27 files changed, 188 insertions, 91 deletions

diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index 89a47b5aff07..04e6c819b28a 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -451,3 +451,33 @@ Why:	OSS sound_core grabs all legacy minors (0-255) of SOUND_MAJOR
         will also allow making ALSA OSS emulation independent of
         sound_core.  The dependency will be broken then too.
 Who:    Tejun Heo <tj@kernel.org>
+
+----------------------------
+
+What:   Support for VMware's guest paravirtuliazation technique [VMI] will be
+        dropped.
+When:   2.6.37 or earlier.
+Why:    With the recent innovations in CPU hardware acceleration technologies
+        from Intel and AMD, VMware ran a few experiments to compare these
+        techniques to guest paravirtualization technique on VMware's platform.
+        These hardware assisted virtualization techniques have outperformed the
+        performance benefits provided by VMI in most of the workloads. VMware
+        expects that these hardware features will be ubiquitous in a couple of
+        years, as a result, VMware has started a phased retirement of this
+        feature from the hypervisor. We will be removing this feature from the
+        Kernel too. Right now we are targeting 2.6.37 but can retire earlier if
+        technical reasons (read opportunity to remove major chunk of pvops)
+        arise.
+
+        Please note that VMI has always been an optimization and non-VMI kernels
+        still work fine on VMware's platform.
+        Latest versions of VMware's product which support VMI are,
+        Workstation 7.0 and VSphere 4.0 on ESX side, future maintainence
+        releases for these products will continue supporting VMI.
+
+        For more details about VMI retirement take a look at this,
+        http://blogs.vmware.com/guestosguide/2009/09/vmi-retirement.html
+
+Who:    Alok N Kataria <akataria@vmware.com>
+
+----------------------------
diff --git a/MAINTAINERS b/MAINTAINERS
index ff968842ce56..6b057778477d 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4076,6 +4076,13 @@ M:	Peter Zijlstra <a.p.zijlstra@chello.nl>
 M:      Paul Mackerras <paulus@samba.org>
 M:      Ingo Molnar <mingo@elte.hu>
 S:      Supported
+F:      kernel/perf_event.c
+F:      include/linux/perf_event.h
+F:      arch/*/*/kernel/perf_event.c
+F:      arch/*/include/asm/perf_event.h
+F:      arch/*/lib/perf_event.c
+F:      arch/*/kernel/perf_callchain.c
+F:      tools/perf/
 
 PERSONALITY HANDLING
 M:      Christoph Hellwig <hch@infradead.org>
diff --git a/arch/sh/kernel/entry-common.S b/arch/sh/kernel/entry-common.S
index 68d9223b145e..3eb84931d2aa 100644
--- a/arch/sh/kernel/entry-common.S
+++ b/arch/sh/kernel/entry-common.S
@@ -121,7 +121,7 @@ noresched:
 ENTRY(resume_userspace)
         ! r8: current_thread_info
         cli
-        TRACE_IRQS_OfF
+        TRACE_IRQS_OFF
         mov.l   @(TI_FLAGS,r8), r0              ! current_thread_info->flags
         tst     #(_TIF_WORK_MASK & 0xff), r0
         bt/s    __restore_all
diff --git a/arch/sh/kernel/ftrace.c b/arch/sh/kernel/ftrace.c
index a3dcc6d5d253..2c48e267256e 100644
--- a/arch/sh/kernel/ftrace.c
+++ b/arch/sh/kernel/ftrace.c
@@ -291,31 +291,48 @@ struct syscall_metadata *syscall_nr_to_meta(int nr)
         return syscalls_metadata[nr];
 }
 
