Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux-2.6-cpumask into merge-rr-cpumask

Conflicts:
	arch/x86/kernel/io_apic.c
	kernel/rcuclassic.c
	kernel/sched.c
	kernel/time/tick-sched.c

Signed-off-by: Mike Travis <travis@sgi.com>
[ mingo@elte.hu: backmerged typo fix for io_apic.c ]
Signed-off-by: Ingo Molnar <mingo@elte.hu>

81 files changed, 4636 insertions, 2040 deletions

diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt
index 9fdba03dc1fc..bf987b95b356 100644
--- a/kernel/Kconfig.preempt
+++ b/kernel/Kconfig.preempt
@@ -52,28 +52,3 @@ config PREEMPT
 
 endchoice
 
-config PREEMPT_RCU
-        bool "Preemptible RCU"
-        depends on PREEMPT
-        default n
-        help
-          This option reduces the latency of the kernel by making certain
-          RCU sections preemptible. Normally RCU code is non-preemptible, if
-          this option is selected then read-only RCU sections become
-          preemptible. This helps latency, but may expose bugs due to
-          now-naive assumptions about each RCU read-side critical section
-          remaining on a given CPU through its execution.
-
-          Say N if you are unsure.
-
-config RCU_TRACE
-        bool "Enable tracing for RCU - currently stats in debugfs"
-        depends on PREEMPT_RCU
-        select DEBUG_FS
-        default y
-        help
-          This option provides tracing in RCU which presents stats
-          in debugfs for debugging RCU implementation.
-
-          Say Y here if you want to enable RCU tracing
-          Say N if you are unsure.
diff --git a/kernel/Makefile b/kernel/Makefile
index 6a212b842d86..e1c5bf3365c0 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -9,7 +9,7 @@ obj-y     = sched.o fork.o exec_domain.o panic.o printk.o \
             rcupdate.o extable.o params.o posix-timers.o \
             kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \
             hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \
-            notifier.o ksysfs.o pm_qos_params.o sched_clock.o
+            notifier.o ksysfs.o pm_qos_params.o sched_clock.o cred.o
 
 ifdef CONFIG_FUNCTION_TRACER
 # Do not trace debug files and internal ftrace files
@@ -73,10 +73,10 @@ obj-$(CONFIG_GENERIC_HARDIRQS) += irq/
 obj-$(CONFIG_SECCOMP) += seccomp.o
 obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
 obj-$(CONFIG_CLASSIC_RCU) += rcuclassic.o
+obj-$(CONFIG_TREE_RCU) += rcutree.o
 obj-$(CONFIG_PREEMPT_RCU) += rcupreempt.o
-ifeq ($(CONFIG_PREEMPT_RCU),y)
-obj-$(CONFIG_RCU_TRACE) += rcupreempt_trace.o
-endif
+obj-$(CONFIG_TREE_RCU_TRACE) += rcutree_trace.o
+obj-$(CONFIG_PREEMPT_RCU_TRACE) += rcupreempt_trace.o
 obj-$(CONFIG_RELAY) += relay.o
 obj-$(CONFIG_SYSCTL) += utsname_sysctl.o
 obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o
diff --git a/kernel/acct.c b/kernel/acct.c
index f6006a60df5d..d57b7cbb98b6 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -530,15 +530,14 @@ static void do_acct_process(struct bsd_acct_struct *acct,
         do_div(elapsed, AHZ);
         ac.ac_btime = get_seconds() - elapsed;
         /* we really need to bite the bullet and change layout */
-        ac.ac_uid = current->uid;
-        ac.ac_gid = current->gid;
+        current_uid_gid(&ac.ac_uid, &ac.ac_gid);
 #if ACCT_VERSION==2
         ac.ac_ahz = AHZ;
 #endif
 #if ACCT_VERSION==1 || ACCT_VERSION==2
         /* backward-compatible 16 bit fields */
-        ac.ac_uid16 = current->uid;
-        ac.ac_gid16 = current->gid;
+        ac.ac_uid16 = ac.ac_uid;
+        ac.ac_gid16 = ac.ac_gid;
 #endif
 #if ACCT_VERSION==3
         ac.ac_pid = task_tgid_nr_ns(current, ns);
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 2a3f0afc4d2a..4819f3711973 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -65,6 +65,7 @@
 #include <linux/highmem.h>
 #include <linux/syscalls.h>
 #include <linux/inotify.h>
+#include <linux/capability.h>
 
 #include "audit.h"
 
@@ -84,6 +85,15 @@ int audit_n_rules;
 /* determines whether we collect data for signals sent */
 int audit_signals;
 
+struct audit_cap_data {
+        kernel_cap_t            permitted;
+        kernel_cap_t            inheritable;
+        union {
+                unsigned int    fE;             /* effective bit of a file capability */
+                kernel_cap_t    effective;      /* effective set of a process */
+        };
+};
+
 /* When fs/namei.c:getname() is called, we store the pointer in name and
  * we don't let putname() free it (instead we free all of the saved
  * pointers at syscall exit time).
@@ -100,6 +110,8 @@ struct audit_names {
         gid_t           gid;
         dev_t           rdev;
         u32             osid;
+        struct audit_cap_data fcap;
+        unsigned int    fcap_ver;
 };
 
 struct audit_aux_data {
@@ -184,6 +196,20 @@ struct audit_aux_data_pids {
         int                     pid_count;
 };
 
+struct audit_aux_data_bprm_fcaps {
+        struct audit_aux_data   d;
+        struct audit_cap_data   fcap;
+        unsigned int            fcap_ver;
+        struct audit_cap_data   old_pcap;
+        struct audit_cap_data   new_pcap;
+};
+
+struct audit_aux_data_capset {
+        struct audit_aux_data   d;
+        pid_t                   pid;
+        struct audit_cap_data   cap;
+};
+
 struct audit_tree_refs {
         struct audit_tree_refs *next;
         struct audit_chunk *c[31];
@@ -421,6 +447,7 @@ static int audit_filter_rules(struct task_struct *tsk,
                               struct audit_names *name,
                               enum audit_state *state)
 {
+        const struct cred *cred = get_task_cred(tsk);
         int i, j, need_sid = 1;
         u32 sid;
 
@@ -440,28 +467,28 @@ static int audit_filter_rules(struct task_struct *tsk,
                         }
                         break;
                 case AUDIT_UID:
-                        result = audit_comparator(tsk->uid, f->op, f->val);
+                        result = audit_comparator(cred->uid, f->op, f->val);
                         break;
                 case AUDIT_EUID:
-                        result = audit_comparator(tsk->euid, f->op, f->val);
+                        result = audit_comparator(cred->euid, f->op, f->val);
                         break;
                 case AUDIT_SUID:
-                        result = audit_comparator(tsk->suid, f->op, f->val);
+                        result = audit_comparator(cred->suid, f->op, f->val);
                         break;
                 case AUDIT_FSUID:
-                        result = audit_comparator(tsk->fsuid, f->op, f->val);
+                        result = audit_comparator(cred->fsuid, f->op, f->val);
                         break;
                 case AUDIT_GID:
-                        result = audit_comparator(tsk->gid, f->op, f->val);
+                        result = audit_comparator(cred->gid, f->op, f->val);
                         break;
                 case AUDIT_EGID:
-                        result = audit_comparator(tsk->egid, f->op, f->val);
+                        result = audit_comparator(cred->egid, f->op, f->val);
                         break;
                 case AUDIT_SGID:
-                        result = audit_comparator(tsk->sgid, f->op, f->val);
+                        result = audit_comparator(cred->sgid, f->op, f->val);
                         break;
                 case AUDIT_FSGID:
-                        result = audit_comparator(tsk->fsgid, f->op, f->val);
+                        result = audit_comparator(cred->fsgid, f->op, f->val);
                         break;
                 case AUDIT_PERS:
                         result = audit_comparator(tsk->personality, f->op, f->val);
@@ -615,8 +642,10 @@ static int audit_filter_rules(struct task_struct *tsk,
                         break;
                 }
 
-                if (!result)
+                if (!result) {
+                        put_cred(cred);
                         return 0;
+                }
         }
         if (rule->filterkey && ctx)
                 ctx->filterkey = kstrdup(rule->filterkey, GFP_ATOMIC);
@@ -624,6 +653,7 @@ static int audit_filter_rules(struct task_struct *tsk,
         case AUDIT_NEVER:    *state = AUDIT_DISABLED;       break;
         case AUDIT_ALWAYS:   *state = AUDIT_RECORD_CONTEXT; break;
         }
+        put_cred(cred);
         return 1;
 }
 
@@ -1171,8 +1201,38 @@ static void audit_log_execve_info(struct audit_context *context,
         kfree(buf);
 }
 
+static void audit_log_cap(struct audit_buffer *ab, char *prefix, kernel_cap_t *cap)
+{
+        int i;
+
+        audit_log_format(ab, " %s=", prefix);
+        CAP_FOR_EACH_U32(i) {
+                audit_log_format(ab, "%08x", cap->cap[(_KERNEL_CAPABILITY_U32S-1) - i]);
+        }
+}
+
+static void audit_log_fcaps(struct audit_buffer *ab, struct audit_names *name)
+{
+        kernel_cap_t *perm = &name->fcap.permitted;
+        kernel_cap_t *inh = &name->fcap.inheritable;
+        int log = 0;
+
+        if (!cap_isclear(*perm)) {
+                audit_log_cap(ab, "cap_fp", perm);
+                log = 1;
+        }
+        if (!cap_isclear(*inh)) {
+                audit_log_cap(ab, "cap_fi", inh);
+                log = 1;
+        }
+
+        if (log)
+                audit_log_format(ab, " cap_fe=%d cap_fver=%x", name->fcap.fE, name->fcap_ver);
+}
+
 static void audit_log_exit(struct audit_context *context, struct task_struct *tsk)
 {
+        const struct cred *cred;
         int i, call_panic = 0;
         struct audit_buffer *ab;
         struct audit_aux_data *aux;
@@ -1182,14 +1242,15 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
         context->pid = tsk->pid;
         if (!context->ppid)
                 context->ppid = sys_getppid();
-        context->uid = tsk->uid;
-        context->gid = tsk->gid;
-        context->euid = tsk->euid;
-        context->suid = tsk->suid;
-        context->fsuid = tsk->fsuid;
-        context->egid = tsk->egid;
-        context->sgid = tsk->sgid;
-        context->fsgid = tsk->fsgid;
+        cred = current_cred();
+        context->uid   = cred->uid;
+        context->gid   = cred->gid;
+        context->euid  = cred->euid;
+        context->suid  = cred->suid;
+        context->fsuid = cred->fsuid;
+        context->egid  = cred->egid;
+        context->sgid  = cred->sgid;
+        context->fsgid = cred->fsgid;
         context->personality = tsk->personality;
 
         ab = audit_log_start(context, GFP_KERNEL, AUDIT_SYSCALL);
@@ -1334,6 +1395,28 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
                         audit_log_format(ab, "fd0=%d fd1=%d", axs->fd[0], axs->fd[1]);
                         break; }
 
+                case AUDIT_BPRM_FCAPS: {
+                        struct audit_aux_data_bprm_fcaps *axs = (void *)aux;
+                        audit_log_format(ab, "fver=%x", axs->fcap_ver);
+                        audit_log_cap(ab, "fp", &axs->fcap.permitted);
+                        audit_log_cap(ab, "fi", &axs->fcap.inheritable);
+                        audit_log_format(ab, " fe=%d", axs->fcap.fE);
+                        audit_log_cap(ab, "old_pp", &axs->old_pcap.permitted);
+                        audit_log_cap(ab, "old_pi", &axs->old_pcap.inheritable);
+                        audit_log_cap(ab, "old_pe", &axs->old_pcap.effective);
+                        audit_log_cap(ab, "new_pp", &axs->new_pcap.permitted);
+                        audit_log_cap(ab, "new_pi", &axs->new_pcap.inheritable);
+                        audit_log_cap(ab, "new_pe", &axs->new_pcap.effective);
+                        break; }
+
+                case AUDIT_CAPSET: {
+                        struct audit_aux_data_capset *axs = (void *)aux;
+                        audit_log_format(ab, "pid=%d", axs->pid);
+                        audit_log_cap(ab, "cap_pi", &axs->cap.inheritable);
+                        audit_log_cap(ab, "cap_pp", &axs->cap.permitted);
+                        audit_log_cap(ab, "cap_pe", &axs->cap.effective);
+                        break; }
+
                 }
                 audit_log_end(ab);
         }
@@ -1421,6 +1504,8 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
                         }
                 }
 
+                audit_log_fcaps(ab, n);
+
                 audit_log_end(ab);
         }
 
@@ -1802,8 +1887,36 @@ static int audit_inc_name_count(struct audit_context *context,
         return 0;
 }
 
+
+static inline int audit_copy_fcaps(struct audit_names *name, const struct dentry *dentry)
+{
+        struct cpu_vfs_cap_data caps;
+        int rc;
+
+        memset(&name->fcap.permitted, 0, sizeof(kernel_cap_t));
+        memset(&name->fcap.inheritable, 0, sizeof(kernel_cap_t));
+        name->fcap.fE = 0;
+        name->fcap_ver = 0;
+
+        if (!dentry)
+                return 0;
+
+        rc = get_vfs_caps_from_disk(dentry, &caps);
+        if (rc)
+                return rc;
+
+        name->fcap.permitted = caps.permitted;
+        name->fcap.inheritable = caps.inheritable;
+        name->fcap.fE = !!(caps.magic_etc & VFS_CAP_FLAGS_EFFECTIVE);
+        name->fcap_ver = (caps.magic_etc & VFS_CAP_REVISION_MASK) >> VFS_CAP_REVISION_SHIFT;
+
+        return 0;
+}
+
+
 /* Copy inode data into an audit_names. */
-static void audit_copy_inode(struct audit_names *name, const struct inode *inode)
+static void audit_copy_inode(struct audit_names *name, const struct dentry *dentry,
+                             const struct inode *inode)
 {
         name->ino   = inode->i_ino;
         name->dev   = inode->i_sb->s_dev;
@@ -1812,6 +1925,7 @@ static void audit_copy_inode(struct audit_names *name, const struct inode *inode
         name->gid   = inode->i_gid;
         name->rdev  = inode->i_rdev;
         security_inode_getsecid(inode, &name->osid);
+        audit_copy_fcaps(name, dentry);
 }
 
 /**
@@ -1846,7 +1960,7 @@ void __audit_inode(const char *name, const struct dentry *dentry)
                 context->names[idx].name = NULL;
         }
         handle_path(dentry);
-        audit_copy_inode(&context->names[idx], inode);
+        audit_copy_inode(&context->names[idx], dentry, inode);
 }
 
 /**
@@ -1907,7 +2021,7 @@ void __audit_inode_child(const char *dname, const struct dentry *dentry,
                 if (!strcmp(dname, n->name) ||
                      !audit_compare_dname_path(dname, n->name, &dirlen)) {
                         if (inode)
-                                audit_copy_inode(n, inode);
+                                audit_copy_inode(n, NULL, inode);
                         else
                                 n->ino = (unsigned long)-1;
                         found_child = n->name;
@@ -1921,7 +2035,7 @@ add_names:
                         return;
                 idx = context->name_count - 1;
                 context->names[idx].name = NULL;
-                audit_copy_inode(&context->names[idx], parent);
+                audit_copy_inode(&context->names[idx], NULL, parent);
         }
 
         if (!found_child) {
@@ -1942,7 +2056,7 @@ add_names:
                 }
 
                 if (inode)
-                        audit_copy_inode(&context->names[idx], inode);
+                        audit_copy_inode(&context->names[idx], NULL, inode);
                 else
                         context->names[idx].ino = (unsigned long)-1;
         }
@@ -1996,7 +2110,7 @@ int audit_set_loginuid(struct task_struct *task, uid_t loginuid)
                         audit_log_format(ab, "login pid=%d uid=%u "
                                 "old auid=%u new auid=%u"
                                 " old ses=%u new ses=%u",
-                                task->pid, task->uid,
+                                task->pid, task_uid(task),
                                 task->loginuid, loginuid,
                                 task->sessionid, sessionid);
                         audit_log_end(ab);
@@ -2379,7 +2493,7 @@ void __audit_ptrace(struct task_struct *t)
 
         context->target_pid = t->pid;
         context->target_auid = audit_get_loginuid(t);
-        context->target_uid = t->uid;
+        context->target_uid = task_uid(t);
         context->target_sessionid = audit_get_sessionid(t);
         security_task_getsecid(t, &context->target_sid);
         memcpy(context->target_comm, t->comm, TASK_COMM_LEN);
@@ -2398,6 +2512,7 @@ int __audit_signal_info(int sig, struct task_struct *t)
         struct audit_aux_data_pids *axp;
         struct task_struct *tsk = current;
         struct audit_context *ctx = tsk->audit_context;
+        uid_t uid = current_uid(), t_uid = task_uid(t);
 
         if (audit_pid && t->tgid == audit_pid) {
                 if (sig == SIGTERM || sig == SIGHUP || sig == SIGUSR1 || sig == SIGUSR2) {
@@ -2405,7 +2520,7 @@ int __audit_signal_info(int sig, struct task_struct *t)
                         if (tsk->loginuid != -1)
                                 audit_sig_uid = tsk->loginuid;
                         else
-                                audit_sig_uid = tsk->uid;
+                                audit_sig_uid = uid;
                         security_task_getsecid(tsk, &audit_sig_sid);
                 }
                 if (!audit_signals || audit_dummy_context())
@@ -2417,7 +2532,7 @@ int __audit_signal_info(int sig, struct task_struct *t)
         if (!ctx->target_pid) {
                 ctx->target_pid = t->tgid;
                 ctx->target_auid = audit_get_loginuid(t);
-                ctx->target_uid = t->uid;
+                ctx->target_uid = t_uid;
                 ctx->target_sessionid = audit_get_sessionid(t);
                 security_task_getsecid(t, &ctx->target_sid);
                 memcpy(ctx->target_comm, t->comm, TASK_COMM_LEN);
@@ -2438,7 +2553,7 @@ int __audit_signal_info(int sig, struct task_struct *t)
 
         axp->target_pid[axp->pid_count] = t->tgid;
         axp->target_auid[axp->pid_count] = audit_get_loginuid(t);
-        axp->target_uid[axp->pid_count] = t->uid;
+        axp->target_uid[axp->pid_count] = t_uid;
         axp->target_sessionid[axp->pid_count] = audit_get_sessionid(t);
         security_task_getsecid(t, &axp->target_sid[axp->pid_count]);
         memcpy(axp->target_comm[axp->pid_count], t->comm, TASK_COMM_LEN);
@@ -2448,6 +2563,86 @@ int __audit_signal_info(int sig, struct task_struct *t)
 }
 
 /**
+ * __audit_log_bprm_fcaps - store information about a loading bprm and relevant fcaps
+ * @bprm: pointer to the bprm being processed
+ * @new: the proposed new credentials
+ * @old: the old credentials
+ *
+ * Simply check if the proc already has the caps given by the file and if not
+ * store the priv escalation info for later auditing at the end of the syscall
+ *
+ * -Eric
+ */
+int __audit_log_bprm_fcaps(struct linux_binprm *bprm,
+                           const struct cred *new, const struct cred *old)
+{
+        struct audit_aux_data_bprm_fcaps *ax;
+        struct audit_context *context = current->audit_context;
+        struct cpu_vfs_cap_data vcaps;
+        struct dentry *dentry;
+
+        ax = kmalloc(sizeof(*ax), GFP_KERNEL);
+        if (!ax)
+                return -ENOMEM;
+
+        ax->d.type = AUDIT_BPRM_FCAPS;
+        ax->d.next = context->aux;
+        context->aux = (void *)ax;
+
+        dentry = dget(bprm->file->f_dentry);
+        get_vfs_caps_from_disk(dentry, &vcaps);
+        dput(dentry);
+
+        ax->fcap.permitted = vcaps.permitted;
+        ax->fcap.inheritable = vcaps.inheritable;
+        ax->fcap.fE = !!(vcaps.magic_etc & VFS_CAP_FLAGS_EFFECTIVE);
+        ax->fcap_ver = (vcaps.magic_etc & VFS_CAP_REVISION_MASK) >> VFS_CAP_REVISION_SHIFT;
+
+        ax->old_pcap.permitted   = old->cap_permitted;
+        ax->old_pcap.inheritable = old->cap_inheritable;
+        ax->old_pcap.effective   = old->cap_effective;
+
+        ax->new_pcap.permitted   = new->cap_permitted;
+        ax->new_pcap.inheritable = new->cap_inheritable;
+        ax->new_pcap.effective   = new->cap_effective;
+        return 0;
+}
+
+/**
+ * __audit_log_capset - store information about the arguments to the capset syscall
+ * @pid: target pid of the capset call
+ * @new: the new credentials
+ * @old: the old (current) credentials
+ *
+ * Record the aguments userspace sent to sys_capset for later printing by the
+ * audit system if applicable
+ */
+int __audit_log_capset(pid_t pid,
+                       const struct cred *new, const struct cred *old)
+{
+        struct audit_aux_data_capset *ax;
+        struct audit_context *context = current->audit_context;
+
+        if (likely(!audit_enabled || !context || context->dummy))
+                return 0;
+
+        ax = kmalloc(sizeof(*ax), GFP_KERNEL);
+        if (!ax)
+                return -ENOMEM;
+
+        ax->d.type = AUDIT_CAPSET;
+        ax->d.next = context->aux;
+        context->aux = (void *)ax;
+
+        ax->pid = pid;
+        ax->cap.effective   = new->cap_effective;
+        ax->cap.inheritable = new->cap_effective;
+        ax->cap.permitted   = new->cap_permitted;
+
+        return 0;
+}
+
+/**
  * audit_core_dumps - record information about processes that end abnormally
  * @signr: signal value
  *
@@ -2458,7 +2653,8 @@ void audit_core_dumps(long signr)
 {
         struct audit_buffer *ab;
         u32 sid;
-        uid_t auid = audit_get_loginuid(current);
+        uid_t auid = audit_get_loginuid(current), uid;
+        gid_t gid;
         unsigned int sessionid = audit_get_sessionid(current);
 
         if (!audit_enabled)
@@ -2468,8 +2664,9 @@ void audit_core_dumps(long signr)
                 return;
 
         ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_ANOM_ABEND);
+        current_uid_gid(&uid, &gid);
         audit_log_format(ab, "auid=%u uid=%u gid=%u ses=%u",
-                        auid, current->uid, current->gid, sessionid);
+                         auid, uid, gid, sessionid);
         security_task_getsecid(current, &sid);
         if (sid) {
                 char *ctx = NULL;
diff --git a/kernel/capability.c b/kernel/capability.c
index 33e51e78c2d8..36b4b4daebec 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -7,6 +7,7 @@
  * 30 May 2002: Cleanup, Robert M. Love <rml@tech9.net>
  */
 
+#include <linux/audit.h>
 #include <linux/capability.h>
 #include <linux/mm.h>
 #include <linux/module.h>
@@ -14,12 +15,7 @@
 #include <linux/syscalls.h>
 #include <linux/pid_namespace.h>
 #include <asm/uaccess.h>
-
-/*
- * This lock protects task->cap_* for all tasks including current.
- * Locking rule: acquire this prior to tasklist_lock.
- */
-static DEFINE_SPINLOCK(task_capability_lock);
+#include "cred-internals.h"
 
 /*
  * Leveraged for setting/resetting capabilities
@@ -33,6 +29,17 @@ EXPORT_SYMBOL(__cap_empty_set);
 EXPORT_SYMBOL(__cap_full_set);
 EXPORT_SYMBOL(__cap_init_eff_set);
 
+#ifdef CONFIG_SECURITY_FILE_CAPABILITIES
+int file_caps_enabled = 1;
+
+static int __init file_caps_disable(char *str)
+{
+        file_caps_enabled = 0;
+        return 1;
+}
+__setup("no_file_caps", file_caps_disable);
+#endif
+
 /*
  * More recent versions of libcap are available from:
  *
@@ -115,167 +122,12 @@ static int cap_validate_magic(cap_user_header_t header, unsigned *tocopy)
         return 0;
 }
 
-#ifndef CONFIG_SECURITY_FILE_CAPABILITIES
-
-/*
- * Without filesystem capability support, we nominally support one process
- * setting the capabilities of another
- */
-static inline int cap_get_target_pid(pid_t pid, kernel_cap_t *pEp,
-                                     kernel_cap_t *pIp, kernel_cap_t *pPp)
-{
-        struct task_struct *target;
-        int ret;
-
-        spin_lock(&task_capability_lock);
-        read_lock(&tasklist_lock);
-
-        if (pid && pid != task_pid_vnr(current)) {
-                target = find_task_by_vpid(pid);
-                if (!target) {
-                        ret = -ESRCH;
-                        goto out;
-                }
-        } else
-                target = current;
-
-        ret = security_capget(target, pEp, pIp, pPp);
-
-out:
-        read_unlock(&tasklist_lock);
-        spin_unlock(&task_capability_lock);
-
-        return ret;
-}
-
-/*
- * cap_set_pg - set capabilities for all processes in a given process
- * group.  We call this holding task_capability_lock and tasklist_lock.
- */
-static inline int cap_set_pg(int pgrp_nr, kernel_cap_t *effective,
-                             kernel_cap_t *inheritable,
-                             kernel_cap_t *permitted)
-{
-        struct task_struct *g, *target;
-        int ret = -EPERM;
-        int found = 0;
-        struct pid *pgrp;
-
-        spin_lock(&task_capability_lock);
-        read_lock(&tasklist_lock);
-
-        pgrp = find_vpid(pgrp_nr);
-        do_each_pid_task(pgrp, PIDTYPE_PGID, g) {
-                target = g;
-                while_each_thread(g, target) {
-                        if (!security_capset_check(target, effective,
-                                                   inheritable, permitted)) {
-                                security_capset_set(target, effective,
-                                                    inheritable, permitted);
-                                ret = 0;
-                        }
-                        found = 1;
-                }
-        } while_each_pid_task(pgrp, PIDTYPE_PGID, g);
-
-        read_unlock(&tasklist_lock);
-        spin_unlock(&task_capability_lock);
-
-        if (!found)
-                ret = 0;
-        return ret;
-}
-
-/*
- * cap_set_all - set capabilities for all processes other than init
- * and self.  We call this holding task_capability_lock and tasklist_lock.
- */
-static inline int cap_set_all(kernel_cap_t *effective,
-                              kernel_cap_t *inheritable,
-                              kernel_cap_t *permitted)
-{
-        struct task_struct *g, *target;
-        int ret = -EPERM;
-        int found = 0;
-
-        spin_lock(&task_capability_lock);
-        read_lock(&tasklist_lock);
-
-        do_each_thread(g, target) {
-                if (target == current
-                    || is_container_init(target->group_leader))
-                        continue;
-                found = 1;
-                if (security_capset_check(target, effective, inheritable,
-                                          permitted))
-                        continue;
-                ret = 0;
-                security_capset_set(target, effective, inheritable, permitted);
-        } while_each_thread(g, target);
-
-        read_unlock(&tasklist_lock);
-        spin_unlock(&task_capability_lock);
-
-        if (!found)
-                ret = 0;
-
-        return ret;
-}
-
-/*
- * Given the target pid does not refer to the current process we
- * need more elaborate support... (This support is not present when
- * filesystem capabilities are configured.)
- */
-static inline int do_sys_capset_other_tasks(pid_t pid, kernel_cap_t *effective,
-                                            kernel_cap_t *inheritable,
-                                            kernel_cap_t *permitted)
-{
-        struct task_struct *target;
-        int ret;
-
-        if (!capable(CAP_SETPCAP))
-                return -EPERM;
-
-        if (pid == -1)            /* all procs other than current and init */
-                return cap_set_all(effective, inheritable, permitted);
-
-        else if (pid < 0)                    /* all procs in process group */
-                return cap_set_pg(-pid, effective, inheritable, permitted);
-
-        /* target != current */
-        spin_lock(&task_capability_lock);
-        read_lock(&tasklist_lock);
-
-        target = find_task_by_vpid(pid);
-        if (!target)
-                ret = -ESRCH;
-        else {
-                ret = security_capset_check(target, effective, inheritable,
-                                            permitted);
-
-                /* having verified that the proposed changes are legal,
-                   we now put them into effect. */
-                if (!ret)
-                        security_capset_set(target, effective, inheritable,
-                                            permitted);
-        }
-
-        read_unlock(&tasklist_lock);
-        spin_unlock(&task_capability_lock);
-
-        return ret;
-}
-
-#else /* ie., def CONFIG_SECURITY_FILE_CAPABILITIES */
-
 /*
- * If we have configured with filesystem capability support, then the
- * only thing that can change the capabilities of the current process
- * is the current process. As such, we can't be in this code at the
- * same time as we are in the process of setting capabilities in this
- * process. The net result is that we can limit our use of locks to
- * when we are reading the caps of another process.
+ * The only thing that can change the capabilities of the current
+ * process is the current process. As such, we can't be in this code
+ * at the same time as we are in the process of setting capabilities
+ * in this process. The net result is that we can limit our use of
+ * locks to when we are reading the caps of another process.
  */
 static inline int cap_get_target_pid(pid_t pid, kernel_cap_t *pEp,
                                      kernel_cap_t *pIp, kernel_cap_t *pPp)
@@ -285,7 +137,6 @@ static inline int cap_get_target_pid(pid_t pid, kernel_cap_t *pEp,
         if (pid && (pid != task_pid_vnr(current))) {
                 struct task_struct *target;
 
-                spin_lock(&task_capability_lock);
                 read_lock(&tasklist_lock);
 
                 target = find_task_by_vpid(pid);
@@ -295,50 +146,12 @@ static inline int cap_get_target_pid(pid_t pid, kernel_cap_t *pEp,
                         ret = security_capget(target, pEp, pIp, pPp);
 
                 read_unlock(&tasklist_lock);
-                spin_unlock(&task_capability_lock);
         } else
                 ret = security_capget(current, pEp, pIp, pPp);
 
         return ret;
 }
 
-/*
- * With filesystem capability support configured, the kernel does not
- * permit the changing of capabilities in one process by another
- * process. (CAP_SETPCAP has much less broad semantics when configured
- * this way.)
- */
-static inline int do_sys_capset_other_tasks(pid_t pid,
-                                            kernel_cap_t *effective,
-                                            kernel_cap_t *inheritable,
-                                            kernel_cap_t *permitted)
-{
-        return -EPERM;
-}
-
-#endif /* ie., ndef CONFIG_SECURITY_FILE_CAPABILITIES */
-
-/*
- * Atomically modify the effective capabilities returning the original
- * value. No permission check is performed here - it is assumed that the
- * caller is permitted to set the desired effective capabilities.
- */
-kernel_cap_t cap_set_effective(const kernel_cap_t pE_new)
-{
-        kernel_cap_t pE_old;
-
-        spin_lock(&task_capability_lock);
-
-        pE_old = current->cap_effective;
-        current->cap_effective = pE_new;
-
-        spin_unlock(&task_capability_lock);
-
-        return pE_old;
-}
-
-EXPORT_SYMBOL(cap_set_effective);
-
 /**
  * sys_capget - get the capabilities of a given process.
  * @header: pointer to struct that contains capability version and
@@ -366,7 +179,6 @@ asmlinkage long sys_capget(cap_user_header_t header, cap_user_data_t dataptr)
                 return -EINVAL;
 
         ret = cap_get_target_pid(pid, &pE, &pI, &pP);
-
         if (!ret) {
                 struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S];
                 unsigned i;
@@ -412,16 +224,14 @@ asmlinkage long sys_capget(cap_user_header_t header, cap_user_data_t dataptr)
  * @data: pointer to struct that contains the effective, permitted,
  *      and inheritable capabilities
  *
- * Set capabilities for a given process, all processes, or all
- * processes in a given process group.
+ * Set capabilities for the current process only.  The ability to any other
+ * process(es) has been deprecated and removed.
  *
  * The restrictions on setting capabilities are specified as:
  *
- * [pid is for the 'target' task.  'current' is the calling task.]
- *
- * I: any raised capabilities must be a subset of the (old current) permitted
- * P: any raised capabilities must be a subset of the (old current) permitted
- * E: must be set to a subset of (new target) permitted
+ * I: any raised capabilities must be a subset of the old permitted
+ * P: any raised capabilities must be a subset of the old permitted
+ * E: must be set to a subset of new permitted
  *
  * Returns 0 on success and < 0 on error.
  */
@@ -430,6 +240,7 @@ asmlinkage long sys_capset(cap_user_header_t header, const cap_user_data_t data)
         struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S];
         unsigned i, tocopy;
         kernel_cap_t inheritable, permitted, effective;
+        struct cred *new;
         int ret;
         pid_t pid;
 
@@ -440,10 +251,13 @@ asmlinkage long sys_capset(cap_user_header_t header, const cap_user_data_t data)
         if (get_user(pid, &header->pid))
                 return -EFAULT;
 
-        if (copy_from_user(&kdata, data, tocopy
-                           * sizeof(struct __user_cap_data_struct))) {
+        /* may only affect current now */
+        if (pid != 0 && pid != task_pid_vnr(current))
+                return -EPERM;
+
+        if (copy_from_user(&kdata, data,
+                           tocopy * sizeof(struct __user_cap_data_struct)))
                 return -EFAULT;
-        }
 
         for (i = 0; i < tocopy; i++) {
                 effective.cap[i] = kdata[i].effective;
@@ -457,32 +271,23 @@ asmlinkage long sys_capset(cap_user_header_t header, const cap_user_data_t data)
                 i++;
         }
 
-        if (pid && (pid != task_pid_vnr(current)))
-                ret = do_sys_capset_other_tasks(pid, &effective, &inheritable,
-                                                &permitted);
-        else {
-                /*
-                 * This lock is required even when filesystem
-                 * capability support is configured - it protects the
-                 * sys_capget() call from returning incorrect data in
-                 * the case that the targeted process is not the
-                 * current one.
-                 */
-                spin_lock(&task_capability_lock);
+        new = prepare_creds();
+        if (!new)
+                return -ENOMEM;
 
-                ret = security_capset_check(current, &effective, &inheritable,
-                                            &permitted);
-                /*
-                 * Having verified that the proposed changes are
-                 * legal, we now put them into effect.
-                 */
-                if (!ret)
-                        security_capset_set(current, &effective, &inheritable,
-                                            &permitted);
-                spin_unlock(&task_capability_lock);
-        }
+        ret = security_capset(new, current_cred(),
+                              &effective, &inheritable, &permitted);
+        if (ret < 0)
+                goto error;
+
+        ret = audit_log_capset(pid, new, current_cred());
+        if (ret < 0)
+                return ret;
 
+        return commit_creds(new);
 
+error:
+        abort_creds(new);
         return ret;
 }
 
@@ -498,6 +303,11 @@ asmlinkage long sys_capset(cap_user_header_t header, const cap_user_data_t data)
  */
 int capable(int cap)
 {
+        if (unlikely(!cap_valid(cap))) {
+                printk(KERN_CRIT "capable() called with invalid cap=%u\n", cap);
+                BUG();
+        }
+
         if (has_capability(current, cap)) {
                 current->flags |= PF_SUPERPRIV;
                 return 1;
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 8185a0f09594..48348dde6d81 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -571,8 +571,8 @@ static struct inode *cgroup_new_inode(mode_t mode, struct super_block *sb)
 
         if (inode) {
                 inode->i_mode = mode;
-                inode->i_uid = current->fsuid;
-                inode->i_gid = current->fsgid;
+                inode->i_uid = current_fsuid();
+                inode->i_gid = current_fsgid();
                 inode->i_blocks = 0;
                 inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
                 inode->i_mapping->backing_dev_info = &cgroup_backing_dev_info;
@@ -1024,7 +1024,7 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
                 if (ret == -EBUSY) {
                         mutex_unlock(&cgroup_mutex);
                         mutex_unlock(&inode->i_mutex);
-                        goto drop_new_super;
+                        goto free_cg_links;
                 }
 
                 /* EBUSY should be the only error here */
@@ -1073,10 +1073,11 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
 
         return simple_set_mnt(mnt, sb);
 
+ free_cg_links:
+        free_cg_links(&tmp_cg_links);
  drop_new_super:
         up_write(&sb->s_umount);
         deactivate_super(sb);
-        free_cg_links(&tmp_cg_links);
         return ret;
 }
 
@@ -1279,6 +1280,7 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
 static int attach_task_by_pid(struct cgroup *cgrp, u64 pid)
 {
         struct task_struct *tsk;
+        const struct cred *cred = current_cred(), *tcred;
         int ret;
 
         if (pid) {
@@ -1288,14 +1290,16 @@ static int attach_task_by_pid(struct cgroup *cgrp, u64 pid)
                         rcu_read_unlock();
                         return -ESRCH;
                 }
-                get_task_struct(tsk);
-                rcu_read_unlock();
 
-                if ((current->euid) && (current->euid != tsk->uid)
-                    && (current->euid != tsk->suid)) {
-                        put_task_struct(tsk);
+                tcred = __task_cred(tsk);
+                if (cred->euid &&
+                    cred->euid != tcred->uid &&
+                    cred->euid != tcred->suid) {
+                        rcu_read_unlock();
                         return -EACCES;
                 }
+                get_task_struct(tsk);
+                rcu_read_unlock();
         } else {
                 tsk = current;
                 get_task_struct(tsk);
@@ -2934,9 +2938,6 @@ int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys,
  again:
         root = subsys->root;
         if (root == &rootnode) {
-                printk(KERN_INFO
-                       "Not cloning cgroup for unused subsystem %s\n",
-                       subsys->name);
                 mutex_unlock(&cgroup_mutex);
                 return 0;
         }
diff --git a/kernel/compat.c b/kernel/compat.c
index 8eafe3eb50d9..d52e2ec1deb5 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -454,16 +454,16 @@ asmlinkage long compat_sys_waitid(int which, compat_pid_t pid,
 }
 
 static int compat_get_user_cpu_mask(compat_ulong_t __user *user_mask_ptr,
-                                    unsigned len, cpumask_t *new_mask)
+                                    unsigned len, struct cpumask *new_mask)
 {
         unsigned long *k;
 
-        if (len < sizeof(cpumask_t))
-                memset(new_mask, 0, sizeof(cpumask_t));
-        else if (len > sizeof(cpumask_t))
-                len = sizeof(cpumask_t);
+        if (len < cpumask_size())
+                memset(new_mask, 0, cpumask_size());
+        else if (len > cpumask_size())
+                len = cpumask_size();
 
-        k = cpus_addr(*new_mask);
+        k = cpumask_bits(new_mask);
         return compat_get_bitmap(k, user_mask_ptr, len * 8);
 }
 
@@ -471,40 +471,51 @@ asmlinkage long compat_sys_sched_setaffinity(compat_pid_t pid,
                                              unsigned int len,
                                              compat_ulong_t __user *user_mask_ptr)
 {
-        cpumask_t new_mask;
+        cpumask_var_t new_mask;
         int retval;
 
-        retval = compat_get_user_cpu_mask(user_mask_ptr, len, &new_mask);
+        if (!alloc_cpumask_var(&new_mask, GFP_KERNEL))
+                return -ENOMEM;
+
+        retval = compat_get_user_cpu_mask(user_mask_ptr, len, new_mask);
         if (retval)
-                return retval;
+                goto out;
 
-        return sched_setaffinity(pid, &new_mask);
+        retval = sched_setaffinity(pid, new_mask);
+out:
+        free_cpumask_var(new_mask);
+        return retval;
 }
 
 asmlinkage long compat_sys_sched_getaffinity(compat_pid_t pid, unsigned int len,
                                              compat_ulong_t __user *user_mask_ptr)
 {
         int ret;
-        cpumask_t mask;
+        cpumask_var_t mask;
         unsigned long *k;
-        unsigned int min_length = sizeof(cpumask_t);
+        unsigned int min_length = cpumask_size();
 
-        if (NR_CPUS <= BITS_PER_COMPAT_LONG)
+        if (nr_cpu_ids <= BITS_PER_COMPAT_LONG)
                 min_length = sizeof(compat_ulong_t);
 
         if (len < min_length)
                 return -EINVAL;
 
-        ret = sched_getaffinity(pid, &mask);
+        if (!alloc_cpumask_var(&mask, GFP_KERNEL))
+                return -ENOMEM;
+
+        ret = sched_getaffinity(pid, mask);
         if (ret < 0)
-                return ret;
+                goto out;
 
-        k = cpus_addr(mask);
+        k = cpumask_bits(mask);
         ret = compat_put_bitmap(user_mask_ptr, k, min_length * 8);
-        if (ret)
-                return ret;
+        if (ret == 0)
+                ret = min_length;
 
-        return min_length;
+out:
+        free_cpumask_var(mask);
+        return ret;
 }
 
 int get_compat_itimerspec(struct itimerspec *dst,
diff --git a/kernel/cpu.c b/kernel/cpu.c
index bae131a1211b..47fff3b63cbf 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -15,30 +15,8 @@
 #include <linux/stop_machine.h>
 #include <linux/mutex.h>
 
-/*
- * Represents all cpu's present in the system
- * In systems capable of hotplug, this map could dynamically grow
- * as new cpu's are detected in the system via any platform specific
- * method, such as ACPI for e.g.
- */
-cpumask_t cpu_present_map __read_mostly;
-EXPORT_SYMBOL(cpu_present_map);
-
-/*
- * Represents all cpu's that are currently online.
- */
-cpumask_t cpu_online_map __read_mostly;
-EXPORT_SYMBOL(cpu_online_map);
-
-#ifdef CONFIG_INIT_ALL_POSSIBLE
-cpumask_t cpu_possible_map __read_mostly = CPU_MASK_ALL;
-#else
-cpumask_t cpu_possible_map __read_mostly;
-#endif
-EXPORT_SYMBOL(cpu_possible_map);
-
 #ifdef CONFIG_SMP
-/* Serializes the updates to cpu_online_map, cpu_present_map */
+/* Serializes the updates to cpu_online_mask, cpu_present_mask */
 static DEFINE_MUTEX(cpu_add_remove_lock);
 
 static __cpuinitdata RAW_NOTIFIER_HEAD(cpu_chain);
@@ -65,8 +43,6 @@ void __init cpu_hotplug_init(void)
         cpu_hotplug.refcount = 0;
 }
 
-cpumask_t cpu_active_map;
-
 #ifdef CONFIG_HOTPLUG_CPU
 
 void get_online_cpus(void)
@@ -97,7 +73,7 @@ EXPORT_SYMBOL_GPL(put_online_cpus);
 
 /*
  * The following two API's must be used when attempting
- * to serialize the updates to cpu_online_map, cpu_present_map.
+ * to serialize the updates to cpu_online_mask, cpu_present_mask.
  */
 void cpu_maps_update_begin(void)
 {
@@ -218,7 +194,7 @@ static int __ref take_cpu_down(void *_param)
 static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 {
         int err, nr_calls = 0;
-        cpumask_t old_allowed, tmp;
+        cpumask_var_t old_allowed;
         void *hcpu = (void *)(long)cpu;
         unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0;
         struct take_cpu_down_param tcd_param = {
@@ -232,6 +208,9 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
         if (!cpu_online(cpu))
                 return -EINVAL;
 
+        if (!alloc_cpumask_var(&old_allowed, GFP_KERNEL))
+                return -ENOMEM;
+
         cpu_hotplug_begin();
         err = __raw_notifier_call_chain(&cpu_chain, CPU_DOWN_PREPARE | mod,
                                         hcpu, -1, &nr_calls);
@@ -246,13 +225,11 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
         }
 
         /* Ensure that we are not runnable on dying cpu */
-        old_allowed = current->cpus_allowed;
-        cpus_setall(tmp);
-        cpu_clear(cpu, tmp);
-        set_cpus_allowed_ptr(current, &tmp);
-        tmp = cpumask_of_cpu(cpu);
+        cpumask_copy(old_allowed, &current->cpus_allowed);
+        set_cpus_allowed_ptr(current,
+                             cpumask_of(cpumask_any_but(cpu_online_mask, cpu)));
 
-        err = __stop_machine(take_cpu_down, &tcd_param, &tmp);
+        err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu));
         if (err) {
                 /* CPU didn't die: tell everyone.  Can't complain. */
                 if (raw_notifier_call_chain(&cpu_chain, CPU_DOWN_FAILED | mod,
@@ -278,7 +255,7 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
         check_for_tasks(cpu);
 
 out_allowed:
-        set_cpus_allowed_ptr(current, &old_allowed);
+        set_cpus_allowed_ptr(current, old_allowed);
 out_release:
         cpu_hotplug_done();
         if (!err) {
@@ -286,6 +263,7 @@ out_release:
                                             hcpu) == NOTIFY_BAD)
                         BUG();
         }
+        free_cpumask_var(old_allowed);
         return err;
 }
 
@@ -304,7 +282,7 @@ int __ref cpu_down(unsigned int cpu)
 
         /*
          * Make sure the all cpus did the reschedule and are not
-         * using stale version of the cpu_active_map.
+         * using stale version of the cpu_active_mask.
          * This is not strictly necessary becuase stop_machine()
          * that we run down the line already provides the required
          * synchronization. But it's really a side effect and we do not
@@ -368,7 +346,7 @@ out_notify:
 int __cpuinit cpu_up(unsigned int cpu)
 {
         int err = 0;
-        if (!cpu_isset(cpu, cpu_possible_map)) {
+        if (!cpu_possible(cpu)) {
                 printk(KERN_ERR "can't online cpu %d because it is not "
                         "configured as may-hotadd at boot time\n", cpu);
 #if defined(CONFIG_IA64) || defined(CONFIG_X86_64)
@@ -393,25 +371,25 @@ out:
 }
 
 #ifdef CONFIG_PM_SLEEP_SMP
-static cpumask_t frozen_cpus;
+static cpumask_var_t frozen_cpus;
 
 int disable_nonboot_cpus(void)
 {
         int cpu, first_cpu, error = 0;
 
         cpu_maps_update_begin();
-        first_cpu = first_cpu(cpu_online_map);
+        first_cpu = cpumask_first(cpu_online_mask);
         /* We take down all of the non-boot CPUs in one shot to avoid races
          * with the userspace trying to use the CPU hotplug at the same time
          */
-        cpus_clear(frozen_cpus);
+        cpumask_clear(frozen_cpus);
         printk("Disabling non-boot CPUs ...\n");
         for_each_online_cpu(cpu) {
                 if (cpu == first_cpu)
                         continue;
                 error = _cpu_down(cpu, 1);
                 if (!error) {
-                        cpu_set(cpu, frozen_cpus);
+                        cpumask_set_cpu(cpu, frozen_cpus);
                         printk("CPU%d is down\n", cpu);
                 } else {
                         printk(KERN_ERR "Error taking CPU%d down: %d\n",
@@ -437,11 +415,11 @@ void __ref enable_nonboot_cpus(void)
         /* Allow everyone to use the CPU hotplug again */
         cpu_maps_update_begin();
         cpu_hotplug_disabled = 0;
-        if (cpus_empty(frozen_cpus))
+        if (cpumask_empty(frozen_cpus))
                 goto out;
 
         printk("Enabling non-boot CPUs ...\n");
-        for_each_cpu_mask_nr(cpu, frozen_cpus) {
+        for_each_cpu(cpu, frozen_cpus) {
                 error = _cpu_up(cpu, 1);
                 if (!error) {
                         printk("CPU%d is up\n", cpu);
@@ -449,10 +427,18 @@ void __ref enable_nonboot_cpus(void)
                 }
                 printk(KERN_WARNING "Error taking CPU%d up: %d\n", cpu, error);
         }
-        cpus_clear(frozen_cpus);
+        cpumask_clear(frozen_cpus);
 out:
         cpu_maps_update_done();
 }
+
+static int alloc_frozen_cpus(void)
+{
+        if (!alloc_cpumask_var(&frozen_cpus, GFP_KERNEL|__GFP_ZERO))
+                return -ENOMEM;
+        return 0;
+}
+core_initcall(alloc_frozen_cpus);
 #endif /* CONFIG_PM_SLEEP_SMP */
 
 /**
@@ -468,7 +454,7 @@ void __cpuinit notify_cpu_starting(unsigned int cpu)
         unsigned long val = CPU_STARTING;
 
 #ifdef CONFIG_PM_SLEEP_SMP
-        if (cpu_isset(cpu, frozen_cpus))
+        if (frozen_cpus != NULL && cpumask_test_cpu(cpu, frozen_cpus))
                 val = CPU_STARTING_FROZEN;
 #endif /* CONFIG_PM_SLEEP_SMP */
         raw_notifier_call_chain(&cpu_chain, val, (void *)(long)cpu);
@@ -480,7 +466,7 @@ void __cpuinit notify_cpu_starting(unsigned int cpu)
  * cpu_bit_bitmap[] is a special, "compressed" data structure that
  * represents all NR_CPUS bits binary values of 1<<nr.
  *
- * It is used by cpumask_of_cpu() to get a constant address to a CPU
+ * It is used by cpumask_of() to get a constant address to a CPU
  * mask value that has a single bit set only.
  */
 
