Merge branch 'linus' into sched/core

Merge reason: merge the latest fixes, update to -rc4.

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

59 files changed, 309 insertions, 193 deletions

diff --git a/kernel/async.c b/kernel/async.c
index 27235f5de198..15319d6c18fe 100644
--- a/kernel/async.c
+++ b/kernel/async.c
@@ -56,6 +56,7 @@ asynchronous and synchronous parts of the kernel.
 #include <linux/init.h>
 #include <linux/kthread.h>
 #include <linux/delay.h>
+#include <linux/slab.h>
 #include <asm/atomic.h>
 
 static async_cookie_t next_cookie = 1;
diff --git a/kernel/audit.c b/kernel/audit.c
index 78f7f86aa238..c71bd26631a2 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -46,6 +46,7 @@
 #include <asm/atomic.h>
 #include <linux/mm.h>
 #include <linux/module.h>
+#include <linux/slab.h>
 #include <linux/err.h>
 #include <linux/kthread.h>
 
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index 028e85663f27..46a57b57a335 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -3,6 +3,7 @@
 #include <linux/namei.h>
 #include <linux/mount.h>
 #include <linux/kthread.h>
+#include <linux/slab.h>
 
 struct audit_tree;
 struct audit_chunk;
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index cc7e87936cbc..8df43696f4ba 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -27,6 +27,7 @@
 #include <linux/namei.h>
 #include <linux/netlink.h>
 #include <linux/sched.h>
+#include <linux/slab.h>
 #include <linux/inotify.h>
 #include <linux/security.h>
 #include "audit.h"
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index a70604047f3c..ce08041f578d 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -27,6 +27,7 @@
 #include <linux/namei.h>
 #include <linux/netlink.h>
 #include <linux/sched.h>
+#include <linux/slab.h>
 #include <linux/security.h>
 #include "audit.h"
 
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index f3a461c0970a..3828ad5fb8f1 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -49,6 +49,7 @@
 #include <linux/namei.h>
 #include <linux/mm.h>
 #include <linux/module.h>
+#include <linux/slab.h>
 #include <linux/mount.h>
 #include <linux/socket.h>
 #include <linux/mqueue.h>
@@ -1893,7 +1894,7 @@ static int audit_inc_name_count(struct audit_context *context,
 {
         if (context->name_count >= AUDIT_NAMES) {
                 if (inode)
-                        printk(KERN_DEBUG "name_count maxed, losing inode data: "
+                        printk(KERN_DEBUG "audit: name_count maxed, losing inode data: "
                                "dev=%02x:%02x, inode=%lu\n",
                                MAJOR(inode->i_sb->s_dev),
                                MINOR(inode->i_sb->s_dev),
diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c
index 59e9ef6aab40..da5e13975531 100644
--- a/kernel/cgroup_freezer.c
+++ b/kernel/cgroup_freezer.c
@@ -15,6 +15,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/slab.h>
 #include <linux/cgroup.h>
 #include <linux/fs.h>
 #include <linux/uaccess.h>
@@ -47,17 +48,20 @@ static inline struct freezer *task_freezer(struct task_struct *task)
                             struct freezer, css);
 }
 
-int cgroup_frozen(struct task_struct *task)
+int cgroup_freezing_or_frozen(struct task_struct *task)
 {
         struct freezer *freezer;
         enum freezer_state state;
 
         task_lock(task);
         freezer = task_freezer(task);
-        state = freezer->state;
+        if (!freezer->css.cgroup->parent)
+                state = CGROUP_THAWED; /* root cgroup can't be frozen */
+        else
+                state = freezer->state;
         task_unlock(task);
 
-        return state == CGROUP_FROZEN;
+        return (state == CGROUP_FREEZING) || (state == CGROUP_FROZEN);
 }
 
 /*
diff --git a/kernel/compat.c b/kernel/compat.c
index f6c204f07ea6..7f40e9275fd9 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -25,6 +25,7 @@
 #include <linux/posix-timers.h>
 #include <linux/times.h>
 #include <linux/ptrace.h>
+#include <linux/gfp.h>
 
 #include <asm/uaccess.h>
 
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 8d340faac380..914aedcde849 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -14,6 +14,7 @@
 #include <linux/kthread.h>
 #include <linux/stop_machine.h>
 #include <linux/mutex.h>
+#include <linux/gfp.h>
 
 #ifdef CONFIG_SMP
 /* Serializes the updates to cpu_online_mask, cpu_present_mask */
diff --git a/kernel/cred.c b/kernel/cred.c
index 19d3ccce3d4d..4f483be5944c 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -10,6 +10,7 @@
  */
 #include <linux/module.h>
 #include <linux/cred.h>
+#include <linux/slab.h>
 #include <linux/sched.h>
 #include <linux/key.h>
 #include <linux/keyctl.h>
diff --git a/kernel/exit.c b/kernel/exit.c
index 84dc4b294e47..eabca5a73a85 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -952,7 +952,8 @@ NORET_TYPE void do_exit(long code)
 
         acct_update_integrals(tsk);
         /* sync mm's RSS info before statistics gathering */
-        sync_mm_rss(tsk, tsk->mm);
+        if (tsk->mm)
+                sync_mm_rss(tsk, tsk->mm);
         group_dead = atomic_dec_and_test(&tsk->signal->live);
         if (group_dead) {
                 hrtimer_cancel(&tsk->signal->real_timer);
diff --git a/kernel/fork.c b/kernel/fork.c
index 4799c5f0e6d0..44b0791b0a2e 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1052,6 +1052,9 @@ static struct task_struct *copy_process(unsigned long clone_flags,
         p->prev_utime = cputime_zero;
         p->prev_stime = cputime_zero;
 #endif
+#if defined(SPLIT_RSS_COUNTING)
+        memset(&p->rss_stat, 0, sizeof(p->rss_stat));
+#endif
 
         p->default_timer_slack_ns = current->timer_slack_ns;
 
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 398fda155f6e..704e488730a5 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -757,6 +757,16 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
                 if (new->flags & IRQF_ONESHOT)
                         desc->status |= IRQ_ONESHOT;
 
+                /*
+                 * Force MSI interrupts to run with interrupts
+                 * disabled. The multi vector cards can cause stack
+                 * overflows due to nested interrupts when enough of
+                 * them are directed to a core and fire at the same
+                 * time.
+                 */
+                if (desc->msi_desc)
+                        new->flags |= IRQF_DISABLED;
+
                 if (!(desc->status & IRQ_NOAUTOEN)) {
                         desc->depth = 0;
                         desc->status &= ~IRQ_DISABLED;
diff --git a/kernel/irq/numa_migrate.c b/kernel/irq/numa_migrate.c
index 963559dbd858..65d3845665ac 100644
--- a/kernel/irq/numa_migrate.c
+++ b/kernel/irq/numa_migrate.c
@@ -6,6 +6,7 @@
  */
 
