry(pos, member) \
        list_entry(pos->member.next, typeof(*pos), member)
-static void perf_counter_sync_stat(struct perf_counter_context *ctx,
+static void perf_event_sync_stat(struct perf_event_context *ctx,
-                                   struct perf_counter_context *next_ctx)
+                                   struct perf_event_context *next_ctx)
 {
-        struct perf_counter *counter, *next_counter;
+        struct perf_event *event, *next_event;
        if (!ctx->nr_stat)
                return;
-        counter = list_first_entry(&ctx->event_list,
+        event = list_first_entry(&ctx->event_list,
-                                   struct perf_counter, event_entry);
+                                   struct perf_event, event_entry);
-        next_counter = list_first_entry(&next_ctx->event_list,
+        next_event = list_first_entry(&next_ctx->event_list,
-                                        struct perf_counter, event_entry);
+                                        struct perf_event, event_entry);
-        while (&counter->event_entry != &ctx->event_list &&
+        while (&event->event_entry != &ctx->event_list &&
-               &next_counter->event_entry != &next_ctx->event_list) {
+               &next_event->event_entry != &next_ctx->event_list) {
-                __perf_counter_sync_stat(counter, next_counter);
+                __perf_event_sync_stat(event, next_event);
-                counter = list_next_entry(counter, event_entry);
+                event = list_next_entry(event, event_entry);
-                next_counter = list_next_entry(next_counter, event_entry);
+                next_event = list_next_entry(next_event, event_entry);
        }
 }
 /*
- * Called from scheduler to remove the counters of the current task,
+ * Called from scheduler to remove the events of the current task,
 * with interrupts disabled.
 *
- * We stop each counter and update the counter value in counter->count.
+ * We stop each event and update the event value in event->count.
 *
 * This does not protect us against NMI, but disable()
- * sets the disabled bit in the control field of counter _before_
+ * sets the disabled bit in the control field of event _before_
- * accessing the counter control register. If a NMI hits, then it will
+ * accessing the event control register. If a NMI hits, then it will
- * not restart the counter.
+ * not restart the event.
 */
-void perf_counter_task_sched_out(struct task_struct *task,
+void perf_event_task_sched_out(struct task_struct *task,
                                 struct task_struct *next, int cpu)
 {
        struct perf_cpu_context *cpuctx = &per_cpu(perf_cpu_context, cpu);
-        struct perf_counter_context *ctx = task->perf_counter_ctxp;
+        struct perf_event_context *ctx = task->perf_event_ctxp;
-        struct perf_counter_context *next_ctx;
+        struct perf_event_context *next_ctx;
-        struct perf_counter_context *parent;
+        struct perf_event_context *parent;
        struct pt_regs *regs;
        int do_switch = 1;
        regs = task_pt_regs(task);
-        perf_swcounter_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 1, regs, 0);
+        perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 1, regs, 0);
        if (likely(!ctx || !cpuctx->task_ctx))
                return;
@@ -1169,7 +1168,7 @@ void perf_counter_task_sched_out(struct task_struct *task,
        rcu_read_lock();
        parent = rcu_dereference(ctx->parent_ctx);
-        next_ctx = next->perf_counter_ctxp;
+        next_ctx = next->perf_event_ctxp;
        if (parent && next_ctx &&
            rcu_dereference(next_ctx->parent_ctx) == parent) {
                /*
@@ -1186,15 +1185,15 @@ void perf_counter_task_sched_out(struct task_struct *task,
                if (context_equiv(ctx, next_ctx)) {
                        /*
                         * XXX do we need a memory barrier of sorts
-                         * wrt to rcu_dereference() of perf_counter_ctxp
+                         * wrt to rcu_dereference() of perf_event_ctxp
                         */
-                        task->perf_counter_ctxp = next_ctx;
+                        task->perf_event_ctxp = next_ctx;
-                        next->perf_counter_ctxp = ctx;
+                        next->perf_event_ctxp = ctx;
                        ctx->task = next;
                        next_ctx->task = task;
                        do_switch = 0;
-                        perf_counter_sync_stat(ctx, next_ctx);
+                        perf_event_sync_stat(ctx, next_ctx);
                }
                spin_unlock(&next_ctx->lock);
                spin_unlock(&ctx->lock);
@@ -1202,7 +1201,7 @@ void perf_counter_task_sched_out(struct task_struct *task,
        rcu_read_unlock();
        if (do_switch) {
-                __perf_counter_sched_out(ctx, cpuctx);
+                __perf_event_sched_out(ctx, cpuctx);
                cpuctx->task_ctx = NULL;
        }
 }
@@ -1210,7 +1209,7 @@ void perf_counter_task_sched_out(struct task_struct *task,
 /*
 * Called with IRQs disabled
 */
-static void __perf_counter_task_sched_out(struct perf_counter_context *ctx)
+static void __perf_event_task_sched_out(struct perf_event_context *ctx)
 {
        struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
@@ -1220,28 +1219,28 @@ static void __perf_counter_task_sched_out(struct perf_counter_context *ctx)
        if (WARN_ON_ONCE(ctx != cpuctx->task_ctx))
                return;
-        __perf_counter_sched_out(ctx, cpuctx);
+        __perf_event_sched_out(ctx, cpuctx);
        cpuctx->task_ctx = NULL;
 }
 /*
 * Called with IRQs disabled
 */
-static void perf_counter_cpu_sched_out(struct perf_cpu_context *cpuctx)
+static void perf_event_cpu_sched_out(struct perf_cpu_context *cpuctx)
 {
-        __perf_counter_sched_out(&cpuctx->ctx, cpuctx);
+        __perf_event_sched_out(&cpuctx->ctx, cpuctx);
 }
 static void
-__perf_counter_sched_in(struct perf_counter_context *ctx,
+__perf_event_sched_in(struct perf_event_context *ctx,
                        struct perf_cpu_context *cpuctx, int cpu)
 {
-        struct perf_counter *counter;
+        struct perf_event *event;
        int can_add_hw = 1;
        spin_lock(&ctx->lock);
        ctx->is_active = 1;
-        if (likely(!ctx->nr_counters))
+        if (likely(!ctx->nr_events))
                goto out;
        ctx->timestamp = perf_clock();
@@ -1252,52 +1251,52 @@ __perf_counter_sched_in(struct perf_counter_context *ctx,
         * First go through the list and put on any pinned groups
         * in order to give them the best chance of going on.
         */
-        list_for_each_entry(counter, &ctx->counter_list, list_entry) {
+        list_for_each_entry(event, &ctx->group_list, group_entry) {
-                if (counter->state <= PERF_COUNTER_STATE_OFF ||
+                if (event->state <= PERF_EVENT_STATE_OFF ||
-                    !counter->attr.pinned)
+                    !event->attr.pinned)
                        continue;
-                if (counter->cpu != -1 && counter->cpu != cpu)
+                if (event->cpu != -1 && event->cpu != cpu)
                        continue;
-                if (counter != counter->group_leader)
+                if (event != event->group_leader)
-                        counter_sched_in(counter, cpuctx, ctx, cpu);
+                        event_sched_in(event, cpuctx, ctx, cpu);
                else {
-                        if (group_can_go_on(counter, cpuctx, 1))
+                        if (group_can_go_on(event, cpuctx, 1))
-                                group_sched_in(counter, cpuctx, ctx, cpu);
+                                group_sched_in(event, cpuctx, ctx, cpu);
                }
                /*
                 * If this pinned group hasn't been scheduled,
                 * put it in error state.
                 */
-                if (counter->state == PERF_COUNTER_STATE_INACTIVE) {
+                if (event->state == PERF_EVENT_STATE_INACTIVE) {
-                        update_group_times(counter);
+                        update_group_times(event);
-                        counter->state = PERF_COUNTER_STATE_ERROR;
+                        event->state = PERF_EVENT_STATE_ERROR;
                }
        }
-        list_for_each_entry(counter, &ctx->counter_list, list_entry) {
+        list_for_each_entry(event, &ctx->group_list, group_entry) {
                /*
-                 * Ignore counters in OFF or ERROR state, and
+                 * Ignore events in OFF or ERROR state, and
-                 * ignore pinned counters since we did them already.
+                 * ignore pinned events since we did them already.
                 */
-                if (counter->state <= PERF_COUNTER_STATE_OFF ||
+                if (event->state <= PERF_EVENT_STATE_OFF ||
-                    counter->attr.pinned)
+                    event->attr.pinned)
                        continue;
                /*
                 * Listen to the 'cpu' scheduling filter constraint
-                 * of counters:
+                 * of events:
                 */
-                if (counter->cpu != -1 && counter->cpu != cpu)
+                if (event->cpu != -1 && event->cpu != cpu)
                        continue;
-                if (counter != counter->group_leader) {
+                if (event != event->group_leader) {
-                        if (counter_sched_in(counter, cpuctx, ctx, cpu))
+                        if (event_sched_in(event, cpuctx, ctx, cpu))
                                can_add_hw = 0;
                } else {
-                        if (group_can_go_on(counter, cpuctx, can_add_hw)) {
+                        if (group_can_go_on(event, cpuctx, can_add_hw)) {
-                                if (group_sched_in(counter, cpuctx, ctx, cpu))
+                                if (group_sched_in(event, cpuctx, ctx, cpu))
                                        can_add_hw = 0;
                        }
                }
@@ -1308,48 +1307,48 @@ __perf_counter_sched_in(struct perf_counter_context *ctx,
 }
 /*
- * Called from scheduler to add the counters of the current task
+ * Called from scheduler to add the events of the current task
 * with interrupts disabled.
 *
- * We restore the counter value and then enable it.
+ * We restore the event value and then enable it.
 *
 * This does not protect us against NMI, but enable()
- * sets the enabled bit in the control field of counter _before_
+ * sets the enabled bit in the control field of event _before_
- * accessing the counter control register. If a NMI hits, then it will
+ * accessing the event control register. If a NMI hits, then it will
- * keep the counter running.
+ * keep the event running.
 */
-void perf_counter_task_sched_in(struct task_struct *task, int cpu)
+void perf_event_task_sched_in(struct task_struct *task, int cpu)
 {
        struct perf_cpu_context *cpuctx = &per_cpu(perf_cpu_context, cpu);
-        struct perf_counter_context *ctx = task->perf_counter_ctxp;
+        struct perf_event_context *ctx = task->perf_event_ctxp;
        if (likely(!ctx))
                return;
        if (cpuctx->task_ctx == ctx)
                return;
-        __perf_counter_sched_in(ctx, cpuctx, cpu);
+        __perf_event_sched_in(ctx, cpuctx, cpu);
        cpuctx->task_ctx = ctx;
 }
-static void perf_counter_cpu_sched_in(struct perf_cpu_context *cpuctx, int cpu)
+static void perf_event_cpu_sched_in(struct perf_cpu_context *cpuctx, int cpu)
 {
-        struct perf_counter_context *ctx = &cpuctx->ctx;
+        struct perf_event_context *ctx = &cpuctx->ctx;
-        __perf_counter_sched_in(ctx, cpuctx, cpu);
+        __perf_event_sched_in(ctx, cpuctx, cpu);
 }
 #define MAX_INTERRUPTS (~0ULL)
-static void perf_log_throttle(struct perf_counter *counter, int enable);
+static void perf_log_throttle(struct perf_event *event, int enable);
-static void perf_adjust_period(struct perf_counter *counter, u64 events)
+static void perf_adjust_period(struct perf_event *event, u64 events)
 {
-        struct hw_perf_counter *hwc = &counter->hw;
+        struct hw_perf_event *hwc = &event->hw;
        u64 period, sample_period;
        s64 delta;
        events *= hwc->sample_period;
-        period = div64_u64(events, counter->attr.sample_freq);
+        period = div64_u64(events, event->attr.sample_freq);
        delta = (s64)(period - hwc->sample_period);
        delta = (delta + 7) / 8; /* low pass filter */
@@ -1362,39 +1361,39 @@ static void perf_adjust_period(struct perf_counter *counter, u64 events)
        hwc->sample_period = sample_period;
 }
-static void perf_ctx_adjust_freq(struct perf_counter_context *ctx)
+static void perf_ctx_adjust_freq(struct perf_event_context *ctx)
 {
-        struct perf_counter *counter;
+        struct perf_event *event;
-        struct hw_perf_counter *hwc;
+        struct hw_perf_event *hwc;
        u64 interrupts, freq;
        spin_lock(&ctx->lock);
-        list_for_each_entry(counter, &ctx->counter_list, list_entry) {
+        list_for_each_entry(event, &ctx->group_list, group_entry) {
-                if (counter->state != PERF_COUNTER_STATE_ACTIVE)
+                if (event->state != PERF_EVENT_STATE_ACTIVE)
                        continue;
-                hwc = &counter->hw;
+                hwc = &event->hw;
                interrupts = hwc->interrupts;
                hwc->interrupts = 0;
                /*
-                 * unthrottle counters on the tick
+                 * unthrottle events on the tick
                 */
                if (interrupts == MAX_INTERRUPTS) {
-                        perf_log_throttle(counter, 1);
+                        perf_log_throttle(event, 1);
-                        counter->pmu->unthrottle(counter);
+                        event->pmu->unthrottle(event);
-                        interrupts = 2*sysctl_perf_counter_sample_rate/HZ;
+                        interrupts = 2*sysctl_perf_event_sample_rate/HZ;
                }
-                if (!counter->attr.freq || !counter->attr.sample_freq)
+                if (!event->attr.freq || !event->attr.sample_freq)
                        continue;
                /*
                 * if the specified freq < HZ then we need to skip ticks
                 */
-                if (counter->attr.sample_freq < HZ) {
+                if (event->attr.sample_freq < HZ) {
-                        freq = counter->attr.sample_freq;
+                        freq = event->attr.sample_freq;
                        hwc->freq_count += freq;
                        hwc->freq_interrupts += interrupts;
@@ -1408,7 +1407,7 @@ static void perf_ctx_adjust_freq(struct perf_counter_context *ctx)
                } else
                        freq = HZ;
-                perf_adjust_period(counter, freq * interrupts);
+                perf_adjust_period(event, freq * interrupts);
                /*
                 * In order to avoid being stalled by an (accidental) huge
@@ -1417,9 +1416,9 @@ static void perf_ctx_adjust_freq(struct perf_counter_context *ctx)
                 */
                if (!interrupts) {
                        perf_disable();
-                        counter->pmu->disable(counter);
+                        event->pmu->disable(event);
                        atomic64_set(&hwc->period_left, 0);
-                        counter->pmu->enable(counter);
+                        event->pmu->enable(event);
                        perf_enable();
                }
        }
@@ -1427,22 +1426,22 @@ static void perf_ctx_adjust_freq(struct perf_counter_context *ctx)
 }
 /*
- * Round-robin a context's counters:
+ * Round-robin a context's events:
 */
-static void rotate_ctx(struct perf_counter_context *ctx)
+static void rotate_ctx(struct perf_event_context *ctx)
 {
-        struct perf_counter *counter;
+        struct perf_event *event;
-        if (!ctx->nr_counters)
+        if (!ctx->nr_events)
                return;
        spin_lock(&ctx->lock);
        /*
-         * Rotate the first entry last (works just fine for group counters too):
+         * Rotate the first entry last (works just fine for group events too):
         */
        perf_disable();
-        list_for_each_entry(counter, &ctx->counter_list, list_entry) {
+        list_for_each_entry(event, &ctx->group_list, group_entry) {
-                list_move_tail(&counter->list_entry, &ctx->counter_list);
+                list_move_tail(&event->group_entry, &ctx->group_list);
                break;
        }
        perf_enable();
@@ -1450,93 +1449,93 @@ static void rotate_ctx(struct perf_counter_context *ctx)
        spin_unlock(&ctx->lock);
 }
-void perf_counter_task_tick(struct task_struct *curr, int cpu)
+void perf_event_task_tick(struct task_struct *curr, int cpu)
 {
        struct perf_cpu_context *cpuctx;
-        struct perf_counter_context *ctx;
+        struct perf_event_context *ctx;
-        if (!atomic_read(&nr_counters))
+        if (!atomic_read(&nr_events))
                return;
        cpuctx = &per_cpu(perf_cpu_context, cpu);
-        ctx = curr->perf_counter_ctxp;
+        ctx = curr->perf_event_ctxp;
        perf_ctx_adjust_freq(&cpuctx->ctx);
        if (ctx)
                perf_ctx_adjust_freq(ctx);
-        perf_counter_cpu_sched_out(cpuctx);
+        perf_event_cpu_sched_out(cpuctx);
        if (ctx)
-                __perf_counter_task_sched_out(ctx);
+                __perf_event_task_sched_out(ctx);
        rotate_ctx(&cpuctx->ctx);
        if (ctx)
                rotate_ctx(ctx);
-        perf_counter_cpu_sched_in(cpuctx, cpu);
+        perf_event_cpu_sched_in(cpuctx, cpu);
        if (ctx)
-                perf_counter_task_sched_in(curr, cpu);
+                perf_event_task_sched_in(curr, cpu);
 }
 /*
- * Enable all of a task's counters that have been marked enable-on-exec.
+ * Enable all of a task's events that have been marked enable-on-exec.
 * This expects task == current.
 */
-static void perf_counter_enable_on_exec(struct task_struct *task)
+static void perf_event_enable_on_exec(struct task_struct *task)
 {
-        struct perf_counter_context *ctx;
+        struct perf_event_context *ctx;
-        struct perf_counter *counter;
+        struct perf_event *event;
        unsigned long flags;
        int enabled = 0;
        local_irq_save(flags);
-        ctx = task->perf_counter_ctxp;
+        ctx = task->perf_event_ctxp;
-        if (!ctx || !ctx->nr_counters)
+        if (!ctx || !ctx->nr_events)
                goto out;
-        __perf_counter_task_sched_out(ctx);
+        __perf_event_task_sched_out(ctx);
        spin_lock(&ctx->lock);
-        list_for_each_entry(counter, &ctx->counter_list, list_entry) {
+        list_for_each_entry(event, &ctx->group_list, group_entry) {
-                if (!counter->attr.enable_on_exec)
+                if (!event->attr.enable_on_exec)
                        continue;
-                counter->attr.enable_on_exec = 0;
+                event->attr.enable_on_exec = 0;
-                if (counter->state >= PERF_COUNTER_STATE_INACTIVE)
+                if (event->state >= PERF_EVENT_STATE_INACTIVE)
                        continue;
-                __perf_counter_mark_enabled(counter, ctx);
+                __perf_event_mark_enabled(event, ctx);
                enabled = 1;
        }
        /*
-         * Unclone this context if we enabled any counter.
+         * Unclone this context if we enabled any event.
         */
        if (enabled)
                unclone_ctx(ctx);
        spin_unlock(&ctx->lock);
-        perf_counter_task_sched_in(task, smp_processor_id());
+        perf_event_task_sched_in(task, smp_processor_id());
 out:
        local_irq_restore(flags);
 }
 /*
- * Cross CPU call to read the hardware counter
+ * Cross CPU call to read the hardware event
 */
-static void __perf_counter_read(void *info)
+static void __perf_event_read(void *info)
 {
        struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
-        struct perf_counter *counter = info;
+        struct perf_event *event = info;
-        struct perf_counter_context *ctx = counter->ctx;
+        struct perf_event_context *ctx = event->ctx;
        unsigned long flags;
        /*
         * If this is a task context, we need to check whether it is
         * the current task context of this cpu.  If not it has been
         * scheduled out before the smp call arrived.  In that case
-         * counter->count would have been updated to a recent sample
+         * event->count would have been updated to a recent sample
-         * when the counter was scheduled out.
+         * when the event was scheduled out.
         */
        if (ctx->task && cpuctx->task_ctx != ctx)
                return;
@@ -1544,56 +1543,56 @@ static void __perf_counter_read(void *info)
        local_irq_save(flags);
        if (ctx->is_active)
                update_context_time(ctx);
-        counter->pmu->read(counter);
+        event->pmu->read(event);
-        update_counter_times(counter);
+        update_event_times(event);
        local_irq_restore(flags);
 }
-static u64 perf_counter_read(struct perf_counter *counter)
+static u64 perf_event_read(struct perf_event *event)
 {
        /*
-         * If counter is enabled and currently active on a CPU, update the
+         * If event is enabled and currently active on a CPU, update the
-         * value in the counter structure:
+         * value in the event structure:
         */
-        if (counter->state == PERF_COUNTER_STATE_ACTIVE) {
+        if (event->state == PERF_EVENT_STATE_ACTIVE) {
-                smp_call_function_single(counter->oncpu,
+                smp_call_function_single(event->oncpu,
-                                         __perf_counter_read, counter, 1);
+                                         __perf_event_read, event, 1);
-        } else if (counter->state == PERF_COUNTER_STATE_INACTIVE) {
+        } else if (event->state == PERF_EVENT_STATE_INACTIVE) {
-                update_counter_times(counter);
+                update_event_times(event);
        }
-        return atomic64_read(&counter->count);
+        return atomic64_read(&event->count);
 }
 /*
- * Initialize the perf_counter context in a task_struct:
+ * Initialize the perf_event context in a task_struct:
 */
 static void
-__perf_counter_init_context(struct perf_counter_context *ctx,
+__perf_event_init_context(struct perf_event_context *ctx,
                            struct task_struct *task)
 {
        memset(ctx, 0, sizeof(*ctx));
        spin_lock_init(&ctx->lock);
        mutex_init(&ctx->mutex);
-        INIT_LIST_HEAD(&ctx->counter_list);
+        INIT_LIST_HEAD(&ctx->group_list);
        INIT_LIST_HEAD(&ctx->event_list);
        atomic_set(&ctx->refcount, 1);
        ctx->task = task;
 }
-static struct perf_counter_context *find_get_context(pid_t pid, int cpu)
+static struct perf_event_context *find_get_context(pid_t pid, int cpu)
 {
-        struct perf_counter_context *ctx;
+        struct perf_event_context *ctx;
        struct perf_cpu_context *cpuctx;
        struct task_struct *task;
        unsigned long flags;
        int err;
        /*
-         * If cpu is not a wildcard then this is a percpu counter:
+         * If cpu is not a wildcard then this is a percpu event:
         */
        if (cpu != -1) {
-                /* Must be root to operate on a CPU counter: */
+                /* Must be root to operate on a CPU event: */
                if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN))
                        return ERR_PTR(-EACCES);
@@ -1601,7 +1600,7 @@ static struct perf_counter_context *find_get_context(pid_t pid, int cpu)
                        return ERR_PTR(-EINVAL);
                /*
-                 * We could be clever and allow to attach a counter to an
+                 * We could be clever and allow to attach a event to an
                 * offline CPU and activate it when the CPU comes up, but
                 * that's for later.
                 */
@@ -1628,7 +1627,7 @@ static struct perf_counter_context *find_get_context(pid_t pid, int cpu)
                return ERR_PTR(-ESRCH);
        /*
-         * Can't attach counters to a dying task.
+         * Can't attach events to a dying task.
         */
        err = -ESRCH;
        if (task->flags & PF_EXITING)
@@ -1647,13 +1646,13 @@ static struct perf_counter_context *find_get_context(pid_t pid, int cpu)
        }
        if (!ctx) {
-                ctx = kmalloc(sizeof(struct perf_counter_context), GFP_KERNEL);
+                ctx = kmalloc(sizeof(struct perf_event_context), GFP_KERNEL);
                err = -ENOMEM;
                if (!ctx)
                        goto errout;
-                __perf_counter_init_context(ctx, task);
+                __perf_event_init_context(ctx, task);
                get_ctx(ctx);
-                if (cmpxchg(&task->perf_counter_ctxp, NULL, ctx)) {
+                if (cmpxchg(&task->perf_event_ctxp, NULL, ctx)) {
                        /*
                         * We raced with some other task; use
                         * the context they set.
@@ -1672,42 +1671,42 @@ static struct perf_counter_context *find_get_context(pid_t pid, int cpu)
        return ERR_PTR(err);
 }
-static void free_counter_rcu(struct rcu_head *head)
+static void free_event_rcu(struct rcu_head *head)
 {
-        struct perf_counter *counter;
+        struct perf_event *event;
-        counter = container_of(head, struct perf_counter, rcu_head);
+        event = container_of(head, struct perf_event, rcu_head);
-        if (counter->ns)
+        if (event->ns)
-                put_pid_ns(counter->ns);
+                put_pid_ns(event->ns);
-        kfree(counter);
+        kfree(event);
 }
-static void perf_pending_sync(struct perf_counter *counter);
+static void perf_pending_sync(struct perf_event *event);
-static void free_counter(struct perf_counter *counter)
+static void free_event(struct perf_event *event)
 {
-        perf_pending_sync(counter);
+        perf_pending_sync(event);
-        if (!counter->parent) {
+        if (!event->parent) {
-                atomic_dec(&nr_counters);
+                atomic_dec(&nr_events);
-                if (counter->attr.mmap)
+                if (event->attr.mmap)
-                        atomic_dec(&nr_mmap_counters);
+                        atomic_dec(&nr_mmap_events);
-                if (counter->attr.comm)
+                if (event->attr.comm)
-                        atomic_dec(&nr_comm_counters);
+                        atomic_dec(&nr_comm_events);
-                if (counter->attr.task)
+                if (event->attr.task)
-                        atomic_dec(&nr_task_counters);
+                        atomic_dec(&nr_task_events);
        }
-        if (counter->output) {
+        if (event->output) {
-                fput(counter->output->filp);
+                fput(event->output->filp);
-                counter->output = NULL;
+                event->output = NULL;
        }
-        if (counter->destroy)
+        if (event->destroy)
-                counter->destroy(counter);
+                event->destroy(event);
-        put_ctx(counter->ctx);
+        put_ctx(event->ctx);
-        call_rcu(&counter->rcu_head, free_counter_rcu);
+        call_rcu(&event->rcu_head, free_event_rcu);
 }
 /*
@@ -1715,43 +1714,43 @@ static void free_counter(struct perf_counter *counter)
 */
 static int perf_release(struct inode *inode, struct file *file)
 {
-        struct perf_counter *counter = file->private_data;
+        struct perf_event *event = file->private_data;
-        struct perf_counter_context *ctx = counter->ctx;
+        struct perf_event_context *ctx = event->ctx;
        file->private_data = NULL;
        WARN_ON_ONCE(ctx->parent_ctx);
        mutex_lock(&ctx->mutex);
-        perf_counter_remove_from_context(counter);
+        perf_event_remove_from_context(event);
        mutex_unlock(&ctx->mutex);
-        mutex_lock(&counter->owner->perf_counter_mutex);
+        mutex_lock(&event->owner->perf_event_mutex);
-        list_del_init(&counter->owner_entry);
+        list_del_init(&event->owner_entry);
-        mutex_unlock(&counter->owner->perf_counter_mutex);
+        mutex_unlock(&event->owner->perf_event_mutex);
-        put_task_struct(counter->owner);
+        put_task_struct(event->owner);
-        free_counter(counter);
+        free_event(event);
        return 0;
 }
-static int perf_counter_read_size(struct perf_counter *counter)
+static int perf_event_read_size(struct perf_event *event)
 {
        int entry = sizeof(u64); /* value */
        int size = 0;
        int nr = 1;
-        if (counter->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+        if (event->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
                size += sizeof(u64);
-        if (counter->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+        if (event->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
                size += sizeof(u64);
-        if (counter->attr.read_format & PERF_FORMAT_ID)
+        if (event->attr.read_format & PERF_FORMAT_ID)
                entry += sizeof(u64);
-        if (counter->attr.read_format & PERF_FORMAT_GROUP) {
+        if (event->attr.read_format & PERF_FORMAT_GROUP) {
-                nr += counter->group_leader->nr_siblings;
+                nr += event->group_leader->nr_siblings;
                size += sizeof(u64);
        }
@@ -1760,27 +1759,27 @@ static int perf_counter_read_size(struct perf_counter *counter)
        return size;
 }
-static u64 perf_counter_read_value(struct perf_counter *counter)
+static u64 perf_event_read_value(struct perf_event *event)
 {
-        struct perf_counter *child;
+        struct perf_event *child;
        u64 total = 0;
-        total += perf_counter_read(counter);
+        total += perf_event_read(event);
-        list_for_each_entry(child, &counter->child_list, child_list)
+        list_for_each_entry(child, &event->child_list, child_list)
-                total += perf_counter_read(child);
+                total += perf_event_read(child);
        return total;
 }
-static int perf_counter_read_entry(struct perf_counter *counter,
+static int perf_event_read_entry(struct perf_event *event,
                                   u64 read_format, char __user *buf)
 {
        int n = 0, count = 0;
        u64 values[2];
-        values[n++] = perf_counter_read_value(counter);
+        values[n++] = perf_event_read_value(event);
        if (read_format & PERF_FORMAT_ID)
-                values[n++] = primary_counter_id(counter);
+                values[n++] = primary_event_id(event);
        count = n * sizeof(u64);
@@ -1790,10 +1789,10 @@ static int perf_counter_read_entry(struct perf_counter *counter,
        return count;
 }
-static int perf_counter_read_group(struct perf_counter *counter,
+static int perf_event_read_group(struct perf_event *event,
                                   u64 read_format, char __user *buf)
 {
-        struct perf_counter *leader = counter->group_leader, *sub;
+        struct perf_event *leader = event->group_leader, *sub;
        int n = 0, size = 0, err = -EFAULT;
        u64 values[3];
@@ -1812,14 +1811,14 @@ static int perf_counter_read_group(struct perf_counter *counter,
        if (copy_to_user(buf, values, size))
                return -EFAULT;
-        err = perf_counter_read_entry(leader, read_format, buf + size);
+        err = perf_event_read_entry(leader, read_format, buf + size);
        if (err < 0)
                return err;
        size += err;
-        list_for_each_entry(sub, &leader->sibling_list, list_entry) {
+        list_for_each_entry(sub, &leader->sibling_list, group_entry) {
-                err = perf_counter_read_entry(sub, read_format,
+                err = perf_event_read_entry(sub, read_format,
                                buf + size);
                if (err < 0)
                        return err;
@@ -1830,23 +1829,23 @@ static int perf_counter_read_group(struct perf_counter *counter,
        return size;
 }
-static int perf_counter_read_one(struct perf_counter *counter,
+static int perf_event_read_one(struct perf_event *event,
                                 u64 read_format, char __user *buf)
 {
        u64 values[4];
        int n = 0;
-        values[n++] = perf_counter_read_value(counter);
+        values[n++] = perf_event_read_value(event);
        if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) {
-                values[n++] = counter->total_time_enabled +
+                values[n++] = event->total_time_enabled +
-                        atomic64_read(&counter->child_total_time_enabled);
+                        atomic64_read(&event->child_total_time_enabled);
        }
        if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) {
-                values[n++] = counter->total_time_running +
+                values[n++] = event->total_time_running +
-                        atomic64_read(&counter->child_total_time_running);
+                        atomic64_read(&event->child_total_time_running);
        }
        if (read_format & PERF_FORMAT_ID)
-                values[n++] = primary_counter_id(counter);
+                values[n++] = primary_event_id(event);
        if (copy_to_user(buf, values, n * sizeof(u64)))
                return -EFAULT;
@@ -1855,32 +1854,32 @@ static int perf_counter_read_one(struct perf_counter *counter,
 }
 /*
- * Read the performance counter - simple non blocking version for now
+ * Read the performance event - simple non blocking version for now
 */
 static ssize_t
-perf_read_hw(struct perf_counter *counter, char __user *buf, size_t count)
+perf_read_hw(struct perf_event *event, char __user *buf, size_t count)
 {
-        u64 read_format = counter->attr.read_format;
+        u64 read_format = event->attr.read_format;
        int ret;
        /*
-         * Return end-of-file for a read on a counter that is in
+         * Return end-of-file for a read on a event that is in
         * error state (i.e. because it was pinned but it couldn't be
         * scheduled on to the CPU at some point).