@@ -503,3 +489,71 @@ EXPORT_SYMBOL_GPL(cpu_bit_bitmap);
 
 const DECLARE_BITMAP(cpu_all_bits, NR_CPUS) = CPU_BITS_ALL;
 EXPORT_SYMBOL(cpu_all_bits);
+
+#ifdef CONFIG_INIT_ALL_POSSIBLE
+static DECLARE_BITMAP(cpu_possible_bits, CONFIG_NR_CPUS) __read_mostly
+        = CPU_BITS_ALL;
+#else
+static DECLARE_BITMAP(cpu_possible_bits, CONFIG_NR_CPUS) __read_mostly;
+#endif
+const struct cpumask *const cpu_possible_mask = to_cpumask(cpu_possible_bits);
+EXPORT_SYMBOL(cpu_possible_mask);
+
+static DECLARE_BITMAP(cpu_online_bits, CONFIG_NR_CPUS) __read_mostly;
+const struct cpumask *const cpu_online_mask = to_cpumask(cpu_online_bits);
+EXPORT_SYMBOL(cpu_online_mask);
+
+static DECLARE_BITMAP(cpu_present_bits, CONFIG_NR_CPUS) __read_mostly;
+const struct cpumask *const cpu_present_mask = to_cpumask(cpu_present_bits);
+EXPORT_SYMBOL(cpu_present_mask);
+
+static DECLARE_BITMAP(cpu_active_bits, CONFIG_NR_CPUS) __read_mostly;
+const struct cpumask *const cpu_active_mask = to_cpumask(cpu_active_bits);
+EXPORT_SYMBOL(cpu_active_mask);
+
+void set_cpu_possible(unsigned int cpu, bool possible)
+{
+        if (possible)
+                cpumask_set_cpu(cpu, to_cpumask(cpu_possible_bits));
+        else
+                cpumask_clear_cpu(cpu, to_cpumask(cpu_possible_bits));
+}
+
+void set_cpu_present(unsigned int cpu, bool present)
+{
+        if (present)
+                cpumask_set_cpu(cpu, to_cpumask(cpu_present_bits));
+        else
+                cpumask_clear_cpu(cpu, to_cpumask(cpu_present_bits));
+}
+
+void set_cpu_online(unsigned int cpu, bool online)
+{
+        if (online)
+                cpumask_set_cpu(cpu, to_cpumask(cpu_online_bits));
+        else
+                cpumask_clear_cpu(cpu, to_cpumask(cpu_online_bits));
+}
+
+void set_cpu_active(unsigned int cpu, bool active)
+{
+        if (active)
+                cpumask_set_cpu(cpu, to_cpumask(cpu_active_bits));
+        else
+                cpumask_clear_cpu(cpu, to_cpumask(cpu_active_bits));
+}
+
+void init_cpu_present(const struct cpumask *src)
+{
+        cpumask_copy(to_cpumask(cpu_present_bits), src);
+}
+
+void init_cpu_possible(const struct cpumask *src)
+{
+        cpumask_copy(to_cpumask(cpu_possible_bits), src);
+}
+
+void init_cpu_online(const struct cpumask *src)
+{
+        cpumask_copy(to_cpumask(cpu_online_bits), src);
+}
diff --git a/kernel/cred-internals.h b/kernel/cred-internals.h
new file mode 100644
index 000000000000..2dc4fc2d0bf1
--- /dev/null
+++ b/kernel/cred-internals.h
@@ -0,0 +1,21 @@
+/* Internal credentials stuff
+ *
+ * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+/*
+ * user.c
+ */
+static inline void sched_switch_user(struct task_struct *p)
+{
+#ifdef CONFIG_USER_SCHED
+        sched_move_task(p);
+#endif  /* CONFIG_USER_SCHED */
+}
+
diff --git a/kernel/cred.c b/kernel/cred.c
new file mode 100644
index 000000000000..ff7bc071991c
--- /dev/null
+++ b/kernel/cred.c
@@ -0,0 +1,588 @@
+/* Task credentials management - see Documentation/credentials.txt
+ *
+ * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+#include <linux/module.h>
+#include <linux/cred.h>
+#include <linux/sched.h>
+#include <linux/key.h>
+#include <linux/keyctl.h>
+#include <linux/init_task.h>
+#include <linux/security.h>
+#include <linux/cn_proc.h>
+#include "cred-internals.h"
+
+static struct kmem_cache *cred_jar;
+
+/*
+ * The common credentials for the initial task's thread group
+ */
+#ifdef CONFIG_KEYS
+static struct thread_group_cred init_tgcred = {
+        .usage  = ATOMIC_INIT(2),
+        .tgid   = 0,
+        .lock   = SPIN_LOCK_UNLOCKED,
+};
+#endif
+
+/*
+ * The initial credentials for the initial task
+ */
+struct cred init_cred = {
+        .usage                  = ATOMIC_INIT(4),
+        .securebits             = SECUREBITS_DEFAULT,
+        .cap_inheritable        = CAP_INIT_INH_SET,
+        .cap_permitted          = CAP_FULL_SET,
+        .cap_effective          = CAP_INIT_EFF_SET,
+        .cap_bset               = CAP_INIT_BSET,
+        .user                   = INIT_USER,
+        .group_info             = &init_groups,
+#ifdef CONFIG_KEYS
+        .tgcred                 = &init_tgcred,
+#endif
+};
+
+/*
+ * Dispose of the shared task group credentials
+ */
+#ifdef CONFIG_KEYS
+static void release_tgcred_rcu(struct rcu_head *rcu)
+{
+        struct thread_group_cred *tgcred =
+                container_of(rcu, struct thread_group_cred, rcu);
+
+        BUG_ON(atomic_read(&tgcred->usage) != 0);
+
+        key_put(tgcred->session_keyring);
+        key_put(tgcred->process_keyring);
+        kfree(tgcred);
+}
+#endif
+
+/*
+ * Release a set of thread group credentials.
+ */
+static void release_tgcred(struct cred *cred)
+{
+#ifdef CONFIG_KEYS
+        struct thread_group_cred *tgcred = cred->tgcred;
+
+        if (atomic_dec_and_test(&tgcred->usage))
+                call_rcu(&tgcred->rcu, release_tgcred_rcu);
+#endif
+}
+
+/*
+ * The RCU callback to actually dispose of a set of credentials
+ */
+static void put_cred_rcu(struct rcu_head *rcu)
+{
+        struct cred *cred = container_of(rcu, struct cred, rcu);
+
+        if (atomic_read(&cred->usage) != 0)
+                panic("CRED: put_cred_rcu() sees %p with usage %d\n",
+                      cred, atomic_read(&cred->usage));
+
+        security_cred_free(cred);
+        key_put(cred->thread_keyring);
+        key_put(cred->request_key_auth);
+        release_tgcred(cred);
+        put_group_info(cred->group_info);
+        free_uid(cred->user);
+        kmem_cache_free(cred_jar, cred);
+}
+
+/**
+ * __put_cred - Destroy a set of credentials
+ * @cred: The record to release
+ *
+ * Destroy a set of credentials on which no references remain.
+ */
+void __put_cred(struct cred *cred)
+{
+        BUG_ON(atomic_read(&cred->usage) != 0);
+
+        call_rcu(&cred->rcu, put_cred_rcu);
+}
+EXPORT_SYMBOL(__put_cred);
+
+/**
+ * prepare_creds - Prepare a new set of credentials for modification
+ *
+ * Prepare a new set of task credentials for modification.  A task's creds
+ * shouldn't generally be modified directly, therefore this function is used to
+ * prepare a new copy, which the caller then modifies and then commits by
+ * calling commit_creds().
+ *
+ * Preparation involves making a copy of the objective creds for modification.
+ *
+ * Returns a pointer to the new creds-to-be if successful, NULL otherwise.
+ *
+ * Call commit_creds() or abort_creds() to clean up.
+ */
+struct cred *prepare_creds(void)
+{
+        struct task_struct *task = current;
+        const struct cred *old;
+        struct cred *new;
+
+        BUG_ON(atomic_read(&task->real_cred->usage) < 1);
+
+        new = kmem_cache_alloc(cred_jar, GFP_KERNEL);
+        if (!new)
+                return NULL;
+
+        old = task->cred;
+        memcpy(new, old, sizeof(struct cred));
+
+        atomic_set(&new->usage, 1);
+        get_group_info(new->group_info);
+        get_uid(new->user);
+
+#ifdef CONFIG_KEYS
+        key_get(new->thread_keyring);
+        key_get(new->request_key_auth);
+        atomic_inc(&new->tgcred->usage);
+#endif
+
+#ifdef CONFIG_SECURITY
+        new->security = NULL;
+#endif
+
+        if (security_prepare_creds(new, old, GFP_KERNEL) < 0)
+                goto error;
+        return new;
+
+error:
+        abort_creds(new);
+        return NULL;
+}
+EXPORT_SYMBOL(prepare_creds);
+
+/*
+ * Prepare credentials for current to perform an execve()
+ * - The caller must hold current->cred_exec_mutex
+ */
+struct cred *prepare_exec_creds(void)
+{
+        struct thread_group_cred *tgcred = NULL;
+        struct cred *new;
+
+#ifdef CONFIG_KEYS
+        tgcred = kmalloc(sizeof(*tgcred), GFP_KERNEL);
+        if (!tgcred)
+                return NULL;
+#endif
+
+        new = prepare_creds();
+        if (!new) {
+                kfree(tgcred);
+                return new;
+        }
+
+#ifdef CONFIG_KEYS
+        /* newly exec'd tasks don't get a thread keyring */
+        key_put(new->thread_keyring);
+        new->thread_keyring = NULL;
+
+        /* create a new per-thread-group creds for all this set of threads to
+         * share */
+        memcpy(tgcred, new->tgcred, sizeof(struct thread_group_cred));
+
+        atomic_set(&tgcred->usage, 1);
+        spin_lock_init(&tgcred->lock);
+
+        /* inherit the session keyring; new process keyring */
+        key_get(tgcred->session_keyring);
+        tgcred->process_keyring = NULL;
+
+        release_tgcred(new);
+        new->tgcred = tgcred;
+#endif
+
+        return new;
+}
+
+/*
+ * prepare new credentials for the usermode helper dispatcher
+ */
+struct cred *prepare_usermodehelper_creds(void)
+{
+#ifdef CONFIG_KEYS
+        struct thread_group_cred *tgcred = NULL;
+#endif
+        struct cred *new;
+
+#ifdef CONFIG_KEYS
+        tgcred = kzalloc(sizeof(*new->tgcred), GFP_ATOMIC);
+        if (!tgcred)
+                return NULL;
+#endif
+
+        new = kmem_cache_alloc(cred_jar, GFP_ATOMIC);
+        if (!new)
+                return NULL;
+
+        memcpy(new, &init_cred, sizeof(struct cred));
+
+        atomic_set(&new->usage, 1);
+        get_group_info(new->group_info);
+        get_uid(new->user);
+
+#ifdef CONFIG_KEYS
+        new->thread_keyring = NULL;
+        new->request_key_auth = NULL;
+        new->jit_keyring = KEY_REQKEY_DEFL_DEFAULT;
+
+        atomic_set(&tgcred->usage, 1);
+        spin_lock_init(&tgcred->lock);
+        new->tgcred = tgcred;
+#endif
+
+#ifdef CONFIG_SECURITY
+        new->security = NULL;
+#endif
+        if (security_prepare_creds(new, &init_cred, GFP_ATOMIC) < 0)
+                goto error;
+
+        BUG_ON(atomic_read(&new->usage) != 1);
+        return new;
+
+error:
+        put_cred(new);
+        return NULL;
+}
+
+/*
+ * Copy credentials for the new process created by fork()
+ *
+ * We share if we can, but under some circumstances we have to generate a new
+ * set.
+ *
+ * The new process gets the current process's subjective credentials as its
+ * objective and subjective credentials
+ */
+int copy_creds(struct task_struct *p, unsigned long clone_flags)
+{
+#ifdef CONFIG_KEYS
+        struct thread_group_cred *tgcred;
+#endif
+        struct cred *new;
+        int ret;
+
+        mutex_init(&p->cred_exec_mutex);
+
+        if (
+#ifdef CONFIG_KEYS
+                !p->cred->thread_keyring &&
+#endif
+                clone_flags & CLONE_THREAD
+            ) {
+                p->real_cred = get_cred(p->cred);
+                get_cred(p->cred);
+                atomic_inc(&p->cred->user->processes);
+                return 0;
+        }
+
+        new = prepare_creds();
+        if (!new)
+                return -ENOMEM;
+
+        if (clone_flags & CLONE_NEWUSER) {
+                ret = create_user_ns(new);
+                if (ret < 0)
+                        goto error_put;
+        }
+
+#ifdef CONFIG_KEYS
+        /* new threads get their own thread keyrings if their parent already
+         * had one */
+        if (new->thread_keyring) {
+                key_put(new->thread_keyring);
+                new->thread_keyring = NULL;
+                if (clone_flags & CLONE_THREAD)
+                        install_thread_keyring_to_cred(new);
+        }
+
+        /* we share the process and session keyrings between all the threads in
+         * a process - this is slightly icky as we violate COW credentials a
+         * bit */
+        if (!(clone_flags & CLONE_THREAD)) {
+                tgcred = kmalloc(sizeof(*tgcred), GFP_KERNEL);
+                if (!tgcred) {
+                        ret = -ENOMEM;
+                        goto error_put;
+                }
+                atomic_set(&tgcred->usage, 1);
+                spin_lock_init(&tgcred->lock);
+                tgcred->process_keyring = NULL;
+                tgcred->session_keyring = key_get(new->tgcred->session_keyring);
+
+                release_tgcred(new);
+                new->tgcred = tgcred;
+        }
+#endif
+
+        atomic_inc(&new->user->processes);
+        p->cred = p->real_cred = get_cred(new);
+        return 0;
+
+error_put:
+        put_cred(new);
+        return ret;
+}
+
+/**
+ * commit_creds - Install new credentials upon the current task
+ * @new: The credentials to be assigned
+ *
+ * Install a new set of credentials to the current task, using RCU to replace
+ * the old set.  Both the objective and the subjective credentials pointers are
+ * updated.  This function may not be called if the subjective credentials are
+ * in an overridden state.
+ *
+ * This function eats the caller's reference to the new credentials.
+ *
+ * Always returns 0 thus allowing this function to be tail-called at the end
+ * of, say, sys_setgid().
+ */
+int commit_creds(struct cred *new)
+{
+        struct task_struct *task = current;
+        const struct cred *old;
+
+        BUG_ON(task->cred != task->real_cred);
+        BUG_ON(atomic_read(&task->real_cred->usage) < 2);
+        BUG_ON(atomic_read(&new->usage) < 1);
+
+        old = task->real_cred;
+        security_commit_creds(new, old);
+
+        get_cred(new); /* we will require a ref for the subj creds too */
+
+        /* dumpability changes */
+        if (old->euid != new->euid ||
+            old->egid != new->egid ||
+            old->fsuid != new->fsuid ||
+            old->fsgid != new->fsgid ||
+            !cap_issubset(new->cap_permitted, old->cap_permitted)) {
+                set_dumpable(task->mm, suid_dumpable);
+                task->pdeath_signal = 0;
+                smp_wmb();
+        }
+
+        /* alter the thread keyring */
+        if (new->fsuid != old->fsuid)
+                key_fsuid_changed(task);
+        if (new->fsgid != old->fsgid)
+                key_fsgid_changed(task);
+
+        /* do it
+         * - What if a process setreuid()'s and this brings the
+         *   new uid over his NPROC rlimit?  We can check this now
+         *   cheaply with the new uid cache, so if it matters
+         *   we should be checking for it.  -DaveM
+         */
+        if (new->user != old->user)
+                atomic_inc(&new->user->processes);
+        rcu_assign_pointer(task->real_cred, new);
+        rcu_assign_pointer(task->cred, new);
+        if (new->user != old->user)
+                atomic_dec(&old->user->processes);
+
+        sched_switch_user(task);
+
+        /* send notifications */
+        if (new->uid   != old->uid  ||
+            new->euid  != old->euid ||
+            new->suid  != old->suid ||
+            new->fsuid != old->fsuid)
+                proc_id_connector(task, PROC_EVENT_UID);
+
+        if (new->gid   != old->gid  ||
+            new->egid  != old->egid ||
+            new->sgid  != old->sgid ||
+            new->fsgid != old->fsgid)
+                proc_id_connector(task, PROC_EVENT_GID);
+
+        /* release the old obj and subj refs both */
+        put_cred(old);
+        put_cred(old);
+        return 0;
+}
+EXPORT_SYMBOL(commit_creds);
+
+/**
+ * abort_creds - Discard a set of credentials and unlock the current task
+ * @new: The credentials that were going to be applied
+ *
+ * Discard a set of credentials that were under construction and unlock the
+ * current task.
+ */
+void abort_creds(struct cred *new)
+{
+        BUG_ON(atomic_read(&new->usage) < 1);
+        put_cred(new);
+}
+EXPORT_SYMBOL(abort_creds);
+
+/**
+ * override_creds - Override the current process's subjective credentials
+ * @new: The credentials to be assigned
+ *
+ * Install a set of temporary override subjective credentials on the current
+ * process, returning the old set for later reversion.
+ */
+const struct cred *override_creds(const struct cred *new)
+{
+        const struct cred *old = current->cred;
+
+        rcu_assign_pointer(current->cred, get_cred(new));
+        return old;
+}
+EXPORT_SYMBOL(override_creds);
+
+/**
+ * revert_creds - Revert a temporary subjective credentials override
+ * @old: The credentials to be restored
+ *
+ * Revert a temporary set of override subjective credentials to an old set,
+ * discarding the override set.
+ */
+void revert_creds(const struct cred *old)
+{
+        const struct cred *override = current->cred;
+
+        rcu_assign_pointer(current->cred, old);
+        put_cred(override);
+}
+EXPORT_SYMBOL(revert_creds);
+
+/*
+ * initialise the credentials stuff
+ */
+void __init cred_init(void)
+{
+        /* allocate a slab in which we can store credentials */
+        cred_jar = kmem_cache_create("cred_jar", sizeof(struct cred),
+                                     0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
+}
+
+/**
+ * prepare_kernel_cred - Prepare a set of credentials for a kernel service
+ * @daemon: A userspace daemon to be used as a reference
+ *
+ * Prepare a set of credentials for a kernel service.  This can then be used to
+ * override a task's own credentials so that work can be done on behalf of that
+ * task that requires a different subjective context.
+ *
+ * @daemon is used to provide a base for the security record, but can be NULL.
+ * If @daemon is supplied, then the security data will be derived from that;
+ * otherwise they'll be set to 0 and no groups, full capabilities and no keys.
+ *
+ * The caller may change these controls afterwards if desired.
+ *
+ * Returns the new credentials or NULL if out of memory.
+ *
+ * Does not take, and does not return holding current->cred_replace_mutex.
+ */
+struct cred *prepare_kernel_cred(struct task_struct *daemon)
+{
+        const struct cred *old;
+        struct cred *new;
+
+        new = kmem_cache_alloc(cred_jar, GFP_KERNEL);
+        if (!new)
+                return NULL;
+
+        if (daemon)
+                old = get_task_cred(daemon);
+        else
+                old = get_cred(&init_cred);
+
+        get_uid(new->user);
+        get_group_info(new->group_info);
+
+#ifdef CONFIG_KEYS
+        atomic_inc(&init_tgcred.usage);
+        new->tgcred = &init_tgcred;
+        new->request_key_auth = NULL;
+        new->thread_keyring = NULL;
+        new->jit_keyring = KEY_REQKEY_DEFL_THREAD_KEYRING;
+#endif
+
+#ifdef CONFIG_SECURITY
+        new->security = NULL;
+#endif
+        if (security_prepare_creds(new, old, GFP_KERNEL) < 0)
+                goto error;
+
+        atomic_set(&new->usage, 1);
+        put_cred(old);
+        return new;
+
+error:
+        put_cred(new);
+        return NULL;
+}
+EXPORT_SYMBOL(prepare_kernel_cred);
+
+/**
+ * set_security_override - Set the security ID in a set of credentials
+ * @new: The credentials to alter
+ * @secid: The LSM security ID to set
+ *
+ * Set the LSM security ID in a set of credentials so that the subjective
+ * security is overridden when an alternative set of credentials is used.
+ */
+int set_security_override(struct cred *new, u32 secid)
+{
+        return security_kernel_act_as(new, secid);
+}
+EXPORT_SYMBOL(set_security_override);
+
+/**
+ * set_security_override_from_ctx - Set the security ID in a set of credentials
+ * @new: The credentials to alter
+ * @secctx: The LSM security context to generate the security ID from.
+ *
+ * Set the LSM security ID in a set of credentials so that the subjective
+ * security is overridden when an alternative set of credentials is used.  The
+ * security ID is specified in string form as a security context to be
+ * interpreted by the LSM.
+ */
+int set_security_override_from_ctx(struct cred *new, const char *secctx)
+{
+        u32 secid;
+        int ret;
+
+        ret = security_secctx_to_secid(secctx, strlen(secctx), &secid);
+        if (ret < 0)
+                return ret;
+
+        return set_security_override(new, secid);
+}
+EXPORT_SYMBOL(set_security_override_from_ctx);
+
+/**
+ * set_create_files_as - Set the LSM file create context in a set of credentials
+ * @new: The credentials to alter
+ * @inode: The inode to take the context from
+ *
+ * Change the LSM file creation context in a set of credentials to be the same
+ * as the object context of the specified inode, so that the new inodes have
+ * the same MAC context as that inode.
+ */
+int set_create_files_as(struct cred *new, struct inode *inode)
+{
+        new->fsuid = inode->i_uid;
+        new->fsgid = inode->i_gid;
+        return security_kernel_create_files_as(new, inode);
+}
+EXPORT_SYMBOL(set_create_files_as);
diff --git a/kernel/delayacct.c b/kernel/delayacct.c
index b3179dad71be..abb6e17505e2 100644
--- a/kernel/delayacct.c
+++ b/kernel/delayacct.c
@@ -127,7 +127,7 @@ int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
          */
         t1 = tsk->sched_info.pcount;
         t2 = tsk->sched_info.run_delay;
-        t3 = tsk->sched_info.cpu_time;
+        t3 = tsk->se.sum_exec_runtime;
 
         d->cpu_count += t1;
 
diff --git a/kernel/exit.c b/kernel/exit.c
index 61ba5b4b10cf..c9e5a1c14e08 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -46,12 +46,14 @@
 #include <linux/blkdev.h>
 #include <linux/task_io_accounting_ops.h>
 #include <linux/tracehook.h>
+#include <linux/init_task.h>
 #include <trace/sched.h>
 
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
 #include <asm/pgtable.h>
 #include <asm/mmu_context.h>
+#include "cred-internals.h"
 
 DEFINE_TRACE(sched_process_free);
 DEFINE_TRACE(sched_process_exit);
@@ -168,7 +170,10 @@ void release_task(struct task_struct * p)
         int zap_leader;
 repeat:
         tracehook_prepare_release_task(p);
-        atomic_dec(&p->user->processes);
+        /* don't need to get the RCU readlock here - the process is dead and
+         * can't be modifying its own credentials */
+        atomic_dec(&__task_cred(p)->user->processes);
+
         proc_flush_task(p);
         write_lock_irq(&tasklist_lock);
         tracehook_finish_release_task(p);
@@ -343,12 +348,12 @@ static void reparent_to_kthreadd(void)
         /* cpus_allowed? */
         /* rt_priority? */
         /* signals? */
-        security_task_reparent_to_init(current);
         memcpy(current->signal->rlim, init_task.signal->rlim,
                sizeof(current->signal->rlim));
-        atomic_inc(&(INIT_USER->__count));
+
+        atomic_inc(&init_cred.usage);
+        commit_creds(&init_cred);
         write_unlock_irq(&tasklist_lock);
-        switch_uid(INIT_USER);
 }
 
 void __set_special_pids(struct pid *pid)
@@ -1032,8 +1037,6 @@ NORET_TYPE void do_exit(long code)
                  * task into the wait for ever nirwana as well.
                  */
                 tsk->flags |= PF_EXITPIDONE;
-                if (tsk->io_context)
-                        exit_io_context();
                 set_current_state(TASK_UNINTERRUPTIBLE);
                 schedule();
         }
@@ -1082,7 +1085,6 @@ NORET_TYPE void do_exit(long code)
         check_stack_usage();
         exit_thread();
         cgroup_exit(tsk, 1);
-        exit_keys(tsk);
 
         if (group_dead && tsk->signal->leader)
                 disassociate_ctty(1);
@@ -1266,12 +1268,12 @@ static int wait_task_zombie(struct task_struct *p, int options,
         unsigned long state;
         int retval, status, traced;
         pid_t pid = task_pid_vnr(p);
+        uid_t uid = __task_cred(p)->uid;
 
         if (!likely(options & WEXITED))
                 return 0;
 
         if (unlikely(options & WNOWAIT)) {
-                uid_t uid = p->uid;
                 int exit_code = p->exit_code;
                 int why, status;
 
@@ -1392,7 +1394,7 @@ static int wait_task_zombie(struct task_struct *p, int options,
         if (!retval && infop)
                 retval = put_user(pid, &infop->si_pid);
         if (!retval && infop)
-                retval = put_user(p->uid, &infop->si_uid);
+                retval = put_user(uid, &infop->si_uid);
         if (!retval)
                 retval = pid;
 
@@ -1457,7 +1459,8 @@ static int wait_task_stopped(int ptrace, struct task_struct *p,
         if (!unlikely(options & WNOWAIT))
                 p->exit_code = 0;
 
-        uid = p->uid;
+        /* don't need the RCU readlock here as we're holding a spinlock */
+        uid = __task_cred(p)->uid;
 unlock_sig:
         spin_unlock_irq(&p->sighand->siglock);
         if (!exit_code)
@@ -1531,10 +1534,10 @@ static int wait_task_continued(struct task_struct *p, int options,
         }
         if (!unlikely(options & WNOWAIT))
                 p->signal->flags &= ~SIGNAL_STOP_CONTINUED;
+        uid = __task_cred(p)->uid;
         spin_unlock_irq(&p->sighand->siglock);
 
         pid = task_pid_vnr(p);
-        uid = p->uid;
         get_task_struct(p);
         read_unlock(&tasklist_lock);
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 7b93da72d4a2..43cbf30669e6 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -151,9 +151,8 @@ void __put_task_struct(struct task_struct *tsk)
         WARN_ON(atomic_read(&tsk->usage));
         WARN_ON(tsk == current);
 
-        security_task_free(tsk);
-        free_uid(tsk->user);
-        put_group_info(tsk->group_info);
+        put_cred(tsk->real_cred);
+        put_cred(tsk->cred);
         delayacct_tsk_free(tsk);
 
         if (!profile_handoff_task(tsk))
@@ -416,8 +415,8 @@ static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p)
         set_mm_counter(mm, file_rss, 0);
         set_mm_counter(mm, anon_rss, 0);
         spin_lock_init(&mm->page_table_lock);
-        rwlock_init(&mm->ioctx_list_lock);
-        mm->ioctx_list = NULL;
+        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_owner(mm, p);
@@ -822,12 +821,6 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
         if (!sig)
                 return -ENOMEM;
 
-        ret = copy_thread_group_keys(tsk);
-        if (ret < 0) {
-                kmem_cache_free(signal_cachep, sig);
-                return ret;
-        }
-
         atomic_set(&sig->count, 1);
         atomic_set(&sig->live, 1);
         init_waitqueue_head(&sig->wait_chldexit);
@@ -872,7 +865,6 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 void __cleanup_signal(struct signal_struct *sig)
 {
         thread_group_cputime_free(sig);
-        exit_thread_group_keys(sig);
         tty_kref_put(sig->tty);
         kmem_cache_free(signal_cachep, sig);
 }
@@ -988,16 +980,16 @@ static struct task_struct *copy_process(unsigned long clone_flags,
         DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled);
 #endif
         retval = -EAGAIN;
-        if (atomic_read(&p->user->processes) >=
+        if (atomic_read(&p->real_cred->user->processes) >=
                         p->signal->rlim[RLIMIT_NPROC].rlim_cur) {
                 if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_RESOURCE) &&
-                    p->user != current->nsproxy->user_ns->root_user)
+                    p->real_cred->user != INIT_USER)
                         goto bad_fork_free;
         }
 
-        atomic_inc(&p->user->__count);
-        atomic_inc(&p->user->processes);
-        get_group_info(p->group_info);
+        retval = copy_creds(p, clone_flags);
+        if (retval < 0)
+                goto bad_fork_free;
 
         /*
          * If multiple threads are within copy_process(), then this check
@@ -1052,10 +1044,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
         do_posix_clock_monotonic_gettime(&p->start_time);
         p->real_start_time = p->start_time;
         monotonic_to_bootbased(&p->real_start_time);
-#ifdef CONFIG_SECURITY
-        p->security = NULL;
-#endif
-        p->cap_bset = current->cap_bset;
         p->io_context = NULL;
         p->audit_context = NULL;
         cgroup_fork(p);
@@ -1096,14 +1084,14 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 #ifdef CONFIG_DEBUG_MUTEXES
         p->blocked_on = NULL; /* not blocked yet */
 #endif
+        if (unlikely(ptrace_reparented(current)))
+                ptrace_fork(p, clone_flags);
 
         /* Perform scheduler related setup. Assign this task to a CPU. */
         sched_fork(p, clone_flags);
 
-        if ((retval = security_task_alloc(p)))
-                goto bad_fork_cleanup_policy;
         if ((retval = audit_alloc(p)))
-                goto bad_fork_cleanup_security;
+                goto bad_fork_cleanup_policy;
         /* copy all the process information */
         if ((retval = copy_semundo(clone_flags, p)))
                 goto bad_fork_cleanup_audit;
@@ -1117,10 +1105,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
                 goto bad_fork_cleanup_sighand;
         if ((retval = copy_mm(clone_flags, p)))
                 goto bad_fork_cleanup_signal;
-        if ((retval = copy_keys(clone_flags, p)))
-                goto bad_fork_cleanup_mm;
         if ((retval = copy_namespaces(clone_flags, p)))
-                goto bad_fork_cleanup_keys;
+                goto bad_fork_cleanup_mm;
         if ((retval = copy_io(clone_flags, p)))
                 goto bad_fork_cleanup_namespaces;
         retval = copy_thread(0, clone_flags, stack_start, stack_size, p, regs);
@@ -1289,8 +1275,6 @@ bad_fork_cleanup_io:
         put_io_context(p->io_context);
 bad_fork_cleanup_namespaces:
         exit_task_namespaces(p);
-bad_fork_cleanup_keys:
-        exit_keys(p);
 bad_fork_cleanup_mm:
         if (p->mm)
                 mmput(p->mm);
@@ -1306,8 +1290,6 @@ bad_fork_cleanup_semundo:
         exit_sem(p);
 bad_fork_cleanup_audit:
         audit_free(p);
-bad_fork_cleanup_security:
-        security_task_free(p);
 bad_fork_cleanup_policy:
 #ifdef CONFIG_NUMA
         mpol_put(p->mempolicy);
@@ -1320,9 +1302,9 @@ bad_fork_cleanup_cgroup:
 bad_fork_cleanup_put_domain:
         module_put(task_thread_info(p)->exec_domain->module);
 bad_fork_cleanup_count:
-        put_group_info(p->group_info);
-        atomic_dec(&p->user->processes);
-        free_uid(p->user);
+        atomic_dec(&p->cred->user->processes);
+        put_cred(p->real_cred);
+        put_cred(p->cred);
 bad_fork_free:
         free_task(p);
 fork_out:
@@ -1366,6 +1348,21 @@ long do_fork(unsigned long clone_flags,
         long nr;
 
         /*
+         * Do some preliminary argument and permissions checking before we
+         * actually start allocating stuff
+         */
+        if (clone_flags & CLONE_NEWUSER) {
+                if (clone_flags & CLONE_THREAD)
+                        return -EINVAL;
+                /* hopefully this check will go away when userns support is
+                 * complete
+                 */
+                if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SETUID) ||
+                                !capable(CAP_SETGID))
+                        return -EPERM;
+        }
+
+        /*
          * We hope to recycle these flags after 2.6.26
          */
         if (unlikely(clone_flags & CLONE_STOPPED)) {
@@ -1613,8 +1610,7 @@ asmlinkage long sys_unshare(unsigned long unshare_flags)
         err = -EINVAL;
         if (unshare_flags & ~(CLONE_THREAD|CLONE_FS|CLONE_NEWNS|CLONE_SIGHAND|
                                 CLONE_VM|CLONE_FILES|CLONE_SYSVSEM|
-                                CLONE_NEWUTS|CLONE_NEWIPC|CLONE_NEWUSER|
-                                CLONE_NEWNET))
+                                CLONE_NEWUTS|CLONE_NEWIPC|CLONE_NEWNET))
                 goto bad_unshare_out;
 
         /*
diff --git a/kernel/futex.c b/kernel/futex.c
index e10c5c8786a6..7c6cbabe52b3 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -92,11 +92,12 @@ struct futex_pi_state {
  * A futex_q has a woken state, just like tasks have TASK_RUNNING.
  * It is considered woken when plist_node_empty(&q->list) || q->lock_ptr == 0.
  * The order of wakup is always to make the first condition true, then
- * wake up q->waiters, then make the second condition true.
+ * wake up q->waiter, then make the second condition true.
  */
 struct futex_q {
         struct plist_node list;
-        wait_queue_head_t waiters;
+        /* There can only be a single waiter */
+        wait_queue_head_t waiter;
 
         /* Which hash list lock to use: */
         spinlock_t *lock_ptr;
@@ -405,13 +406,20 @@ static void free_pi_state(struct futex_pi_state *pi_state)
 static struct task_struct * futex_find_get_task(pid_t pid)
 {
         struct task_struct *p;
+        const struct cred *cred = current_cred(), *pcred;
 
         rcu_read_lock();
         p = find_task_by_vpid(pid);
-        if (!p || ((current->euid != p->euid) && (current->euid != p->uid)))
+        if (!p) {
                 p = ERR_PTR(-ESRCH);
-        else
-                get_task_struct(p);
+        } else {
+                pcred = __task_cred(p);
+                if (cred->euid != pcred->euid &&
+                    cred->euid != pcred->uid)
+                        p = ERR_PTR(-ESRCH);
+                else
+                        get_task_struct(p);
+        }
 
         rcu_read_unlock();
 
@@ -573,7 +581,7 @@ static void wake_futex(struct futex_q *q)
          * The lock in wake_up_all() is a crucial memory barrier after the
          * plist_del() and also before assigning to q->lock_ptr.
          */
-        wake_up_all(&q->waiters);
+        wake_up(&q->waiter);
         /*
          * The waiting task can free the futex_q as soon as this is written,
          * without taking any locks.  This must come last.
@@ -930,7 +938,7 @@ static inline struct futex_hash_bucket *queue_lock(struct futex_q *q)
 {
         struct futex_hash_bucket *hb;
 
-        init_waitqueue_head(&q->waiters);
+        init_waitqueue_head(&q->waiter);
 
         get_futex_key_refs(&q->key);
         hb = hash_futex(&q->key);
@@ -1142,12 +1150,13 @@ handle_fault:
  * In case we must use restart_block to restart a futex_wait,
  * we encode in the 'flags' shared capability
  */
-#define FLAGS_SHARED  1
+#define FLAGS_SHARED            0x01
+#define FLAGS_CLOCKRT           0x02
 
 static long futex_wait_restart(struct restart_block *restart);
 
 static int futex_wait(u32 __user *uaddr, int fshared,
-                      u32 val, ktime_t *abs_time, u32 bitset)
+                      u32 val, ktime_t *abs_time, u32 bitset, int clockrt)
 {
         struct task_struct *curr = current;
         DECLARE_WAITQUEUE(wait, curr);
@@ -1220,7 +1229,7 @@ static int futex_wait(u32 __user *uaddr, int fshared,
 
         /* add_wait_queue is the barrier after __set_current_state. */
         __set_current_state(TASK_INTERRUPTIBLE);
-        add_wait_queue(&q.waiters, &wait);
+        add_wait_queue(&q.waiter, &wait);
         /*
          * !plist_node_empty() is safe here without any lock.
          * q.lock_ptr != 0 is not safe, because of ordering against wakeup.
@@ -1233,8 +1242,10 @@ static int futex_wait(u32 __user *uaddr, int fshared,
                         slack = current->timer_slack_ns;
                         if (rt_task(current))
                                 slack = 0;
-                        hrtimer_init_on_stack(&t.timer, CLOCK_MONOTONIC,
-                                                HRTIMER_MODE_ABS);
+                        hrtimer_init_on_stack(&t.timer,
+                                              clockrt ? CLOCK_REALTIME :
+                                              CLOCK_MONOTONIC,
+                                              HRTIMER_MODE_ABS);
                         hrtimer_init_sleeper(&t, current);
                         hrtimer_set_expires_range_ns(&t.timer, *abs_time, slack);
 
@@ -1289,6 +1300,8 @@ static int futex_wait(u32 __user *uaddr, int fshared,
 
                 if (fshared)
                         restart->futex.flags |= FLAGS_SHARED;
+                if (clockrt)
+                        restart->futex.flags |= FLAGS_CLOCKRT;
                 return -ERESTART_RESTARTBLOCK;
         }
 
@@ -1312,7 +1325,8 @@ static long futex_wait_restart(struct restart_block *restart)
         if (restart->futex.flags & FLAGS_SHARED)
                 fshared = 1;
         return (long)futex_wait(uaddr, fshared, restart->futex.val, &t,
-                                restart->futex.bitset);
+                                restart->futex.bitset,
+                                restart->futex.flags & FLAGS_CLOCKRT);
 }
 
 
@@ -1558,12 +1572,11 @@ static int futex_lock_pi(u32 __user *uaddr, int fshared,
 
  uaddr_faulted:
         /*
-         * We have to r/w  *(int __user *)uaddr, but we can't modify it
-         * non-atomically.  Therefore, if get_user below is not
-         * enough, we need to handle the fault ourselves, while
-         * still holding the mmap_sem.
-         *
-         * ... and hb->lock. :-) --ANK
+         * We have to r/w  *(int __user *)uaddr, and we have to modify it
+         * atomically.  Therefore, if we continue to fault after get_user()
+         * below, we need to handle the fault ourselves, while still holding
+         * the mmap_sem.  This can occur if the uaddr is under contention as
+         * we have to drop the mmap_sem in order to call get_user().
          */
         queue_unlock(&q, hb);
 
@@ -1575,7 +1588,7 @@ static int futex_lock_pi(u32 __user *uaddr, int fshared,
         }
 
         ret = get_user(uval, uaddr);
-        if (!ret && (uval != -EFAULT))
+        if (!ret)
                 goto retry;
 
         if (to)
@@ -1669,12 +1682,11 @@ out:
 
 pi_faulted:
         /*
-         * We have to r/w  *(int __user *)uaddr, but we can't modify it
-         * non-atomically.  Therefore, if get_user below is not
-         * enough, we need to handle the fault ourselves, while
-         * still holding the mmap_sem.
-         *
-         * ... and hb->lock. --ANK
+         * We have to r/w  *(int __user *)uaddr, and we have to modify it
+         * atomically.  Therefore, if we continue to fault after get_user()
+         * below, we need to handle the fault ourselves, while still holding
+         * the mmap_sem.  This can occur if the uaddr is under contention as
+         * we have to drop the mmap_sem in order to call get_user().
          */
         spin_unlock(&hb->lock);
 
@@ -1687,7 +1699,7 @@ pi_faulted:
         }
 
         ret = get_user(uval, uaddr);
-        if (!ret && (uval != -EFAULT))
+        if (!ret)
                 goto retry;
 
         return ret;
@@ -1742,6 +1754,7 @@ sys_get_robust_list(int pid, struct robust_list_head __user * __user *head_ptr,
 {
         struct robust_list_head __user *head;
         unsigned long ret;
+        const struct cred *cred = current_cred(), *pcred;
 
         if (!futex_cmpxchg_enabled)
                 return -ENOSYS;
@@ -1757,8 +1770,10 @@ sys_get_robust_list(int pid, struct robust_list_head __user * __user *head_ptr,
                 if (!p)
                         goto err_unlock;
                 ret = -EPERM;
-                if ((current->euid != p->euid) && (current->euid != p->uid) &&
-                                !capable(CAP_SYS_PTRACE))
+                pcred = __task_cred(p);
+                if (cred->euid != pcred->euid &&
+                    cred->euid != pcred->uid &&
+                    !capable(CAP_SYS_PTRACE))
                         goto err_unlock;
                 head = p->robust_list;
                 rcu_read_unlock();
@@ -1905,18 +1920,22 @@ void exit_robust_list(struct task_struct *curr)
 long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
                 u32 __user *uaddr2, u32 val2, u32 val3)
 {
-        int ret = -ENOSYS;
+        int clockrt, ret = -ENOSYS;
         int cmd = op & FUTEX_CMD_MASK;
         int fshared = 0;
 
         if (!(op & FUTEX_PRIVATE_FLAG))
                 fshared = 1;
 
+        clockrt = op & FUTEX_CLOCK_REALTIME;
+        if (clockrt && cmd != FUTEX_WAIT_BITSET)
+                return -ENOSYS;
+
         switch (cmd) {
         case FUTEX_WAIT:
                 val3 = FUTEX_BITSET_MATCH_ANY;
         case FUTEX_WAIT_BITSET:
-                ret = futex_wait(uaddr, fshared, val, timeout, val3);
+                ret = futex_wait(uaddr, fshared, val, timeout, val3, clockrt);
                 break;
         case FUTEX_WAKE:
                 val3 = FUTEX_BITSET_MATCH_ANY;
diff --git a/kernel/futex_compat.c b/kernel/futex_compat.c
index 04ac3a9e42cf..d607a5b9ee29 100644
--- a/kernel/futex_compat.c
+++ b/kernel/futex_compat.c
@@ -135,6 +135,7 @@ compat_sys_get_robust_list(int pid, compat_uptr_t __user *head_ptr,
 {
         struct compat_robust_list_head __user *head;
         unsigned long ret;
+        const struct cred *cred = current_cred(), *pcred;
 
         if (!futex_cmpxchg_enabled)
                 return -ENOSYS;
@@ -150,8 +151,10 @@ compat_sys_get_robust_list(int pid, compat_uptr_t __user *head_ptr,
                 if (!p)
                         goto err_unlock;
                 ret = -EPERM;
-                if ((current->euid != p->euid) && (current->euid != p->uid) &&
-                                !capable(CAP_SYS_PTRACE))
+                pcred = __task_cred(p);
+                if (cred->euid != pcred->euid &&
+                    cred->euid != pcred->uid &&
+                    !capable(CAP_SYS_PTRACE))
                         goto err_unlock;
                 head = p->compat_robust_list;
                 read_unlock(&tasklist_lock);
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 47e63349d1b2..bda9cb924276 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -442,22 +442,6 @@ static inline void debug_hrtimer_activate(struct hrtimer *timer) { }
 static inline void debug_hrtimer_deactivate(struct hrtimer *timer) { }
 #endif
 
-/*
- * Check, whether the timer is on the callback pending list
- */
-static inline int hrtimer_cb_pending(const struct hrtimer *timer)
-{
-        return timer->state & HRTIMER_STATE_PENDING;
-}
-
-/*
- * Remove a timer from the callback pending list
- */
-static inline void hrtimer_remove_cb_pending(struct hrtimer *timer)
-{
-        list_del_init(&timer->cb_entry);
-}
-
 /* High resolution timer related functions */
 #ifdef CONFIG_HIGH_RES_TIMERS
 
@@ -651,6 +635,8 @@ static inline void hrtimer_init_timer_hres(struct hrtimer *timer)
 {
 }
 
+static void __run_hrtimer(struct hrtimer *timer);
+
 /*
  * When High resolution timers are active, try to reprogram. Note, that in case
  * the state has HRTIMER_STATE_CALLBACK set, no reprogramming and no expiry
@@ -661,31 +647,14 @@ static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
                                             struct hrtimer_clock_base *base)
 {
         if (base->cpu_base->hres_active && hrtimer_reprogram(timer, base)) {
-
-                /* Timer is expired, act upon the callback mode */
-                switch(timer->cb_mode) {
-                case HRTIMER_CB_IRQSAFE_PERCPU:
-                case HRTIMER_CB_IRQSAFE_UNLOCKED:
-                        /*
-                         * This is solely for the sched tick emulation with
-                         * dynamic tick support to ensure that we do not
-                         * restart the tick right on the edge and end up with
-                         * the tick timer in the softirq ! The calling site
-                         * takes care of this. Also used for hrtimer sleeper !
-                         */
-                        debug_hrtimer_deactivate(timer);
-                        return 1;
-                case HRTIMER_CB_SOFTIRQ:
-                        /*
-                         * Move everything else into the softirq pending list !
-                         */
-                        list_add_tail(&timer->cb_entry,
-                                      &base->cpu_base->cb_pending);
-                        timer->state = HRTIMER_STATE_PENDING;
-                        return 1;
-                default:
-                        BUG();
-                }
+                /*
+                 * XXX: recursion check?
+                 * hrtimer_forward() should round up with timer granularity
+                 * so that we never get into inf recursion here,
+                 * it doesn't do that though
+                 */
+                __run_hrtimer(timer);
+                return 1;
         }
         return 0;
 }
@@ -724,11 +693,6 @@ static int hrtimer_switch_to_hres(void)
         return 1;
 }
 
-static inline void hrtimer_raise_softirq(void)
-{
-        raise_softirq(HRTIMER_SOFTIRQ);
-}
-
 #else
 
 static inline int hrtimer_hres_active(void) { return 0; }
@@ -747,7 +711,6 @@ static inline int hrtimer_reprogram(struct hrtimer *timer,
 {
         return 0;
 }
-static inline void hrtimer_raise_softirq(void) { }
 
 #endif /* CONFIG_HIGH_RES_TIMERS */
 
@@ -890,10 +853,7 @@ static void __remove_hrtimer(struct hrtimer *timer,
                              struct hrtimer_clock_base *base,
                              unsigned long newstate, int reprogram)
 {
-        /* High res. callback list. NOP for !HIGHRES */
-        if (hrtimer_cb_pending(timer))
-                hrtimer_remove_cb_pending(timer);
-        else {
+        if (timer->state & HRTIMER_STATE_ENQUEUED) {
                 /*
                  * Remove the timer from the rbtree and replace the
                  * first entry pointer if necessary.
@@ -953,7 +913,7 @@ hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, unsigned long delta_n
 {
         struct hrtimer_clock_base *base, *new_base;
         unsigned long flags;
-        int ret, raise;
+        int ret;
 
         base = lock_hrtimer_base(timer, &flags);
 
@@ -988,26 +948,8 @@ hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, unsigned long delta_n
         enqueue_hrtimer(timer, new_base,
                         new_base->cpu_base == &__get_cpu_var(hrtimer_bases));
 
-        /*
-         * The timer may be expired and moved to the cb_pending
-         * list. We can not raise the softirq with base lock held due
-         * to a possible deadlock with runqueue lock.
-         */
-        raise = timer->state == HRTIMER_STATE_PENDING;
-
-        /*
-         * We use preempt_disable to prevent this task from migrating after
-         * setting up the softirq and raising it. Otherwise, if me migrate
-         * we will raise the softirq on the wrong CPU.
-         */
-        preempt_disable();
-
         unlock_hrtimer_base(timer, &flags);
 
-        if (raise)
-                hrtimer_raise_softirq();
-        preempt_enable();
-
         return ret;
 }
 EXPORT_SYMBOL_GPL(hrtimer_start_range_ns);
@@ -1192,75 +1134,6 @@ int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp)
 }
 EXPORT_SYMBOL_GPL(hrtimer_get_res);
 
-static void run_hrtimer_pending(struct hrtimer_cpu_base *cpu_base)
-{
-        spin_lock_irq(&cpu_base->lock);
-
-        while (!list_empty(&cpu_base->cb_pending)) {
-                enum hrtimer_restart (*fn)(struct hrtimer *);
-                struct hrtimer *timer;
-                int restart;
-                int emulate_hardirq_ctx = 0;
-
-                timer = list_entry(cpu_base->cb_pending.next,
-                                   struct hrtimer, cb_entry);
-
-                debug_hrtimer_deactivate(timer);
-                timer_stats_account_hrtimer(timer);
-
-                fn = timer->function;
-                /*
-                 * A timer might have been added to the cb_pending list
-                 * when it was migrated during a cpu-offline operation.
-                 * Emulate hardirq context for such timers.
-                 */
-                if (timer->cb_mode == HRTIMER_CB_IRQSAFE_PERCPU ||
-                    timer->cb_mode == HRTIMER_CB_IRQSAFE_UNLOCKED)
-                        emulate_hardirq_ctx = 1;
-
-                __remove_hrtimer(timer, timer->base, HRTIMER_STATE_CALLBACK, 0);
-                spin_unlock_irq(&cpu_base->lock);
-
-                if (unlikely(emulate_hardirq_ctx)) {
-                        local_irq_disable();
-                        restart = fn(timer);
-                        local_irq_enable();
-                } else
-                        restart = fn(timer);
-
-                spin_lock_irq(&cpu_base->lock);
-
-                timer->state &= ~HRTIMER_STATE_CALLBACK;
-                if (restart == HRTIMER_RESTART) {
-                        BUG_ON(hrtimer_active(timer));
-                        /*
-                         * Enqueue the timer, allow reprogramming of the event
-                         * device
-                         */
-                        enqueue_hrtimer(timer, timer->base, 1);
-                } else if (hrtimer_active(timer)) {
-                        /*
-                         * If the timer was rearmed on another CPU, reprogram
-                         * the event device.
-                         */
-                        struct hrtimer_clock_base *base = timer->base;
-
-                        if (base->first == &timer->node &&
-                            hrtimer_reprogram(timer, base)) {
-                                /*
-                                 * Timer is expired. Thus move it from tree to
-                                 * pending list again.
-                                 */
-                                __remove_hrtimer(timer, base,
-                                                 HRTIMER_STATE_PENDING, 0);
-                                list_add_tail(&timer->cb_entry,
-                                              &base->cpu_base->cb_pending);
-                        }
-                }
-        }
-        spin_unlock_irq(&cpu_base->lock);
-}
-
 static void __run_hrtimer(struct hrtimer *timer)
 {
         struct hrtimer_clock_base *base = timer->base;
@@ -1268,25 +1141,21 @@ static void __run_hrtimer(struct hrtimer *timer)
         enum hrtimer_restart (*fn)(struct hrtimer *);
         int restart;
 
+        WARN_ON(!irqs_disabled());
+
         debug_hrtimer_deactivate(timer);
         __remove_hrtimer(timer, base, HRTIMER_STATE_CALLBACK, 0);
         timer_stats_account_hrtimer(timer);
-
         fn = timer->function;
-        if (timer->cb_mode == HRTIMER_CB_IRQSAFE_PERCPU ||
-            timer->cb_mode == HRTIMER_CB_IRQSAFE_UNLOCKED) {
-                /*
-                 * Used for scheduler timers, avoid lock inversion with
-                 * rq->lock and tasklist_lock.
-                 *
-                 * These timers are required to deal with enqueue expiry
-                 * themselves and are not allowed to migrate.
-                 */
-                spin_unlock(&cpu_base->lock);
-                restart = fn(timer);
-                spin_lock(&cpu_base->lock);
-        } else
-                restart = fn(timer);
+
+        /*
+         * Because we run timers from hardirq context, there is no chance
+         * they get migrated to another cpu, therefore its safe to unlock
+         * the timer base.
+         */
+        spin_unlock(&cpu_base->lock);
+        restart = fn(timer);
+        spin_lock(&cpu_base->lock);
 
         /*
          * Note: We clear the CALLBACK bit after enqueue_hrtimer to avoid
@@ -1311,7 +1180,7 @@ void hrtimer_interrupt(struct clock_event_device *dev)
         struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
         struct hrtimer_clock_base *base;
         ktime_t expires_next, now;
-        int i, raise = 0;
+        int i;
 
         BUG_ON(!cpu_base->hres_active);
         cpu_base->nr_events++;
@@ -1360,16 +1229,6 @@ void hrtimer_interrupt(struct clock_event_device *dev)
                                 break;
                         }
 
-                        /* Move softirq callbacks to the pending list */
-                        if (timer->cb_mode == HRTIMER_CB_SOFTIRQ) {
-                                __remove_hrtimer(timer, base,
-                                                 HRTIMER_STATE_PENDING, 0);
-                                list_add_tail(&timer->cb_entry,
-                                              &base->cpu_base->cb_pending);
-                                raise = 1;
-                                continue;
-                        }
-
                         __run_hrtimer(timer);
                 }
                 spin_unlock(&cpu_base->lock);
@@ -1383,10 +1242,6 @@ void hrtimer_interrupt(struct clock_event_device *dev)
                 if (tick_program_event(expires_next, 0))
                         goto retry;
         }
-
-        /* Raise softirq ? */
-        if (raise)
-                raise_softirq(HRTIMER_SOFTIRQ);
 }
 
 /**
@@ -1413,11 +1268,6 @@ void hrtimer_peek_ahead_timers(void)
         local_irq_restore(flags);
 }
 
-static void run_hrtimer_softirq(struct softirq_action *h)
-{
-        run_hrtimer_pending(&__get_cpu_var(hrtimer_bases));
-}
-
 #endif  /* CONFIG_HIGH_RES_TIMERS */
 
 /*
@@ -1429,8 +1279,6 @@ static void run_hrtimer_softirq(struct softirq_action *h)
  */
 void hrtimer_run_pending(void)
 {
-        struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
-
         if (hrtimer_hres_active())
                 return;
 
@@ -1444,8 +1292,6 @@ void hrtimer_run_pending(void)
          */
         if (tick_check_oneshot_change(!hrtimer_is_hres_enabled()))
                 hrtimer_switch_to_hres();
-
-        run_hrtimer_pending(cpu_base);
 }
 
 /*
@@ -1482,14 +1328,6 @@ void hrtimer_run_queues(void)
                                         hrtimer_get_expires_tv64(timer))
                                 break;
 