-void arch_init_ftrace_syscalls(void)
+int syscall_name_to_nr(char *name)
+{
+        int i;
+
+        if (!syscalls_metadata)
+                return -1;
+        for (i = 0; i < NR_syscalls; i++)
+                if (syscalls_metadata[i])
+                        if (!strcmp(syscalls_metadata[i]->name, name))
+                                return i;
+        return -1;
+}
+
+void set_syscall_enter_id(int num, int id)
+{
+        syscalls_metadata[num]->enter_id = id;
+}
+
+void set_syscall_exit_id(int num, int id)
+{
+        syscalls_metadata[num]->exit_id = id;
+}
+
+static int __init arch_init_ftrace_syscalls(void)
 {
         int i;
         struct syscall_metadata *meta;
         unsigned long **psys_syscall_table = &sys_call_table;
-        static atomic_t refs;
-
-        if (atomic_inc_return(&refs) != 1)
-                goto end;
 
         syscalls_metadata = kzalloc(sizeof(*syscalls_metadata) *
                                         FTRACE_SYSCALL_MAX, GFP_KERNEL);
         if (!syscalls_metadata) {
                 WARN_ON(1);
-                return;
+                return -ENOMEM;
         }
 
         for (i = 0; i < FTRACE_SYSCALL_MAX; i++) {
                 meta = find_syscall_meta(psys_syscall_table[i]);
                 syscalls_metadata[i] = meta;
         }
-        return;
 
-        /* Paranoid: avoid overflow */
-end:
-        atomic_dec(&refs);
+        return 0;
 }
+arch_initcall(arch_init_ftrace_syscalls);
 #endif /* CONFIG_FTRACE_SYSCALLS */
diff --git a/arch/sh/kernel/setup.c b/arch/sh/kernel/setup.c
index f9d44f8e0df6..99b4fb553bf1 100644
--- a/arch/sh/kernel/setup.c
+++ b/arch/sh/kernel/setup.c
@@ -549,6 +549,8 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 
         if (cpu == 0)
                 seq_printf(m, "machine\t\t: %s\n", get_system_type());
+        else
+                seq_printf(m, "\n");
 
         seq_printf(m, "processor\t: %d\n", cpu);
         seq_printf(m, "cpu family\t: %s\n", init_utsname()->machine);
diff --git a/arch/sh/kernel/signal_32.c b/arch/sh/kernel/signal_32.c
index 6729703547a1..3db37425210d 100644
--- a/arch/sh/kernel/signal_32.c
+++ b/arch/sh/kernel/signal_32.c
@@ -145,7 +145,7 @@ static inline int restore_sigcontext_fpu(struct sigcontext __user *sc)
 {
         struct task_struct *tsk = current;
 
-        if (!(current_cpu_data.flags & CPU_HAS_FPU))
+        if (!(boot_cpu_data.flags & CPU_HAS_FPU))
                 return 0;
 
         set_used_math();
@@ -158,7 +158,7 @@ static inline int save_sigcontext_fpu(struct sigcontext __user *sc,
 {
         struct task_struct *tsk = current;
 
-        if (!(current_cpu_data.flags & CPU_HAS_FPU))
+        if (!(boot_cpu_data.flags & CPU_HAS_FPU))
                 return 0;
 
         if (!used_math()) {
@@ -199,7 +199,7 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, int *r0_p
 #undef COPY
 
 #ifdef CONFIG_SH_FPU
-        if (current_cpu_data.flags & CPU_HAS_FPU) {
+        if (boot_cpu_data.flags & CPU_HAS_FPU) {
                 int owned_fp;
                 struct task_struct *tsk = current;
 
@@ -472,6 +472,7 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
                 err |= __put_user(OR_R0_R0, &frame->retcode[6]);
                 err |= __put_user((__NR_rt_sigreturn), &frame->retcode[7]);
                 regs->pr = (unsigned long) frame->retcode;
+                flush_icache_range(regs->pr, regs->pr + sizeof(frame->retcode));
         }
 
         if (err)
@@ -497,8 +498,6 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
         pr_debug("SIG deliver (%s:%d): sp=%p pc=%08lx pr=%08lx\n",
                  current->comm, task_pid_nr(current), frame, regs->pc, regs->pr);
 
-        flush_icache_range(regs->pr, regs->pr + sizeof(frame->retcode));
-
         return 0;
 
 give_sigsegv:
diff --git a/arch/sh/kernel/smp.c b/arch/sh/kernel/smp.c
index 442d8d47a41e..160db1003cfb 100644
--- a/arch/sh/kernel/smp.c
+++ b/arch/sh/kernel/smp.c
@@ -35,6 +35,8 @@ static inline void __init smp_store_cpu_info(unsigned int cpu)
 {
         struct sh_cpuinfo *c = cpu_data + cpu;
 