         */
-        if (counter->state == PERF_COUNTER_STATE_ERROR)
+        if (event->state == PERF_EVENT_STATE_ERROR)
                return 0;
-        if (count < perf_counter_read_size(counter))
+        if (count < perf_event_read_size(event))
                return -ENOSPC;
-        WARN_ON_ONCE(counter->ctx->parent_ctx);
+        WARN_ON_ONCE(event->ctx->parent_ctx);
-        mutex_lock(&counter->child_mutex);
+        mutex_lock(&event->child_mutex);
        if (read_format & PERF_FORMAT_GROUP)
-                ret = perf_counter_read_group(counter, read_format, buf);
+                ret = perf_event_read_group(event, read_format, buf);
        else
-                ret = perf_counter_read_one(counter, read_format, buf);
+                ret = perf_event_read_one(event, read_format, buf);
-        mutex_unlock(&counter->child_mutex);
+        mutex_unlock(&event->child_mutex);
        return ret;
 }
@@ -1888,79 +1887,79 @@ perf_read_hw(struct perf_counter *counter, char __user *buf, size_t count)
 static ssize_t
 perf_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
 {
-        struct perf_counter *counter = file->private_data;
+        struct perf_event *event = file->private_data;
-        return perf_read_hw(counter, buf, count);
+        return perf_read_hw(event, buf, count);
 }
 static unsigned int perf_poll(struct file *file, poll_table *wait)
 {
-        struct perf_counter *counter = file->private_data;
+        struct perf_event *event = file->private_data;
        struct perf_mmap_data *data;
        unsigned int events = POLL_HUP;
        rcu_read_lock();
-        data = rcu_dereference(counter->data);
+        data = rcu_dereference(event->data);
        if (data)
                events = atomic_xchg(&data->poll, 0);
        rcu_read_unlock();
-        poll_wait(file, &counter->waitq, wait);
+        poll_wait(file, &event->waitq, wait);
        return events;
 }
-static void perf_counter_reset(struct perf_counter *counter)
+static void perf_event_reset(struct perf_event *event)
 {
-        (void)perf_counter_read(counter);
+        (void)perf_event_read(event);
-        atomic64_set(&counter->count, 0);
+        atomic64_set(&event->count, 0);
-        perf_counter_update_userpage(counter);
+        perf_event_update_userpage(event);
 }
 /*
- * Holding the top-level counter's child_mutex means that any
+ * Holding the top-level event's child_mutex means that any
- * descendant process that has inherited this counter will block
+ * descendant process that has inherited this event will block
- * in sync_child_counter if it goes to exit, thus satisfying the
+ * in sync_child_event if it goes to exit, thus satisfying the
- * task existence requirements of perf_counter_enable/disable.
+ * task existence requirements of perf_event_enable/disable.
 */
-static void perf_counter_for_each_child(struct perf_counter *counter,
+static void perf_event_for_each_child(struct perf_event *event,
-                                        void (*func)(struct perf_counter *))
+                                        void (*func)(struct perf_event *))
 {
-        struct perf_counter *child;
+        struct perf_event *child;
-        WARN_ON_ONCE(counter->ctx->parent_ctx);
+        WARN_ON_ONCE(event->ctx->parent_ctx);
-        mutex_lock(&counter->child_mutex);
+        mutex_lock(&event->child_mutex);
-        func(counter);
+        func(event);
-        list_for_each_entry(child, &counter->child_list, child_list)
+        list_for_each_entry(child, &event->child_list, child_list)
                func(child);
-        mutex_unlock(&counter->child_mutex);
+        mutex_unlock(&event->child_mutex);
 }
-static void perf_counter_for_each(struct perf_counter *counter,
+static void perf_event_for_each(struct perf_event *event,
-                                  void (*func)(struct perf_counter *))
+                                  void (*func)(struct perf_event *))
 {
-        struct perf_counter_context *ctx = counter->ctx;
+        struct perf_event_context *ctx = event->ctx;
-        struct perf_counter *sibling;
+        struct perf_event *sibling;
        WARN_ON_ONCE(ctx->parent_ctx);
        mutex_lock(&ctx->mutex);
-        counter = counter->group_leader;
+        event = event->group_leader;
-        perf_counter_for_each_child(counter, func);
+        perf_event_for_each_child(event, func);
-        func(counter);
+        func(event);
-        list_for_each_entry(sibling, &counter->sibling_list, list_entry)
+        list_for_each_entry(sibling, &event->sibling_list, group_entry)
-                perf_counter_for_each_child(counter, func);
+                perf_event_for_each_child(event, func);
        mutex_unlock(&ctx->mutex);
 }
-static int perf_counter_period(struct perf_counter *counter, u64 __user *arg)
+static int perf_event_period(struct perf_event *event, u64 __user *arg)
 {
-        struct perf_counter_context *ctx = counter->ctx;
+        struct perf_event_context *ctx = event->ctx;
        unsigned long size;
        int ret = 0;
        u64 value;
-        if (!counter->attr.sample_period)
+        if (!event->attr.sample_period)
                return -EINVAL;
        size = copy_from_user(&value, arg, sizeof(value));
@@ -1971,16 +1970,16 @@ static int perf_counter_period(struct perf_counter *counter, u64 __user *arg)
                return -EINVAL;
        spin_lock_irq(&ctx->lock);
-        if (counter->attr.freq) {
+        if (event->attr.freq) {
-                if (value > sysctl_perf_counter_sample_rate) {
+                if (value > sysctl_perf_event_sample_rate) {
                        ret = -EINVAL;
                        goto unlock;
                }
-                counter->attr.sample_freq = value;
+                event->attr.sample_freq = value;
        } else {
-                counter->attr.sample_period = value;
+                event->attr.sample_period = value;
-                counter->hw.sample_period = value;
+                event->hw.sample_period = value;
        }
 unlock:
        spin_unlock_irq(&ctx->lock);
@@ -1988,80 +1987,80 @@ unlock:
        return ret;
 }
-int perf_counter_set_output(struct perf_counter *counter, int output_fd);
+int perf_event_set_output(struct perf_event *event, int output_fd);
 static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
-        struct perf_counter *counter = file->private_data;
+        struct perf_event *event = file->private_data;
-        void (*func)(struct perf_counter *);
+        void (*func)(struct perf_event *);
        u32 flags = arg;
        switch (cmd) {
-        case PERF_COUNTER_IOC_ENABLE:
+        case PERF_EVENT_IOC_ENABLE:
-                func = perf_counter_enable;
+                func = perf_event_enable;
                break;
-        case PERF_COUNTER_IOC_DISABLE:
+        case PERF_EVENT_IOC_DISABLE:
-                func = perf_counter_disable;
+                func = perf_event_disable;
                break;
-        case PERF_COUNTER_IOC_RESET:
+        case PERF_EVENT_IOC_RESET:
-                func = perf_counter_reset;
+                func = perf_event_reset;
                break;
-        case PERF_COUNTER_IOC_REFRESH:
+        case PERF_EVENT_IOC_REFRESH:
-                return perf_counter_refresh(counter, arg);
+                return perf_event_refresh(event, arg);
-        case PERF_COUNTER_IOC_PERIOD:
+        case PERF_EVENT_IOC_PERIOD:
-                return perf_counter_period(counter, (u64 __user *)arg);
+                return perf_event_period(event, (u64 __user *)arg);
-        case PERF_COUNTER_IOC_SET_OUTPUT:
+        case PERF_EVENT_IOC_SET_OUTPUT:
-                return perf_counter_set_output(counter, arg);
+                return perf_event_set_output(event, arg);
        default:
                return -ENOTTY;
        }
        if (flags & PERF_IOC_FLAG_GROUP)
-                perf_counter_for_each(counter, func);
+                perf_event_for_each(event, func);
        else
-                perf_counter_for_each_child(counter, func);
+                perf_event_for_each_child(event, func);
        return 0;
 }
-int perf_counter_task_enable(void)
+int perf_event_task_enable(void)
 {
-        struct perf_counter *counter;
+        struct perf_event *event;
-        mutex_lock(&current->perf_counter_mutex);
+        mutex_lock(&current->perf_event_mutex);
-        list_for_each_entry(counter, &current->perf_counter_list, owner_entry)
+        list_for_each_entry(event, &current->perf_event_list, owner_entry)
-                perf_counter_for_each_child(counter, perf_counter_enable);
+                perf_event_for_each_child(event, perf_event_enable);
-        mutex_unlock(&current->perf_counter_mutex);
+        mutex_unlock(&current->perf_event_mutex);
        return 0;
 }
-int perf_counter_task_disable(void)
+int perf_event_task_disable(void)
 {
-        struct perf_counter *counter;
+        struct perf_event *event;
-        mutex_lock(&current->perf_counter_mutex);
+        mutex_lock(&current->perf_event_mutex);
-        list_for_each_entry(counter, &current->perf_counter_list, owner_entry)
+        list_for_each_entry(event, &current->perf_event_list, owner_entry)
-                perf_counter_for_each_child(counter, perf_counter_disable);
+                perf_event_for_each_child(event, perf_event_disable);
-        mutex_unlock(&current->perf_counter_mutex);
+        mutex_unlock(&current->perf_event_mutex);
        return 0;
 }
-#ifndef PERF_COUNTER_INDEX_OFFSET
+#ifndef PERF_EVENT_INDEX_OFFSET
-# define PERF_COUNTER_INDEX_OFFSET 0
+# define PERF_EVENT_INDEX_OFFSET 0
 #endif
-static int perf_counter_index(struct perf_counter *counter)
+static int perf_event_index(struct perf_event *event)
 {
-        if (counter->state != PERF_COUNTER_STATE_ACTIVE)
+        if (event->state != PERF_EVENT_STATE_ACTIVE)
                return 0;
-        return counter->hw.idx + 1 - PERF_COUNTER_INDEX_OFFSET;
+        return event->hw.idx + 1 - PERF_EVENT_INDEX_OFFSET;
 }
 /*
@@ -2069,13 +2068,13 @@ static int perf_counter_index(struct perf_counter *counter)
 * the seqlock logic goes bad. We can not serialize this because the arch
 * code calls this from NMI context.
 */
-void perf_counter_update_userpage(struct perf_counter *counter)
+void perf_event_update_userpage(struct perf_event *event)
 {
-        struct perf_counter_mmap_page *userpg;
+        struct perf_event_mmap_page *userpg;
        struct perf_mmap_data *data;
        rcu_read_lock();
-        data = rcu_dereference(counter->data);
+        data = rcu_dereference(event->data);
        if (!data)
                goto unlock;
@@ -2088,16 +2087,16 @@ void perf_counter_update_userpage(struct perf_counter *counter)
        preempt_disable();
        ++userpg->lock;
        barrier();
-        userpg->index = perf_counter_index(counter);
+        userpg->index = perf_event_index(event);
-        userpg->offset = atomic64_read(&counter->count);
+        userpg->offset = atomic64_read(&event->count);
-        if (counter->state == PERF_COUNTER_STATE_ACTIVE)
+        if (event->state == PERF_EVENT_STATE_ACTIVE)
-                userpg->offset -= atomic64_read(&counter->hw.prev_count);
+                userpg->offset -= atomic64_read(&event->hw.prev_count);
-        userpg->time_enabled = counter->total_time_enabled +
+        userpg->time_enabled = event->total_time_enabled +
-                        atomic64_read(&counter->child_total_time_enabled);
+                        atomic64_read(&event->child_total_time_enabled);
-        userpg->time_running = counter->total_time_running +
+        userpg->time_running = event->total_time_running +
-                        atomic64_read(&counter->child_total_time_running);
+                        atomic64_read(&event->child_total_time_running);
        barrier();
        ++userpg->lock;
@@ -2108,7 +2107,7 @@ unlock:
 static int perf_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
-        struct perf_counter *counter = vma->vm_file->private_data;
+        struct perf_event *event = vma->vm_file->private_data;
        struct perf_mmap_data *data;
        int ret = VM_FAULT_SIGBUS;
@@ -2119,7 +2118,7 @@ static int perf_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
        }
        rcu_read_lock();
-        data = rcu_dereference(counter->data);
+        data = rcu_dereference(event->data);
        if (!data)
                goto unlock;
@@ -2148,13 +2147,13 @@ unlock:
        return ret;
 }
-static int perf_mmap_data_alloc(struct perf_counter *counter, int nr_pages)
+static int perf_mmap_data_alloc(struct perf_event *event, int nr_pages)
 {
        struct perf_mmap_data *data;
        unsigned long size;
        int i;
-        WARN_ON(atomic_read(&counter->mmap_count));
+        WARN_ON(atomic_read(&event->mmap_count));
        size = sizeof(struct perf_mmap_data);
        size += nr_pages * sizeof(void *);
@@ -2176,14 +2175,14 @@ static int perf_mmap_data_alloc(struct perf_counter *counter, int nr_pages)
        data->nr_pages = nr_pages;
        atomic_set(&data->lock, -1);
-        if (counter->attr.watermark) {
+        if (event->attr.watermark) {
                data->watermark = min_t(long, PAGE_SIZE * nr_pages,
-                                      counter->attr.wakeup_watermark);
+                                      event->attr.wakeup_watermark);
        }
        if (!data->watermark)
                data->watermark = max(PAGE_SIZE, PAGE_SIZE * nr_pages / 4);
-        rcu_assign_pointer(counter->data, data);
+        rcu_assign_pointer(event->data, data);
        return 0;
@@ -2222,35 +2221,35 @@ static void __perf_mmap_data_free(struct rcu_head *rcu_head)
        kfree(data);
 }
-static void perf_mmap_data_free(struct perf_counter *counter)
+static void perf_mmap_data_free(struct perf_event *event)
 {
-        struct perf_mmap_data *data = counter->data;
+        struct perf_mmap_data *data = event->data;
-        WARN_ON(atomic_read(&counter->mmap_count));
+        WARN_ON(atomic_read(&event->mmap_count));
-        rcu_assign_pointer(counter->data, NULL);
+        rcu_assign_pointer(event->data, NULL);
        call_rcu(&data->rcu_head, __perf_mmap_data_free);
 }
 static void perf_mmap_open(struct vm_area_struct *vma)
 {
-        struct perf_counter *counter = vma->vm_file->private_data;
+        struct perf_event *event = vma->vm_file->private_data;
-        atomic_inc(&counter->mmap_count);
+        atomic_inc(&event->mmap_count);
 }
 static void perf_mmap_close(struct vm_area_struct *vma)
 {
-        struct perf_counter *counter = vma->vm_file->private_data;
+        struct perf_event *event = vma->vm_file->private_data;
-        WARN_ON_ONCE(counter->ctx->parent_ctx);
+        WARN_ON_ONCE(event->ctx->parent_ctx);
-        if (atomic_dec_and_mutex_lock(&counter->mmap_count, &counter->mmap_mutex)) {
+        if (atomic_dec_and_mutex_lock(&event->mmap_count, &event->mmap_mutex)) {
                struct user_struct *user = current_user();
-                atomic_long_sub(counter->data->nr_pages + 1, &user->locked_vm);
+                atomic_long_sub(event->data->nr_pages + 1, &user->locked_vm);
-                vma->vm_mm->locked_vm -= counter->data->nr_locked;
+                vma->vm_mm->locked_vm -= event->data->nr_locked;
-                perf_mmap_data_free(counter);
+                perf_mmap_data_free(event);
-                mutex_unlock(&counter->mmap_mutex);
+                mutex_unlock(&event->mmap_mutex);
        }
 }
@@ -2263,7 +2262,7 @@ static struct vm_operations_struct perf_mmap_vmops = {
 static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 {
-        struct perf_counter *counter = file->private_data;
+        struct perf_event *event = file->private_data;
        unsigned long user_locked, user_lock_limit;
        struct user_struct *user = current_user();
        unsigned long locked, lock_limit;
@@ -2291,21 +2290,21 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
        if (vma->vm_pgoff != 0)
                return -EINVAL;
-        WARN_ON_ONCE(counter->ctx->parent_ctx);
+        WARN_ON_ONCE(event->ctx->parent_ctx);
-        mutex_lock(&counter->mmap_mutex);
+        mutex_lock(&event->mmap_mutex);
-        if (counter->output) {
+        if (event->output) {
                ret = -EINVAL;
                goto unlock;
        }
-        if (atomic_inc_not_zero(&counter->mmap_count)) {
+        if (atomic_inc_not_zero(&event->mmap_count)) {
-                if (nr_pages != counter->data->nr_pages)
+                if (nr_pages != event->data->nr_pages)
                        ret = -EINVAL;
                goto unlock;
        }
        user_extra = nr_pages + 1;
-        user_lock_limit = sysctl_perf_counter_mlock >> (PAGE_SHIFT - 10);
+        user_lock_limit = sysctl_perf_event_mlock >> (PAGE_SHIFT - 10);
        /*
         * Increase the limit linearly with more CPUs:
@@ -2328,20 +2327,20 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
                goto unlock;
        }
-        WARN_ON(counter->data);
+        WARN_ON(event->data);
-        ret = perf_mmap_data_alloc(counter, nr_pages);
+        ret = perf_mmap_data_alloc(event, nr_pages);
        if (ret)
                goto unlock;
-        atomic_set(&counter->mmap_count, 1);
+        atomic_set(&event->mmap_count, 1);
        atomic_long_add(user_extra, &user->locked_vm);
        vma->vm_mm->locked_vm += extra;
-        counter->data->nr_locked = extra;
+        event->data->nr_locked = extra;
        if (vma->vm_flags & VM_WRITE)
-                counter->data->writable = 1;
+                event->data->writable = 1;
 unlock:
-        mutex_unlock(&counter->mmap_mutex);
+        mutex_unlock(&event->mmap_mutex);
        vma->vm_flags |= VM_RESERVED;
        vma->vm_ops = &perf_mmap_vmops;
@@ -2352,11 +2351,11 @@ unlock:
 static int perf_fasync(int fd, struct file *filp, int on)
 {
        struct inode *inode = filp->f_path.dentry->d_inode;
-        struct perf_counter *counter = filp->private_data;
+        struct perf_event *event = filp->private_data;
        int retval;
        mutex_lock(&inode->i_mutex);
-        retval = fasync_helper(fd, filp, on, &counter->fasync);
+        retval = fasync_helper(fd, filp, on, &event->fasync);
        mutex_unlock(&inode->i_mutex);
        if (retval < 0)
@@ -2376,19 +2375,19 @@ static const struct file_operations perf_fops = {
 };
 /*
- * Perf counter wakeup
+ * Perf event wakeup
 *
 * If there's data, ensure we set the poll() state and publish everything
 * to user-space before waking everybody up.
 */
-void perf_counter_wakeup(struct perf_counter *counter)
+void perf_event_wakeup(struct perf_event *event)
 {
-        wake_up_all(&counter->waitq);
+        wake_up_all(&event->waitq);
-        if (counter->pending_kill) {
+        if (event->pending_kill) {
-                kill_fasync(&counter->fasync, SIGIO, counter->pending_kill);
+                kill_fasync(&event->fasync, SIGIO, event->pending_kill);
-                counter->pending_kill = 0;
+                event->pending_kill = 0;
        }
 }
@@ -2401,19 +2400,19 @@ void perf_counter_wakeup(struct perf_counter *counter)
 * single linked list and use cmpxchg() to add entries lockless.
 */
-static void perf_pending_counter(struct perf_pending_entry *entry)
+static void perf_pending_event(struct perf_pending_entry *entry)
 {
-        struct perf_counter *counter = container_of(entry,
+        struct perf_event *event = container_of(entry,
-                        struct perf_counter, pending);
+                        struct perf_event, pending);
-        if (counter->pending_disable) {
+        if (event->pending_disable) {
-                counter->pending_disable = 0;
+                event->pending_disable = 0;
-                __perf_counter_disable(counter);
+                __perf_event_disable(event);
        }
-        if (counter->pending_wakeup) {
+        if (event->pending_wakeup) {
-                counter->pending_wakeup = 0;
+                event->pending_wakeup = 0;
-                perf_counter_wakeup(counter);
+                perf_event_wakeup(event);
        }
 }
@@ -2439,7 +2438,7 @@ static void perf_pending_queue(struct perf_pending_entry *entry,
                entry->next = *head;
        } while (cmpxchg(head, entry->next, entry) != entry->next);
-        set_perf_counter_pending();
+        set_perf_event_pending();
        put_cpu_var(perf_pending_head);
 }
@@ -2472,7 +2471,7 @@ static int __perf_pending_run(void)
        return nr;
 }
-static inline int perf_not_pending(struct perf_counter *counter)
+static inline int perf_not_pending(struct perf_event *event)
 {
        /*
         * If we flush on whatever cpu we run, there is a chance we don't
@@ -2487,15 +2486,15 @@ static inline int perf_not_pending(struct perf_counter *counter)
         * so that we do not miss the wakeup. -- see perf_pending_handle()
         */
        smp_rmb();
-        return counter->pending.next == NULL;
+        return event->pending.next == NULL;
 }
-static void perf_pending_sync(struct perf_counter *counter)
+static void perf_pending_sync(struct perf_event *event)
 {
-        wait_event(counter->waitq, perf_not_pending(counter));
+        wait_event(event->waitq, perf_not_pending(event));
 }
-void perf_counter_do_pending(void)
+void perf_event_do_pending(void)
 {
        __perf_pending_run();
 }
@@ -2536,25 +2535,25 @@ static void perf_output_wakeup(struct perf_output_handle *handle)
        atomic_set(&handle->data->poll, POLL_IN);
        if (handle->nmi) {
-                handle->counter->pending_wakeup = 1;
+                handle->event->pending_wakeup = 1;
-                perf_pending_queue(&handle->counter->pending,
+                perf_pending_queue(&handle->event->pending,
-                                   perf_pending_counter);
+                                   perf_pending_event);
        } else
-                perf_counter_wakeup(handle->counter);
+                perf_event_wakeup(handle->event);
 }
 /*
 * Curious locking construct.
 *
- * We need to ensure a later event doesn't publish a head when a former
+ * We need to ensure a later event_id doesn't publish a head when a former
- * event isn't done writing. However since we need to deal with NMIs we
+ * event_id isn't done writing. However since we need to deal with NMIs we
 * cannot fully serialize things.
 *
 * What we do is serialize between CPUs so we only have to deal with NMI
 * nesting on a single CPU.
 *
 * We only publish the head (and generate a wakeup) when the outer-most
- * event completes.
+ * event_id completes.
 */
 static void perf_output_lock(struct perf_output_handle *handle)
 {
@@ -2658,10 +2657,10 @@ void perf_output_copy(struct perf_output_handle *handle,
 }
 int perf_output_begin(struct perf_output_handle *handle,
-                      struct perf_counter *counter, unsigned int size,
+                      struct perf_event *event, unsigned int size,
                      int nmi, int sample)
 {
-        struct perf_counter *output_counter;
+        struct perf_event *output_event;
        struct perf_mmap_data *data;
        unsigned long tail, offset, head;
        int have_lost;
@@ -2673,21 +2672,21 @@ int perf_output_begin(struct perf_output_handle *handle,
        rcu_read_lock();
        /*
-         * For inherited counters we send all the output towards the parent.
+         * For inherited events we send all the output towards the parent.