-                        if (timer->cb_mode == HRTIMER_CB_SOFTIRQ) {
-                                __remove_hrtimer(timer, base,
-                                        HRTIMER_STATE_PENDING, 0);
-                                list_add_tail(&timer->cb_entry,
-                                        &base->cpu_base->cb_pending);
-                                continue;
-                        }
-
                         __run_hrtimer(timer);
                 }
                 spin_unlock(&cpu_base->lock);
@@ -1516,9 +1354,6 @@ void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, struct task_struct *task)
 {
         sl->timer.function = hrtimer_wakeup;
         sl->task = task;
-#ifdef CONFIG_HIGH_RES_TIMERS
-        sl->timer.cb_mode = HRTIMER_CB_IRQSAFE_UNLOCKED;
-#endif
 }
 
 static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mode)
@@ -1655,18 +1490,16 @@ static void __cpuinit init_hrtimers_cpu(int cpu)
         for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++)
                 cpu_base->clock_base[i].cpu_base = cpu_base;
 
-        INIT_LIST_HEAD(&cpu_base->cb_pending);
         hrtimer_init_hres(cpu_base);
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
 
-static int migrate_hrtimer_list(struct hrtimer_clock_base *old_base,
-                                struct hrtimer_clock_base *new_base, int dcpu)
+static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base,
+                                struct hrtimer_clock_base *new_base)
 {
         struct hrtimer *timer;
         struct rb_node *node;
-        int raise = 0;
 
         while ((node = rb_first(&old_base->active))) {
                 timer = rb_entry(node, struct hrtimer, node);
@@ -1674,18 +1507,6 @@ static int migrate_hrtimer_list(struct hrtimer_clock_base *old_base,
                 debug_hrtimer_deactivate(timer);
 
                 /*
-                 * Should not happen. Per CPU timers should be
-                 * canceled _before_ the migration code is called
-                 */
-                if (timer->cb_mode == HRTIMER_CB_IRQSAFE_PERCPU) {
-                        __remove_hrtimer(timer, old_base,
-                                         HRTIMER_STATE_INACTIVE, 0);
-                        WARN(1, "hrtimer (%p %p)active but cpu %d dead\n",
-                             timer, timer->function, dcpu);
-                        continue;
-                }
-
-                /*
                  * Mark it as STATE_MIGRATE not INACTIVE otherwise the
                  * timer could be seen as !active and just vanish away
                  * under us on another CPU
@@ -1693,69 +1514,34 @@ static int migrate_hrtimer_list(struct hrtimer_clock_base *old_base,
                 __remove_hrtimer(timer, old_base, HRTIMER_STATE_MIGRATE, 0);
                 timer->base = new_base;
                 /*
-                 * Enqueue the timer. Allow reprogramming of the event device
+                 * Enqueue the timers on the new cpu, but do not reprogram 
+                 * the timer as that would enable a deadlock between
+                 * hrtimer_enqueue_reprogramm() running the timer and us still
+                 * holding a nested base lock.
+                 *
+                 * Instead we tickle the hrtimer interrupt after the migration
+                 * is done, which will run all expired timers and re-programm
+                 * the timer device.
                  */
-                enqueue_hrtimer(timer, new_base, 1);
+                enqueue_hrtimer(timer, new_base, 0);
 
-#ifdef CONFIG_HIGH_RES_TIMERS
-                /*
-                 * Happens with high res enabled when the timer was
-                 * already expired and the callback mode is
-                 * HRTIMER_CB_IRQSAFE_UNLOCKED (hrtimer_sleeper). The
-                 * enqueue code does not move them to the soft irq
-                 * pending list for performance/latency reasons, but
-                 * in the migration state, we need to do that
-                 * otherwise we end up with a stale timer.
-                 */
-                if (timer->state == HRTIMER_STATE_MIGRATE) {
-                        timer->state = HRTIMER_STATE_PENDING;
-                        list_add_tail(&timer->cb_entry,
-                                      &new_base->cpu_base->cb_pending);
-                        raise = 1;
-                }
-#endif
                 /* Clear the migration state bit */
                 timer->state &= ~HRTIMER_STATE_MIGRATE;
         }
-        return raise;
-}
-
-#ifdef CONFIG_HIGH_RES_TIMERS
-static int migrate_hrtimer_pending(struct hrtimer_cpu_base *old_base,
-                                   struct hrtimer_cpu_base *new_base)
-{
-        struct hrtimer *timer;
-        int raise = 0;
-
-        while (!list_empty(&old_base->cb_pending)) {
-                timer = list_entry(old_base->cb_pending.next,
-                                   struct hrtimer, cb_entry);
-
-                __remove_hrtimer(timer, timer->base, HRTIMER_STATE_PENDING, 0);
-                timer->base = &new_base->clock_base[timer->base->index];
-                list_add_tail(&timer->cb_entry, &new_base->cb_pending);
-                raise = 1;
-        }
-        return raise;
-}
-#else
-static int migrate_hrtimer_pending(struct hrtimer_cpu_base *old_base,
-                                   struct hrtimer_cpu_base *new_base)
-{
-        return 0;
 }
-#endif
 
-static void migrate_hrtimers(int cpu)
+static int migrate_hrtimers(int scpu)
 {
         struct hrtimer_cpu_base *old_base, *new_base;
-        int i, raise = 0;
+        int dcpu, i;
 
-        BUG_ON(cpu_online(cpu));
-        old_base = &per_cpu(hrtimer_bases, cpu);
+        BUG_ON(cpu_online(scpu));
+        old_base = &per_cpu(hrtimer_bases, scpu);
         new_base = &get_cpu_var(hrtimer_bases);
 
-        tick_cancel_sched_timer(cpu);
+        dcpu = smp_processor_id();
+
+        tick_cancel_sched_timer(scpu);
         /*
          * The caller is globally serialized and nobody else
          * takes two locks at once, deadlock is not possible.
@@ -1764,41 +1550,47 @@ static void migrate_hrtimers(int cpu)
         spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING);
 
         for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
-                if (migrate_hrtimer_list(&old_base->clock_base[i],
-                                         &new_base->clock_base[i], cpu))
-                        raise = 1;
+                migrate_hrtimer_list(&old_base->clock_base[i],
+                                     &new_base->clock_base[i]);
         }
 
-        if (migrate_hrtimer_pending(old_base, new_base))
-                raise = 1;
-
         spin_unlock(&old_base->lock);
         spin_unlock_irq(&new_base->lock);
         put_cpu_var(hrtimer_bases);
 
-        if (raise)
-                hrtimer_raise_softirq();
+        return dcpu;
+}
+
+static void tickle_timers(void *arg)
+{
+        hrtimer_peek_ahead_timers();
 }
+
 #endif /* CONFIG_HOTPLUG_CPU */
 
 static int __cpuinit hrtimer_cpu_notify(struct notifier_block *self,
                                         unsigned long action, void *hcpu)
 {
-        unsigned int cpu = (long)hcpu;
+        int scpu = (long)hcpu;
 
         switch (action) {
 
         case CPU_UP_PREPARE:
         case CPU_UP_PREPARE_FROZEN:
-                init_hrtimers_cpu(cpu);
+                init_hrtimers_cpu(scpu);
                 break;
 
 #ifdef CONFIG_HOTPLUG_CPU
         case CPU_DEAD:
         case CPU_DEAD_FROZEN:
-                clockevents_notify(CLOCK_EVT_NOTIFY_CPU_DEAD, &cpu);
-                migrate_hrtimers(cpu);
+        {
+                int dcpu;
+
+                clockevents_notify(CLOCK_EVT_NOTIFY_CPU_DEAD, &scpu);
+                dcpu = migrate_hrtimers(scpu);
+                smp_call_function_single(dcpu, tickle_timers, NULL, 0);
                 break;
+        }
 #endif
 
         default:
@@ -1817,9 +1609,6 @@ void __init hrtimers_init(void)
         hrtimer_cpu_notify(&hrtimers_nb, (unsigned long)CPU_UP_PREPARE,
                           (void *)(long)smp_processor_id());
         register_cpu_notifier(&hrtimers_nb);
-#ifdef CONFIG_HIGH_RES_TIMERS
-        open_softirq(HRTIMER_SOFTIRQ, run_hrtimer_softirq);
-#endif
 }
 
 /**
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index b343deedae91..f63c706d25e1 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -125,6 +125,7 @@ int set_irq_type(unsigned int irq, unsigned int type)
                 return -ENODEV;
         }
 
+        type &= IRQ_TYPE_SENSE_MASK;
         if (type == IRQ_TYPE_NONE)
                 return 0;
 
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index f1a23069c20a..6492400cb50d 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -422,11 +422,8 @@ out:
 }
 #endif
 
-
-#ifdef CONFIG_TRACE_IRQFLAGS
 void early_init_irq_lock_class(void)
 {
-#ifndef CONFIG_SPARSE_IRQ
         struct irq_desc *desc;
         int i;
 
@@ -436,9 +433,7 @@ void early_init_irq_lock_class(void)
 
                 lockdep_set_class(&desc->lock, &irq_desc_lock_class);
         }
-#endif
 }
-#endif
 
 #ifdef CONFIG_SPARSE_IRQ
 unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 10ad2f87ed9a..cd0cd8dcb345 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -16,8 +16,15 @@
 #include "internals.h"
 
 #ifdef CONFIG_SMP
+cpumask_var_t irq_default_affinity;
 
-cpumask_t irq_default_affinity = CPU_MASK_ALL;
+static int init_irq_default_affinity(void)
+{
+        alloc_cpumask_var(&irq_default_affinity, GFP_KERNEL);
+        cpumask_setall(irq_default_affinity);
+        return 0;
+}
+core_initcall(init_irq_default_affinity);
 
 /**
  *      synchronize_irq - wait for pending IRQ handlers (on other CPUs)
@@ -127,7 +134,7 @@ int do_irq_select_affinity(unsigned int irq, struct irq_desc *desc)
                         desc->status &= ~IRQ_AFFINITY_SET;
         }
 
-        cpumask_and(&desc->affinity, cpu_online_mask, &irq_default_affinity);
+        cpumask_and(&desc->affinity, cpu_online_mask, irq_default_affinity);
 set_affinity:
         desc->chip->set_affinity(irq, &desc->affinity);
 
@@ -368,16 +375,18 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
                 return 0;
         }
 
-        ret = chip->set_type(irq, flags & IRQF_TRIGGER_MASK);
+        /* caller masked out all except trigger mode flags */
+        ret = chip->set_type(irq, flags);
 
         if (ret)
                 pr_err("setting trigger mode %d for irq %u failed (%pF)\n",
-                                (int)(flags & IRQF_TRIGGER_MASK),
-                                irq, chip->set_type);
+                                (int)flags, irq, chip->set_type);
         else {
+                if (flags & (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH))
+                        flags |= IRQ_LEVEL;
                 /* note that IRQF_TRIGGER_MASK == IRQ_TYPE_SENSE_MASK */
-                desc->status &= ~IRQ_TYPE_SENSE_MASK;
-                desc->status |= flags & IRQ_TYPE_SENSE_MASK;
+                desc->status &= ~(IRQ_LEVEL | IRQ_TYPE_SENSE_MASK);
+                desc->status |= flags;
         }
 
         return ret;
@@ -457,7 +466,8 @@ __setup_irq(unsigned int irq, struct irq_desc * desc, struct irqaction *new)
 
                 /* Setup the type (level, edge polarity) if configured: */
                 if (new->flags & IRQF_TRIGGER_MASK) {
-                        ret = __irq_set_trigger(desc, irq, new->flags);
+                        ret = __irq_set_trigger(desc, irq,
+                                        new->flags & IRQF_TRIGGER_MASK);
 
                         if (ret) {
                                 spin_unlock_irqrestore(&desc->lock, flags);
@@ -671,6 +681,18 @@ int request_irq(unsigned int irq, irq_handler_t handler,
         struct irq_desc *desc;
         int retval;
 
+        /*
+         * handle_IRQ_event() always ignores IRQF_DISABLED except for
+         * the _first_ irqaction (sigh).  That can cause oopsing, but
+         * the behavior is classified as "will not fix" so we need to
+         * start nudging drivers away from using that idiom.
+         */
+        if ((irqflags & (IRQF_SHARED|IRQF_DISABLED))
+                        == (IRQF_SHARED|IRQF_DISABLED))
+                pr_warning("IRQ %d/%s: IRQF_DISABLED is not "
+                                "guaranteed on shared IRQs\n",
+                                irq, devname);
+
 #ifdef CONFIG_LOCKDEP
         /*
          * Lockdep wants atomic interrupt handlers:
diff --git a/kernel/irq/numa_migrate.c b/kernel/irq/numa_migrate.c
index 0178e2296990..089c3746358a 100644
--- a/kernel/irq/numa_migrate.c
+++ b/kernel/irq/numa_migrate.c
@@ -1,13 +1,8 @@
 /*
- * linux/kernel/irq/handle.c
- *
- * Copyright (C) 1992, 1998-2006 Linus Torvalds, Ingo Molnar
- * Copyright (C) 2005-2006, Thomas Gleixner, Russell King
- *
- * This file contains the core interrupt handling code.
- *
- * Detailed information is available in Documentation/DocBook/genericirq
+ * NUMA irq-desc migration code
  *
+ * Migrate IRQ data structures (irq_desc, chip_data, etc.) over to
+ * the new "home node" of the IRQ.
  */
 
 #include <linux/irq.h>
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index d2c0e5ee53c5..2abd3a7716ed 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -20,7 +20,7 @@ static struct proc_dir_entry *root_irq_dir;
 static int irq_affinity_proc_show(struct seq_file *m, void *v)
 {
         struct irq_desc *desc = irq_to_desc((long)m->private);
-        cpumask_t *mask = &desc->affinity;
+        const struct cpumask *mask = &desc->affinity;
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
         if (desc->status & IRQ_MOVE_PENDING)
@@ -93,7 +93,7 @@ static const struct file_operations irq_affinity_proc_fops = {
 
 static int default_affinity_show(struct seq_file *m, void *v)
 {
-        seq_cpumask(m, &irq_default_affinity);
+        seq_cpumask(m, irq_default_affinity);
         seq_putc(m, '\n');
         return 0;
 }
@@ -101,27 +101,37 @@ static int default_affinity_show(struct seq_file *m, void *v)
 static ssize_t default_affinity_write(struct file *file,
                 const char __user *buffer, size_t count, loff_t *ppos)
 {
-        cpumask_t new_value;
+        cpumask_var_t new_value;
         int err;
 
-        err = cpumask_parse_user(buffer, count, &new_value);
+        if (!alloc_cpumask_var(&new_value, GFP_KERNEL))
+                return -ENOMEM;
+
+        err = cpumask_parse_user(buffer, count, new_value);
         if (err)
-                return err;
+                goto out;
 
-        if (!is_affinity_mask_valid(new_value))
-                return -EINVAL;
+        if (!is_affinity_mask_valid(new_value)) {
+                err = -EINVAL;
+                goto out;
+        }
 
         /*
          * Do not allow disabling IRQs completely - it's a too easy
          * way to make the system unusable accidentally :-) At least
          * one online CPU still has to be targeted.
          */
-        if (!cpus_intersects(new_value, cpu_online_map))
-                return -EINVAL;
+        if (!cpumask_intersects(new_value, cpu_online_mask)) {
+                err = -EINVAL;
+                goto out;
+        }
 
-        irq_default_affinity = new_value;
+        cpumask_copy(irq_default_affinity, new_value);
+        err = count;
 
-        return count;
+out:
+        free_cpumask_var(new_value);
+        return err;
 }
 
 static int default_affinity_open(struct inode *inode, struct file *file)
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index 7b8b0f21a5b1..e694afa0eb8c 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -30,20 +30,19 @@
 #define all_var 0
 #endif
 
-/* These will be re-linked against their real values during the second link stage */
-extern const unsigned long kallsyms_addresses[] __attribute__((weak));
-extern const u8 kallsyms_names[] __attribute__((weak));
+extern const unsigned long kallsyms_addresses[];
+extern const u8 kallsyms_names[];
 
 /* tell the compiler that the count isn't in the small data section if the arch
  * has one (eg: FRV)
  */
 extern const unsigned long kallsyms_num_syms
-__attribute__((weak, section(".rodata")));
+        __attribute__((__section__(".rodata")));
 
-extern const u8 kallsyms_token_table[] __attribute__((weak));
-extern const u16 kallsyms_token_index[] __attribute__((weak));
+extern const u8 kallsyms_token_table[];
+extern const u16 kallsyms_token_index[];
 
-extern const unsigned long kallsyms_markers[] __attribute__((weak));
+extern const unsigned long kallsyms_markers[];
 
 static inline int is_kernel_inittext(unsigned long addr)
 {
@@ -168,9 +167,6 @@ static unsigned long get_symbol_pos(unsigned long addr,
         unsigned long symbol_start = 0, symbol_end = 0;
         unsigned long i, low, high, mid;
 
-        /* This kernel should never had been booted. */
-        BUG_ON(!kallsyms_addresses);
-
         /* do a binary search on the sorted kallsyms_addresses array */
         low = 0;
         high = kallsyms_num_syms;
diff --git a/kernel/kexec.c b/kernel/kexec.c
index ac0fde7b54d0..3fb855ad6aa0 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -1116,7 +1116,7 @@ void crash_save_cpu(struct pt_regs *regs, int cpu)
         struct elf_prstatus prstatus;
         u32 *buf;
 
-        if ((cpu < 0) || (cpu >= NR_CPUS))
+        if ((cpu < 0) || (cpu >= nr_cpu_ids))
                 return;
 
         /* Using ELF notes here is opportunistic.
diff --git a/kernel/kmod.c b/kernel/kmod.c
index 3d3c3ea3a023..b46dbb908669 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -118,10 +118,10 @@ EXPORT_SYMBOL(request_module);
 struct subprocess_info {
         struct work_struct work;
         struct completion *complete;
+        struct cred *cred;
         char *path;
         char **argv;
         char **envp;
-        struct key *ring;
         enum umh_wait wait;
         int retval;
         struct file *stdin;
@@ -134,19 +134,20 @@ struct subprocess_info {
 static int ____call_usermodehelper(void *data)
 {
         struct subprocess_info *sub_info = data;
-        struct key *new_session, *old_session;
         int retval;
 
-        /* Unblock all signals and set the session keyring. */
-        new_session = key_get(sub_info->ring);
+        BUG_ON(atomic_read(&sub_info->cred->usage) != 1);
+
+        /* Unblock all signals */
         spin_lock_irq(&current->sighand->siglock);
-        old_session = __install_session_keyring(current, new_session);
         flush_signal_handlers(current, 1);
         sigemptyset(&current->blocked);
         recalc_sigpending();
         spin_unlock_irq(&current->sighand->siglock);
 
-        key_put(old_session);
+        /* Install the credentials */
+        commit_creds(sub_info->cred);
+        sub_info->cred = NULL;
 
         /* Install input pipe when needed */
         if (sub_info->stdin) {
@@ -185,6 +186,8 @@ void call_usermodehelper_freeinfo(struct subprocess_info *info)
 {
         if (info->cleanup)
                 (*info->cleanup)(info->argv, info->envp);
+        if (info->cred)
+                put_cred(info->cred);
         kfree(info);
 }
 EXPORT_SYMBOL(call_usermodehelper_freeinfo);
@@ -240,6 +243,8 @@ static void __call_usermodehelper(struct work_struct *work)
         pid_t pid;
         enum umh_wait wait = sub_info->wait;
 
+        BUG_ON(atomic_read(&sub_info->cred->usage) != 1);
+
         /* CLONE_VFORK: wait until the usermode helper has execve'd
          * successfully We need the data structures to stay around
          * until that is done.  */
@@ -362,6 +367,9 @@ struct subprocess_info *call_usermodehelper_setup(char *path, char **argv,
         sub_info->path = path;
         sub_info->argv = argv;
         sub_info->envp = envp;
+        sub_info->cred = prepare_usermodehelper_creds();
+        if (!sub_info->cred)
+                return NULL;
 
   out:
         return sub_info;
@@ -376,7 +384,13 @@ EXPORT_SYMBOL(call_usermodehelper_setup);
 void call_usermodehelper_setkeys(struct subprocess_info *info,
                                  struct key *session_keyring)
 {
-        info->ring = session_keyring;
+#ifdef CONFIG_KEYS
+        struct thread_group_cred *tgcred = info->cred->tgcred;
+        key_put(tgcred->session_keyring);
+        tgcred->session_keyring = key_get(session_keyring);
+#else
+        BUG();
+#endif
 }
 EXPORT_SYMBOL(call_usermodehelper_setkeys);
 
@@ -444,6 +458,8 @@ int call_usermodehelper_exec(struct subprocess_info *sub_info,
         DECLARE_COMPLETION_ONSTACK(done);
         int retval = 0;
 
+        BUG_ON(atomic_read(&sub_info->cred->usage) != 1);
+
         helper_lock();
         if (sub_info->path[0] == '\0')
                 goto out;
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index c4c7df23f8c7..06b0c3568f0b 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -292,14 +292,12 @@ void lockdep_off(void)
 {
         current->lockdep_recursion++;
 }
-
 EXPORT_SYMBOL(lockdep_off);
 
 void lockdep_on(void)
 {
         current->lockdep_recursion--;
 }
-
 EXPORT_SYMBOL(lockdep_on);
 
 /*
@@ -581,7 +579,8 @@ static void print_lock_class_header(struct lock_class *class, int depth)
 /*
  * printk all lock dependencies starting at <entry>:
  */
-static void print_lock_dependencies(struct lock_class *class, int depth)
+static void __used
+print_lock_dependencies(struct lock_class *class, int depth)
 {
         struct lock_list *entry;
 
@@ -2513,7 +2512,6 @@ void lockdep_init_map(struct lockdep_map *lock, const char *name,
         if (subclass)
                 register_lock_class(lock, subclass, 1);
 }
-
 EXPORT_SYMBOL_GPL(lockdep_init_map);
 
 /*
@@ -2694,8 +2692,9 @@ static int check_unlock(struct task_struct *curr, struct lockdep_map *lock,
 }
 
 static int
-__lock_set_subclass(struct lockdep_map *lock,
-                    unsigned int subclass, unsigned long ip)
+__lock_set_class(struct lockdep_map *lock, const char *name,
+                 struct lock_class_key *key, unsigned int subclass,
+                 unsigned long ip)
 {
         struct task_struct *curr = current;
         struct held_lock *hlock, *prev_hlock;
@@ -2722,6 +2721,7 @@ __lock_set_subclass(struct lockdep_map *lock,
         return print_unlock_inbalance_bug(curr, lock, ip);
 
 found_it:
+        lockdep_init_map(lock, name, key, 0);
         class = register_lock_class(lock, subclass, 0);
         hlock->class_idx = class - lock_classes + 1;
 
@@ -2906,9 +2906,9 @@ static void check_flags(unsigned long flags)
 #endif
 }
 
-void
-lock_set_subclass(struct lockdep_map *lock,
-                  unsigned int subclass, unsigned long ip)
+void lock_set_class(struct lockdep_map *lock, const char *name,
+                    struct lock_class_key *key, unsigned int subclass,
+                    unsigned long ip)
 {
         unsigned long flags;
 
@@ -2918,13 +2918,12 @@ lock_set_subclass(struct lockdep_map *lock,
         raw_local_irq_save(flags);
         current->lockdep_recursion = 1;
         check_flags(flags);
-        if (__lock_set_subclass(lock, subclass, ip))
+        if (__lock_set_class(lock, name, key, subclass, ip))
                 check_chain_key(current);
         current->lockdep_recursion = 0;
         raw_local_irq_restore(flags);
 }
-
-EXPORT_SYMBOL_GPL(lock_set_subclass);
+EXPORT_SYMBOL_GPL(lock_set_class);
 
 /*
  * We are not always called with irqs disabled - do that here,
@@ -2948,7 +2947,6 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
         current->lockdep_recursion = 0;
         raw_local_irq_restore(flags);
 }
-
 EXPORT_SYMBOL_GPL(lock_acquire);
 
 void lock_release(struct lockdep_map *lock, int nested,
@@ -2966,7 +2964,6 @@ void lock_release(struct lockdep_map *lock, int nested,
         current->lockdep_recursion = 0;
         raw_local_irq_restore(flags);
 }
-
 EXPORT_SYMBOL_GPL(lock_release);
 
 #ifdef CONFIG_LOCK_STAT
@@ -3451,7 +3448,6 @@ retry:
         if (unlock)
                 read_unlock(&tasklist_lock);
 }
-
 EXPORT_SYMBOL_GPL(debug_show_all_locks);
 
 /*
@@ -3472,7 +3468,6 @@ void debug_show_held_locks(struct task_struct *task)
 {
                 __debug_show_held_locks(task);
 }
-
 EXPORT_SYMBOL_GPL(debug_show_held_locks);
 
 void lockdep_sys_exit(void)
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index 1d3ef29a2583..63598dca2d0c 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -80,12 +80,6 @@ static struct nsproxy *create_new_namespaces(unsigned long flags,
                 goto out_pid;
         }
 
-        new_nsp->user_ns = copy_user_ns(flags, tsk->nsproxy->user_ns);
-        if (IS_ERR(new_nsp->user_ns)) {
-                err = PTR_ERR(new_nsp->user_ns);
-                goto out_user;
-        }
-
         new_nsp->net_ns = copy_net_ns(flags, tsk->nsproxy->net_ns);
         if (IS_ERR(new_nsp->net_ns)) {
                 err = PTR_ERR(new_nsp->net_ns);
@@ -95,9 +89,6 @@ static struct nsproxy *create_new_namespaces(unsigned long flags,
         return new_nsp;
 
 out_net:
-        if (new_nsp->user_ns)
-                put_user_ns(new_nsp->user_ns);
-out_user:
         if (new_nsp->pid_ns)
                 put_pid_ns(new_nsp->pid_ns);
 out_pid:
@@ -130,7 +121,7 @@ int copy_namespaces(unsigned long flags, struct task_struct *tsk)
         get_nsproxy(old_ns);
 
         if (!(flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC |
-                                CLONE_NEWUSER | CLONE_NEWPID | CLONE_NEWNET)))
+                                CLONE_NEWPID | CLONE_NEWNET)))
                 return 0;
 
         if (!capable(CAP_SYS_ADMIN)) {
@@ -173,8 +164,6 @@ void free_nsproxy(struct nsproxy *ns)
                 put_ipc_ns(ns->ipc_ns);
         if (ns->pid_ns)
                 put_pid_ns(ns->pid_ns);
-        if (ns->user_ns)
-                put_user_ns(ns->user_ns);
         put_net(ns->net_ns);
         kmem_cache_free(nsproxy_cachep, ns);
 }
@@ -189,7 +178,7 @@ int unshare_nsproxy_namespaces(unsigned long unshare_flags,
         int err = 0;
 
         if (!(unshare_flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC |
-                               CLONE_NEWUSER | CLONE_NEWNET)))
+                               CLONE_NEWNET)))
                 return 0;
 
         if (!capable(CAP_SYS_ADMIN))
diff --git a/kernel/panic.c b/kernel/panic.c
index 4d5088355bfe..13f06349a786 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -21,6 +21,7 @@
 #include <linux/debug_locks.h>
 #include <linux/random.h>
 #include <linux/kallsyms.h>
+#include <linux/dmi.h>
 
 int panic_on_oops;
 static unsigned long tainted_mask;
@@ -321,36 +322,27 @@ void oops_exit(void)
 }
 
 #ifdef WANT_WARN_ON_SLOWPATH
-void warn_on_slowpath(const char *file, int line)
-{
-        char function[KSYM_SYMBOL_LEN];
-        unsigned long caller = (unsigned long) __builtin_return_address(0);
-        sprint_symbol(function, caller);
-
-        printk(KERN_WARNING "------------[ cut here ]------------\n");
-        printk(KERN_WARNING "WARNING: at %s:%d %s()\n", file,
-                line, function);
-        print_modules();
-        dump_stack();
-        print_oops_end_marker();
-        add_taint(TAINT_WARN);
-}
-EXPORT_SYMBOL(warn_on_slowpath);
-
-
 void warn_slowpath(const char *file, int line, const char *fmt, ...)
 {
         va_list args;
         char function[KSYM_SYMBOL_LEN];
         unsigned long caller = (unsigned long)__builtin_return_address(0);
+        const char *board;
+
         sprint_symbol(function, caller);
 
         printk(KERN_WARNING "------------[ cut here ]------------\n");
         printk(KERN_WARNING "WARNING: at %s:%d %s()\n", file,
                 line, function);
-        va_start(args, fmt);
-        vprintk(fmt, args);
-        va_end(args);
+        board = dmi_get_system_info(DMI_PRODUCT_NAME);
+        if (board)
+                printk(KERN_WARNING "Hardware name: %s\n", board);
+
+        if (fmt) {
+                va_start(args, fmt);
+                vprintk(fmt, args);
+                va_end(args);
+        }
 
         print_modules();
         dump_stack();
diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c
index 5e79c662294b..887c63787de6 100644
--- a/kernel/posix-timers.c
+++ b/kernel/posix-timers.c
@@ -116,7 +116,7 @@ static DEFINE_SPINLOCK(idr_lock);
  *          must supply functions here, even if the function just returns
  *          ENOSYS.  The standard POSIX timer management code assumes the
  *          following: 1.) The k_itimer struct (sched.h) is used for the
- *          timer.  2.) The list, it_lock, it_clock, it_id and it_process
+ *          timer.  2.) The list, it_lock, it_clock, it_id and it_pid
  *          fields are not modified by timer code.
  *
  *          At this time all functions EXCEPT clock_nanosleep can be
@@ -197,6 +197,11 @@ static int common_timer_create(struct k_itimer *new_timer)
         return 0;
 }
 
+static int no_timer_create(struct k_itimer *new_timer)
+{
+        return -EOPNOTSUPP;
+}
+
 /*
  * Return nonzero if we know a priori this clockid_t value is bogus.
  */
@@ -248,6 +253,7 @@ static __init int init_posix_timers(void)
                 .clock_getres = hrtimer_get_res,
                 .clock_get = posix_get_monotonic_raw,
                 .clock_set = do_posix_clock_nosettime,
+                .timer_create = no_timer_create,
         };
 
         register_posix_clock(CLOCK_REALTIME, &clock_realtime);
@@ -313,7 +319,8 @@ void do_schedule_next_timer(struct siginfo *info)
 
 int posix_timer_event(struct k_itimer *timr, int si_private)
 {
-        int shared, ret;
+        struct task_struct *task;
+        int shared, ret = -1;
         /*
          * FIXME: if ->sigq is queued we can race with
          * dequeue_signal()->do_schedule_next_timer().
@@ -327,8 +334,13 @@ int posix_timer_event(struct k_itimer *timr, int si_private)
          */
         timr->sigq->info.si_sys_private = si_private;
 
-        shared = !(timr->it_sigev_notify & SIGEV_THREAD_ID);
-        ret = send_sigqueue(timr->sigq, timr->it_process, shared);
+        rcu_read_lock();
+        task = pid_task(timr->it_pid, PIDTYPE_PID);
+        if (task) {
+                shared = !(timr->it_sigev_notify & SIGEV_THREAD_ID);
+                ret = send_sigqueue(timr->sigq, task, shared);
+        }
+        rcu_read_unlock();
         /* If we failed to send the signal the timer stops. */
         return ret > 0;
 }
@@ -405,7 +417,7 @@ static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer)
         return ret;
 }
 
-static struct task_struct * good_sigevent(sigevent_t * event)
+static struct pid *good_sigevent(sigevent_t * event)
 {
         struct task_struct *rtn = current->group_leader;
 
@@ -419,7 +431,7 @@ static struct task_struct * good_sigevent(sigevent_t * event)
             ((event->sigev_signo <= 0) || (event->sigev_signo > SIGRTMAX)))
                 return NULL;
 
-        return rtn;
+        return task_pid(rtn);
 }
 
 void register_posix_clock(const clockid_t clock_id, struct k_clock *new_clock)
@@ -458,6 +470,7 @@ static void release_posix_timer(struct k_itimer *tmr, int it_id_set)
                 idr_remove(&posix_timers_id, tmr->it_id);
                 spin_unlock_irqrestore(&idr_lock, flags);
         }
+        put_pid(tmr->it_pid);
         sigqueue_free(tmr->sigq);
         kmem_cache_free(posix_timers_cache, tmr);
 }
@@ -471,7 +484,6 @@ sys_timer_create(const clockid_t which_clock,
 {
         struct k_itimer *new_timer;
         int error, new_timer_id;
-        struct task_struct *process;
         sigevent_t event;
         int it_id_set = IT_ID_NOT_SET;
 
@@ -525,11 +537,9 @@ sys_timer_create(const clockid_t which_clock,
                         goto out;
                 }
                 rcu_read_lock();
-                process = good_sigevent(&event);
-                if (process)
-                        get_task_struct(process);
+                new_timer->it_pid = get_pid(good_sigevent(&event));
                 rcu_read_unlock();
-                if (!process) {
+                if (!new_timer->it_pid) {
                         error = -EINVAL;
                         goto out;
                 }
@@ -537,8 +547,7 @@ sys_timer_create(const clockid_t which_clock,
                 event.sigev_notify = SIGEV_SIGNAL;
                 event.sigev_signo = SIGALRM;
                 event.sigev_value.sival_int = new_timer->it_id;
-                process = current->group_leader;
-                get_task_struct(process);
+                new_timer->it_pid = get_pid(task_tgid(current));
         }
 
         new_timer->it_sigev_notify     = event.sigev_notify;
@@ -548,7 +557,7 @@ sys_timer_create(const clockid_t which_clock,
         new_timer->sigq->info.si_code  = SI_TIMER;
 
         spin_lock_irq(&current->sighand->siglock);
-        new_timer->it_process = process;
+        new_timer->it_signal = current->signal;
         list_add(&new_timer->list, &current->signal->posix_timers);
         spin_unlock_irq(&current->sighand->siglock);
 
@@ -583,8 +592,7 @@ static struct k_itimer *lock_timer(timer_t timer_id, unsigned long *flags)
         timr = idr_find(&posix_timers_id, (int)timer_id);
         if (timr) {
                 spin_lock(&timr->it_lock);
-                if (timr->it_process &&
-                    same_thread_group(timr->it_process, current)) {
+                if (timr->it_signal == current->signal) {
                         spin_unlock(&idr_lock);
                         return timr;
                 }
@@ -831,8 +839,7 @@ retry_delete:
          * This keeps any tasks waiting on the spin lock from thinking
          * they got something (see the lock code above).
          */
-        put_task_struct(timer->it_process);
-        timer->it_process = NULL;
+        timer->it_signal = NULL;
 
         unlock_timer(timer, flags);
         release_posix_timer(timer, IT_ID_SET);
@@ -858,8 +865,7 @@ retry_delete:
          * This keeps any tasks waiting on the spin lock from thinking
          * they got something (see the lock code above).
          */
-        put_task_struct(timer->it_process);
-        timer->it_process = NULL;
+        timer->it_signal = NULL;
 
         unlock_timer(timer, flags);
         release_posix_timer(timer, IT_ID_SET);
diff --git a/kernel/power/poweroff.c b/kernel/power/poweroff.c
index 72016f051477..97890831e1b5 100644
--- a/kernel/power/poweroff.c
+++ b/kernel/power/poweroff.c
@@ -27,7 +27,7 @@ static DECLARE_WORK(poweroff_work, do_poweroff);
 static void handle_poweroff(int key, struct tty_struct *tty)
 {
         /* run sysrq poweroff on boot cpu */
-        schedule_work_on(first_cpu(cpu_online_map), &poweroff_work);
+        schedule_work_on(cpumask_first(cpu_online_mask), &poweroff_work);
 }
 
 static struct sysrq_key_op      sysrq_poweroff_op = {
diff --git a/kernel/printk.c b/kernel/printk.c
index f492f1583d77..e651ab05655f 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -662,7 +662,7 @@ asmlinkage int vprintk(const char *fmt, va_list args)
         if (recursion_bug) {
                 recursion_bug = 0;
                 strcpy(printk_buf, recursion_bug_msg);
-                printed_len = sizeof(recursion_bug_msg);
+                printed_len = strlen(recursion_bug_msg);
         }
         /* Emit the output into the temporary buffer */
         printed_len += vscnprintf(printk_buf + printed_len,
diff --git a/kernel/profile.c b/kernel/profile.c
index 4cb7d68fed82..d18e2d2654f2 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -45,7 +45,7 @@ static unsigned long prof_len, prof_shift;
 int prof_on __read_mostly;
 EXPORT_SYMBOL_GPL(prof_on);
 
-static cpumask_t prof_cpu_mask = CPU_MASK_ALL;
+static cpumask_var_t prof_cpu_mask;
 #ifdef CONFIG_SMP
 static DEFINE_PER_CPU(struct profile_hit *[2], cpu_profile_hits);
 static DEFINE_PER_CPU(int, cpu_profile_flip);
@@ -113,9 +113,13 @@ int __ref profile_init(void)
         buffer_bytes = prof_len*sizeof(atomic_t);
         if (!slab_is_available()) {
                 prof_buffer = alloc_bootmem(buffer_bytes);
+                alloc_bootmem_cpumask_var(&prof_cpu_mask);
                 return 0;
         }
 
+        if (!alloc_cpumask_var(&prof_cpu_mask, GFP_KERNEL))
+                return -ENOMEM;
+
         prof_buffer = kzalloc(buffer_bytes, GFP_KERNEL);
         if (prof_buffer)
                 return 0;
@@ -128,6 +132,7 @@ int __ref profile_init(void)
         if (prof_buffer)
                 return 0;
 
+        free_cpumask_var(prof_cpu_mask);
         return -ENOMEM;
 }
 
@@ -386,13 +391,15 @@ out_free:
                 return NOTIFY_BAD;
         case CPU_ONLINE:
         case CPU_ONLINE_FROZEN:
-                cpu_set(cpu, prof_cpu_mask);
+                if (prof_cpu_mask != NULL)
+                        cpumask_set_cpu(cpu, prof_cpu_mask);
                 break;
         case CPU_UP_CANCELED:
         case CPU_UP_CANCELED_FROZEN:
         case CPU_DEAD:
         case CPU_DEAD_FROZEN:
-                cpu_clear(cpu, prof_cpu_mask);
+                if (prof_cpu_mask != NULL)
+                        cpumask_clear_cpu(cpu, prof_cpu_mask);
                 if (per_cpu(cpu_profile_hits, cpu)[0]) {
                         page = virt_to_page(per_cpu(cpu_profile_hits, cpu)[0]);
                         per_cpu(cpu_profile_hits, cpu)[0] = NULL;
@@ -430,7 +437,8 @@ void profile_tick(int type)
 
         if (type == CPU_PROFILING && timer_hook)
                 timer_hook(regs);
-        if (!user_mode(regs) && cpu_isset(smp_processor_id(), prof_cpu_mask))
+        if (!user_mode(regs) && prof_cpu_mask != NULL &&
+            cpumask_test_cpu(smp_processor_id(), prof_cpu_mask))
                 profile_hit(type, (void *)profile_pc(regs));
 }
 
@@ -442,7 +450,7 @@ void profile_tick(int type)
 static int prof_cpu_mask_read_proc(char *page, char **start, off_t off,
                         int count, int *eof, void *data)
 {
-        int len = cpumask_scnprintf(page, count, (cpumask_t *)data);
+        int len = cpumask_scnprintf(page, count, data);
         if (count - len < 2)
                 return -EINVAL;
         len += sprintf(page + len, "\n");
@@ -452,16 +460,20 @@ static int prof_cpu_mask_read_proc(char *page, char **start, off_t off,
 static int prof_cpu_mask_write_proc(struct file *file,
         const char __user *buffer,  unsigned long count, void *data)
 {
-        cpumask_t *mask = (cpumask_t *)data;
+        struct cpumask *mask = data;
         unsigned long full_count = count, err;
-        cpumask_t new_value;
+        cpumask_var_t new_value;
 
-        err = cpumask_parse_user(buffer, count, &new_value);
-        if (err)
-                return err;
+        if (!alloc_cpumask_var(&new_value, GFP_KERNEL))
+                return -ENOMEM;
 
-        *mask = new_value;
-        return full_count;
+        err = cpumask_parse_user(buffer, count, new_value);
+        if (!err) {
+                cpumask_copy(mask, new_value);
+                err = full_count;
+        }
+        free_cpumask_var(new_value);
+        return err;
 }
 
 void create_prof_cpu_mask(struct proc_dir_entry *root_irq_dir)
@@ -472,7 +484,7 @@ void create_prof_cpu_mask(struct proc_dir_entry *root_irq_dir)
         entry = create_proc_entry("prof_cpu_mask", 0600, root_irq_dir);
         if (!entry)
                 return;
-        entry->data = (void *)&prof_cpu_mask;
+        entry->data = prof_cpu_mask;
         entry->read_proc = prof_cpu_mask_read_proc;
         entry->write_proc = prof_cpu_mask_write_proc;
 }
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 4c8bcd7dd8e0..29dc700e198c 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -25,6 +25,17 @@
 #include <asm/pgtable.h>
 #include <asm/uaccess.h>
 
+
+/*
+ * Initialize a new task whose father had been ptraced.
+ *
+ * Called from copy_process().
+ */
+void ptrace_fork(struct task_struct *child, unsigned long clone_flags)
+{
+        arch_ptrace_fork(child, clone_flags);
+}
+
 /*
  * ptrace a task: make the debugger its new parent and
  * move it to the ptrace list.
@@ -72,6 +83,7 @@ void __ptrace_unlink(struct task_struct *child)
         child->parent = child->real_parent;
         list_del_init(&child->ptrace_entry);
 
+        arch_ptrace_untrace(child);
         if (task_is_traced(child))
                 ptrace_untrace(child);
 }
@@ -115,6 +127,8 @@ int ptrace_check_attach(struct task_struct *child, int kill)
 
 int __ptrace_may_access(struct task_struct *task, unsigned int mode)
 {
+        const struct cred *cred = current_cred(), *tcred;
+
         /* May we inspect the given task?
          * This check is used both for attaching with ptrace
          * and for allowing access to sensitive information in /proc.
@@ -127,13 +141,19 @@ int __ptrace_may_access(struct task_struct *task, unsigned int mode)
         /* Don't let security modules deny introspection */
         if (task == current)
                 return 0;
-        if (((current->uid != task->euid) ||
-             (current->uid != task->suid) ||
-             (current->uid != task->uid) ||
-             (current->gid != task->egid) ||
-             (current->gid != task->sgid) ||
-             (current->gid != task->gid)) && !capable(CAP_SYS_PTRACE))
+        rcu_read_lock();
+        tcred = __task_cred(task);
+        if ((cred->uid != tcred->euid ||
+             cred->uid != tcred->suid ||
+             cred->uid != tcred->uid  ||
+             cred->gid != tcred->egid ||
+             cred->gid != tcred->sgid ||
+             cred->gid != tcred->gid) &&
+            !capable(CAP_SYS_PTRACE)) {
+                rcu_read_unlock();
                 return -EPERM;
+        }
+        rcu_read_unlock();
         smp_rmb();
         if (task->mm)
                 dumpable = get_dumpable(task->mm);
@@ -163,6 +183,14 @@ int ptrace_attach(struct task_struct *task)
         if (same_thread_group(task, current))
                 goto out;
 
+        /* Protect exec's credential calculations against our interference;
+         * SUID, SGID and LSM creds get determined differently under ptrace.
+         */
+        retval = mutex_lock_interruptible(&current->cred_exec_mutex);
+        if (retval  < 0)
+                goto out;
+
+        retval = -EPERM;
 repeat:
         /*
          * Nasty, nasty.
@@ -202,6 +230,7 @@ repeat:
 bad:
         write_unlock_irqrestore(&tasklist_lock, flags);
         task_unlock(task);
+        mutex_unlock(&current->cred_exec_mutex);
 out:
         return retval;
 }
diff --git a/kernel/rcuclassic.c b/kernel/rcuclassic.c
index c03ca3e61919..6ec495f60ead 100644
--- a/kernel/rcuclassic.c
+++ b/kernel/rcuclassic.c
@@ -63,14 +63,14 @@ static struct rcu_ctrlblk rcu_ctrlblk = {
         .completed = -300,
         .pending = -300,
         .lock = __SPIN_LOCK_UNLOCKED(&rcu_ctrlblk.lock),
-        .cpumask = CPU_MASK_NONE,
+        .cpumask = CPU_BITS_NONE,
 };
 static struct rcu_ctrlblk rcu_bh_ctrlblk = {
         .cur = -300,
         .completed = -300,
         .pending = -300,
         .lock = __SPIN_LOCK_UNLOCKED(&rcu_bh_ctrlblk.lock),
-        .cpumask = CPU_MASK_NONE,
+        .cpumask = CPU_BITS_NONE,
 };
 
 DEFINE_PER_CPU(struct rcu_data, rcu_data) = { 0L };
@@ -85,7 +85,6 @@ static void force_quiescent_state(struct rcu_data *rdp,
                         struct rcu_ctrlblk *rcp)
 {
         int cpu;
-        cpumask_t cpumask;
         unsigned long flags;
 
         set_need_resched();
@@ -96,10 +95,10 @@ static void force_quiescent_state(struct rcu_data *rdp,
                  * Don't send IPI to itself. With irqs disabled,
                  * rdp->cpu is the current cpu.
                  *
-                 * cpu_online_map is updated by the _cpu_down()
+                 * cpu_online_mask is updated by the _cpu_down()
                  * using __stop_machine(). Since we're in irqs disabled
                  * section, __stop_machine() is not exectuting, hence
-                 * the cpu_online_map is stable.
+                 * the cpu_online_mask is stable.
                  *
                  * However,  a cpu might have been offlined _just_ before
                  * we disabled irqs while entering here.
@@ -107,13 +106,14 @@ static void force_quiescent_state(struct rcu_data *rdp,
                  * notification, leading to the offlined cpu's bit
                  * being set in the rcp->cpumask.
                  *
-                 * Hence cpumask = (rcp->cpumask & cpu_online_map) to prevent
+                 * Hence cpumask = (rcp->cpumask & cpu_online_mask) to prevent
                  * sending smp_reschedule() to an offlined CPU.
                  */
-                cpus_and(cpumask, rcp->cpumask, cpu_online_map);
-                cpu_clear(rdp->cpu, cpumask);
-                for_each_cpu_mask_nr(cpu, cpumask)
-                        smp_send_reschedule(cpu);
+                for_each_cpu_and(cpu,
+                                  to_cpumask(rcp->cpumask), cpu_online_mask) {
+                        if (cpu != rdp->cpu)
+                                smp_send_reschedule(cpu);
+                }
         }
         spin_unlock_irqrestore(&rcp->lock, flags);
 }
@@ -193,7 +193,7 @@ static void print_other_cpu_stall(struct rcu_ctrlblk *rcp)
 
         printk(KERN_ERR "INFO: RCU detected CPU stalls:");
         for_each_possible_cpu(cpu) {
-                if (cpu_isset(cpu, rcp->cpumask))
+                if (cpumask_test_cpu(cpu, to_cpumask(rcp->cpumask)))
                         printk(" %d", cpu);
         }
         printk(" (detected by %d, t=%ld jiffies)\n",
@@ -221,7 +221,8 @@ static void check_cpu_stall(struct rcu_ctrlblk *rcp)
         long delta;
 
         delta = jiffies - rcp->jiffies_stall;
-        if (cpu_isset(smp_processor_id(), rcp->cpumask) && delta >= 0) {
+        if (cpumask_test_cpu(smp_processor_id(), to_cpumask(rcp->cpumask)) &&
+                delta >= 0) {
 
                 /* We haven't checked in, so go dump stack. */
                 print_cpu_stall(rcp);
@@ -406,8 +407,8 @@ static void rcu_start_batch(struct rcu_ctrlblk *rcp)
  */
 static void cpu_quiet(int cpu, struct rcu_ctrlblk *rcp)
 {
-        cpu_clear(cpu, rcp->cpumask);
-        if (cpus_empty(rcp->cpumask)) {
+        cpumask_clear_cpu(cpu, to_cpumask(rcp->cpumask));
+        if (cpumask_empty(to_cpumask(rcp->cpumask))) {
                 /* batch completed ! */
                 rcp->completed = rcp->cur;
                 rcu_start_batch(rcp);
diff --git a/kernel/rcupreempt.c b/kernel/rcupreempt.c
index 59236e8b9daa..f9dc8f3720f6 100644
--- a/kernel/rcupreempt.c
+++ b/kernel/rcupreempt.c
@@ -164,7 +164,8 @@ static char *rcu_try_flip_state_names[] =
         { "idle", "waitack", "waitzero", "waitmb" };
 #endif /* #ifdef CONFIG_RCU_TRACE */
 
-static cpumask_t rcu_cpu_online_map __read_mostly = CPU_MASK_NONE;
+static DECLARE_BITMAP(rcu_cpu_online_map, NR_CPUS) __read_mostly
+        = CPU_BITS_NONE;
 
 /*
  * Enum and per-CPU flag to determine when each CPU has seen
@@ -551,6 +552,16 @@ void rcu_irq_exit(void)
         }
 }
 
+void rcu_nmi_enter(void)
+{
+        rcu_irq_enter();
+}
+
+void rcu_nmi_exit(void)
+{
+        rcu_irq_exit();
+}
+
 static void dyntick_save_progress_counter(int cpu)
 {
         struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu);
@@ -748,7 +759,7 @@ rcu_try_flip_idle(void)
 
         /* Now ask each CPU for acknowledgement of the flip. */
 
-        for_each_cpu_mask_nr(cpu, rcu_cpu_online_map) {
+        for_each_cpu(cpu, to_cpumask(rcu_cpu_online_map)) {
                 per_cpu(rcu_flip_flag, cpu) = rcu_flipped;
                 dyntick_save_progress_counter(cpu);
         }
@@ -766,7 +777,7 @@ rcu_try_flip_waitack(void)
         int cpu;
 
         RCU_TRACE_ME(rcupreempt_trace_try_flip_a1);
-        for_each_cpu_mask_nr(cpu, rcu_cpu_online_map)
+        for_each_cpu(cpu, to_cpumask(rcu_cpu_online_map))
                 if (rcu_try_flip_waitack_needed(cpu) &&
                     per_cpu(rcu_flip_flag, cpu) != rcu_flip_seen) {
                         RCU_TRACE_ME(rcupreempt_trace_try_flip_ae1);
@@ -798,7 +809,7 @@ rcu_try_flip_waitzero(void)
         /* Check to see if the sum of the "last" counters is zero. */
 
         RCU_TRACE_ME(rcupreempt_trace_try_flip_z1);
-        for_each_cpu_mask_nr(cpu, rcu_cpu_online_map)
+        for_each_cpu(cpu, to_cpumask(rcu_cpu_online_map))
                 sum += RCU_DATA_CPU(cpu)->rcu_flipctr[lastidx];
         if (sum != 0) {
                 RCU_TRACE_ME(rcupreempt_trace_try_flip_ze1);
@@ -813,7 +824,7 @@ rcu_try_flip_waitzero(void)
         smp_mb();  /*  ^^^^^^^^^^^^ */
 
         /* Call for a memory barrier from each CPU. */
-        for_each_cpu_mask_nr(cpu, rcu_cpu_online_map) {
+        for_each_cpu(cpu, to_cpumask(rcu_cpu_online_map)) {
                 per_cpu(rcu_mb_flag, cpu) = rcu_mb_needed;
                 dyntick_save_progress_counter(cpu);
         }
@@ -833,7 +844,7 @@ rcu_try_flip_waitmb(void)
         int cpu;
 