+        memcpy(c, &boot_cpu_data, sizeof(struct sh_cpuinfo));
+
         c->loops_per_jiffy = loops_per_jiffy;
 }
 
diff --git a/arch/sh/kernel/traps_32.c b/arch/sh/kernel/traps_32.c
index e0b5e4b5accd..7a2ee3a6b8e7 100644
--- a/arch/sh/kernel/traps_32.c
+++ b/arch/sh/kernel/traps_32.c
@@ -25,6 +25,7 @@
 #include <linux/kexec.h>
 #include <linux/limits.h>
 #include <linux/proc_fs.h>
+#include <linux/sysfs.h>
 #include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/fpu.h>
@@ -159,12 +160,12 @@ void die(const char * str, struct pt_regs * regs, long err)
 
         oops_enter();
 
-        console_verbose();
         spin_lock_irq(&die_lock);
+        console_verbose();
         bust_spinlocks(1);
 
         printk("%s: %04lx [#%d]\n", str, err & 0xffff, ++die_counter);
-
+        sysfs_printk_last_file();
         print_modules();
         show_regs(regs);
 
@@ -180,6 +181,7 @@ void die(const char * str, struct pt_regs * regs, long err)
         bust_spinlocks(0);
         add_taint(TAINT_DIE);
         spin_unlock_irq(&die_lock);
+        oops_exit();
 
         if (kexec_should_crash(current))
                 crash_kexec(regs);
@@ -190,7 +192,6 @@ void die(const char * str, struct pt_regs * regs, long err)
         if (panic_on_oops)
                 panic("Fatal exception");
 
-        oops_exit();
         do_exit(SIGSEGV);
 }
 
diff --git a/arch/sh/mm/cache.c b/arch/sh/mm/cache.c
index 35c37b7f717a..5e1091be9dc4 100644
--- a/arch/sh/mm/cache.c
+++ b/arch/sh/mm/cache.c
@@ -128,7 +128,7 @@ void __update_cache(struct vm_area_struct *vma,
                 return;
 
         page = pfn_to_page(pfn);
-        if (pfn_valid(pfn) && page_mapping(page)) {
+        if (pfn_valid(pfn)) {
                 int dirty = test_and_clear_bit(PG_dcache_dirty, &page->flags);
                 if (dirty) {
                         unsigned long addr = (unsigned long)page_address(page);
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index c876bace8fdc..07e01149e3bf 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -491,7 +491,7 @@ if PARAVIRT_GUEST
 source "arch/x86/xen/Kconfig"
 
 config VMI
-        bool "VMI Guest support"
+        bool "VMI Guest support (DEPRECATED)"
         select PARAVIRT
         depends on X86_32
         ---help---
@@ -500,6 +500,15 @@ config VMI
           at the moment), by linking the kernel to a GPL-ed ROM module
           provided by the hypervisor.
 
+          As of September 2009, VMware has started a phased retirement
+          of this feature from VMware's products. Please see
+          feature-removal-schedule.txt for details.  If you are
+          planning to enable this option, please note that you cannot
+          live migrate a VMI enabled VM to a future VMware product,
+          which doesn't support VMI. So if you expect your kernel to
+          seamlessly migrate to newer VMware products, keep this
+          disabled.
+
 config KVM_CLOCK
         bool "KVM paravirtualized clock"
         select PARAVIRT
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 8aebcc41041d..efb38994859c 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -840,42 +840,22 @@ static __always_inline void __raw_spin_unlock(struct raw_spinlock *lock)
 
 static inline unsigned long __raw_local_save_flags(void)
 {
-        unsigned long f;
-
-        asm volatile(paravirt_alt(PARAVIRT_CALL)
-                     : "=a"(f)
-                     : paravirt_type(pv_irq_ops.save_fl),
-                       paravirt_clobber(CLBR_EAX)
-                     : "memory", "cc");
-        return f;
+        return PVOP_CALLEE0(unsigned long, pv_irq_ops.save_fl);
 }
 