 #include <linux/irq.h>
+#include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/random.h>
 #include <linux/interrupt.h>
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 6f50eccc79c0..7a6eb04ef6b5 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -7,6 +7,7 @@
  */
 
 #include <linux/irq.h>
+#include <linux/gfp.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/interrupt.h>
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index 8e5288a8a355..13aff293f4de 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -21,6 +21,7 @@
 #include <linux/sched.h>        /* for cond_resched */
 #include <linux/mm.h>
 #include <linux/ctype.h>
+#include <linux/slab.h>
 
 #include <asm/sections.h>
 
diff --git a/kernel/kgdb.c b/kernel/kgdb.c
index 761fdd2b3034..11f3515ca83f 100644
--- a/kernel/kgdb.c
+++ b/kernel/kgdb.c
@@ -69,9 +69,16 @@ struct kgdb_state {
         struct pt_regs          *linux_regs;
 };
 
+/* Exception state values */
+#define DCPU_WANT_MASTER 0x1 /* Waiting to become a master kgdb cpu */
+#define DCPU_NEXT_MASTER 0x2 /* Transition from one master cpu to another */
+#define DCPU_IS_SLAVE    0x4 /* Slave cpu enter exception */
+#define DCPU_SSTEP       0x8 /* CPU is single stepping */
+
 static struct debuggerinfo_struct {
         void                    *debuggerinfo;
         struct task_struct      *task;
+        int                     exception_state;
 } kgdb_info[NR_CPUS];
 
 /**
@@ -391,27 +398,22 @@ int kgdb_mem2hex(char *mem, char *buf, int count)
 
 /*
  * Copy the binary array pointed to by buf into mem.  Fix $, #, and
- * 0x7d escaped with 0x7d.  Return a pointer to the character after
- * the last byte written.
+ * 0x7d escaped with 0x7d. Return -EFAULT on failure or 0 on success.
+ * The input buf is overwitten with the result to write to mem.
  */
 static int kgdb_ebin2mem(char *buf, char *mem, int count)
 {
-        int err = 0;
-        char c;
+        int size = 0;
+        char *c = buf;
 
         while (count-- > 0) {
-                c = *buf++;
-                if (c == 0x7d)
-                        c = *buf++ ^ 0x20;
-
-                err = probe_kernel_write(mem, &c, 1);
-                if (err)
-                        break;
-
-                mem++;
+                c[size] = *buf++;
+                if (c[size] == 0x7d)
+                        c[size] = *buf++ ^ 0x20;
+                size++;
         }
 
-        return err;
+        return probe_kernel_write(mem, c, size);
 }
 
 /*
@@ -563,49 +565,6 @@ static struct task_struct *getthread(struct pt_regs *regs, int tid)
 }
 
 /*
- * CPU debug state control:
- */
-
-#ifdef CONFIG_SMP
-static void kgdb_wait(struct pt_regs *regs)
-{
-        unsigned long flags;
-        int cpu;
-
-        local_irq_save(flags);
-        cpu = raw_smp_processor_id();
-        kgdb_info[cpu].debuggerinfo = regs;
-        kgdb_info[cpu].task = current;
-        /*
-         * Make sure the above info reaches the primary CPU before
-         * our cpu_in_kgdb[] flag setting does:
-         */
-        smp_wmb();
-        atomic_set(&cpu_in_kgdb[cpu], 1);
-
-        /* Disable any cpu specific hw breakpoints */
-        kgdb_disable_hw_debug(regs);
-
-        /* Wait till primary CPU is done with debugging */
-        while (atomic_read(&passive_cpu_wait[cpu]))
-                cpu_relax();
-
-        kgdb_info[cpu].debuggerinfo = NULL;
-        kgdb_info[cpu].task = NULL;
-
-        /* fix up hardware debug registers on local cpu */
-        if (arch_kgdb_ops.correct_hw_break)
-                arch_kgdb_ops.correct_hw_break();
-
-        /* Signal the primary CPU that we are done: */
-        atomic_set(&cpu_in_kgdb[cpu], 0);
-        touch_softlockup_watchdog_sync();
-        clocksource_touch_watchdog();
-        local_irq_restore(flags);
-}
-#endif
-
-/*
  * Some architectures need cache flushes when we set/clear a
  * breakpoint:
  */
@@ -1400,34 +1359,13 @@ static int kgdb_reenter_check(struct kgdb_state *ks)
         return 1;
 }
 
-/*
- * kgdb_handle_exception() - main entry point from a kernel exception
- *
- * Locking hierarchy:
- *      interface locks, if any (begin_session)
- *      kgdb lock (kgdb_active)
- */
-int
-kgdb_handle_exception(int evector, int signo, int ecode, struct pt_regs *regs)
+static int kgdb_cpu_enter(struct kgdb_state *ks, struct pt_regs *regs)
 {
-        struct kgdb_state kgdb_var;
-        struct kgdb_state *ks = &kgdb_var;
         unsigned long flags;
         int sstep_tries = 100;
         int error = 0;
         int i, cpu;
-
-        ks->cpu                 = raw_smp_processor_id();
-        ks->ex_vector           = evector;
-        ks->signo               = signo;
-        ks->ex_vector           = evector;
-        ks->err_code            = ecode;
-        ks->kgdb_usethreadid    = 0;
-        ks->linux_regs          = regs;
-
-        if (kgdb_reenter_check(ks))
-                return 0; /* Ouch, double exception ! */
-
+        int trace_on = 0;
 acquirelock:
         /*
          * Interrupts will be restored by the 'trap return' code, except when
@@ -1435,13 +1373,43 @@ acquirelock:
          */
         local_irq_save(flags);
 
-        cpu = raw_smp_processor_id();
+        cpu = ks->cpu;
+        kgdb_info[cpu].debuggerinfo = regs;
+        kgdb_info[cpu].task = current;
+        /*
+         * Make sure the above info reaches the primary CPU before
+         * our cpu_in_kgdb[] flag setting does:
+         */
+        atomic_inc(&cpu_in_kgdb[cpu]);
 