         RCU_TRACE_ME(rcupreempt_trace_try_flip_m1);
-        for_each_cpu_mask_nr(cpu, rcu_cpu_online_map)
+        for_each_cpu(cpu, to_cpumask(rcu_cpu_online_map))
                 if (rcu_try_flip_waitmb_needed(cpu) &&
                     per_cpu(rcu_mb_flag, cpu) != rcu_mb_done) {
                         RCU_TRACE_ME(rcupreempt_trace_try_flip_me1);
@@ -1022,7 +1033,7 @@ void rcu_offline_cpu(int cpu)
         RCU_DATA_CPU(cpu)->rcu_flipctr[0] = 0;
         RCU_DATA_CPU(cpu)->rcu_flipctr[1] = 0;
 
-        cpu_clear(cpu, rcu_cpu_online_map);
+        cpumask_clear_cpu(cpu, to_cpumask(rcu_cpu_online_map));
 
         spin_unlock_irqrestore(&rcu_ctrlblk.fliplock, flags);
 
@@ -1062,7 +1073,7 @@ void __cpuinit rcu_online_cpu(int cpu)
         struct rcu_data *rdp;
 
         spin_lock_irqsave(&rcu_ctrlblk.fliplock, flags);
-        cpu_set(cpu, rcu_cpu_online_map);
+        cpumask_set_cpu(cpu, to_cpumask(rcu_cpu_online_map));
         spin_unlock_irqrestore(&rcu_ctrlblk.fliplock, flags);
 
         /*
@@ -1420,7 +1431,7 @@ void __init __rcu_init(void)
          * We don't need protection against CPU-Hotplug here
          * since
          * a) If a CPU comes online while we are iterating over the
-         *    cpu_online_map below, we would only end up making a
+         *    cpu_online_mask below, we would only end up making a
          *    duplicate call to rcu_online_cpu() which sets the corresponding
          *    CPU's mask in the rcu_cpu_online_map.
          *
diff --git a/kernel/rcupreempt_trace.c b/kernel/rcupreempt_trace.c
index 35c2d3360ecf..7c2665cac172 100644
--- a/kernel/rcupreempt_trace.c
+++ b/kernel/rcupreempt_trace.c
@@ -149,12 +149,12 @@ static void rcupreempt_trace_sum(struct rcupreempt_trace *sp)
                 sp->done_length += cp->done_length;
                 sp->done_add += cp->done_add;
                 sp->done_remove += cp->done_remove;
-                atomic_set(&sp->done_invoked, atomic_read(&cp->done_invoked));
+                atomic_add(atomic_read(&cp->done_invoked), &sp->done_invoked);
                 sp->rcu_check_callbacks += cp->rcu_check_callbacks;
-                atomic_set(&sp->rcu_try_flip_1,
-                           atomic_read(&cp->rcu_try_flip_1));
-                atomic_set(&sp->rcu_try_flip_e1,
-                           atomic_read(&cp->rcu_try_flip_e1));
+                atomic_add(atomic_read(&cp->rcu_try_flip_1),
+                           &sp->rcu_try_flip_1);
+                atomic_add(atomic_read(&cp->rcu_try_flip_e1),
+                           &sp->rcu_try_flip_e1);
                 sp->rcu_try_flip_i1 += cp->rcu_try_flip_i1;
                 sp->rcu_try_flip_ie1 += cp->rcu_try_flip_ie1;
                 sp->rcu_try_flip_g1 += cp->rcu_try_flip_g1;
diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c
index 85cb90588a55..3245b40952c6 100644
--- a/kernel/rcutorture.c
+++ b/kernel/rcutorture.c
@@ -39,6 +39,7 @@
 #include <linux/moduleparam.h>
 #include <linux/percpu.h>
 #include <linux/notifier.h>
+#include <linux/reboot.h>
 #include <linux/freezer.h>
 #include <linux/cpu.h>
 #include <linux/delay.h>
@@ -108,7 +109,6 @@ struct rcu_torture {
         int rtort_mbtest;
 };
 
-static int fullstop = 0;        /* stop generating callbacks at test end. */
 static LIST_HEAD(rcu_torture_freelist);
 static struct rcu_torture *rcu_torture_current = NULL;
 static long rcu_torture_current_version = 0;
@@ -136,6 +136,30 @@ static int stutter_pause_test = 0;
 #endif
 int rcutorture_runnable = RCUTORTURE_RUNNABLE_INIT;
 
+#define FULLSTOP_SIGNALED 1     /* Bail due to signal. */
+#define FULLSTOP_CLEANUP  2     /* Orderly shutdown. */
+static int fullstop;            /* stop generating callbacks at test end. */
+DEFINE_MUTEX(fullstop_mutex);   /* protect fullstop transitions and */
+                                /*  spawning of kthreads. */
+
+/*
+ * Detect and respond to a signal-based shutdown.
+ */
+static int
+rcutorture_shutdown_notify(struct notifier_block *unused1,
+                           unsigned long unused2, void *unused3)
+{
+        if (fullstop)
+                return NOTIFY_DONE;
+        if (signal_pending(current)) {
+                mutex_lock(&fullstop_mutex);
+                if (!ACCESS_ONCE(fullstop))
+                        fullstop = FULLSTOP_SIGNALED;
+                mutex_unlock(&fullstop_mutex);
+        }
+        return NOTIFY_DONE;
+}
+
 /*
  * Allocate an element from the rcu_tortures pool.
  */
@@ -199,11 +223,12 @@ rcu_random(struct rcu_random_state *rrsp)
 static void
 rcu_stutter_wait(void)
 {
-        while (stutter_pause_test || !rcutorture_runnable)
+        while ((stutter_pause_test || !rcutorture_runnable) && !fullstop) {
                 if (rcutorture_runnable)
                         schedule_timeout_interruptible(1);
                 else
                         schedule_timeout_interruptible(round_jiffies_relative(HZ));
+        }
 }
 
 /*
@@ -599,7 +624,7 @@ rcu_torture_writer(void *arg)
                 rcu_stutter_wait();
         } while (!kthread_should_stop() && !fullstop);
         VERBOSE_PRINTK_STRING("rcu_torture_writer task stopping");
-        while (!kthread_should_stop())
+        while (!kthread_should_stop() && fullstop != FULLSTOP_SIGNALED)
                 schedule_timeout_uninterruptible(1);
         return 0;
 }
@@ -624,7 +649,7 @@ rcu_torture_fakewriter(void *arg)
         } while (!kthread_should_stop() && !fullstop);
 
         VERBOSE_PRINTK_STRING("rcu_torture_fakewriter task stopping");
-        while (!kthread_should_stop())
+        while (!kthread_should_stop() && fullstop != FULLSTOP_SIGNALED)
                 schedule_timeout_uninterruptible(1);
         return 0;
 }
@@ -734,7 +759,7 @@ rcu_torture_reader(void *arg)
         VERBOSE_PRINTK_STRING("rcu_torture_reader task stopping");
         if (irqreader && cur_ops->irqcapable)
                 del_timer_sync(&t);
-        while (!kthread_should_stop())
+        while (!kthread_should_stop() && fullstop != FULLSTOP_SIGNALED)
                 schedule_timeout_uninterruptible(1);
         return 0;
 }
@@ -831,7 +856,7 @@ rcu_torture_stats(void *arg)
         do {
                 schedule_timeout_interruptible(stat_interval * HZ);
                 rcu_torture_stats_print();
-        } while (!kthread_should_stop());
+        } while (!kthread_should_stop() && !fullstop);
         VERBOSE_PRINTK_STRING("rcu_torture_stats task stopping");
         return 0;
 }
@@ -843,49 +868,52 @@ static int rcu_idle_cpu;	/* Force all torture tasks off this CPU */
  */
 static void rcu_torture_shuffle_tasks(void)
 {
-        cpumask_t tmp_mask;
+        cpumask_var_t tmp_mask;
         int i;
 
-        cpus_setall(tmp_mask);
+        if (!alloc_cpumask_var(&tmp_mask, GFP_KERNEL))
+                BUG();
+
+        cpumask_setall(tmp_mask);
         get_online_cpus();
 
         /* No point in shuffling if there is only one online CPU (ex: UP) */
-        if (num_online_cpus() == 1) {
-                put_online_cpus();
-                return;
-        }
+        if (num_online_cpus() == 1)
+                goto out;
 
         if (rcu_idle_cpu != -1)
-                cpu_clear(rcu_idle_cpu, tmp_mask);
+                cpumask_clear_cpu(rcu_idle_cpu, tmp_mask);
 
-        set_cpus_allowed_ptr(current, &tmp_mask);
+        set_cpus_allowed_ptr(current, tmp_mask);
 
         if (reader_tasks) {
                 for (i = 0; i < nrealreaders; i++)
                         if (reader_tasks[i])
                                 set_cpus_allowed_ptr(reader_tasks[i],
-                                                     &tmp_mask);
+                                                     tmp_mask);
         }
 
         if (fakewriter_tasks) {
                 for (i = 0; i < nfakewriters; i++)
                         if (fakewriter_tasks[i])
                                 set_cpus_allowed_ptr(fakewriter_tasks[i],
-                                                     &tmp_mask);
+                                                     tmp_mask);
         }
 
         if (writer_task)
-                set_cpus_allowed_ptr(writer_task, &tmp_mask);
+                set_cpus_allowed_ptr(writer_task, tmp_mask);
 
         if (stats_task)
-                set_cpus_allowed_ptr(stats_task, &tmp_mask);
+                set_cpus_allowed_ptr(stats_task, tmp_mask);
 
         if (rcu_idle_cpu == -1)
                 rcu_idle_cpu = num_online_cpus() - 1;
         else
                 rcu_idle_cpu--;
 
+out:
         put_online_cpus();
+        free_cpumask_var(tmp_mask);
 }
 
 /* Shuffle tasks across CPUs, with the intent of allowing each CPU in the
@@ -899,7 +927,7 @@ rcu_torture_shuffle(void *arg)
         do {
                 schedule_timeout_interruptible(shuffle_interval * HZ);
                 rcu_torture_shuffle_tasks();
-        } while (!kthread_should_stop());
+        } while (!kthread_should_stop() && !fullstop);
         VERBOSE_PRINTK_STRING("rcu_torture_shuffle task stopping");
         return 0;
 }
@@ -914,10 +942,10 @@ rcu_torture_stutter(void *arg)
         do {
                 schedule_timeout_interruptible(stutter * HZ);
                 stutter_pause_test = 1;
-                if (!kthread_should_stop())
+                if (!kthread_should_stop() && !fullstop)
                         schedule_timeout_interruptible(stutter * HZ);
                 stutter_pause_test = 0;
-        } while (!kthread_should_stop());
+        } while (!kthread_should_stop() && !fullstop);
         VERBOSE_PRINTK_STRING("rcu_torture_stutter task stopping");
         return 0;
 }
@@ -934,12 +962,27 @@ rcu_torture_print_module_parms(char *tag)
                 stutter, irqreader);
 }
 
+static struct notifier_block rcutorture_nb = {
+        .notifier_call = rcutorture_shutdown_notify,
+};
+
 static void
 rcu_torture_cleanup(void)
 {
         int i;
 
-        fullstop = 1;
+        mutex_lock(&fullstop_mutex);
+        if (!fullstop) {
+                /* If being signaled, let it happen, then exit. */
+                mutex_unlock(&fullstop_mutex);
+                schedule_timeout_interruptible(10 * HZ);
+                if (cur_ops->cb_barrier != NULL)
+                        cur_ops->cb_barrier();
+                return;
+        }
+        fullstop = FULLSTOP_CLEANUP;
+        mutex_unlock(&fullstop_mutex);
+        unregister_reboot_notifier(&rcutorture_nb);
         if (stutter_task) {
                 VERBOSE_PRINTK_STRING("Stopping rcu_torture_stutter task");
                 kthread_stop(stutter_task);
@@ -1015,6 +1058,8 @@ rcu_torture_init(void)
                 { &rcu_ops, &rcu_sync_ops, &rcu_bh_ops, &rcu_bh_sync_ops,
                   &srcu_ops, &sched_ops, &sched_ops_sync, };
 
+        mutex_lock(&fullstop_mutex);
+
         /* Process args and tell the world that the torturer is on the job. */
         for (i = 0; i < ARRAY_SIZE(torture_ops); i++) {
                 cur_ops = torture_ops[i];
@@ -1024,6 +1069,7 @@ rcu_torture_init(void)
         if (i == ARRAY_SIZE(torture_ops)) {
                 printk(KERN_ALERT "rcutorture: invalid torture type: \"%s\"\n",
                        torture_type);
+                mutex_unlock(&fullstop_mutex);
                 return (-EINVAL);
         }
         if (cur_ops->init)
@@ -1146,9 +1192,12 @@ rcu_torture_init(void)
                         goto unwind;
                 }
         }
+        register_reboot_notifier(&rcutorture_nb);
+        mutex_unlock(&fullstop_mutex);
         return 0;
 
 unwind:
+        mutex_unlock(&fullstop_mutex);
         rcu_torture_cleanup();
         return firsterr;
 }
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
new file mode 100644
index 000000000000..a342b032112c
--- /dev/null
+++ b/kernel/rcutree.c
@@ -0,0 +1,1535 @@
+/*
+ * Read-Copy Update mechanism for mutual exclusion
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program 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 General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright IBM Corporation, 2008
+ *
+ * Authors: Dipankar Sarma <dipankar@in.ibm.com>
+ *          Manfred Spraul <manfred@colorfullife.com>
+ *          Paul E. McKenney <paulmck@linux.vnet.ibm.com> Hierarchical version
+ *
+ * Based on the original work by Paul McKenney <paulmck@us.ibm.com>
+ * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen.
+ *
+ * For detailed explanation of Read-Copy Update mechanism see -
+ *      Documentation/RCU
+ */
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/spinlock.h>
+#include <linux/smp.h>
+#include <linux/rcupdate.h>
+#include <linux/interrupt.h>
+#include <linux/sched.h>
+#include <asm/atomic.h>
+#include <linux/bitops.h>
+#include <linux/module.h>
+#include <linux/completion.h>
+#include <linux/moduleparam.h>
+#include <linux/percpu.h>
+#include <linux/notifier.h>
+#include <linux/cpu.h>
+#include <linux/mutex.h>
+#include <linux/time.h>
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+static struct lock_class_key rcu_lock_key;
+struct lockdep_map rcu_lock_map =
+        STATIC_LOCKDEP_MAP_INIT("rcu_read_lock", &rcu_lock_key);
+EXPORT_SYMBOL_GPL(rcu_lock_map);
+#endif
+
+/* Data structures. */
+
+#define RCU_STATE_INITIALIZER(name) { \
+        .level = { &name.node[0] }, \
+        .levelcnt = { \
+                NUM_RCU_LVL_0,  /* root of hierarchy. */ \
+                NUM_RCU_LVL_1, \
+                NUM_RCU_LVL_2, \
+                NUM_RCU_LVL_3, /* == MAX_RCU_LVLS */ \
+        }, \
+        .signaled = RCU_SIGNAL_INIT, \
+        .gpnum = -300, \
+        .completed = -300, \
+        .onofflock = __SPIN_LOCK_UNLOCKED(&name.onofflock), \
+        .fqslock = __SPIN_LOCK_UNLOCKED(&name.fqslock), \
+        .n_force_qs = 0, \
+        .n_force_qs_ngp = 0, \
+}
+
+struct rcu_state rcu_state = RCU_STATE_INITIALIZER(rcu_state);
+DEFINE_PER_CPU(struct rcu_data, rcu_data);
+
+struct rcu_state rcu_bh_state = RCU_STATE_INITIALIZER(rcu_bh_state);
+DEFINE_PER_CPU(struct rcu_data, rcu_bh_data);
+
+#ifdef CONFIG_NO_HZ
+DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks);
+#endif /* #ifdef CONFIG_NO_HZ */
+
+static int blimit = 10;         /* Maximum callbacks per softirq. */
+static int qhimark = 10000;     /* If this many pending, ignore blimit. */
+static int qlowmark = 100;      /* Once only this many pending, use blimit. */
+
+static void force_quiescent_state(struct rcu_state *rsp, int relaxed);
+
+/*
+ * Return the number of RCU batches processed thus far for debug & stats.
+ */
+long rcu_batches_completed(void)
+{
+        return rcu_state.completed;
+}
+EXPORT_SYMBOL_GPL(rcu_batches_completed);
+
+/*
+ * Return the number of RCU BH batches processed thus far for debug & stats.
+ */
+long rcu_batches_completed_bh(void)
+{
+        return rcu_bh_state.completed;
+}
+EXPORT_SYMBOL_GPL(rcu_batches_completed_bh);
+
+/*
+ * Does the CPU have callbacks ready to be invoked?
+ */
+static int
+cpu_has_callbacks_ready_to_invoke(struct rcu_data *rdp)
+{
+        return &rdp->nxtlist != rdp->nxttail[RCU_DONE_TAIL];
+}
+
+/*
+ * Does the current CPU require a yet-as-unscheduled grace period?
+ */
+static int
+cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp)
+{
+        /* ACCESS_ONCE() because we are accessing outside of lock. */
+        return *rdp->nxttail[RCU_DONE_TAIL] &&
+               ACCESS_ONCE(rsp->completed) == ACCESS_ONCE(rsp->gpnum);
+}
+
+/*
+ * Return the root node of the specified rcu_state structure.
+ */
+static struct rcu_node *rcu_get_root(struct rcu_state *rsp)
+{
+        return &rsp->node[0];
+}
+
+#ifdef CONFIG_SMP
+
+/*
+ * If the specified CPU is offline, tell the caller that it is in
+ * a quiescent state.  Otherwise, whack it with a reschedule IPI.
+ * Grace periods can end up waiting on an offline CPU when that
+ * CPU is in the process of coming online -- it will be added to the
+ * rcu_node bitmasks before it actually makes it online.  The same thing
+ * can happen while a CPU is in the process of coming online.  Because this
+ * race is quite rare, we check for it after detecting that the grace
+ * period has been delayed rather than checking each and every CPU
+ * each and every time we start a new grace period.
+ */
+static int rcu_implicit_offline_qs(struct rcu_data *rdp)
+{
+        /*
+         * If the CPU is offline, it is in a quiescent state.  We can
+         * trust its state not to change because interrupts are disabled.
+         */
+        if (cpu_is_offline(rdp->cpu)) {
+                rdp->offline_fqs++;
+                return 1;
+        }
+
+        /* The CPU is online, so send it a reschedule IPI. */
+        if (rdp->cpu != smp_processor_id())
+                smp_send_reschedule(rdp->cpu);
+        else
+                set_need_resched();
+        rdp->resched_ipi++;
+        return 0;
+}
+
+#endif /* #ifdef CONFIG_SMP */
+
+#ifdef CONFIG_NO_HZ
+static DEFINE_RATELIMIT_STATE(rcu_rs, 10 * HZ, 5);
+
+/**
+ * rcu_enter_nohz - inform RCU that current CPU is entering nohz
+ *
+ * Enter nohz mode, in other words, -leave- the mode in which RCU
+ * read-side critical sections can occur.  (Though RCU read-side
+ * critical sections can occur in irq handlers in nohz mode, a possibility
+ * handled by rcu_irq_enter() and rcu_irq_exit()).
+ */
+void rcu_enter_nohz(void)
+{
+        unsigned long flags;
+        struct rcu_dynticks *rdtp;
+
+        smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */
+        local_irq_save(flags);
+        rdtp = &__get_cpu_var(rcu_dynticks);
+        rdtp->dynticks++;
+        rdtp->dynticks_nesting--;
+        WARN_ON_RATELIMIT(rdtp->dynticks & 0x1, &rcu_rs);
+        local_irq_restore(flags);
+}
+
+/*
+ * rcu_exit_nohz - inform RCU that current CPU is leaving nohz
+ *
+ * Exit nohz mode, in other words, -enter- the mode in which RCU
+ * read-side critical sections normally occur.
+ */
+void rcu_exit_nohz(void)
+{
+        unsigned long flags;
+        struct rcu_dynticks *rdtp;
+
+        local_irq_save(flags);
+        rdtp = &__get_cpu_var(rcu_dynticks);
+        rdtp->dynticks++;
+        rdtp->dynticks_nesting++;
+        WARN_ON_RATELIMIT(!(rdtp->dynticks & 0x1), &rcu_rs);
+        local_irq_restore(flags);
+        smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */
+}
+
+/**
+ * rcu_nmi_enter - inform RCU of entry to NMI context
+ *
+ * If the CPU was idle with dynamic ticks active, and there is no
+ * irq handler running, this updates rdtp->dynticks_nmi to let the
+ * RCU grace-period handling know that the CPU is active.
+ */
+void rcu_nmi_enter(void)
+{
+        struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks);
+
+        if (rdtp->dynticks & 0x1)
+                return;
+        rdtp->dynticks_nmi++;
+        WARN_ON_RATELIMIT(!(rdtp->dynticks_nmi & 0x1), &rcu_rs);
+        smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */
+}
+
+/**
+ * rcu_nmi_exit - inform RCU of exit from NMI context
+ *
+ * If the CPU was idle with dynamic ticks active, and there is no
+ * irq handler running, this updates rdtp->dynticks_nmi to let the
+ * RCU grace-period handling know that the CPU is no longer active.
+ */
+void rcu_nmi_exit(void)
+{
+        struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks);
+
+        if (rdtp->dynticks & 0x1)
+                return;
+        smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */
+        rdtp->dynticks_nmi++;
+        WARN_ON_RATELIMIT(rdtp->dynticks_nmi & 0x1, &rcu_rs);
+}
+
+/**
+ * rcu_irq_enter - inform RCU of entry to hard irq context
+ *
+ * If the CPU was idle with dynamic ticks active, this updates the
+ * rdtp->dynticks to let the RCU handling know that the CPU is active.
+ */
+void rcu_irq_enter(void)
+{
+        struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks);
+
+        if (rdtp->dynticks_nesting++)
+                return;
+        rdtp->dynticks++;
+        WARN_ON_RATELIMIT(!(rdtp->dynticks & 0x1), &rcu_rs);
+        smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */
+}
+
+/**
+ * rcu_irq_exit - inform RCU of exit from hard irq context
+ *
+ * If the CPU was idle with dynamic ticks active, update the rdp->dynticks
+ * to put let the RCU handling be aware that the CPU is going back to idle
+ * with no ticks.
+ */
+void rcu_irq_exit(void)
+{
+        struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks);
+
+        if (--rdtp->dynticks_nesting)
+                return;
+        smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */
+        rdtp->dynticks++;
+        WARN_ON_RATELIMIT(rdtp->dynticks & 0x1, &rcu_rs);
+
+        /* If the interrupt queued a callback, get out of dyntick mode. */
+        if (__get_cpu_var(rcu_data).nxtlist ||
+            __get_cpu_var(rcu_bh_data).nxtlist)
+                set_need_resched();
+}
+
+/*
+ * Record the specified "completed" value, which is later used to validate
+ * dynticks counter manipulations.  Specify "rsp->completed - 1" to
+ * unconditionally invalidate any future dynticks manipulations (which is
+ * useful at the beginning of a grace period).
+ */
+static void dyntick_record_completed(struct rcu_state *rsp, long comp)
+{
+        rsp->dynticks_completed = comp;
+}
+
+#ifdef CONFIG_SMP
+
+/*
+ * Recall the previously recorded value of the completion for dynticks.
+ */
+static long dyntick_recall_completed(struct rcu_state *rsp)
+{
+        return rsp->dynticks_completed;
+}
+
+/*
+ * Snapshot the specified CPU's dynticks counter so that we can later
+ * credit them with an implicit quiescent state.  Return 1 if this CPU
+ * is already in a quiescent state courtesy of dynticks idle mode.
+ */
+static int dyntick_save_progress_counter(struct rcu_data *rdp)
+{
+        int ret;
+        int snap;
+        int snap_nmi;
+
+        snap = rdp->dynticks->dynticks;
+        snap_nmi = rdp->dynticks->dynticks_nmi;
+        smp_mb();       /* Order sampling of snap with end of grace period. */
+        rdp->dynticks_snap = snap;
+        rdp->dynticks_nmi_snap = snap_nmi;
+        ret = ((snap & 0x1) == 0) && ((snap_nmi & 0x1) == 0);
+        if (ret)
+                rdp->dynticks_fqs++;
+        return ret;
+}
+
+/*
+ * Return true if the specified CPU has passed through a quiescent
+ * state by virtue of being in or having passed through an dynticks
+ * idle state since the last call to dyntick_save_progress_counter()
+ * for this same CPU.
+ */
+static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
+{
+        long curr;
+        long curr_nmi;
+        long snap;
+        long snap_nmi;
+
+        curr = rdp->dynticks->dynticks;
+        snap = rdp->dynticks_snap;
+        curr_nmi = rdp->dynticks->dynticks_nmi;
+        snap_nmi = rdp->dynticks_nmi_snap;
+        smp_mb(); /* force ordering with cpu entering/leaving dynticks. */
+
+        /*
+         * If the CPU passed through or entered a dynticks idle phase with
+         * no active irq/NMI handlers, then we can safely pretend that the CPU
+         * already acknowledged the request to pass through a quiescent
+         * state.  Either way, that CPU cannot possibly be in an RCU
+         * read-side critical section that started before the beginning
+         * of the current RCU grace period.
+         */
+        if ((curr != snap || (curr & 0x1) == 0) &&
+            (curr_nmi != snap_nmi || (curr_nmi & 0x1) == 0)) {
+                rdp->dynticks_fqs++;
+                return 1;
+        }
+
+        /* Go check for the CPU being offline. */
+        return rcu_implicit_offline_qs(rdp);
+}
+
+#endif /* #ifdef CONFIG_SMP */
+
+#else /* #ifdef CONFIG_NO_HZ */
+
+static void dyntick_record_completed(struct rcu_state *rsp, long comp)
+{
+}
+
+#ifdef CONFIG_SMP
+
+/*
+ * If there are no dynticks, then the only way that a CPU can passively
+ * be in a quiescent state is to be offline.  Unlike dynticks idle, which
+ * is a point in time during the prior (already finished) grace period,
+ * an offline CPU is always in a quiescent state, and thus can be
+ * unconditionally applied.  So just return the current value of completed.
+ */
+static long dyntick_recall_completed(struct rcu_state *rsp)
+{
+        return rsp->completed;
+}
+
+static int dyntick_save_progress_counter(struct rcu_data *rdp)
+{
+        return 0;
+}
+
+static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
+{
+        return rcu_implicit_offline_qs(rdp);
+}
+
+#endif /* #ifdef CONFIG_SMP */
+
+#endif /* #else #ifdef CONFIG_NO_HZ */
+
+#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
+
+static void record_gp_stall_check_time(struct rcu_state *rsp)
+{
+        rsp->gp_start = jiffies;
+        rsp->jiffies_stall = jiffies + RCU_SECONDS_TILL_STALL_CHECK;
+}
+
+static void print_other_cpu_stall(struct rcu_state *rsp)
+{
+        int cpu;
+        long delta;
+        unsigned long flags;
+        struct rcu_node *rnp = rcu_get_root(rsp);
+        struct rcu_node *rnp_cur = rsp->level[NUM_RCU_LVLS - 1];
+        struct rcu_node *rnp_end = &rsp->node[NUM_RCU_NODES];
+
+        /* Only let one CPU complain about others per time interval. */
+
+        spin_lock_irqsave(&rnp->lock, flags);
+        delta = jiffies - rsp->jiffies_stall;
+        if (delta < RCU_STALL_RAT_DELAY || rsp->gpnum == rsp->completed) {
+                spin_unlock_irqrestore(&rnp->lock, flags);
+                return;
+        }
+        rsp->jiffies_stall = jiffies + RCU_SECONDS_TILL_STALL_RECHECK;
+        spin_unlock_irqrestore(&rnp->lock, flags);
+
+        /* OK, time to rat on our buddy... */
+
+        printk(KERN_ERR "INFO: RCU detected CPU stalls:");
+        for (; rnp_cur < rnp_end; rnp_cur++) {
+                if (rnp_cur->qsmask == 0)
+                        continue;
+                for (cpu = 0; cpu <= rnp_cur->grphi - rnp_cur->grplo; cpu++)
+                        if (rnp_cur->qsmask & (1UL << cpu))
+                                printk(" %d", rnp_cur->grplo + cpu);
+        }
+        printk(" (detected by %d, t=%ld jiffies)\n",
+               smp_processor_id(), (long)(jiffies - rsp->gp_start));
+        force_quiescent_state(rsp, 0);  /* Kick them all. */
+}
+
+static void print_cpu_stall(struct rcu_state *rsp)
+{
+        unsigned long flags;
+        struct rcu_node *rnp = rcu_get_root(rsp);
+
+        printk(KERN_ERR "INFO: RCU detected CPU %d stall (t=%lu jiffies)\n",
+                        smp_processor_id(), jiffies - rsp->gp_start);
+        dump_stack();
+        spin_lock_irqsave(&rnp->lock, flags);
+        if ((long)(jiffies - rsp->jiffies_stall) >= 0)
+                rsp->jiffies_stall =
+                        jiffies + RCU_SECONDS_TILL_STALL_RECHECK;
+        spin_unlock_irqrestore(&rnp->lock, flags);
+        set_need_resched();  /* kick ourselves to get things going. */
+}
+
+static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
+{
+        long delta;
+        struct rcu_node *rnp;
+
+        delta = jiffies - rsp->jiffies_stall;
+        rnp = rdp->mynode;
+        if ((rnp->qsmask & rdp->grpmask) && delta >= 0) {
+
+                /* We haven't checked in, so go dump stack. */
+                print_cpu_stall(rsp);
+
+        } else if (rsp->gpnum != rsp->completed &&
+                   delta >= RCU_STALL_RAT_DELAY) {
+
+                /* They had two time units to dump stack, so complain. */
+                print_other_cpu_stall(rsp);
+        }
+}
+
+#else /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
+
+static void record_gp_stall_check_time(struct rcu_state *rsp)
+{
+}
+
+static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
+{
+}
+
+#endif /* #else #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
+
+/*
+ * Update CPU-local rcu_data state to record the newly noticed grace period.
+ * This is used both when we started the grace period and when we notice
+ * that someone else started the grace period.
+ */
+static void note_new_gpnum(struct rcu_state *rsp, struct rcu_data *rdp)
+{
+        rdp->qs_pending = 1;
+        rdp->passed_quiesc = 0;
+        rdp->gpnum = rsp->gpnum;
+        rdp->n_rcu_pending_force_qs = rdp->n_rcu_pending +
+                                      RCU_JIFFIES_TILL_FORCE_QS;
+}
+
+/*
+ * Did someone else start a new RCU grace period start since we last
+ * checked?  Update local state appropriately if so.  Must be called
+ * on the CPU corresponding to rdp.
+ */
+static int
+check_for_new_grace_period(struct rcu_state *rsp, struct rcu_data *rdp)
+{
+        unsigned long flags;
+        int ret = 0;
+
+        local_irq_save(flags);
+        if (rdp->gpnum != rsp->gpnum) {
+                note_new_gpnum(rsp, rdp);
+                ret = 1;
+        }
+        local_irq_restore(flags);
+        return ret;
+}
+
+/*
+ * Start a new RCU grace period if warranted, re-initializing the hierarchy
+ * in preparation for detecting the next grace period.  The caller must hold
+ * the root node's ->lock, which is released before return.  Hard irqs must
+ * be disabled.
+ */
+static void
+rcu_start_gp(struct rcu_state *rsp, unsigned long flags)
+        __releases(rcu_get_root(rsp)->lock)
+{
+        struct rcu_data *rdp = rsp->rda[smp_processor_id()];
+        struct rcu_node *rnp = rcu_get_root(rsp);
+        struct rcu_node *rnp_cur;
+        struct rcu_node *rnp_end;
+
+        if (!cpu_needs_another_gp(rsp, rdp)) {
+                spin_unlock_irqrestore(&rnp->lock, flags);
+                return;
+        }
+
+        /* Advance to a new grace period and initialize state. */
+        rsp->gpnum++;
+        rsp->signaled = RCU_GP_INIT; /* Hold off force_quiescent_state. */
+        rsp->jiffies_force_qs = jiffies + RCU_JIFFIES_TILL_FORCE_QS;
+        rdp->n_rcu_pending_force_qs = rdp->n_rcu_pending +
+                                      RCU_JIFFIES_TILL_FORCE_QS;
+        record_gp_stall_check_time(rsp);
+        dyntick_record_completed(rsp, rsp->completed - 1);
+        note_new_gpnum(rsp, rdp);
+
+        /*
+         * Because we are first, we know that all our callbacks will
+         * be covered by this upcoming grace period, even the ones
+         * that were registered arbitrarily recently.
+         */
+        rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
+        rdp->nxttail[RCU_WAIT_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
+
+        /* Special-case the common single-level case. */
+        if (NUM_RCU_NODES == 1) {
+                rnp->qsmask = rnp->qsmaskinit;
+                spin_unlock_irqrestore(&rnp->lock, flags);
+                return;
+        }
+
+        spin_unlock(&rnp->lock);  /* leave irqs disabled. */
+
+
+        /* Exclude any concurrent CPU-hotplug operations. */
+        spin_lock(&rsp->onofflock);  /* irqs already disabled. */
+
+        /*
+         * Set the quiescent-state-needed bits in all the non-leaf RCU
+         * nodes for all currently online CPUs.  This operation relies
+         * on the layout of the hierarchy within the rsp->node[] array.
+         * Note that other CPUs will access only the leaves of the
+         * hierarchy, which still indicate that no grace period is in
+         * progress.  In addition, we have excluded CPU-hotplug operations.
+         *
+         * We therefore do not need to hold any locks.  Any required
+         * memory barriers will be supplied by the locks guarding the
+         * leaf rcu_nodes in the hierarchy.
+         */
+
+        rnp_end = rsp->level[NUM_RCU_LVLS - 1];
+        for (rnp_cur = &rsp->node[0]; rnp_cur < rnp_end; rnp_cur++)
+                rnp_cur->qsmask = rnp_cur->qsmaskinit;
+
+        /*
+         * Now set up the leaf nodes.  Here we must be careful.  First,
+         * we need to hold the lock in order to exclude other CPUs, which
+         * might be contending for the leaf nodes' locks.  Second, as
+         * soon as we initialize a given leaf node, its CPUs might run
+         * up the rest of the hierarchy.  We must therefore acquire locks
+         * for each node that we touch during this stage.  (But we still
+         * are excluding CPU-hotplug operations.)
+         *
+         * Note that the grace period cannot complete until we finish
+         * the initialization process, as there will be at least one
+         * qsmask bit set in the root node until that time, namely the
+         * one corresponding to this CPU.
+         */
+        rnp_end = &rsp->node[NUM_RCU_NODES];
+        rnp_cur = rsp->level[NUM_RCU_LVLS - 1];
+        for (; rnp_cur < rnp_end; rnp_cur++) {
+                spin_lock(&rnp_cur->lock);      /* irqs already disabled. */
+                rnp_cur->qsmask = rnp_cur->qsmaskinit;
+                spin_unlock(&rnp_cur->lock);    /* irqs already disabled. */
+        }
+
+        rsp->signaled = RCU_SIGNAL_INIT; /* force_quiescent_state now OK. */
+        spin_unlock_irqrestore(&rsp->onofflock, flags);
+}
+
+/*
+ * Advance this CPU's callbacks, but only if the current grace period
+ * has ended.  This may be called only from the CPU to whom the rdp
+ * belongs.
+ */
+static void
+rcu_process_gp_end(struct rcu_state *rsp, struct rcu_data *rdp)
+{
+        long completed_snap;
+        unsigned long flags;
+
+        local_irq_save(flags);
+        completed_snap = ACCESS_ONCE(rsp->completed);  /* outside of lock. */
+
+        /* Did another grace period end? */
+        if (rdp->completed != completed_snap) {
+
+                /* Advance callbacks.  No harm if list empty. */
+                rdp->nxttail[RCU_DONE_TAIL] = rdp->nxttail[RCU_WAIT_TAIL];
+                rdp->nxttail[RCU_WAIT_TAIL] = rdp->nxttail[RCU_NEXT_READY_TAIL];
+                rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
+
+                /* Remember that we saw this grace-period completion. */
+                rdp->completed = completed_snap;
+        }
+        local_irq_restore(flags);
+}
+
+/*
+ * Similar to cpu_quiet(), for which it is a helper function.  Allows
+ * a group of CPUs to be quieted at one go, though all the CPUs in the
+ * group must be represented by the same leaf rcu_node structure.
+ * That structure's lock must be held upon entry, and it is released
+ * before return.
+ */
+static void
+cpu_quiet_msk(unsigned long mask, struct rcu_state *rsp, struct rcu_node *rnp,
+              unsigned long flags)
+        __releases(rnp->lock)
+{
+        /* Walk up the rcu_node hierarchy. */
+        for (;;) {
+                if (!(rnp->qsmask & mask)) {
+
+                        /* Our bit has already been cleared, so done. */
+                        spin_unlock_irqrestore(&rnp->lock, flags);
+                        return;
+                }
+                rnp->qsmask &= ~mask;
+                if (rnp->qsmask != 0) {
+
+                        /* Other bits still set at this level, so done. */
+                        spin_unlock_irqrestore(&rnp->lock, flags);
+                        return;
+                }
+                mask = rnp->grpmask;
+                if (rnp->parent == NULL) {
+
+                        /* No more levels.  Exit loop holding root lock. */
+
+                        break;
+                }
+                spin_unlock_irqrestore(&rnp->lock, flags);
+                rnp = rnp->parent;
+                spin_lock_irqsave(&rnp->lock, flags);
+        }
+
+        /*
+         * Get here if we are the last CPU to pass through a quiescent
+         * state for this grace period.  Clean up and let rcu_start_gp()
+         * start up the next grace period if one is needed.  Note that
+         * we still hold rnp->lock, as required by rcu_start_gp(), which
+         * will release it.
+         */
+        rsp->completed = rsp->gpnum;
+        rcu_process_gp_end(rsp, rsp->rda[smp_processor_id()]);
+        rcu_start_gp(rsp, flags);  /* releases rnp->lock. */
+}
+
+/*
+ * Record a quiescent state for the specified CPU, which must either be
+ * the current CPU or an offline CPU.  The lastcomp argument is used to
+ * make sure we are still in the grace period of interest.  We don't want
+ * to end the current grace period based on quiescent states detected in
+ * an earlier grace period!
+ */
+static void
+cpu_quiet(int cpu, struct rcu_state *rsp, struct rcu_data *rdp, long lastcomp)
+{
+        unsigned long flags;
+        unsigned long mask;
+        struct rcu_node *rnp;
+
+        rnp = rdp->mynode;
+        spin_lock_irqsave(&rnp->lock, flags);
+        if (lastcomp != ACCESS_ONCE(rsp->completed)) {
+
+                /*
+                 * Someone beat us to it for this grace period, so leave.
+                 * The race with GP start is resolved by the fact that we
+                 * hold the leaf rcu_node lock, so that the per-CPU bits
+                 * cannot yet be initialized -- so we would simply find our
+                 * CPU's bit already cleared in cpu_quiet_msk() if this race
+                 * occurred.
+                 */
+                rdp->passed_quiesc = 0; /* try again later! */
+                spin_unlock_irqrestore(&rnp->lock, flags);
+                return;
+        }
+        mask = rdp->grpmask;
+        if ((rnp->qsmask & mask) == 0) {
+                spin_unlock_irqrestore(&rnp->lock, flags);
+        } else {
+                rdp->qs_pending = 0;
+
+                /*
+                 * This GP can't end until cpu checks in, so all of our
+                 * callbacks can be processed during the next GP.
+                 */
+                rdp = rsp->rda[smp_processor_id()];
+                rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
+
+                cpu_quiet_msk(mask, rsp, rnp, flags); /* releases rnp->lock */
+        }
+}
+
+/*
+ * Check to see if there is a new grace period of which this CPU
+ * is not yet aware, and if so, set up local rcu_data state for it.
+ * Otherwise, see if this CPU has just passed through its first
+ * quiescent state for this grace period, and record that fact if so.
+ */
+static void
+rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp)
+{
+        /* If there is now a new grace period, record and return. */
+        if (check_for_new_grace_period(rsp, rdp))
+                return;
+
+        /*
+         * Does this CPU still need to do its part for current grace period?
+         * If no, return and let the other CPUs do their part as well.
+         */
+        if (!rdp->qs_pending)
+                return;
+
+        /*
+         * Was there a quiescent state since the beginning of the grace
+         * period? If no, then exit and wait for the next call.
+         */
+        if (!rdp->passed_quiesc)
+                return;
+
+        /* Tell RCU we are done (but cpu_quiet() will be the judge of that). */
+        cpu_quiet(rdp->cpu, rsp, rdp, rdp->passed_quiesc_completed);
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+
+/*
+ * Remove the outgoing CPU from the bitmasks in the rcu_node hierarchy
+ * and move all callbacks from the outgoing CPU to the current one.
+ */
+static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp)
+{
+        int i;
+        unsigned long flags;
+        long lastcomp;
+        unsigned long mask;
+        struct rcu_data *rdp = rsp->rda[cpu];
+        struct rcu_data *rdp_me;
+        struct rcu_node *rnp;
+
+        /* Exclude any attempts to start a new grace period. */
+        spin_lock_irqsave(&rsp->onofflock, flags);
+
+        /* Remove the outgoing CPU from the masks in the rcu_node hierarchy. */
+        rnp = rdp->mynode;
+        mask = rdp->grpmask;    /* rnp->grplo is constant. */
+        do {
+                spin_lock(&rnp->lock);          /* irqs already disabled. */
+                rnp->qsmaskinit &= ~mask;
+                if (rnp->qsmaskinit != 0) {
+                        spin_unlock(&rnp->lock); /* irqs already disabled. */
+                        break;
+                }
+                mask = rnp->grpmask;
+                spin_unlock(&rnp->lock);        /* irqs already disabled. */
+                rnp = rnp->parent;
+        } while (rnp != NULL);
+        lastcomp = rsp->completed;
+
+        spin_unlock(&rsp->onofflock);           /* irqs remain disabled. */
+
+        /* Being offline is a quiescent state, so go record it. */
+        cpu_quiet(cpu, rsp, rdp, lastcomp);
+
+        /*
+         * Move callbacks from the outgoing CPU to the running CPU.
+         * Note that the outgoing CPU is now quiscent, so it is now
+         * (uncharacteristically) safe to access it rcu_data structure.
+         * Note also that we must carefully retain the order of the
+         * outgoing CPU's callbacks in order for rcu_barrier() to work
+         * correctly.  Finally, note that we start all the callbacks
+         * afresh, even those that have passed through a grace period
+         * and are therefore ready to invoke.  The theory is that hotplug
+         * events are rare, and that if they are frequent enough to
+         * indefinitely delay callbacks, you have far worse things to
+         * be worrying about.
+         */
+        rdp_me = rsp->rda[smp_processor_id()];
+        if (rdp->nxtlist != NULL) {
+                *rdp_me->nxttail[RCU_NEXT_TAIL] = rdp->nxtlist;
+                rdp_me->nxttail[RCU_NEXT_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
+                rdp->nxtlist = NULL;
+                for (i = 0; i < RCU_NEXT_SIZE; i++)
+                        rdp->nxttail[i] = &rdp->nxtlist;
+                rdp_me->qlen += rdp->qlen;
+                rdp->qlen = 0;
+        }
+        local_irq_restore(flags);
+}
+
+/*
+ * Remove the specified CPU from the RCU hierarchy and move any pending
+ * callbacks that it might have to the current CPU.  This code assumes
+ * that at least one CPU in the system will remain running at all times.
+ * Any attempt to offline -all- CPUs is likely to strand RCU callbacks.
+ */
+static void rcu_offline_cpu(int cpu)
+{
+        __rcu_offline_cpu(cpu, &rcu_state);
+        __rcu_offline_cpu(cpu, &rcu_bh_state);
+}
+
+#else /* #ifdef CONFIG_HOTPLUG_CPU */
+
+static void rcu_offline_cpu(int cpu)
+{
+}
+
+#endif /* #else #ifdef CONFIG_HOTPLUG_CPU */
+
+/*
+ * Invoke any RCU callbacks that have made it to the end of their grace
+ * period.  Thottle as specified by rdp->blimit.
+ */
+static void rcu_do_batch(struct rcu_data *rdp)
+{
+        unsigned long flags;
+        struct rcu_head *next, *list, **tail;
+        int count;
+
+        /* If no callbacks are ready, just return.*/
+        if (!cpu_has_callbacks_ready_to_invoke(rdp))
+                return;
+
+        /*
+         * Extract the list of ready callbacks, disabling to prevent
+         * races with call_rcu() from interrupt handlers.
+         */
+        local_irq_save(flags);
+        list = rdp->nxtlist;
+        rdp->nxtlist = *rdp->nxttail[RCU_DONE_TAIL];
+        *rdp->nxttail[RCU_DONE_TAIL] = NULL;
+        tail = rdp->nxttail[RCU_DONE_TAIL];
+        for (count = RCU_NEXT_SIZE - 1; count >= 0; count--)
+                if (rdp->nxttail[count] == rdp->nxttail[RCU_DONE_TAIL])
+                        rdp->nxttail[count] = &rdp->nxtlist;
+        local_irq_restore(flags);
+
+        /* Invoke callbacks. */
+        count = 0;
+        while (list) {
+                next = list->next;
+                prefetch(next);
+                list->func(list);
+                list = next;
+                if (++count >= rdp->blimit)
+                        break;
+        }
+
+        local_irq_save(flags);
+
+        /* Update count, and requeue any remaining callbacks. */
+        rdp->qlen -= count;
+        if (list != NULL) {
+                *tail = rdp->nxtlist;
+                rdp->nxtlist = list;
+                for (count = 0; count < RCU_NEXT_SIZE; count++)
+                        if (&rdp->nxtlist == rdp->nxttail[count])
+                                rdp->nxttail[count] = tail;
+                        else
+                                break;
+        }
+
+        /* Reinstate batch limit if we have worked down the excess. */
+        if (rdp->blimit == LONG_MAX && rdp->qlen <= qlowmark)
+                rdp->blimit = blimit;
+
+        local_irq_restore(flags);
+
+        /* Re-raise the RCU softirq if there are callbacks remaining. */
+        if (cpu_has_callbacks_ready_to_invoke(rdp))
+                raise_softirq(RCU_SOFTIRQ);
+}
+
+/*
+ * Check to see if this CPU is in a non-context-switch quiescent state
+ * (user mode or idle loop for rcu, non-softirq execution for rcu_bh).
+ * Also schedule the RCU softirq handler.
+ *
+ * This function must be called with hardirqs disabled.  It is normally
+ * invoked from the scheduling-clock interrupt.  If rcu_pending returns
+ * false, there is no point in invoking rcu_check_callbacks().
+ */
+void rcu_check_callbacks(int cpu, int user)
+{
+        if (user ||
+            (idle_cpu(cpu) && !in_softirq() &&
+                                hardirq_count() <= (1 << HARDIRQ_SHIFT))) {
+
+                /*
+                 * Get here if this CPU took its interrupt from user
+                 * mode or from the idle loop, and if this is not a
+                 * nested interrupt.  In this case, the CPU is in
+                 * a quiescent state, so count it.
+                 *
+                 * No memory barrier is required here because both
+                 * rcu_qsctr_inc() and rcu_bh_qsctr_inc() reference
+                 * only CPU-local variables that other CPUs neither
+                 * access nor modify, at least not while the corresponding
+                 * CPU is online.
+                 */
+
+                rcu_qsctr_inc(cpu);
+                rcu_bh_qsctr_inc(cpu);
+
+        } else if (!in_softirq()) {
+
+                /*
+                 * Get here if this CPU did not take its interrupt from
+                 * softirq, in other words, if it is not interrupting
+                 * a rcu_bh read-side critical section.  This is an _bh
+                 * critical section, so count it.
+                 */
+
+                rcu_bh_qsctr_inc(cpu);
+        }
+        raise_softirq(RCU_SOFTIRQ);
+}
+
+#ifdef CONFIG_SMP
+
+/*
+ * Scan the leaf rcu_node structures, processing dyntick state for any that
+ * have not yet encountered a quiescent state, using the function specified.
+ * Returns 1 if the current grace period ends while scanning (possibly
+ * because we made it end).
+ */
+static int rcu_process_dyntick(struct rcu_state *rsp, long lastcomp,
+                               int (*f)(struct rcu_data *))
+{
+        unsigned long bit;
+        int cpu;
+        unsigned long flags;
+        unsigned long mask;
+        struct rcu_node *rnp_cur = rsp->level[NUM_RCU_LVLS - 1];
+        struct rcu_node *rnp_end = &rsp->node[NUM_RCU_NODES];
+
+        for (; rnp_cur < rnp_end; rnp_cur++) {
+                mask = 0;
+                spin_lock_irqsave(&rnp_cur->lock, flags);
+                if (rsp->completed != lastcomp) {
+                        spin_unlock_irqrestore(&rnp_cur->lock, flags);
+                        return 1;
+                }
+                if (rnp_cur->qsmask == 0) {
+                        spin_unlock_irqrestore(&rnp_cur->lock, flags);
+                        continue;
+                }
+                cpu = rnp_cur->grplo;
+                bit = 1;
+                for (; cpu <= rnp_cur->grphi; cpu++, bit <<= 1) {
+                        if ((rnp_cur->qsmask & bit) != 0 && f(rsp->rda[cpu]))
+                                mask |= bit;
+                }
+                if (mask != 0 && rsp->completed == lastcomp) {
+
+                        /* cpu_quiet_msk() releases rnp_cur->lock. */
+                        cpu_quiet_msk(mask, rsp, rnp_cur, flags);
+                        continue;
+                }
+                spin_unlock_irqrestore(&rnp_cur->lock, flags);
+        }
+        return 0;
+}
+
+/*
+ * Force quiescent states on reluctant CPUs, and also detect which
+ * CPUs are in dyntick-idle mode.
+ */
+static void force_quiescent_state(struct rcu_state *rsp, int relaxed)
+{
+        unsigned long flags;
+        long lastcomp;
+        struct rcu_data *rdp = rsp->rda[smp_processor_id()];
+        struct rcu_node *rnp = rcu_get_root(rsp);
+        u8 signaled;
+
+        if (ACCESS_ONCE(rsp->completed) == ACCESS_ONCE(rsp->gpnum))
+                return;  /* No grace period in progress, nothing to force. */
+        if (!spin_trylock_irqsave(&rsp->fqslock, flags)) {
+                rsp->n_force_qs_lh++; /* Inexact, can lose counts.  Tough! */
+                return; /* Someone else is already on the job. */
+        }
+        if (relaxed &&
+            (long)(rsp->jiffies_force_qs - jiffies) >= 0 &&
+            (rdp->n_rcu_pending_force_qs - rdp->n_rcu_pending) >= 0)
+                goto unlock_ret; /* no emergency and done recently. */
+        rsp->n_force_qs++;
+        spin_lock(&rnp->lock);
+        lastcomp = rsp->completed;
+        signaled = rsp->signaled;
+        rsp->jiffies_force_qs = jiffies + RCU_JIFFIES_TILL_FORCE_QS;
+        rdp->n_rcu_pending_force_qs = rdp->n_rcu_pending +
+                                      RCU_JIFFIES_TILL_FORCE_QS;
+        if (lastcomp == rsp->gpnum) {
+                rsp->n_force_qs_ngp++;
+                spin_unlock(&rnp->lock);
+                goto unlock_ret;  /* no GP in progress, time updated. */
+        }
+        spin_unlock(&rnp->lock);
+        switch (signaled) {
+        case RCU_GP_INIT:
+
+                break; /* grace period still initializing, ignore. */
+
+        case RCU_SAVE_DYNTICK:
+
+                if (RCU_SIGNAL_INIT != RCU_SAVE_DYNTICK)
+                        break; /* So gcc recognizes the dead code. */
+
+                /* Record dyntick-idle state. */
+                if (rcu_process_dyntick(rsp, lastcomp,
+                                        dyntick_save_progress_counter))
+                        goto unlock_ret;
+
+                /* Update state, record completion counter. */
+                spin_lock(&rnp->lock);
+                if (lastcomp == rsp->completed) {
+                        rsp->signaled = RCU_FORCE_QS;
+                        dyntick_record_completed(rsp, lastcomp);
+                }
+                spin_unlock(&rnp->lock);
+                break;
+
+        case RCU_FORCE_QS:
+
+                /* Check dyntick-idle state, send IPI to laggarts. */
+                if (rcu_process_dyntick(rsp, dyntick_recall_completed(rsp),
+                                        rcu_implicit_dynticks_qs))
+                        goto unlock_ret;
+
+                /* Leave state in case more forcing is required. */
+
+                break;
+        }
+unlock_ret:
+        spin_unlock_irqrestore(&rsp->fqslock, flags);
+}
+
+#else /* #ifdef CONFIG_SMP */
+
+static void force_quiescent_state(struct rcu_state *rsp, int relaxed)
+{
+        set_need_resched();
+}
+
+#endif /* #else #ifdef CONFIG_SMP */
+
+/*
+ * This does the RCU processing work from softirq context for the
+ * specified rcu_state and rcu_data structures.  This may be called
+ * only from the CPU to whom the rdp belongs.
+ */
+static void
+__rcu_process_callbacks(struct rcu_state *rsp, struct rcu_data *rdp)
+{
+        unsigned long flags;
+
+        /*
+         * If an RCU GP has gone long enough, go check for dyntick
+         * idle CPUs and, if needed, send resched IPIs.
+         */
+        if ((long)(ACCESS_ONCE(rsp->jiffies_force_qs) - jiffies) < 0 ||
+            (rdp->n_rcu_pending_force_qs - rdp->n_rcu_pending) < 0)
+                force_quiescent_state(rsp, 1);
+
+        /*
+         * Advance callbacks in response to end of earlier grace
+         * period that some other CPU ended.
+         */
+        rcu_process_gp_end(rsp, rdp);
+
+        /* Update RCU state based on any recent quiescent states. */
+        rcu_check_quiescent_state(rsp, rdp);
+
+        /* Does this CPU require a not-yet-started grace period? */
+        if (cpu_needs_another_gp(rsp, rdp)) {
+                spin_lock_irqsave(&rcu_get_root(rsp)->lock, flags);
+                rcu_start_gp(rsp, flags);  /* releases above lock */
+        }
+
+        /* If there are callbacks ready, invoke them. */
+        rcu_do_batch(rdp);
+}
+
+/*
+ * Do softirq processing for the current CPU.
+ */
+static void rcu_process_callbacks(struct softirq_action *unused)
+{
+        /*
+         * Memory references from any prior RCU read-side critical sections
+         * executed by the interrupted code must be seen before any RCU
+         * grace-period manipulations below.
+         */
+        smp_mb(); /* See above block comment. */
+
+        __rcu_process_callbacks(&rcu_state, &__get_cpu_var(rcu_data));
+        __rcu_process_callbacks(&rcu_bh_state, &__get_cpu_var(rcu_bh_data));
+
+        /*
+         * Memory references from any later RCU read-side critical sections
+         * executed by the interrupted code must be seen after any RCU
+         * grace-period manipulations above.
+         */
+        smp_mb(); /* See above block comment. */
+}
+
+static void
+__call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
+           struct rcu_state *rsp)
+{
+        unsigned long flags;
+        struct rcu_data *rdp;
+
+        head->func = func;
+        head->next = NULL;
+
+        smp_mb(); /* Ensure RCU update seen before callback registry. */
+
+        /*
+         * Opportunistically note grace-period endings and beginnings.
+         * Note that we might see a beginning right after we see an
+         * end, but never vice versa, since this CPU has to pass through
+         * a quiescent state betweentimes.
+         */
+        local_irq_save(flags);
+        rdp = rsp->rda[smp_processor_id()];
+        rcu_process_gp_end(rsp, rdp);
+        check_for_new_grace_period(rsp, rdp);
+
+        /* Add the callback to our list. */
+        *rdp->nxttail[RCU_NEXT_TAIL] = head;
+        rdp->nxttail[RCU_NEXT_TAIL] = &head->next;
+
+        /* Start a new grace period if one not already started. */
+        if (ACCESS_ONCE(rsp->completed) == ACCESS_ONCE(rsp->gpnum)) {
+                unsigned long nestflag;
+                struct rcu_node *rnp_root = rcu_get_root(rsp);
+
+                spin_lock_irqsave(&rnp_root->lock, nestflag);
+                rcu_start_gp(rsp, nestflag);  /* releases rnp_root->lock. */
+        }
+
+        /* Force the grace period if too many callbacks or too long waiting. */
+        if (unlikely(++rdp->qlen > qhimark)) {
+                rdp->blimit = LONG_MAX;
+                force_quiescent_state(rsp, 0);
+        } else if ((long)(ACCESS_ONCE(rsp->jiffies_force_qs) - jiffies) < 0 ||
+                   (rdp->n_rcu_pending_force_qs - rdp->n_rcu_pending) < 0)
+                force_quiescent_state(rsp, 1);
+        local_irq_restore(flags);
+}
+
+/*
+ * Queue an RCU callback for invocation after a grace period.
+ */
+void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
+{
+        __call_rcu(head, func, &rcu_state);
+}
+EXPORT_SYMBOL_GPL(call_rcu);
+
+/*
+ * Queue an RCU for invocation after a quicker grace period.
+ */
+void call_rcu_bh(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
+{
+        __call_rcu(head, func, &rcu_bh_state);
+}
+EXPORT_SYMBOL_GPL(call_rcu_bh);
+
+/*
+ * Check to see if there is any immediate RCU-related work to be done
+ * by the current CPU, for the specified type of RCU, returning 1 if so.
+ * The checks are in order of increasing expense: checks that can be
+ * carried out against CPU-local state are performed first.  However,
+ * we must check for CPU stalls first, else we might not get a chance.
+ */
+static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
+{
+        rdp->n_rcu_pending++;
+
+        /* Check for CPU stalls, if enabled. */
+        check_cpu_stall(rsp, rdp);
+
+        /* Is the RCU core waiting for a quiescent state from this CPU? */
+        if (rdp->qs_pending)
+                return 1;
+
+        /* Does this CPU have callbacks ready to invoke? */
+        if (cpu_has_callbacks_ready_to_invoke(rdp))
+                return 1;
+
+        /* Has RCU gone idle with this CPU needing another grace period? */
+        if (cpu_needs_another_gp(rsp, rdp))
+                return 1;
+
+        /* Has another RCU grace period completed?  */
+        if (ACCESS_ONCE(rsp->completed) != rdp->completed) /* outside of lock */
+                return 1;
+
+        /* Has a new RCU grace period started? */
+        if (ACCESS_ONCE(rsp->gpnum) != rdp->gpnum) /* outside of lock */
+                return 1;
+
+        /* Has an RCU GP gone long enough to send resched IPIs &c? */
+        if (ACCESS_ONCE(rsp->completed) != ACCESS_ONCE(rsp->gpnum) &&
+            ((long)(ACCESS_ONCE(rsp->jiffies_force_qs) - jiffies) < 0 ||
+             (rdp->n_rcu_pending_force_qs - rdp->n_rcu_pending) < 0))
+                return 1;
+
+        /* nothing to do */
+        return 0;
+}
+
+/*
+ * Check to see if there is any immediate RCU-related work to be done
+ * by the current CPU, returning 1 if so.  This function is part of the
+ * RCU implementation; it is -not- an exported member of the RCU API.
+ */
+int rcu_pending(int cpu)
+{
+        return __rcu_pending(&rcu_state, &per_cpu(rcu_data, cpu)) ||
+               __rcu_pending(&rcu_bh_state, &per_cpu(rcu_bh_data, cpu));
+}
+
+/*
+ * Check to see if any future RCU-related work will need to be done
+ * by the current CPU, even if none need be done immediately, returning
+ * 1 if so.  This function is part of the RCU implementation; it is -not-
+ * an exported member of the RCU API.
+ */
+int rcu_needs_cpu(int cpu)
+{
+        /* RCU callbacks either ready or pending? */
+        return per_cpu(rcu_data, cpu).nxtlist ||
+               per_cpu(rcu_bh_data, cpu).nxtlist;
+}
+
+/*
+ * Initialize a CPU's per-CPU RCU data.  We take this "scorched earth"
+ * approach so that we don't have to worry about how long the CPU has
+ * been gone, or whether it ever was online previously.  We do trust the
+ * ->mynode field, as it is constant for a given struct rcu_data and
+ * initialized during early boot.
+ *
+ * Note that only one online or offline event can be happening at a given
+ * time.  Note also that we can accept some slop in the rsp->completed
+ * access due to the fact that this CPU cannot possibly have any RCU
+ * callbacks in flight yet.
+ */
+static void
+rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
+{
+        unsigned long flags;
+        int i;
+        long lastcomp;
+        unsigned long mask;
+        struct rcu_data *rdp = rsp->rda[cpu];
+        struct rcu_node *rnp = rcu_get_root(rsp);
+
+        /* Set up local state, ensuring consistent view of global state. */
+        spin_lock_irqsave(&rnp->lock, flags);
+        lastcomp = rsp->completed;
+        rdp->completed = lastcomp;
+        rdp->gpnum = lastcomp;
+        rdp->passed_quiesc = 0;  /* We could be racing with new GP, */
+        rdp->qs_pending = 1;     /*  so set up to respond to current GP. */
+        rdp->beenonline = 1;     /* We have now been online. */
+        rdp->passed_quiesc_completed = lastcomp - 1;
+        rdp->grpmask = 1UL << (cpu - rdp->mynode->grplo);
+        rdp->nxtlist = NULL;
+        for (i = 0; i < RCU_NEXT_SIZE; i++)
+                rdp->nxttail[i] = &rdp->nxtlist;
+        rdp->qlen = 0;
+        rdp->blimit = blimit;
+#ifdef CONFIG_NO_HZ
+        rdp->dynticks = &per_cpu(rcu_dynticks, cpu);
+#endif /* #ifdef CONFIG_NO_HZ */
+        rdp->cpu = cpu;
+        spin_unlock(&rnp->lock);                /* irqs remain disabled. */
+
+        /*
+         * A new grace period might start here.  If so, we won't be part
+         * of it, but that is OK, as we are currently in a quiescent state.
+         */
+
+        /* Exclude any attempts to start a new GP on large systems. */
+        spin_lock(&rsp->onofflock);             /* irqs already disabled. */
+
+        /* Add CPU to rcu_node bitmasks. */
+        rnp = rdp->mynode;
+        mask = rdp->grpmask;
+        do {
+                /* Exclude any attempts to start a new GP on small systems. */
+                spin_lock(&rnp->lock);  /* irqs already disabled. */
+                rnp->qsmaskinit |= mask;
+                mask = rnp->grpmask;
+                spin_unlock(&rnp->lock); /* irqs already disabled. */
+                rnp = rnp->parent;
+        } while (rnp != NULL && !(rnp->qsmaskinit & mask));
+
+        spin_unlock(&rsp->onofflock);           /* irqs remain disabled. */
+
+        /*
+         * A new grace period might start here.  If so, we will be part of
+         * it, and its gpnum will be greater than ours, so we will
+         * participate.  It is also possible for the gpnum to have been
+         * incremented before this function was called, and the bitmasks
+         * to not be filled out until now, in which case we will also
+         * participate due to our gpnum being behind.
+         */
+
+        /* Since it is coming online, the CPU is in a quiescent state. */
+        cpu_quiet(cpu, rsp, rdp, lastcomp);
+        local_irq_restore(flags);
+}
+
+static void __cpuinit rcu_online_cpu(int cpu)
+{
+#ifdef CONFIG_NO_HZ
+        struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
+
+        rdtp->dynticks_nesting = 1;
+        rdtp->dynticks |= 1;    /* need consecutive #s even for hotplug. */
+        rdtp->dynticks_nmi = (rdtp->dynticks_nmi + 1) & ~0x1;
+#endif /* #ifdef CONFIG_NO_HZ */
+        rcu_init_percpu_data(cpu, &rcu_state);
+        rcu_init_percpu_data(cpu, &rcu_bh_state);
+        open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
+}
+
+/*
+ * Handle CPU online/offline notifcation events.
+ */
+static int __cpuinit rcu_cpu_notify(struct notifier_block *self,
+                                unsigned long action, void *hcpu)
+{
+        long cpu = (long)hcpu;
+
+        switch (action) {
+        case CPU_UP_PREPARE:
+        case CPU_UP_PREPARE_FROZEN:
+                rcu_online_cpu(cpu);
+                break;
+        case CPU_DEAD:
+        case CPU_DEAD_FROZEN:
+        case CPU_UP_CANCELED:
+        case CPU_UP_CANCELED_FROZEN:
+                rcu_offline_cpu(cpu);
+                break;
+        default:
+                break;
+        }
+        return NOTIFY_OK;
+}
+
+/*
+ * Compute the per-level fanout, either using the exact fanout specified
+ * or balancing the tree, depending on CONFIG_RCU_FANOUT_EXACT.
+ */
+#ifdef CONFIG_RCU_FANOUT_EXACT
+static void __init rcu_init_levelspread(struct rcu_state *rsp)
+{
+        int i;
+
+        for (i = NUM_RCU_LVLS - 1; i >= 0; i--)
+                rsp->levelspread[i] = CONFIG_RCU_FANOUT;
+}
+#else /* #ifdef CONFIG_RCU_FANOUT_EXACT */
+static void __init rcu_init_levelspread(struct rcu_state *rsp)
+{
+        int ccur;
+        int cprv;
+        int i;
+
+        cprv = NR_CPUS;
+        for (i = NUM_RCU_LVLS - 1; i >= 0; i--) {
+                ccur = rsp->levelcnt[i];
+                rsp->levelspread[i] = (cprv + ccur - 1) / ccur;
+                cprv = ccur;
+        }
+}
+#endif /* #else #ifdef CONFIG_RCU_FANOUT_EXACT */
+
+/*
+ * Helper function for rcu_init() that initializes one rcu_state structure.
+ */
+static void __init rcu_init_one(struct rcu_state *rsp)
+{
+        int cpustride = 1;
+        int i;
+        int j;
+        struct rcu_node *rnp;
+
+        /* Initialize the level-tracking arrays. */
+
+        for (i = 1; i < NUM_RCU_LVLS; i++)
+                rsp->level[i] = rsp->level[i - 1] + rsp->levelcnt[i - 1];
+        rcu_init_levelspread(rsp);
+
+        /* Initialize the elements themselves, starting from the leaves. */
+
+        for (i = NUM_RCU_LVLS - 1; i >= 0; i--) {
+                cpustride *= rsp->levelspread[i];
+                rnp = rsp->level[i];
+                for (j = 0; j < rsp->levelcnt[i]; j++, rnp++) {
+                        spin_lock_init(&rnp->lock);
+                        rnp->qsmask = 0;
+                        rnp->qsmaskinit = 0;
+                        rnp->grplo = j * cpustride;
+                        rnp->grphi = (j + 1) * cpustride - 1;
+                        if (rnp->grphi >= NR_CPUS)
+                                rnp->grphi = NR_CPUS - 1;
+                        if (i == 0) {
+                                rnp->grpnum = 0;
+                                rnp->grpmask = 0;
+                                rnp->parent = NULL;
+                        } else {
+                                rnp->grpnum = j % rsp->levelspread[i - 1];
+                                rnp->grpmask = 1UL << rnp->grpnum;
+                                rnp->parent = rsp->level[i - 1] +
+                                              j / rsp->levelspread[i - 1];
+                        }
+                        rnp->level = i;
+                }
+        }
+}
+
+/*
+ * Helper macro for __rcu_init().  To be used nowhere else!
+ * Assigns leaf node pointers into each CPU's rcu_data structure.
+ */
+#define RCU_DATA_PTR_INIT(rsp, rcu_data) \
+do { \
+        rnp = (rsp)->level[NUM_RCU_LVLS - 1]; \
+        j = 0; \
+        for_each_possible_cpu(i) { \
+                if (i > rnp[j].grphi) \
+                        j++; \
+                per_cpu(rcu_data, i).mynode = &rnp[j]; \
+                (rsp)->rda[i] = &per_cpu(rcu_data, i); \
+        } \
+} while (0)
+
+static struct notifier_block __cpuinitdata rcu_nb = {
+        .notifier_call  = rcu_cpu_notify,
+};
+
+void __init __rcu_init(void)
+{
+        int i;                  /* All used by RCU_DATA_PTR_INIT(). */
+        int j;
+        struct rcu_node *rnp;
+
+        printk(KERN_WARNING "Experimental hierarchical RCU implementation.\n");
+#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
+        printk(KERN_INFO "RCU-based detection of stalled CPUs is enabled.\n");
+#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
+        rcu_init_one(&rcu_state);
+        RCU_DATA_PTR_INIT(&rcu_state, rcu_data);
+        rcu_init_one(&rcu_bh_state);
+        RCU_DATA_PTR_INIT(&rcu_bh_state, rcu_bh_data);
+
+        for_each_online_cpu(i)
+                rcu_cpu_notify(&rcu_nb, CPU_UP_PREPARE, (void *)(long)i);
+        /* Register notifier for non-boot CPUs */
+        register_cpu_notifier(&rcu_nb);
+        printk(KERN_WARNING "Experimental hierarchical RCU init done.\n");
+}
+
+module_param(blimit, int, 0);
+module_param(qhimark, int, 0);
+module_param(qlowmark, int, 0);
diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c
new file mode 100644
index 000000000000..d6db3e837826
--- /dev/null
+++ b/kernel/rcutree_trace.c
@@ -0,0 +1,271 @@
+/*
+ * Read-Copy Update tracing for classic implementation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program 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 General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright IBM Corporation, 2008
+ *
+ * Papers:  http://www.rdrop.com/users/paulmck/RCU
+ *
+ * For detailed explanation of Read-Copy Update mechanism see -
+ *              Documentation/RCU
+ *
+ */
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/spinlock.h>
+#include <linux/smp.h>
+#include <linux/rcupdate.h>
+#include <linux/interrupt.h>
+#include <linux/sched.h>
+#include <asm/atomic.h>
+#include <linux/bitops.h>
+#include <linux/module.h>
+#include <linux/completion.h>
+#include <linux/moduleparam.h>
+#include <linux/percpu.h>
+#include <linux/notifier.h>
+#include <linux/cpu.h>
+#include <linux/mutex.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+
+static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp)
+{
+        if (!rdp->beenonline)
+                return;
+        seq_printf(m, "%3d%cc=%ld g=%ld pq=%d pqc=%ld qp=%d rpfq=%ld rp=%x",
+                   rdp->cpu,
+                   cpu_is_offline(rdp->cpu) ? '!' : ' ',
+                   rdp->completed, rdp->gpnum,
+                   rdp->passed_quiesc, rdp->passed_quiesc_completed,
+                   rdp->qs_pending,
+                   rdp->n_rcu_pending_force_qs - rdp->n_rcu_pending,
+                   (int)(rdp->n_rcu_pending & 0xffff));
+#ifdef CONFIG_NO_HZ
+        seq_printf(m, " dt=%d/%d dn=%d df=%lu",
+                   rdp->dynticks->dynticks,
+                   rdp->dynticks->dynticks_nesting,
+                   rdp->dynticks->dynticks_nmi,
+                   rdp->dynticks_fqs);
+#endif /* #ifdef CONFIG_NO_HZ */
+        seq_printf(m, " of=%lu ri=%lu", rdp->offline_fqs, rdp->resched_ipi);
+        seq_printf(m, " ql=%ld b=%ld\n", rdp->qlen, rdp->blimit);
+}
+
+#define PRINT_RCU_DATA(name, func, m) \
+        do { \
+                int _p_r_d_i; \
+                \
+                for_each_possible_cpu(_p_r_d_i) \
+                        func(m, &per_cpu(name, _p_r_d_i)); \
+        } while (0)
+
+static int show_rcudata(struct seq_file *m, void *unused)
+{
+        seq_puts(m, "rcu:\n");
+        PRINT_RCU_DATA(rcu_data, print_one_rcu_data, m);
+        seq_puts(m, "rcu_bh:\n");
+        PRINT_RCU_DATA(rcu_bh_data, print_one_rcu_data, m);
+        return 0;
+}
+
+static int rcudata_open(struct inode *inode, struct file *file)
+{
+        return single_open(file, show_rcudata, NULL);
+}
+
+static struct file_operations rcudata_fops = {
+        .owner = THIS_MODULE,
+        .open = rcudata_open,
+        .read = seq_read,
+        .llseek = seq_lseek,
+        .release = single_release,
+};
+
+static void print_one_rcu_data_csv(struct seq_file *m, struct rcu_data *rdp)
+{
+        if (!rdp->beenonline)
+                return;
+        seq_printf(m, "%d,%s,%ld,%ld,%d,%ld,%d,%ld,%ld",
+                   rdp->cpu,
+                   cpu_is_offline(rdp->cpu) ? "\"Y\"" : "\"N\"",
+                   rdp->completed, rdp->gpnum,
+                   rdp->passed_quiesc, rdp->passed_quiesc_completed,
+                   rdp->qs_pending,
+                   rdp->n_rcu_pending_force_qs - rdp->n_rcu_pending,
+                   rdp->n_rcu_pending);
+#ifdef CONFIG_NO_HZ
+        seq_printf(m, ",%d,%d,%d,%lu",
+                   rdp->dynticks->dynticks,
+                   rdp->dynticks->dynticks_nesting,
+                   rdp->dynticks->dynticks_nmi,
+                   rdp->dynticks_fqs);
+#endif /* #ifdef CONFIG_NO_HZ */
+        seq_printf(m, ",%lu,%lu", rdp->offline_fqs, rdp->resched_ipi);
+        seq_printf(m, ",%ld,%ld\n", rdp->qlen, rdp->blimit);
+}
+
+static int show_rcudata_csv(struct seq_file *m, void *unused)
+{
+        seq_puts(m, "\"CPU\",\"Online?\",\"c\",\"g\",\"pq\",\"pqc\",\"pq\",\"rpfq\",\"rp\",");
+#ifdef CONFIG_NO_HZ
+        seq_puts(m, "\"dt\",\"dt nesting\",\"dn\",\"df\",");
+#endif /* #ifdef CONFIG_NO_HZ */
+        seq_puts(m, "\"of\",\"ri\",\"ql\",\"b\"\n");
+        seq_puts(m, "\"rcu:\"\n");
+        PRINT_RCU_DATA(rcu_data, print_one_rcu_data_csv, m);
+        seq_puts(m, "\"rcu_bh:\"\n");
+        PRINT_RCU_DATA(rcu_bh_data, print_one_rcu_data_csv, m);
+        return 0;
+}
+
+static int rcudata_csv_open(struct inode *inode, struct file *file)
+{
+        return single_open(file, show_rcudata_csv, NULL);
+}
+
+static struct file_operations rcudata_csv_fops = {
+        .owner = THIS_MODULE,
+        .open = rcudata_csv_open,
+        .read = seq_read,
+        .llseek = seq_lseek,
+        .release = single_release,
+};
+
+static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp)
+{
+        int level = 0;
+        struct rcu_node *rnp;
+
+        seq_printf(m, "c=%ld g=%ld s=%d jfq=%ld j=%x "
+                      "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu\n",
+                   rsp->completed, rsp->gpnum, rsp->signaled,
+                   (long)(rsp->jiffies_force_qs - jiffies),
+                   (int)(jiffies & 0xffff),
+                   rsp->n_force_qs, rsp->n_force_qs_ngp,
+                   rsp->n_force_qs - rsp->n_force_qs_ngp,
+                   rsp->n_force_qs_lh);
+        for (rnp = &rsp->node[0]; rnp - &rsp->node[0] < NUM_RCU_NODES; rnp++) {
+                if (rnp->level != level) {
+                        seq_puts(m, "\n");
+                        level = rnp->level;
+                }
+                seq_printf(m, "%lx/%lx %d:%d ^%d    ",
+                           rnp->qsmask, rnp->qsmaskinit,
+                           rnp->grplo, rnp->grphi, rnp->grpnum);
+        }
+        seq_puts(m, "\n");
+}
+
+static int show_rcuhier(struct seq_file *m, void *unused)
+{
+        seq_puts(m, "rcu:\n");
+        print_one_rcu_state(m, &rcu_state);
+        seq_puts(m, "rcu_bh:\n");
+        print_one_rcu_state(m, &rcu_bh_state);
+        return 0;
+}
+
+static int rcuhier_open(struct inode *inode, struct file *file)
+{
+        return single_open(file, show_rcuhier, NULL);
+}
+
+static struct file_operations rcuhier_fops = {
+        .owner = THIS_MODULE,
+        .open = rcuhier_open,
+        .read = seq_read,
+        .llseek = seq_lseek,
+        .release = single_release,
+};
+
+static int show_rcugp(struct seq_file *m, void *unused)
+{
+        seq_printf(m, "rcu: completed=%ld  gpnum=%ld\n",
+                   rcu_state.completed, rcu_state.gpnum);
+        seq_printf(m, "rcu_bh: completed=%ld  gpnum=%ld\n",
+                   rcu_bh_state.completed, rcu_bh_state.gpnum);
+        return 0;
+}
+
+static int rcugp_open(struct inode *inode, struct file *file)
+{
+        return single_open(file, show_rcugp, NULL);
+}
+
+static struct file_operations rcugp_fops = {
+        .owner = THIS_MODULE,
+        .open = rcugp_open,
+        .read = seq_read,
+        .llseek = seq_lseek,
+        .release = single_release,
+};
+
+static struct dentry *rcudir, *datadir, *datadir_csv, *hierdir, *gpdir;
+static int __init rcuclassic_trace_init(void)
+{
+        rcudir = debugfs_create_dir("rcu", NULL);
+        if (!rcudir)
+                goto out;
+
+        datadir = debugfs_create_file("rcudata", 0444, rcudir,
+                                                NULL, &rcudata_fops);
+        if (!datadir)
+                goto free_out;
+
+        datadir_csv = debugfs_create_file("rcudata.csv", 0444, rcudir,
+                                                NULL, &rcudata_csv_fops);
+        if (!datadir_csv)
+                goto free_out;
+
+        gpdir = debugfs_create_file("rcugp", 0444, rcudir, NULL, &rcugp_fops);
+        if (!gpdir)
+                goto free_out;
+
+        hierdir = debugfs_create_file("rcuhier", 0444, rcudir,
+                                                NULL, &rcuhier_fops);
+        if (!hierdir)
+                goto free_out;
+        return 0;
+free_out:
+        if (datadir)
+                debugfs_remove(datadir);
+        if (datadir_csv)
+                debugfs_remove(datadir_csv);
+        if (gpdir)
+                debugfs_remove(gpdir);
+        debugfs_remove(rcudir);
+out:
+        return 1;
+}
+
+static void __exit rcuclassic_trace_cleanup(void)
+{
+        debugfs_remove(datadir);
+        debugfs_remove(datadir_csv);
+        debugfs_remove(gpdir);
+        debugfs_remove(hierdir);
+        debugfs_remove(rcudir);
+}
+
+
+module_init(rcuclassic_trace_init);
+module_exit(rcuclassic_trace_cleanup);
+
+MODULE_AUTHOR("Paul E. McKenney");
+MODULE_DESCRIPTION("Read-Copy Update tracing for hierarchical implementation");
+MODULE_LICENSE("GPL");
diff --git a/kernel/resource.c b/kernel/resource.c
index 4337063663ef..e633106b12f6 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -853,6 +853,15 @@ int iomem_map_sanity_check(resource_size_t addr, unsigned long size)
                 if (PFN_DOWN(p->start) <= PFN_DOWN(addr) &&
                     PFN_DOWN(p->end) >= PFN_DOWN(addr + size - 1))
                         continue;
+                /*
+                 * if a resource is "BUSY", it's not a hardware resource
+                 * but a driver mapping of such a resource; we don't want
+                 * to warn for those; some drivers legitimately map only
+                 * partial hardware resources. (example: vesafb)
+                 */
+                if (p->flags & IORESOURCE_BUSY)
+                        continue;
+
                 printk(KERN_WARNING "resource map sanity check conflict: "
                        "0x%llx 0x%llx 0x%llx 0x%llx %s\n",
                        (unsigned long long)addr,
diff --git a/kernel/sched.c b/kernel/sched.c
index 756d981d91a4..27ba1d642f0f 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -209,7 +209,6 @@ void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime)
         hrtimer_init(&rt_b->rt_period_timer,
                         CLOCK_MONOTONIC, HRTIMER_MODE_REL);
         rt_b->rt_period_timer.function = sched_rt_period_timer;
-        rt_b->rt_period_timer.cb_mode = HRTIMER_CB_IRQSAFE_UNLOCKED;
 }
 