 static inline void raw_local_irq_restore(unsigned long f)
 {
-        asm volatile(paravirt_alt(PARAVIRT_CALL)
-                     : "=a"(f)
-                     : PV_FLAGS_ARG(f),
-                       paravirt_type(pv_irq_ops.restore_fl),
-                       paravirt_clobber(CLBR_EAX)
-                     : "memory", "cc");
+        PVOP_VCALLEE1(pv_irq_ops.restore_fl, f);
 }
 
 static inline void raw_local_irq_disable(void)
 {
-        asm volatile(paravirt_alt(PARAVIRT_CALL)
-                     :
-                     : paravirt_type(pv_irq_ops.irq_disable),
-                       paravirt_clobber(CLBR_EAX)
-                     : "memory", "eax", "cc");
+        PVOP_VCALLEE0(pv_irq_ops.irq_disable);
 }
 
 static inline void raw_local_irq_enable(void)
 {
-        asm volatile(paravirt_alt(PARAVIRT_CALL)
-                     :
-                     : paravirt_type(pv_irq_ops.irq_enable),
-                       paravirt_clobber(CLBR_EAX)
-                     : "memory", "eax", "cc");
+        PVOP_VCALLEE0(pv_irq_ops.irq_enable);
 }
 
 static inline unsigned long __raw_local_irq_save(void)
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index dd0f5b32489d..9357473c8da0 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -494,10 +494,11 @@ int paravirt_disable_iospace(void);
 #define EXTRA_CLOBBERS
 #define VEXTRA_CLOBBERS
 #else  /* CONFIG_X86_64 */
+/* [re]ax isn't an arg, but the return val */
 #define PVOP_VCALL_ARGS                                 \
         unsigned long __edi = __edi, __esi = __esi,     \
-                __edx = __edx, __ecx = __ecx
-#define PVOP_CALL_ARGS          PVOP_VCALL_ARGS, __eax
+                __edx = __edx, __ecx = __ecx, __eax = __eax
+#define PVOP_CALL_ARGS          PVOP_VCALL_ARGS
 
 #define PVOP_CALL_ARG1(x)               "D" ((unsigned long)(x))
 #define PVOP_CALL_ARG2(x)               "S" ((unsigned long)(x))
@@ -509,6 +510,7 @@ int paravirt_disable_iospace(void);
                                 "=c" (__ecx)
 #define PVOP_CALL_CLOBBERS      PVOP_VCALL_CLOBBERS, "=a" (__eax)
 
+/* void functions are still allowed [re]ax for scratch */
 #define PVOP_VCALLEE_CLOBBERS   "=a" (__eax)
 #define PVOP_CALLEE_CLOBBERS    PVOP_VCALLEE_CLOBBERS
 
@@ -583,8 +585,8 @@ int paravirt_disable_iospace(void);
                        VEXTRA_CLOBBERS,                                 \
                        pre, post, ##__VA_ARGS__)
 
-#define __PVOP_VCALLEESAVE(rettype, op, pre, post, ...)                 \
-        ____PVOP_CALL(rettype, op.func, CLBR_RET_REG,                   \
+#define __PVOP_VCALLEESAVE(op, pre, post, ...)                          \
+        ____PVOP_VCALL(op.func, CLBR_RET_REG,                           \
                       PVOP_VCALLEE_CLOBBERS, ,                          \
                       pre, post, ##__VA_ARGS__)
 
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 391206199515..74656d1d4e30 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -244,7 +244,6 @@ unsigned int __irq_entry do_IRQ(struct pt_regs *regs)
                                 __func__, smp_processor_id(), vector, irq);
         }
 
-        run_local_timers();
         irq_exit();
 
         set_irq_regs(old_regs);
@@ -269,7 +268,6 @@ void smp_generic_interrupt(struct pt_regs *regs)
         if (generic_interrupt_extension)
                 generic_interrupt_extension();
 