         /*
-         * Acquire the kgdb_active lock:
+         * CPU will loop if it is a slave or request to become a kgdb
+         * master cpu and acquire the kgdb_active lock:
          */
-        while (atomic_cmpxchg(&kgdb_active, -1, cpu) != -1)
+        while (1) {
+                if (kgdb_info[cpu].exception_state & DCPU_WANT_MASTER) {
+                        if (atomic_cmpxchg(&kgdb_active, -1, cpu) == cpu)
+                                break;
+                } else if (kgdb_info[cpu].exception_state & DCPU_IS_SLAVE) {
+                        if (!atomic_read(&passive_cpu_wait[cpu]))
+                                goto return_normal;
+                } else {
+return_normal:
+                        /* Return to normal operation by executing any
+                         * hw breakpoint fixup.
+                         */
+                        if (arch_kgdb_ops.correct_hw_break)
+                                arch_kgdb_ops.correct_hw_break();
+                        if (trace_on)
+                                tracing_on();
+                        atomic_dec(&cpu_in_kgdb[cpu]);
+                        touch_softlockup_watchdog_sync();
+                        clocksource_touch_watchdog();
+                        local_irq_restore(flags);
+                        return 0;
+                }
                 cpu_relax();
+        }
 
         /*
          * For single stepping, try to only enter on the processor
@@ -1475,9 +1443,6 @@ acquirelock:
         if (kgdb_io_ops->pre_exception)
                 kgdb_io_ops->pre_exception();
 
-        kgdb_info[ks->cpu].debuggerinfo = ks->linux_regs;
-        kgdb_info[ks->cpu].task = current;
-
         kgdb_disable_hw_debug(ks->linux_regs);
 
         /*
@@ -1486,15 +1451,9 @@ acquirelock:
          */
         if (!kgdb_single_step) {
                 for (i = 0; i < NR_CPUS; i++)
-                        atomic_set(&passive_cpu_wait[i], 1);
+                        atomic_inc(&passive_cpu_wait[i]);
         }
 
-        /*
-         * spin_lock code is good enough as a barrier so we don't
-         * need one here:
-         */
-        atomic_set(&cpu_in_kgdb[ks->cpu], 1);
-
 #ifdef CONFIG_SMP
         /* Signal the other CPUs to enter kgdb_wait() */
         if ((!kgdb_single_step) && kgdb_do_roundup)
@@ -1518,6 +1477,9 @@ acquirelock:
         kgdb_single_step = 0;
         kgdb_contthread = current;
         exception_level = 0;
+        trace_on = tracing_is_on();
+        if (trace_on)
+                tracing_off();
 
         /* Talk to debugger with gdbserial protocol */
         error = gdb_serial_stub(ks);
@@ -1526,13 +1488,11 @@ acquirelock:
         if (kgdb_io_ops->post_exception)
                 kgdb_io_ops->post_exception();
 
-        kgdb_info[ks->cpu].debuggerinfo = NULL;
-        kgdb_info[ks->cpu].task = NULL;
-        atomic_set(&cpu_in_kgdb[ks->cpu], 0);
+        atomic_dec(&cpu_in_kgdb[ks->cpu]);
 
         if (!kgdb_single_step) {
                 for (i = NR_CPUS-1; i >= 0; i--)
-                        atomic_set(&passive_cpu_wait[i], 0);
+                        atomic_dec(&passive_cpu_wait[i]);
                 /*
                  * Wait till all the CPUs have quit
                  * from the debugger.
@@ -1551,6 +1511,8 @@ kgdb_restore:
                 else
                         kgdb_sstep_pid = 0;
         }
+        if (trace_on)
+                tracing_on();
         /* Free kgdb_active */
         atomic_set(&kgdb_active, -1);
         touch_softlockup_watchdog_sync();
@@ -1560,13 +1522,52 @@ kgdb_restore:
         return error;
 }
 
+/*
+ * kgdb_handle_exception() - main entry point from a kernel exception
+ *
+ * Locking hierarchy:
+ *      interface locks, if any (begin_session)
+ *      kgdb lock (kgdb_active)
+ */
+int
+kgdb_handle_exception(int evector, int signo, int ecode, struct pt_regs *regs)
+{
+        struct kgdb_state kgdb_var;
+        struct kgdb_state *ks = &kgdb_var;
+        int ret;
+
+        ks->cpu                 = raw_smp_processor_id();
+        ks->ex_vector           = evector;
+        ks->signo               = signo;
+        ks->ex_vector           = evector;
+        ks->err_code            = ecode;
+        ks->kgdb_usethreadid    = 0;
+        ks->linux_regs          = regs;
+
+        if (kgdb_reenter_check(ks))
+                return 0; /* Ouch, double exception ! */
+        kgdb_info[ks->cpu].exception_state |= DCPU_WANT_MASTER;
+        ret = kgdb_cpu_enter(ks, regs);
+        kgdb_info[ks->cpu].exception_state &= ~DCPU_WANT_MASTER;
+        return ret;
+}
+
 int kgdb_nmicallback(int cpu, void *regs)
 {
 #ifdef CONFIG_SMP
+        struct kgdb_state kgdb_var;
+        struct kgdb_state *ks = &kgdb_var;
+
+        memset(ks, 0, sizeof(struct kgdb_state));
+        ks->cpu                 = cpu;
+        ks->linux_regs          = regs;
+
         if (!atomic_read(&cpu_in_kgdb[cpu]) &&
-                        atomic_read(&kgdb_active) != cpu &&
-                        atomic_read(&cpu_in_kgdb[atomic_read(&kgdb_active)])) {
-                kgdb_wait((struct pt_regs *)regs);
+            atomic_read(&kgdb_active) != -1 &&
+            atomic_read(&kgdb_active) != cpu) {
+                kgdb_info[cpu].exception_state |= DCPU_IS_SLAVE;
+                kgdb_cpu_enter(ks, regs);
+                kgdb_info[cpu].exception_state &= ~DCPU_IS_SLAVE;
                 return 0;
         }
 #endif
@@ -1742,11 +1743,11 @@ EXPORT_SYMBOL_GPL(kgdb_unregister_io_module);
  */
 void kgdb_breakpoint(void)
 {
-        atomic_set(&kgdb_setting_breakpoint, 1);
+        atomic_inc(&kgdb_setting_breakpoint);
         wmb(); /* Sync point before breakpoint */
         arch_kgdb_breakpoint();
         wmb(); /* Sync point after breakpoint */
-        atomic_set(&kgdb_setting_breakpoint, 0);
+        atomic_dec(&kgdb_setting_breakpoint);
 }
 EXPORT_SYMBOL_GPL(kgdb_breakpoint);
 
diff --git a/kernel/latencytop.c b/kernel/latencytop.c
index ca07c5c0c914..877fb306d415 100644
--- a/kernel/latencytop.c
+++ b/kernel/latencytop.c
@@ -56,7 +56,6 @@
 #include <linux/module.h>
 #include <linux/sched.h>
 #include <linux/list.h>
-#include <linux/slab.h>
 #include <linux/stacktrace.h>
 
 static DEFINE_SPINLOCK(latency_lock);
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index c927a549db2c..2594e1ce41cb 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -43,6 +43,7 @@
 #include <linux/ftrace.h>
 #include <linux/stringify.h>
 #include <linux/bitops.h>
+#include <linux/gfp.h>
 