 static inline int rt_bandwidth_enabled(void)
@@ -361,7 +360,9 @@ static inline struct task_group *task_group(struct task_struct *p)
         struct task_group *tg;
 
 #ifdef CONFIG_USER_SCHED
-        tg = p->user->tg;
+        rcu_read_lock();
+        tg = __task_cred(p)->user->tg;
+        rcu_read_unlock();
 #elif defined(CONFIG_CGROUP_SCHED)
         tg = container_of(task_subsys_state(p, cpu_cgroup_subsys_id),
                                 struct task_group, css);
@@ -610,6 +611,8 @@ struct rq {
 #ifdef CONFIG_SCHEDSTATS
         /* latency stats */
         struct sched_info rq_sched_info;
+        unsigned long long rq_cpu_time;
+        /* could above be rq->cfs_rq.exec_clock + rq->rt_rq.rt_runtime ? */
 
         /* sys_sched_yield() stats */
         unsigned int yld_exp_empty;
@@ -1143,7 +1146,6 @@ static void init_rq_hrtick(struct rq *rq)
 
         hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
         rq->hrtick_timer.function = hrtick;
-        rq->hrtick_timer.cb_mode = HRTIMER_CB_IRQSAFE_PERCPU;
 }
 #else   /* CONFIG_SCHED_HRTICK */
 static inline void hrtick_clear(struct rq *rq)
@@ -1871,6 +1873,8 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 
         clock_offset = old_rq->clock - new_rq->clock;
 
+        trace_sched_migrate_task(p, task_cpu(p), new_cpu);
+
 #ifdef CONFIG_SCHEDSTATS
         if (p->se.wait_start)
                 p->se.wait_start -= clock_offset;
@@ -2277,6 +2281,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync)
 
         smp_wmb();
         rq = task_rq_lock(p, &flags);
+        update_rq_clock(rq);
         old_state = p->state;
         if (!(old_state & state))
                 goto out;
@@ -2334,12 +2339,11 @@ out_activate:
                 schedstat_inc(p, se.nr_wakeups_local);
         else
                 schedstat_inc(p, se.nr_wakeups_remote);
-        update_rq_clock(rq);
         activate_task(rq, p, 1);
         success = 1;
 
 out_running:
-        trace_sched_wakeup(rq, p);
+        trace_sched_wakeup(rq, p, success);
         check_preempt_curr(rq, p, sync);
 
         p->state = TASK_RUNNING;
@@ -2472,7 +2476,7 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
                 p->sched_class->task_new(rq, p);
                 inc_nr_running(rq);
         }
-        trace_sched_wakeup_new(rq, p);
+        trace_sched_wakeup_new(rq, p, 1);
         check_preempt_curr(rq, p, 0);
 #ifdef CONFIG_SMP
         if (p->sched_class->task_wake_up)
@@ -2851,7 +2855,6 @@ static void sched_migrate_task(struct task_struct *p, int dest_cpu)
             || unlikely(!cpu_active(dest_cpu)))
                 goto out;
 
-        trace_sched_migrate_task(rq, p, dest_cpu);
         /* force the process onto the specified CPU */
         if (migrate_task(p, dest_cpu, &req)) {
                 /* Need to wait for migration thread (might exit: take ref). */
@@ -5187,6 +5190,22 @@ __setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio)
         set_load_weight(p);
 }
 
+/*
+ * check the target process has a UID that matches the current process's
+ */
+static bool check_same_owner(struct task_struct *p)
+{
+        const struct cred *cred = current_cred(), *pcred;
+        bool match;
+
+        rcu_read_lock();
+        pcred = __task_cred(p);
+        match = (cred->euid == pcred->euid ||
+                 cred->euid == pcred->uid);
+        rcu_read_unlock();
+        return match;
+}
+
 static int __sched_setscheduler(struct task_struct *p, int policy,
                                 struct sched_param *param, bool user)
 {
@@ -5246,8 +5265,7 @@ recheck:
                         return -EPERM;
 
                 /* can't change other user's priorities */
-                if ((current->euid != p->euid) &&
-                    (current->euid != p->uid))
+                if (!check_same_owner(p))
                         return -EPERM;
         }
 
@@ -5486,8 +5504,7 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
                 goto out_free_cpus_allowed;
         }
         retval = -EPERM;
-        if ((current->euid != p->euid) && (current->euid != p->uid) &&
-                        !capable(CAP_SYS_NICE))
+        if (!check_same_owner(p) && !capable(CAP_SYS_NICE))
                 goto out_unlock;
 
         retval = security_task_setscheduler(p, 0, NULL);
@@ -9423,6 +9440,41 @@ cpuacct_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp)
         kfree(ca);
 }
 
+static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu)
+{
+        u64 *cpuusage = percpu_ptr(ca->cpuusage, cpu);
+        u64 data;
+
+#ifndef CONFIG_64BIT
+        /*
+         * Take rq->lock to make 64-bit read safe on 32-bit platforms.
+         */
+        spin_lock_irq(&cpu_rq(cpu)->lock);
+        data = *cpuusage;
+        spin_unlock_irq(&cpu_rq(cpu)->lock);
+#else
+        data = *cpuusage;
+#endif
+
+        return data;
+}
+
+static void cpuacct_cpuusage_write(struct cpuacct *ca, int cpu, u64 val)
+{
+        u64 *cpuusage = percpu_ptr(ca->cpuusage, cpu);
+
+#ifndef CONFIG_64BIT
+        /*
+         * Take rq->lock to make 64-bit write safe on 32-bit platforms.
+         */
+        spin_lock_irq(&cpu_rq(cpu)->lock);
+        *cpuusage = val;
+        spin_unlock_irq(&cpu_rq(cpu)->lock);
+#else
+        *cpuusage = val;
+#endif
+}
+
 /* return total cpu usage (in nanoseconds) of a group */
 static u64 cpuusage_read(struct cgroup *cgrp, struct cftype *cft)
 {
@@ -9430,17 +9482,8 @@ static u64 cpuusage_read(struct cgroup *cgrp, struct cftype *cft)
         u64 totalcpuusage = 0;
         int i;
 
-        for_each_possible_cpu(i) {
-                u64 *cpuusage = percpu_ptr(ca->cpuusage, i);
-
-                /*
-                 * Take rq->lock to make 64-bit addition safe on 32-bit
-                 * platforms.
-                 */
-                spin_lock_irq(&cpu_rq(i)->lock);
-                totalcpuusage += *cpuusage;
-                spin_unlock_irq(&cpu_rq(i)->lock);
-        }
+        for_each_present_cpu(i)
+                totalcpuusage += cpuacct_cpuusage_read(ca, i);
 
         return totalcpuusage;
 }
@@ -9457,23 +9500,39 @@ static int cpuusage_write(struct cgroup *cgrp, struct cftype *cftype,
                 goto out;
         }
 
-        for_each_possible_cpu(i) {
-                u64 *cpuusage = percpu_ptr(ca->cpuusage, i);
+        for_each_present_cpu(i)
+                cpuacct_cpuusage_write(ca, i, 0);
 
-                spin_lock_irq(&cpu_rq(i)->lock);
-                *cpuusage = 0;
-                spin_unlock_irq(&cpu_rq(i)->lock);
-        }
 out:
         return err;
 }
 
+static int cpuacct_percpu_seq_read(struct cgroup *cgroup, struct cftype *cft,
+                                   struct seq_file *m)
+{
+        struct cpuacct *ca = cgroup_ca(cgroup);
+        u64 percpu;
+        int i;
+
+        for_each_present_cpu(i) {
+                percpu = cpuacct_cpuusage_read(ca, i);
+                seq_printf(m, "%llu ", (unsigned long long) percpu);
+        }
+        seq_printf(m, "\n");
+        return 0;
+}
+
 static struct cftype files[] = {
         {
                 .name = "usage",
                 .read_u64 = cpuusage_read,
                 .write_u64 = cpuusage_write,
         },
+        {
+                .name = "usage_percpu",
+                .read_seq_string = cpuacct_percpu_seq_read,
+        },
+
 };
 
 static int cpuacct_populate(struct cgroup_subsys *ss, struct cgroup *cgrp)
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 36b5e34fa99e..56c0efe902a7 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -492,6 +492,8 @@ static void update_curr(struct cfs_rq *cfs_rq)
          * overflow on 32 bits):
          */
         delta_exec = (unsigned long)(now - curr->exec_start);
+        if (!delta_exec)
+                return;
 
         __update_curr(cfs_rq, curr, delta_exec);
         curr->exec_start = now;
@@ -1361,12 +1363,11 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int sync)
 {
         struct task_struct *curr = rq->curr;
         struct sched_entity *se = &curr->se, *pse = &p->se;
+        struct cfs_rq *cfs_rq = task_cfs_rq(curr);
 
-        if (unlikely(rt_prio(p->prio))) {
-                struct cfs_rq *cfs_rq = task_cfs_rq(curr);
+        update_curr(cfs_rq);
 
-                update_rq_clock(rq);
-                update_curr(cfs_rq);
+        if (unlikely(rt_prio(p->prio))) {
                 resched_task(curr);
                 return;
         }
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index 1bbd99014011..833b6d44483c 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -77,7 +77,7 @@ static inline u64 sched_rt_period(struct rt_rq *rt_rq)
 }
 
 #define for_each_leaf_rt_rq(rt_rq, rq) \
-        list_for_each_entry(rt_rq, &rq->leaf_rt_rq_list, leaf_rt_rq_list)
+        list_for_each_entry_rcu(rt_rq, &rq->leaf_rt_rq_list, leaf_rt_rq_list)
 
 static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq)
 {
diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h
index 5fcf0e184586..f2773b5d1226 100644
--- a/kernel/sched_stats.h
+++ b/kernel/sched_stats.h
@@ -31,7 +31,7 @@ static int show_schedstat(struct seq_file *seq, void *v)
                     rq->yld_act_empty, rq->yld_exp_empty, rq->yld_count,
                     rq->sched_switch, rq->sched_count, rq->sched_goidle,
                     rq->ttwu_count, rq->ttwu_local,
-                    rq->rq_sched_info.cpu_time,
+                    rq->rq_cpu_time,
                     rq->rq_sched_info.run_delay, rq->rq_sched_info.pcount);
 
                 seq_printf(seq, "\n");
@@ -124,7 +124,7 @@ static inline void
 rq_sched_info_depart(struct rq *rq, unsigned long long delta)
 {
         if (rq)
-                rq->rq_sched_info.cpu_time += delta;
+                rq->rq_cpu_time += delta;
 }
 
 static inline void
@@ -237,7 +237,6 @@ static inline void sched_info_depart(struct task_struct *t)
         unsigned long long delta = task_rq(t)->clock -
                                         t->sched_info.last_arrival;
 
-        t->sched_info.cpu_time += delta;
         rq_sched_info_depart(task_rq(t), delta);
 
         if (t->state == TASK_RUNNING)
diff --git a/kernel/signal.c b/kernel/signal.c
index e9afe63da24b..8e95855ff3cf 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -179,6 +179,11 @@ int next_signal(struct sigpending *pending, sigset_t *mask)
         return sig;
 }
 
+/*
+ * allocate a new signal queue record
+ * - this may be called without locks if and only if t == current, otherwise an
+ *   appopriate lock must be held to stop the target task from exiting
+ */
 static struct sigqueue *__sigqueue_alloc(struct task_struct *t, gfp_t flags,
                                          int override_rlimit)
 {
@@ -186,11 +191,12 @@ static struct sigqueue *__sigqueue_alloc(struct task_struct *t, gfp_t flags,
         struct user_struct *user;
 
         /*
-         * In order to avoid problems with "switch_user()", we want to make
-         * sure that the compiler doesn't re-load "t->user"
+         * We won't get problems with the target's UID changing under us
+         * because changing it requires RCU be used, and if t != current, the
+         * caller must be holding the RCU readlock (by way of a spinlock) and
+         * we use RCU protection here
          */
-        user = t->user;
-        barrier();
+        user = get_uid(__task_cred(t)->user);
         atomic_inc(&user->sigpending);
         if (override_rlimit ||
             atomic_read(&user->sigpending) <=
@@ -198,12 +204,14 @@ static struct sigqueue *__sigqueue_alloc(struct task_struct *t, gfp_t flags,
                 q = kmem_cache_alloc(sigqueue_cachep, flags);
         if (unlikely(q == NULL)) {
                 atomic_dec(&user->sigpending);
+                free_uid(user);
         } else {
                 INIT_LIST_HEAD(&q->list);
                 q->flags = 0;
-                q->user = get_uid(user);
+                q->user = user;
         }
-        return(q);
+
+        return q;
 }
 
 static void __sigqueue_free(struct sigqueue *q)
@@ -564,10 +572,12 @@ static int rm_from_queue(unsigned long mask, struct sigpending *s)
 
 /*
  * Bad permissions for sending the signal
+ * - the caller must hold at least the RCU read lock
  */
 static int check_kill_permission(int sig, struct siginfo *info,
                                  struct task_struct *t)
 {
+        const struct cred *cred = current_cred(), *tcred;
         struct pid *sid;
         int error;
 
@@ -581,8 +591,11 @@ static int check_kill_permission(int sig, struct siginfo *info,
         if (error)
                 return error;
 
-        if ((current->euid ^ t->suid) && (current->euid ^ t->uid) &&
-            (current->uid  ^ t->suid) && (current->uid  ^ t->uid) &&
+        tcred = __task_cred(t);
+        if ((cred->euid ^ tcred->suid) &&
+            (cred->euid ^ tcred->uid) &&
+            (cred->uid  ^ tcred->suid) &&
+            (cred->uid  ^ tcred->uid) &&
             !capable(CAP_KILL)) {
                 switch (sig) {
                 case SIGCONT:
@@ -846,7 +859,7 @@ static int send_signal(int sig, struct siginfo *info, struct task_struct *t,
                         q->info.si_errno = 0;
                         q->info.si_code = SI_USER;
                         q->info.si_pid = task_pid_vnr(current);
-                        q->info.si_uid = current->uid;
+                        q->info.si_uid = current_uid();
                         break;
                 case (unsigned long) SEND_SIG_PRIV:
                         q->info.si_signo = sig;
@@ -1010,6 +1023,10 @@ struct sighand_struct *lock_task_sighand(struct task_struct *tsk, unsigned long
         return sighand;
 }
 
+/*
+ * send signal info to all the members of a group
+ * - the caller must hold the RCU read lock at least
+ */
 int group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p)
 {
         unsigned long flags;
@@ -1031,8 +1048,8 @@ int group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p)
 /*
  * __kill_pgrp_info() sends a signal to a process group: this is what the tty
  * control characters do (^C, ^Z etc)
+ * - the caller must hold at least a readlock on tasklist_lock
  */
-
 int __kill_pgrp_info(int sig, struct siginfo *info, struct pid *pgrp)
 {
         struct task_struct *p = NULL;
@@ -1088,6 +1105,7 @@ int kill_pid_info_as_uid(int sig, struct siginfo *info, struct pid *pid,
 {
         int ret = -EINVAL;
         struct task_struct *p;
+        const struct cred *pcred;
 
         if (!valid_signal(sig))
                 return ret;
@@ -1098,9 +1116,11 @@ int kill_pid_info_as_uid(int sig, struct siginfo *info, struct pid *pid,
                 ret = -ESRCH;
                 goto out_unlock;
         }
-        if ((info == SEND_SIG_NOINFO || (!is_si_special(info) && SI_FROMUSER(info)))
-            && (euid != p->suid) && (euid != p->uid)
-            && (uid != p->suid) && (uid != p->uid)) {
+        pcred = __task_cred(p);
+        if ((info == SEND_SIG_NOINFO ||
+             (!is_si_special(info) && SI_FROMUSER(info))) &&
+            euid != pcred->suid && euid != pcred->uid &&
+            uid  != pcred->suid && uid  != pcred->uid) {
                 ret = -EPERM;
                 goto out_unlock;
         }
@@ -1371,10 +1391,9 @@ int do_notify_parent(struct task_struct *tsk, int sig)
          */
         rcu_read_lock();
         info.si_pid = task_pid_nr_ns(tsk, tsk->parent->nsproxy->pid_ns);
+        info.si_uid = __task_cred(tsk)->uid;
         rcu_read_unlock();
 
-        info.si_uid = tsk->uid;
-
         thread_group_cputime(tsk, &cputime);
         info.si_utime = cputime_to_jiffies(cputime.utime);
         info.si_stime = cputime_to_jiffies(cputime.stime);
@@ -1442,10 +1461,9 @@ static void do_notify_parent_cldstop(struct task_struct *tsk, int why)
          */
         rcu_read_lock();
         info.si_pid = task_pid_nr_ns(tsk, tsk->parent->nsproxy->pid_ns);
+        info.si_uid = __task_cred(tsk)->uid;
         rcu_read_unlock();
 
-        info.si_uid = tsk->uid;
-
         info.si_utime = cputime_to_clock_t(tsk->utime);
         info.si_stime = cputime_to_clock_t(tsk->stime);
 
@@ -1600,7 +1618,7 @@ void ptrace_notify(int exit_code)
         info.si_signo = SIGTRAP;
         info.si_code = exit_code;
         info.si_pid = task_pid_vnr(current);
-        info.si_uid = current->uid;
+        info.si_uid = current_uid();
 
         /* Let the debugger run.  */
         spin_lock_irq(&current->sighand->siglock);
@@ -1712,7 +1730,7 @@ static int ptrace_signal(int signr, siginfo_t *info,
                 info->si_errno = 0;
                 info->si_code = SI_USER;
                 info->si_pid = task_pid_vnr(current->parent);
-                info->si_uid = current->parent->uid;
+                info->si_uid = task_uid(current->parent);
         }
 
         /* If the (new) signal is now blocked, requeue it.  */
@@ -2213,7 +2231,7 @@ sys_kill(pid_t pid, int sig)
         info.si_errno = 0;
         info.si_code = SI_USER;
         info.si_pid = task_tgid_vnr(current);
-        info.si_uid = current->uid;
+        info.si_uid = current_uid();
 
         return kill_something_info(sig, &info, pid);
 }
@@ -2230,7 +2248,7 @@ static int do_tkill(pid_t tgid, pid_t pid, int sig)
         info.si_errno = 0;
         info.si_code = SI_TKILL;
         info.si_pid = task_tgid_vnr(current);
-        info.si_uid = current->uid;
+        info.si_uid = current_uid();
 
         rcu_read_lock();
         p = find_task_by_vpid(pid);
diff --git a/kernel/smp.c b/kernel/smp.c
index 75c8dde58c55..5cfa0e5e3e88 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -24,8 +24,8 @@ struct call_function_data {
         struct call_single_data csd;
         spinlock_t lock;
         unsigned int refs;
-        cpumask_t cpumask;
         struct rcu_head rcu_head;
+        unsigned long cpumask_bits[];
 };
 
 struct call_single_queue {
@@ -110,13 +110,13 @@ void generic_smp_call_function_interrupt(void)
         list_for_each_entry_rcu(data, &call_function_queue, csd.list) {
                 int refs;
 
-                if (!cpu_isset(cpu, data->cpumask))
+                if (!cpumask_test_cpu(cpu, to_cpumask(data->cpumask_bits)))
                         continue;
 
                 data->csd.func(data->csd.info);
 
                 spin_lock(&data->lock);
-                cpu_clear(cpu, data->cpumask);
+                cpumask_clear_cpu(cpu, to_cpumask(data->cpumask_bits));
                 WARN_ON(data->refs == 0);
                 data->refs--;
                 refs = data->refs;
@@ -223,7 +223,7 @@ int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
                 local_irq_save(flags);
                 func(info);
                 local_irq_restore(flags);
-        } else if ((unsigned)cpu < NR_CPUS && cpu_online(cpu)) {
+        } else if ((unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) {
                 struct call_single_data *data = NULL;
 
                 if (!wait) {
@@ -266,51 +266,19 @@ void __smp_call_function_single(int cpu, struct call_single_data *data)
         generic_exec_single(cpu, data);
 }
 
-/* Dummy function */
-static void quiesce_dummy(void *unused)
-{
-}
-
-/*
- * Ensure stack based data used in call function mask is safe to free.
- *
- * This is needed by smp_call_function_mask when using on-stack data, because
- * a single call function queue is shared by all CPUs, and any CPU may pick up
- * the data item on the queue at any time before it is deleted. So we need to
- * ensure that all CPUs have transitioned through a quiescent state after
- * this call.
- *
- * This is a very slow function, implemented by sending synchronous IPIs to
- * all possible CPUs. For this reason, we have to alloc data rather than use
- * stack based data even in the case of synchronous calls. The stack based
- * data is then just used for deadlock/oom fallback which will be very rare.
- *
- * If a faster scheme can be made, we could go back to preferring stack based
- * data -- the data allocation/free is non-zero cost.
- */
-static void smp_call_function_mask_quiesce_stack(cpumask_t mask)
-{
-        struct call_single_data data;
-        int cpu;
-
-        data.func = quiesce_dummy;
-        data.info = NULL;
-
-        for_each_cpu_mask(cpu, mask) {
-                data.flags = CSD_FLAG_WAIT;
-                generic_exec_single(cpu, &data);
-        }
-}
+/* FIXME: 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_mask(): Run a function on a set of other CPUs.
- * @mask: The set of cpus to run on.
+ * 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).
  * @func: The function to run. This must be fast and non-blocking.
  * @info: An arbitrary pointer to pass to the function.
  * @wait: If true, wait (atomically) until function has completed on other CPUs.
  *
- * Returns 0 on success, else a negative status code.
- *
  * If @wait is true, then returns once @func has returned. Note that @wait
  * will be implicitly turned on in case of allocation failures, since
  * we fall back to on-stack allocation.
@@ -319,53 +287,57 @@ static void smp_call_function_mask_quiesce_stack(cpumask_t mask)
  * hardware interrupt handler or from a bottom half handler. Preemption
  * must be disabled when calling this function.
  */
-int smp_call_function_mask(cpumask_t mask, void (*func)(void *), void *info,
-                           int wait)
+void smp_call_function_many(const struct cpumask *mask,
+                            void (*func)(void *), void *info,
+                            bool wait)
 {
-        struct call_function_data d;
-        struct call_function_data *data = NULL;
-        cpumask_t allbutself;
+        struct call_function_data *data;
         unsigned long flags;
-        int cpu, num_cpus;
-        int slowpath = 0;
+        int cpu, next_cpu;
 
         /* Can deadlock when called with interrupts disabled */
         WARN_ON(irqs_disabled());
 