-        run_local_timers();
         irq_exit();
 
         set_irq_regs(old_regs);
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index d915d956e66d..ec1de97600e7 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -198,7 +198,6 @@ void smp_reschedule_interrupt(struct pt_regs *regs)
 {
         ack_APIC_irq();
         inc_irq_stat(irq_resched_count);
-        run_local_timers();
         /*
          * KVM uses this interrupt to force a cpu out of guest mode
          */
diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c
index dcb00d278512..be2573448ed9 100644
--- a/arch/x86/kernel/time.c
+++ b/arch/x86/kernel/time.c
@@ -38,7 +38,8 @@ unsigned long profile_pc(struct pt_regs *regs)
 #ifdef CONFIG_FRAME_POINTER
                 return *(unsigned long *)(regs->bp + sizeof(long));
 #else
-                unsigned long *sp = (unsigned long *)regs->sp;
+                unsigned long *sp =
+                        (unsigned long *)kernel_stack_pointer(regs);
                 /*
                  * Return address is either directly at stack pointer
                  * or above a saved flags. Eflags has bits 22-31 zero,
diff --git a/arch/x86/kernel/trampoline.c b/arch/x86/kernel/trampoline.c
index 699f7eeb896a..cd022121cab6 100644
--- a/arch/x86/kernel/trampoline.c
+++ b/arch/x86/kernel/trampoline.c
@@ -3,8 +3,16 @@
 #include <asm/trampoline.h>
 #include <asm/e820.h>
 
+#if defined(CONFIG_X86_64) && defined(CONFIG_ACPI_SLEEP)
+#define __trampinit
+#define __trampinitdata
+#else
+#define __trampinit __cpuinit
+#define __trampinitdata __cpuinitdata
+#endif
+
 /* ready for x86_64 and x86 */
-unsigned char *__cpuinitdata trampoline_base = __va(TRAMPOLINE_BASE);
+unsigned char *__trampinitdata trampoline_base = __va(TRAMPOLINE_BASE);
 
 void __init reserve_trampoline_memory(void)
 {
@@ -26,7 +34,7 @@ void __init reserve_trampoline_memory(void)
  * bootstrap into the page concerned. The caller
  * has made sure it's suitably aligned.
  */
-unsigned long __cpuinit setup_trampoline(void)
+unsigned long __trampinit setup_trampoline(void)
 {
         memcpy(trampoline_base, trampoline_data, TRAMPOLINE_SIZE);
         return virt_to_phys(trampoline_base);
diff --git a/arch/x86/kernel/trampoline_64.S b/arch/x86/kernel/trampoline_64.S
index 596d54c660a5..3af2dff58b21 100644
--- a/arch/x86/kernel/trampoline_64.S
+++ b/arch/x86/kernel/trampoline_64.S
@@ -32,8 +32,12 @@
 #include <asm/segment.h>
 #include <asm/processor-flags.h>
 
+#ifdef CONFIG_ACPI_SLEEP
+.section .rodata, "a", @progbits
+#else
 /* We can free up the trampoline after bootup if cpu hotplug is not supported. */
 __CPUINITRODATA
+#endif
 .code16
 
 ENTRY(trampoline_data)
diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c
index 31e6f6cfe53e..d430e4c30193 100644
--- a/arch/x86/kernel/vmi_32.c
+++ b/arch/x86/kernel/vmi_32.c
@@ -648,7 +648,7 @@ static inline int __init activate_vmi(void)
 
         pv_info.paravirt_enabled = 1;
         pv_info.kernel_rpl = kernel_cs & SEGMENT_RPL_MASK;
-        pv_info.name = "vmi";
+        pv_info.name = "vmi [deprecated]";
 
         pv_init_ops.patch = vmi_patch;
 
diff --git a/drivers/oprofile/event_buffer.c b/drivers/oprofile/event_buffer.c
index 2b7ae366ceb1..5df60a6b6776 100644
--- a/drivers/oprofile/event_buffer.c
+++ b/drivers/oprofile/event_buffer.c
@@ -35,12 +35,23 @@ static size_t buffer_pos;
 /* atomic_t because wait_event checks it outside of buffer_mutex */
 static atomic_t buffer_ready = ATOMIC_INIT(0);
 