 #include <asm/sections.h>
 
@@ -582,9 +583,6 @@ static int static_obj(void *obj)
         unsigned long start = (unsigned long) &_stext,
                       end   = (unsigned long) &_end,
                       addr  = (unsigned long) obj;
-#ifdef CONFIG_SMP
-        int i;
-#endif
 
         /*
          * static variable?
@@ -595,24 +593,16 @@ static int static_obj(void *obj)
         if (arch_is_kernel_data(addr))
                 return 1;
 
-#ifdef CONFIG_SMP
         /*
-         * percpu var?
+         * in-kernel percpu var?
          */
-        for_each_possible_cpu(i) {
-                start = (unsigned long) &__per_cpu_start + per_cpu_offset(i);
-                end   = (unsigned long) &__per_cpu_start + PERCPU_ENOUGH_ROOM
-                                        + per_cpu_offset(i);
-
-                if ((addr >= start) && (addr < end))
-                        return 1;
-        }
-#endif
+        if (is_kernel_percpu_address(addr))
+                return 1;
 
         /*
-         * module var?
+         * module static or percpu var?
          */
-        return is_module_address(addr);
+        return is_module_address(addr) || is_module_percpu_address(addr);
 }
 
 /*
diff --git a/kernel/module.c b/kernel/module.c
index c968d3606dca..1016b75b026a 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -370,27 +370,33 @@ EXPORT_SYMBOL_GPL(find_module);
 
 #ifdef CONFIG_SMP
 
-static void *percpu_modalloc(unsigned long size, unsigned long align,
-                             const char *name)
+static inline void __percpu *mod_percpu(struct module *mod)
 {
-        void *ptr;
+        return mod->percpu;
+}
 
+static int percpu_modalloc(struct module *mod,
+                           unsigned long size, unsigned long align)
+{
         if (align > PAGE_SIZE) {
                 printk(KERN_WARNING "%s: per-cpu alignment %li > %li\n",
-                       name, align, PAGE_SIZE);
+                       mod->name, align, PAGE_SIZE);
                 align = PAGE_SIZE;
         }
 
-        ptr = __alloc_reserved_percpu(size, align);
-        if (!ptr)
+        mod->percpu = __alloc_reserved_percpu(size, align);
+        if (!mod->percpu) {
                 printk(KERN_WARNING
                        "Could not allocate %lu bytes percpu data\n", size);
-        return ptr;
+                return -ENOMEM;
+        }
+        mod->percpu_size = size;
+        return 0;
 }
 
-static void percpu_modfree(void *freeme)
+static void percpu_modfree(struct module *mod)
 {
-        free_percpu(freeme);
+        free_percpu(mod->percpu);
 }
 
 static unsigned int find_pcpusec(Elf_Ehdr *hdr,
@@ -400,24 +406,62 @@ static unsigned int find_pcpusec(Elf_Ehdr *hdr,
         return find_sec(hdr, sechdrs, secstrings, ".data.percpu");
 }
 
-static void percpu_modcopy(void *pcpudest, const void *from, unsigned long size)
+static void percpu_modcopy(struct module *mod,
+                           const void *from, unsigned long size)
 {
         int cpu;
 
         for_each_possible_cpu(cpu)
-                memcpy(pcpudest + per_cpu_offset(cpu), from, size);
+                memcpy(per_cpu_ptr(mod->percpu, cpu), from, size);
+}
+
+/**
+ * is_module_percpu_address - test whether address is from module static percpu
+ * @addr: address to test
+ *
+ * Test whether @addr belongs to module static percpu area.
+ *
+ * RETURNS:
+ * %true if @addr is from module static percpu area
+ */
+bool is_module_percpu_address(unsigned long addr)
+{
+        struct module *mod;
+        unsigned int cpu;
+
+        preempt_disable();
+
+        list_for_each_entry_rcu(mod, &modules, list) {
+                if (!mod->percpu_size)
+                        continue;
+                for_each_possible_cpu(cpu) {
+                        void *start = per_cpu_ptr(mod->percpu, cpu);
+
+                        if ((void *)addr >= start &&
+                            (void *)addr < start + mod->percpu_size) {
+                                preempt_enable();
+                                return true;
+                        }
+                }
+        }
+
+        preempt_enable();
+        return false;
 }
 
 #else /* ... !CONFIG_SMP */
 
-static inline void *percpu_modalloc(unsigned long size, unsigned long align,
-                                    const char *name)
+static inline void __percpu *mod_percpu(struct module *mod)
 {
         return NULL;
 }
-static inline void percpu_modfree(void *pcpuptr)
+static inline int percpu_modalloc(struct module *mod,
+                                  unsigned long size, unsigned long align)
+{
+        return -ENOMEM;
+}
+static inline void percpu_modfree(struct module *mod)
 {
-        BUG();
 }
 static inline unsigned int find_pcpusec(Elf_Ehdr *hdr,
                                         Elf_Shdr *sechdrs,
@@ -425,12 +469,16 @@ static inline unsigned int find_pcpusec(Elf_Ehdr *hdr,
 {
         return 0;
 }
-static inline void percpu_modcopy(void *pcpudst, const void *src,
-                                  unsigned long size)
+static inline void percpu_modcopy(struct module *mod,
+                                  const void *from, unsigned long size)
 {
         /* pcpusec should be 0, and size of that section should be 0. */
         BUG_ON(size != 0);
 }
+bool is_module_percpu_address(unsigned long addr)
+{
+        return false;
+}
 
 #endif /* CONFIG_SMP */
 
@@ -473,11 +521,13 @@ static void module_unload_init(struct module *mod)
         int cpu;
 