-        cpu = smp_processor_id();
-        allbutself = cpu_online_map;
-        cpu_clear(cpu, allbutself);
-        cpus_and(mask, mask, allbutself);
-        num_cpus = cpus_weight(mask);
-
-        /*
-         * If zero CPUs, return. If just a single CPU, turn this request
-         * into a targetted single call instead since it's faster.
-         */
-        if (!num_cpus)
-                return 0;
-        else if (num_cpus == 1) {
-                cpu = first_cpu(mask);
-                return smp_call_function_single(cpu, func, info, wait);
+        /* So, what's a CPU they want?  Ignoring this one. */
+        cpu = cpumask_first_and(mask, cpu_online_mask);
+        if (cpu == smp_processor_id())
+                cpu = cpumask_next_and(cpu, mask, cpu_online_mask);
+        /* No online cpus?  We're done. */
+        if (cpu >= nr_cpu_ids)
+                return;
+
+        /* Do we have another CPU which isn't us? */
+        next_cpu = cpumask_next_and(cpu, mask, cpu_online_mask);
+        if (next_cpu == smp_processor_id())
+                next_cpu = cpumask_next_and(next_cpu, mask, cpu_online_mask);
+
+        /* Fastpath: do that cpu by itself. */
+        if (next_cpu >= nr_cpu_ids) {
+                smp_call_function_single(cpu, func, info, wait);
+                return;
         }
 
-        data = kmalloc(sizeof(*data), GFP_ATOMIC);
-        if (data) {
-                data->csd.flags = CSD_FLAG_ALLOC;
-                if (wait)
-                        data->csd.flags |= CSD_FLAG_WAIT;
-        } else {
-                data = &d;
-                data->csd.flags = CSD_FLAG_WAIT;
-                wait = 1;
-                slowpath = 1;
+        data = kmalloc(sizeof(*data) + cpumask_size(), GFP_ATOMIC);
+        if (unlikely(!data)) {
+                /* Slow path. */
+                for_each_online_cpu(cpu) {
+                        if (cpu == smp_processor_id())
+                                continue;
+                        if (cpumask_test_cpu(cpu, mask))
+                                smp_call_function_single(cpu, func, info, wait);
+                }
+                return;
         }
 
         spin_lock_init(&data->lock);
+        data->csd.flags = CSD_FLAG_ALLOC;
+        if (wait)
+                data->csd.flags |= CSD_FLAG_WAIT;
         data->csd.func = func;
         data->csd.info = info;
-        data->refs = num_cpus;
-        data->cpumask = mask;
+        cpumask_and(to_cpumask(data->cpumask_bits), mask, cpu_online_mask);
+        cpumask_clear_cpu(smp_processor_id(), to_cpumask(data->cpumask_bits));
+        data->refs = cpumask_weight(to_cpumask(data->cpumask_bits));
 
         spin_lock_irqsave(&call_function_lock, flags);
         list_add_tail_rcu(&data->csd.list, &call_function_queue);
@@ -377,18 +349,13 @@ int smp_call_function_mask(cpumask_t mask, void (*func)(void *), void *info,
         smp_mb();
 
         /* Send a message to all CPUs in the map */
-        arch_send_call_function_ipi(mask);
+        arch_send_call_function_ipi_mask(to_cpumask(data->cpumask_bits));
 
         /* optionally wait for the CPUs to complete */
-        if (wait) {
+        if (wait)
                 csd_flag_wait(&data->csd);
-                if (unlikely(slowpath))
-                        smp_call_function_mask_quiesce_stack(mask);
-        }
-
-        return 0;
 }
-EXPORT_SYMBOL(smp_call_function_mask);
+EXPORT_SYMBOL(smp_call_function_many);
 
 /**
  * smp_call_function(): Run a function on all other CPUs.
@@ -396,7 +363,7 @@ EXPORT_SYMBOL(smp_call_function_mask);
  * @info: An arbitrary pointer to pass to the function.
  * @wait: If true, wait (atomically) until function has completed on other CPUs.
  *
- * Returns 0 on success, else a negative status code.
+ * Returns 0.
  *
  * If @wait is true, then returns once @func has returned; otherwise
  * it returns just before the target cpu calls @func. In case of allocation
@@ -407,12 +374,10 @@ EXPORT_SYMBOL(smp_call_function_mask);
  */
 int smp_call_function(void (*func)(void *), void *info, int wait)
 {
-        int ret;
-
         preempt_disable();
-        ret = smp_call_function_mask(cpu_online_map, func, info, wait);
+        smp_call_function_many(cpu_online_mask, func, info, wait);
         preempt_enable();
-        return ret;
+        return 0;
 }
 EXPORT_SYMBOL(smp_call_function);
 
diff --git a/kernel/softirq.c b/kernel/softirq.c
index e7c69a720d69..b7568d7def23 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -102,20 +102,6 @@ void local_bh_disable(void)
 
 EXPORT_SYMBOL(local_bh_disable);
 
-void __local_bh_enable(void)
-{
-        WARN_ON_ONCE(in_irq());
-
-        /*
-         * softirqs should never be enabled by __local_bh_enable(),
-         * it always nests inside local_bh_enable() sections:
-         */
-        WARN_ON_ONCE(softirq_count() == SOFTIRQ_OFFSET);
-
-        sub_preempt_count(SOFTIRQ_OFFSET);
-}
-EXPORT_SYMBOL_GPL(__local_bh_enable);
-
 /*
  * Special-case - softirqs can safely be enabled in
  * cond_resched_softirq(), or by __do_softirq(),
@@ -269,6 +255,7 @@ void irq_enter(void)
 {
         int cpu = smp_processor_id();
 
+        rcu_irq_enter();
         if (idle_cpu(cpu) && !in_interrupt()) {
                 __irq_enter();
                 tick_check_idle(cpu);
@@ -295,9 +282,9 @@ void irq_exit(void)
 
 #ifdef CONFIG_NO_HZ
         /* Make sure that timer wheel updates are propagated */
-        if (!in_interrupt() && idle_cpu(smp_processor_id()) && !need_resched())
-                tick_nohz_stop_sched_tick(0);
         rcu_irq_exit();
+        if (idle_cpu(smp_processor_id()) && !in_interrupt() && !need_resched())
+                tick_nohz_stop_sched_tick(0);
 #endif
         preempt_enable_no_resched();
 }
@@ -746,7 +733,7 @@ static int __cpuinit cpu_callback(struct notifier_block *nfb,
                         break;
                 /* Unbind so it can run.  Fall thru. */
                 kthread_bind(per_cpu(ksoftirqd, hotcpu),
-                             any_online_cpu(cpu_online_map));
+                             cpumask_any(cpu_online_mask));
         case CPU_DEAD:
         case CPU_DEAD_FROZEN: {
                 struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
diff --git a/kernel/softlockup.c b/kernel/softlockup.c
index 1ab790c67b17..d9188c66278a 100644
--- a/kernel/softlockup.c
+++ b/kernel/softlockup.c
@@ -303,17 +303,15 @@ cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
                 break;
         case CPU_ONLINE:
         case CPU_ONLINE_FROZEN:
-                check_cpu = any_online_cpu(cpu_online_map);
+                check_cpu = cpumask_any(cpu_online_mask);
                 wake_up_process(per_cpu(watchdog_task, hotcpu));
                 break;
 #ifdef CONFIG_HOTPLUG_CPU
         case CPU_DOWN_PREPARE:
         case CPU_DOWN_PREPARE_FROZEN:
                 if (hotcpu == check_cpu) {
-                        cpumask_t temp_cpu_online_map = cpu_online_map;
-
-                        cpu_clear(hotcpu, temp_cpu_online_map);
-                        check_cpu = any_online_cpu(temp_cpu_online_map);
+                        /* Pick any other online cpu. */
+                        check_cpu = cpumask_any_but(cpu_online_mask, hotcpu);
                 }
                 break;
 
@@ -323,7 +321,7 @@ cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
                         break;
                 /* Unbind so it can run.  Fall thru. */
                 kthread_bind(per_cpu(watchdog_task, hotcpu),
-                             any_online_cpu(cpu_online_map));
+                             cpumask_any(cpu_online_mask));
         case CPU_DEAD:
         case CPU_DEAD_FROZEN:
                 p = per_cpu(watchdog_task, hotcpu);
diff --git a/kernel/stacktrace.c b/kernel/stacktrace.c
index 94b527ef1d1e..eb212f8f8bc8 100644
--- a/kernel/stacktrace.c
+++ b/kernel/stacktrace.c
@@ -6,6 +6,7 @@
  *  Copyright (C) 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
  */
 #include <linux/sched.h>
+#include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/kallsyms.h>
 #include <linux/stacktrace.h>
@@ -24,3 +25,13 @@ void print_stack_trace(struct stack_trace *trace, int spaces)
 }
 EXPORT_SYMBOL_GPL(print_stack_trace);
 
+/*
+ * Architectures that do not implement save_stack_trace_tsk get this
+ * weak alias and a once-per-bootup warning (whenever this facility
+ * is utilized - for example by procfs):
+ */
+__weak void
+save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
+{
+        WARN_ONCE(1, KERN_INFO "save_stack_trace_tsk() not implemented yet.\n");
+}
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 24e8ceacc388..286c41722e8c 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -69,10 +69,10 @@ static void stop_cpu(struct work_struct *unused)
         int err;
 
         if (!active_cpus) {
-                if (cpu == first_cpu(cpu_online_map))
+                if (cpu == cpumask_first(cpu_online_mask))
                         smdata = &active;
         } else {
-                if (cpu_isset(cpu, *active_cpus))
+                if (cpumask_test_cpu(cpu, active_cpus))
                         smdata = &active;
         }
         /* Simple state machine */
@@ -109,7 +109,7 @@ static int chill(void *unused)
         return 0;
 }
 
-int __stop_machine(int (*fn)(void *), void *data, const cpumask_t *cpus)
+int __stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus)
 {
         struct work_struct *sm_work;
         int i, ret;
@@ -142,7 +142,7 @@ int __stop_machine(int (*fn)(void *), void *data, const cpumask_t *cpus)
         return ret;
 }
 
-int stop_machine(int (*fn)(void *), void *data, const cpumask_t *cpus)
+int stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus)
 {
         int ret;
 
diff --git a/kernel/sys.c b/kernel/sys.c
index 5fc3a0cfb994..d356d79e84ac 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -112,12 +112,17 @@ EXPORT_SYMBOL(cad_pid);
 
 void (*pm_power_off_prepare)(void);
 
+/*
+ * set the priority of a task
+ * - the caller must hold the RCU read lock
+ */
 static int set_one_prio(struct task_struct *p, int niceval, int error)
 {
+        const struct cred *cred = current_cred(), *pcred = __task_cred(p);
         int no_nice;
 
-        if (p->uid != current->euid &&
-                p->euid != current->euid && !capable(CAP_SYS_NICE)) {
+        if (pcred->uid  != cred->euid &&
+            pcred->euid != cred->euid && !capable(CAP_SYS_NICE)) {
                 error = -EPERM;
                 goto out;
         }
@@ -141,6 +146,7 @@ asmlinkage long sys_setpriority(int which, int who, int niceval)
 {
         struct task_struct *g, *p;
         struct user_struct *user;
+        const struct cred *cred = current_cred();
         int error = -EINVAL;
         struct pid *pgrp;
 
@@ -174,18 +180,18 @@ asmlinkage long sys_setpriority(int which, int who, int niceval)
                         } while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
                         break;
                 case PRIO_USER:
-                        user = current->user;
+                        user = (struct user_struct *) cred->user;
                         if (!who)
-                                who = current->uid;
-                        else
-                                if ((who != current->uid) && !(user = find_user(who)))
-                                        goto out_unlock;        /* No processes for this user */
+                                who = cred->uid;
+                        else if ((who != cred->uid) &&
+                                 !(user = find_user(who)))
+                                goto out_unlock;        /* No processes for this user */
 
                         do_each_thread(g, p)
-                                if (p->uid == who)
+                                if (__task_cred(p)->uid == who)
                                         error = set_one_prio(p, niceval, error);
                         while_each_thread(g, p);
-                        if (who != current->uid)
+                        if (who != cred->uid)
                                 free_uid(user);         /* For find_user() */
                         break;
         }
@@ -205,6 +211,7 @@ asmlinkage long sys_getpriority(int which, int who)
 {
         struct task_struct *g, *p;
         struct user_struct *user;
+        const struct cred *cred = current_cred();
         long niceval, retval = -ESRCH;
         struct pid *pgrp;
 
@@ -236,21 +243,21 @@ asmlinkage long sys_getpriority(int which, int who)
                         } while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
                         break;
                 case PRIO_USER:
-                        user = current->user;
+                        user = (struct user_struct *) cred->user;
                         if (!who)
-                                who = current->uid;
-                        else
-                                if ((who != current->uid) && !(user = find_user(who)))
-                                        goto out_unlock;        /* No processes for this user */
+                                who = cred->uid;
+                        else if ((who != cred->uid) &&
+                                 !(user = find_user(who)))
+                                goto out_unlock;        /* No processes for this user */
 
                         do_each_thread(g, p)
-                                if (p->uid == who) {
+                                if (__task_cred(p)->uid == who) {
                                         niceval = 20 - task_nice(p);
                                         if (niceval > retval)
                                                 retval = niceval;
                                 }
                         while_each_thread(g, p);
-                        if (who != current->uid)
+                        if (who != cred->uid)
                                 free_uid(user);         /* for find_user() */
                         break;
         }
@@ -472,46 +479,48 @@ void ctrl_alt_del(void)
  */
 asmlinkage long sys_setregid(gid_t rgid, gid_t egid)
 {
-        int old_rgid = current->gid;
-        int old_egid = current->egid;
-        int new_rgid = old_rgid;
-        int new_egid = old_egid;
+        const struct cred *old;
+        struct cred *new;
         int retval;
 
+        new = prepare_creds();
+        if (!new)
+                return -ENOMEM;
+        old = current_cred();
+
         retval = security_task_setgid(rgid, egid, (gid_t)-1, LSM_SETID_RE);
         if (retval)
-                return retval;
+                goto error;
 
+        retval = -EPERM;
         if (rgid != (gid_t) -1) {
-                if ((old_rgid == rgid) ||
-                    (current->egid==rgid) ||
+                if (old->gid == rgid ||
+                    old->egid == rgid ||
                     capable(CAP_SETGID))
-                        new_rgid = rgid;
+                        new->gid = rgid;
                 else
-                        return -EPERM;
+                        goto error;
         }
         if (egid != (gid_t) -1) {
-                if ((old_rgid == egid) ||
-                    (current->egid == egid) ||
-                    (current->sgid == egid) ||
+                if (old->gid == egid ||
+                    old->egid == egid ||
+                    old->sgid == egid ||
                     capable(CAP_SETGID))
-                        new_egid = egid;
+                        new->egid = egid;
                 else
-                        return -EPERM;
-        }
-        if (new_egid != old_egid) {
-                set_dumpable(current->mm, suid_dumpable);
-                smp_wmb();
+                        goto error;
         }
+
         if (rgid != (gid_t) -1 ||
-            (egid != (gid_t) -1 && egid != old_rgid))
-                current->sgid = new_egid;
-        current->fsgid = new_egid;
-        current->egid = new_egid;
-        current->gid = new_rgid;
-        key_fsgid_changed(current);
-        proc_id_connector(current, PROC_EVENT_GID);
-        return 0;
+            (egid != (gid_t) -1 && egid != old->gid))
+                new->sgid = new->egid;
+        new->fsgid = new->egid;
+
+        return commit_creds(new);
+
+error:
+        abort_creds(new);
+        return retval;
 }
 
 /*
@@ -521,56 +530,54 @@ asmlinkage long sys_setregid(gid_t rgid, gid_t egid)
  */
 asmlinkage long sys_setgid(gid_t gid)
 {
-        int old_egid = current->egid;
+        const struct cred *old;
+        struct cred *new;
         int retval;
 
+        new = prepare_creds();
+        if (!new)
+                return -ENOMEM;
+        old = current_cred();
+
         retval = security_task_setgid(gid, (gid_t)-1, (gid_t)-1, LSM_SETID_ID);
         if (retval)
-                return retval;
+                goto error;
 
-        if (capable(CAP_SETGID)) {
-                if (old_egid != gid) {
-                        set_dumpable(current->mm, suid_dumpable);
-                        smp_wmb();
-                }
-                current->gid = current->egid = current->sgid = current->fsgid = gid;
-        } else if ((gid == current->gid) || (gid == current->sgid)) {
-                if (old_egid != gid) {
-                        set_dumpable(current->mm, suid_dumpable);
-                        smp_wmb();
-                }
-                current->egid = current->fsgid = gid;
-        }
+        retval = -EPERM;
+        if (capable(CAP_SETGID))
+                new->gid = new->egid = new->sgid = new->fsgid = gid;
+        else if (gid == old->gid || gid == old->sgid)
+                new->egid = new->fsgid = gid;
         else
-                return -EPERM;
+                goto error;
 
-        key_fsgid_changed(current);
-        proc_id_connector(current, PROC_EVENT_GID);
-        return 0;
+        return commit_creds(new);
+
+error:
+        abort_creds(new);
+        return retval;
 }
   
-static int set_user(uid_t new_ruid, int dumpclear)
+/*
+ * change the user struct in a credentials set to match the new UID
+ */
+static int set_user(struct cred *new)
 {
         struct user_struct *new_user;
 
-        new_user = alloc_uid(current->nsproxy->user_ns, new_ruid);
+        new_user = alloc_uid(current_user_ns(), new->uid);
         if (!new_user)
                 return -EAGAIN;
 
         if (atomic_read(&new_user->processes) >=
                                 current->signal->rlim[RLIMIT_NPROC].rlim_cur &&
-                        new_user != current->nsproxy->user_ns->root_user) {
+                        new_user != INIT_USER) {
                 free_uid(new_user);
                 return -EAGAIN;
         }
 
-        switch_uid(new_user);
-
-        if (dumpclear) {
-                set_dumpable(current->mm, suid_dumpable);
-                smp_wmb();
-        }
-        current->uid = new_ruid;
+        free_uid(new->user);
+        new->user = new_user;
         return 0;
 }
 
@@ -591,54 +598,56 @@ static int set_user(uid_t new_ruid, int dumpclear)
  */
 asmlinkage long sys_setreuid(uid_t ruid, uid_t euid)
 {
-        int old_ruid, old_euid, old_suid, new_ruid, new_euid;
+        const struct cred *old;
+        struct cred *new;
         int retval;
 
+        new = prepare_creds();
+        if (!new)
+                return -ENOMEM;
+        old = current_cred();
+
         retval = security_task_setuid(ruid, euid, (uid_t)-1, LSM_SETID_RE);
         if (retval)
-                return retval;
-
-        new_ruid = old_ruid = current->uid;
-        new_euid = old_euid = current->euid;
-        old_suid = current->suid;
+                goto error;
 
+        retval = -EPERM;
         if (ruid != (uid_t) -1) {
-                new_ruid = ruid;
-                if ((old_ruid != ruid) &&
-                    (current->euid != ruid) &&
+                new->uid = ruid;
+                if (old->uid != ruid &&
+                    old->euid != ruid &&
                     !capable(CAP_SETUID))
-                        return -EPERM;
+                        goto error;
         }
 
         if (euid != (uid_t) -1) {
-                new_euid = euid;
-                if ((old_ruid != euid) &&
-                    (current->euid != euid) &&
-                    (current->suid != euid) &&
+                new->euid = euid;
+                if (old->uid != euid &&
+                    old->euid != euid &&
+                    old->suid != euid &&
                     !capable(CAP_SETUID))
-                        return -EPERM;
+                        goto error;
         }
 
-        if (new_ruid != old_ruid && set_user(new_ruid, new_euid != old_euid) < 0)
-                return -EAGAIN;
+        retval = -EAGAIN;
+        if (new->uid != old->uid && set_user(new) < 0)
+                goto error;
 
-        if (new_euid != old_euid) {
-                set_dumpable(current->mm, suid_dumpable);
-                smp_wmb();
-        }
-        current->fsuid = current->euid = new_euid;
         if (ruid != (uid_t) -1 ||
-            (euid != (uid_t) -1 && euid != old_ruid))
-                current->suid = current->euid;
-        current->fsuid = current->euid;
+            (euid != (uid_t) -1 && euid != old->uid))
+                new->suid = new->euid;
+        new->fsuid = new->euid;
 
-        key_fsuid_changed(current);
-        proc_id_connector(current, PROC_EVENT_UID);
-
-        return security_task_post_setuid(old_ruid, old_euid, old_suid, LSM_SETID_RE);
-}
+        retval = security_task_fix_setuid(new, old, LSM_SETID_RE);
+        if (retval < 0)
+                goto error;
 
+        return commit_creds(new);
 
+error:
+        abort_creds(new);
+        return retval;
+}
                 
 /*
  * setuid() is implemented like SysV with SAVED_IDS 
@@ -653,36 +662,41 @@ asmlinkage long sys_setreuid(uid_t ruid, uid_t euid)
  */
 asmlinkage long sys_setuid(uid_t uid)
 {
-        int old_euid = current->euid;
-        int old_ruid, old_suid, new_suid;
+        const struct cred *old;
+        struct cred *new;
         int retval;
 
+        new = prepare_creds();
+        if (!new)
+                return -ENOMEM;
+        old = current_cred();
+
         retval = security_task_setuid(uid, (uid_t)-1, (uid_t)-1, LSM_SETID_ID);
         if (retval)
-                return retval;
+                goto error;
 
-        old_ruid = current->uid;
-        old_suid = current->suid;
-        new_suid = old_suid;
-        
+        retval = -EPERM;
         if (capable(CAP_SETUID)) {
-                if (uid != old_ruid && set_user(uid, old_euid != uid) < 0)
-                        return -EAGAIN;
-                new_suid = uid;
-        } else if ((uid != current->uid) && (uid != new_suid))
-                return -EPERM;
-
-        if (old_euid != uid) {
-                set_dumpable(current->mm, suid_dumpable);
-                smp_wmb();
+                new->suid = new->uid = uid;
+                if (uid != old->uid && set_user(new) < 0) {
+                        retval = -EAGAIN;
+                        goto error;
+                }
+        } else if (uid != old->uid && uid != new->suid) {
+                goto error;
         }
-        current->fsuid = current->euid = uid;
-        current->suid = new_suid;
 
-        key_fsuid_changed(current);
-        proc_id_connector(current, PROC_EVENT_UID);
+        new->fsuid = new->euid = uid;
+
+        retval = security_task_fix_setuid(new, old, LSM_SETID_ID);
+        if (retval < 0)
+                goto error;
 
-        return security_task_post_setuid(old_ruid, old_euid, old_suid, LSM_SETID_ID);
+        return commit_creds(new);
+
+error:
+        abort_creds(new);
+        return retval;
 }
 
 
@@ -692,54 +706,63 @@ asmlinkage long sys_setuid(uid_t uid)
  */
 asmlinkage long sys_setresuid(uid_t ruid, uid_t euid, uid_t suid)
 {
-        int old_ruid = current->uid;
-        int old_euid = current->euid;
-        int old_suid = current->suid;
+        const struct cred *old;
+        struct cred *new;
         int retval;
 
+        new = prepare_creds();
+        if (!new)
+                return -ENOMEM;
+
         retval = security_task_setuid(ruid, euid, suid, LSM_SETID_RES);
         if (retval)
-                return retval;
+                goto error;
+        old = current_cred();
 
+        retval = -EPERM;
         if (!capable(CAP_SETUID)) {
-                if ((ruid != (uid_t) -1) && (ruid != current->uid) &&
-                    (ruid != current->euid) && (ruid != current->suid))
-                        return -EPERM;
-                if ((euid != (uid_t) -1) && (euid != current->uid) &&
-                    (euid != current->euid) && (euid != current->suid))
-                        return -EPERM;
-                if ((suid != (uid_t) -1) && (suid != current->uid) &&
-                    (suid != current->euid) && (suid != current->suid))
-                        return -EPERM;
+                if (ruid != (uid_t) -1 && ruid != old->uid &&
+                    ruid != old->euid  && ruid != old->suid)
+                        goto error;
+                if (euid != (uid_t) -1 && euid != old->uid &&
+                    euid != old->euid  && euid != old->suid)
+                        goto error;
+                if (suid != (uid_t) -1 && suid != old->uid &&
+                    suid != old->euid  && suid != old->suid)
+                        goto error;
         }
+
+        retval = -EAGAIN;
         if (ruid != (uid_t) -1) {
-                if (ruid != current->uid && set_user(ruid, euid != current->euid) < 0)
-                        return -EAGAIN;
+                new->uid = ruid;
+                if (ruid != old->uid && set_user(new) < 0)
+                        goto error;
         }
-        if (euid != (uid_t) -1) {
-                if (euid != current->euid) {
-                        set_dumpable(current->mm, suid_dumpable);
-                        smp_wmb();
-                }
-                current->euid = euid;
-        }
-        current->fsuid = current->euid;
+        if (euid != (uid_t) -1)
+                new->euid = euid;
         if (suid != (uid_t) -1)
-                current->suid = suid;
+                new->suid = suid;
+        new->fsuid = new->euid;
+
+        retval = security_task_fix_setuid(new, old, LSM_SETID_RES);
+        if (retval < 0)
+                goto error;
 
-        key_fsuid_changed(current);
-        proc_id_connector(current, PROC_EVENT_UID);
+        return commit_creds(new);
 
-        return security_task_post_setuid(old_ruid, old_euid, old_suid, LSM_SETID_RES);
+error:
+        abort_creds(new);
+        return retval;
 }
 
 asmlinkage long sys_getresuid(uid_t __user *ruid, uid_t __user *euid, uid_t __user *suid)
 {
+        const struct cred *cred = current_cred();
         int retval;
 
-        if (!(retval = put_user(current->uid, ruid)) &&
-            !(retval = put_user(current->euid, euid)))
-                retval = put_user(current->suid, suid);
+        if (!(retval   = put_user(cred->uid,  ruid)) &&
+            !(retval   = put_user(cred->euid, euid)))
+                retval = put_user(cred->suid, suid);
 
         return retval;
 }
@@ -749,48 +772,55 @@ asmlinkage long sys_getresuid(uid_t __user *ruid, uid_t __user *euid, uid_t __us
  */
 asmlinkage long sys_setresgid(gid_t rgid, gid_t egid, gid_t sgid)
 {
+        const struct cred *old;
+        struct cred *new;
         int retval;
 
+        new = prepare_creds();
+        if (!new)
+                return -ENOMEM;
+        old = current_cred();
+
         retval = security_task_setgid(rgid, egid, sgid, LSM_SETID_RES);
         if (retval)
-                return retval;
+                goto error;
 
+        retval = -EPERM;
         if (!capable(CAP_SETGID)) {
-                if ((rgid != (gid_t) -1) && (rgid != current->gid) &&
-                    (rgid != current->egid) && (rgid != current->sgid))
-                        return -EPERM;
-                if ((egid != (gid_t) -1) && (egid != current->gid) &&
-                    (egid != current->egid) && (egid != current->sgid))
-                        return -EPERM;
-                if ((sgid != (gid_t) -1) && (sgid != current->gid) &&
-                    (sgid != current->egid) && (sgid != current->sgid))
-                        return -EPERM;
+                if (rgid != (gid_t) -1 && rgid != old->gid &&
+                    rgid != old->egid  && rgid != old->sgid)
+                        goto error;
+                if (egid != (gid_t) -1 && egid != old->gid &&
+                    egid != old->egid  && egid != old->sgid)
+                        goto error;
+                if (sgid != (gid_t) -1 && sgid != old->gid &&
+                    sgid != old->egid  && sgid != old->sgid)
+                        goto error;
         }
-        if (egid != (gid_t) -1) {
-                if (egid != current->egid) {
-                        set_dumpable(current->mm, suid_dumpable);
-                        smp_wmb();
-                }
-                current->egid = egid;
-        }
-        current->fsgid = current->egid;
+
         if (rgid != (gid_t) -1)
-                current->gid = rgid;
+                new->gid = rgid;
+        if (egid != (gid_t) -1)
+                new->egid = egid;
         if (sgid != (gid_t) -1)
-                current->sgid = sgid;
+                new->sgid = sgid;
+        new->fsgid = new->egid;
 
-        key_fsgid_changed(current);
-        proc_id_connector(current, PROC_EVENT_GID);
-        return 0;
+        return commit_creds(new);
+
+error:
+        abort_creds(new);
+        return retval;
 }
 
 asmlinkage long sys_getresgid(gid_t __user *rgid, gid_t __user *egid, gid_t __user *sgid)
 {
+        const struct cred *cred = current_cred();
         int retval;
 
-        if (!(retval = put_user(current->gid, rgid)) &&
-            !(retval = put_user(current->egid, egid)))
-                retval = put_user(current->sgid, sgid);
+        if (!(retval   = put_user(cred->gid,  rgid)) &&
+            !(retval   = put_user(cred->egid, egid)))
+                retval = put_user(cred->sgid, sgid);
 
         return retval;
 }
@@ -804,27 +834,35 @@ asmlinkage long sys_getresgid(gid_t __user *rgid, gid_t __user *egid, gid_t __us
  */
 asmlinkage long sys_setfsuid(uid_t uid)
 {
-        int old_fsuid;
+        const struct cred *old;
+        struct cred *new;
+        uid_t old_fsuid;
 
-        old_fsuid = current->fsuid;
-        if (security_task_setuid(uid, (uid_t)-1, (uid_t)-1, LSM_SETID_FS))
-                return old_fsuid;
+        new = prepare_creds();
+        if (!new)
+                return current_fsuid();
+        old = current_cred();
+        old_fsuid = old->fsuid;
 
-        if (uid == current->uid || uid == current->euid ||
-            uid == current->suid || uid == current->fsuid || 
+        if (security_task_setuid(uid, (uid_t)-1, (uid_t)-1, LSM_SETID_FS) < 0)
+                goto error;
+
+        if (uid == old->uid  || uid == old->euid  ||
+            uid == old->suid || uid == old->fsuid ||
             capable(CAP_SETUID)) {
                 if (uid != old_fsuid) {
-                        set_dumpable(current->mm, suid_dumpable);
-                        smp_wmb();
+                        new->fsuid = uid;
+                        if (security_task_fix_setuid(new, old, LSM_SETID_FS) == 0)
+                                goto change_okay;
                 }
-                current->fsuid = uid;
         }
 
-        key_fsuid_changed(current);
-        proc_id_connector(current, PROC_EVENT_UID);
-
-        security_task_post_setuid(old_fsuid, (uid_t)-1, (uid_t)-1, LSM_SETID_FS);
+error:
+        abort_creds(new);
+        return old_fsuid;
 
+change_okay:
+        commit_creds(new);
         return old_fsuid;
 }
 
@@ -833,23 +871,34 @@ asmlinkage long sys_setfsuid(uid_t uid)
  */
 asmlinkage long sys_setfsgid(gid_t gid)
 {
-        int old_fsgid;
+        const struct cred *old;
+        struct cred *new;
+        gid_t old_fsgid;
+
+        new = prepare_creds();
+        if (!new)
+                return current_fsgid();
+        old = current_cred();
+        old_fsgid = old->fsgid;
 
-        old_fsgid = current->fsgid;
         if (security_task_setgid(gid, (gid_t)-1, (gid_t)-1, LSM_SETID_FS))
-                return old_fsgid;
+                goto error;
 
-        if (gid == current->gid || gid == current->egid ||
-            gid == current->sgid || gid == current->fsgid || 
+        if (gid == old->gid  || gid == old->egid  ||
+            gid == old->sgid || gid == old->fsgid ||
             capable(CAP_SETGID)) {
                 if (gid != old_fsgid) {
-                        set_dumpable(current->mm, suid_dumpable);
-                        smp_wmb();
+                        new->fsgid = gid;
+                        goto change_okay;
                 }
-                current->fsgid = gid;
-                key_fsgid_changed(current);
-                proc_id_connector(current, PROC_EVENT_GID);
         }
+
+error:
+        abort_creds(new);
+        return old_fsgid;
+
+change_okay:
+        commit_creds(new);
         return old_fsgid;
 }
 
@@ -1118,7 +1167,7 @@ EXPORT_SYMBOL(groups_free);
 
 /* export the group_info to a user-space array */
 static int groups_to_user(gid_t __user *grouplist,
-    struct group_info *group_info)
+                          const struct group_info *group_info)
 {
         int i;
         unsigned int count = group_info->ngroups;
@@ -1186,7 +1235,7 @@ static void groups_sort(struct group_info *group_info)
 }
 
 /* a simple bsearch */
-int groups_search(struct group_info *group_info, gid_t grp)
+int groups_search(const struct group_info *group_info, gid_t grp)
 {
         unsigned int left, right;
 
@@ -1208,51 +1257,74 @@ int groups_search(struct group_info *group_info, gid_t grp)
         return 0;
 }
 
-/* validate and set current->group_info */
-int set_current_groups(struct group_info *group_info)
+/**
+ * set_groups - Change a group subscription in a set of credentials
+ * @new: The newly prepared set of credentials to alter
+ * @group_info: The group list to install
+ *
+ * Validate a group subscription and, if valid, insert it into a set
+ * of credentials.
+ */
+int set_groups(struct cred *new, struct group_info *group_info)
 {
         int retval;
-        struct group_info *old_info;
 
         retval = security_task_setgroups(group_info);
         if (retval)
                 return retval;
 
+        put_group_info(new->group_info);
         groups_sort(group_info);
         get_group_info(group_info);
+        new->group_info = group_info;
+        return 0;
+}
+
+EXPORT_SYMBOL(set_groups);
 
-        task_lock(current);
-        old_info = current->group_info;
-        current->group_info = group_info;
-        task_unlock(current);
+/**
+ * set_current_groups - Change current's group subscription
+ * @group_info: The group list to impose
+ *
+ * Validate a group subscription and, if valid, impose it upon current's task
+ * security record.
+ */
+int set_current_groups(struct group_info *group_info)
+{
+        struct cred *new;
+        int ret;
 
-        put_group_info(old_info);
+        new = prepare_creds();
+        if (!new)
+                return -ENOMEM;
 
-        return 0;
+        ret = set_groups(new, group_info);
+        if (ret < 0) {
+                abort_creds(new);
+                return ret;
+        }
+
+        return commit_creds(new);
 }
 
 EXPORT_SYMBOL(set_current_groups);
 
 asmlinkage long sys_getgroups(int gidsetsize, gid_t __user *grouplist)
 {
-        int i = 0;
-
-        /*
-         *      SMP: Nobody else can change our grouplist. Thus we are
-         *      safe.
-         */
+        const struct cred *cred = current_cred();
+        int i;
 
         if (gidsetsize < 0)
                 return -EINVAL;
 
         /* no need to grab task_lock here; it cannot change */
-        i = current->group_info->ngroups;
+        i = cred->group_info->ngroups;
         if (gidsetsize) {
                 if (i > gidsetsize) {
                         i = -EINVAL;
                         goto out;
                 }
-                if (groups_to_user(grouplist, current->group_info)) {
+                if (groups_to_user(grouplist, cred->group_info)) {
                         i = -EFAULT;
                         goto out;
                 }
@@ -1296,9 +1368,11 @@ asmlinkage long sys_setgroups(int gidsetsize, gid_t __user *grouplist)
  */
 int in_group_p(gid_t grp)
 {
+        const struct cred *cred = current_cred();
         int retval = 1;
-        if (grp != current->fsgid)
-                retval = groups_search(current->group_info, grp);
+
+        if (grp != cred->fsgid)
+                retval = groups_search(cred->group_info, grp);
         return retval;
 }
 
@@ -1306,9 +1380,11 @@ EXPORT_SYMBOL(in_group_p);
 
 int in_egroup_p(gid_t grp)
 {
+        const struct cred *cred = current_cred();
         int retval = 1;
-        if (grp != current->egid)
-                retval = groups_search(current->group_info, grp);
+
+        if (grp != cred->egid)
+                retval = groups_search(cred->group_info, grp);
         return retval;
 }
 
@@ -1624,50 +1700,56 @@ asmlinkage long sys_umask(int mask)
 asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3,
                           unsigned long arg4, unsigned long arg5)
 {
-        long error = 0;
+        struct task_struct *me = current;
+        unsigned char comm[sizeof(me->comm)];
+        long error;
 
-        if (security_task_prctl(option, arg2, arg3, arg4, arg5, &error))
+        error = security_task_prctl(option, arg2, arg3, arg4, arg5);
+        if (error != -ENOSYS)
                 return error;
 
+        error = 0;
         switch (option) {
                 case PR_SET_PDEATHSIG:
                         if (!valid_signal(arg2)) {
                                 error = -EINVAL;
                                 break;
                         }
-                        current->pdeath_signal = arg2;
+                        me->pdeath_signal = arg2;
+                        error = 0;
                         break;
                 case PR_GET_PDEATHSIG:
-                        error = put_user(current->pdeath_signal, (int __user *)arg2);
+                        error = put_user(me->pdeath_signal, (int __user *)arg2);
                         break;
                 case PR_GET_DUMPABLE:
-                        error = get_dumpable(current->mm);
+                        error = get_dumpable(me->mm);
                         break;
                 case PR_SET_DUMPABLE:
                         if (arg2 < 0 || arg2 > 1) {
                                 error = -EINVAL;
                                 break;
                         }
-                        set_dumpable(current->mm, arg2);
+                        set_dumpable(me->mm, arg2);
+                        error = 0;
                         break;
 
                 case PR_SET_UNALIGN:
-                        error = SET_UNALIGN_CTL(current, arg2);
+                        error = SET_UNALIGN_CTL(me, arg2);
                         break;
                 case PR_GET_UNALIGN:
-                        error = GET_UNALIGN_CTL(current, arg2);
+                        error = GET_UNALIGN_CTL(me, arg2);
                         break;
                 case PR_SET_FPEMU:
-                        error = SET_FPEMU_CTL(current, arg2);
+                        error = SET_FPEMU_CTL(me, arg2);
                         break;
                 case PR_GET_FPEMU:
-                        error = GET_FPEMU_CTL(current, arg2);
+                        error = GET_FPEMU_CTL(me, arg2);
                         break;
                 case PR_SET_FPEXC:
-                        error = SET_FPEXC_CTL(current, arg2);
+                        error = SET_FPEXC_CTL(me, arg2);
                         break;
                 case PR_GET_FPEXC:
-                        error = GET_FPEXC_CTL(current, arg2);
+                        error = GET_FPEXC_CTL(me, arg2);
                         break;
                 case PR_GET_TIMING:
                         error = PR_TIMING_STATISTICAL;
@@ -1675,33 +1757,28 @@ asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3,
                 case PR_SET_TIMING:
                         if (arg2 != PR_TIMING_STATISTICAL)
                                 error = -EINVAL;
+                        else
+                                error = 0;
                         break;
 
-                case PR_SET_NAME: {
-                        struct task_struct *me = current;
-                        unsigned char ncomm[sizeof(me->comm)];
-
-                        ncomm[sizeof(me->comm)-1] = 0;
-                        if (strncpy_from_user(ncomm, (char __user *)arg2,
-                                                sizeof(me->comm)-1) < 0)
+                case PR_SET_NAME:
+                        comm[sizeof(me->comm)-1] = 0;
+                        if (strncpy_from_user(comm, (char __user *)arg2,
+                                              sizeof(me->comm) - 1) < 0)
                                 return -EFAULT;
-                        set_task_comm(me, ncomm);
+                        set_task_comm(me, comm);
                         return 0;
-                }
-                case PR_GET_NAME: {
-                        struct task_struct *me = current;
-                        unsigned char tcomm[sizeof(me->comm)];
-
-                        get_task_comm(tcomm, me);
-                        if (copy_to_user((char __user *)arg2, tcomm, sizeof(tcomm)))
+                case PR_GET_NAME:
+                        get_task_comm(comm, me);
+                        if (copy_to_user((char __user *)arg2, comm,
+                                         sizeof(comm)))
                                 return -EFAULT;
                         return 0;
-                }
                 case PR_GET_ENDIAN:
-                        error = GET_ENDIAN(current, arg2);
+                        error = GET_ENDIAN(me, arg2);
                         break;
                 case PR_SET_ENDIAN:
-                        error = SET_ENDIAN(current, arg2);
+                        error = SET_ENDIAN(me, arg2);
                         break;
 
                 case PR_GET_SECCOMP:
@@ -1725,6 +1802,7 @@ asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3,
                                         current->default_timer_slack_ns;
                         else
                                 current->timer_slack_ns = arg2;
+                        error = 0;
                         break;
                 default:
                         error = -EINVAL;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index c83f566e940a..ff6d45c7626f 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -121,6 +121,10 @@ extern int sg_big_buff;
 #include <asm/system.h>
 #endif
 
+#ifdef CONFIG_SPARC64
+extern int sysctl_tsb_ratio;
+#endif
+
 #ifdef __hppa__
 extern int pwrsw_enabled;
 extern int unaligned_enabled;
@@ -451,6 +455,16 @@ static struct ctl_table kern_table[] = {
                 .proc_handler   = &proc_dointvec,
         },
 #endif
+#ifdef CONFIG_SPARC64
+        {
+                .ctl_name       = CTL_UNNUMBERED,
+                .procname       = "tsb-ratio",
+                .data           = &sysctl_tsb_ratio,
+                .maxlen         = sizeof (int),
+                .mode           = 0644,
+                .proc_handler   = &proc_dointvec,
+        },
+#endif
 #ifdef __hppa__
         {
                 .ctl_name       = KERN_HPPA_PWRSW,
@@ -487,6 +501,16 @@ static struct ctl_table kern_table[] = {
                 .proc_handler   = &ftrace_enable_sysctl,
         },
 #endif
+#ifdef CONFIG_STACK_TRACER
+        {
+                .ctl_name       = CTL_UNNUMBERED,
+                .procname       = "stack_tracer_enabled",
+                .data           = &stack_tracer_enabled,
+                .maxlen         = sizeof(int),
+                .mode           = 0644,
+                .proc_handler   = &stack_trace_sysctl,
+        },
+#endif
 #ifdef CONFIG_TRACING
         {
                 .ctl_name       = CTL_UNNUMBERED,
@@ -1661,7 +1685,7 @@ out:
 
 static int test_perm(int mode, int op)
 {
-        if (!current->euid)
+        if (!current_euid())
                 mode >>= 6;
         else if (in_egroup_p(0))
                 mode >>= 3;
diff --git a/kernel/sysctl_check.c b/kernel/sysctl_check.c
index c35da23ab8fb..fafeb48f27c0 100644
--- a/kernel/sysctl_check.c
+++ b/kernel/sysctl_check.c
@@ -730,7 +730,6 @@ static const struct trans_ctl_table trans_fs_quota_table[] = {
 };
 
 static const struct trans_ctl_table trans_fs_xfs_table[] = {
-        { XFS_RESTRICT_CHOWN,   "restrict_chown" },
         { XFS_SGID_INHERIT,     "irix_sgid_inherit" },
         { XFS_SYMLINK_MODE,     "irix_symlink_mode" },
         { XFS_PANIC_MASK,       "panic_mask" },
diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index 6d7dc4ec4aa5..888adbcca30c 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -290,18 +290,17 @@ ret:
         return;
 }
 
-static int add_del_listener(pid_t pid, cpumask_t *maskp, int isadd)
+static int add_del_listener(pid_t pid, const struct cpumask *mask, int isadd)
 {
         struct listener_list *listeners;
         struct listener *s, *tmp;
         unsigned int cpu;
-        cpumask_t mask = *maskp;
 
-        if (!cpus_subset(mask, cpu_possible_map))
+        if (!cpumask_subset(mask, cpu_possible_mask))
                 return -EINVAL;
 
         if (isadd == REGISTER) {
-                for_each_cpu_mask_nr(cpu, mask) {
+                for_each_cpu(cpu, mask) {
                         s = kmalloc_node(sizeof(struct listener), GFP_KERNEL,
                                          cpu_to_node(cpu));
                         if (!s)
@@ -320,7 +319,7 @@ static int add_del_listener(pid_t pid, cpumask_t *maskp, int isadd)
 
         /* Deregister or cleanup */
 cleanup:
-        for_each_cpu_mask_nr(cpu, mask) {
+        for_each_cpu(cpu, mask) {
                 listeners = &per_cpu(listener_array, cpu);
                 down_write(&listeners->sem);
                 list_for_each_entry_safe(s, tmp, &listeners->list, list) {
@@ -335,7 +334,7 @@ cleanup:
         return 0;
 }
 
-static int parse(struct nlattr *na, cpumask_t *mask)
+static int parse(struct nlattr *na, struct cpumask *mask)
 {
         char *data;
         int len;
@@ -428,23 +427,33 @@ err:
 
 static int taskstats_user_cmd(struct sk_buff *skb, struct genl_info *info)
 {
-        int rc = 0;
+        int rc;
         struct sk_buff *rep_skb;
         struct taskstats *stats;
         size_t size;
-        cpumask_t mask;
+        cpumask_var_t mask;
+
+        if (!alloc_cpumask_var(&mask, GFP_KERNEL))
+                return -ENOMEM;
 
-        rc = parse(info->attrs[TASKSTATS_CMD_ATTR_REGISTER_CPUMASK], &mask);
+        rc = parse(info->attrs[TASKSTATS_CMD_ATTR_REGISTER_CPUMASK], mask);
         if (rc < 0)
-                return rc;
-        if (rc == 0)
-                return add_del_listener(info->snd_pid, &mask, REGISTER);
+                goto free_return_rc;
+        if (rc == 0) {
+                rc = add_del_listener(info->snd_pid, mask, REGISTER);
+                goto free_return_rc;
+        }
 
-        rc = parse(info->attrs[TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK], &mask);
+        rc = parse(info->attrs[TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK], mask);
         if (rc < 0)
+                goto free_return_rc;
+        if (rc == 0) {
+                rc = add_del_listener(info->snd_pid, mask, DEREGISTER);
+free_return_rc:
+                free_cpumask_var(mask);
                 return rc;
-        if (rc == 0)
-                return add_del_listener(info->snd_pid, &mask, DEREGISTER);
+        }
+        free_cpumask_var(mask);
 
         /*
          * Size includes space for nested attributes
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 9ed2eec97526..ca89e1593f08 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -145,10 +145,11 @@ static void clocksource_watchdog(unsigned long data)
                  * Cycle through CPUs to check if the CPUs stay
                  * synchronized to each other.
                  */
-                int next_cpu = next_cpu_nr(raw_smp_processor_id(), cpu_online_map);
+                int next_cpu = cpumask_next(raw_smp_processor_id(),
+                                            cpu_online_mask);
 
                 if (next_cpu >= nr_cpu_ids)
-                        next_cpu = first_cpu(cpu_online_map);
+                        next_cpu = cpumask_first(cpu_online_mask);
                 watchdog_timer.expires += WATCHDOG_INTERVAL;
                 add_timer_on(&watchdog_timer, next_cpu);
         }
@@ -173,7 +174,7 @@ static void clocksource_check_watchdog(struct clocksource *cs)
                         watchdog_last = watchdog->read();
                         watchdog_timer.expires = jiffies + WATCHDOG_INTERVAL;
                         add_timer_on(&watchdog_timer,
-                                     first_cpu(cpu_online_map));
+                                     cpumask_first(cpu_online_mask));
                 }
         } else {
                 if (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS)
@@ -195,7 +196,7 @@ static void clocksource_check_watchdog(struct clocksource *cs)
                                 watchdog_timer.expires =
                                         jiffies + WATCHDOG_INTERVAL;
                                 add_timer_on(&watchdog_timer,
-                                             first_cpu(cpu_online_map));
+                                             cpumask_first(cpu_online_mask));
                         }
                 }
         }
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 8ff15e5d486b..f5f793d92415 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -131,7 +131,7 @@ static enum hrtimer_restart ntp_leap_second(struct hrtimer *timer)
 {
         enum hrtimer_restart res = HRTIMER_NORESTART;
 
-        write_seqlock_irq(&xtime_lock);
+        write_seqlock(&xtime_lock);
 
         switch (time_state) {
         case TIME_OK:
@@ -164,7 +164,7 @@ static enum hrtimer_restart ntp_leap_second(struct hrtimer *timer)
         }
         update_vsyscall(&xtime, clock);
 
-        write_sequnlock_irq(&xtime_lock);
+        write_sequnlock(&xtime_lock);
 
         return res;
 }
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 9590af2327be..118a3b3b3f9a 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -28,7 +28,9 @@
  */
 
 struct tick_device tick_broadcast_device;
-static cpumask_t tick_broadcast_mask;
+/* FIXME: Use cpumask_var_t. */
+static DECLARE_BITMAP(tick_broadcast_mask, NR_CPUS);
+static DECLARE_BITMAP(tmpmask, NR_CPUS);
 static DEFINE_SPINLOCK(tick_broadcast_lock);
 static int tick_broadcast_force;
 
@@ -46,9 +48,9 @@ struct tick_device *tick_get_broadcast_device(void)
         return &tick_broadcast_device;
 }
 
-cpumask_t *tick_get_broadcast_mask(void)
+struct cpumask *tick_get_broadcast_mask(void)
 {
-        return &tick_broadcast_mask;
+        return to_cpumask(tick_broadcast_mask);
 }
 
 /*
@@ -72,7 +74,7 @@ int tick_check_broadcast_device(struct clock_event_device *dev)
 
         clockevents_exchange_device(NULL, dev);
         tick_broadcast_device.evtdev = dev;
-        if (!cpus_empty(tick_broadcast_mask))
+        if (!cpumask_empty(tick_get_broadcast_mask()))
                 tick_broadcast_start_periodic(dev);
         return 1;
 }
@@ -104,7 +106,7 @@ int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu)
          */
         if (!tick_device_is_functional(dev)) {
                 dev->event_handler = tick_handle_periodic;
-                cpu_set(cpu, tick_broadcast_mask);
+                cpumask_set_cpu(cpu, tick_get_broadcast_mask());
                 tick_broadcast_start_periodic(tick_broadcast_device.evtdev);
                 ret = 1;
         } else {
@@ -116,7 +118,7 @@ int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu)
                 if (!(dev->features & CLOCK_EVT_FEAT_C3STOP)) {
                         int cpu = smp_processor_id();
 
-                        cpu_clear(cpu, tick_broadcast_mask);
+                        cpumask_clear_cpu(cpu, tick_get_broadcast_mask());
                         tick_broadcast_clear_oneshot(cpu);
                 }
         }
@@ -125,9 +127,9 @@ int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu)
 }
 
 /*
- * Broadcast the event to the cpus, which are set in the mask
+ * Broadcast the event to the cpus, which are set in the mask (mangled).
  */
-static void tick_do_broadcast(cpumask_t mask)
+static void tick_do_broadcast(struct cpumask *mask)
 {
         int cpu = smp_processor_id();
         struct tick_device *td;
@@ -135,22 +137,21 @@ static void tick_do_broadcast(cpumask_t mask)
         /*
          * Check, if the current cpu is in the mask
          */
-        if (cpu_isset(cpu, mask)) {
-                cpu_clear(cpu, mask);
+        if (cpumask_test_cpu(cpu, mask)) {
+                cpumask_clear_cpu(cpu, mask);
                 td = &per_cpu(tick_cpu_device, cpu);
                 td->evtdev->event_handler(td->evtdev);
         }
 
-        if (!cpus_empty(mask)) {
+        if (!cpumask_empty(mask)) {
                 /*
                  * It might be necessary to actually check whether the devices
                  * have different broadcast functions. For now, just use the
                  * one of the first device. This works as long as we have this
                  * misfeature only on x86 (lapic)
                  */
-                cpu = first_cpu(mask);
-                td = &per_cpu(tick_cpu_device, cpu);
-                td->evtdev->broadcast(&mask);
+                td = &per_cpu(tick_cpu_device, cpumask_first(mask));
+                td->evtdev->broadcast(mask);
         }
 }
 
@@ -160,12 +161,11 @@ static void tick_do_broadcast(cpumask_t mask)
  */
 static void tick_do_periodic_broadcast(void)
 {
-        cpumask_t mask;
-
         spin_lock(&tick_broadcast_lock);
 