         */
-        if (counter->parent)
+        if (event->parent)
-                counter = counter->parent;
+                event = event->parent;
-        output_counter = rcu_dereference(counter->output);
+        output_event = rcu_dereference(event->output);
-        if (output_counter)
+        if (output_event)
-                counter = output_counter;
+                event = output_event;
-        data = rcu_dereference(counter->data);
+        data = rcu_dereference(event->data);
        if (!data)
                goto out;
        handle->data    = data;
-        handle->counter = counter;
+        handle->event   = event;
        handle->nmi     = nmi;
        handle->sample  = sample;
@@ -2721,10 +2720,10 @@ int perf_output_begin(struct perf_output_handle *handle,
                atomic_set(&data->wakeup, 1);
        if (have_lost) {
-                lost_event.header.type = PERF_EVENT_LOST;
+                lost_event.header.type = PERF_RECORD_LOST;
                lost_event.header.misc = 0;
                lost_event.header.size = sizeof(lost_event);
-                lost_event.id          = counter->id;
+                lost_event.id          = event->id;
                lost_event.lost        = atomic_xchg(&data->lost, 0);
                perf_output_put(handle, lost_event);
@@ -2743,10 +2742,10 @@ out:
 void perf_output_end(struct perf_output_handle *handle)
 {
-        struct perf_counter *counter = handle->counter;
+        struct perf_event *event = handle->event;
        struct perf_mmap_data *data = handle->data;
-        int wakeup_events = counter->attr.wakeup_events;
+        int wakeup_events = event->attr.wakeup_events;
        if (handle->sample && wakeup_events) {
                int events = atomic_inc_return(&data->events);
@@ -2760,58 +2759,58 @@ void perf_output_end(struct perf_output_handle *handle)
        rcu_read_unlock();
 }
-static u32 perf_counter_pid(struct perf_counter *counter, struct task_struct *p)
+static u32 perf_event_pid(struct perf_event *event, struct task_struct *p)
 {
        /*
-         * only top level counters have the pid namespace they were created in
+         * only top level events have the pid namespace they were created in
         */
-        if (counter->parent)
+        if (event->parent)
-                counter = counter->parent;
+                event = event->parent;
-        return task_tgid_nr_ns(p, counter->ns);
+        return task_tgid_nr_ns(p, event->ns);
 }
-static u32 perf_counter_tid(struct perf_counter *counter, struct task_struct *p)
+static u32 perf_event_tid(struct perf_event *event, struct task_struct *p)
 {
        /*
-         * only top level counters have the pid namespace they were created in
+         * only top level events have the pid namespace they were created in
         */
-        if (counter->parent)
+        if (event->parent)
-                counter = counter->parent;
+                event = event->parent;
-        return task_pid_nr_ns(p, counter->ns);
+        return task_pid_nr_ns(p, event->ns);
 }
 static void perf_output_read_one(struct perf_output_handle *handle,
-                                 struct perf_counter *counter)
+                                 struct perf_event *event)
 {
-        u64 read_format = counter->attr.read_format;
+        u64 read_format = event->attr.read_format;
        u64 values[4];
        int n = 0;
-        values[n++] = atomic64_read(&counter->count);
+        values[n++] = atomic64_read(&event->count);
        if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) {
-                values[n++] = counter->total_time_enabled +
+                values[n++] = event->total_time_enabled +
-                        atomic64_read(&counter->child_total_time_enabled);
+                        atomic64_read(&event->child_total_time_enabled);
        }
        if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) {
-                values[n++] = counter->total_time_running +
+                values[n++] = event->total_time_running +
-                        atomic64_read(&counter->child_total_time_running);
+                        atomic64_read(&event->child_total_time_running);
        }
        if (read_format & PERF_FORMAT_ID)
-                values[n++] = primary_counter_id(counter);
+                values[n++] = primary_event_id(event);
        perf_output_copy(handle, values, n * sizeof(u64));
 }
 /*
- * XXX PERF_FORMAT_GROUP vs inherited counters seems difficult.
+ * XXX PERF_FORMAT_GROUP vs inherited events seems difficult.
 */
 static void perf_output_read_group(struct perf_output_handle *handle,
-                            struct perf_counter *counter)
+                            struct perf_event *event)
 {
-        struct perf_counter *leader = counter->group_leader, *sub;
+        struct perf_event *leader = event->group_leader, *sub;
-        u64 read_format = counter->attr.read_format;
+        u64 read_format = event->attr.read_format;
        u64 values[5];
        int n = 0;
@@ -2823,42 +2822,42 @@ static void perf_output_read_group(struct perf_output_handle *handle,
        if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
                values[n++] = leader->total_time_running;
-        if (leader != counter)
+        if (leader != event)
                leader->pmu->read(leader);
        values[n++] = atomic64_read(&leader->count);
        if (read_format & PERF_FORMAT_ID)
-                values[n++] = primary_counter_id(leader);
+                values[n++] = primary_event_id(leader);
        perf_output_copy(handle, values, n * sizeof(u64));
-        list_for_each_entry(sub, &leader->sibling_list, list_entry) {
+        list_for_each_entry(sub, &leader->sibling_list, group_entry) {
                n = 0;
-                if (sub != counter)
+                if (sub != event)
                        sub->pmu->read(sub);
                values[n++] = atomic64_read(&sub->count);
                if (read_format & PERF_FORMAT_ID)
-                        values[n++] = primary_counter_id(sub);
+                        values[n++] = primary_event_id(sub);
                perf_output_copy(handle, values, n * sizeof(u64));
        }
 }
 static void perf_output_read(struct perf_output_handle *handle,
-                             struct perf_counter *counter)
+                             struct perf_event *event)
 {
-        if (counter->attr.read_format & PERF_FORMAT_GROUP)
+        if (event->attr.read_format & PERF_FORMAT_GROUP)
-                perf_output_read_group(handle, counter);
+                perf_output_read_group(handle, event);
        else
-                perf_output_read_one(handle, counter);
+                perf_output_read_one(handle, event);
 }
 void perf_output_sample(struct perf_output_handle *handle,
                        struct perf_event_header *header,
                        struct perf_sample_data *data,
-                        struct perf_counter *counter)
+                        struct perf_event *event)
 {
        u64 sample_type = data->type;
@@ -2889,7 +2888,7 @@ void perf_output_sample(struct perf_output_handle *handle,
                perf_output_put(handle, data->period);
        if (sample_type & PERF_SAMPLE_READ)
-                perf_output_read(handle, counter);
+                perf_output_read(handle, event);
        if (sample_type & PERF_SAMPLE_CALLCHAIN) {
                if (data->callchain) {
@@ -2927,14 +2926,14 @@ void perf_output_sample(struct perf_output_handle *handle,
 void perf_prepare_sample(struct perf_event_header *header,
                         struct perf_sample_data *data,
-                         struct perf_counter *counter,
+                         struct perf_event *event,
                         struct pt_regs *regs)
 {
-        u64 sample_type = counter->attr.sample_type;
+        u64 sample_type = event->attr.sample_type;
        data->type = sample_type;
-        header->type = PERF_EVENT_SAMPLE;
+        header->type = PERF_RECORD_SAMPLE;
        header->size = sizeof(*header);
        header->misc = 0;
@@ -2948,8 +2947,8 @@ void perf_prepare_sample(struct perf_event_header *header,
        if (sample_type & PERF_SAMPLE_TID) {
                /* namespace issues */
-                data->tid_entry.pid = perf_counter_pid(counter, current);
+                data->tid_entry.pid = perf_event_pid(event, current);
-                data->tid_entry.tid = perf_counter_tid(counter, current);
+                data->tid_entry.tid = perf_event_tid(event, current);
                header->size += sizeof(data->tid_entry);
        }
@@ -2964,13 +2963,13 @@ void perf_prepare_sample(struct perf_event_header *header,
                header->size += sizeof(data->addr);
        if (sample_type & PERF_SAMPLE_ID) {
-                data->id = primary_counter_id(counter);
+                data->id = primary_event_id(event);
                header->size += sizeof(data->id);
        }
        if (sample_type & PERF_SAMPLE_STREAM_ID) {
-                data->stream_id = counter->id;
+                data->stream_id = event->id;
                header->size += sizeof(data->stream_id);
        }
@@ -2986,7 +2985,7 @@ void perf_prepare_sample(struct perf_event_header *header,
                header->size += sizeof(data->period);
        if (sample_type & PERF_SAMPLE_READ)
-                header->size += perf_counter_read_size(counter);
+                header->size += perf_event_read_size(event);
        if (sample_type & PERF_SAMPLE_CALLCHAIN) {
                int size = 1;
@@ -3012,25 +3011,25 @@ void perf_prepare_sample(struct perf_event_header *header,
        }
 }
-static void perf_counter_output(struct perf_counter *counter, int nmi,
+static void perf_event_output(struct perf_event *event, int nmi,
                                struct perf_sample_data *data,
                                struct pt_regs *regs)
 {
        struct perf_output_handle handle;
        struct perf_event_header header;
-        perf_prepare_sample(&header, data, counter, regs);
+        perf_prepare_sample(&header, data, event, regs);
-        if (perf_output_begin(&handle, counter, header.size, nmi, 1))
+        if (perf_output_begin(&handle, event, header.size, nmi, 1))
                return;
-        perf_output_sample(&handle, &header, data, counter);
+        perf_output_sample(&handle, &header, data, event);
        perf_output_end(&handle);
 }
 /*
- * read event
+ * read event_id
 */
 struct perf_read_event {
@@ -3041,27 +3040,27 @@ struct perf_read_event {
 };
 static void
-perf_counter_read_event(struct perf_counter *counter,
+perf_event_read_event(struct perf_event *event,
                        struct task_struct *task)
 {
        struct perf_output_handle handle;
-        struct perf_read_event event = {
+        struct perf_read_event read_event = {
                .header = {
-                        .type = PERF_EVENT_READ,
+                        .type = PERF_RECORD_READ,
                        .misc = 0,
-                        .size = sizeof(event) + perf_counter_read_size(counter),
+                        .size = sizeof(read_event) + perf_event_read_size(event),
                },
-                .pid = perf_counter_pid(counter, task),
+                .pid = perf_event_pid(event, task),
-                .tid = perf_counter_tid(counter, task),
+                .tid = perf_event_tid(event, task),
        };
        int ret;
-        ret = perf_output_begin(&handle, counter, event.header.size, 0, 0);
+        ret = perf_output_begin(&handle, event, read_event.header.size, 0, 0);
        if (ret)
                return;
-        perf_output_put(&handle, event);
+        perf_output_put(&handle, read_event);
-        perf_output_read(&handle, counter);
+        perf_output_read(&handle, event);
        perf_output_end(&handle);
 }
@@ -3074,7 +3073,7 @@ perf_counter_read_event(struct perf_counter *counter,
 struct perf_task_event {
        struct task_struct              *task;
-        struct perf_counter_context     *task_ctx;
+        struct perf_event_context       *task_ctx;
        struct {
                struct perf_event_header        header;
@@ -3084,10 +3083,10 @@ struct perf_task_event {
                u32                             tid;
                u32                             ptid;
                u64                             time;
-        } event;
+        } event_id;
 };
-static void perf_counter_task_output(struct perf_counter *counter,
+static void perf_event_task_output(struct perf_event *event,
                                     struct perf_task_event *task_event)
 {
        struct perf_output_handle handle;
@@ -3095,85 +3094,85 @@ static void perf_counter_task_output(struct perf_counter *counter,
        struct task_struct *task = task_event->task;
        int ret;
-        size  = task_event->event.header.size;
+        size  = task_event->event_id.header.size;
-        ret = perf_output_begin(&handle, counter, size, 0, 0);
+        ret = perf_output_begin(&handle, event, size, 0, 0);
        if (ret)
                return;
-        task_event->event.pid = perf_counter_pid(counter, task);
+        task_event->event_id.pid = perf_event_pid(event, task);
-        task_event->event.ppid = perf_counter_pid(counter, current);
+        task_event->event_id.ppid = perf_event_pid(event, current);
-        task_event->event.tid = perf_counter_tid(counter, task);
+        task_event->event_id.tid = perf_event_tid(event, task);
-        task_event->event.ptid = perf_counter_tid(counter, current);
+        task_event->event_id.ptid = perf_event_tid(event, current);
-        task_event->event.time = perf_clock();
+        task_event->event_id.time = perf_clock();
-        perf_output_put(&handle, task_event->event);
+        perf_output_put(&handle, task_event->event_id);
        perf_output_end(&handle);
 }
-static int perf_counter_task_match(struct perf_counter *counter)
+static int perf_event_task_match(struct perf_event *event)
 {
-        if (counter->attr.comm || counter->attr.mmap || counter->attr.task)
+        if (event->attr.comm || event->attr.mmap || event->attr.task)
                return 1;
        return 0;
 }
-static void perf_counter_task_ctx(struct perf_counter_context *ctx,
+static void perf_event_task_ctx(struct perf_event_context *ctx,
                                  struct perf_task_event *task_event)
 {
-        struct perf_counter *counter;
+        struct perf_event *event;
        if (system_state != SYSTEM_RUNNING || list_empty(&ctx->event_list))
                return;
        rcu_read_lock();
-        list_for_each_entry_rcu(counter, &ctx->event_list, event_entry) {
+        list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
-                if (perf_counter_task_match(counter))
+                if (perf_event_task_match(event))
-                        perf_counter_task_output(counter, task_event);
+                        perf_event_task_output(event, task_event);
        }
        rcu_read_unlock();
 }
-static void perf_counter_task_event(struct perf_task_event *task_event)
+static void perf_event_task_event(struct perf_task_event *task_event)
 {
        struct perf_cpu_context *cpuctx;
-        struct perf_counter_context *ctx = task_event->task_ctx;
+        struct perf_event_context *ctx = task_event->task_ctx;
        cpuctx = &get_cpu_var(perf_cpu_context);
-        perf_counter_task_ctx(&cpuctx->ctx, task_event);
+        perf_event_task_ctx(&cpuctx->ctx, task_event);
        put_cpu_var(perf_cpu_context);
        rcu_read_lock();
        if (!ctx)
-                ctx = rcu_dereference(task_event->task->perf_counter_ctxp);
+                ctx = rcu_dereference(task_event->task->perf_event_ctxp);
        if (ctx)
-                perf_counter_task_ctx(ctx, task_event);
+                perf_event_task_ctx(ctx, task_event);
        rcu_read_unlock();
 }
-static void perf_counter_task(struct task_struct *task,
+static void perf_event_task(struct task_struct *task,
-                              struct perf_counter_context *task_ctx,
+                              struct perf_event_context *task_ctx,
                              int new)
 {
        struct perf_task_event task_event;
-        if (!atomic_read(&nr_comm_counters) &&
+        if (!atomic_read(&nr_comm_events) &&
-            !atomic_read(&nr_mmap_counters) &&
+            !atomic_read(&nr_mmap_events) &&
-            !atomic_read(&nr_task_counters))
+            !atomic_read(&nr_task_events))
                return;
        task_event = (struct perf_task_event){
                .task     = task,
                .task_ctx = task_ctx,
-                .event    = {
+                .event_id    = {
                        .header = {
-                                .type = new ? PERF_EVENT_FORK : PERF_EVENT_EXIT,
+                                .type = new ? PERF_RECORD_FORK : PERF_RECORD_EXIT,
                                .misc = 0,
-                                .size = sizeof(task_event.event),
+                                .size = sizeof(task_event.event_id),
                        },
                        /* .pid  */
                        /* .ppid */
@@ -3182,12 +3181,12 @@ static void perf_counter_task(struct task_struct *task,
                },
        };
-        perf_counter_task_event(&task_event);
+        perf_event_task_event(&task_event);
 }
-void perf_counter_fork(struct task_struct *task)
+void perf_event_fork(struct task_struct *task)
 {
-        perf_counter_task(task, NULL, 1);
+        perf_event_task(task, NULL, 1);
 }
 /*
@@ -3204,56 +3203,56 @@ struct perf_comm_event {
                u32                             pid;
                u32                             tid;
-        } event;
+        } event_id;
 };
-static void perf_counter_comm_output(struct perf_counter *counter,
+static void perf_event_comm_output(struct perf_event *event,
                                     struct perf_comm_event *comm_event)
 {
        struct perf_output_handle handle;
-        int size = comm_event->event.header.size;
+        int size = comm_event->event_id.header.size;
-        int ret = perf_output_begin(&handle, counter, size, 0, 0);
+        int ret = perf_output_begin(&handle, event, size, 0, 0);
        if (ret)
                return;
-        comm_event->event.pid = perf_counter_pid(counter, comm_event->task);
+        comm_event->event_id.pid = perf_event_pid(event, comm_event->task);
-        comm_event->event.tid = perf_counter_tid(counter, comm_event->task);
+        comm_event->event_id.tid = perf_event_tid(event, comm_event->task);
-        perf_output_put(&handle, comm_event->event);
+        perf_output_put(&handle, comm_event->event_id);
        perf_output_copy(&handle, comm_event->comm,
                                   comm_event->comm_size);
        perf_output_end(&handle);
 }
-static int perf_counter_comm_match(struct perf_counter *counter)
+static int perf_event_comm_match(struct perf_event *event)
 {
-        if (counter->attr.comm)
+        if (event->attr.comm)
                return 1;
        return 0;
 }
-static void perf_counter_comm_ctx(struct perf_counter_context *ctx,
+static void perf_event_comm_ctx(struct perf_event_context *ctx,
                                  struct perf_comm_event *comm_event)
 {
-        struct perf_counter *counter;
+        struct perf_event *event;
        if (system_state != SYSTEM_RUNNING || list_empty(&ctx->event_list))
                return;
        rcu_read_lock();
-        list_for_each_entry_rcu(counter, &ctx->event_list, event_entry) {
+        list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
-                if (perf_counter_comm_match(counter))
+                if (perf_event_comm_match(event))
-                        perf_counter_comm_output(counter, comm_event);
+                        perf_event_comm_output(event, comm_event);
        }
        rcu_read_unlock();
 }
-static void perf_counter_comm_event(struct perf_comm_event *comm_event)
+static void perf_event_comm_event(struct perf_comm_event *comm_event)
 {
        struct perf_cpu_context *cpuctx;
-        struct perf_counter_context *ctx;
+        struct perf_event_context *ctx;
        unsigned int size;
        char comm[TASK_COMM_LEN];
@@ -3264,10 +3263,10 @@ static void perf_counter_comm_event(struct perf_comm_event *comm_event)
        comm_event->comm = comm;
        comm_event->comm_size = size;
-        comm_event->event.header.size = sizeof(comm_event->event) + size;
+        comm_event->event_id.header.size = sizeof(comm_event->event_id) + size;
        cpuctx = &get_cpu_var(perf_cpu_context);
-        perf_counter_comm_ctx(&cpuctx->ctx, comm_event);
+        perf_event_comm_ctx(&cpuctx->ctx, comm_event);
        put_cpu_var(perf_cpu_context);
        rcu_read_lock();
@@ -3275,29 +3274,29 @@ static void perf_counter_comm_event(struct perf_comm_event *comm_event)
         * doesn't really matter which of the child contexts the
         * events ends up in.
         */
-        ctx = rcu_dereference(current->perf_counter_ctxp);
+        ctx = rcu_dereference(current->perf_event_ctxp);
        if (ctx)
-                perf_counter_comm_ctx(ctx, comm_event);
+                perf_event_comm_ctx(ctx, comm_event);
        rcu_read_unlock();
 }
-void perf_counter_comm(struct task_struct *task)
+void perf_event_comm(struct task_struct *task)
 {
        struct perf_comm_event comm_event;
-        if (task->perf_counter_ctxp)
+        if (task->perf_event_ctxp)
-                perf_counter_enable_on_exec(task);
+                perf_event_enable_on_exec(task);
-        if (!atomic_read(&nr_comm_counters))
+        if (!atomic_read(&nr_comm_events))
                return;
        comm_event = (struct perf_comm_event){
                .task   = task,
                /* .comm      */
                /* .comm_size */
-                .event  = {
+                .event_id  = {
                        .header = {
-                                .type = PERF_EVENT_COMM,
+                                .type = PERF_RECORD_COMM,
                                .misc = 0,
                                /* .size */
                        },
@@ -3306,7 +3305,7 @@ void perf_counter_comm(struct task_struct *task)
                },
        };
-        perf_counter_comm_event(&comm_event);
+        perf_event_comm_event(&comm_event);
 }
 /*
@@ -3327,57 +3326,57 @@ struct perf_mmap_event {
                u64                             start;
                u64                             len;
                u64                             pgoff;
-        } event;
+        } event_id;
 };
-static void perf_counter_mmap_output(struct perf_counter *counter,
+static void perf_event_mmap_output(struct perf_event *event,
                                     struct perf_mmap_event *mmap_event)
 {
        struct perf_output_handle handle;
-        int size = mmap_event->event.header.size;
+        int size = mmap_event->event_id.header.size;
-        int ret = perf_output_begin(&handle, counter, size, 0, 0);
+        int ret = perf_output_begin(&handle, event, size, 0, 0);
        if (ret)
                return;
-        mmap_event->event.pid = perf_counter_pid(counter, current);
+        mmap_event->event_id.pid = perf_event_pid(event, current);
-        mmap_event->event.tid = perf_counter_tid(counter, current);
+        mmap_event->event_id.tid = perf_event_tid(event, current);
-        perf_output_put(&handle, mmap_event->event);
+        perf_output_put(&handle, mmap_event->event_id);
        perf_output_copy(&handle, mmap_event->file_name,
                                   mmap_event->file_size);
        perf_output_end(&handle);
 }
-static int perf_counter_mmap_match(struct perf_counter *counter,
+static int perf_event_mmap_match(struct perf_event *event,
                                   struct perf_mmap_event *mmap_event)
 {
-        if (counter->attr.mmap)
+        if (event->attr.mmap)
                return 1;
        return 0;
 }
-static void perf_counter_mmap_ctx(struct perf_counter_context *ctx,
+static void perf_event_mmap_ctx(struct perf_event_context *ctx,
                                  struct perf_mmap_event *mmap_event)
 {
-        struct perf_counter *counter;
+        struct perf_event *event;
        if (system_state != SYSTEM_RUNNING || list_empty(&ctx->event_list))
                return;
        rcu_read_lock();
-        list_for_each_entry_rcu(counter, &ctx->event_list, event_entry) {
+        list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
-                if (perf_counter_mmap_match(counter, mmap_event))
+                if (perf_event_mmap_match(event, mmap_event))
-                        perf_counter_mmap_output(counter, mmap_event);
+                        perf_event_mmap_output(event, mmap_event);
        }
        rcu_read_unlock();
 }
-static void perf_counter_mmap_event(struct perf_mmap_event *mmap_event)
+static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
 {
        struct perf_cpu_context *cpuctx;
-        struct perf_counter_context *ctx;
+        struct perf_event_context *ctx;
        struct vm_area_struct *vma = mmap_event->vma;
        struct file *file = vma->vm_file;
        unsigned int size;
@@ -3425,10 +3424,10 @@ got_name:
        mmap_event->file_name = name;
        mmap_event->file_size = size;
-        mmap_event->event.header.size = sizeof(mmap_event->event) + size;
+        mmap_event->event_id.header.size = sizeof(mmap_event->event_id) + size;
        cpuctx = &get_cpu_var(perf_cpu_context);
-        perf_counter_mmap_ctx(&cpuctx->ctx, mmap_event);
+        perf_event_mmap_ctx(&cpuctx->ctx, mmap_event);
        put_cpu_var(perf_cpu_context);
        rcu_read_lock();
@@ -3436,28 +3435,28 @@ got_name:
         * doesn't really matter which of the child contexts the
         * events ends up in.
         */
-        ctx = rcu_dereference(current->perf_counter_ctxp);
+        ctx = rcu_dereference(current->perf_event_ctxp);
        if (ctx)
-                perf_counter_mmap_ctx(ctx, mmap_event);
+                perf_event_mmap_ctx(ctx, mmap_event);
        rcu_read_unlock();
        kfree(buf);
 }
-void __perf_counter_mmap(struct vm_area_struct *vma)
+void __perf_event_mmap(struct vm_area_struct *vma)
 {
        struct perf_mmap_event mmap_event;
-        if (!atomic_read(&nr_mmap_counters))
+        if (!atomic_read(&nr_mmap_events))
                return;
        mmap_event = (struct perf_mmap_event){
                .vma    = vma,
                /* .file_name */
                /* .file_size */
-                .event  = {
+                .event_id  = {
                        .header = {
-                                .type = PERF_EVENT_MMAP,
+                                .type = PERF_RECORD_MMAP,
                                .misc = 0,
                                /* .size */
                        },
@@ -3469,14 +3468,14 @@ void __perf_counter_mmap(struct vm_area_struct *vma)
                },
        };
-        perf_counter_mmap_event(&mmap_event);
+        perf_event_mmap_event(&mmap_event);
 }
 /*
 * IRQ throttle logging
 */
-static void perf_log_throttle(struct perf_counter *counter, int enable)
+static void perf_log_throttle(struct perf_event *event, int enable)
 {
        struct perf_output_handle handle;
        int ret;
@@ -3488,19 +3487,19 @@ static void perf_log_throttle(struct perf_counter *counter, int enable)
                u64                             stream_id;
        } throttle_event = {
                .header = {
-                        .type = PERF_EVENT_THROTTLE,
+                        .type = PERF_RECORD_THROTTLE,
                        .misc = 0,
                        .size = sizeof(throttle_event),
                },
                .time           = perf_clock(),
-                .id             = primary_counter_id(counter),
+                .id             = primary_event_id(event),
-                .stream_id      = counter->id,
+                .stream_id      = event->id,
        };
        if (enable)
-                throttle_event.header.type = PERF_EVENT_UNTHROTTLE;
+                throttle_event.header.type = PERF_RECORD_UNTHROTTLE;
-        ret = perf_output_begin(&handle, counter, sizeof(throttle_event), 1, 0);
+        ret = perf_output_begin(&handle, event, sizeof(throttle_event), 1, 0);
        if (ret)
                return;
@@ -3509,18 +3508,18 @@ static void perf_log_throttle(struct perf_counter *counter, int enable)
 }
 /*
- * Generic counter overflow handling, sampling.
+ * Generic event overflow handling, sampling.
 */
-static int __perf_counter_overflow(struct perf_counter *counter, int nmi,
+static int __perf_event_overflow(struct perf_event *event, int nmi,
                                   int throttle, struct perf_sample_data *data,
                                   struct pt_regs *regs)
 {
-        int events = atomic_read(&counter->event_limit);
+        int events = atomic_read(&event->event_limit);
-        struct hw_perf_counter *hwc = &counter->hw;
+        struct hw_perf_event *hwc = &event->hw;
        int ret = 0;
-        throttle = (throttle && counter->pmu->unthrottle != NULL);
+        throttle = (throttle && event->pmu->unthrottle != NULL);
        if (!throttle) {
                hwc->interrupts++;
@@ -3528,73 +3527,73 @@ static int __perf_counter_overflow(struct perf_counter *counter, int nmi,
                if (hwc->interrupts != MAX_INTERRUPTS) {
                        hwc->interrupts++;
                        if (HZ * hwc->interrupts >
-                                        (u64)sysctl_perf_counter_sample_rate) {
+                                        (u64)sysctl_perf_event_sample_rate) {
                                hwc->interrupts = MAX_INTERRUPTS;
-                                perf_log_throttle(counter, 0);
+                                perf_log_throttle(event, 0);
                                ret = 1;
                        }
                } else {
                        /*
-                         * Keep re-disabling counters even though on the previous
+                         * Keep re-disabling events even though on the previous
                         * pass we disabled it - just in case we raced with a
-                         * sched-in and the counter got enabled again:
+                         * sched-in and the event got enabled again:
                         */
                        ret = 1;
                }
        }
-        if (counter->attr.freq) {
+        if (event->attr.freq) {
                u64 now = perf_clock();
                s64 delta = now - hwc->freq_stamp;
                hwc->freq_stamp = now;
                if (delta > 0 && delta < TICK_NSEC)
-                        perf_adjust_period(counter, NSEC_PER_SEC / (int)delta);
+                        perf_adjust_period(event, NSEC_PER_SEC / (int)delta);
        }
        /*
         * XXX event_limit might not quite work as expected on inherited
-         * counters
+         * events
         */
-        counter->pending_kill = POLL_IN;
+        event->pending_kill = POLL_IN;
-        if (events && atomic_dec_and_test(&counter->event_limit)) {
+        if (events && atomic_dec_and_test(&event->event_limit)) {
                ret = 1;
-                counter->pending_kill = POLL_HUP;
+                event->pending_kill = POLL_HUP;
                if (nmi) {
-                        counter->pending_disable = 1;
+                        event->pending_disable = 1;
-                        perf_pending_queue(&counter->pending,
+                        perf_pending_queue(&event->pending,
-                                           perf_pending_counter);
+                                           perf_pending_event);
                } else
-                        perf_counter_disable(counter);
+                        perf_event_disable(event);
        }
-        perf_counter_output(counter, nmi, data, regs);
+        perf_event_output(event, nmi, data, regs);
        return ret;
 }
-int perf_counter_overflow(struct perf_counter *counter, int nmi,
+int perf_event_overflow(struct perf_event *event, int nmi,
                          struct perf_sample_data *data,
                          struct pt_regs *regs)
 {
-        return __perf_counter_overflow(counter, nmi, 1, data, regs);
+        return __perf_event_overflow(event, nmi, 1, data, regs);
 }
 /*
- * Generic software counter infrastructure
+ * Generic software event infrastructure
 */
 /*
- * We directly increment counter->count and keep a second value in
+ * We directly increment event->count and keep a second value in
- * counter->hw.period_left to count intervals. This period counter
+ * event->hw.period_left to count intervals. This period event
 * is kept in the range [-sample_period, 0] so that we can use the
 * sign as trigger.