         INIT_LIST_HEAD(&mod->modules_which_use_me);
-        for_each_possible_cpu(cpu)
-                per_cpu_ptr(mod->refptr, cpu)->count = 0;
+        for_each_possible_cpu(cpu) {
+                per_cpu_ptr(mod->refptr, cpu)->incs = 0;
+                per_cpu_ptr(mod->refptr, cpu)->decs = 0;
+        }
 
         /* Hold reference count during initialization. */
-        __this_cpu_write(mod->refptr->count, 1);
+        __this_cpu_write(mod->refptr->incs, 1);
         /* Backwards compatibility macros put refcount during init. */
         mod->waiter = current;
 }
@@ -616,12 +666,28 @@ static int try_stop_module(struct module *mod, int flags, int *forced)
 
 unsigned int module_refcount(struct module *mod)
 {
-        unsigned int total = 0;
+        unsigned int incs = 0, decs = 0;
         int cpu;
 
         for_each_possible_cpu(cpu)
-                total += per_cpu_ptr(mod->refptr, cpu)->count;
-        return total;
+                decs += per_cpu_ptr(mod->refptr, cpu)->decs;
+        /*
+         * ensure the incs are added up after the decs.
+         * module_put ensures incs are visible before decs with smp_wmb.
+         *
+         * This 2-count scheme avoids the situation where the refcount
+         * for CPU0 is read, then CPU0 increments the module refcount,
+         * then CPU1 drops that refcount, then the refcount for CPU1 is
+         * read. We would record a decrement but not its corresponding
+         * increment so we would see a low count (disaster).
+         *
+         * Rare situation? But module_refcount can be preempted, and we
+         * might be tallying up 4096+ CPUs. So it is not impossible.
+         */
+        smp_rmb();
+        for_each_possible_cpu(cpu)
+                incs += per_cpu_ptr(mod->refptr, cpu)->incs;
+        return incs - decs;
 }
 EXPORT_SYMBOL(module_refcount);
 
@@ -798,10 +864,11 @@ void module_put(struct module *module)
 {
         if (module) {
                 preempt_disable();
-                __this_cpu_dec(module->refptr->count);
+                smp_wmb(); /* see comment in module_refcount */
+                __this_cpu_inc(module->refptr->decs);
 
                 trace_module_put(module, _RET_IP_,
-                                 __this_cpu_read(module->refptr->count));
+                                 __this_cpu_read(module->refptr->decs));
                 /* Maybe they're waiting for us to drop reference? */
                 if (unlikely(!module_is_live(module)))
                         wake_up_process(module->waiter);
@@ -1400,8 +1467,7 @@ static void free_module(struct module *mod)
         /* This may be NULL, but that's OK */
         module_free(mod, mod->module_init);
         kfree(mod->args);
-        if (mod->percpu)
-                percpu_modfree(mod->percpu);
+        percpu_modfree(mod);
 #if defined(CONFIG_MODULE_UNLOAD)
         if (mod->refptr)
                 free_percpu(mod->refptr);
@@ -1520,7 +1586,7 @@ static int simplify_symbols(Elf_Shdr *sechdrs,
                 default:
                         /* Divert to percpu allocation if a percpu var. */
                         if (sym[i].st_shndx == pcpuindex)
-                                secbase = (unsigned long)mod->percpu;
+                                secbase = (unsigned long)mod_percpu(mod);
                         else
                                 secbase = sechdrs[sym[i].st_shndx].sh_addr;
                         sym[i].st_value += secbase;
@@ -1954,7 +2020,7 @@ static noinline struct module *load_module(void __user *umod,
         unsigned int modindex, versindex, infoindex, pcpuindex;
         struct module *mod;
         long err = 0;
-        void *percpu = NULL, *ptr = NULL; /* Stops spurious gcc warning */
+        void *ptr = NULL; /* Stops spurious gcc warning */
         unsigned long symoffs, stroffs, *strmap;
 
         mm_segment_t old_fs;
@@ -2094,15 +2160,11 @@ static noinline struct module *load_module(void __user *umod,
 
         if (pcpuindex) {
                 /* We have a special allocation for this section. */
-                percpu = percpu_modalloc(sechdrs[pcpuindex].sh_size,
-                                         sechdrs[pcpuindex].sh_addralign,
-                                         mod->name);
-                if (!percpu) {
-                        err = -ENOMEM;
+                err = percpu_modalloc(mod, sechdrs[pcpuindex].sh_size,
+                                      sechdrs[pcpuindex].sh_addralign);
+                if (err)
                         goto free_mod;
-                }
                 sechdrs[pcpuindex].sh_flags &= ~(unsigned long)SHF_ALLOC;
-                mod->percpu = percpu;
         }
 
         /* Determine total sizes, and put offsets in sh_entsize.  For now
@@ -2317,7 +2379,7 @@ static noinline struct module *load_module(void __user *umod,
         sort_extable(mod->extable, mod->extable + mod->num_exentries);
 
         /* Finally, copy percpu area over. */
-        percpu_modcopy(mod->percpu, (void *)sechdrs[pcpuindex].sh_addr,
+        percpu_modcopy(mod, (void *)sechdrs[pcpuindex].sh_addr,
                        sechdrs[pcpuindex].sh_size);
 
         add_kallsyms(mod, sechdrs, hdr->e_shnum, symindex, strindex,
@@ -2409,8 +2471,7 @@ static noinline struct module *load_module(void __user *umod,
         module_free(mod, mod->module_core);
         /* mod will be freed with core. Don't access it beyond this line! */
  free_percpu:
-        if (percpu)
-                percpu_modfree(percpu);
+        percpu_modfree(mod);
  free_mod:
         kfree(args);
         kfree(strmap);
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index 2ab67233ee8f..f74e6c00e26d 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -13,6 +13,7 @@
  *             Pavel Emelianov <xemul@openvz.org>
  */
 
+#include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/nsproxy.h>
 #include <linux/init_task.h>
diff --git a/kernel/padata.c b/kernel/padata.c
index 93caf65ff57c..fd03513c7327 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -25,6 +25,7 @@
 #include <linux/padata.h>
 #include <linux/mutex.h>
 #include <linux/sched.h>
+#include <linux/slab.h>
 #include <linux/rcupdate.h>
 
 #define MAX_SEQ_NR INT_MAX - NR_CPUS
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 574ee58a3046..2f3fbf84215a 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -15,6 +15,7 @@
 #include <linux/smp.h>
 #include <linux/file.h>
 #include <linux/poll.h>
+#include <linux/slab.h>
 #include <linux/sysfs.h>
 #include <linux/dcache.h>
 #include <linux/percpu.h>
@@ -1164,11 +1165,9 @@ void perf_event_task_sched_out(struct task_struct *task,
         struct perf_event_context *ctx = task->perf_event_ctxp;
         struct perf_event_context *next_ctx;
         struct perf_event_context *parent;
-        struct pt_regs *regs;
         int do_switch = 1;
 