-        cpus_and(mask, cpu_online_map, tick_broadcast_mask);
-        tick_do_broadcast(mask);
+        cpumask_and(to_cpumask(tmpmask),
+                    cpu_online_mask, tick_get_broadcast_mask());
+        tick_do_broadcast(to_cpumask(tmpmask));
 
         spin_unlock(&tick_broadcast_lock);
 }
@@ -228,13 +228,13 @@ static void tick_do_broadcast_on_off(void *why)
         if (!tick_device_is_functional(dev))
                 goto out;
 
-        bc_stopped = cpus_empty(tick_broadcast_mask);
+        bc_stopped = cpumask_empty(tick_get_broadcast_mask());
 
         switch (*reason) {
         case CLOCK_EVT_NOTIFY_BROADCAST_ON:
         case CLOCK_EVT_NOTIFY_BROADCAST_FORCE:
-                if (!cpu_isset(cpu, tick_broadcast_mask)) {
-                        cpu_set(cpu, tick_broadcast_mask);
+                if (!cpumask_test_cpu(cpu, tick_get_broadcast_mask())) {
+                        cpumask_set_cpu(cpu, tick_get_broadcast_mask());
                         if (tick_broadcast_device.mode ==
                             TICKDEV_MODE_PERIODIC)
                                 clockevents_shutdown(dev);
@@ -244,8 +244,8 @@ static void tick_do_broadcast_on_off(void *why)
                 break;
         case CLOCK_EVT_NOTIFY_BROADCAST_OFF:
                 if (!tick_broadcast_force &&
-                    cpu_isset(cpu, tick_broadcast_mask)) {
-                        cpu_clear(cpu, tick_broadcast_mask);
+                    cpumask_test_cpu(cpu, tick_get_broadcast_mask())) {
+                        cpumask_clear_cpu(cpu, tick_get_broadcast_mask());
                         if (tick_broadcast_device.mode ==
                             TICKDEV_MODE_PERIODIC)
                                 tick_setup_periodic(dev, 0);
@@ -253,7 +253,7 @@ static void tick_do_broadcast_on_off(void *why)
                 break;
         }
 
-        if (cpus_empty(tick_broadcast_mask)) {
+        if (cpumask_empty(tick_get_broadcast_mask())) {
                 if (!bc_stopped)
                         clockevents_shutdown(bc);
         } else if (bc_stopped) {
@@ -272,7 +272,7 @@ out:
  */
 void tick_broadcast_on_off(unsigned long reason, int *oncpu)
 {
-        if (!cpu_isset(*oncpu, cpu_online_map))
+        if (!cpumask_test_cpu(*oncpu, cpu_online_mask))
                 printk(KERN_ERR "tick-broadcast: ignoring broadcast for "
                        "offline CPU #%d\n", *oncpu);
         else
@@ -303,10 +303,10 @@ void tick_shutdown_broadcast(unsigned int *cpup)
         spin_lock_irqsave(&tick_broadcast_lock, flags);
 
         bc = tick_broadcast_device.evtdev;
-        cpu_clear(cpu, tick_broadcast_mask);
+        cpumask_clear_cpu(cpu, tick_get_broadcast_mask());
 
         if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) {
-                if (bc && cpus_empty(tick_broadcast_mask))
+                if (bc && cpumask_empty(tick_get_broadcast_mask()))
                         clockevents_shutdown(bc);
         }
 
@@ -342,10 +342,10 @@ int tick_resume_broadcast(void)
 
                 switch (tick_broadcast_device.mode) {
                 case TICKDEV_MODE_PERIODIC:
-                        if(!cpus_empty(tick_broadcast_mask))
+                        if (!cpumask_empty(tick_get_broadcast_mask()))
                                 tick_broadcast_start_periodic(bc);
-                        broadcast = cpu_isset(smp_processor_id(),
-                                              tick_broadcast_mask);
+                        broadcast = cpumask_test_cpu(smp_processor_id(),
+                                                     tick_get_broadcast_mask());
                         break;
                 case TICKDEV_MODE_ONESHOT:
                         broadcast = tick_resume_broadcast_oneshot(bc);
@@ -360,14 +360,15 @@ int tick_resume_broadcast(void)
 
 #ifdef CONFIG_TICK_ONESHOT
 
-static cpumask_t tick_broadcast_oneshot_mask;
+/* FIXME: use cpumask_var_t. */
+static DECLARE_BITMAP(tick_broadcast_oneshot_mask, NR_CPUS);
 
 /*
- * Debugging: see timer_list.c
+ * Exposed for debugging: see timer_list.c
  */
-cpumask_t *tick_get_broadcast_oneshot_mask(void)
+struct cpumask *tick_get_broadcast_oneshot_mask(void)
 {
-        return &tick_broadcast_oneshot_mask;
+        return to_cpumask(tick_broadcast_oneshot_mask);
 }
 
 static int tick_broadcast_set_event(ktime_t expires, int force)
@@ -389,7 +390,7 @@ int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
  */
 void tick_check_oneshot_broadcast(int cpu)
 {
-        if (cpu_isset(cpu, tick_broadcast_oneshot_mask)) {
+        if (cpumask_test_cpu(cpu, to_cpumask(tick_broadcast_oneshot_mask))) {
                 struct tick_device *td = &per_cpu(tick_cpu_device, cpu);
 
                 clockevents_set_mode(td->evtdev, CLOCK_EVT_MODE_ONESHOT);
@@ -402,7 +403,6 @@ void tick_check_oneshot_broadcast(int cpu)
 static void tick_handle_oneshot_broadcast(struct clock_event_device *dev)
 {
         struct tick_device *td;
-        cpumask_t mask;
         ktime_t now, next_event;
         int cpu;
 
@@ -410,13 +410,13 @@ static void tick_handle_oneshot_broadcast(struct clock_event_device *dev)
 again:
         dev->next_event.tv64 = KTIME_MAX;
         next_event.tv64 = KTIME_MAX;
-        mask = CPU_MASK_NONE;
+        cpumask_clear(to_cpumask(tmpmask));
         now = ktime_get();
         /* Find all expired events */
-        for_each_cpu_mask_nr(cpu, tick_broadcast_oneshot_mask) {
+        for_each_cpu(cpu, tick_get_broadcast_oneshot_mask()) {
                 td = &per_cpu(tick_cpu_device, cpu);
                 if (td->evtdev->next_event.tv64 <= now.tv64)
-                        cpu_set(cpu, mask);
+                        cpumask_set_cpu(cpu, to_cpumask(tmpmask));
                 else if (td->evtdev->next_event.tv64 < next_event.tv64)
                         next_event.tv64 = td->evtdev->next_event.tv64;
         }
@@ -424,7 +424,7 @@ again:
         /*
          * Wakeup the cpus which have an expired event.
          */
-        tick_do_broadcast(mask);
+        tick_do_broadcast(to_cpumask(tmpmask));
 
         /*
          * Two reasons for reprogram:
@@ -476,15 +476,16 @@ void tick_broadcast_oneshot_control(unsigned long reason)
                 goto out;
 
         if (reason == CLOCK_EVT_NOTIFY_BROADCAST_ENTER) {
-                if (!cpu_isset(cpu, tick_broadcast_oneshot_mask)) {
-                        cpu_set(cpu, tick_broadcast_oneshot_mask);
+                if (!cpumask_test_cpu(cpu, tick_get_broadcast_oneshot_mask())) {
+                        cpumask_set_cpu(cpu, tick_get_broadcast_oneshot_mask());
                         clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN);
                         if (dev->next_event.tv64 < bc->next_event.tv64)
                                 tick_broadcast_set_event(dev->next_event, 1);
                 }
         } else {
-                if (cpu_isset(cpu, tick_broadcast_oneshot_mask)) {
-                        cpu_clear(cpu, tick_broadcast_oneshot_mask);
+                if (cpumask_test_cpu(cpu, tick_get_broadcast_oneshot_mask())) {
+                        cpumask_clear_cpu(cpu,
+                                          tick_get_broadcast_oneshot_mask());
                         clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT);
                         if (dev->next_event.tv64 != KTIME_MAX)
                                 tick_program_event(dev->next_event, 1);
@@ -502,15 +503,16 @@ out:
  */
 static void tick_broadcast_clear_oneshot(int cpu)
 {
-        cpu_clear(cpu, tick_broadcast_oneshot_mask);
+        cpumask_clear_cpu(cpu, tick_get_broadcast_oneshot_mask());
 }
 
-static void tick_broadcast_init_next_event(cpumask_t *mask, ktime_t expires)
+static void tick_broadcast_init_next_event(struct cpumask *mask,
+                                           ktime_t expires)
 {
         struct tick_device *td;
         int cpu;
 
-        for_each_cpu_mask_nr(cpu, *mask) {
+        for_each_cpu(cpu, mask) {
                 td = &per_cpu(tick_cpu_device, cpu);
                 if (td->evtdev)
                         td->evtdev->next_event = expires;
@@ -526,7 +528,6 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
         if (bc->event_handler != tick_handle_oneshot_broadcast) {
                 int was_periodic = bc->mode == CLOCK_EVT_MODE_PERIODIC;
                 int cpu = smp_processor_id();
-                cpumask_t mask;
 
                 bc->event_handler = tick_handle_oneshot_broadcast;
                 clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
@@ -540,13 +541,15 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
                  * oneshot_mask bits for those and program the
                  * broadcast device to fire.
                  */
-                mask = tick_broadcast_mask;
-                cpu_clear(cpu, mask);
-                cpus_or(tick_broadcast_oneshot_mask,
-                        tick_broadcast_oneshot_mask, mask);
-
-                if (was_periodic && !cpus_empty(mask)) {
-                        tick_broadcast_init_next_event(&mask, tick_next_period);
+                cpumask_copy(to_cpumask(tmpmask), tick_get_broadcast_mask());
+                cpumask_clear_cpu(cpu, to_cpumask(tmpmask));
+                cpumask_or(tick_get_broadcast_oneshot_mask(),
+                           tick_get_broadcast_oneshot_mask(),
+                           to_cpumask(tmpmask));
+
+                if (was_periodic && !cpumask_empty(to_cpumask(tmpmask))) {
+                        tick_broadcast_init_next_event(to_cpumask(tmpmask),
+                                                       tick_next_period);
                         tick_broadcast_set_event(tick_next_period, 1);
                 } else
                         bc->next_event.tv64 = KTIME_MAX;
@@ -585,7 +588,7 @@ void tick_shutdown_broadcast_oneshot(unsigned int *cpup)
          * Clear the broadcast mask flag for the dead cpu, but do not
          * stop the broadcast device!
          */
-        cpu_clear(cpu, tick_broadcast_oneshot_mask);
+        cpumask_clear_cpu(cpu, tick_get_broadcast_oneshot_mask());
 
         spin_unlock_irqrestore(&tick_broadcast_lock, flags);
 }
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index f8372be74122..63e05d423a09 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -254,7 +254,7 @@ static int tick_check_new_device(struct clock_event_device *newdev)
                 curdev = NULL;
         }
         clockevents_exchange_device(curdev, newdev);
-        tick_setup_device(td, newdev, cpu, &cpumask_of_cpu(cpu));
+        tick_setup_device(td, newdev, cpu, cpumask_of(cpu));
         if (newdev->features & CLOCK_EVT_FEAT_ONESHOT)
                 tick_oneshot_notify();
 
@@ -299,9 +299,9 @@ static void tick_shutdown(unsigned int *cpup)
         }
         /* Transfer the do_timer job away from this cpu */
         if (*cpup == tick_do_timer_cpu) {
-                int cpu = first_cpu(cpu_online_map);
+                int cpu = cpumask_first(cpu_online_mask);
 
-                tick_do_timer_cpu = (cpu != NR_CPUS) ? cpu :
+                tick_do_timer_cpu = (cpu < nr_cpu_ids) ? cpu :
                         TICK_DO_TIMER_NONE;
         }
         spin_unlock_irqrestore(&tick_device_lock, flags);
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 70f872c71f4e..76a574bbef97 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -247,7 +247,7 @@ void tick_nohz_stop_sched_tick(int inidle)
         if (need_resched())
                 goto end;
 
-        if (unlikely(local_softirq_pending())) {
+        if (unlikely(local_softirq_pending() && cpu_online(cpu))) {
                 static int ratelimit;
 
                 if (ratelimit < 10) {
@@ -282,8 +282,31 @@ void tick_nohz_stop_sched_tick(int inidle)
         /* Schedule the tick, if we are at least one jiffie off */
         if ((long)delta_jiffies >= 1) {
 
+                /*
+                * calculate the expiry time for the next timer wheel
+                * timer
+                */
+                expires = ktime_add_ns(last_update, tick_period.tv64 *
+                                   delta_jiffies);
+
+                /*
+                 * If this cpu is the one which updates jiffies, then
+                 * give up the assignment and let it be taken by the
+                 * cpu which runs the tick timer next, which might be
+                 * this cpu as well. If we don't drop this here the
+                 * jiffies might be stale and do_timer() never
+                 * invoked.
+                 */
+                if (cpu == tick_do_timer_cpu)
+                        tick_do_timer_cpu = TICK_DO_TIMER_NONE;
+
                 if (delta_jiffies > 1)
                         cpumask_set_cpu(cpu, nohz_cpu_mask);
+
+                /* Skip reprogram of event if its not changed */
+                if (ts->tick_stopped && ktime_equal(expires, dev->next_event))
+                        goto out;
+
                 /*
                  * nohz_stop_sched_tick can be called several times before
                  * the nohz_restart_sched_tick is called. This happens when
@@ -306,17 +329,6 @@ void tick_nohz_stop_sched_tick(int inidle)
                         rcu_enter_nohz();
                 }
 
-                /*
-                 * If this cpu is the one which updates jiffies, then
-                 * give up the assignment and let it be taken by the
-                 * cpu which runs the tick timer next, which might be
-                 * this cpu as well. If we don't drop this here the
-                 * jiffies might be stale and do_timer() never
-                 * invoked.
-                 */
-                if (cpu == tick_do_timer_cpu)
-                        tick_do_timer_cpu = TICK_DO_TIMER_NONE;
-
                 ts->idle_sleeps++;
 
                 /*
@@ -332,12 +344,7 @@ void tick_nohz_stop_sched_tick(int inidle)
                         goto out;
                 }
 
-                /*
-                 * calculate the expiry time for the next timer wheel
-                 * timer
-                 */
-                expires = ktime_add_ns(last_update, tick_period.tv64 *
-                                       delta_jiffies);
+                /* Mark expiries */
                 ts->idle_expires = expires;
 
                 if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
@@ -681,7 +688,6 @@ void tick_setup_sched_timer(void)
          */
         hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
         ts->sched_timer.function = tick_sched_timer;
-        ts->sched_timer.cb_mode = HRTIMER_CB_IRQSAFE_PERCPU;
 
         /* Get the next period (per cpu) */
         hrtimer_set_expires(&ts->sched_timer, tick_init_jiffy_update());
diff --git a/kernel/timer.c b/kernel/timer.c
index dbd50fabe4c7..566257d1dc10 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -1192,25 +1192,25 @@ asmlinkage long sys_getppid(void)
 asmlinkage long sys_getuid(void)
 {
         /* Only we change this so SMP safe */
-        return current->uid;
+        return current_uid();
 }
 
 asmlinkage long sys_geteuid(void)
 {
         /* Only we change this so SMP safe */
-        return current->euid;
+        return current_euid();
 }
 
 asmlinkage long sys_getgid(void)
 {
         /* Only we change this so SMP safe */
-        return current->gid;
+        return current_gid();
 }
 
 asmlinkage long sys_getegid(void)
 {
         /* Only we change this so SMP safe */
-        return  current->egid;
+        return  current_egid();
 }
 
 #endif
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index bde6f03512d5..e2a4ff6fc3a6 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -244,16 +244,21 @@ config STACK_TRACER
 
           This tracer works by hooking into every function call that the
           kernel executes, and keeping a maximum stack depth value and
-          stack-trace saved. Because this logic has to execute in every
-          kernel function, all the time, this option can slow down the
-          kernel measurably and is generally intended for kernel
-          developers only.
+          stack-trace saved.  If this is configured with DYNAMIC_FTRACE
+          then it will not have any overhead while the stack tracer
+          is disabled.
+
+          To enable the stack tracer on bootup, pass in 'stacktrace'
+          on the kernel command line.
+
+          The stack tracer can also be enabled or disabled via the
+          sysctl kernel.stack_tracer_enabled
 
           Say N if unsure.
 
-config BTS_TRACER
+config HW_BRANCH_TRACER
         depends on HAVE_HW_BRANCH_TRACER
-        bool "Trace branches"
+        bool "Trace hw branches"
         select TRACING
         help
           This tracer records all branches on the system in a circular
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 62dc561b6676..349d5a93653f 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -31,7 +31,7 @@ obj-$(CONFIG_MMIOTRACE) += trace_mmiotrace.o
 obj-$(CONFIG_BOOT_TRACER) += trace_boot.o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += trace_functions_graph.o
 obj-$(CONFIG_TRACE_BRANCH_PROFILING) += trace_branch.o
-obj-$(CONFIG_BTS_TRACER) += trace_bts.o
+obj-$(CONFIG_HW_BRANCH_TRACER) += trace_hw_branches.o
 obj-$(CONFIG_POWER_TRACER) += trace_power.o
 
 libftrace-y := ftrace.o
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index a12f80efceaa..2f32969c09df 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1047,6 +1047,13 @@ ftrace_match(unsigned char *buff, int len, int enable)
         int type = MATCH_FULL;
         unsigned long flag = enable ? FTRACE_FL_FILTER : FTRACE_FL_NOTRACE;
         unsigned i, match = 0, search_len = 0;
+        int not = 0;
+
+        if (buff[0] == '!') {
+                not = 1;
+                buff++;
+                len--;
+        }
 
         for (i = 0; i < len; i++) {
                 if (buff[i] == '*') {
@@ -1100,8 +1107,12 @@ ftrace_match(unsigned char *buff, int len, int enable)
                                         matched = 1;
                                 break;
                         }
-                        if (matched)
-                                rec->flags |= flag;
+                        if (matched) {
+                                if (not)
+                                        rec->flags &= ~flag;
+                                else
+                                        rec->flags |= flag;
+                        }
                 }
                 pg = pg->next;
         }
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 7f69cfeaadf7..a9d9760dc7b6 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -69,6 +69,7 @@ void tracing_on(void)
 {
         set_bit(RB_BUFFERS_ON_BIT, &ring_buffer_flags);
 }
+EXPORT_SYMBOL_GPL(tracing_on);
 
 /**
  * tracing_off - turn off all tracing buffers
@@ -82,6 +83,7 @@ void tracing_off(void)
 {
         clear_bit(RB_BUFFERS_ON_BIT, &ring_buffer_flags);
 }
+EXPORT_SYMBOL_GPL(tracing_off);
 
 /**
  * tracing_off_permanent - permanently disable ring buffers
@@ -107,16 +109,18 @@ u64 ring_buffer_time_stamp(int cpu)
         preempt_disable_notrace();
         /* shift to debug/test normalization and TIME_EXTENTS */
         time = sched_clock() << DEBUG_SHIFT;
-        preempt_enable_notrace();
+        preempt_enable_no_resched_notrace();
 
         return time;
 }
+EXPORT_SYMBOL_GPL(ring_buffer_time_stamp);
 
 void ring_buffer_normalize_time_stamp(int cpu, u64 *ts)
 {
         /* Just stupid testing the normalize function and deltas */
         *ts >>= DEBUG_SHIFT;
 }
+EXPORT_SYMBOL_GPL(ring_buffer_normalize_time_stamp);
 
 #define RB_EVNT_HDR_SIZE (sizeof(struct ring_buffer_event))
 #define RB_ALIGNMENT_SHIFT      2
@@ -166,6 +170,7 @@ unsigned ring_buffer_event_length(struct ring_buffer_event *event)
 {
         return rb_event_length(event);
 }
+EXPORT_SYMBOL_GPL(ring_buffer_event_length);
 
 /* inline for ring buffer fast paths */
 static inline void *
@@ -187,9 +192,10 @@ void *ring_buffer_event_data(struct ring_buffer_event *event)
 {
         return rb_event_data(event);
 }
+EXPORT_SYMBOL_GPL(ring_buffer_event_data);
 
 #define for_each_buffer_cpu(buffer, cpu)                \
-        for_each_cpu_mask(cpu, buffer->cpumask)
+        for_each_cpu(cpu, buffer->cpumask)
 
 #define TS_SHIFT        27
 #define TS_MASK         ((1ULL << TS_SHIFT) - 1)
@@ -258,11 +264,10 @@ struct ring_buffer_per_cpu {
 };
 
 struct ring_buffer {
-        unsigned long                   size;
         unsigned                        pages;
         unsigned                        flags;
         int                             cpus;
-        cpumask_t                       cpumask;
+        cpumask_var_t                   cpumask;
         atomic_t                        record_disabled;
 
         struct mutex                    mutex;
@@ -428,7 +433,7 @@ extern int ring_buffer_page_too_big(void);
 
 /**
  * ring_buffer_alloc - allocate a new ring_buffer
- * @size: the size in bytes that is needed.
+ * @size: the size in bytes per cpu that is needed.
  * @flags: attributes to set for the ring buffer.
  *
  * Currently the only flag that is available is the RB_FL_OVERWRITE
@@ -453,6 +458,9 @@ struct ring_buffer *ring_buffer_alloc(unsigned long size, unsigned flags)
         if (!buffer)
                 return NULL;
 
+        if (!alloc_cpumask_var(&buffer->cpumask, GFP_KERNEL))
+                goto fail_free_buffer;
+
         buffer->pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
         buffer->flags = flags;
 
@@ -460,14 +468,14 @@ struct ring_buffer *ring_buffer_alloc(unsigned long size, unsigned flags)
         if (buffer->pages == 1)
                 buffer->pages++;
 
-        buffer->cpumask = cpu_possible_map;
+        cpumask_copy(buffer->cpumask, cpu_possible_mask);
         buffer->cpus = nr_cpu_ids;
 
         bsize = sizeof(void *) * nr_cpu_ids;
         buffer->buffers = kzalloc(ALIGN(bsize, cache_line_size()),
                                   GFP_KERNEL);
         if (!buffer->buffers)
-                goto fail_free_buffer;
+                goto fail_free_cpumask;
 
         for_each_buffer_cpu(buffer, cpu) {
                 buffer->buffers[cpu] =
@@ -487,10 +495,14 @@ struct ring_buffer *ring_buffer_alloc(unsigned long size, unsigned flags)
         }
         kfree(buffer->buffers);
 
+ fail_free_cpumask:
+        free_cpumask_var(buffer->cpumask);
+
  fail_free_buffer:
         kfree(buffer);
         return NULL;
 }
+EXPORT_SYMBOL_GPL(ring_buffer_alloc);
 
 /**
  * ring_buffer_free - free a ring buffer.
@@ -504,8 +516,11 @@ ring_buffer_free(struct ring_buffer *buffer)
         for_each_buffer_cpu(buffer, cpu)
                 rb_free_cpu_buffer(buffer->buffers[cpu]);
 
+        free_cpumask_var(buffer->cpumask);
+
         kfree(buffer);
 }
+EXPORT_SYMBOL_GPL(ring_buffer_free);
 
 static void rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer);
 
@@ -681,6 +696,7 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
         mutex_unlock(&buffer->mutex);
         return -ENOMEM;
 }
+EXPORT_SYMBOL_GPL(ring_buffer_resize);
 
 static inline int rb_null_event(struct ring_buffer_event *event)
 {
@@ -839,6 +855,7 @@ rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer)
          * back to us). This allows us to do a simple loop to
          * assign the commit to the tail.
          */
+ again:
         while (cpu_buffer->commit_page != cpu_buffer->tail_page) {
                 cpu_buffer->commit_page->page->commit =
                         cpu_buffer->commit_page->write;
@@ -854,6 +871,17 @@ rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer)
                         cpu_buffer->commit_page->write;
                 barrier();
         }
+
+        /* again, keep gcc from optimizing */
+        barrier();
+
+        /*
+         * If an interrupt came in just after the first while loop
+         * and pushed the tail page forward, we will be left with
+         * a dangling commit that will never go forward.
+         */
+        if (unlikely(cpu_buffer->commit_page != cpu_buffer->tail_page))
+                goto again;
 }
 
 static void rb_reset_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
@@ -951,12 +979,15 @@ static struct ring_buffer_event *
 __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
                   unsigned type, unsigned long length, u64 *ts)
 {
-        struct buffer_page *tail_page, *head_page, *reader_page;
+        struct buffer_page *tail_page, *head_page, *reader_page, *commit_page;
         unsigned long tail, write;
         struct ring_buffer *buffer = cpu_buffer->buffer;
         struct ring_buffer_event *event;
         unsigned long flags;
 
+        commit_page = cpu_buffer->commit_page;
+        /* we just need to protect against interrupts */
+        barrier();
         tail_page = cpu_buffer->tail_page;
         write = local_add_return(length, &tail_page->write);
         tail = write - length;
@@ -982,7 +1013,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
                  * it all the way around the buffer, bail, and warn
                  * about it.
                  */
-                if (unlikely(next_page == cpu_buffer->commit_page)) {
+                if (unlikely(next_page == commit_page)) {
                         WARN_ON_ONCE(1);
                         goto out_unlock;
                 }
@@ -1260,7 +1291,7 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer,
 
         cpu = raw_smp_processor_id();
 
-        if (!cpu_isset(cpu, buffer->cpumask))
+        if (!cpumask_test_cpu(cpu, buffer->cpumask))
                 goto out;
 
         cpu_buffer = buffer->buffers[cpu];
@@ -1290,6 +1321,7 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer,
         ftrace_preempt_enable(resched);
         return NULL;
 }
+EXPORT_SYMBOL_GPL(ring_buffer_lock_reserve);
 
 static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer,
                       struct ring_buffer_event *event)
@@ -1336,6 +1368,7 @@ int ring_buffer_unlock_commit(struct ring_buffer *buffer,
 
         return 0;
 }
+EXPORT_SYMBOL_GPL(ring_buffer_unlock_commit);
 
 /**
  * ring_buffer_write - write data to the buffer without reserving
@@ -1371,7 +1404,7 @@ int ring_buffer_write(struct ring_buffer *buffer,
 
         cpu = raw_smp_processor_id();
 
-        if (!cpu_isset(cpu, buffer->cpumask))
+        if (!cpumask_test_cpu(cpu, buffer->cpumask))
                 goto out;
 
         cpu_buffer = buffer->buffers[cpu];
@@ -1397,6 +1430,7 @@ int ring_buffer_write(struct ring_buffer *buffer,
 
         return ret;
 }
+EXPORT_SYMBOL_GPL(ring_buffer_write);
 
 static inline int rb_per_cpu_empty(struct ring_buffer_per_cpu *cpu_buffer)
 {
@@ -1423,6 +1457,7 @@ void ring_buffer_record_disable(struct ring_buffer *buffer)
 {
         atomic_inc(&buffer->record_disabled);
 }
+EXPORT_SYMBOL_GPL(ring_buffer_record_disable);
 
 /**
  * ring_buffer_record_enable - enable writes to the buffer
@@ -1435,6 +1470,7 @@ void ring_buffer_record_enable(struct ring_buffer *buffer)
 {
         atomic_dec(&buffer->record_disabled);
 }
+EXPORT_SYMBOL_GPL(ring_buffer_record_enable);
 
 /**
  * ring_buffer_record_disable_cpu - stop all writes into the cpu_buffer
@@ -1450,12 +1486,13 @@ void ring_buffer_record_disable_cpu(struct ring_buffer *buffer, int cpu)
 {
         struct ring_buffer_per_cpu *cpu_buffer;
 
-        if (!cpu_isset(cpu, buffer->cpumask))
+        if (!cpumask_test_cpu(cpu, buffer->cpumask))
                 return;
 
         cpu_buffer = buffer->buffers[cpu];
         atomic_inc(&cpu_buffer->record_disabled);
 }
+EXPORT_SYMBOL_GPL(ring_buffer_record_disable_cpu);
 
 /**
  * ring_buffer_record_enable_cpu - enable writes to the buffer
@@ -1469,12 +1506,13 @@ void ring_buffer_record_enable_cpu(struct ring_buffer *buffer, int cpu)
 {
         struct ring_buffer_per_cpu *cpu_buffer;
 
-        if (!cpu_isset(cpu, buffer->cpumask))
+        if (!cpumask_test_cpu(cpu, buffer->cpumask))
                 return;
 
         cpu_buffer = buffer->buffers[cpu];
         atomic_dec(&cpu_buffer->record_disabled);
 }
+EXPORT_SYMBOL_GPL(ring_buffer_record_enable_cpu);
 
 /**
  * ring_buffer_entries_cpu - get the number of entries in a cpu buffer
@@ -1485,12 +1523,13 @@ unsigned long ring_buffer_entries_cpu(struct ring_buffer *buffer, int cpu)
 {
         struct ring_buffer_per_cpu *cpu_buffer;
 
-        if (!cpu_isset(cpu, buffer->cpumask))
+        if (!cpumask_test_cpu(cpu, buffer->cpumask))
                 return 0;
 
         cpu_buffer = buffer->buffers[cpu];
         return cpu_buffer->entries;
 }
+EXPORT_SYMBOL_GPL(ring_buffer_entries_cpu);
 
 /**
  * ring_buffer_overrun_cpu - get the number of overruns in a cpu_buffer
@@ -1501,12 +1540,13 @@ unsigned long ring_buffer_overrun_cpu(struct ring_buffer *buffer, int cpu)
 {
         struct ring_buffer_per_cpu *cpu_buffer;
 
-        if (!cpu_isset(cpu, buffer->cpumask))
+        if (!cpumask_test_cpu(cpu, buffer->cpumask))
                 return 0;
 
         cpu_buffer = buffer->buffers[cpu];
         return cpu_buffer->overrun;
 }
+EXPORT_SYMBOL_GPL(ring_buffer_overrun_cpu);
 
 /**
  * ring_buffer_entries - get the number of entries in a buffer
@@ -1529,6 +1569,7 @@ unsigned long ring_buffer_entries(struct ring_buffer *buffer)
 
         return entries;
 }
+EXPORT_SYMBOL_GPL(ring_buffer_entries);
 
 /**
  * ring_buffer_overrun_cpu - get the number of overruns in buffer
@@ -1551,6 +1592,7 @@ unsigned long ring_buffer_overruns(struct ring_buffer *buffer)
 
         return overruns;
 }
+EXPORT_SYMBOL_GPL(ring_buffer_overruns);
 
 static void rb_iter_reset(struct ring_buffer_iter *iter)
 {
@@ -1586,6 +1628,7 @@ void ring_buffer_iter_reset(struct ring_buffer_iter *iter)
         rb_iter_reset(iter);
         spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 }
+EXPORT_SYMBOL_GPL(ring_buffer_iter_reset);
 
 /**
  * ring_buffer_iter_empty - check if an iterator has no more to read
@@ -1600,6 +1643,7 @@ int ring_buffer_iter_empty(struct ring_buffer_iter *iter)
         return iter->head_page == cpu_buffer->commit_page &&
                 iter->head == rb_commit_index(cpu_buffer);
 }
+EXPORT_SYMBOL_GPL(ring_buffer_iter_empty);
 
 static void
 rb_update_read_stamp(struct ring_buffer_per_cpu *cpu_buffer,
@@ -1814,7 +1858,7 @@ rb_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
         struct buffer_page *reader;
         int nr_loops = 0;
 
-        if (!cpu_isset(cpu, buffer->cpumask))
+        if (!cpumask_test_cpu(cpu, buffer->cpumask))
                 return NULL;
 
         cpu_buffer = buffer->buffers[cpu];
@@ -1866,6 +1910,7 @@ rb_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
 
         return NULL;
 }
+EXPORT_SYMBOL_GPL(ring_buffer_peek);
 
 static struct ring_buffer_event *
 rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
@@ -1926,6 +1971,7 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 
         return NULL;
 }
+EXPORT_SYMBOL_GPL(ring_buffer_iter_peek);
 
 /**
  * ring_buffer_peek - peek at the next event to be read
@@ -1987,7 +2033,7 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
         struct ring_buffer_event *event;
         unsigned long flags;
 
-        if (!cpu_isset(cpu, buffer->cpumask))
+        if (!cpumask_test_cpu(cpu, buffer->cpumask))
                 return NULL;
 
         spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
@@ -2003,6 +2049,7 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
 
         return event;
 }
+EXPORT_SYMBOL_GPL(ring_buffer_consume);
 
 /**
  * ring_buffer_read_start - start a non consuming read of the buffer
@@ -2023,7 +2070,7 @@ ring_buffer_read_start(struct ring_buffer *buffer, int cpu)
         struct ring_buffer_iter *iter;
         unsigned long flags;
 
-        if (!cpu_isset(cpu, buffer->cpumask))
+        if (!cpumask_test_cpu(cpu, buffer->cpumask))
                 return NULL;
 
         iter = kmalloc(sizeof(*iter), GFP_KERNEL);
@@ -2045,6 +2092,7 @@ ring_buffer_read_start(struct ring_buffer *buffer, int cpu)
 
         return iter;
 }
+EXPORT_SYMBOL_GPL(ring_buffer_read_start);
 
 /**
  * ring_buffer_finish - finish reading the iterator of the buffer
@@ -2061,6 +2109,7 @@ ring_buffer_read_finish(struct ring_buffer_iter *iter)
         atomic_dec(&cpu_buffer->record_disabled);
         kfree(iter);
 }
+EXPORT_SYMBOL_GPL(ring_buffer_read_finish);
 
 /**
  * ring_buffer_read - read the next item in the ring buffer by the iterator
@@ -2087,6 +2136,7 @@ ring_buffer_read(struct ring_buffer_iter *iter, u64 *ts)
 
         return event;
 }
+EXPORT_SYMBOL_GPL(ring_buffer_read);
 
 /**
  * ring_buffer_size - return the size of the ring buffer (in bytes)
@@ -2096,6 +2146,7 @@ unsigned long ring_buffer_size(struct ring_buffer *buffer)
 {
         return BUF_PAGE_SIZE * buffer->pages;
 }
+EXPORT_SYMBOL_GPL(ring_buffer_size);
 
 static void
 rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
@@ -2129,7 +2180,7 @@ void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu)
         struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
         unsigned long flags;
 
-        if (!cpu_isset(cpu, buffer->cpumask))
+        if (!cpumask_test_cpu(cpu, buffer->cpumask))
                 return;
 
         spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
@@ -2142,6 +2193,7 @@ void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu)
 
         spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 }
+EXPORT_SYMBOL_GPL(ring_buffer_reset_cpu);
 
 /**
  * ring_buffer_reset - reset a ring buffer
@@ -2154,6 +2206,7 @@ void ring_buffer_reset(struct ring_buffer *buffer)
         for_each_buffer_cpu(buffer, cpu)
                 ring_buffer_reset_cpu(buffer, cpu);
 }
+EXPORT_SYMBOL_GPL(ring_buffer_reset);
 
 /**
  * rind_buffer_empty - is the ring buffer empty?
@@ -2172,6 +2225,7 @@ int ring_buffer_empty(struct ring_buffer *buffer)
         }
         return 1;
 }
+EXPORT_SYMBOL_GPL(ring_buffer_empty);
 
 /**
  * ring_buffer_empty_cpu - is a cpu buffer of a ring buffer empty?
@@ -2182,12 +2236,13 @@ int ring_buffer_empty_cpu(struct ring_buffer *buffer, int cpu)
 {
         struct ring_buffer_per_cpu *cpu_buffer;
 
-        if (!cpu_isset(cpu, buffer->cpumask))
+        if (!cpumask_test_cpu(cpu, buffer->cpumask))
                 return 1;
 
         cpu_buffer = buffer->buffers[cpu];
         return rb_per_cpu_empty(cpu_buffer);
 }
+EXPORT_SYMBOL_GPL(ring_buffer_empty_cpu);
 
 /**
  * ring_buffer_swap_cpu - swap a CPU buffer between two ring buffers
@@ -2205,13 +2260,12 @@ int ring_buffer_swap_cpu(struct ring_buffer *buffer_a,
         struct ring_buffer_per_cpu *cpu_buffer_a;
         struct ring_buffer_per_cpu *cpu_buffer_b;
 
-        if (!cpu_isset(cpu, buffer_a->cpumask) ||
-            !cpu_isset(cpu, buffer_b->cpumask))
+        if (!cpumask_test_cpu(cpu, buffer_a->cpumask) ||
+            !cpumask_test_cpu(cpu, buffer_b->cpumask))
                 return -EINVAL;
 
         /* At least make sure the two buffers are somewhat the same */
-        if (buffer_a->size != buffer_b->size ||
-            buffer_a->pages != buffer_b->pages)
+        if (buffer_a->pages != buffer_b->pages)
                 return -EINVAL;
 
         cpu_buffer_a = buffer_a->buffers[cpu];
@@ -2237,6 +2291,7 @@ int ring_buffer_swap_cpu(struct ring_buffer *buffer_a,
 
         return 0;
 }
+EXPORT_SYMBOL_GPL(ring_buffer_swap_cpu);
 
 static void rb_remove_entries(struct ring_buffer_per_cpu *cpu_buffer,
                               struct buffer_data_page *bpage)
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 6adf660fc816..c580233add95 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -30,7 +30,6 @@
 #include <linux/gfp.h>
 #include <linux/fs.h>
 #include <linux/kprobes.h>
-#include <linux/seq_file.h>
 #include <linux/writeback.h>
 
 #include <linux/stacktrace.h>
@@ -90,10 +89,10 @@ static inline void ftrace_enable_cpu(void)
         preempt_enable();
 }
 
-static cpumask_t __read_mostly          tracing_buffer_mask;
+static cpumask_var_t __read_mostly      tracing_buffer_mask;
 
 #define for_each_tracing_cpu(cpu)       \
-        for_each_cpu_mask(cpu, tracing_buffer_mask)
+        for_each_cpu(cpu, tracing_buffer_mask)
 
 /*
  * ftrace_dump_on_oops - variable to dump ftrace buffer on oops
@@ -287,6 +286,7 @@ static const char *trace_options[] = {
         "annotate",
         "userstacktrace",
         "sym-userobj",
+        "printk-msg-only",
         NULL
 };
 
@@ -320,7 +320,7 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 
         memcpy(data->comm, tsk->comm, TASK_COMM_LEN);
         data->pid = tsk->pid;
-        data->uid = tsk->uid;
+        data->uid = task_uid(tsk);
         data->nice = tsk->static_prio - 20 - MAX_RT_PRIO;
         data->policy = tsk->policy;
         data->rt_priority = tsk->rt_priority;
@@ -678,6 +678,16 @@ void tracing_reset(struct trace_array *tr, int cpu)
         ftrace_enable_cpu();
 }
 
+void tracing_reset_online_cpus(struct trace_array *tr)
+{
+        int cpu;
+
+        tr->time_start = ftrace_now(tr->cpu);
+
+        for_each_online_cpu(cpu)
+                tracing_reset(tr, cpu);
+}
+
 #define SAVED_CMDLINES 128
 static unsigned map_pid_to_cmdline[PID_MAX_DEFAULT+1];
 static unsigned map_cmdline_to_pid[SAVED_CMDLINES];
@@ -1299,7 +1309,7 @@ enum trace_file_type {
         TRACE_FILE_ANNOTATE     = 2,
 };
 
-static void trace_iterator_increment(struct trace_iterator *iter, int cpu)
+static void trace_iterator_increment(struct trace_iterator *iter)
 {
         /* Don't allow ftrace to trace into the ring buffers */
         ftrace_disable_cpu();
@@ -1378,7 +1388,7 @@ static void *find_next_entry_inc(struct trace_iterator *iter)
         iter->ent = __find_next_entry(iter, &iter->cpu, &iter->ts);
 
         if (iter->ent)
-                trace_iterator_increment(iter, iter->cpu);
+                trace_iterator_increment(iter);
 
         return iter->ent ? iter : NULL;
 }
@@ -1747,6 +1757,13 @@ lat_print_timestamp(struct trace_seq *s, u64 abs_usecs,
 
 static const char state_to_char[] = TASK_STATE_TO_CHAR_STR;
 
+static int task_state_char(unsigned long state)
+{
+        int bit = state ? __ffs(state) + 1 : 0;
+
+        return bit < sizeof(state_to_char) - 1 ? state_to_char[bit] : '?';
+}
+
 /*
  * The message is supposed to contain an ending newline.
  * If the printing stops prematurely, try to add a newline of our own.
@@ -1794,10 +1811,10 @@ static void test_cpu_buff_start(struct trace_iterator *iter)
         if (!(iter->iter_flags & TRACE_FILE_ANNOTATE))
                 return;
 
-        if (cpu_isset(iter->cpu, iter->started))
+        if (cpumask_test_cpu(iter->cpu, iter->started))
                 return;
 
-        cpu_set(iter->cpu, iter->started);
+        cpumask_set_cpu(iter->cpu, iter->started);
         trace_seq_printf(s, "##### CPU %u buffer started ####\n", iter->cpu);
 }
 
@@ -1815,7 +1832,6 @@ print_lat_fmt(struct trace_iterator *iter, unsigned int trace_idx, int cpu)
         char *comm;
         int S, T;
         int i;
-        unsigned state;
 
         if (entry->type == TRACE_CONT)
                 return TRACE_TYPE_HANDLED;
@@ -1861,12 +1877,8 @@ print_lat_fmt(struct trace_iterator *iter, unsigned int trace_idx, int cpu)
 
                 trace_assign_type(field, entry);
 
-                T = field->next_state < sizeof(state_to_char) ?
-                        state_to_char[field->next_state] : 'X';
-
-                state = field->prev_state ?
-                        __ffs(field->prev_state) + 1 : 0;
-                S = state < sizeof(state_to_char) - 1 ? state_to_char[state] : 'X';
+                T = task_state_char(field->next_state);
+                S = task_state_char(field->prev_state);
                 comm = trace_find_cmdline(field->next_pid);
                 trace_seq_printf(s, " %5d:%3d:%c %s [%03d] %5d:%3d:%c %s\n",
                                  field->prev_pid,
@@ -2007,10 +2019,8 @@ static enum print_line_t print_trace_fmt(struct trace_iterator *iter)
 
                 trace_assign_type(field, entry);
 
-                S = field->prev_state < sizeof(state_to_char) ?
-                        state_to_char[field->prev_state] : 'X';
-                T = field->next_state < sizeof(state_to_char) ?
-                        state_to_char[field->next_state] : 'X';
+                T = task_state_char(field->next_state);
+                S = task_state_char(field->prev_state);
                 ret = trace_seq_printf(s, " %5d:%3d:%c %s [%03d] %5d:%3d:%c\n",
                                        field->prev_pid,
                                        field->prev_prio,
@@ -2140,12 +2150,9 @@ static enum print_line_t print_raw_fmt(struct trace_iterator *iter)
 
                 trace_assign_type(field, entry);
 
-                S = field->prev_state < sizeof(state_to_char) ?
-                        state_to_char[field->prev_state] : 'X';
-                T = field->next_state < sizeof(state_to_char) ?
-                        state_to_char[field->next_state] : 'X';
-                if (entry->type == TRACE_WAKE)
-                        S = '+';
+                T = task_state_char(field->next_state);
+                S = entry->type == TRACE_WAKE ? '+' :
+                        task_state_char(field->prev_state);
                 ret = trace_seq_printf(s, "%d %d %c %d %d %d %c\n",
                                        field->prev_pid,
                                        field->prev_prio,
@@ -2232,12 +2239,9 @@ static enum print_line_t print_hex_fmt(struct trace_iterator *iter)
 
                 trace_assign_type(field, entry);
 
-                S = field->prev_state < sizeof(state_to_char) ?
-                        state_to_char[field->prev_state] : 'X';
-                T = field->next_state < sizeof(state_to_char) ?
-                        state_to_char[field->next_state] : 'X';
-                if (entry->type == TRACE_WAKE)
-                        S = '+';
+                T = task_state_char(field->next_state);
+                S = entry->type == TRACE_WAKE ? '+' :
+                        task_state_char(field->prev_state);
                 SEQ_PUT_HEX_FIELD_RET(s, field->prev_pid);
                 SEQ_PUT_HEX_FIELD_RET(s, field->prev_prio);
                 SEQ_PUT_HEX_FIELD_RET(s, S);
@@ -2265,6 +2269,25 @@ static enum print_line_t print_hex_fmt(struct trace_iterator *iter)
         return TRACE_TYPE_HANDLED;
 }
 
+static enum print_line_t print_printk_msg_only(struct trace_iterator *iter)
+{
+        struct trace_seq *s = &iter->seq;
+        struct trace_entry *entry = iter->ent;
+        struct print_entry *field;
+        int ret;
+
+        trace_assign_type(field, entry);
+
+        ret = trace_seq_printf(s, field->buf);
+        if (!ret)
+                return TRACE_TYPE_PARTIAL_LINE;
+
+        if (entry->flags & TRACE_FLAG_CONT)
+                trace_seq_print_cont(s, iter);
+
+        return TRACE_TYPE_HANDLED;
+}
+
 static enum print_line_t print_bin_fmt(struct trace_iterator *iter)
 {
         struct trace_seq *s = &iter->seq;
@@ -2345,6 +2368,11 @@ static enum print_line_t print_trace_line(struct trace_iterator *iter)
                         return ret;
         }
 
+        if (iter->ent->type == TRACE_PRINT &&
+                        trace_flags & TRACE_ITER_PRINTK &&
+                        trace_flags & TRACE_ITER_PRINTK_MSGONLY)
+                return print_printk_msg_only(iter);
+
         if (trace_flags & TRACE_ITER_BIN)
                 return print_bin_fmt(iter);
 
@@ -2425,7 +2453,7 @@ __tracing_open(struct inode *inode, struct file *file, int *ret)
 
         /* Notify the tracer early; before we stop tracing. */
         if (iter->trace && iter->trace->open)
-                        iter->trace->open(iter);
+                iter->trace->open(iter);
 
         /* Annotate start of buffers if we had overruns */
         if (ring_buffer_overruns(iter->tr->buffer))
@@ -2618,13 +2646,7 @@ static struct file_operations show_traces_fops = {
 /*
  * Only trace on a CPU if the bitmask is set:
  */
-static cpumask_t tracing_cpumask = CPU_MASK_ALL;
-
-/*
- * When tracing/tracing_cpu_mask is modified then this holds
- * the new bitmask we are about to install:
- */
-static cpumask_t tracing_cpumask_new;
+static cpumask_var_t tracing_cpumask;
 
 /*
  * The tracer itself will not take this lock, but still we want
@@ -2646,7 +2668,7 @@ tracing_cpumask_read(struct file *filp, char __user *ubuf,
 
         mutex_lock(&tracing_cpumask_update_lock);
 
-        len = cpumask_scnprintf(mask_str, count, &tracing_cpumask);
+        len = cpumask_scnprintf(mask_str, count, tracing_cpumask);
         if (count - len < 2) {
                 count = -EINVAL;
                 goto out_err;
@@ -2665,9 +2687,13 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
                       size_t count, loff_t *ppos)
 {
         int err, cpu;
+        cpumask_var_t tracing_cpumask_new;
+
+        if (!alloc_cpumask_var(&tracing_cpumask_new, GFP_KERNEL))
+                return -ENOMEM;
 
         mutex_lock(&tracing_cpumask_update_lock);
-        err = cpumask_parse_user(ubuf, count, &tracing_cpumask_new);
+        err = cpumask_parse_user(ubuf, count, tracing_cpumask_new);
         if (err)
                 goto err_unlock;
 
@@ -2678,26 +2704,28 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
                  * Increase/decrease the disabled counter if we are
                  * about to flip a bit in the cpumask:
                  */
-                if (cpu_isset(cpu, tracing_cpumask) &&
-                                !cpu_isset(cpu, tracing_cpumask_new)) {
+                if (cpumask_test_cpu(cpu, tracing_cpumask) &&
+                                !cpumask_test_cpu(cpu, tracing_cpumask_new)) {
                         atomic_inc(&global_trace.data[cpu]->disabled);
                 }
-                if (!cpu_isset(cpu, tracing_cpumask) &&
-                                cpu_isset(cpu, tracing_cpumask_new)) {
+                if (!cpumask_test_cpu(cpu, tracing_cpumask) &&
+                                cpumask_test_cpu(cpu, tracing_cpumask_new)) {
                         atomic_dec(&global_trace.data[cpu]->disabled);
                 }
         }
         __raw_spin_unlock(&ftrace_max_lock);
         local_irq_enable();
 
-        tracing_cpumask = tracing_cpumask_new;
+        cpumask_copy(tracing_cpumask, tracing_cpumask_new);
 
         mutex_unlock(&tracing_cpumask_update_lock);
+        free_cpumask_var(tracing_cpumask_new);
 
         return count;
 
 err_unlock:
         mutex_unlock(&tracing_cpumask_update_lock);
+        free_cpumask_var(tracing_cpumask);
 
         return err;
 }
@@ -3086,10 +3114,15 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
         if (!iter)
                 return -ENOMEM;
 
+        if (!alloc_cpumask_var(&iter->started, GFP_KERNEL)) {
+                kfree(iter);
+                return -ENOMEM;
+        }
+
         mutex_lock(&trace_types_lock);
 
         /* trace pipe does not show start of buffer */
-        cpus_setall(iter->started);
+        cpumask_setall(iter->started);
 
         iter->tr = &global_trace;
         iter->trace = current_trace;
@@ -3106,6 +3139,7 @@ static int tracing_release_pipe(struct inode *inode, struct file *file)
 {
         struct trace_iterator *iter = file->private_data;
 
+        free_cpumask_var(iter->started);
         kfree(iter);
         atomic_dec(&tracing_reader);
 
@@ -3724,7 +3758,6 @@ void ftrace_dump(void)
         static DEFINE_SPINLOCK(ftrace_dump_lock);
         /* use static because iter can be a bit big for the stack */
         static struct trace_iterator iter;
-        static cpumask_t mask;
         static int dump_ran;
         unsigned long flags;
         int cnt = 0, cpu;
@@ -3758,8 +3791,6 @@ void ftrace_dump(void)
          * and then release the locks again.
          */
 
-        cpus_clear(mask);
-
         while (!trace_empty(&iter)) {
 
                 if (!cnt)
@@ -3795,19 +3826,28 @@ __init static int tracer_alloc_buffers(void)
 {
         struct trace_array_cpu *data;
         int i;
+        int ret = -ENOMEM;
 
-        /* TODO: make the number of buffers hot pluggable with CPUS */
-        tracing_buffer_mask = cpu_possible_map;
+        if (!alloc_cpumask_var(&tracing_buffer_mask, GFP_KERNEL))
+                goto out;
+
+        if (!alloc_cpumask_var(&tracing_cpumask, GFP_KERNEL))
+                goto out_free_buffer_mask;
 
+        cpumask_copy(tracing_buffer_mask, cpu_possible_mask);
+        cpumask_copy(tracing_cpumask, cpu_all_mask);
+
+        /* TODO: make the number of buffers hot pluggable with CPUS */
         global_trace.buffer = ring_buffer_alloc(trace_buf_size,
                                                    TRACE_BUFFER_FLAGS);
         if (!global_trace.buffer) {
                 printk(KERN_ERR "tracer: failed to allocate ring buffer!\n");
                 WARN_ON(1);
-                return 0;
+                goto out_free_cpumask;
         }
         global_trace.entries = ring_buffer_size(global_trace.buffer);
 