-/* Add an entry to the event buffer. When we
- * get near to the end we wake up the process
- * sleeping on the read() of the file.
+/*
+ * Add an entry to the event buffer. When we get near to the end we
+ * wake up the process sleeping on the read() of the file. To protect
+ * the event_buffer this function may only be called when buffer_mutex
+ * is set.
  */
 void add_event_entry(unsigned long value)
 {
+        /*
+         * This shouldn't happen since all workqueues or handlers are
+         * canceled or flushed before the event buffer is freed.
+         */
+        if (!event_buffer) {
+                WARN_ON_ONCE(1);
+                return;
+        }
+
         if (buffer_pos == buffer_size) {
                 atomic_inc(&oprofile_stats.event_lost_overflow);
                 return;
@@ -69,7 +80,6 @@ void wake_up_buffer_waiter(void)
 
 int alloc_event_buffer(void)
 {
-        int err = -ENOMEM;
         unsigned long flags;
 
         spin_lock_irqsave(&oprofilefs_lock, flags);
@@ -80,21 +90,22 @@ int alloc_event_buffer(void)
         if (buffer_watershed >= buffer_size)
                 return -EINVAL;
 
+        buffer_pos = 0;
         event_buffer = vmalloc(sizeof(unsigned long) * buffer_size);
         if (!event_buffer)
-                goto out;
+                return -ENOMEM;
 
-        err = 0;
-out:
-        return err;
+        return 0;
 }
 
 
 void free_event_buffer(void)
 {
+        mutex_lock(&buffer_mutex);
         vfree(event_buffer);
-
+        buffer_pos = 0;
         event_buffer = NULL;
+        mutex_unlock(&buffer_mutex);
 }
 
 
@@ -167,6 +178,12 @@ static ssize_t event_buffer_read(struct file *file, char __user *buf,
 
         mutex_lock(&buffer_mutex);
 
+        /* May happen if the buffer is freed during pending reads. */
+        if (!event_buffer) {
+                retval = -EINTR;
+                goto out;
+        }
+
         atomic_set(&buffer_ready, 0);
 
         retval = -EFAULT;
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index 3815ac1d58b2..9af56723c096 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -142,6 +142,11 @@ static inline struct lock_class *hlock_class(struct held_lock *hlock)
 #ifdef CONFIG_LOCK_STAT
 static DEFINE_PER_CPU(struct lock_class_stats[MAX_LOCKDEP_KEYS], lock_stats);
 
+static inline u64 lockstat_clock(void)
+{
+        return cpu_clock(smp_processor_id());
+}
+
 static int lock_point(unsigned long points[], unsigned long ip)
 {
         int i;
@@ -158,7 +163,7 @@ static int lock_point(unsigned long points[], unsigned long ip)
         return i;
 }
 
-static void lock_time_inc(struct lock_time *lt, s64 time)
+static void lock_time_inc(struct lock_time *lt, u64 time)
 {
         if (time > lt->max)
                 lt->max = time;
@@ -234,12 +239,12 @@ static void put_lock_stats(struct lock_class_stats *stats)
 static void lock_release_holdtime(struct held_lock *hlock)
 {
         struct lock_class_stats *stats;
-        s64 holdtime;
+        u64 holdtime;
 
         if (!lock_stat)
                 return;
 
-        holdtime = sched_clock() - hlock->holdtime_stamp;
+        holdtime = lockstat_clock() - hlock->holdtime_stamp;
 
         stats = get_lock_stats(hlock_class(hlock));
         if (hlock->read)
@@ -2792,7 +2797,7 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
         hlock->references = references;
 #ifdef CONFIG_LOCK_STAT
         hlock->waittime_stamp = 0;
-        hlock->holdtime_stamp = sched_clock();
+        hlock->holdtime_stamp = lockstat_clock();
 #endif
 
         if (check == 2 && !mark_irqflags(curr, hlock))
@@ -3322,7 +3327,7 @@ found_it:
         if (hlock->instance != lock)
                 return;
 