-        regs = task_pt_regs(task);
-        perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 1, regs, 0);
+        perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 1, NULL, 0);
 
         if (likely(!ctx || !cpuctx->task_ctx))
                 return;
@@ -2786,12 +2785,11 @@ __weak struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
         return NULL;
 }
 
-#ifdef CONFIG_EVENT_TRACING
 __weak
 void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip)
 {
 }
-#endif
+
 
 /*
  * Output
@@ -3378,15 +3376,23 @@ static void perf_event_task_output(struct perf_event *event,
                                      struct perf_task_event *task_event)
 {
         struct perf_output_handle handle;
-        int size;
         struct task_struct *task = task_event->task;
-        int ret;
+        unsigned long flags;
+        int size, ret;
+
+        /*
+         * If this CPU attempts to acquire an rq lock held by a CPU spinning
+         * in perf_output_lock() from interrupt context, it's game over.
+         */
+        local_irq_save(flags);
 
         size  = task_event->event_id.header.size;
         ret = perf_output_begin(&handle, event, size, 0, 0);
 
-        if (ret)
+        if (ret) {
+                local_irq_restore(flags);
                 return;
+        }
 
         task_event->event_id.pid = perf_event_pid(event, task);
         task_event->event_id.ppid = perf_event_pid(event, current);
@@ -3397,6 +3403,7 @@ static void perf_event_task_output(struct perf_event *event,
         perf_output_put(&handle, task_event->event_id);
 
         perf_output_end(&handle);
+        local_irq_restore(flags);
 }
 
 static int perf_event_task_match(struct perf_event *event)
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 79aac93acf99..a5aff94e1f0b 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -13,6 +13,7 @@
 #include <linux/syscalls.h>
 #include <linux/err.h>
 #include <linux/acct.h>
+#include <linux/slab.h>
 
 #define BITS_PER_PAGE           (PAGE_SIZE*8)
 
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index da5288ec2392..aa9e916da4d5 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -22,6 +22,7 @@
 #include <linux/console.h>
 #include <linux/cpu.h>
 #include <linux/freezer.h>
+#include <linux/gfp.h>
 #include <scsi/scsi_scan.h>
 #include <asm/suspend.h>
 
diff --git a/kernel/power/hibernate_nvs.c b/kernel/power/hibernate_nvs.c
index 39ac698ef836..fdcad9ed5a7b 100644
--- a/kernel/power/hibernate_nvs.c
+++ b/kernel/power/hibernate_nvs.c
@@ -10,6 +10,7 @@
 #include <linux/kernel.h>
 #include <linux/list.h>
 #include <linux/mm.h>
+#include <linux/slab.h>
 #include <linux/suspend.h>
 
 /*
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 5ade1bdcf366..71ae29052ab6 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -88,12 +88,11 @@ static int try_to_freeze_tasks(bool sig_only)
                 printk(KERN_ERR "Freezing of tasks failed after %d.%02d seconds "
                                 "(%d tasks refusing to freeze):\n",
                                 elapsed_csecs / 100, elapsed_csecs % 100, todo);
-                show_state();
                 read_lock(&tasklist_lock);
                 do_each_thread(g, p) {
                         task_lock(p);
                         if (freezing(p) && !freezer_should_skip(p))
-                                printk(KERN_ERR " %s\n", p->comm);
+                                sched_show_task(p);
                         cancel_freezing(p);
                         task_unlock(p);
                 } while_each_thread(g, p);
@@ -145,7 +144,7 @@ static void thaw_tasks(bool nosig_only)
                 if (nosig_only && should_send_signal(p))
                         continue;
 
-                if (cgroup_frozen(p))
+                if (cgroup_freezing_or_frozen(p))
                         continue;
 
                 thaw_process(p);
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 830cadecbdfc..be861c26dda7 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -26,6 +26,7 @@
 #include <linux/console.h>
 #include <linux/highmem.h>
 #include <linux/list.h>
+#include <linux/slab.h>
 
 #include <asm/uaccess.h>
 #include <asm/mmu_context.h>
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 44cce10b582d..56e7dbb8b996 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -15,6 +15,7 @@
 #include <linux/console.h>
 #include <linux/cpu.h>
 #include <linux/syscalls.h>
+#include <linux/gfp.h>
 
 #include "power.h"
 
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index 1d575733d4e1..66824d71983a 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -23,6 +23,7 @@
 #include <linux/swap.h>
 #include <linux/swapops.h>
 #include <linux/pm.h>
+#include <linux/slab.h>
 
 #include "power.h"
 
diff --git a/kernel/power/user.c b/kernel/power/user.c
index 4d2289626a84..a8c96212bc1b 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -420,7 +420,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
                          * User space encodes device types as two-byte values,
                          * so we need to recode them
                          */
-                        swdev = old_decode_dev(swap_area.dev);
+                        swdev = new_decode_dev(swap_area.dev);
                         if (swdev) {
                                 offset = swap_area.offset;
                                 data->swap = swap_type_of(swdev, offset, NULL);
diff --git a/kernel/res_counter.c b/kernel/res_counter.c
index bcdabf37c40b..c7eaa37a768b 100644
--- a/kernel/res_counter.c
+++ b/kernel/res_counter.c
@@ -10,7 +10,6 @@
 #include <linux/types.h>
 #include <linux/parser.h>
 #include <linux/fs.h>
-#include <linux/slab.h>
 #include <linux/res_counter.h>
 #include <linux/uaccess.h>
 #include <linux/mm.h>
diff --git a/kernel/sched.c b/kernel/sched.c
index 4a57e96dd6c7..ab562ae4007c 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -71,6 +71,7 @@
 #include <linux/debugfs.h>
 #include <linux/ctype.h>
 #include <linux/ftrace.h>
+#include <linux/slab.h>
 
 #include <asm/tlb.h>
 #include <asm/irq_regs.h>
@@ -4809,7 +4810,7 @@ SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len,
         int ret;
         cpumask_var_t mask;
 