+
 #ifdef CONFIG_TRACER_MAX_TRACE
         max_tr.buffer = ring_buffer_alloc(trace_buf_size,
                                              TRACE_BUFFER_FLAGS);
@@ -3815,7 +3855,7 @@ __init static int tracer_alloc_buffers(void)
                 printk(KERN_ERR "tracer: failed to allocate max ring buffer!\n");
                 WARN_ON(1);
                 ring_buffer_free(global_trace.buffer);
-                return 0;
+                goto out_free_cpumask;
         }
         max_tr.entries = ring_buffer_size(max_tr.buffer);
         WARN_ON(max_tr.entries != global_trace.entries);
@@ -3845,8 +3885,14 @@ __init static int tracer_alloc_buffers(void)
                                        &trace_panic_notifier);
 
         register_die_notifier(&trace_die_notifier);
+        ret = 0;
 
-        return 0;
+out_free_cpumask:
+        free_cpumask_var(tracing_cpumask);
+out_free_buffer_mask:
+        free_cpumask_var(tracing_buffer_mask);
+out:
+        return ret;
 }
 early_initcall(tracer_alloc_buffers);
 fs_initcall(tracer_init_debugfs);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 5ac697065a48..4d3d381bfd95 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -28,7 +28,7 @@ enum trace_type {
         TRACE_GRAPH_RET,
         TRACE_GRAPH_ENT,
         TRACE_USER_STACK,
-        TRACE_BTS,
+        TRACE_HW_BRANCHES,
         TRACE_POWER,
 
         __TRACE_LAST_TYPE
@@ -159,10 +159,10 @@ struct trace_branch {
         char                    correct;
 };
 
-struct bts_entry {
+struct hw_branch_entry {
         struct trace_entry      ent;
-        unsigned long           from;
-        unsigned long           to;
+        u64                     from;
+        u64                     to;
 };
 
 struct trace_power {
@@ -278,7 +278,7 @@ extern void __ftrace_bad_type(void);
                           TRACE_GRAPH_ENT);             \
                 IF_ASSIGN(var, ent, struct ftrace_graph_ret_entry,      \
                           TRACE_GRAPH_RET);             \
-                IF_ASSIGN(var, ent, struct bts_entry, TRACE_BTS);\
+                IF_ASSIGN(var, ent, struct hw_branch_entry, TRACE_HW_BRANCHES);\
                 IF_ASSIGN(var, ent, struct trace_power, TRACE_POWER); \
                 __ftrace_bad_type();                                    \
         } while (0)
@@ -368,12 +368,13 @@ struct trace_iterator {
         loff_t                  pos;
         long                    idx;
 
-        cpumask_t               started;
+        cpumask_var_t           started;
 };
 
 int tracing_is_enabled(void);
 void trace_wake_up(void);
 void tracing_reset(struct trace_array *tr, int cpu);
+void tracing_reset_online_cpus(struct trace_array *tr);
 int tracing_open_generic(struct inode *inode, struct file *filp);
 struct dentry *tracing_init_dentry(void);
 void init_tracer_sysprof_debugfs(struct dentry *d_tracer);
@@ -414,9 +415,7 @@ void trace_function(struct trace_array *tr,
 
 void trace_graph_return(struct ftrace_graph_ret *trace);
 int trace_graph_entry(struct ftrace_graph_ent *trace);
-void trace_bts(struct trace_array *tr,
-               unsigned long from,
-               unsigned long to);
+void trace_hw_branch(struct trace_array *tr, u64 from, u64 to);
 
 void tracing_start_cmdline_record(void);
 void tracing_stop_cmdline_record(void);
@@ -580,7 +579,8 @@ enum trace_iterator_flags {
         TRACE_ITER_BRANCH               = 0x1000,
         TRACE_ITER_ANNOTATE             = 0x2000,
         TRACE_ITER_USERSTACKTRACE       = 0x4000,
-        TRACE_ITER_SYM_USEROBJ          = 0x8000
+        TRACE_ITER_SYM_USEROBJ          = 0x8000,
+        TRACE_ITER_PRINTK_MSGONLY       = 0x10000
 };
 
 /*
diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c
index a4fa2c57e34e..366c8c333e13 100644
--- a/kernel/trace/trace_boot.c
+++ b/kernel/trace/trace_boot.c
@@ -37,22 +37,12 @@ void disable_boot_trace(void)
                 tracing_stop_sched_switch_record();
 }
 
-static void reset_boot_trace(struct trace_array *tr)
-{
-        int cpu;
-
-        tr->time_start = ftrace_now(tr->cpu);
-
-        for_each_online_cpu(cpu)
-                tracing_reset(tr, cpu);
-}
-
 static int boot_trace_init(struct trace_array *tr)
 {
         int cpu;
         boot_trace = tr;
 
-        for_each_cpu_mask(cpu, cpu_possible_map)
+        for_each_cpu(cpu, cpu_possible_mask)
                 tracing_reset(tr, cpu);
 
         tracing_sched_switch_assign_trace(tr);
@@ -130,7 +120,7 @@ struct tracer boot_tracer __read_mostly =
 {
         .name           = "initcall",
         .init           = boot_trace_init,
-        .reset          = reset_boot_trace,
+        .reset          = tracing_reset_online_cpus,
         .print_line     = initcall_print_line,
 };
 
diff --git a/kernel/trace/trace_bts.c b/kernel/trace/trace_bts.c
deleted file mode 100644
index 23b76e4690ef..000000000000
--- a/kernel/trace/trace_bts.c
+++ /dev/null
@@ -1,276 +0,0 @@
-/*
- * BTS tracer
- *
- * Copyright (C) 2008 Markus Metzger <markus.t.metzger@gmail.com>
- *
- */
-
-#include <linux/module.h>
-#include <linux/fs.h>
-#include <linux/debugfs.h>
-#include <linux/ftrace.h>
-#include <linux/kallsyms.h>
-
-#include <asm/ds.h>
-
-#include "trace.h"
-
-
-#define SIZEOF_BTS (1 << 13)
-
-static DEFINE_PER_CPU(struct bts_tracer *, tracer);
-static DEFINE_PER_CPU(unsigned char[SIZEOF_BTS], buffer);
-
-#define this_tracer per_cpu(tracer, smp_processor_id())
-#define this_buffer per_cpu(buffer, smp_processor_id())
-
-
-/*
- * Information to interpret a BTS record.
- * This will go into an in-kernel BTS interface.
- */
-static unsigned char sizeof_field;
-static unsigned long debugctl_mask;
-
-#define sizeof_bts (3 * sizeof_field)
-
-static void bts_trace_cpuinit(struct cpuinfo_x86 *c)
-{
-        switch (c->x86) {
-        case 0x6:
-                switch (c->x86_model) {
-                case 0x0 ... 0xC:
-                        break;
-                case 0xD:
-                case 0xE: /* Pentium M */
-                        sizeof_field = sizeof(long);
-                        debugctl_mask = (1<<6)|(1<<7);
-                        break;
-                default:
-                        sizeof_field = 8;
-                        debugctl_mask = (1<<6)|(1<<7);
-                        break;
-                }
-                break;
-        case 0xF:
-                switch (c->x86_model) {
-                case 0x0:
-                case 0x1:
-                case 0x2: /* Netburst */
-                        sizeof_field = sizeof(long);
-                        debugctl_mask = (1<<2)|(1<<3);
-                        break;
-                default:
-                        /* sorry, don't know about them */
-                        break;
-                }
-                break;
-        default:
-                /* sorry, don't know about them */
-                break;
-        }
-}
-
-static inline void bts_enable(void)
-{
-        unsigned long debugctl;
-
-        rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
-        wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl | debugctl_mask);
-}
-
-static inline void bts_disable(void)
-{
-        unsigned long debugctl;
-
-        rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
-        wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl & ~debugctl_mask);
-}
-
-static void bts_trace_reset(struct trace_array *tr)
-{
-        int cpu;
-
-        tr->time_start = ftrace_now(tr->cpu);
-
-        for_each_online_cpu(cpu)
-                tracing_reset(tr, cpu);
-}
-
-static void bts_trace_start_cpu(void *arg)
-{
-        this_tracer =
-                ds_request_bts(/* task = */ NULL, this_buffer, SIZEOF_BTS,
-                               /* ovfl = */ NULL, /* th = */ (size_t)-1);
-        if (IS_ERR(this_tracer)) {
-                this_tracer = NULL;
-                return;
-        }
-
-        bts_enable();
-}
-
-static void bts_trace_start(struct trace_array *tr)
-{
-        int cpu;
-
-        bts_trace_reset(tr);
-
-        for_each_cpu_mask(cpu, cpu_possible_map)
-                smp_call_function_single(cpu, bts_trace_start_cpu, NULL, 1);
-}
-
-static void bts_trace_stop_cpu(void *arg)
-{
-        if (this_tracer) {
-                bts_disable();
-
-                ds_release_bts(this_tracer);
-                this_tracer = NULL;
-        }
-}
-
-static void bts_trace_stop(struct trace_array *tr)
-{
-        int cpu;
-
-        for_each_cpu_mask(cpu, cpu_possible_map)
-                smp_call_function_single(cpu, bts_trace_stop_cpu, NULL, 1);
-}
-
-static int bts_trace_init(struct trace_array *tr)
-{
-        bts_trace_cpuinit(&boot_cpu_data);
-        bts_trace_reset(tr);
-        bts_trace_start(tr);
-
-        return 0;
-}
-
-static void bts_trace_print_header(struct seq_file *m)
-{
-#ifdef __i386__
-        seq_puts(m, "# CPU#    FROM           TO     FUNCTION\n");
-        seq_puts(m, "#  |       |             |         |\n");
-#else
-        seq_puts(m,
-                 "# CPU#        FROM                   TO         FUNCTION\n");
-        seq_puts(m,
-                 "#  |           |                     |             |\n");
-#endif
-}
-
-static enum print_line_t bts_trace_print_line(struct trace_iterator *iter)
-{
-        struct trace_entry *entry = iter->ent;
-        struct trace_seq *seq = &iter->seq;
-        struct bts_entry *it;
-
-        trace_assign_type(it, entry);
-
-        if (entry->type == TRACE_BTS) {
-                int ret;
-#ifdef CONFIG_KALLSYMS
-                char function[KSYM_SYMBOL_LEN];
-                sprint_symbol(function, it->from);
-#else
-                char *function = "<unknown>";
-#endif
-
-                ret = trace_seq_printf(seq, "%4d  0x%lx -> 0x%lx [%s]\n",
-                                       entry->cpu, it->from, it->to, function);
-                if (!ret)
-                        return TRACE_TYPE_PARTIAL_LINE;;
-                return TRACE_TYPE_HANDLED;
-        }
-        return TRACE_TYPE_UNHANDLED;
-}
-
-void trace_bts(struct trace_array *tr, unsigned long from, unsigned long to)
-{
-        struct ring_buffer_event *event;
-        struct bts_entry *entry;
-        unsigned long irq;
-
-        event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry), &irq);
-        if (!event)
-                return;
-        entry   = ring_buffer_event_data(event);
-        tracing_generic_entry_update(&entry->ent, 0, from);
-        entry->ent.type = TRACE_BTS;
-        entry->ent.cpu = smp_processor_id();
-        entry->from = from;
-        entry->to   = to;
-        ring_buffer_unlock_commit(tr->buffer, event, irq);
-}
-
-static void trace_bts_at(struct trace_array *tr, size_t index)
-{
-        const void *raw = NULL;
-        unsigned long from, to;
-        int err;
-
-        err = ds_access_bts(this_tracer, index, &raw);
-        if (err < 0)
-                return;
-
-        from = *(const unsigned long *)raw;
-        to = *(const unsigned long *)((const char *)raw + sizeof_field);
-
-        trace_bts(tr, from, to);
-}
-
-static void trace_bts_cpu(void *arg)
-{
-        struct trace_array *tr = (struct trace_array *) arg;
-        size_t index = 0, end = 0, i;
-        int err;
-
-        if (!this_tracer)
-                return;
-
-        bts_disable();
-
-        err = ds_get_bts_index(this_tracer, &index);
-        if (err < 0)
-                goto out;
-
-        err = ds_get_bts_end(this_tracer, &end);
-        if (err < 0)
-                goto out;
-
-        for (i = index; i < end; i++)
-                trace_bts_at(tr, i);
-
-        for (i = 0; i < index; i++)
-                trace_bts_at(tr, i);
-
-out:
-        bts_enable();
-}
-
-static void trace_bts_prepare(struct trace_iterator *iter)
-{
-        int cpu;
-
-        for_each_cpu_mask(cpu, cpu_possible_map)
-                smp_call_function_single(cpu, trace_bts_cpu, iter->tr, 1);
-}
-
-struct tracer bts_tracer __read_mostly =
-{
-        .name           = "bts",
-        .init           = bts_trace_init,
-        .reset          = bts_trace_stop,
-        .print_header   = bts_trace_print_header,
-        .print_line     = bts_trace_print_line,
-        .start          = bts_trace_start,
-        .stop           = bts_trace_stop,
-        .open           = trace_bts_prepare
-};
-
-__init static int init_bts_trace(void)
-{
-        return register_tracer(&bts_tracer);
-}
-device_initcall(init_bts_trace);
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index e74f6d0a3216..9236d7e25a16 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -16,20 +16,10 @@
 
 #include "trace.h"
 
-static void function_reset(struct trace_array *tr)
-{
-        int cpu;
-
-        tr->time_start = ftrace_now(tr->cpu);
-
-        for_each_online_cpu(cpu)
-                tracing_reset(tr, cpu);
-}
-
 static void start_function_trace(struct trace_array *tr)
 {
         tr->cpu = get_cpu();
-        function_reset(tr);
+        tracing_reset_online_cpus(tr);
         put_cpu();
 
         tracing_start_cmdline_record();
@@ -55,7 +45,7 @@ static void function_trace_reset(struct trace_array *tr)
 
 static void function_trace_start(struct trace_array *tr)
 {
-        function_reset(tr);
+        tracing_reset_online_cpus(tr);
 }
 
 static struct tracer function_trace __read_mostly =
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index af60eef4cbcc..930c08e5b38e 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -79,7 +79,7 @@ print_graph_cpu(struct trace_seq *s, int cpu)
         int i;
         int ret;
         int log10_this = log10_cpu(cpu);
-        int log10_all = log10_cpu(cpus_weight_nr(cpu_online_map));
+        int log10_all = log10_cpu(cpumask_weight(cpu_online_mask));
 
 
         /*
@@ -231,6 +231,49 @@ trace_branch_is_leaf(struct trace_iterator *iter,
         return true;
 }
 
+static enum print_line_t
+print_graph_irq(struct trace_seq *s, unsigned long addr,
+                                enum trace_type type, int cpu, pid_t pid)
+{
+        int ret;
+
+        if (addr < (unsigned long)__irqentry_text_start ||
+                addr >= (unsigned long)__irqentry_text_end)
+                return TRACE_TYPE_UNHANDLED;
+
+        if (type == TRACE_GRAPH_ENT) {
+                ret = trace_seq_printf(s, "==========> |  ");
+        } else {
+                /* Cpu */
+                if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU) {
+                        ret = print_graph_cpu(s, cpu);
+                        if (ret == TRACE_TYPE_PARTIAL_LINE)
+                                return TRACE_TYPE_PARTIAL_LINE;
+                }
+                /* Proc */
+                if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC) {
+                        ret = print_graph_proc(s, pid);
+                        if (ret == TRACE_TYPE_PARTIAL_LINE)
+                                return TRACE_TYPE_PARTIAL_LINE;
+
+                        ret = trace_seq_printf(s, " | ");
+                        if (!ret)
+                                return TRACE_TYPE_PARTIAL_LINE;
+                }
+
+                /* No overhead */
+                if (tracer_flags.val & TRACE_GRAPH_PRINT_OVERHEAD) {
+                        ret = trace_seq_printf(s, "  ");
+                        if (!ret)
+                                return TRACE_TYPE_PARTIAL_LINE;
+                }
+
+                ret = trace_seq_printf(s, "<========== |\n");
+        }
+        if (!ret)
+                return TRACE_TYPE_PARTIAL_LINE;
+        return TRACE_TYPE_HANDLED;
+}
 
 static enum print_line_t
 print_graph_duration(unsigned long long duration, struct trace_seq *s)
@@ -344,7 +387,7 @@ print_graph_entry_leaf(struct trace_iterator *iter,
 
 static enum print_line_t
 print_graph_entry_nested(struct ftrace_graph_ent_entry *entry,
-                        struct trace_seq *s)
+                        struct trace_seq *s, pid_t pid, int cpu)
 {
         int i;
         int ret;
@@ -357,8 +400,18 @@ print_graph_entry_nested(struct ftrace_graph_ent_entry *entry,
                         return TRACE_TYPE_PARTIAL_LINE;
         }
 
-        /* No time */
-        ret = trace_seq_printf(s, "            |  ");
+        /* Interrupt */
+        ret = print_graph_irq(s, call->func, TRACE_GRAPH_ENT, cpu, pid);
+        if (ret == TRACE_TYPE_UNHANDLED) {
+                /* No time */
+                ret = trace_seq_printf(s, "            |  ");
+                if (!ret)
+                        return TRACE_TYPE_PARTIAL_LINE;
+        } else {
+                if (ret == TRACE_TYPE_PARTIAL_LINE)
+                        return TRACE_TYPE_PARTIAL_LINE;
+        }
+
 
         /* Function */
         for (i = 0; i < call->depth * TRACE_GRAPH_INDENT; i++) {
@@ -410,7 +463,7 @@ print_graph_entry(struct ftrace_graph_ent_entry *field, struct trace_seq *s,
         if (trace_branch_is_leaf(iter, field))
                 return print_graph_entry_leaf(iter, field, s);
         else
-                return print_graph_entry_nested(field, s);
+                return print_graph_entry_nested(field, s, iter->ent->pid, cpu);
 
 }
 
@@ -474,6 +527,11 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
                 if (!ret)
                         return TRACE_TYPE_PARTIAL_LINE;
         }
+
+        ret = print_graph_irq(s, trace->func, TRACE_GRAPH_RET, cpu, ent->pid);
+        if (ret == TRACE_TYPE_PARTIAL_LINE)
+                return TRACE_TYPE_PARTIAL_LINE;
+
         return TRACE_TYPE_HANDLED;
 }
 
diff --git a/kernel/trace/trace_hw_branches.c b/kernel/trace/trace_hw_branches.c
new file mode 100644
index 000000000000..649df22d435f
--- /dev/null
+++ b/kernel/trace/trace_hw_branches.c
@@ -0,0 +1,195 @@
+/*
+ * h/w branch tracer for x86 based on bts
+ *
+ * Copyright (C) 2008 Markus Metzger <markus.t.metzger@gmail.com>
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/debugfs.h>
+#include <linux/ftrace.h>
+#include <linux/kallsyms.h>
+
+#include <asm/ds.h>
+
+#include "trace.h"
+
+
+#define SIZEOF_BTS (1 << 13)
+
+static DEFINE_PER_CPU(struct bts_tracer *, tracer);
+static DEFINE_PER_CPU(unsigned char[SIZEOF_BTS], buffer);
+
+#define this_tracer per_cpu(tracer, smp_processor_id())
+#define this_buffer per_cpu(buffer, smp_processor_id())
+
+
+static void bts_trace_start_cpu(void *arg)
+{
+        if (this_tracer)
+                ds_release_bts(this_tracer);
+
+        this_tracer =
+                ds_request_bts(/* task = */ NULL, this_buffer, SIZEOF_BTS,
+                               /* ovfl = */ NULL, /* th = */ (size_t)-1,
+                               BTS_KERNEL);
+        if (IS_ERR(this_tracer)) {
+                this_tracer = NULL;
+                return;
+        }
+}
+
+static void bts_trace_start(struct trace_array *tr)
+{
+        int cpu;
+
+        tracing_reset_online_cpus(tr);
+
+        for_each_cpu(cpu, cpu_possible_mask)
+                smp_call_function_single(cpu, bts_trace_start_cpu, NULL, 1);
+}
+
+static void bts_trace_stop_cpu(void *arg)
+{
+        if (this_tracer) {
+                ds_release_bts(this_tracer);
+                this_tracer = NULL;
+        }
+}
+
+static void bts_trace_stop(struct trace_array *tr)
+{
+        int cpu;
+
+        for_each_cpu(cpu, cpu_possible_mask)
+                smp_call_function_single(cpu, bts_trace_stop_cpu, NULL, 1);
+}
+
+static int bts_trace_init(struct trace_array *tr)
+{
+        tracing_reset_online_cpus(tr);
+        bts_trace_start(tr);
+
+        return 0;
+}
+
+static void bts_trace_print_header(struct seq_file *m)
+{
+        seq_puts(m,
+                 "# CPU#        FROM                   TO         FUNCTION\n");
+        seq_puts(m,
+                 "#  |           |                     |             |\n");
+}
+
+static enum print_line_t bts_trace_print_line(struct trace_iterator *iter)
+{
+        struct trace_entry *entry = iter->ent;
+        struct trace_seq *seq = &iter->seq;
+        struct hw_branch_entry *it;
+
+        trace_assign_type(it, entry);
+
+        if (entry->type == TRACE_HW_BRANCHES) {
+                if (trace_seq_printf(seq, "%4d  ", entry->cpu) &&
+                    trace_seq_printf(seq, "0x%016llx -> 0x%016llx ",
+                                     it->from, it->to) &&
+                    (!it->from ||
+                     seq_print_ip_sym(seq, it->from, /* sym_flags = */ 0)) &&
+                    trace_seq_printf(seq, "\n"))
+                        return TRACE_TYPE_HANDLED;
+                return TRACE_TYPE_PARTIAL_LINE;;
+        }
+        return TRACE_TYPE_UNHANDLED;
+}
+
+void trace_hw_branch(struct trace_array *tr, u64 from, u64 to)
+{
+        struct ring_buffer_event *event;
+        struct hw_branch_entry *entry;
+        unsigned long irq;
+
+        event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry), &irq);
+        if (!event)
+                return;
+        entry   = ring_buffer_event_data(event);
+        tracing_generic_entry_update(&entry->ent, 0, from);
+        entry->ent.type = TRACE_HW_BRANCHES;
+        entry->ent.cpu = smp_processor_id();
+        entry->from = from;
+        entry->to   = to;
+        ring_buffer_unlock_commit(tr->buffer, event, irq);
+}
+
+static void trace_bts_at(struct trace_array *tr,
+                         const struct bts_trace *trace, void *at)
+{
+        struct bts_struct bts;
+        int err = 0;
+
+        WARN_ON_ONCE(!trace->read);
+        if (!trace->read)
+                return;
+
+        err = trace->read(this_tracer, at, &bts);
+        if (err < 0)
+                return;
+
+        switch (bts.qualifier) {
+        case BTS_BRANCH:
+                trace_hw_branch(tr, bts.variant.lbr.from, bts.variant.lbr.to);
+                break;
+        }
+}
+
+static void trace_bts_cpu(void *arg)
+{
+        struct trace_array *tr = (struct trace_array *) arg;
+        const struct bts_trace *trace;
+        unsigned char *at;
+
+        if (!this_tracer)
+                return;
+
+        ds_suspend_bts(this_tracer);
+        trace = ds_read_bts(this_tracer);
+        if (!trace)
+                goto out;
+
+        for (at = trace->ds.top; (void *)at < trace->ds.end;
+             at += trace->ds.size)
+                trace_bts_at(tr, trace, at);
+
+        for (at = trace->ds.begin; (void *)at < trace->ds.top;
+             at += trace->ds.size)
+                trace_bts_at(tr, trace, at);
+
+out:
+        ds_resume_bts(this_tracer);
+}
+
+static void trace_bts_prepare(struct trace_iterator *iter)
+{
+        int cpu;
+
+        for_each_cpu(cpu, cpu_possible_mask)
+                smp_call_function_single(cpu, trace_bts_cpu, iter->tr, 1);
+}
+
+struct tracer bts_tracer __read_mostly =
+{
+        .name           = "hw-branch-tracer",
+        .init           = bts_trace_init,
+        .reset          = bts_trace_stop,
+        .print_header   = bts_trace_print_header,
+        .print_line     = bts_trace_print_line,
+        .start          = bts_trace_start,
+        .stop           = bts_trace_stop,
+        .open           = trace_bts_prepare
+};
+
+__init static int init_bts_trace(void)
+{
+        return register_tracer(&bts_tracer);
+}
+device_initcall(init_bts_trace);
diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c
index 2fb6da6523b3..fffcb069f1dc 100644
--- a/kernel/trace/trace_mmiotrace.c
+++ b/kernel/trace/trace_mmiotrace.c
@@ -22,14 +22,10 @@ static unsigned long prev_overruns;
 
 static void mmio_reset_data(struct trace_array *tr)
 {
-        int cpu;
-
         overrun_detected = false;
         prev_overruns = 0;
-        tr->time_start = ftrace_now(tr->cpu);
 
-        for_each_online_cpu(cpu)
-                tracing_reset(tr, cpu);
+        tracing_reset_online_cpus(tr);
 }
 
 static int mmio_trace_init(struct trace_array *tr)
diff --git a/kernel/trace/trace_power.c b/kernel/trace/trace_power.c
index a7172a352f62..7bda248daf55 100644
--- a/kernel/trace/trace_power.c
+++ b/kernel/trace/trace_power.c
@@ -39,7 +39,7 @@ static int power_trace_init(struct trace_array *tr)
 
         trace_power_enabled = 1;
 
-        for_each_cpu_mask(cpu, cpu_possible_map)
+        for_each_cpu(cpu, cpu_possible_mask)
                 tracing_reset(tr, cpu);
         return 0;
 }
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index 863390557b44..df175cb4564f 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -49,7 +49,7 @@ probe_sched_switch(struct rq *__rq, struct task_struct *prev,
 }
 
 static void
-probe_sched_wakeup(struct rq *__rq, struct task_struct *wakee)
+probe_sched_wakeup(struct rq *__rq, struct task_struct *wakee, int success)
 {
         struct trace_array_cpu *data;
         unsigned long flags;
@@ -72,16 +72,6 @@ probe_sched_wakeup(struct rq *__rq, struct task_struct *wakee)
         local_irq_restore(flags);
 }
 
-static void sched_switch_reset(struct trace_array *tr)
-{
-        int cpu;
-
-        tr->time_start = ftrace_now(tr->cpu);
-
-        for_each_online_cpu(cpu)
-                tracing_reset(tr, cpu);
-}
-
 static int tracing_sched_register(void)
 {
         int ret;
@@ -197,7 +187,7 @@ void tracing_sched_switch_assign_trace(struct trace_array *tr)
 
 static void start_sched_trace(struct trace_array *tr)
 {
-        sched_switch_reset(tr);
+        tracing_reset_online_cpus(tr);
         tracing_start_sched_switch_record();
 }
 
@@ -221,7 +211,7 @@ static void sched_switch_trace_reset(struct trace_array *tr)
 
 static void sched_switch_trace_start(struct trace_array *tr)
 {
-        sched_switch_reset(tr);
+        tracing_reset_online_cpus(tr);
         tracing_start_sched_switch();
 }
 
@@ -247,3 +237,4 @@ __init static int init_sched_switch_trace(void)
         return register_tracer(&sched_switch_trace);
 }
 device_initcall(init_sched_switch_trace);
+
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 0067b49746c1..43586b689e31 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -211,7 +211,7 @@ static void wakeup_reset(struct trace_array *tr)
 }
 
 static void
-probe_wakeup(struct rq *rq, struct task_struct *p)
+probe_wakeup(struct rq *rq, struct task_struct *p, int success)
 {
         int cpu = smp_processor_id();
         unsigned long flags;
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 0b863f2cbc8e..d0871bc0aca5 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -10,6 +10,7 @@
 #include <linux/debugfs.h>
 #include <linux/ftrace.h>
 #include <linux/module.h>
+#include <linux/sysctl.h>
 #include <linux/init.h>
 #include <linux/fs.h>
 #include "trace.h"
@@ -31,6 +32,10 @@ static raw_spinlock_t max_stack_lock =
 
 static int stack_trace_disabled __read_mostly;
 static DEFINE_PER_CPU(int, trace_active);
+static DEFINE_MUTEX(stack_sysctl_mutex);
+
+int stack_tracer_enabled;
+static int last_stack_tracer_enabled;
 
 static inline void check_stack(void)
 {
@@ -174,7 +179,7 @@ stack_max_size_write(struct file *filp, const char __user *ubuf,
         return count;
 }
 
-static struct file_operations stack_max_size_fops = {
+static const struct file_operations stack_max_size_fops = {
         .open           = tracing_open_generic,
         .read           = stack_max_size_read,
         .write          = stack_max_size_write,
@@ -272,7 +277,7 @@ static int t_show(struct seq_file *m, void *v)
         return 0;
 }
 
-static struct seq_operations stack_trace_seq_ops = {
+static const struct seq_operations stack_trace_seq_ops = {
         .start          = t_start,
         .next           = t_next,
         .stop           = t_stop,
@@ -288,12 +293,47 @@ static int stack_trace_open(struct inode *inode, struct file *file)
         return ret;
 }
 
-static struct file_operations stack_trace_fops = {
+static const struct file_operations stack_trace_fops = {
         .open           = stack_trace_open,
         .read           = seq_read,
         .llseek         = seq_lseek,
 };
 
+int
+stack_trace_sysctl(struct ctl_table *table, int write,
+                   struct file *file, 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);
+
+        if (ret || !write ||
+            (last_stack_tracer_enabled == stack_tracer_enabled))
+                goto out;
+
+        last_stack_tracer_enabled = stack_tracer_enabled;
+
+        if (stack_tracer_enabled)
+                register_ftrace_function(&trace_ops);
+        else
+                unregister_ftrace_function(&trace_ops);
+
+ out:
+        mutex_unlock(&stack_sysctl_mutex);
+        return ret;
+}
+
+static __init int enable_stacktrace(char *str)
+{
+        stack_tracer_enabled = 1;
+        last_stack_tracer_enabled = 1;
+        return 1;
+}
+__setup("stacktrace", enable_stacktrace);
+
 static __init int stack_trace_init(void)
 {
         struct dentry *d_tracer;
@@ -311,7 +351,8 @@ static __init int stack_trace_init(void)
         if (!entry)
                 pr_warning("Could not create debugfs 'stack_trace' entry\n");
 
-        register_ftrace_function(&trace_ops);
+        if (stack_tracer_enabled)
+                register_ftrace_function(&trace_ops);
 
         return 0;
 }
diff --git a/kernel/trace/trace_sysprof.c b/kernel/trace/trace_sysprof.c
index 54960edb96d0..eaca5ad803ff 100644
--- a/kernel/trace/trace_sysprof.c
+++ b/kernel/trace/trace_sysprof.c
@@ -196,27 +196,19 @@ static enum hrtimer_restart stack_trace_timer_fn(struct hrtimer *hrtimer)
         return HRTIMER_RESTART;
 }
 
-static void start_stack_timer(int cpu)
+static void start_stack_timer(void *unused)
 {
-        struct hrtimer *hrtimer = &per_cpu(stack_trace_hrtimer, cpu);
+        struct hrtimer *hrtimer = &__get_cpu_var(stack_trace_hrtimer);
 
         hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
         hrtimer->function = stack_trace_timer_fn;
-        hrtimer->cb_mode = HRTIMER_CB_IRQSAFE_PERCPU;
 
         hrtimer_start(hrtimer, ns_to_ktime(sample_period), HRTIMER_MODE_REL);
 }
 
 static void start_stack_timers(void)
 {
-        cpumask_t saved_mask = current->cpus_allowed;
-        int cpu;
-
-        for_each_online_cpu(cpu) {
-                set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
-                start_stack_timer(cpu);
-        }
-        set_cpus_allowed_ptr(current, &saved_mask);
+        on_each_cpu(start_stack_timer, NULL, 1);
 }
 
 static void stop_stack_timer(int cpu)
@@ -234,20 +226,10 @@ static void stop_stack_timers(void)
                 stop_stack_timer(cpu);
 }
 
-static void stack_reset(struct trace_array *tr)
-{
-        int cpu;
-
-        tr->time_start = ftrace_now(tr->cpu);
-
-        for_each_online_cpu(cpu)
-                tracing_reset(tr, cpu);
-}
-
 static void start_stack_trace(struct trace_array *tr)
 {
         mutex_lock(&sample_timer_lock);
-        stack_reset(tr);
+        tracing_reset_online_cpus(tr);
         start_stack_timers();
         tracer_enabled = 1;
         mutex_unlock(&sample_timer_lock);
diff --git a/kernel/tsacct.c b/kernel/tsacct.c
index 8ebcd8532dfb..2dc06ab35716 100644
--- a/kernel/tsacct.c
+++ b/kernel/tsacct.c
@@ -27,6 +27,7 @@
  */
 void bacct_add_tsk(struct taskstats *stats, struct task_struct *tsk)
 {
+        const struct cred *tcred;
         struct timespec uptime, ts;
         u64 ac_etime;
 
@@ -53,10 +54,11 @@ void bacct_add_tsk(struct taskstats *stats, struct task_struct *tsk)
                 stats->ac_flag |= AXSIG;
         stats->ac_nice   = task_nice(tsk);
         stats->ac_sched  = tsk->policy;
-        stats->ac_uid    = tsk->uid;
-        stats->ac_gid    = tsk->gid;
         stats->ac_pid    = tsk->pid;
         rcu_read_lock();
+        tcred = __task_cred(tsk);
+        stats->ac_uid    = tcred->uid;
+        stats->ac_gid    = tcred->gid;
         stats->ac_ppid   = pid_alive(tsk) ?
                                 rcu_dereference(tsk->real_parent)->tgid : 0;
         rcu_read_unlock();
diff --git a/kernel/uid16.c b/kernel/uid16.c
index 3e41c1673e2f..2460c3199b5a 100644
--- a/kernel/uid16.c
+++ b/kernel/uid16.c
@@ -84,11 +84,12 @@ asmlinkage long sys_setresuid16(old_uid_t ruid, old_uid_t euid, old_uid_t suid)
 
 asmlinkage long sys_getresuid16(old_uid_t __user *ruid, old_uid_t __user *euid, old_uid_t __user *suid)
 {
+        const struct cred *cred = current_cred();
         int retval;
 
-        if (!(retval = put_user(high2lowuid(current->uid), ruid)) &&
-            !(retval = put_user(high2lowuid(current->euid), euid)))
-                retval = put_user(high2lowuid(current->suid), suid);
+        if (!(retval   = put_user(high2lowuid(cred->uid),  ruid)) &&
+            !(retval   = put_user(high2lowuid(cred->euid), euid)))
+                retval = put_user(high2lowuid(cred->suid), suid);
 
         return retval;
 }
@@ -104,11 +105,12 @@ asmlinkage long sys_setresgid16(old_gid_t rgid, old_gid_t egid, old_gid_t sgid)
 
 asmlinkage long sys_getresgid16(old_gid_t __user *rgid, old_gid_t __user *egid, old_gid_t __user *sgid)
 {
+        const struct cred *cred = current_cred();
         int retval;
 
-        if (!(retval = put_user(high2lowgid(current->gid), rgid)) &&
-            !(retval = put_user(high2lowgid(current->egid), egid)))
-                retval = put_user(high2lowgid(current->sgid), sgid);
+        if (!(retval   = put_user(high2lowgid(cred->gid),  rgid)) &&
+            !(retval   = put_user(high2lowgid(cred->egid), egid)))
+                retval = put_user(high2lowgid(cred->sgid), sgid);
 
         return retval;
 }
@@ -161,25 +163,24 @@ static int groups16_from_user(struct group_info *group_info,
 
 asmlinkage long sys_getgroups16(int gidsetsize, old_gid_t __user *grouplist)
 {
-        int i = 0;
+        const struct cred *cred = current_cred();
+        int i;
 
         if (gidsetsize < 0)
                 return -EINVAL;
 
-        get_group_info(current->group_info);
-        i = current->group_info->ngroups;
+        i = cred->group_info->ngroups;
         if (gidsetsize) {
                 if (i > gidsetsize) {
                         i = -EINVAL;
                         goto out;
                 }
-                if (groups16_to_user(grouplist, current->group_info)) {
+                if (groups16_to_user(grouplist, cred->group_info)) {
                         i = -EFAULT;
                         goto out;
                 }
         }
 out:
-        put_group_info(current->group_info);
         return i;
 }
 
@@ -210,20 +211,20 @@ asmlinkage long sys_setgroups16(int gidsetsize, old_gid_t __user *grouplist)
 
 asmlinkage long sys_getuid16(void)
 {
-        return high2lowuid(current->uid);
+        return high2lowuid(current_uid());
 }
 
 asmlinkage long sys_geteuid16(void)
 {
-        return high2lowuid(current->euid);
+        return high2lowuid(current_euid());
 }
 
 asmlinkage long sys_getgid16(void)
 {
-        return high2lowgid(current->gid);
+        return high2lowgid(current_gid());
 }
 
 asmlinkage long sys_getegid16(void)
 {
-        return high2lowgid(current->egid);
+        return high2lowgid(current_egid());
 }
diff --git a/kernel/user.c b/kernel/user.c
index cec2224bc9f5..477b6660f447 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -16,12 +16,13 @@
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/user_namespace.h>
+#include "cred-internals.h"
 
 struct user_namespace init_user_ns = {
         .kref = {
-                .refcount       = ATOMIC_INIT(2),
+                .refcount       = ATOMIC_INIT(1),
         },
-        .root_user = &root_user,
+        .creator = &root_user,
 };
 EXPORT_SYMBOL_GPL(init_user_ns);
 
@@ -47,12 +48,14 @@ static struct kmem_cache *uid_cachep;
  */
 static DEFINE_SPINLOCK(uidhash_lock);
 
+/* root_user.__count is 2, 1 for init task cred, 1 for init_user_ns->creator */
 struct user_struct root_user = {
-        .__count        = ATOMIC_INIT(1),
+        .__count        = ATOMIC_INIT(2),
         .processes      = ATOMIC_INIT(1),
         .files          = ATOMIC_INIT(0),
         .sigpending     = ATOMIC_INIT(0),
         .locked_shm     = 0,
+        .user_ns        = &init_user_ns,
 #ifdef CONFIG_USER_SCHED
         .tg             = &init_task_group,
 #endif
@@ -106,16 +109,10 @@ static int sched_create_user(struct user_struct *up)
         return rc;
 }
 
-static void sched_switch_user(struct task_struct *p)
-{
-        sched_move_task(p);
-}
-
 #else   /* CONFIG_USER_SCHED */
 
 static void sched_destroy_user(struct user_struct *up) { }
 static int sched_create_user(struct user_struct *up) { return 0; }
-static void sched_switch_user(struct task_struct *p) { }
 
 #endif  /* CONFIG_USER_SCHED */
 
@@ -244,13 +241,21 @@ static struct kobj_type uids_ktype = {
         .release = uids_release,
 };
 
-/* create /sys/kernel/uids/<uid>/cpu_share file for this user */
+/*
+ * Create /sys/kernel/uids/<uid>/cpu_share file for this user
+ * We do not create this file for users in a user namespace (until
+ * sysfs tagging is implemented).
+ *
+ * See Documentation/scheduler/sched-design-CFS.txt for ramifications.
+ */
 static int uids_user_create(struct user_struct *up)
 {
         struct kobject *kobj = &up->kobj;
         int error;
 
         memset(kobj, 0, sizeof(struct kobject));
+        if (up->user_ns != &init_user_ns)
+                return 0;
         kobj->kset = uids_kset;
         error = kobject_init_and_add(kobj, &uids_ktype, NULL, "%d", up->uid);
         if (error) {
@@ -286,6 +291,8 @@ static void remove_user_sysfs_dir(struct work_struct *w)
         unsigned long flags;
         int remove_user = 0;
 
+        if (up->user_ns != &init_user_ns)
+                return;
         /* Make uid_hash_remove() + sysfs_remove_file() + kobject_del()
          * atomic.
          */
@@ -321,12 +328,13 @@ done:
  * IRQ state (as stored in flags) is restored and uidhash_lock released
  * upon function exit.
  */
-static inline void free_user(struct user_struct *up, unsigned long flags)
+static void free_user(struct user_struct *up, unsigned long flags)
 {
         /* restore back the count */
         atomic_inc(&up->__count);
         spin_unlock_irqrestore(&uidhash_lock, flags);
 
+        put_user_ns(up->user_ns);
         INIT_WORK(&up->work, remove_user_sysfs_dir);
         schedule_work(&up->work);
 }
@@ -342,13 +350,14 @@ static inline void uids_mutex_unlock(void) { }
  * IRQ state (as stored in flags) is restored and uidhash_lock released
  * upon function exit.
  */
-static inline void free_user(struct user_struct *up, unsigned long flags)
+static void free_user(struct user_struct *up, unsigned long flags)
 {
         uid_hash_remove(up);
         spin_unlock_irqrestore(&uidhash_lock, flags);
         sched_destroy_user(up);
         key_put(up->uid_keyring);
         key_put(up->session_keyring);
+        put_user_ns(up->user_ns);
         kmem_cache_free(uid_cachep, up);
 }
 
@@ -364,7 +373,7 @@ struct user_struct *find_user(uid_t uid)
 {
         struct user_struct *ret;
         unsigned long flags;
-        struct user_namespace *ns = current->nsproxy->user_ns;
+        struct user_namespace *ns = current_user_ns();
 
         spin_lock_irqsave(&uidhash_lock, flags);
         ret = uid_hash_find(uid, uidhashentry(ns, uid));
@@ -411,6 +420,8 @@ struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid)
                 if (sched_create_user(new) < 0)
                         goto out_free_user;
 
+                new->user_ns = get_user_ns(ns);
+
                 if (uids_user_create(new))
                         goto out_destoy_sched;
 
@@ -434,7 +445,6 @@ struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid)
                         up = new;
                 }
                 spin_unlock_irq(&uidhash_lock);
-
         }
 
         uids_mutex_unlock();
@@ -443,6 +453,7 @@ struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid)
 
 out_destoy_sched:
         sched_destroy_user(new);
+        put_user_ns(new->user_ns);
 out_free_user:
         kmem_cache_free(uid_cachep, new);
 out_unlock:
@@ -450,63 +461,6 @@ out_unlock:
         return NULL;
 }
 
-void switch_uid(struct user_struct *new_user)
-{
-        struct user_struct *old_user;
-
-        /* What if a process setreuid()'s and this brings the
-         * new uid over his NPROC rlimit?  We can check this now
-         * cheaply with the new uid cache, so if it matters
-         * we should be checking for it.  -DaveM
-         */
-        old_user = current->user;
-        atomic_inc(&new_user->processes);
-        atomic_dec(&old_user->processes);
-        switch_uid_keyring(new_user);
-        current->user = new_user;
-        sched_switch_user(current);
-
-        /*
-         * We need to synchronize with __sigqueue_alloc()
-         * doing a get_uid(p->user).. If that saw the old
-         * user value, we need to wait until it has exited
-         * its critical region before we can free the old
-         * structure.
-         */
-        smp_mb();
-        spin_unlock_wait(&current->sighand->siglock);
-
-        free_uid(old_user);
-        suid_keys(current);
-}
-
-#ifdef CONFIG_USER_NS
-void release_uids(struct user_namespace *ns)
-{
-        int i;
-        unsigned long flags;
-        struct hlist_head *head;
-        struct hlist_node *nd;
-
-        spin_lock_irqsave(&uidhash_lock, flags);
-        /*
-         * collapse the chains so that the user_struct-s will
-         * be still alive, but not in hashes. subsequent free_uid()
-         * will free them.
-         */
-        for (i = 0; i < UIDHASH_SZ; i++) {
-                head = ns->uidhash_table + i;
-                while (!hlist_empty(head)) {
-                        nd = head->first;
-                        hlist_del_init(nd);
-                }
-        }
-        spin_unlock_irqrestore(&uidhash_lock, flags);
-
-        free_uid(ns->root_user);
-}
-#endif
-
 static int __init uid_cache_init(void)
 {
         int n;
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 532858fa5b88..79084311ee57 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -9,60 +9,55 @@
 #include <linux/nsproxy.h>
 #include <linux/slab.h>
 #include <linux/user_namespace.h>
+#include <linux/cred.h>
 
 /*
- * Clone a new ns copying an original user ns, setting refcount to 1
- * @old_ns: namespace to clone
- * Return NULL on error (failure to kmalloc), new ns otherwise
+ * Create a new user namespace, deriving the creator from the user in the
+ * passed credentials, and replacing that user with the new root user for the
+ * new namespace.
+ *
+ * This is called by copy_creds(), which will finish setting the target task's
+ * credentials.
  */
-static struct user_namespace *clone_user_ns(struct user_namespace *old_ns)
+int create_user_ns(struct cred *new)
 {
         struct user_namespace *ns;
-        struct user_struct *new_user;
+        struct user_struct *root_user;
         int n;
 
         ns = kmalloc(sizeof(struct user_namespace), GFP_KERNEL);
         if (!ns)
-                return ERR_PTR(-ENOMEM);
+                return -ENOMEM;
 
         kref_init(&ns->kref);
 
         for (n = 0; n < UIDHASH_SZ; ++n)
                 INIT_HLIST_HEAD(ns->uidhash_table + n);
 
-        /* Insert new root user.  */
-        ns->root_user = alloc_uid(ns, 0);
-        if (!ns->root_user) {
+        /* Alloc new root user.  */
+        root_user = alloc_uid(ns, 0);
+        if (!root_user) {
                 kfree(ns);
-                return ERR_PTR(-ENOMEM);
+                return -ENOMEM;
         }
 
-        /* Reset current->user with a new one */
-        new_user = alloc_uid(ns, current->uid);
-        if (!new_user) {
-                free_uid(ns->root_user);
-                kfree(ns);
-                return ERR_PTR(-ENOMEM);
-        }
-
-        switch_uid(new_user);
-        return ns;
-}
-
-struct user_namespace * copy_user_ns(int flags, struct user_namespace *old_ns)
-{
-        struct user_namespace *new_ns;
-
-        BUG_ON(!old_ns);
-        get_user_ns(old_ns);
-
-        if (!(flags & CLONE_NEWUSER))
-                return old_ns;
+        /* set the new root user in the credentials under preparation */
+        ns->creator = new->user;
+        new->user = root_user;
+        new->uid = new->euid = new->suid = new->fsuid = 0;
+        new->gid = new->egid = new->sgid = new->fsgid = 0;
+        put_group_info(new->group_info);
+        new->group_info = get_group_info(&init_groups);
+#ifdef CONFIG_KEYS
+        key_put(new->request_key_auth);
+        new->request_key_auth = NULL;
+#endif
+        /* tgcred will be cleared in our caller bc CLONE_THREAD won't be set */
 
-        new_ns = clone_user_ns(old_ns);
+        /* alloc_uid() incremented the userns refcount.  Just set it to 1 */
+        kref_set(&ns->kref, 1);
 
-        put_user_ns(old_ns);
-        return new_ns;
+        return 0;
 }
 
 void free_user_ns(struct kref *kref)
@@ -70,7 +65,7 @@ void free_user_ns(struct kref *kref)
         struct user_namespace *ns;
 
         ns = container_of(kref, struct user_namespace, kref);
-        release_uids(ns);
+        free_uid(ns->creator);
         kfree(ns);
 }
 EXPORT_SYMBOL(free_user_ns);
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index d4dc69ddebd7..2f445833ae37 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -73,7 +73,7 @@ static DEFINE_SPINLOCK(workqueue_lock);
 static LIST_HEAD(workqueues);
 
 static int singlethread_cpu __read_mostly;
-static cpumask_t cpu_singlethread_map __read_mostly;
+static const struct cpumask *cpu_singlethread_map __read_mostly;
 /*
  * _cpu_down() first removes CPU from cpu_online_map, then CPU_DEAD
  * flushes cwq->worklist. This means that flush_workqueue/wait_on_work
@@ -81,24 +81,24 @@ static cpumask_t cpu_singlethread_map __read_mostly;
  * use cpu_possible_map, the cpumask below is more a documentation
  * than optimization.
  */
-static cpumask_t cpu_populated_map __read_mostly;
+static cpumask_var_t cpu_populated_map __read_mostly;
 
 /* If it's single threaded, it isn't in the list of workqueues. */
-static inline int is_single_threaded(struct workqueue_struct *wq)
+static inline int is_wq_single_threaded(struct workqueue_struct *wq)
 {
         return wq->singlethread;
 }
 
-static const cpumask_t *wq_cpu_map(struct workqueue_struct *wq)
+static const struct cpumask *wq_cpu_map(struct workqueue_struct *wq)
 {
-        return is_single_threaded(wq)
-                ? &cpu_singlethread_map : &cpu_populated_map;
+        return is_wq_single_threaded(wq)
+                ? cpu_singlethread_map : cpu_populated_map;
 }
 
 static
 struct cpu_workqueue_struct *wq_per_cpu(struct workqueue_struct *wq, int cpu)
 {
-        if (unlikely(is_single_threaded(wq)))
+        if (unlikely(is_wq_single_threaded(wq)))
                 cpu = singlethread_cpu;
         return per_cpu_ptr(wq->cpu_wq, cpu);
 }
@@ -410,7 +410,7 @@ static int flush_cpu_workqueue(struct cpu_workqueue_struct *cwq)
  */
 void flush_workqueue(struct workqueue_struct *wq)
 {
-        const cpumask_t *cpu_map = wq_cpu_map(wq);
+        const struct cpumask *cpu_map = wq_cpu_map(wq);
         int cpu;
 
         might_sleep();
@@ -532,7 +532,7 @@ static void wait_on_work(struct work_struct *work)
 {
         struct cpu_workqueue_struct *cwq;
         struct workqueue_struct *wq;
-        const cpumask_t *cpu_map;
+        const struct cpumask *cpu_map;
         int cpu;
 
         might_sleep();
@@ -769,7 +769,7 @@ static int create_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu)
 {
         struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
         struct workqueue_struct *wq = cwq->wq;
-        const char *fmt = is_single_threaded(wq) ? "%s" : "%s/%d";
+        const char *fmt = is_wq_single_threaded(wq) ? "%s" : "%s/%d";
         struct task_struct *p;
 
         p = kthread_create(worker_thread, cwq, fmt, wq->name, cpu);
@@ -903,7 +903,7 @@ static void cleanup_workqueue_thread(struct cpu_workqueue_struct *cwq)
  */
 void destroy_workqueue(struct workqueue_struct *wq)
 {
-        const cpumask_t *cpu_map = wq_cpu_map(wq);
+        const struct cpumask *cpu_map = wq_cpu_map(wq);
         int cpu;
 
         cpu_maps_update_begin();
@@ -933,7 +933,7 @@ static int __devinit workqueue_cpu_callback(struct notifier_block *nfb,
 
         switch (action) {
         case CPU_UP_PREPARE:
-                cpu_set(cpu, cpu_populated_map);
+                cpumask_set_cpu(cpu, cpu_populated_map);
         }
 undo:
         list_for_each_entry(wq, &workqueues, list) {
@@ -964,7 +964,7 @@ undo:
         switch (action) {
         case CPU_UP_CANCELED:
         case CPU_POST_DEAD:
-                cpu_clear(cpu, cpu_populated_map);
+                cpumask_clear_cpu(cpu, cpu_populated_map);
         }
 
         return ret;
@@ -1017,9 +1017,11 @@ EXPORT_SYMBOL_GPL(work_on_cpu);
 
 void __init init_workqueues(void)
 {
-        cpu_populated_map = cpu_online_map;
-        singlethread_cpu = first_cpu(cpu_possible_map);
-        cpu_singlethread_map = cpumask_of_cpu(singlethread_cpu);
+        alloc_cpumask_var(&cpu_populated_map, GFP_KERNEL);
+
+        cpumask_copy(cpu_populated_map, cpu_online_mask);
+        singlethread_cpu = cpumask_first(cpu_possible_mask);
+        cpu_singlethread_map = cpumask_of(singlethread_cpu);
         hotcpu_notifier(workqueue_cpu_callback, 0);
         keventd_wq = create_workqueue("events");
         BUG_ON(!keventd_wq);