 */
-static u64 perf_swcounter_set_period(struct perf_counter *counter)
+static u64 perf_swevent_set_period(struct perf_event *event)
 {
-        struct hw_perf_counter *hwc = &counter->hw;
+        struct hw_perf_event *hwc = &event->hw;
        u64 period = hwc->last_period;
        u64 nr, offset;
        s64 old, val;
@@ -3615,22 +3614,22 @@ again:
        return nr;
 }
-static void perf_swcounter_overflow(struct perf_counter *counter,
+static void perf_swevent_overflow(struct perf_event *event,
                                    int nmi, struct perf_sample_data *data,
                                    struct pt_regs *regs)
 {
-        struct hw_perf_counter *hwc = &counter->hw;
+        struct hw_perf_event *hwc = &event->hw;
        int throttle = 0;
        u64 overflow;
-        data->period = counter->hw.last_period;
+        data->period = event->hw.last_period;
-        overflow = perf_swcounter_set_period(counter);
+        overflow = perf_swevent_set_period(event);
        if (hwc->interrupts == MAX_INTERRUPTS)
                return;
        for (; overflow; overflow--) {
-                if (__perf_counter_overflow(counter, nmi, throttle,
+                if (__perf_event_overflow(event, nmi, throttle,
                                            data, regs)) {
                        /*
                         * We inhibit the overflow from happening when
@@ -3642,20 +3641,20 @@ static void perf_swcounter_overflow(struct perf_counter *counter,
        }
 }
-static void perf_swcounter_unthrottle(struct perf_counter *counter)
+static void perf_swevent_unthrottle(struct perf_event *event)
 {
        /*
         * Nothing to do, we already reset hwc->interrupts.
         */
 }
-static void perf_swcounter_add(struct perf_counter *counter, u64 nr,
+static void perf_swevent_add(struct perf_event *event, u64 nr,
                               int nmi, struct perf_sample_data *data,
                               struct pt_regs *regs)
 {
-        struct hw_perf_counter *hwc = &counter->hw;
+        struct hw_perf_event *hwc = &event->hw;
-        atomic64_add(nr, &counter->count);
+        atomic64_add(nr, &event->count);
        if (!hwc->sample_period)
                return;
@@ -3664,29 +3663,29 @@ static void perf_swcounter_add(struct perf_counter *counter, u64 nr,
                return;
        if (!atomic64_add_negative(nr, &hwc->period_left))
-                perf_swcounter_overflow(counter, nmi, data, regs);
+                perf_swevent_overflow(event, nmi, data, regs);
 }
-static int perf_swcounter_is_counting(struct perf_counter *counter)
+static int perf_swevent_is_counting(struct perf_event *event)
 {
        /*
-         * The counter is active, we're good!
+         * The event is active, we're good!
         */
-        if (counter->state == PERF_COUNTER_STATE_ACTIVE)
+        if (event->state == PERF_EVENT_STATE_ACTIVE)
                return 1;
        /*
-         * The counter is off/error, not counting.
+         * The event is off/error, not counting.
         */
-        if (counter->state != PERF_COUNTER_STATE_INACTIVE)
+        if (event->state != PERF_EVENT_STATE_INACTIVE)
                return 0;
        /*
-         * The counter is inactive, if the context is active
+         * The event is inactive, if the context is active
         * we're part of a group that didn't make it on the 'pmu',
         * not counting.
         */
-        if (counter->ctx->is_active)
+        if (event->ctx->is_active)
                return 0;
        /*
@@ -3697,49 +3696,49 @@ static int perf_swcounter_is_counting(struct perf_counter *counter)
        return 1;
 }
-static int perf_swcounter_match(struct perf_counter *counter,
+static int perf_swevent_match(struct perf_event *event,
                                enum perf_type_id type,
-                                u32 event, struct pt_regs *regs)
+                                u32 event_id, struct pt_regs *regs)
 {
-        if (!perf_swcounter_is_counting(counter))
+        if (!perf_swevent_is_counting(event))
                return 0;
-        if (counter->attr.type != type)
+        if (event->attr.type != type)
                return 0;
-        if (counter->attr.config != event)
+        if (event->attr.config != event_id)
                return 0;
        if (regs) {
-                if (counter->attr.exclude_user && user_mode(regs))
+                if (event->attr.exclude_user && user_mode(regs))
                        return 0;
-                if (counter->attr.exclude_kernel && !user_mode(regs))
+                if (event->attr.exclude_kernel && !user_mode(regs))
                        return 0;
        }
        return 1;
 }
-static void perf_swcounter_ctx_event(struct perf_counter_context *ctx,
+static void perf_swevent_ctx_event(struct perf_event_context *ctx,
                                     enum perf_type_id type,
-                                     u32 event, u64 nr, int nmi,
+                                     u32 event_id, u64 nr, int nmi,
                                     struct perf_sample_data *data,
                                     struct pt_regs *regs)
 {
-        struct perf_counter *counter;
+        struct perf_event *event;
        if (system_state != SYSTEM_RUNNING || list_empty(&ctx->event_list))
                return;
        rcu_read_lock();
-        list_for_each_entry_rcu(counter, &ctx->event_list, event_entry) {
+        list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
-                if (perf_swcounter_match(counter, type, event, regs))
+                if (perf_swevent_match(event, type, event_id, regs))
-                        perf_swcounter_add(counter, nr, nmi, data, regs);
+                        perf_swevent_add(event, nr, nmi, data, regs);
        }
        rcu_read_unlock();
 }
-static int *perf_swcounter_recursion_context(struct perf_cpu_context *cpuctx)
+static int *perf_swevent_recursion_context(struct perf_cpu_context *cpuctx)
 {
        if (in_nmi())
                return &cpuctx->recursion[3];
@@ -3753,14 +3752,14 @@ static int *perf_swcounter_recursion_context(struct perf_cpu_context *cpuctx)
        return &cpuctx->recursion[0];
 }
-static void do_perf_swcounter_event(enum perf_type_id type, u32 event,
+static void do_perf_sw_event(enum perf_type_id type, u32 event_id,
                                    u64 nr, int nmi,
                                    struct perf_sample_data *data,
                                    struct pt_regs *regs)
 {
        struct perf_cpu_context *cpuctx = &get_cpu_var(perf_cpu_context);
-        int *recursion = perf_swcounter_recursion_context(cpuctx);
+        int *recursion = perf_swevent_recursion_context(cpuctx);
-        struct perf_counter_context *ctx;
+        struct perf_event_context *ctx;
        if (*recursion)
                goto out;
@@ -3768,16 +3767,16 @@ static void do_perf_swcounter_event(enum perf_type_id type, u32 event,
        (*recursion)++;
        barrier();
-        perf_swcounter_ctx_event(&cpuctx->ctx, type, event,
+        perf_swevent_ctx_event(&cpuctx->ctx, type, event_id,
                                 nr, nmi, data, regs);
        rcu_read_lock();
        /*
         * doesn't really matter which of the child contexts the
         * events ends up in.
         */
-        ctx = rcu_dereference(current->perf_counter_ctxp);
+        ctx = rcu_dereference(current->perf_event_ctxp);
        if (ctx)
-                perf_swcounter_ctx_event(ctx, type, event, nr, nmi, data, regs);
+                perf_swevent_ctx_event(ctx, type, event_id, nr, nmi, data, regs);
        rcu_read_unlock();
        barrier();
@@ -3787,57 +3786,57 @@ out:
        put_cpu_var(perf_cpu_context);
 }
-void __perf_swcounter_event(u32 event, u64 nr, int nmi,
+void __perf_sw_event(u32 event_id, u64 nr, int nmi,
                            struct pt_regs *regs, u64 addr)
 {
        struct perf_sample_data data = {
                .addr = addr,
        };
-        do_perf_swcounter_event(PERF_TYPE_SOFTWARE, event, nr, nmi,
+        do_perf_sw_event(PERF_TYPE_SOFTWARE, event_id, nr, nmi,
                                &data, regs);
 }
-static void perf_swcounter_read(struct perf_counter *counter)
+static void perf_swevent_read(struct perf_event *event)
 {
 }
-static int perf_swcounter_enable(struct perf_counter *counter)
+static int perf_swevent_enable(struct perf_event *event)
 {
-        struct hw_perf_counter *hwc = &counter->hw;
+        struct hw_perf_event *hwc = &event->hw;
        if (hwc->sample_period) {
                hwc->last_period = hwc->sample_period;
-                perf_swcounter_set_period(counter);
+                perf_swevent_set_period(event);
        }
        return 0;
 }
-static void perf_swcounter_disable(struct perf_counter *counter)
+static void perf_swevent_disable(struct perf_event *event)
 {
 }
 static const struct pmu perf_ops_generic = {
-        .enable         = perf_swcounter_enable,
+        .enable         = perf_swevent_enable,
-        .disable        = perf_swcounter_disable,
+        .disable        = perf_swevent_disable,
-        .read           = perf_swcounter_read,
+        .read           = perf_swevent_read,
-        .unthrottle     = perf_swcounter_unthrottle,
+        .unthrottle     = perf_swevent_unthrottle,
 };
 /*
- * hrtimer based swcounter callback
+ * hrtimer based swevent callback
 */
-static enum hrtimer_restart perf_swcounter_hrtimer(struct hrtimer *hrtimer)
+static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer)
 {
        enum hrtimer_restart ret = HRTIMER_RESTART;
        struct perf_sample_data data;
        struct pt_regs *regs;
-        struct perf_counter *counter;
+        struct perf_event *event;
        u64 period;
-        counter = container_of(hrtimer, struct perf_counter, hw.hrtimer);
+        event   = container_of(hrtimer, struct perf_event, hw.hrtimer);
-        counter->pmu->read(counter);
+        event->pmu->read(event);
        data.addr = 0;
        regs = get_irq_regs();
@@ -3845,45 +3844,45 @@ static enum hrtimer_restart perf_swcounter_hrtimer(struct hrtimer *hrtimer)
         * In case we exclude kernel IPs or are somehow not in interrupt
         * context, provide the next best thing, the user IP.
         */
-        if ((counter->attr.exclude_kernel || !regs) &&
+        if ((event->attr.exclude_kernel || !regs) &&
-                        !counter->attr.exclude_user)
+                        !event->attr.exclude_user)
                regs = task_pt_regs(current);
        if (regs) {
-                if (perf_counter_overflow(counter, 0, &data, regs))
+                if (perf_event_overflow(event, 0, &data, regs))
                        ret = HRTIMER_NORESTART;
        }
-        period = max_t(u64, 10000, counter->hw.sample_period);
+        period = max_t(u64, 10000, event->hw.sample_period);
        hrtimer_forward_now(hrtimer, ns_to_ktime(period));
        return ret;
 }
 /*
- * Software counter: cpu wall time clock
+ * Software event: cpu wall time clock
 */
-static void cpu_clock_perf_counter_update(struct perf_counter *counter)
+static void cpu_clock_perf_event_update(struct perf_event *event)
 {
        int cpu = raw_smp_processor_id();
        s64 prev;
        u64 now;
        now = cpu_clock(cpu);
-        prev = atomic64_read(&counter->hw.prev_count);
+        prev = atomic64_read(&event->hw.prev_count);
-        atomic64_set(&counter->hw.prev_count, now);
+        atomic64_set(&event->hw.prev_count, now);
-        atomic64_add(now - prev, &counter->count);
+        atomic64_add(now - prev, &event->count);
 }
-static int cpu_clock_perf_counter_enable(struct perf_counter *counter)
+static int cpu_clock_perf_event_enable(struct perf_event *event)
 {
-        struct hw_perf_counter *hwc = &counter->hw;
+        struct hw_perf_event *hwc = &event->hw;
        int cpu = raw_smp_processor_id();
        atomic64_set(&hwc->prev_count, cpu_clock(cpu));
        hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-        hwc->hrtimer.function = perf_swcounter_hrtimer;
+        hwc->hrtimer.function = perf_swevent_hrtimer;
        if (hwc->sample_period) {
                u64 period = max_t(u64, 10000, hwc->sample_period);
                __hrtimer_start_range_ns(&hwc->hrtimer,
@@ -3894,48 +3893,48 @@ static int cpu_clock_perf_counter_enable(struct perf_counter *counter)
        return 0;
 }
-static void cpu_clock_perf_counter_disable(struct perf_counter *counter)
+static void cpu_clock_perf_event_disable(struct perf_event *event)
 {
-        if (counter->hw.sample_period)
+        if (event->hw.sample_period)
-                hrtimer_cancel(&counter->hw.hrtimer);
+                hrtimer_cancel(&event->hw.hrtimer);
-        cpu_clock_perf_counter_update(counter);
+        cpu_clock_perf_event_update(event);
 }
-static void cpu_clock_perf_counter_read(struct perf_counter *counter)
+static void cpu_clock_perf_event_read(struct perf_event *event)
 {
-        cpu_clock_perf_counter_update(counter);
+        cpu_clock_perf_event_update(event);
 }
 static const struct pmu perf_ops_cpu_clock = {
-        .enable         = cpu_clock_perf_counter_enable,
+        .enable         = cpu_clock_perf_event_enable,
-        .disable        = cpu_clock_perf_counter_disable,
+        .disable        = cpu_clock_perf_event_disable,
-        .read           = cpu_clock_perf_counter_read,
+        .read           = cpu_clock_perf_event_read,
 };
 /*
- * Software counter: task time clock
+ * Software event: task time clock
 */
-static void task_clock_perf_counter_update(struct perf_counter *counter, u64 now)
+static void task_clock_perf_event_update(struct perf_event *event, u64 now)
 {
        u64 prev;
        s64 delta;
-        prev = atomic64_xchg(&counter->hw.prev_count, now);
+        prev = atomic64_xchg(&event->hw.prev_count, now);
        delta = now - prev;
-        atomic64_add(delta, &counter->count);
+        atomic64_add(delta, &event->count);
 }
-static int task_clock_perf_counter_enable(struct perf_counter *counter)
+static int task_clock_perf_event_enable(struct perf_event *event)
 {
-        struct hw_perf_counter *hwc = &counter->hw;
+        struct hw_perf_event *hwc = &event->hw;
        u64 now;
-        now = counter->ctx->time;
+        now = event->ctx->time;
        atomic64_set(&hwc->prev_count, now);
        hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-        hwc->hrtimer.function = perf_swcounter_hrtimer;
+        hwc->hrtimer.function = perf_swevent_hrtimer;
        if (hwc->sample_period) {
                u64 period = max_t(u64, 10000, hwc->sample_period);
                __hrtimer_start_range_ns(&hwc->hrtimer,
@@ -3946,38 +3945,38 @@ static int task_clock_perf_counter_enable(struct perf_counter *counter)
        return 0;
 }
-static void task_clock_perf_counter_disable(struct perf_counter *counter)
+static void task_clock_perf_event_disable(struct perf_event *event)
 {
-        if (counter->hw.sample_period)
+        if (event->hw.sample_period)
-                hrtimer_cancel(&counter->hw.hrtimer);
+                hrtimer_cancel(&event->hw.hrtimer);
-        task_clock_perf_counter_update(counter, counter->ctx->time);
+        task_clock_perf_event_update(event, event->ctx->time);
 }
-static void task_clock_perf_counter_read(struct perf_counter *counter)
+static void task_clock_perf_event_read(struct perf_event *event)
 {
        u64 time;
        if (!in_nmi()) {
-                update_context_time(counter->ctx);
+                update_context_time(event->ctx);
-                time = counter->ctx->time;
+                time = event->ctx->time;
        } else {
                u64 now = perf_clock();
-                u64 delta = now - counter->ctx->timestamp;
+                u64 delta = now - event->ctx->timestamp;
-                time = counter->ctx->time + delta;
+                time = event->ctx->time + delta;
        }
-        task_clock_perf_counter_update(counter, time);
+        task_clock_perf_event_update(event, time);
 }
 static const struct pmu perf_ops_task_clock = {
-        .enable         = task_clock_perf_counter_enable,
+        .enable         = task_clock_perf_event_enable,
-        .disable        = task_clock_perf_counter_disable,
+        .disable        = task_clock_perf_event_disable,
-        .read           = task_clock_perf_counter_read,
+        .read           = task_clock_perf_event_read,
 };
 #ifdef CONFIG_EVENT_PROFILE
-void perf_tpcounter_event(int event_id, u64 addr, u64 count, void *record,
+void perf_tp_event(int event_id, u64 addr, u64 count, void *record,
                          int entry_size)
 {
        struct perf_raw_record raw = {
@@ -3995,78 +3994,78 @@ void perf_tpcounter_event(int event_id, u64 addr, u64 count, void *record,
        if (!regs)
                regs = task_pt_regs(current);
-        do_perf_swcounter_event(PERF_TYPE_TRACEPOINT, event_id, count, 1,
+        do_perf_sw_event(PERF_TYPE_TRACEPOINT, event_id, count, 1,
                                &data, regs);
 }
-EXPORT_SYMBOL_GPL(perf_tpcounter_event);
+EXPORT_SYMBOL_GPL(perf_tp_event);
 extern int ftrace_profile_enable(int);
 extern void ftrace_profile_disable(int);
-static void tp_perf_counter_destroy(struct perf_counter *counter)
+static void tp_perf_event_destroy(struct perf_event *event)
 {
-        ftrace_profile_disable(counter->attr.config);
+        ftrace_profile_disable(event->attr.config);
 }
-static const struct pmu *tp_perf_counter_init(struct perf_counter *counter)
+static const struct pmu *tp_perf_event_init(struct perf_event *event)
 {
        /*
         * Raw tracepoint data is a severe data leak, only allow root to
         * have these.
         */
-        if ((counter->attr.sample_type & PERF_SAMPLE_RAW) &&
+        if ((event->attr.sample_type & PERF_SAMPLE_RAW) &&
                        perf_paranoid_tracepoint_raw() &&
                        !capable(CAP_SYS_ADMIN))
                return ERR_PTR(-EPERM);
-        if (ftrace_profile_enable(counter->attr.config))
+        if (ftrace_profile_enable(event->attr.config))
                return NULL;
-        counter->destroy = tp_perf_counter_destroy;
+        event->destroy = tp_perf_event_destroy;
        return &perf_ops_generic;
 }
 #else
-static const struct pmu *tp_perf_counter_init(struct perf_counter *counter)
+static const struct pmu *tp_perf_event_init(struct perf_event *event)
 {
        return NULL;
 }
 #endif
-atomic_t perf_swcounter_enabled[PERF_COUNT_SW_MAX];
+atomic_t perf_swevent_enabled[PERF_COUNT_SW_MAX];
-static void sw_perf_counter_destroy(struct perf_counter *counter)
+static void sw_perf_event_destroy(struct perf_event *event)
 {
-        u64 event = counter->attr.config;
+        u64 event_id = event->attr.config;
-        WARN_ON(counter->parent);
+        WARN_ON(event->parent);
-        atomic_dec(&perf_swcounter_enabled[event]);
+        atomic_dec(&perf_swevent_enabled[event_id]);
 }
-static const struct pmu *sw_perf_counter_init(struct perf_counter *counter)
+static const struct pmu *sw_perf_event_init(struct perf_event *event)
 {
        const struct pmu *pmu = NULL;
-        u64 event = counter->attr.config;
+        u64 event_id = event->attr.config;
        /*
-         * Software counters (currently) can't in general distinguish
+         * Software events (currently) can't in general distinguish
         * between user, kernel and hypervisor events.
         * However, context switches and cpu migrations are considered
         * to be kernel events, and page faults are never hypervisor
         * events.
         */
-        switch (event) {
+        switch (event_id) {
        case PERF_COUNT_SW_CPU_CLOCK:
                pmu = &perf_ops_cpu_clock;
                break;
        case PERF_COUNT_SW_TASK_CLOCK:
                /*
-                 * If the user instantiates this as a per-cpu counter,
+                 * If the user instantiates this as a per-cpu event,
-                 * use the cpu_clock counter instead.
+                 * use the cpu_clock event instead.
                 */
-                if (counter->ctx->task)
+                if (event->ctx->task)
                        pmu = &perf_ops_task_clock;
                else
                        pmu = &perf_ops_cpu_clock;
@@ -4077,9 +4076,9 @@ static const struct pmu *sw_perf_counter_init(struct perf_counter *counter)
        case PERF_COUNT_SW_PAGE_FAULTS_MAJ:
        case PERF_COUNT_SW_CONTEXT_SWITCHES:
        case PERF_COUNT_SW_CPU_MIGRATIONS:
-                if (!counter->parent) {
+                if (!event->parent) {
-                        atomic_inc(&perf_swcounter_enabled[event]);
+                        atomic_inc(&perf_swevent_enabled[event_id]);
-                        counter->destroy = sw_perf_counter_destroy;
+                        event->destroy = sw_perf_event_destroy;
                }
                pmu = &perf_ops_generic;
                break;
@@ -4089,62 +4088,62 @@ static const struct pmu *sw_perf_counter_init(struct perf_counter *counter)
 }
 /*
- * Allocate and initialize a counter structure
+ * Allocate and initialize a event structure
 */
-static struct perf_counter *
+static struct perf_event *
-perf_counter_alloc(struct perf_counter_attr *attr,
+perf_event_alloc(struct perf_event_attr *attr,
                   int cpu,
-                   struct perf_counter_context *ctx,
+                   struct perf_event_context *ctx,
-                   struct perf_counter *group_leader,
+                   struct perf_event *group_leader,
-                   struct perf_counter *parent_counter,
+                   struct perf_event *parent_event,
                   gfp_t gfpflags)
 {
        const struct pmu *pmu;
-        struct perf_counter *counter;
+        struct perf_event *event;
-        struct hw_perf_counter *hwc;
+        struct hw_perf_event *hwc;
        long err;
-        counter = kzalloc(sizeof(*counter), gfpflags);
+        event = kzalloc(sizeof(*event), gfpflags);
-        if (!counter)
+        if (!event)
                return ERR_PTR(-ENOMEM);
        /*
-         * Single counters are their own group leaders, with an
+         * Single events are their own group leaders, with an
         * empty sibling list:
         */
        if (!group_leader)
-                group_leader = counter;
+                group_leader = event;
-        mutex_init(&counter->child_mutex);
+        mutex_init(&event->child_mutex);
-        INIT_LIST_HEAD(&counter->child_list);
+        INIT_LIST_HEAD(&event->child_list);
-        INIT_LIST_HEAD(&counter->list_entry);
+        INIT_LIST_HEAD(&event->group_entry);
-        INIT_LIST_HEAD(&counter->event_entry);
+        INIT_LIST_HEAD(&event->event_entry);
-        INIT_LIST_HEAD(&counter->sibling_list);
+        INIT_LIST_HEAD(&event->sibling_list);
-        init_waitqueue_head(&counter->waitq);
+        init_waitqueue_head(&event->waitq);
-        mutex_init(&counter->mmap_mutex);
+        mutex_init(&event->mmap_mutex);
-        counter->cpu            = cpu;
+        event->cpu              = cpu;
-        counter->attr           = *attr;
+        event->attr             = *attr;
-        counter->group_leader   = group_leader;
+        event->group_leader     = group_leader;
-        counter->pmu            = NULL;
+        event->pmu              = NULL;
-        counter->ctx            = ctx;
+        event->ctx              = ctx;
-        counter->oncpu          = -1;
+        event->oncpu            = -1;
-        counter->parent         = parent_counter;
+        event->parent           = parent_event;
-        counter->ns             = get_pid_ns(current->nsproxy->pid_ns);
+        event->ns               = get_pid_ns(current->nsproxy->pid_ns);
-        counter->id             = atomic64_inc_return(&perf_counter_id);
+        event->id               = atomic64_inc_return(&perf_event_id);
-        counter->state          = PERF_COUNTER_STATE_INACTIVE;
+        event->state            = PERF_EVENT_STATE_INACTIVE;
        if (attr->disabled)
-                counter->state = PERF_COUNTER_STATE_OFF;
+                event->state = PERF_EVENT_STATE_OFF;
        pmu = NULL;
-        hwc = &counter->hw;
+        hwc = &event->hw;
        hwc->sample_period = attr->sample_period;
        if (attr->freq && attr->sample_freq)
                hwc->sample_period = 1;
@@ -4153,7 +4152,7 @@ perf_counter_alloc(struct perf_counter_attr *attr,
        atomic64_set(&hwc->period_left, hwc->sample_period);
        /*
-         * we currently do not support PERF_FORMAT_GROUP on inherited counters
+         * we currently do not support PERF_FORMAT_GROUP on inherited events
         */
        if (attr->inherit && (attr->read_format & PERF_FORMAT_GROUP))
                goto done;
@@ -4162,15 +4161,15 @@ perf_counter_alloc(struct perf_counter_attr *attr,
        case PERF_TYPE_RAW:
        case PERF_TYPE_HARDWARE:
        case PERF_TYPE_HW_CACHE:
-                pmu = hw_perf_counter_init(counter);
+                pmu = hw_perf_event_init(event);
                break;
        case PERF_TYPE_SOFTWARE:
-                pmu = sw_perf_counter_init(counter);
+                pmu = sw_perf_event_init(event);
                break;
        case PERF_TYPE_TRACEPOINT:
-                pmu = tp_perf_counter_init(counter);
+                pmu = tp_perf_event_init(event);
                break;
        default:
@@ -4184,29 +4183,29 @@ done:
                err = PTR_ERR(pmu);
        if (err) {
-                if (counter->ns)
+                if (event->ns)
-                        put_pid_ns(counter->ns);
+                        put_pid_ns(event->ns);
-                kfree(counter);
+                kfree(event);
                return ERR_PTR(err);
        }
-        counter->pmu = pmu;
+        event->pmu = pmu;
-        if (!counter->parent) {
+        if (!event->parent) {
-                atomic_inc(&nr_counters);
+                atomic_inc(&nr_events);
-                if (counter->attr.mmap)
+                if (event->attr.mmap)
-                        atomic_inc(&nr_mmap_counters);
+                        atomic_inc(&nr_mmap_events);
-                if (counter->attr.comm)
+                if (event->attr.comm)
-                        atomic_inc(&nr_comm_counters);
+                        atomic_inc(&nr_comm_events);
-                if (counter->attr.task)
+                if (event->attr.task)
-                        atomic_inc(&nr_task_counters);
+                        atomic_inc(&nr_task_events);
        }
-        return counter;
+        return event;
 }
-static int perf_copy_attr(struct perf_counter_attr __user *uattr,
+static int perf_copy_attr(struct perf_event_attr __user *uattr,
-                          struct perf_counter_attr *attr)
+                          struct perf_event_attr *attr)
 {
        u32 size;
        int ret;
@@ -4285,11 +4284,11 @@ err_size:
        goto out;
 }
-int perf_counter_set_output(struct perf_counter *counter, int output_fd)
+int perf_event_set_output(struct perf_event *event, int output_fd)
 {
-        struct perf_counter *output_counter = NULL;
+        struct perf_event *output_event = NULL;
        struct file *output_file = NULL;
-        struct perf_counter *old_output;
+        struct perf_event *old_output;
        int fput_needed = 0;
        int ret = -EINVAL;
@@ -4303,28 +4302,28 @@ int perf_counter_set_output(struct perf_counter *counter, int output_fd)
        if (output_file->f_op != &perf_fops)
                goto out;
-        output_counter = output_file->private_data;
+        output_event = output_file->private_data;
        /* Don't chain output fds */
-        if (output_counter->output)
+        if (output_event->output)
                goto out;
        /* Don't set an output fd when we already have an output channel */
-        if (counter->data)
+        if (event->data)
                goto out;
        atomic_long_inc(&output_file->f_count);
 set:
-        mutex_lock(&counter->mmap_mutex);
+        mutex_lock(&event->mmap_mutex);
-        old_output = counter->output;
+        old_output = event->output;
-        rcu_assign_pointer(counter->output, output_counter);
+        rcu_assign_pointer(event->output, output_event);
-        mutex_unlock(&counter->mmap_mutex);
+        mutex_unlock(&event->mmap_mutex);
        if (old_output) {
                /*
                 * we need to make sure no existing perf_output_*()
-                 * is still referencing this counter.
+                 * is still referencing this event.