-        if (len < nr_cpu_ids)
+        if ((len * BITS_PER_BYTE) < nr_cpu_ids)
                 return -EINVAL;
         if (len & (sizeof(unsigned long)-1))
                 return -EINVAL;
@@ -5305,7 +5306,7 @@ again:
 
                 get_task_struct(mt);
                 task_rq_unlock(rq, &flags);
-                wake_up_process(rq->migration_thread);
+                wake_up_process(mt);
                 put_task_struct(mt);
                 wait_for_completion(&req.done);
                 tlb_migrate_finish(p->mm);
diff --git a/kernel/sched_cpupri.c b/kernel/sched_cpupri.c
index fccf9fbb0d7b..e6871cb3fc83 100644
--- a/kernel/sched_cpupri.c
+++ b/kernel/sched_cpupri.c
@@ -27,6 +27,7 @@
  *  of the License.
  */
 
+#include <linux/gfp.h>
 #include "sched_cpupri.h"
 
 /* Convert between a 140 based task->prio, and our 102 based cpupri */
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index 0932c5c45b34..9cf1baf6616a 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -486,8 +486,4 @@ void proc_sched_set_task(struct task_struct *p)
 #ifdef CONFIG_SCHEDSTATS
         memset(&p->se.statistics, 0, sizeof(p->se.statistics));
 #endif
-        p->se.sum_exec_runtime                  = 0;
-        p->se.prev_sum_exec_runtime             = 0;
-        p->nvcsw                                = 0;
-        p->nivcsw                               = 0;
 }
diff --git a/kernel/smp.c b/kernel/smp.c
index 9867b6bfefce..3fc697336183 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -9,6 +9,7 @@
 #include <linux/module.h>
 #include <linux/percpu.h>
 #include <linux/init.h>
+#include <linux/gfp.h>
 #include <linux/smp.h>
 #include <linux/cpu.h>
 
diff --git a/kernel/srcu.c b/kernel/srcu.c
index bde4295774c8..2980da3fd509 100644
--- a/kernel/srcu.c
+++ b/kernel/srcu.c
@@ -30,7 +30,6 @@
 #include <linux/preempt.h>
 #include <linux/rcupdate.h>
 #include <linux/sched.h>
-#include <linux/slab.h>
 #include <linux/smp.h>
 #include <linux/srcu.h>
 
diff --git a/kernel/sys.c b/kernel/sys.c
index 8298878f4f71..6d1a7e0f9d5b 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -36,6 +36,7 @@
 #include <linux/personality.h>
 #include <linux/ptrace.h>
 #include <linux/fs_struct.h>
+#include <linux/gfp.h>
 
 #include <linux/compat.h>
 #include <linux/syscalls.h>
diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c
index 8cd50d8f9bde..59030570f5ca 100644
--- a/kernel/sysctl_binary.c
+++ b/kernel/sysctl_binary.c
@@ -13,6 +13,7 @@
 #include <linux/file.h>
 #include <linux/ctype.h>
 #include <linux/netdevice.h>
+#include <linux/slab.h>
 
 #ifdef CONFIG_SYSCTL_SYSCALL
 
diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index 899ca51be5e8..11281d5792bd 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -22,6 +22,7 @@
 #include <linux/delayacct.h>
 #include <linux/cpumask.h>
 #include <linux/percpu.h>
+#include <linux/slab.h>
 #include <linux/cgroupstats.h>
 #include <linux/cgroup.h>
 #include <linux/fs.h>
diff --git a/kernel/time.c b/kernel/time.c
index 804798005d19..656dccfe1cbb 100644
--- a/kernel/time.c
+++ b/kernel/time.c
@@ -35,7 +35,6 @@
 #include <linux/syscalls.h>
 #include <linux/security.h>
 #include <linux/fs.h>
-#include <linux/slab.h>
 #include <linux/math64.h>
 #include <linux/ptrace.h>
 
diff --git a/kernel/time/timecompare.c b/kernel/time/timecompare.c
index 12f5c55090be..ac38fbb176cc 100644
--- a/kernel/time/timecompare.c
+++ b/kernel/time/timecompare.c
@@ -19,6 +19,7 @@
 
 #include <linux/timecompare.h>
 #include <linux/module.h>
+#include <linux/slab.h>
 #include <linux/math64.h>
 
 /*
diff --git a/kernel/timer.c b/kernel/timer.c
index fc965eae0e87..aeb6a54f2771 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -39,6 +39,7 @@
 #include <linux/kallsyms.h>
 #include <linux/perf_event.h>
 #include <linux/sched.h>
+#include <linux/slab.h>
 
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 07f945a99430..b3bc91a3f510 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -21,6 +21,7 @@
 #include <linux/percpu.h>
 #include <linux/init.h>
 #include <linux/mutex.h>
+#include <linux/slab.h>
 #include <linux/debugfs.h>
 #include <linux/smp_lock.h>
 #include <linux/time.h>
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index d9062f5cc0c0..2404b59b3097 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -24,6 +24,7 @@
 #include <linux/uaccess.h>
 #include <linux/ftrace.h>
 #include <linux/sysctl.h>
+#include <linux/slab.h>
 #include <linux/ctype.h>
 #include <linux/list.h>
 #include <linux/hash.h>
diff --git a/kernel/trace/power-traces.c b/kernel/trace/power-traces.c
index 9f4f565b01e6..a22582a06161 100644
--- a/kernel/trace/power-traces.c
+++ b/kernel/trace/power-traces.c
@@ -9,7 +9,6 @@
 #include <linux/workqueue.h>
 #include <linux/sched.h>
 #include <linux/module.h>
-#include <linux/slab.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/power.h>
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index d1187ef20caf..41ca394feb22 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -14,6 +14,7 @@
 #include <linux/module.h>
 #include <linux/percpu.h>
 #include <linux/mutex.h>
+#include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/hash.h>
 #include <linux/list.h>
@@ -1209,18 +1210,19 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned nr_pages)
 
         for (i = 0; i < nr_pages; i++) {
                 if (RB_WARN_ON(cpu_buffer, list_empty(cpu_buffer->pages)))
-                        return;
+                        goto out;
                 p = cpu_buffer->pages->next;
                 bpage = list_entry(p, struct buffer_page, list);
                 list_del_init(&bpage->list);
                 free_buffer_page(bpage);
         }
         if (RB_WARN_ON(cpu_buffer, list_empty(cpu_buffer->pages)))
-                return;
+                goto out;
 
         rb_reset_cpu(cpu_buffer);
         rb_check_pages(cpu_buffer);
 