                 */
                synchronize_rcu();
                fput(old_output->filp);
@@ -4337,21 +4336,21 @@ out:
 }
 /**
- * sys_perf_counter_open - open a performance counter, associate it to a task/cpu
+ * sys_perf_event_open - open a performance event, associate it to a task/cpu
 *
- * @attr_uptr:  event type attributes for monitoring/sampling
+ * @attr_uptr:  event_id type attributes for monitoring/sampling
 * @pid:                target pid
 * @cpu:                target cpu
- * @group_fd:           group leader counter fd
+ * @group_fd:           group leader event fd
 */
-SYSCALL_DEFINE5(perf_counter_open,
+SYSCALL_DEFINE5(perf_event_open,
-                struct perf_counter_attr __user *, attr_uptr,
+                struct perf_event_attr __user *, attr_uptr,
                pid_t, pid, int, cpu, int, group_fd, unsigned long, flags)
 {
-        struct perf_counter *counter, *group_leader;
+        struct perf_event *event, *group_leader;
-        struct perf_counter_attr attr;
+        struct perf_event_attr attr;
-        struct perf_counter_context *ctx;
+        struct perf_event_context *ctx;
-        struct file *counter_file = NULL;
+        struct file *event_file = NULL;
        struct file *group_file = NULL;
        int fput_needed = 0;
        int fput_needed2 = 0;
@@ -4371,7 +4370,7 @@ SYSCALL_DEFINE5(perf_counter_open,
        }
        if (attr.freq) {
-                if (attr.sample_freq > sysctl_perf_counter_sample_rate)
+                if (attr.sample_freq > sysctl_perf_event_sample_rate)
                        return -EINVAL;
        }
@@ -4383,7 +4382,7 @@ SYSCALL_DEFINE5(perf_counter_open,
                return PTR_ERR(ctx);
        /*
-         * Look up the group leader (we will attach this counter to it):
+         * Look up the group leader (we will attach this event to it):
         */
        group_leader = NULL;
        if (group_fd != -1 && !(flags & PERF_FLAG_FD_NO_GROUP)) {
@@ -4414,45 +4413,45 @@ SYSCALL_DEFINE5(perf_counter_open,
                        goto err_put_context;
        }
-        counter = perf_counter_alloc(&attr, cpu, ctx, group_leader,
+        event = perf_event_alloc(&attr, cpu, ctx, group_leader,
                                     NULL, GFP_KERNEL);
-        err = PTR_ERR(counter);
+        err = PTR_ERR(event);
-        if (IS_ERR(counter))
+        if (IS_ERR(event))
                goto err_put_context;
-        err = anon_inode_getfd("[perf_counter]", &perf_fops, counter, 0);
+        err = anon_inode_getfd("[perf_event]", &perf_fops, event, 0);
        if (err < 0)
                goto err_free_put_context;
-        counter_file = fget_light(err, &fput_needed2);
+        event_file = fget_light(err, &fput_needed2);
-        if (!counter_file)
+        if (!event_file)
                goto err_free_put_context;
        if (flags & PERF_FLAG_FD_OUTPUT) {
-                err = perf_counter_set_output(counter, group_fd);
+                err = perf_event_set_output(event, group_fd);
                if (err)
                        goto err_fput_free_put_context;
        }
-        counter->filp = counter_file;
+        event->filp = event_file;
        WARN_ON_ONCE(ctx->parent_ctx);
        mutex_lock(&ctx->mutex);
-        perf_install_in_context(ctx, counter, cpu);
+        perf_install_in_context(ctx, event, cpu);
        ++ctx->generation;
        mutex_unlock(&ctx->mutex);
-        counter->owner = current;
+        event->owner = current;
        get_task_struct(current);
-        mutex_lock(&current->perf_counter_mutex);
+        mutex_lock(&current->perf_event_mutex);
-        list_add_tail(&counter->owner_entry, &current->perf_counter_list);
+        list_add_tail(&event->owner_entry, &current->perf_event_list);
-        mutex_unlock(&current->perf_counter_mutex);
+        mutex_unlock(&current->perf_event_mutex);
 err_fput_free_put_context:
-        fput_light(counter_file, fput_needed2);
+        fput_light(event_file, fput_needed2);
 err_free_put_context:
        if (err < 0)
-                kfree(counter);
+                kfree(event);
 err_put_context:
        if (err < 0)
@@ -4464,88 +4463,88 @@ err_put_context:
 }
 /*
- * inherit a counter from parent task to child task:
+ * inherit a event from parent task to child task:
 */
-static struct perf_counter *
+static struct perf_event *
-inherit_counter(struct perf_counter *parent_counter,
+inherit_event(struct perf_event *parent_event,
              struct task_struct *parent,
-              struct perf_counter_context *parent_ctx,
+              struct perf_event_context *parent_ctx,
              struct task_struct *child,
-              struct perf_counter *group_leader,
+              struct perf_event *group_leader,
-              struct perf_counter_context *child_ctx)
+              struct perf_event_context *child_ctx)
 {
-        struct perf_counter *child_counter;
+        struct perf_event *child_event;
        /*
-         * Instead of creating recursive hierarchies of counters,
+         * Instead of creating recursive hierarchies of events,
-         * we link inherited counters back to the original parent,
+         * we link inherited events back to the original parent,
         * which has a filp for sure, which we use as the reference
         * count:
         */
-        if (parent_counter->parent)
+        if (parent_event->parent)
-                parent_counter = parent_counter->parent;
+                parent_event = parent_event->parent;
-        child_counter = perf_counter_alloc(&parent_counter->attr,
+        child_event = perf_event_alloc(&parent_event->attr,
-                                           parent_counter->cpu, child_ctx,
+                                           parent_event->cpu, child_ctx,
-                                           group_leader, parent_counter,
+                                           group_leader, parent_event,
                                           GFP_KERNEL);
-        if (IS_ERR(child_counter))
+        if (IS_ERR(child_event))
-                return child_counter;
+                return child_event;
        get_ctx(child_ctx);
        /*
-         * Make the child state follow the state of the parent counter,
+         * Make the child state follow the state of the parent event,
         * not its attr.disabled bit.  We hold the parent's mutex,
-         * so we won't race with perf_counter_{en, dis}able_family.
+         * so we won't race with perf_event_{en, dis}able_family.
         */
-        if (parent_counter->state >= PERF_COUNTER_STATE_INACTIVE)
+        if (parent_event->state >= PERF_EVENT_STATE_INACTIVE)
-                child_counter->state = PERF_COUNTER_STATE_INACTIVE;
+                child_event->state = PERF_EVENT_STATE_INACTIVE;
        else
-                child_counter->state = PERF_COUNTER_STATE_OFF;
+                child_event->state = PERF_EVENT_STATE_OFF;
-        if (parent_counter->attr.freq)
+        if (parent_event->attr.freq)
-                child_counter->hw.sample_period = parent_counter->hw.sample_period;
+                child_event->hw.sample_period = parent_event->hw.sample_period;
        /*
         * Link it up in the child's context:
         */
-        add_counter_to_ctx(child_counter, child_ctx);
+        add_event_to_ctx(child_event, child_ctx);
        /*
         * Get a reference to the parent filp - we will fput it
-         * when the child counter exits. This is safe to do because
+         * when the child event exits. This is safe to do because
         * we are in the parent and we know that the filp still
         * exists and has a nonzero count:
         */
-        atomic_long_inc(&parent_counter->filp->f_count);
+        atomic_long_inc(&parent_event->filp->f_count);
        /*
-         * Link this into the parent counter's child list
+         * Link this into the parent event's child list
         */
-        WARN_ON_ONCE(parent_counter->ctx->parent_ctx);
+        WARN_ON_ONCE(parent_event->ctx->parent_ctx);
-        mutex_lock(&parent_counter->child_mutex);
+        mutex_lock(&parent_event->child_mutex);
-        list_add_tail(&child_counter->child_list, &parent_counter->child_list);
+        list_add_tail(&child_event->child_list, &parent_event->child_list);
-        mutex_unlock(&parent_counter->child_mutex);
+        mutex_unlock(&parent_event->child_mutex);
-        return child_counter;
+        return child_event;
 }
-static int inherit_group(struct perf_counter *parent_counter,
+static int inherit_group(struct perf_event *parent_event,
              struct task_struct *parent,
-              struct perf_counter_context *parent_ctx,
+              struct perf_event_context *parent_ctx,
              struct task_struct *child,
-              struct perf_counter_context *child_ctx)
+              struct perf_event_context *child_ctx)
 {
-        struct perf_counter *leader;
+        struct perf_event *leader;
-        struct perf_counter *sub;
+        struct perf_event *sub;
-        struct perf_counter *child_ctr;
+        struct perf_event *child_ctr;
-        leader = inherit_counter(parent_counter, parent, parent_ctx,
+        leader = inherit_event(parent_event, parent, parent_ctx,
                                 child, NULL, child_ctx);
        if (IS_ERR(leader))
                return PTR_ERR(leader);
-        list_for_each_entry(sub, &parent_counter->sibling_list, list_entry) {
+        list_for_each_entry(sub, &parent_event->sibling_list, group_entry) {
-                child_ctr = inherit_counter(sub, parent, parent_ctx,
+                child_ctr = inherit_event(sub, parent, parent_ctx,
                                            child, leader, child_ctx);
                if (IS_ERR(child_ctr))
                        return PTR_ERR(child_ctr);
@@ -4553,74 +4552,74 @@ static int inherit_group(struct perf_counter *parent_counter,
        return 0;
 }
-static void sync_child_counter(struct perf_counter *child_counter,
+static void sync_child_event(struct perf_event *child_event,
                               struct task_struct *child)
 {
-        struct perf_counter *parent_counter = child_counter->parent;
+        struct perf_event *parent_event = child_event->parent;
        u64 child_val;
-        if (child_counter->attr.inherit_stat)
+        if (child_event->attr.inherit_stat)
-                perf_counter_read_event(child_counter, child);
+                perf_event_read_event(child_event, child);
-        child_val = atomic64_read(&child_counter->count);
+        child_val = atomic64_read(&child_event->count);
        /*
         * Add back the child's count to the parent's count:
         */
-        atomic64_add(child_val, &parent_counter->count);
+        atomic64_add(child_val, &parent_event->count);
-        atomic64_add(child_counter->total_time_enabled,
+        atomic64_add(child_event->total_time_enabled,
-                     &parent_counter->child_total_time_enabled);
+                     &parent_event->child_total_time_enabled);
-        atomic64_add(child_counter->total_time_running,
+        atomic64_add(child_event->total_time_running,
-                     &parent_counter->child_total_time_running);
+                     &parent_event->child_total_time_running);
        /*
-         * Remove this counter from the parent's list
+         * Remove this event from the parent's list
         */
-        WARN_ON_ONCE(parent_counter->ctx->parent_ctx);
+        WARN_ON_ONCE(parent_event->ctx->parent_ctx);
-        mutex_lock(&parent_counter->child_mutex);
+        mutex_lock(&parent_event->child_mutex);
-        list_del_init(&child_counter->child_list);
+        list_del_init(&child_event->child_list);
-        mutex_unlock(&parent_counter->child_mutex);
+        mutex_unlock(&parent_event->child_mutex);
        /*
-         * Release the parent counter, if this was the last
+         * Release the parent event, if this was the last
         * reference to it.
         */
-        fput(parent_counter->filp);
+        fput(parent_event->filp);
 }
 static void
-__perf_counter_exit_task(struct perf_counter *child_counter,
+__perf_event_exit_task(struct perf_event *child_event,
-                         struct perf_counter_context *child_ctx,
+                         struct perf_event_context *child_ctx,
                         struct task_struct *child)
 {
-        struct perf_counter *parent_counter;
+        struct perf_event *parent_event;
-        update_counter_times(child_counter);
+        update_event_times(child_event);
-        perf_counter_remove_from_context(child_counter);
+        perf_event_remove_from_context(child_event);
-        parent_counter = child_counter->parent;
+        parent_event = child_event->parent;
        /*
-         * It can happen that parent exits first, and has counters
+         * It can happen that parent exits first, and has events
         * that are still around due to the child reference. These
-         * counters need to be zapped - but otherwise linger.
+         * events need to be zapped - but otherwise linger.
         */
-        if (parent_counter) {
+        if (parent_event) {
-                sync_child_counter(child_counter, child);
+                sync_child_event(child_event, child);
-                free_counter(child_counter);
+                free_event(child_event);
        }
 }
 /*
- * When a child task exits, feed back counter values to parent counters.
+ * When a child task exits, feed back event values to parent events.
 */
-void perf_counter_exit_task(struct task_struct *child)
+void perf_event_exit_task(struct task_struct *child)
 {
-        struct perf_counter *child_counter, *tmp;
+        struct perf_event *child_event, *tmp;
-        struct perf_counter_context *child_ctx;
+        struct perf_event_context *child_ctx;
        unsigned long flags;
-        if (likely(!child->perf_counter_ctxp)) {
+        if (likely(!child->perf_event_ctxp)) {
-                perf_counter_task(child, NULL, 0);
+                perf_event_task(child, NULL, 0);
                return;
        }
@@ -4631,37 +4630,37 @@ void perf_counter_exit_task(struct task_struct *child)
         * scheduled, so we are now safe from rescheduling changing
         * our context.
         */
-        child_ctx = child->perf_counter_ctxp;
+        child_ctx = child->perf_event_ctxp;
-        __perf_counter_task_sched_out(child_ctx);
+        __perf_event_task_sched_out(child_ctx);
        /*
         * Take the context lock here so that if find_get_context is
-         * reading child->perf_counter_ctxp, we wait until it has
+         * reading child->perf_event_ctxp, we wait until it has
         * incremented the context's refcount before we do put_ctx below.
         */
        spin_lock(&child_ctx->lock);
-        child->perf_counter_ctxp = NULL;
+        child->perf_event_ctxp = NULL;
        /*
         * If this context is a clone; unclone it so it can't get
         * swapped to another process while we're removing all
-         * the counters from it.
+         * the events from it.
         */
        unclone_ctx(child_ctx);
        spin_unlock_irqrestore(&child_ctx->lock, flags);
        /*
-         * Report the task dead after unscheduling the counters so that we
+         * Report the task dead after unscheduling the events so that we
-         * won't get any samples after PERF_EVENT_EXIT. We can however still
+         * won't get any samples after PERF_RECORD_EXIT. We can however still
-         * get a few PERF_EVENT_READ events.
+         * get a few PERF_RECORD_READ events.
         */
-        perf_counter_task(child, child_ctx, 0);
+        perf_event_task(child, child_ctx, 0);
        /*
         * We can recurse on the same lock type through:
         *
-         *   __perf_counter_exit_task()
+         *   __perf_event_exit_task()
-         *     sync_child_counter()
+         *     sync_child_event()
-         *       fput(parent_counter->filp)
+         *       fput(parent_event->filp)
         *         perf_release()
         *           mutex_lock(&ctx->mutex)
         *
@@ -4670,16 +4669,16 @@ void perf_counter_exit_task(struct task_struct *child)
        mutex_lock_nested(&child_ctx->mutex, SINGLE_DEPTH_NESTING);
 again:
-        list_for_each_entry_safe(child_counter, tmp, &child_ctx->counter_list,
+        list_for_each_entry_safe(child_event, tmp, &child_ctx->group_list,
-                                 list_entry)
+                                 group_entry)
-                __perf_counter_exit_task(child_counter, child_ctx, child);
+                __perf_event_exit_task(child_event, child_ctx, child);
        /*
-         * If the last counter was a group counter, it will have appended all
+         * If the last event was a group event, it will have appended all
         * its siblings to the list, but we obtained 'tmp' before that which
         * will still point to the list head terminating the iteration.
         */
-        if (!list_empty(&child_ctx->counter_list))
+        if (!list_empty(&child_ctx->group_list))
                goto again;
        mutex_unlock(&child_ctx->mutex);
@@ -4691,33 +4690,33 @@ again:
 * free an unexposed, unused context as created by inheritance by
 * init_task below, used by fork() in case of fail.
 */
-void perf_counter_free_task(struct task_struct *task)
+void perf_event_free_task(struct task_struct *task)
 {
-        struct perf_counter_context *ctx = task->perf_counter_ctxp;
+        struct perf_event_context *ctx = task->perf_event_ctxp;
-        struct perf_counter *counter, *tmp;
+        struct perf_event *event, *tmp;
        if (!ctx)
                return;
        mutex_lock(&ctx->mutex);
 again:
-        list_for_each_entry_safe(counter, tmp, &ctx->counter_list, list_entry) {
+        list_for_each_entry_safe(event, tmp, &ctx->group_list, group_entry) {
-                struct perf_counter *parent = counter->parent;
+                struct perf_event *parent = event->parent;
                if (WARN_ON_ONCE(!parent))
                        continue;
                mutex_lock(&parent->child_mutex);
-                list_del_init(&counter->child_list);
+                list_del_init(&event->child_list);
                mutex_unlock(&parent->child_mutex);
                fput(parent->filp);
-                list_del_counter(counter, ctx);
+                list_del_event(event, ctx);
-                free_counter(counter);
+                free_event(event);
        }
-        if (!list_empty(&ctx->counter_list))
+        if (!list_empty(&ctx->group_list))
                goto again;
        mutex_unlock(&ctx->mutex);
@@ -4726,37 +4725,37 @@ again:
 }
 /*
- * Initialize the perf_counter context in task_struct
+ * Initialize the perf_event context in task_struct
 */
-int perf_counter_init_task(struct task_struct *child)
+int perf_event_init_task(struct task_struct *child)
 {
-        struct perf_counter_context *child_ctx, *parent_ctx;
+        struct perf_event_context *child_ctx, *parent_ctx;
-        struct perf_counter_context *cloned_ctx;
+        struct perf_event_context *cloned_ctx;
-        struct perf_counter *counter;
+        struct perf_event *event;
        struct task_struct *parent = current;
        int inherited_all = 1;
        int ret = 0;
-        child->perf_counter_ctxp = NULL;
+        child->perf_event_ctxp = NULL;
-        mutex_init(&child->perf_counter_mutex);
+        mutex_init(&child->perf_event_mutex);
-        INIT_LIST_HEAD(&child->perf_counter_list);
+        INIT_LIST_HEAD(&child->perf_event_list);
-        if (likely(!parent->perf_counter_ctxp))
+        if (likely(!parent->perf_event_ctxp))
                return 0;
        /*
         * This is executed from the parent task context, so inherit
-         * counters that have been marked for cloning.
+         * events that have been marked for cloning.
         * First allocate and initialize a context for the child.
         */
-        child_ctx = kmalloc(sizeof(struct perf_counter_context), GFP_KERNEL);
+        child_ctx = kmalloc(sizeof(struct perf_event_context), GFP_KERNEL);
        if (!child_ctx)
                return -ENOMEM;
-        __perf_counter_init_context(child_ctx, child);
+        __perf_event_init_context(child_ctx, child);
-        child->perf_counter_ctxp = child_ctx;
+        child->perf_event_ctxp = child_ctx;
        get_task_struct(child);
        /*
@@ -4782,16 +4781,16 @@ int perf_counter_init_task(struct task_struct *child)
         * We dont have to disable NMIs - we are only looking at
         * the list, not manipulating it:
         */
-        list_for_each_entry_rcu(counter, &parent_ctx->event_list, event_entry) {
+        list_for_each_entry_rcu(event, &parent_ctx->event_list, event_entry) {
-                if (counter != counter->group_leader)
+                if (event != event->group_leader)
                        continue;
-                if (!counter->attr.inherit) {
+                if (!event->attr.inherit) {
                        inherited_all = 0;
                        continue;
                }
-                ret = inherit_group(counter, parent, parent_ctx,
+                ret = inherit_group(event, parent, parent_ctx,
                                             child, child_ctx);
                if (ret) {
                        inherited_all = 0;
@@ -4805,7 +4804,7 @@ int perf_counter_init_task(struct task_struct *child)
                 * context, or of whatever the parent is a clone of.
                 * Note that if the parent is a clone, it could get
                 * uncloned at any point, but that doesn't matter
-                 * because the list of counters and the generation
+                 * because the list of events and the generation
                 * count can't have changed since we took the mutex.
                 */
                cloned_ctx = rcu_dereference(parent_ctx->parent_ctx);
@@ -4826,41 +4825,41 @@ int perf_counter_init_task(struct task_struct *child)
        return ret;
 }
-static void __cpuinit perf_counter_init_cpu(int cpu)
+static void __cpuinit perf_event_init_cpu(int cpu)
 {
        struct perf_cpu_context *cpuctx;
        cpuctx = &per_cpu(perf_cpu_context, cpu);
-        __perf_counter_init_context(&cpuctx->ctx, NULL);
+        __perf_event_init_context(&cpuctx->ctx, NULL);
        spin_lock(&perf_resource_lock);
-        cpuctx->max_pertask = perf_max_counters - perf_reserved_percpu;
+        cpuctx->max_pertask = perf_max_events - perf_reserved_percpu;
        spin_unlock(&perf_resource_lock);
-        hw_perf_counter_setup(cpu);
+        hw_perf_event_setup(cpu);
 }
 #ifdef CONFIG_HOTPLUG_CPU
-static void __perf_counter_exit_cpu(void *info)
+static void __perf_event_exit_cpu(void *info)
 {
        struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
-        struct perf_counter_context *ctx = &cpuctx->ctx;
+        struct perf_event_context *ctx = &cpuctx->ctx;
-        struct perf_counter *counter, *tmp;
+        struct perf_event *event, *tmp;
-        list_for_each_entry_safe(counter, tmp, &ctx->counter_list, list_entry)
+        list_for_each_entry_safe(event, tmp, &ctx->group_list, group_entry)
-                __perf_counter_remove_from_context(counter);
+                __perf_event_remove_from_context(event);
 }
-static void perf_counter_exit_cpu(int cpu)
+static void perf_event_exit_cpu(int cpu)
 {
        struct perf_cpu_context *cpuctx = &per_cpu(perf_cpu_context, cpu);
-        struct perf_counter_context *ctx = &cpuctx->ctx;
+        struct perf_event_context *ctx = &cpuctx->ctx;
        mutex_lock(&ctx->mutex);
-        smp_call_function_single(cpu, __perf_counter_exit_cpu, NULL, 1);
+        smp_call_function_single(cpu, __perf_event_exit_cpu, NULL, 1);
        mutex_unlock(&ctx->mutex);
 }
 #else
-static inline void perf_counter_exit_cpu(int cpu) { }
+static inline void perf_event_exit_cpu(int cpu) { }
 #endif
 static int __cpuinit
@@ -4872,17 +4871,17 @@ perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
        case CPU_UP_PREPARE:
        case CPU_UP_PREPARE_FROZEN:
-                perf_counter_init_cpu(cpu);
+                perf_event_init_cpu(cpu);
                break;
        case CPU_ONLINE:
        case CPU_ONLINE_FROZEN:
-                hw_perf_counter_setup_online(cpu);
+                hw_perf_event_setup_online(cpu);
                break;
        case CPU_DOWN_PREPARE:
        case CPU_DOWN_PREPARE_FROZEN:
-                perf_counter_exit_cpu(cpu);
+                perf_event_exit_cpu(cpu);
                break;
        default:
@@ -4900,7 +4899,7 @@ static struct notifier_block __cpuinitdata perf_cpu_nb = {
        .priority               = 20,
 };
-void __init perf_counter_init(void)
+void __init perf_event_init(void)
 {
        perf_cpu_notify(&perf_cpu_nb, (unsigned long)CPU_UP_PREPARE,
                        (void *)(long)smp_processor_id());
@@ -4926,7 +4925,7 @@ perf_set_reserve_percpu(struct sysdev_class *class,
        err = strict_strtoul(buf, 10, &val);
        if (err)
                return err;
-        if (val > perf_max_counters)
+        if (val > perf_max_events)
                return -EINVAL;
        spin_lock(&perf_resource_lock);
@@ -4934,8 +4933,8 @@ perf_set_reserve_percpu(struct sysdev_class *class,
        for_each_online_cpu(cpu) {
                cpuctx = &per_cpu(perf_cpu_context, cpu);
                spin_lock_irq(&cpuctx->ctx.lock);
-                mpt = min(perf_max_counters - cpuctx->ctx.nr_counters,
+                mpt = min(perf_max_events - cpuctx->ctx.nr_events,
-                          perf_max_counters - perf_reserved_percpu);
+                          perf_max_events - perf_reserved_percpu);
                cpuctx->max_pertask = mpt;
                spin_unlock_irq(&cpuctx->ctx.lock);
        }
@@ -4990,12 +4989,12 @@ static struct attribute *perfclass_attrs[] = {
 static struct attribute_group perfclass_attr_group = {
        .attrs                  = perfclass_attrs,
-        .name                   = "perf_counters",
+        .name                   = "perf_events",
 };
-static int __init perf_counter_sysfs_init(void)
+static int __init perf_event_sysfs_init(void)
 {
        return sysfs_create_group(&cpu_sysdev_class.kset.kobj,
                                  &perfclass_attr_group);
 }
-device_initcall(perf_counter_sysfs_init);
+device_initcall(perf_event_sysfs_init);
diff --git a/kernel/pid.c b/kernel/pid.c
index 31310b5d3f50..d3f722d20f9c 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -40,7 +40,7 @@
 #define pid_hashfn(nr, ns)      \
        hash_long((unsigned long)nr + (unsigned long)ns, pidhash_shift)
 static struct hlist_head *pid_hash;
-static int pidhash_shift;
+static unsigned int pidhash_shift = 4;
 struct pid init_struct_pid = INIT_STRUCT_PID;
 int pid_max = PID_MAX_DEFAULT;
@@ -499,19 +499,12 @@ struct pid *find_ge_pid(int nr, struct pid_namespace *ns)
 void __init pidhash_init(void)
 {
        int i, pidhash_size;
-        unsigned long megabytes = nr_kernel_pages >> (20 - PAGE_SHIFT);
-        pidhash_shift = max(4, fls(megabytes * 4));
+        pid_hash = alloc_large_system_hash("PID", sizeof(*pid_hash), 0, 18,
-        pidhash_shift = min(12, pidhash_shift);
+                                           HASH_EARLY | HASH_SMALL,
+                                           &pidhash_shift, NULL, 4096);
        pidhash_size = 1 << pidhash_shift;
-        printk("PID hash table entries: %d (order: %d, %Zd bytes)\n",
-                pidhash_size, pidhash_shift,
-                pidhash_size * sizeof(struct hlist_head));
-        pid_hash = alloc_bootmem(pidhash_size * sizeof(*(pid_hash)));
-        if (!pid_hash)
-                panic("Could not alloc pidhash!\n");
        for (i = 0; i < pidhash_size; i++)
                INIT_HLIST_HEAD(&pid_hash[i]);
 }
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 821722ae58a7..86b3796b0436 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -118,7 +118,7 @@ struct pid_namespace *copy_pid_ns(unsigned long flags, struct pid_namespace *old
 {
        if (!(flags & CLONE_NEWPID))
                return get_pid_ns(old_ns);
-        if (flags & CLONE_THREAD)
+        if (flags & (CLONE_THREAD|CLONE_PARENT))
                return ERR_PTR(-EINVAL);
        return create_pid_namespace(old_ns);
 }
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index e33a21cb9407..5c9dc228747b 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -8,17 +8,18 @@
 #include <linux/math64.h>
 #include <asm/uaccess.h>
 #include <linux/kernel_stat.h>
+#include <trace/events/timer.h>
 /*
 * Called after updating RLIMIT_CPU to set timer expiration if necessary.
 */
 void update_rlimit_cpu(unsigned long rlim_new)
 {
-        cputime_t cputime;
+        cputime_t cputime = secs_to_cputime(rlim_new);
+        struct signal_struct *const sig = current->signal;
-        cputime = secs_to_cputime(rlim_new);
+        if (cputime_eq(sig->it[CPUCLOCK_PROF].expires, cputime_zero) ||
-        if (cputime_eq(current->signal->it_prof_expires, cputime_zero) ||
+            cputime_gt(sig->it[CPUCLOCK_PROF].expires, cputime)) {
-            cputime_gt(current->signal->it_prof_expires, cputime)) {
                spin_lock_irq(&current->sighand->siglock);
                set_process_cpu_timer(current, CPUCLOCK_PROF, &cputime, NULL);
                spin_unlock_irq(&current->sighand->siglock);
@@ -542,6 +543,17 @@ static void clear_dead_task(struct k_itimer *timer, union cpu_time_count now)
                                             now);
 }
+static inline int expires_gt(cputime_t expires, cputime_t new_exp)
+{
+        return cputime_eq(expires, cputime_zero) ||
+               cputime_gt(expires, new_exp);
+}
+static inline int expires_le(cputime_t expires, cputime_t new_exp)
+{
+        return !cputime_eq(expires, cputime_zero) &&
+               cputime_le(expires, new_exp);
+}
 /*
 * Insert the timer on the appropriate list before any timers that
 * expire later.  This must be called with the tasklist_lock held
@@ -586,34 +598,32 @@ static void arm_timer(struct k_itimer *timer, union cpu_time_count now)
                 */
                if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
+                        union cpu_time_count *exp = &nt->expires;
                        switch (CPUCLOCK_WHICH(timer->it_clock)) {
                        default:
                                BUG();
                        case CPUCLOCK_PROF:
-                                if (cputime_eq(p->cputime_expires.prof_exp,
+                                if (expires_gt(p->cputime_expires.prof_exp,
-                                               cputime_zero) ||
+                                               exp->cpu))
-                                    cputime_gt(p->cputime_expires.prof_exp,
+                                        p->cputime_expires.prof_exp = exp->cpu;
-                                               nt->expires.cpu))
-                                        p->cputime_expires.prof_exp =
-                                                nt->expires.cpu;
                                break;
                        case CPUCLOCK_VIRT:
-                                if (cputime_eq(p->cputime_expires.virt_exp,
+                                if (expires_gt(p->cputime_expires.virt_exp,
-                                               cputime_zero) ||
+                                               exp->cpu))
-                                    cputime_gt(p->cputime_expires.virt_exp,
+                                        p->cputime_expires.virt_exp = exp->cpu;
-                                               nt->expires.cpu))
-                                        p->cputime_expires.virt_exp =
-                                                nt->expires.cpu;
                                break;
                        case CPUCLOCK_SCHED:
                                if (p->cputime_expires.sched_exp == 0 ||
-                                    p->cputime_expires.sched_exp >
+                                    p->cputime_expires.sched_exp > exp->sched)
-                                                        nt->expires.sched)
                                        p->cputime_expires.sched_exp =
-                                                nt->expires.sched;
+                                                                exp->sched;
                                break;
                        }
                } else {
+                        struct signal_struct *const sig = p->signal;
+                        union cpu_time_count *exp = &timer->it.cpu.expires;
                        /*
                         * For a process timer, set the cached expiration time.
                         */
@@ -621,30 +631,23 @@ static void arm_timer(struct k_itimer *timer, union cpu_time_count now)
                        default:
                                BUG();
                        case CPUCLOCK_VIRT:
-                                if (!cputime_eq(p->signal->it_virt_expires,
+                                if (expires_le(sig->it[CPUCLOCK_VIRT].expires,
-                                                cputime_zero) &&
+                                               exp->cpu))
-                                    cputime_lt(p->signal->it_virt_expires,
-                                               timer->it.cpu.expires.cpu))
                                        break;
-                                p->signal->cputime_expires.virt_exp =
+                                sig->cputime_expires.virt_exp = exp->cpu;
-                                        timer->it.cpu.expires.cpu;
                                break;
                        case CPUCLOCK_PROF:
-                                if (!cputime_eq(p->signal->it_prof_expires,
+                                if (expires_le(sig->it[CPUCLOCK_PROF].expires,
-                                                cputime_zero) &&
+                                               exp->cpu))
-                                    cputime_lt(p->signal->it_prof_expires,
-                                               timer->it.cpu.expires.cpu))
                                        break;
-                                i = p->signal->rlim[RLIMIT_CPU].rlim_cur;
+                                i = sig->rlim[RLIMIT_CPU].rlim_cur;
                                if (i != RLIM_INFINITY &&
-                                    i <= cputime_to_secs(timer->it.cpu.expires.cpu))
+                                    i <= cputime_to_secs(exp->cpu))
                                        break;
-                                p->signal->cputime_expires.prof_exp =
+                                sig->cputime_expires.prof_exp = exp->cpu;
-                                        timer->it.cpu.expires.cpu;
                                break;
                        case CPUCLOCK_SCHED:
-                                p->signal->cputime_expires.sched_exp =
+                                sig->cputime_expires.sched_exp = exp->sched;
-                                        timer->it.cpu.expires.sched;
                                break;
                        }
                }
@@ -1071,6 +1074,40 @@ static void stop_process_timers(struct task_struct *tsk)
        spin_unlock_irqrestore(&cputimer->lock, flags);
 }
+static u32 onecputick;
+static void check_cpu_itimer(struct task_struct *tsk, struct cpu_itimer *it,
+                             cputime_t *expires, cputime_t cur_time, int signo)
+{
+        if (cputime_eq(it->expires, cputime_zero))
+                return;
+        if (cputime_ge(cur_time, it->expires)) {
+                if (!cputime_eq(it->incr, cputime_zero)) {
+                        it->expires = cputime_add(it->expires, it->incr);
+                        it->error += it->incr_error;
+                        if (it->error >= onecputick) {
+                                it->expires = cputime_sub(it->expires,
+                                                          cputime_one_jiffy);
+                                it->error -= onecputick;
+                        }
+                } else {
+                        it->expires = cputime_zero;
+                }
+                trace_itimer_expire(signo == SIGPROF ?
+                                    ITIMER_PROF : ITIMER_VIRTUAL,
+                                    tsk->signal->leader_pid, cur_time);
+                __group_send_sig_info(signo, SEND_SIG_PRIV, tsk);
+        }
+        if (!cputime_eq(it->expires, cputime_zero) &&
+            (cputime_eq(*expires, cputime_zero) ||
+             cputime_lt(it->expires, *expires))) {
+                *expires = it->expires;
+        }
+}
 /*
 * Check for any per-thread CPU timers that have fired and move them
 * off the tsk->*_timers list onto the firing list.  Per-thread timers
@@ -1090,10 +1127,10 @@ static void check_process_timers(struct task_struct *tsk,
         * Don't sample the current process CPU clocks if there are no timers.
         */
        if (list_empty(&timers[CPUCLOCK_PROF]) &&
-            cputime_eq(sig->it_prof_expires, cputime_zero) &&
+            cputime_eq(sig->it[CPUCLOCK_PROF].expires, cputime_zero) &&
            sig->rlim[RLIMIT_CPU].rlim_cur == RLIM_INFINITY &&
            list_empty(&timers[CPUCLOCK_VIRT]) &&
-            cputime_eq(sig->it_virt_expires, cputime_zero) &&
+            cputime_eq(sig->it[CPUCLOCK_VIRT].expires, cputime_zero) &&
            list_empty(&timers[CPUCLOCK_SCHED])) {
                stop_process_timers(tsk);
                return;
@@ -1153,38 +1190,11 @@ static void check_process_timers(struct task_struct *tsk,
        /*
         * Check for the special case process timers.
         */
-        if (!cputime_eq(sig->it_prof_expires, cputime_zero)) {
+        check_cpu_itimer(tsk, &sig->it[CPUCLOCK_PROF], &prof_expires, ptime,
-                if (cputime_ge(ptime, sig->it_prof_expires)) {
+                         SIGPROF);
-                        /* ITIMER_PROF fires and reloads.  */
+        check_cpu_itimer(tsk, &sig->it[CPUCLOCK_VIRT], &virt_expires, utime,
-                        sig->it_prof_expires = sig->it_prof_incr;
+                         SIGVTALRM);
-                        if (!cputime_eq(sig->it_prof_expires, cputime_zero)) {
-                                sig->it_prof_expires = cputime_add(
-                                        sig->it_prof_expires, ptime);
-                        }
-                        __group_send_sig_info(SIGPROF, SEND_SIG_PRIV, tsk);
-                }
-                if (!cputime_eq(sig->it_prof_expires, cputime_zero) &&
-                    (cputime_eq(prof_expires, cputime_zero) ||
-                     cputime_lt(sig->it_prof_expires, prof_expires))) {
-                        prof_expires = sig->it_prof_expires;
-                }
-        }
-        if (!cputime_eq(sig->it_virt_expires, cputime_zero)) {
-                if (cputime_ge(utime, sig->it_virt_expires)) {
-                        /* ITIMER_VIRTUAL fires and reloads.  */
-                        sig->it_virt_expires = sig->it_virt_incr;
-                        if (!cputime_eq(sig->it_virt_expires, cputime_zero)) {
-                                sig->it_virt_expires = cputime_add(
-                                        sig->it_virt_expires, utime);
-                        }
-                        __group_send_sig_info(SIGVTALRM, SEND_SIG_PRIV, tsk);
-                }
-                if (!cputime_eq(sig->it_virt_expires, cputime_zero) &&
-                    (cputime_eq(virt_expires, cputime_zero) ||
-                     cputime_lt(sig->it_virt_expires, virt_expires))) {
-                        virt_expires = sig->it_virt_expires;
-                }
-        }
        if (sig->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY) {
                unsigned long psecs = cputime_to_secs(ptime);
                cputime_t x;
@@ -1457,7 +1467,7 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
                if (!cputime_eq(*oldval, cputime_zero)) {
                        if (cputime_le(*oldval, now.cpu)) {
                                /* Just about to fire. */
-                                *oldval = jiffies_to_cputime(1);
+                                *oldval = cputime_one_jiffy;
                        } else {
                                *oldval = cputime_sub(*oldval, now.cpu);
                        }
@@ -1703,10 +1713,15 @@ static __init int init_posix_cpu_timers(void)
                .nsleep = thread_cpu_nsleep,
                .nsleep_restart = thread_cpu_nsleep_restart,
        };
+        struct timespec ts;
        register_posix_clock(CLOCK_PROCESS_CPUTIME_ID, &process);
        register_posix_clock(CLOCK_THREAD_CPUTIME_ID, &thread);
+        cputime_to_timespec(cputime_one_jiffy, &ts);
+        onecputick = ts.tv_nsec;
+        WARN_ON(ts.tv_sec != 0);
        return 0;
 }
 __initcall(init_posix_cpu_timers);
diff --git a/kernel/power/process.c b/kernel/power/process.c
index da2072d73811..cc2e55373b68 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -9,6 +9,7 @@
 #undef DEBUG
 #include <linux/interrupt.h>
+#include <linux/oom.h>
 #include <linux/suspend.h>
 #include <linux/module.h>
 #include <linux/syscalls.h>
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 97955b0e44f4..36cb168e4330 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -619,7 +619,7 @@ __register_nosave_region(unsigned long start_pfn, unsigned long end_pfn,
                BUG_ON(!region);
        } else
                /* This allocation cannot fail */
-                region = alloc_bootmem_low(sizeof(struct nosave_region));
+                region = alloc_bootmem(sizeof(struct nosave_region));
        region->start_pfn = start_pfn;
        region->end_pfn = end_pfn;
        list_add_tail(&region->list, &nosave_regions);
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index 8ba052c86d48..b101cdc4df3f 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -13,7 +13,6 @@
 #include <linux/module.h>
 #include <linux/file.h>
-#include <linux/utsname.h>
 #include <linux/delay.h>
 #include <linux/bitops.h>
 #include <linux/genhd.h>
diff --git a/kernel/printk.c b/kernel/printk.c
index 602033acd6c7..f38b07f78a4e 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -206,12 +206,11 @@ __setup("log_buf_len=", log_buf_len_setup);
 #ifdef CONFIG_BOOT_PRINTK_DELAY
 static unsigned int boot_delay; /* msecs delay after each printk during bootup */
-static unsigned long long printk_delay_msec; /* per msec, based on boot_delay */
+static unsigned long long loops_per_msec;       /* based on boot_delay */
 static int __init boot_delay_setup(char *str)
 {
        unsigned long lpj;
-        unsigned long long loops_per_msec;
        lpj = preset_lpj ? preset_lpj : 1000000;        /* some guess */
        loops_per_msec = (unsigned long long)lpj / 1000 * HZ;
@@ -220,10 +219,9 @@ static int __init boot_delay_setup(char *str)
        if (boot_delay > 10 * 1000)
                boot_delay = 0;
-        printk_delay_msec = loops_per_msec;
+        pr_debug("boot_delay: %u, preset_lpj: %ld, lpj: %lu, "
-        printk(KERN_DEBUG "boot_delay: %u, preset_lpj: %ld, lpj: %lu, "
+                "HZ: %d, loops_per_msec: %llu\n",
-                "HZ: %d, printk_delay_msec: %llu\n",
+                boot_delay, preset_lpj, lpj, HZ, loops_per_msec);
-                boot_delay, preset_lpj, lpj, HZ, printk_delay_msec);
        return 1;
 }
 __setup("boot_delay=", boot_delay_setup);
@@ -236,7 +234,7 @@ static void boot_delay_msec(void)
        if (boot_delay == 0 || system_state != SYSTEM_BOOTING)
                return;
-        k = (unsigned long long)printk_delay_msec * boot_delay;
+        k = (unsigned long long)loops_per_msec * boot_delay;
        timeout = jiffies + msecs_to_jiffies(boot_delay);
        while (k) {
@@ -655,6 +653,20 @@ static int recursion_bug;
 static int new_text_line = 1;
 static char printk_buf[1024];
+int printk_delay_msec __read_mostly;
+static inline void printk_delay(void)
+{
+        if (unlikely(printk_delay_msec)) {
+                int m = printk_delay_msec;
+                while (m--) {
+                        mdelay(1);
+                        touch_nmi_watchdog();
+                }
+        }
+}
 asmlinkage int vprintk(const char *fmt, va_list args)
 {
        int printed_len = 0;
@@ -664,6 +676,7 @@ asmlinkage int vprintk(const char *fmt, va_list args)
        char *p;
        boot_delay_msec();
+        printk_delay();
        preempt_disable();
        /* This stops the holder of console_sem just where we want him */
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 307c285af59e..23bd09cd042e 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -266,9 +266,10 @@ static int ignoring_children(struct sighand_struct *sigh)
 * or self-reaping.  Do notification now if it would have happened earlier.
 * If it should reap itself, return true.
 *
- * If it's our own child, there is no notification to do.
+ * If it's our own child, there is no notification to do. But if our normal
- * But if our normal children self-reap, then this child
+ * children self-reap, then this child was prevented by ptrace and we must
- * was prevented by ptrace and we must reap it now.
+ * reap it now, in that case we must also wake up sub-threads sleeping in
+ * do_wait().
 */
 static bool __ptrace_detach(struct task_struct *tracer, struct task_struct *p)
 {
@@ -278,8 +279,10 @@ static bool __ptrace_detach(struct task_struct *tracer, struct task_struct *p)
                if (!task_detached(p) && thread_group_empty(p)) {
                        if (!same_thread_group(p->real_parent, tracer))
                                do_notify_parent(p, p->exit_signal);
-                        else if (ignoring_children(tracer->sighand))
+                        else if (ignoring_children(tracer->sighand)) {
+                                __wake_up_parent(p, tracer);
                                p->exit_signal = -1;
+                        }
                }
                if (task_detached(p)) {
                        /* Mark it as in the process of being reaped. */
diff --git a/kernel/res_counter.c b/kernel/res_counter.c
index e1338f074314..88faec23e833 100644
--- a/kernel/res_counter.c
+++ b/kernel/res_counter.c
@@ -19,6 +19,7 @@ void res_counter_init(struct res_counter *counter, struct res_counter *parent)
 {
        spin_lock_init(&counter->lock);
        counter->limit = RESOURCE_MAX;
+        counter->soft_limit = RESOURCE_MAX;
        counter->parent = parent;
 }
@@ -36,17 +37,27 @@ int res_counter_charge_locked(struct res_counter *counter, unsigned long val)
 }
 int res_counter_charge(struct res_counter *counter, unsigned long val,
-                        struct res_counter **limit_fail_at)
+                        struct res_counter **limit_fail_at,
+                        struct res_counter **soft_limit_fail_at)
 {
        int ret;
        unsigned long flags;
        struct res_counter *c, *u;
        *limit_fail_at = NULL;
+        if (soft_limit_fail_at)
+                *soft_limit_fail_at = NULL;
        local_irq_save(flags);
        for (c = counter; c != NULL; c = c->parent) {
                spin_lock(&c->lock);
                ret = res_counter_charge_locked(c, val);
+                /*
+                 * With soft limits, we return the highest ancestor
+                 * that exceeds its soft limit
+                 */
+                if (soft_limit_fail_at &&
+                        !res_counter_soft_limit_check_locked(c))
+                        *soft_limit_fail_at = c;
                spin_unlock(&c->lock);
                if (ret < 0) {
                        *limit_fail_at = c;
@@ -74,7 +85,8 @@ void res_counter_uncharge_locked(struct res_counter *counter, unsigned long val)
        counter->usage -= val;
 }
-void res_counter_uncharge(struct res_counter *counter, unsigned long val)
+void res_counter_uncharge(struct res_counter *counter, unsigned long val,
+                                bool *was_soft_limit_excess)
 {
        unsigned long flags;
        struct res_counter *c;
@@ -82,6 +94,9 @@ void res_counter_uncharge(struct res_counter *counter, unsigned long val)
        local_irq_save(flags);
        for (c = counter; c != NULL; c = c->parent) {
                spin_lock(&c->lock);
+                if (was_soft_limit_excess)
+                        *was_soft_limit_excess =
+                                !res_counter_soft_limit_check_locked(c);
                res_counter_uncharge_locked(c, val);
                spin_unlock(&c->lock);
        }
@@ -101,6 +116,8 @@ res_counter_member(struct res_counter *counter, int member)
                return &counter->limit;
        case RES_FAILCNT:
                return &counter->failcnt;
+        case RES_SOFT_LIMIT:
+                return &counter->soft_limit;
        };
        BUG();
diff --git a/kernel/resource.c b/kernel/resource.c
index 78b087221c15..fb11a58b9594 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -223,13 +223,13 @@ int release_resource(struct resource *old)
 EXPORT_SYMBOL(release_resource);
-#if defined(CONFIG_MEMORY_HOTPLUG) && !defined(CONFIG_ARCH_HAS_WALK_MEMORY)
+#if !defined(CONFIG_ARCH_HAS_WALK_MEMORY)
 /*
 * Finds the lowest memory reosurce exists within [res->start.res->end)
- * the caller must specify res->start, res->end, res->flags.
+ * the caller must specify res->start, res->end, res->flags and "name".
 * If found, returns 0, res is overwritten, if not found, returns -1.
 */
-static int find_next_system_ram(struct resource *res)
+static int find_next_system_ram(struct resource *res, char *name)
 {
        resource_size_t start, end;
        struct resource *p;
@@ -245,6 +245,8 @@ static int find_next_system_ram(struct resource *res)
                /* system ram is just marked as IORESOURCE_MEM */
                if (p->flags != res->flags)
                        continue;
+                if (name && strcmp(p->name, name))
+                        continue;
                if (p->start > end) {
                        p = NULL;
                        break;
@@ -262,19 +264,26 @@ static int find_next_system_ram(struct resource *res)
                res->end = p->end;
        return 0;
 }
-int
-walk_memory_resource(unsigned long start_pfn, unsigned long nr_pages, void *arg,
+/*
-                        int (*func)(unsigned long, unsigned long, void *))
+ * This function calls callback against all memory range of "System RAM"
+ * which are marked as IORESOURCE_MEM and IORESOUCE_BUSY.
+ * Now, this function is only for "System RAM".
+ */
+int walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages,
+                void *arg, int (*func)(unsigned long, unsigned long, void *))
 {
        struct resource res;
        unsigned long pfn, len;
        u64 orig_end;
        int ret = -1;
        res.start = (u64) start_pfn << PAGE_SHIFT;
        res.end = ((u64)(start_pfn + nr_pages) << PAGE_SHIFT) - 1;
        res.flags = IORESOURCE_MEM | IORESOURCE_BUSY;
        orig_end = res.end;
-        while ((res.start < res.end) && (find_next_system_ram(&res) >= 0)) {
+        while ((res.start < res.end) &&
+                (find_next_system_ram(&res, "System RAM") >= 0)) {
                pfn = (unsigned long)(res.start >> PAGE_SHIFT);
                len = (unsigned long)((res.end + 1 - res.start) >> PAGE_SHIFT);
                ret = (*func)(pfn, len, arg);
diff --git a/kernel/sched.c b/kernel/sched.c
index 830967e18285..ee61f454a98b 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -39,7 +39,7 @@
 #include <linux/completion.h>
 #include <linux/kernel_stat.h>
 #include <linux/debug_locks.h>
-#include <linux/perf_counter.h>
+#include <linux/perf_event.h>
 #include <linux/security.h>
 #include <linux/notifier.h>
 #include <linux/profile.h>
@@ -2053,7 +2053,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
                if (task_hot(p, old_rq->clock, NULL))
                        schedstat_inc(p, se.nr_forced2_migrations);
 #endif
-                perf_swcounter_event(PERF_COUNT_SW_CPU_MIGRATIONS,
+                perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS,
                                     1, 1, NULL, 0);
        }
        p->se.vruntime -= old_cfsrq->min_vruntime -
@@ -2718,7 +2718,7 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
         */
        prev_state = prev->state;
        finish_arch_switch(prev);
-        perf_counter_task_sched_in(current, cpu_of(rq));
+        perf_event_task_sched_in(current, cpu_of(rq));
        finish_lock_switch(rq, prev);
        fire_sched_in_preempt_notifiers(current);
@@ -2904,6 +2904,19 @@ unsigned long nr_iowait(void)
        return sum;
 }
+unsigned long nr_iowait_cpu(void)
+{
+        struct rq *this = this_rq();
+        return atomic_read(&this->nr_iowait);
+}
+unsigned long this_cpu_load(void)
+{
+        struct rq *this = this_rq();
+        return this->cpu_load[0];
+}
 /* Variables and functions for calc_load */
 static atomic_long_t calc_load_tasks;
 static unsigned long calc_load_update;
@@ -5079,17 +5092,16 @@ void account_idle_time(cputime_t cputime)
 */
 void account_process_tick(struct task_struct *p, int user_tick)
 {
-        cputime_t one_jiffy = jiffies_to_cputime(1);
+        cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
-        cputime_t one_jiffy_scaled = cputime_to_scaled(one_jiffy);
        struct rq *rq = this_rq();
        if (user_tick)
-                account_user_time(p, one_jiffy, one_jiffy_scaled);
+                account_user_time(p, cputime_one_jiffy, one_jiffy_scaled);
        else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET))
-                account_system_time(p, HARDIRQ_OFFSET, one_jiffy,
+                account_system_time(p, HARDIRQ_OFFSET, cputime_one_jiffy,
                                    one_jiffy_scaled);
        else
-                account_idle_time(one_jiffy);
+                account_idle_time(cputime_one_jiffy);
 }
 /*
@@ -5193,7 +5205,7 @@ void scheduler_tick(void)
        curr->sched_class->task_tick(rq, curr, 0);
        spin_unlock(&rq->lock);
-        perf_counter_task_tick(curr, cpu);
+        perf_event_task_tick(curr, cpu);
 #ifdef CONFIG_SMP
        rq->idle_at_tick = idle_cpu(cpu);
@@ -5409,7 +5421,7 @@ need_resched_nonpreemptible:
        if (likely(prev != next)) {
                sched_info_switch(prev, next);
-                perf_counter_task_sched_out(prev, next, cpu);
+                perf_event_task_sched_out(prev, next, cpu);
                rq->nr_switches++;
                rq->curr = next;
@@ -7671,7 +7683,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
 /*
 * Register at high priority so that task migration (migrate_all_tasks)
 * happens before everything else.  This has to be lower priority than
- * the notifier in the perf_counter subsystem, though.
+ * the notifier in the perf_event subsystem, though.
 */
 static struct notifier_block __cpuinitdata migration_notifier = {
        .notifier_call = migration_call,
@@ -9528,7 +9540,7 @@ void __init sched_init(void)
        alloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT);
 #endif /* SMP */
-        perf_counter_init();
+        perf_event_init();
        scheduler_running = 1;
 }
@@ -10300,7 +10312,7 @@ static int sched_rt_global_constraints(void)
 #endif /* CONFIG_RT_GROUP_SCHED */
 int sched_rt_handler(struct ctl_table *table, int write,
-                struct file *filp, void __user *buffer, size_t *lenp,
+                void __user *buffer, size_t *lenp,
                loff_t *ppos)
 {
        int ret;
@@ -10311,7 +10323,7 @@ int sched_rt_handler(struct ctl_table *table, int write,
        old_period = sysctl_sched_rt_period;
        old_runtime = sysctl_sched_rt_runtime;
-        ret = proc_dointvec(table, write, filp, buffer, lenp, ppos);
+        ret = proc_dointvec(table, write, buffer, lenp, ppos);
        if (!ret && write) {
                ret = sched_rt_global_constraints();
@@ -10365,8 +10377,7 @@ cpu_cgroup_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp)
 }
 static int
-cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
+cpu_cgroup_can_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
-                      struct task_struct *tsk)
 {
 #ifdef CONFIG_RT_GROUP_SCHED
        if (!sched_rt_can_attach(cgroup_tg(cgrp), tsk))
@@ -10376,15 +10387,45 @@ cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
        if (tsk->sched_class != &fair_sched_class)
                return -EINVAL;
 #endif
+        return 0;
+}
+static int
+cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
+                      struct task_struct *tsk, bool threadgroup)
+{
+        int retval = cpu_cgroup_can_attach_task(cgrp, tsk);
+        if (retval)
+                return retval;
+        if (threadgroup) {
+                struct task_struct *c;
+                rcu_read_lock();
+                list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) {
+                        retval = cpu_cgroup_can_attach_task(cgrp, c);
+                        if (retval) {
+                                rcu_read_unlock();
+                                return retval;
+                        }
+                }
+                rcu_read_unlock();
+        }
        return 0;
 }
 static void
 cpu_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
-                        struct cgroup *old_cont, struct task_struct *tsk)
+                  struct cgroup *old_cont, struct task_struct *tsk,
+                  bool threadgroup)
 {
        sched_move_task(tsk);
+        if (threadgroup) {
+                struct task_struct *c;
+                rcu_read_lock();
+                list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) {
+                        sched_move_task(c);
+                }
+                rcu_read_unlock();
+        }
 }
 #ifdef CONFIG_FAIR_GROUP_SCHED
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index ecc637a0d591..4e777b47eeda 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -384,10 +384,10 @@ static struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq)
 #ifdef CONFIG_SCHED_DEBUG
 int sched_nr_latency_handler(struct ctl_table *table, int write,
-                struct file *filp, void __user *buffer, size_t *lenp,
+                void __user *buffer, size_t *lenp,
                loff_t *ppos)
 {
-        int ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos);
+        int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
        if (ret || !write)
                return ret;
diff --git a/kernel/signal.c b/kernel/signal.c
index 64c5deeaca5d..6705320784fd 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -705,7 +705,7 @@ static int prepare_signal(int sig, struct task_struct *p, int from_ancestor_ns)
                if (why) {
                        /*
-                         * The first thread which returns from finish_stop()
+                         * The first thread which returns from do_signal_stop()
                         * will take ->siglock, notice SIGNAL_CLD_MASK, and
                         * notify its parent. See get_signal_to_deliver().
                         */
@@ -971,6 +971,20 @@ specific_send_sig_info(int sig, struct siginfo *info, struct task_struct *t)
        return send_signal(sig, info, t, 0);
 }
+int do_send_sig_info(int sig, struct siginfo *info, struct task_struct *p,
+                        bool group)
+{
+        unsigned long flags;
+        int ret = -ESRCH;
+        if (lock_task_sighand(p, &flags)) {
+                ret = send_signal(sig, info, p, group);
+                unlock_task_sighand(p, &flags);
+        }
+        return ret;
+}
 /*
 * Force a signal that the process can't ignore: if necessary
 * we unblock the signal and change any SIG_IGN to SIG_DFL.
@@ -1036,12 +1050,6 @@ void zap_other_threads(struct task_struct *p)
        }
 }
-int __fatal_signal_pending(struct task_struct *tsk)
-{
-        return sigismember(&tsk->pending.signal, SIGKILL);
-}
-EXPORT_SYMBOL(__fatal_signal_pending);
 struct sighand_struct *lock_task_sighand(struct task_struct *tsk, unsigned long *flags)
 {
        struct sighand_struct *sighand;
@@ -1068,18 +1076,10 @@ struct sighand_struct *lock_task_sighand(struct task_struct *tsk, unsigned long
 */
 int group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p)
 {
-        unsigned long flags;
+        int ret = check_kill_permission(sig, info, p);
-        int ret;
-        ret = check_kill_permission(sig, info, p);
+        if (!ret && sig)
+                ret = do_send_sig_info(sig, info, p, true);
-        if (!ret && sig) {
-                ret = -ESRCH;
-                if (lock_task_sighand(p, &flags)) {
-                        ret = __group_send_sig_info(sig, info, p);
-                        unlock_task_sighand(p, &flags);
-                }
-        }
        return ret;
 }
@@ -1224,15 +1224,9 @@ static int kill_something_info(int sig, struct siginfo *info, pid_t pid)
 * These are for backward compatibility with the rest of the kernel source.
 */
-/*
- * The caller must ensure the task can't exit.