+out:
         spin_unlock_irq(&cpu_buffer->reader_lock);
 }
 
@@ -1237,7 +1239,7 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer,
 
         for (i = 0; i < nr_pages; i++) {
                 if (RB_WARN_ON(cpu_buffer, list_empty(pages)))
-                        return;
+                        goto out;
                 p = pages->next;
                 bpage = list_entry(p, struct buffer_page, list);
                 list_del_init(&bpage->list);
@@ -1246,6 +1248,7 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer,
         rb_reset_cpu(cpu_buffer);
         rb_check_pages(cpu_buffer);
 
+out:
         spin_unlock_irq(&cpu_buffer->reader_lock);
 }
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 3ec2ee6f6560..44f916a04065 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -33,10 +33,10 @@
 #include <linux/kdebug.h>
 #include <linux/string.h>
 #include <linux/rwsem.h>
+#include <linux/slab.h>
 #include <linux/ctype.h>
 #include <linux/init.h>
 #include <linux/poll.h>
-#include <linux/gfp.h>
 #include <linux/fs.h>
 
 #include "trace.h"
diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c
index 6fbfb8f417b9..9d589d8dcd1a 100644
--- a/kernel/trace/trace_clock.c
+++ b/kernel/trace/trace_clock.c
@@ -84,7 +84,7 @@ u64 notrace trace_clock_global(void)
         int this_cpu;
         u64 now;
 
-        raw_local_irq_save(flags);
+        local_irq_save(flags);
 
         this_cpu = raw_smp_processor_id();
         now = cpu_clock(this_cpu);
@@ -110,7 +110,7 @@ u64 notrace trace_clock_global(void)
         arch_spin_unlock(&trace_clock_struct.lock);
 
  out:
-        raw_local_irq_restore(flags);
+        local_irq_restore(flags);
 
         return now;
 }
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 81f691eb3a30..0565bb42566f 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -17,7 +17,12 @@ EXPORT_SYMBOL_GPL(perf_arch_fetch_caller_regs);
 static char *perf_trace_buf;
 static char *perf_trace_buf_nmi;
 
-typedef typeof(char [PERF_MAX_TRACE_SIZE]) perf_trace_t ;
+/*
+ * Force it to be aligned to unsigned long to avoid misaligned accesses
+ * suprises
+ */
+typedef typeof(unsigned long [PERF_MAX_TRACE_SIZE / sizeof(unsigned long)])
+        perf_trace_t;
 
 /* Count the events in use (per event id, not per instance) */
 static int      total_ref_count;
@@ -130,6 +135,8 @@ __kprobes void *perf_trace_buf_prepare(int size, unsigned short type,
         char *trace_buf, *raw_data;
         int pc, cpu;
 
+        BUILD_BUG_ON(PERF_MAX_TRACE_SIZE % sizeof(unsigned long));
+
         pc = preempt_count();
 
         /* Protect the per cpu buffer, begin the rcu read side */
@@ -152,7 +159,7 @@ __kprobes void *perf_trace_buf_prepare(int size, unsigned short type,
         raw_data = per_cpu_ptr(trace_buf, cpu);
 
         /* zero the dead bytes from align to not leak stack to user */
-        *(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL;
+        memset(&raw_data[size - sizeof(u64)], 0, sizeof(u64));
 
         entry = (struct trace_entry *)raw_data;
         tracing_generic_entry_update(entry, *irq_flags, pc);
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index beab8bf2f310..c697c7043349 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -15,6 +15,7 @@
 #include <linux/uaccess.h>
 #include <linux/module.h>
 #include <linux/ctype.h>
+#include <linux/slab.h>
 #include <linux/delay.h>
 
 #include <asm/setup.h>
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 4615f62a04f1..88c0b6dbd7fe 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -22,6 +22,7 @@
 #include <linux/ctype.h>
 #include <linux/mutex.h>
 #include <linux/perf_event.h>
+#include <linux/slab.h>
 
 #include "trace.h"
 #include "trace_output.h"
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index e6989d9b44da..9aed1a5cf553 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -9,6 +9,7 @@
 #include <linux/debugfs.h>
 #include <linux/uaccess.h>
 #include <linux/ftrace.h>
+#include <linux/slab.h>
 #include <linux/fs.h>
 
 #include "trace.h"
diff --git a/kernel/trace/trace_ksym.c b/kernel/trace/trace_ksym.c
index 94103cdcf9d8..d59cd6879477 100644
--- a/kernel/trace/trace_ksym.c
+++ b/kernel/trace/trace_ksym.c
@@ -23,6 +23,7 @@
 #include <linux/debugfs.h>
 #include <linux/ftrace.h>
 #include <linux/module.h>
+#include <linux/slab.h>
 #include <linux/fs.h>
 
 #include "trace_output.h"
diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c
index 0acd834659ed..017fa376505d 100644
--- a/kernel/trace/trace_mmiotrace.c
+++ b/kernel/trace/trace_mmiotrace.c
@@ -9,6 +9,7 @@
 #include <linux/kernel.h>
 #include <linux/mmiotrace.h>
 #include <linux/pci.h>
+#include <linux/slab.h>
 #include <linux/time.h>
 
 #include <asm/atomic.h>
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 280fea470d67..81003b4d617f 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -3,6 +3,7 @@
 #include <linux/stringify.h>
 #include <linux/kthread.h>
 #include <linux/delay.h>
+#include <linux/slab.h>
 
 static inline int trace_valid_entry(struct trace_entry *entry)
 {
diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c
index a4bb239eb987..96cffb269e73 100644
--- a/kernel/trace/trace_stat.c
+++ b/kernel/trace/trace_stat.c
@@ -10,6 +10,7 @@
 
 
 #include <linux/list.h>
+#include <linux/slab.h>
 #include <linux/rbtree.h>
 #include <linux/debugfs.h>
 #include "trace_stat.h"
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 33c2a5b769dc..4d6d711717f2 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -1,5 +1,6 @@
 #include <trace/syscall.h>
 #include <trace/events/syscalls.h>
+#include <linux/slab.h>
 #include <linux/kernel.h>
 #include <linux/ftrace.h>
 #include <linux/perf_event.h>
diff --git a/kernel/trace/trace_workqueue.c b/kernel/trace/trace_workqueue.c
index 40cafb07dffd..cc2d2faa7d9e 100644
--- a/kernel/trace/trace_workqueue.c
+++ b/kernel/trace/trace_workqueue.c
@@ -9,6 +9,7 @@
 #include <trace/events/workqueue.h>
 #include <linux/list.h>
 #include <linux/percpu.h>
+#include <linux/slab.h>
 #include <linux/kref.h>
 #include "trace_stat.h"
 #include "trace.h"