- */
 int
 send_sig_info(int sig, struct siginfo *info, struct task_struct *p)
 {
-        int ret;
-        unsigned long flags;
        /*
         * Make sure legacy kernel users don't send in bad values
         * (normal paths check this in check_kill_permission).
@@ -1240,10 +1234,7 @@ send_sig_info(int sig, struct siginfo *info, struct task_struct *p)
        if (!valid_signal(sig))
                return -EINVAL;
-        spin_lock_irqsave(&p->sighand->siglock, flags);
+        return do_send_sig_info(sig, info, p, false);
-        ret = specific_send_sig_info(sig, info, p);
-        spin_unlock_irqrestore(&p->sighand->siglock, flags);
-        return ret;
 }
 #define __si_special(priv) \
@@ -1383,15 +1374,6 @@ ret:
 }
 /*
- * Wake up any threads in the parent blocked in wait* syscalls.
- */
-static inline void __wake_up_parent(struct task_struct *p,
-                                    struct task_struct *parent)
-{
-        wake_up_interruptible_sync(&parent->signal->wait_chldexit);
-}
-/*
 * Let a parent know about the death of a child.
 * For a stopped/continued status change, use do_notify_parent_cldstop instead.
 *
@@ -1673,29 +1655,6 @@ void ptrace_notify(int exit_code)
        spin_unlock_irq(&current->sighand->siglock);
 }
-static void
-finish_stop(int stop_count)
-{
-        /*
-         * If there are no other threads in the group, or if there is
-         * a group stop in progress and we are the last to stop,
-         * report to the parent.  When ptraced, every thread reports itself.
-         */
-        if (tracehook_notify_jctl(stop_count == 0, CLD_STOPPED)) {
-                read_lock(&tasklist_lock);
-                do_notify_parent_cldstop(current, CLD_STOPPED);
-                read_unlock(&tasklist_lock);
-        }
-        do {
-                schedule();
-        } while (try_to_freeze());
-        /*
-         * Now we don't run again until continued.
-         */
-        current->exit_code = 0;
-}
 /*
 * This performs the stopping for SIGSTOP and other stop signals.
 * We have to stop all threads in the thread group.
@@ -1705,15 +1664,9 @@ finish_stop(int stop_count)
 static int do_signal_stop(int signr)
 {
        struct signal_struct *sig = current->signal;
-        int stop_count;
+        int notify;
-        if (sig->group_stop_count > 0) {
+        if (!sig->group_stop_count) {
-                /*
-                 * There is a group stop in progress.  We don't need to
-                 * start another one.
-                 */
-                stop_count = --sig->group_stop_count;
-        } else {
                struct task_struct *t;
                if (!likely(sig->flags & SIGNAL_STOP_DEQUEUED) ||
@@ -1725,7 +1678,7 @@ static int do_signal_stop(int signr)
                 */
                sig->group_exit_code = signr;
-                stop_count = 0;
+                sig->group_stop_count = 1;
                for (t = next_thread(current); t != current; t = next_thread(t))
                        /*
                         * Setting state to TASK_STOPPED for a group
@@ -1734,19 +1687,44 @@ static int do_signal_stop(int signr)
                         */
                        if (!(t->flags & PF_EXITING) &&
                            !task_is_stopped_or_traced(t)) {
-                                stop_count++;
+                                sig->group_stop_count++;
                                signal_wake_up(t, 0);
                        }
-                sig->group_stop_count = stop_count;
        }
+        /*
+         * If there are no other threads in the group, or if there is
+         * a group stop in progress and we are the last to stop, report
+         * to the parent.  When ptraced, every thread reports itself.
+         */
+        notify = sig->group_stop_count == 1 ? CLD_STOPPED : 0;
+        notify = tracehook_notify_jctl(notify, CLD_STOPPED);
+        /*
+         * tracehook_notify_jctl() can drop and reacquire siglock, so
+         * we keep ->group_stop_count != 0 before the call. If SIGCONT
+         * or SIGKILL comes in between ->group_stop_count == 0.
+         */
+        if (sig->group_stop_count) {
+                if (!--sig->group_stop_count)
+                        sig->flags = SIGNAL_STOP_STOPPED;
+                current->exit_code = sig->group_exit_code;
+                __set_current_state(TASK_STOPPED);
+        }
+        spin_unlock_irq(&current->sighand->siglock);
-        if (stop_count == 0)
+        if (notify) {
-                sig->flags = SIGNAL_STOP_STOPPED;
+                read_lock(&tasklist_lock);
-        current->exit_code = sig->group_exit_code;
+                do_notify_parent_cldstop(current, notify);
-        __set_current_state(TASK_STOPPED);
+                read_unlock(&tasklist_lock);
+        }
+        /* Now we don't run again until woken by SIGCONT or SIGKILL */
+        do {
+                schedule();
+        } while (try_to_freeze());
+        tracehook_finish_jctl();
+        current->exit_code = 0;
-        spin_unlock_irq(&current->sighand->siglock);
-        finish_stop(stop_count);
        return 1;
 }
@@ -1815,14 +1793,15 @@ relock:
                int why = (signal->flags & SIGNAL_STOP_CONTINUED)
                                ? CLD_CONTINUED : CLD_STOPPED;
                signal->flags &= ~SIGNAL_CLD_MASK;
-                spin_unlock_irq(&sighand->siglock);
-                if (unlikely(!tracehook_notify_jctl(1, why)))
+                why = tracehook_notify_jctl(why, CLD_CONTINUED);
-                        goto relock;
+                spin_unlock_irq(&sighand->siglock);
-                read_lock(&tasklist_lock);
+                if (why) {
-                do_notify_parent_cldstop(current->group_leader, why);
+                        read_lock(&tasklist_lock);
-                read_unlock(&tasklist_lock);
+                        do_notify_parent_cldstop(current->group_leader, why);
+                        read_unlock(&tasklist_lock);
+                }
                goto relock;
        }
@@ -1987,14 +1966,14 @@ void exit_signals(struct task_struct *tsk)
        if (unlikely(tsk->signal->group_stop_count) &&
                        !--tsk->signal->group_stop_count) {
                tsk->signal->flags = SIGNAL_STOP_STOPPED;
-                group_stop = 1;
+                group_stop = tracehook_notify_jctl(CLD_STOPPED, CLD_STOPPED);
        }
 out:
        spin_unlock_irq(&tsk->sighand->siglock);
-        if (unlikely(group_stop) && tracehook_notify_jctl(1, CLD_STOPPED)) {
+        if (unlikely(group_stop)) {
                read_lock(&tasklist_lock);
-                do_notify_parent_cldstop(tsk, CLD_STOPPED);
+                do_notify_parent_cldstop(tsk, group_stop);
                read_unlock(&tasklist_lock);
        }
 }
@@ -2290,7 +2269,6 @@ static int
 do_send_specific(pid_t tgid, pid_t pid, int sig, struct siginfo *info)
 {
        struct task_struct *p;
-        unsigned long flags;
        int error = -ESRCH;
        rcu_read_lock();
@@ -2300,14 +2278,16 @@ do_send_specific(pid_t tgid, pid_t pid, int sig, struct siginfo *info)
                /*
                 * The null signal is a permissions and process existence
                 * probe.  No signal is actually delivered.
-                 *
-                 * If lock_task_sighand() fails we pretend the task dies
-                 * after receiving the signal. The window is tiny, and the
-                 * signal is private anyway.
                 */
-                if (!error && sig && lock_task_sighand(p, &flags)) {
+                if (!error && sig) {
-                        error = specific_send_sig_info(sig, info, p);
+                        error = do_send_sig_info(sig, info, p, false);
-                        unlock_task_sighand(p, &flags);
+                        /*
+                         * If lock_task_sighand() failed we pretend the task
+                         * dies after receiving the signal. The window is tiny,
+                         * and the signal is private anyway.
+                         */
+                        if (unlikely(error == -ESRCH))
+                                error = 0;
                }
        }
        rcu_read_unlock();
diff --git a/kernel/slow-work.c b/kernel/slow-work.c
index 09d7519557d3..0d31135efbf4 100644
--- a/kernel/slow-work.c
+++ b/kernel/slow-work.c
@@ -26,10 +26,10 @@ static void slow_work_cull_timeout(unsigned long);
 static void slow_work_oom_timeout(unsigned long);
 #ifdef CONFIG_SYSCTL
-static int slow_work_min_threads_sysctl(struct ctl_table *, int, struct file *,
+static int slow_work_min_threads_sysctl(struct ctl_table *, int,
                                        void __user *, size_t *, loff_t *);
-static int slow_work_max_threads_sysctl(struct ctl_table *, int , struct file *,
+static int slow_work_max_threads_sysctl(struct ctl_table *, int ,
                                        void __user *, size_t *, loff_t *);
 #endif
@@ -493,10 +493,10 @@ static void slow_work_oom_timeout(unsigned long data)
 * Handle adjustment of the minimum number of threads
 */
 static int slow_work_min_threads_sysctl(struct ctl_table *table, int write,
-                                        struct file *filp, void __user *buffer,
+                                        void __user *buffer,
                                        size_t *lenp, loff_t *ppos)
 {
-        int ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos);
+        int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
        int n;
        if (ret == 0) {
@@ -521,10 +521,10 @@ static int slow_work_min_threads_sysctl(struct ctl_table *table, int write,
 * Handle adjustment of the maximum number of threads
 */
 static int slow_work_max_threads_sysctl(struct ctl_table *table, int write,
-                                        struct file *filp, void __user *buffer,
+                                        void __user *buffer,
                                        size_t *lenp, loff_t *ppos)
 {
-        int ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos);
+        int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
        int n;
        if (ret == 0) {
diff --git a/kernel/smp.c b/kernel/smp.c
index 8e218500ab14..c9d1c7835c2f 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -29,8 +29,7 @@ enum {
 struct call_function_data {
        struct call_single_data csd;
-        spinlock_t              lock;
+        atomic_t                refs;
-        unsigned int            refs;
        cpumask_var_t           cpumask;
 };
@@ -39,9 +38,7 @@ struct call_single_queue {
        spinlock_t              lock;
 };
-static DEFINE_PER_CPU(struct call_function_data, cfd_data) = {
+static DEFINE_PER_CPU(struct call_function_data, cfd_data);
-        .lock                   = __SPIN_LOCK_UNLOCKED(cfd_data.lock),
-};
 static int
 hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu)
@@ -196,25 +193,18 @@ void generic_smp_call_function_interrupt(void)
        list_for_each_entry_rcu(data, &call_function.queue, csd.list) {
                int refs;
-                spin_lock(&data->lock);
+                if (!cpumask_test_and_clear_cpu(cpu, data->cpumask))
-                if (!cpumask_test_cpu(cpu, data->cpumask)) {
-                        spin_unlock(&data->lock);
                        continue;
-                }
-                cpumask_clear_cpu(cpu, data->cpumask);
-                spin_unlock(&data->lock);
                data->csd.func(data->csd.info);
-                spin_lock(&data->lock);
+                refs = atomic_dec_return(&data->refs);
-                WARN_ON(data->refs == 0);
+                WARN_ON(refs < 0);
-                refs = --data->refs;
                if (!refs) {
                        spin_lock(&call_function.lock);
                        list_del_rcu(&data->csd.list);
                        spin_unlock(&call_function.lock);
                }
-                spin_unlock(&data->lock);
                if (refs)
                        continue;
@@ -357,13 +347,6 @@ void __smp_call_function_single(int cpu, struct call_single_data *data,
        generic_exec_single(cpu, data, wait);
 }
-/* Deprecated: shim for archs using old arch_send_call_function_ipi API. */
-#ifndef arch_send_call_function_ipi_mask
-# define arch_send_call_function_ipi_mask(maskp) \
-         arch_send_call_function_ipi(*(maskp))
-#endif
 /**
 * smp_call_function_many(): Run a function on a set of other CPUs.
 * @mask: The set of cpus to run on (only runs on online subset).
@@ -419,23 +402,20 @@ void smp_call_function_many(const struct cpumask *mask,
        data = &__get_cpu_var(cfd_data);
        csd_lock(&data->csd);
-        spin_lock_irqsave(&data->lock, flags);
        data->csd.func = func;
        data->csd.info = info;
        cpumask_and(data->cpumask, mask, cpu_online_mask);
        cpumask_clear_cpu(this_cpu, data->cpumask);
-        data->refs = cpumask_weight(data->cpumask);
+        atomic_set(&data->refs, cpumask_weight(data->cpumask));
-        spin_lock(&call_function.lock);
+        spin_lock_irqsave(&call_function.lock, flags);
        /*
         * Place entry at the _HEAD_ of the list, so that any cpu still
         * observing the entry in generic_smp_call_function_interrupt()
         * will not miss any other list entries:
         */
        list_add_rcu(&data->csd.list, &call_function.queue);
-        spin_unlock(&call_function.lock);
+        spin_unlock_irqrestore(&call_function.lock, flags);
-        spin_unlock_irqrestore(&data->lock, flags);
        /*
         * Make the list addition visible before sending the ipi.
diff --git a/kernel/softlockup.c b/kernel/softlockup.c
index 88796c330838..81324d12eb35 100644
--- a/kernel/softlockup.c
+++ b/kernel/softlockup.c
@@ -90,11 +90,11 @@ void touch_all_softlockup_watchdogs(void)
 EXPORT_SYMBOL(touch_all_softlockup_watchdogs);
 int proc_dosoftlockup_thresh(struct ctl_table *table, int write,
-                             struct file *filp, void __user *buffer,
+                             void __user *buffer,
                             size_t *lenp, loff_t *ppos)
 {
        touch_all_softlockup_watchdogs();
-        return proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos);
+        return proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 }
 /*
diff --git a/kernel/sys.c b/kernel/sys.c
index b3f1097c76fa..255475d163e0 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -14,7 +14,7 @@
 #include <linux/prctl.h>
 #include <linux/highuid.h>
 #include <linux/fs.h>
-#include <linux/perf_counter.h>
+#include <linux/perf_event.h>
 #include <linux/resource.h>
 #include <linux/kernel.h>
 #include <linux/kexec.h>
@@ -1338,6 +1338,7 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
        unsigned long flags;
        cputime_t utime, stime;
        struct task_cputime cputime;
+        unsigned long maxrss = 0;
        memset((char *) r, 0, sizeof *r);
        utime = stime = cputime_zero;
@@ -1346,6 +1347,7 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
                utime = task_utime(current);
                stime = task_stime(current);
                accumulate_thread_rusage(p, r);
+                maxrss = p->signal->maxrss;
                goto out;
        }
@@ -1363,6 +1365,7 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
                        r->ru_majflt = p->signal->cmaj_flt;
                        r->ru_inblock = p->signal->cinblock;
                        r->ru_oublock = p->signal->coublock;
+                        maxrss = p->signal->cmaxrss;
                        if (who == RUSAGE_CHILDREN)
                                break;
@@ -1377,6 +1380,8 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
                        r->ru_majflt += p->signal->maj_flt;
                        r->ru_inblock += p->signal->inblock;
                        r->ru_oublock += p->signal->oublock;
+                        if (maxrss < p->signal->maxrss)
+                                maxrss = p->signal->maxrss;
                        t = p;
                        do {
                                accumulate_thread_rusage(t, r);
@@ -1392,6 +1397,15 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
 out:
        cputime_to_timeval(utime, &r->ru_utime);
        cputime_to_timeval(stime, &r->ru_stime);
+        if (who != RUSAGE_CHILDREN) {
+                struct mm_struct *mm = get_task_mm(p);
+                if (mm) {
+                        setmax_mm_hiwater_rss(&maxrss, mm);
+                        mmput(mm);
+                }
+        }
+        r->ru_maxrss = maxrss * (PAGE_SIZE / 1024); /* convert pages to KBs */
 }
 int getrusage(struct task_struct *p, int who, struct rusage __user *ru)
@@ -1511,11 +1525,11 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
                case PR_SET_TSC:
                        error = SET_TSC_CTL(arg2);
                        break;
-                case PR_TASK_PERF_COUNTERS_DISABLE:
+                case PR_TASK_PERF_EVENTS_DISABLE:
-                        error = perf_counter_task_disable();
+                        error = perf_event_task_disable();
                        break;
-                case PR_TASK_PERF_COUNTERS_ENABLE:
+                case PR_TASK_PERF_EVENTS_ENABLE:
-                        error = perf_counter_task_enable();
+                        error = perf_event_task_enable();
                        break;
                case PR_GET_TIMERSLACK:
                        error = current->timer_slack_ns;
@@ -1528,6 +1542,28 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
                                current->timer_slack_ns = arg2;
                        error = 0;
                        break;
+                case PR_MCE_KILL:
+                        if (arg4 | arg5)
+                                return -EINVAL;
+                        switch (arg2) {
+                        case 0:
+                                if (arg3 != 0)
+                                        return -EINVAL;
+                                current->flags &= ~PF_MCE_PROCESS;
+                                break;
+                        case 1:
+                                current->flags |= PF_MCE_PROCESS;
+                                if (arg3 != 0)
+                                        current->flags |= PF_MCE_EARLY;
+                                else
+                                        current->flags &= ~PF_MCE_EARLY;
+                                break;
+                        default:
+                                return -EINVAL;
+                        }
+                        error = 0;
+                        break;
                default:
                        error = -EINVAL;
                        break;
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 68320f6b07b5..e06d0b8d1951 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -49,6 +49,7 @@ cond_syscall(sys_sendmsg);
 cond_syscall(compat_sys_sendmsg);
 cond_syscall(sys_recvmsg);
 cond_syscall(compat_sys_recvmsg);
+cond_syscall(compat_sys_recvfrom);
 cond_syscall(sys_socketcall);
 cond_syscall(sys_futex);
 cond_syscall(compat_sys_futex);
@@ -177,4 +178,4 @@ cond_syscall(sys_eventfd);
 cond_syscall(sys_eventfd2);
 /* performance counters: */
-cond_syscall(sys_perf_counter_open);
+cond_syscall(sys_perf_event_open);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 1a631ba684a4..0d949c517412 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -26,7 +26,6 @@
 #include <linux/proc_fs.h>
 #include <linux/security.h>
 #include <linux/ctype.h>
-#include <linux/utsname.h>
 #include <linux/kmemcheck.h>
 #include <linux/smp_lock.h>
 #include <linux/fs.h>
@@ -50,7 +49,7 @@
 #include <linux/reboot.h>
 #include <linux/ftrace.h>
 #include <linux/slow-work.h>
-#include <linux/perf_counter.h>
+#include <linux/perf_event.h>
 #include <asm/uaccess.h>
 #include <asm/processor.h>
@@ -77,6 +76,7 @@ extern int max_threads;
 extern int core_uses_pid;
 extern int suid_dumpable;
 extern char core_pattern[];
+extern unsigned int core_pipe_limit;
 extern int pid_max;
 extern int min_free_kbytes;
 extern int pid_max_min, pid_max_max;
@@ -106,6 +106,9 @@ static int __maybe_unused one = 1;
 static int __maybe_unused two = 2;
 static unsigned long one_ul = 1;
 static int one_hundred = 100;
+#ifdef CONFIG_PRINTK
+static int ten_thousand = 10000;
+#endif
 /* this is needed for the proc_doulongvec_minmax of vm_dirty_bytes */
 static unsigned long dirty_bytes_min = 2 * PAGE_SIZE;
@@ -160,9 +163,9 @@ extern int max_lock_depth;
 #endif
 #ifdef CONFIG_PROC_SYSCTL
-static int proc_do_cad_pid(struct ctl_table *table, int write, struct file *filp,
+static int proc_do_cad_pid(struct ctl_table *table, int write,
                  void __user *buffer, size_t *lenp, loff_t *ppos);
-static int proc_taint(struct ctl_table *table, int write, struct file *filp,
+static int proc_taint(struct ctl_table *table, int write,
                               void __user *buffer, size_t *lenp, loff_t *ppos);
 #endif
@@ -421,6 +424,14 @@ static struct ctl_table kern_table[] = {
                .proc_handler   = &proc_dostring,
                .strategy       = &sysctl_string,
        },
+        {
+                .ctl_name       = CTL_UNNUMBERED,
+                .procname       = "core_pipe_limit",
+                .data           = &core_pipe_limit,
+                .maxlen         = sizeof(unsigned int),
+                .mode           = 0644,
+                .proc_handler   = &proc_dointvec,
+        },
 #ifdef CONFIG_PROC_SYSCTL
        {
                .procname       = "tainted",
@@ -722,6 +733,17 @@ static struct ctl_table kern_table[] = {
                .mode           = 0644,
                .proc_handler   = &proc_dointvec,
        },
+        {
+                .ctl_name       = CTL_UNNUMBERED,
+                .procname       = "printk_delay",
+                .data           = &printk_delay_msec,
+                .maxlen         = sizeof(int),
+                .mode           = 0644,
+                .proc_handler   = &proc_dointvec_minmax,
+                .strategy       = &sysctl_intvec,
+                .extra1         = &zero,
+                .extra2         = &ten_thousand,
+        },
 #endif
        {
                .ctl_name       = KERN_NGROUPS_MAX,
@@ -964,28 +986,28 @@ static struct ctl_table kern_table[] = {
                .child          = slow_work_sysctls,
        },
 #endif
-#ifdef CONFIG_PERF_COUNTERS
+#ifdef CONFIG_PERF_EVENTS
        {
                .ctl_name       = CTL_UNNUMBERED,
-                .procname       = "perf_counter_paranoid",
+                .procname       = "perf_event_paranoid",
-                .data           = &sysctl_perf_counter_paranoid,
+                .data           = &sysctl_perf_event_paranoid,
-                .maxlen         = sizeof(sysctl_perf_counter_paranoid),
+                .maxlen         = sizeof(sysctl_perf_event_paranoid),
                .mode           = 0644,
                .proc_handler   = &proc_dointvec,
        },
        {
                .ctl_name       = CTL_UNNUMBERED,
-                .procname       = "perf_counter_mlock_kb",
+                .procname       = "perf_event_mlock_kb",
-                .data           = &sysctl_perf_counter_mlock,
+                .data           = &sysctl_perf_event_mlock,
-                .maxlen         = sizeof(sysctl_perf_counter_mlock),
+                .maxlen         = sizeof(sysctl_perf_event_mlock),
                .mode           = 0644,
                .proc_handler   = &proc_dointvec,
        },
        {
                .ctl_name       = CTL_UNNUMBERED,
-                .procname       = "perf_counter_max_sample_rate",
+                .procname       = "perf_event_max_sample_rate",
-                .data           = &sysctl_perf_counter_sample_rate,
+                .data           = &sysctl_perf_event_sample_rate,
-                .maxlen         = sizeof(sysctl_perf_counter_sample_rate),
+                .maxlen         = sizeof(sysctl_perf_event_sample_rate),
                .mode           = 0644,
                .proc_handler   = &proc_dointvec,
        },
@@ -1376,6 +1398,31 @@ static struct ctl_table vm_table[] = {
                .mode           = 0644,
                .proc_handler   = &scan_unevictable_handler,
        },
+#ifdef CONFIG_MEMORY_FAILURE
+        {
+                .ctl_name       = CTL_UNNUMBERED,
+                .procname       = "memory_failure_early_kill",
+                .data           = &sysctl_memory_failure_early_kill,
+                .maxlen         = sizeof(sysctl_memory_failure_early_kill),
+                .mode           = 0644,
+                .proc_handler   = &proc_dointvec_minmax,
+                .strategy       = &sysctl_intvec,
+                .extra1         = &zero,
+                .extra2         = &one,
+        },
+        {
+                .ctl_name       = CTL_UNNUMBERED,
+                .procname       = "memory_failure_recovery",
+                .data           = &sysctl_memory_failure_recovery,
+                .maxlen         = sizeof(sysctl_memory_failure_recovery),
+                .mode           = 0644,
+                .proc_handler   = &proc_dointvec_minmax,
+                .strategy       = &sysctl_intvec,
+                .extra1         = &zero,
+                .extra2         = &one,
+        },
+#endif
 /*
 * NOTE: do not add new entries to this table unless you have read
 * Documentation/sysctl/ctl_unnumbered.txt
@@ -2204,7 +2251,7 @@ void sysctl_head_put(struct ctl_table_header *head)
 #ifdef CONFIG_PROC_SYSCTL
 static int _proc_do_string(void* data, int maxlen, int write,
-                           struct file *filp, void __user *buffer,
+                           void __user *buffer,
                           size_t *lenp, loff_t *ppos)
 {
        size_t len;
@@ -2265,7 +2312,6 @@ static int _proc_do_string(void* data, int maxlen, int write,
 * proc_dostring - read a string sysctl
 * @table: the sysctl table
 * @write: %TRUE if this is a write to the sysctl file
- * @filp: the file structure
 * @buffer: the user buffer
 * @lenp: the size of the user buffer
 * @ppos: file position
@@ -2279,10 +2325,10 @@ static int _proc_do_string(void* data, int maxlen, int write,
 *
 * Returns 0 on success.
 */
-int proc_dostring(struct ctl_table *table, int write, struct file *filp,
+int proc_dostring(struct ctl_table *table, int write,
                  void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-        return _proc_do_string(table->data, table->maxlen, write, filp,
+        return _proc_do_string(table->data, table->maxlen, write,
                               buffer, lenp, ppos);
 }
@@ -2307,7 +2353,7 @@ static int do_proc_dointvec_conv(int *negp, unsigned long *lvalp,
 }
 static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table,
-                  int write, struct file *filp, void __user *buffer,
+                  int write, void __user *buffer,
                  size_t *lenp, loff_t *ppos,
                  int (*conv)(int *negp, unsigned long *lvalp, int *valp,
                              int write, void *data),
@@ -2414,13 +2460,13 @@ static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table,
 #undef TMPBUFLEN
 }
-static int do_proc_dointvec(struct ctl_table *table, int write, struct file *filp,
+static int do_proc_dointvec(struct ctl_table *table, int write,
                  void __user *buffer, size_t *lenp, loff_t *ppos,
                  int (*conv)(int *negp, unsigned long *lvalp, int *valp,
                              int write, void *data),
                  void *data)
 {
-        return __do_proc_dointvec(table->data, table, write, filp,
+        return __do_proc_dointvec(table->data, table, write,
                        buffer, lenp, ppos, conv, data);
 }
@@ -2428,7 +2474,6 @@ static int do_proc_dointvec(struct ctl_table *table, int write, struct file *fil
 * proc_dointvec - read a vector of integers
 * @table: the sysctl table
 * @write: %TRUE if this is a write to the sysctl file
- * @filp: the file structure
 * @buffer: the user buffer
 * @lenp: the size of the user buffer
 * @ppos: file position
@@ -2438,10 +2483,10 @@ static int do_proc_dointvec(struct ctl_table *table, int write, struct file *fil
 *
 * Returns 0 on success.
 */
-int proc_dointvec(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec(struct ctl_table *table, int write,
                     void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-    return do_proc_dointvec(table,write,filp,buffer,lenp,ppos,
+    return do_proc_dointvec(table,write,buffer,lenp,ppos,
                            NULL,NULL);
 }
@@ -2449,7 +2494,7 @@ int proc_dointvec(struct ctl_table *table, int write, struct file *filp,
 * Taint values can only be increased
 * This means we can safely use a temporary.
 */
-static int proc_taint(struct ctl_table *table, int write, struct file *filp,
+static int proc_taint(struct ctl_table *table, int write,
                               void __user *buffer, size_t *lenp, loff_t *ppos)
 {
        struct ctl_table t;
@@ -2461,7 +2506,7 @@ static int proc_taint(struct ctl_table *table, int write, struct file *filp,
        t = *table;
        t.data = &tmptaint;
-        err = proc_doulongvec_minmax(&t, write, filp, buffer, lenp, ppos);
+        err = proc_doulongvec_minmax(&t, write, buffer, lenp, ppos);
        if (err < 0)
                return err;
@@ -2513,7 +2558,6 @@ static int do_proc_dointvec_minmax_conv(int *negp, unsigned long *lvalp,
 * proc_dointvec_minmax - read a vector of integers with min/max values
 * @table: the sysctl table
 * @write: %TRUE if this is a write to the sysctl file
- * @filp: the file structure
 * @buffer: the user buffer
 * @lenp: the size of the user buffer
 * @ppos: file position
@@ -2526,19 +2570,18 @@ static int do_proc_dointvec_minmax_conv(int *negp, unsigned long *lvalp,
 *
 * Returns 0 on success.
 */
-int proc_dointvec_minmax(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec_minmax(struct ctl_table *table, int write,
                  void __user *buffer, size_t *lenp, loff_t *ppos)
 {
        struct do_proc_dointvec_minmax_conv_param param = {
                .min = (int *) table->extra1,
                .max = (int *) table->extra2,
        };
-        return do_proc_dointvec(table, write, filp, buffer, lenp, ppos,
+        return do_proc_dointvec(table, write, buffer, lenp, ppos,
                                do_proc_dointvec_minmax_conv, &param);
 }
 static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int write,
-                                     struct file *filp,
                                     void __user *buffer,
                                     size_t *lenp, loff_t *ppos,
                                     unsigned long convmul,
@@ -2643,21 +2686,19 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int
 }
 static int do_proc_doulongvec_minmax(struct ctl_table *table, int write,
-                                     struct file *filp,
                                     void __user *buffer,
                                     size_t *lenp, loff_t *ppos,
                                     unsigned long convmul,
                                     unsigned long convdiv)
 {
        return __do_proc_doulongvec_minmax(table->data, table, write,
-                        filp, buffer, lenp, ppos, convmul, convdiv);
+                        buffer, lenp, ppos, convmul, convdiv);
 }
 /**
 * proc_doulongvec_minmax - read a vector of long integers with min/max values
 * @table: the sysctl table
 * @write: %TRUE if this is a write to the sysctl file
- * @filp: the file structure
 * @buffer: the user buffer
 * @lenp: the size of the user buffer
 * @ppos: file position
@@ -2670,17 +2711,16 @@ static int do_proc_doulongvec_minmax(struct ctl_table *table, int write,
 *
 * Returns 0 on success.
 */
-int proc_doulongvec_minmax(struct ctl_table *table, int write, struct file *filp,
+int proc_doulongvec_minmax(struct ctl_table *table, int write,
                           void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-    return do_proc_doulongvec_minmax(table, write, filp, buffer, lenp, ppos, 1l, 1l);
+    return do_proc_doulongvec_minmax(table, write, buffer, lenp, ppos, 1l, 1l);
 }
 /**
 * proc_doulongvec_ms_jiffies_minmax - read a vector of millisecond values with min/max values
 * @table: the sysctl table
 * @write: %TRUE if this is a write to the sysctl file
- * @filp: the file structure
 * @buffer: the user buffer
 * @lenp: the size of the user buffer
 * @ppos: file position
@@ -2695,11 +2735,10 @@ int proc_doulongvec_minmax(struct ctl_table *table, int write, struct file *filp
 * Returns 0 on success.
 */
 int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write,
-                                      struct file *filp,
                                      void __user *buffer,
                                      size_t *lenp, loff_t *ppos)
 {
-    return do_proc_doulongvec_minmax(table, write, filp, buffer,
+    return do_proc_doulongvec_minmax(table, write, buffer,
                                     lenp, ppos, HZ, 1000l);
 }
@@ -2775,7 +2814,6 @@ static int do_proc_dointvec_ms_jiffies_conv(int *negp, unsigned long *lvalp,
 * proc_dointvec_jiffies - read a vector of integers as seconds
 * @table: the sysctl table
 * @write: %TRUE if this is a write to the sysctl file
- * @filp: the file structure
 * @buffer: the user buffer
 * @lenp: the size of the user buffer
 * @ppos: file position
@@ -2787,10 +2825,10 @@ static int do_proc_dointvec_ms_jiffies_conv(int *negp, unsigned long *lvalp,
 *
 * Returns 0 on success.
 */
-int proc_dointvec_jiffies(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec_jiffies(struct ctl_table *table, int write,
                          void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-    return do_proc_dointvec(table,write,filp,buffer,lenp,ppos,
+    return do_proc_dointvec(table,write,buffer,lenp,ppos,
                            do_proc_dointvec_jiffies_conv,NULL);
 }
@@ -2798,7 +2836,6 @@ int proc_dointvec_jiffies(struct ctl_table *table, int write, struct file *filp,
 * proc_dointvec_userhz_jiffies - read a vector of integers as 1/USER_HZ seconds
 * @table: the sysctl table
 * @write: %TRUE if this is a write to the sysctl file
- * @filp: the file structure
 * @buffer: the user buffer
 * @lenp: the size of the user buffer
 * @ppos: pointer to the file position
@@ -2810,10 +2847,10 @@ int proc_dointvec_jiffies(struct ctl_table *table, int write, struct file *filp,
 *
 * Returns 0 on success.
 */
-int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write,
                                 void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-    return do_proc_dointvec(table,write,filp,buffer,lenp,ppos,
+    return do_proc_dointvec(table,write,buffer,lenp,ppos,
                            do_proc_dointvec_userhz_jiffies_conv,NULL);
 }
@@ -2821,7 +2858,6 @@ int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write, struct file
 * proc_dointvec_ms_jiffies - read a vector of integers as 1 milliseconds
 * @table: the sysctl table
 * @write: %TRUE if this is a write to the sysctl file
- * @filp: the file structure
 * @buffer: the user buffer
 * @lenp: the size of the user buffer
 * @ppos: file position
@@ -2834,14 +2870,14 @@ int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write, struct file
 *
 * Returns 0 on success.
 */
-int proc_dointvec_ms_jiffies(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec_ms_jiffies(struct ctl_table *table, int write,
                             void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-        return do_proc_dointvec(table, write, filp, buffer, lenp, ppos,
+        return do_proc_dointvec(table, write, buffer, lenp, ppos,
                                do_proc_dointvec_ms_jiffies_conv, NULL);
 }
-static int proc_do_cad_pid(struct ctl_table *table, int write, struct file *filp,
+static int proc_do_cad_pid(struct ctl_table *table, int write,
                           void __user *buffer, size_t *lenp, loff_t *ppos)
 {
        struct pid *new_pid;
@@ -2850,7 +2886,7 @@ static int proc_do_cad_pid(struct ctl_table *table, int write, struct file *filp
        tmp = pid_vnr(cad_pid);
-        r = __do_proc_dointvec(&tmp, table, write, filp, buffer,
+        r = __do_proc_dointvec(&tmp, table, write, buffer,
                               lenp, ppos, NULL, NULL);
        if (r || !write)
                return r;
@@ -2865,50 +2901,49 @@ static int proc_do_cad_pid(struct ctl_table *table, int write, struct file *filp
 #else /* CONFIG_PROC_FS */
-int proc_dostring(struct ctl_table *table, int write, struct file *filp,
+int proc_dostring(struct ctl_table *table, int write,
                  void __user *buffer, size_t *lenp, loff_t *ppos)
 {
        return -ENOSYS;
 }
-int proc_dointvec(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec(struct ctl_table *table, int write,
                  void __user *buffer, size_t *lenp, loff_t *ppos)
 {
        return -ENOSYS;
 }
-int proc_dointvec_minmax(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec_minmax(struct ctl_table *table, int write,
                    void __user *buffer, size_t *lenp, loff_t *ppos)
 {
        return -ENOSYS;
 }
-int proc_dointvec_jiffies(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec_jiffies(struct ctl_table *table, int write,
                    void __user *buffer, size_t *lenp, loff_t *ppos)
 {
        return -ENOSYS;
 }
-int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write,
                    void __user *buffer, size_t *lenp, loff_t *ppos)
 {
        return -ENOSYS;
 }
-int proc_dointvec_ms_jiffies(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec_ms_jiffies(struct ctl_table *table, int write,
                             void __user *buffer, size_t *lenp, loff_t *ppos)
 {
        return -ENOSYS;
 }
-int proc_doulongvec_minmax(struct ctl_table *table, int write, struct file *filp,
+int proc_doulongvec_minmax(struct ctl_table *table, int write,
                    void __user *buffer, size_t *lenp, loff_t *ppos)
 {
        return -ENOSYS;
 }
 int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write,
-                                      struct file *filp,
                                      void __user *buffer,
                                      size_t *lenp, loff_t *ppos)
 {
diff --git a/kernel/time/Makefile b/kernel/time/Makefile
index 0b0a6366c9d4..ee266620b06c 100644
--- a/kernel/time/Makefile
+++ b/kernel/time/Makefile
@@ -1,4 +1,4 @@
-obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o timecompare.o
+obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o timecompare.o timeconv.o
 obj-$(CONFIG_GENERIC_CLOCKEVENTS_BUILD)         += clockevents.o
 obj-$(CONFIG_GENERIC_CLOCKEVENTS)               += tick-common.o
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 09113347d328..5e18c6ab2c6a 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -394,15 +394,11 @@ void clocksource_resume(void)
 {
        struct clocksource *cs;
-        mutex_lock(&clocksource_mutex);
        list_for_each_entry(cs, &clocksource_list, list)
                if (cs->resume)
                        cs->resume();
        clocksource_resume_watchdog();
-        mutex_unlock(&clocksource_mutex);
 }
 /**
diff --git a/kernel/time/timeconv.c b/kernel/time/timeconv.c
new file mode 100644
index 000000000000..86628e755f38
--- /dev/null
+++ b/kernel/time/timeconv.c
@@ -0,0 +1,127 @@
+/*
+ * Copyright (C) 1993, 1994, 1995, 1996, 1997 Free Software Foundation, Inc.
+ * This file is part of the GNU C Library.
+ * Contributed by Paul Eggert (eggert@twinsun.com).
+ *
+ * The GNU C Library is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Library General Public License as
+ * published by the Free Software Foundation; either version 2 of the
+ * License, or (at your option) any later version.
+ *
+ * The GNU C Library is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * Library General Public License for more details.
+ *
+ * You should have received a copy of the GNU Library General Public
+ * License along with the GNU C Library; see the file COPYING.LIB.  If not,
+ * write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ * Boston, MA 02111-1307, USA.
+ */
+/*
+ * Converts the calendar time to broken-down time representation
+ * Based on code from glibc-2.6
+ *
+ * 2009-7-14:
+ *   Moved from glibc-2.6 to kernel by Zhaolei<zhaolei@cn.fujitsu.com>
+ */
+#include <linux/time.h>
+#include <linux/module.h>
+/*
+ * Nonzero if YEAR is a leap year (every 4 years,
+ * except every 100th isn't, and every 400th is).
+ */
+static int __isleap(long year)
+{
+        return (year) % 4 == 0 && ((year) % 100 != 0 || (year) % 400 == 0);
+}
+/* do a mathdiv for long type */
+static long math_div(long a, long b)
+{
+        return a / b - (a % b < 0);
+}
+/* How many leap years between y1 and y2, y1 must less or equal to y2 */
+static long leaps_between(long y1, long y2)
+{
+        long leaps1 = math_div(y1 - 1, 4) - math_div(y1 - 1, 100)
+                + math_div(y1 - 1, 400);
+        long leaps2 = math_div(y2 - 1, 4) - math_div(y2 - 1, 100)
+                + math_div(y2 - 1, 400);
+        return leaps2 - leaps1;
+}
+/* How many days come before each month (0-12). */
+static const unsigned short __mon_yday[2][13] = {
+        /* Normal years. */
+        {0, 31, 59, 90, 120, 151, 181, 212, 243, 273, 304, 334, 365},
+        /* Leap years. */
+        {0, 31, 60, 91, 121, 152, 182, 213, 244, 274, 305, 335, 366}
+};
+#define SECS_PER_HOUR   (60 * 60)
+#define SECS_PER_DAY    (SECS_PER_HOUR * 24)
+/**
+ * time_to_tm - converts the calendar time to local broken-down time
+ *
+ * @totalsecs   the number of seconds elapsed since 00:00:00 on January 1, 1970,
+ *              Coordinated Universal Time (UTC).
+ * @offset      offset seconds adding to totalsecs.
+ * @result      pointer to struct tm variable to receive broken-down time
+ */
+void time_to_tm(time_t totalsecs, int offset, struct tm *result)
+{
+        long days, rem, y;
+        const unsigned short *ip;
+        days = totalsecs / SECS_PER_DAY;
+        rem = totalsecs % SECS_PER_DAY;
+        rem += offset;
+        while (rem < 0) {
+                rem += SECS_PER_DAY;
+                --days;
+        }
+        while (rem >= SECS_PER_DAY) {
+                rem -= SECS_PER_DAY;
+                ++days;
+        }
+        result->tm_hour = rem / SECS_PER_HOUR;
+        rem %= SECS_PER_HOUR;
+        result->tm_min = rem / 60;
+        result->tm_sec = rem % 60;
+        /* January 1, 1970 was a Thursday. */
+        result->tm_wday = (4 + days) % 7;
+        if (result->tm_wday < 0)
+                result->tm_wday += 7;
+        y = 1970;
+        while (days < 0 || days >= (__isleap(y) ? 366 : 365)) {
+                /* Guess a corrected year, assuming 365 days per year. */
+                long yg = y + math_div(days, 365);
+                /* Adjust DAYS and Y to match the guessed year. */
+                days -= (yg - y) * 365 + leaps_between(y, yg);
+                y = yg;
+        }
+        result->tm_year = y - 1900;
+        result->tm_yday = days;
+        ip = __mon_yday[__isleap(y)];
+        for (y = 11; days < ip[y]; y--)
+                continue;
+        days -= ip[y];
+        result->tm_mon = y;
+        result->tm_mday = days + 1;
+}
+EXPORT_SYMBOL(time_to_tm);
diff --git a/kernel/timer.c b/kernel/timer.c
index bbb51074680e..5db5a8d26811 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -37,7 +37,7 @@
 #include <linux/delay.h>
 #include <linux/tick.h>
 #include <linux/kallsyms.h>
-#include <linux/perf_counter.h>
+#include <linux/perf_event.h>
 #include <linux/sched.h>
 #include <asm/uaccess.h>
@@ -46,6 +46,9 @@
 #include <asm/timex.h>
 #include <asm/io.h>
+#define CREATE_TRACE_POINTS
+#include <trace/events/timer.h>
 u64 jiffies_64 __cacheline_aligned_in_smp = INITIAL_JIFFIES;
 EXPORT_SYMBOL(jiffies_64);
@@ -521,6 +524,25 @@ static inline void debug_timer_activate(struct timer_list *timer) { }
 static inline void debug_timer_deactivate(struct timer_list *timer) { }
 #endif
+static inline void debug_init(struct timer_list *timer)
+{
+        debug_timer_init(timer);
+        trace_timer_init(timer);
+}
+static inline void
+debug_activate(struct timer_list *timer, unsigned long expires)
+{
+        debug_timer_activate(timer);
+        trace_timer_start(timer, expires);
+}
+static inline void debug_deactivate(struct timer_list *timer)
+{
+        debug_timer_deactivate(timer);
+        trace_timer_cancel(timer);
+}
 static void __init_timer(struct timer_list *timer,
                         const char *name,
                         struct lock_class_key *key)
@@ -549,7 +571,7 @@ void init_timer_key(struct timer_list *timer,
                    const char *name,
                    struct lock_class_key *key)
 {
-        debug_timer_init(timer);
+        debug_init(timer);
        __init_timer(timer, name, key);
 }
 EXPORT_SYMBOL(init_timer_key);
@@ -568,7 +590,7 @@ static inline void detach_timer(struct timer_list *timer,
 {
        struct list_head *entry = &timer->entry;
-        debug_timer_deactivate(timer);
+        debug_deactivate(timer);
        __list_del(entry->prev, entry->next);
        if (clear_pending)
@@ -632,7 +654,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires,
                        goto out_unlock;
        }
-        debug_timer_activate(timer);
+        debug_activate(timer, expires);
        new_base = __get_cpu_var(tvec_bases);
@@ -787,7 +809,7 @@ void add_timer_on(struct timer_list *timer, int cpu)
        BUG_ON(timer_pending(timer) || !timer->function);
        spin_lock_irqsave(&base->lock, flags);
        timer_set_base(timer, base);
-        debug_timer_activate(timer);
+        debug_activate(timer, timer->expires);
        if (time_before(timer->expires, base->next_timer) &&
            !tbase_get_deferrable(timer->base))
                base->next_timer = timer->expires;
@@ -1000,7 +1022,9 @@ static inline void __run_timers(struct tvec_base *base)
                                 */
                                lock_map_acquire(&lockdep_map);
+                                trace_timer_expire_entry(timer);
                                fn(data);
+                                trace_timer_expire_exit(timer);
                                lock_map_release(&lockdep_map);
@@ -1187,7 +1211,7 @@ static void run_timer_softirq(struct softirq_action *h)
 {
        struct tvec_base *base = __get_cpu_var(tvec_bases);
-        perf_counter_do_pending();
+        perf_event_do_pending();
        hrtimer_run_pending();
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index e71634604400..b416512ad17f 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -83,7 +83,7 @@ config RING_BUFFER_ALLOW_SWAP
 # This allows those options to appear when no other tracer is selected. But the
 # options do not appear when something else selects it. We need the two options
 # GENERIC_TRACER and TRACING to avoid circular dependencies to accomplish the
-# hidding of the automatic options options.
+# hidding of the automatic options.
 config TRACING
        bool
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index c71e91bf7372..46592feab5a6 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1520,7 +1520,7 @@ static int t_show(struct seq_file *m, void *v)
        return 0;
 }
-static struct seq_operations show_ftrace_seq_ops = {
+static const struct seq_operations show_ftrace_seq_ops = {
        .start = t_start,
        .next = t_next,
        .stop = t_stop,
@@ -1621,8 +1621,10 @@ ftrace_regex_open(struct inode *inode, struct file *file, int enable)
                if (!ret) {
                        struct seq_file *m = file->private_data;
                        m->private = iter;
-                } else
+                } else {
+                        trace_parser_put(&iter->parser);
                        kfree(iter);
+                }
        } else
                file->private_data = iter;
        mutex_unlock(&ftrace_regex_lock);
@@ -2202,7 +2204,7 @@ ftrace_regex_write(struct file *file, const char __user *ubuf,
        struct trace_parser *parser;
        ssize_t ret, read;
-        if (!cnt || cnt < 0)
+        if (!cnt)
                return 0;
        mutex_lock(&ftrace_regex_lock);
@@ -2216,7 +2218,7 @@ ftrace_regex_write(struct file *file, const char __user *ubuf,
        parser = &iter->parser;
        read = trace_get_user(parser, ubuf, cnt, ppos);
-        if (trace_parser_loaded(parser) &&
+        if (read >= 0 && trace_parser_loaded(parser) &&
            !trace_parser_cont(parser)) {
                ret = ftrace_process_regex(parser->buffer,
                                           parser->idx, enable);
@@ -2459,7 +2461,7 @@ static int g_show(struct seq_file *m, void *v)
        return 0;
 }
-static struct seq_operations ftrace_graph_seq_ops = {
+static const struct seq_operations ftrace_graph_seq_ops = {
        .start = g_start,
        .next = g_next,
        .stop = g_stop,
@@ -2552,8 +2554,7 @@ ftrace_graph_write(struct file *file, const char __user *ubuf,
                   size_t cnt, loff_t *ppos)
 {
        struct trace_parser parser;
-        size_t read = 0;
+        ssize_t read, ret;
-        ssize_t ret;
        if (!cnt || cnt < 0)
                return 0;
@@ -2562,29 +2563,31 @@ ftrace_graph_write(struct file *file, const char __user *ubuf,
        if (ftrace_graph_count >= FTRACE_GRAPH_MAX_FUNCS) {
                ret = -EBUSY;
-                goto out;
+                goto out_unlock;
        }
        if (trace_parser_get_init(&parser, FTRACE_BUFF_MAX)) {
                ret = -ENOMEM;
-                goto out;
+                goto out_unlock;
        }
        read = trace_get_user(&parser, ubuf, cnt, ppos);
-        if (trace_parser_loaded((&parser))) {
+        if (read >= 0 && trace_parser_loaded((&parser))) {
                parser.buffer[parser.idx] = 0;
                /* we allow only one expression at a time */
                ret = ftrace_set_func(ftrace_graph_funcs, &ftrace_graph_count,
                                        parser.buffer);
                if (ret)
-                        goto out;
+                        goto out_free;
        }
        ret = read;
- out:
+out_free:
        trace_parser_put(&parser);
+out_unlock:
        mutex_unlock(&graph_lock);
        return ret;
@@ -3015,7 +3018,7 @@ int unregister_ftrace_function(struct ftrace_ops *ops)
 int
 ftrace_enable_sysctl(struct ctl_table *table, int write,
-                     struct file *file, void __user *buffer, size_t *lenp,
+                     void __user *buffer, size_t *lenp,
                     loff_t *ppos)
 {
        int ret;
@@ -3025,7 +3028,7 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
        mutex_lock(&ftrace_lock);
-        ret  = proc_dointvec(table, write, file, buffer, lenp, ppos);
+        ret  = proc_dointvec(table, write, buffer, lenp, ppos);
        if (ret || !write || (last_ftrace_enabled == !!ftrace_enabled))
                goto out;
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index a35925d222ba..45068269ebb1 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -415,7 +415,7 @@ int trace_get_user(struct trace_parser *parser, const char __user *ubuf,
        /* read the non-space input */
        while (cnt && !isspace(ch)) {
-                if (parser->idx < parser->size)
+                if (parser->idx < parser->size - 1)
                        parser->buffer[parser->idx++] = ch;
                else {
                        ret = -EINVAL;
@@ -1949,7 +1949,7 @@ static int s_show(struct seq_file *m, void *v)
        return 0;
 }
-static struct seq_operations tracer_seq_ops = {
+static const struct seq_operations tracer_seq_ops = {
        .start          = s_start,
        .next           = s_next,
        .stop           = s_stop,
@@ -1984,11 +1984,9 @@ __tracing_open(struct inode *inode, struct file *file)
        if (current_trace)
                *iter->trace = *current_trace;
-        if (!alloc_cpumask_var(&iter->started, GFP_KERNEL))
+        if (!zalloc_cpumask_var(&iter->started, GFP_KERNEL))
                goto fail;
-        cpumask_clear(iter->started);
        if (current_trace && current_trace->print_max)
                iter->tr = &max_tr;
        else
@@ -2163,7 +2161,7 @@ static int t_show(struct seq_file *m, void *v)
        return 0;
 }
-static struct seq_operations show_traces_seq_ops = {
+static const struct seq_operations show_traces_seq_ops = {
        .start          = t_start,
        .next           = t_next,
        .stop           = t_stop,
@@ -4389,7 +4387,7 @@ __init static int tracer_alloc_buffers(void)
        if (!alloc_cpumask_var(&tracing_cpumask, GFP_KERNEL))
                goto out_free_buffer_mask;
-        if (!alloc_cpumask_var(&tracing_reader_cpumask, GFP_KERNEL))
+        if (!zalloc_cpumask_var(&tracing_reader_cpumask, GFP_KERNEL))
                goto out_free_tracing_cpumask;
        /* To save memory, keep the ring buffer size to its minimum */
@@ -4400,7 +4398,6 @@ __init static int tracer_alloc_buffers(void)
        cpumask_copy(tracing_buffer_mask, cpu_possible_mask);
        cpumask_copy(tracing_cpumask, cpu_all_mask);
-        cpumask_clear(tracing_reader_cpumask);
        /* TODO: make the number of buffers hot pluggable with CPUS */
        global_trace.buffer = ring_buffer_alloc(ring_buf_size,
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 6f03c8a1105e..d128f65778e6 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -232,10 +232,9 @@ ftrace_event_write(struct file *file, const char __user *ubuf,
                   size_t cnt, loff_t *ppos)
 {
        struct trace_parser parser;
-        size_t read = 0;
+        ssize_t read, ret;
-        ssize_t ret;
-        if (!cnt || cnt < 0)
+        if (!cnt)
                return 0;
        ret = tracing_update_buffers();
@@ -247,7 +246,7 @@ ftrace_event_write(struct file *file, const char __user *ubuf,
        read = trace_get_user(&parser, ubuf, cnt, ppos);
-        if (trace_parser_loaded((&parser))) {
+        if (read >= 0 && trace_parser_loaded((&parser))) {
                int set = 1;
                if (*parser.buffer == '!')
diff --git a/kernel/trace/trace_hw_branches.c b/kernel/trace/trace_hw_branches.c
index ca7d7c4d0c2a..23b63859130e 100644
--- a/kernel/trace/trace_hw_branches.c
+++ b/kernel/trace/trace_hw_branches.c
@@ -155,7 +155,7 @@ static enum print_line_t bts_trace_print_line(struct trace_iterator *iter)
                    seq_print_ip_sym(seq, it->from, symflags) &&
                    trace_seq_printf(seq, "\n"))
                        return TRACE_TYPE_HANDLED;
-                return TRACE_TYPE_PARTIAL_LINE;;
+                return TRACE_TYPE_PARTIAL_LINE;
        }
        return TRACE_TYPE_UNHANDLED;
 }
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 0f6facb050a1..8504ac71e4e8 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -296,14 +296,14 @@ static const struct file_operations stack_trace_fops = {
 int
 stack_trace_sysctl(struct ctl_table *table, int write,
-                   struct file *file, void __user *buffer, size_t *lenp,
+                   void __user *buffer, size_t *lenp,
                   loff_t *ppos)
 {
        int ret;
        mutex_lock(&stack_sysctl_mutex);
-        ret = proc_dointvec(table, write, file, buffer, lenp, ppos);
+        ret = proc_dointvec(table, write, buffer, lenp, ppos);
        if (ret || !write ||
            (last_stack_tracer_enabled == !!stack_tracer_enabled))
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 7a3550cf2597..9fbce6c9d2e1 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -2,7 +2,7 @@
 #include <trace/events/syscalls.h>
 #include <linux/kernel.h>
 #include <linux/ftrace.h>
-#include <linux/perf_counter.h>
+#include <linux/perf_event.h>
 #include <asm/syscall.h>
 #include "trace_output.h"
@@ -433,7 +433,7 @@ static void prof_syscall_enter(struct pt_regs *regs, long id)
        rec->nr = syscall_nr;
        syscall_get_arguments(current, regs, 0, sys_data->nb_args,
                               (unsigned long *)&rec->args);
-        perf_tpcounter_event(sys_data->enter_id, 0, 1, rec, size);
+        perf_tp_event(sys_data->enter_id, 0, 1, rec, size);
 end:
        local_irq_restore(flags);
@@ -532,7 +532,7 @@ static void prof_syscall_exit(struct pt_regs *regs, long ret)
        rec->nr = syscall_nr;
        rec->ret = syscall_get_return_value(current, regs);
-        perf_tpcounter_event(sys_data->exit_id, 0, 1, rec, size);
+        perf_tp_event(sys_data->exit_id, 0, 1, rec, size);
 end:
        local_irq_restore(flags);
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index 9489a0a9b1be..cc89be5bc0f8 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -48,7 +48,7 @@ static struct hlist_head tracepoint_table[TRACEPOINT_TABLE_SIZE];
 /*
 * Note about RCU :
- * It is used to to delay the free of multiple probes array until a quiescent
+ * It is used to delay the free of multiple probes array until a quiescent
 * state is reached.
 * Tracepoint entries modifications are protected by the tracepoints_mutex.
 */
diff --git a/kernel/uid16.c b/kernel/uid16.c
index 0314501688b9..419209893d87 100644
--- a/kernel/uid16.c
+++ b/kernel/uid16.c
@@ -4,7 +4,6 @@
 */
 #include <linux/mm.h>
-#include <linux/utsname.h>
 #include <linux/mman.h>
 #include <linux/notifier.h>
 #include <linux/reboot.h>
diff --git a/kernel/utsname_sysctl.c b/kernel/utsname_sysctl.c
index 92359cc747a7..69eae358a726 100644
--- a/kernel/utsname_sysctl.c
+++ b/kernel/utsname_sysctl.c
@@ -42,14 +42,14 @@ static void put_uts(ctl_table *table, int write, void *which)
 *      Special case of dostring for the UTS structure. This has locks
 *      to observe. Should this be in kernel/sys.c ????
 */
-static int proc_do_uts_string(ctl_table *table, int write, struct file *filp,
+static int proc_do_uts_string(ctl_table *table, int write,
                  void __user *buffer, size_t *lenp, loff_t *ppos)
 {
        struct ctl_table uts_table;
        int r;
        memcpy(&uts_table, table, sizeof(uts_table));
        uts_table.data = get_uts(table, write);
-        r = proc_dostring(&uts_table,write,filp,buffer,lenp, ppos);
+        r = proc_dostring(&uts_table,write,buffer,lenp, ppos);
        put_uts(table, write, uts_table.data);
        return r;
 }