-        hlock->waittime_stamp = sched_clock();
+        hlock->waittime_stamp = lockstat_clock();
 
         contention_point = lock_point(hlock_class(hlock)->contention_point, ip);
         contending_point = lock_point(hlock_class(hlock)->contending_point,
@@ -3345,8 +3350,7 @@ __lock_acquired(struct lockdep_map *lock, unsigned long ip)
         struct held_lock *hlock, *prev_hlock;
         struct lock_class_stats *stats;
         unsigned int depth;
-        u64 now;
-        s64 waittime = 0;
+        u64 now, waittime = 0;
         int i, cpu;
 
         depth = curr->lockdep_depth;
@@ -3374,7 +3378,7 @@ found_it:
 
         cpu = smp_processor_id();
         if (hlock->waittime_stamp) {
-                now = sched_clock();
+                now = lockstat_clock();
                 waittime = now - hlock->waittime_stamp;
                 hlock->holdtime_stamp = now;
         }
diff --git a/kernel/sched.c b/kernel/sched.c
index 8d25be06db62..e88689522e66 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -676,6 +676,7 @@ inline void update_rq_clock(struct rq *rq)
 
 /**
  * runqueue_is_locked
+ * @cpu: the processor in question.
  *
  * Returns true if the current cpu runqueue is locked.
  * This interface allows printk to be called with the runqueue lock
@@ -2311,7 +2312,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
 {
         int cpu, orig_cpu, this_cpu, success = 0;
         unsigned long flags;
-        struct rq *rq;
+        struct rq *rq, *orig_rq;
 
         if (!sched_feat(SYNC_WAKEUPS))
                 wake_flags &= ~WF_SYNC;
@@ -2319,7 +2320,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
         this_cpu = get_cpu();
 
         smp_wmb();
-        rq = task_rq_lock(p, &flags);
+        rq = orig_rq = task_rq_lock(p, &flags);
         update_rq_clock(rq);
         if (!(p->state & state))
                 goto out;
@@ -2350,6 +2351,10 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
                 set_task_cpu(p, cpu);
 
         rq = task_rq_lock(p, &flags);
+
+        if (rq != orig_rq)
+                update_rq_clock(rq);
+
         WARN_ON(p->state != TASK_WAKING);
         cpu = task_cpu(p);
 
@@ -3656,6 +3661,7 @@ static void update_group_power(struct sched_domain *sd, int cpu)
 
 /**
  * update_sg_lb_stats - Update sched_group's statistics for load balancing.
+ * @sd: The sched_domain whose statistics are to be updated.
  * @group: sched_group whose statistics are to be updated.
  * @this_cpu: Cpu for which load balance is currently performed.
  * @idle: Idle status of this_cpu
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 45068269ebb1..c820b0310a12 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1393,7 +1393,7 @@ int trace_array_vprintk(struct trace_array *tr,
 
 int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
 {
-        return trace_array_printk(&global_trace, ip, fmt, args);
+        return trace_array_vprintk(&global_trace, ip, fmt, args);
 }
 EXPORT_SYMBOL_GPL(trace_vprintk);
 
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 23245785927f..98a6cc5c64ed 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -933,8 +933,9 @@ static void postfix_clear(struct filter_parse_state *ps)
 
         while (!list_empty(&ps->postfix)) {
                 elt = list_first_entry(&ps->postfix, struct postfix_elt, list);
-                kfree(elt->operand);
                 list_del(&elt->list);
+                kfree(elt->operand);
+                kfree(elt);
         }
 }
 
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 5881943f0c34..742a32eee8fc 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -157,11 +157,18 @@ uname_R := $(shell sh -c 'uname -r 2>/dev/null || echo not')
 uname_P := $(shell sh -c 'uname -p 2>/dev/null || echo not')
 uname_V := $(shell sh -c 'uname -v 2>/dev/null || echo not')
 
-# If we're on a 64-bit kernel, use -m64
-ifndef NO_64BIT
-        ifneq ($(patsubst %64,%,$(uname_M)),$(uname_M))
-          M64 := -m64
-        endif
+#
+# Add -m32 for cross-builds:
+#
+ifdef NO_64BIT
+  MBITS := -m32
+else
+  #
+  # If we're on a 64-bit kernel, use -m64:
+  #
+  ifneq ($(patsubst %64,%,$(uname_M)),$(uname_M))
+    MBITS := -m64
+  endif
 endif
 
 # CFLAGS and LDFLAGS are for the users to override from the command line.
@@ -194,7 +201,7 @@ EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wold-style-definition
 EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wstrict-prototypes
 EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wdeclaration-after-statement
 
-CFLAGS = $(M64) -ggdb3 -Wall -Wextra -std=gnu99 -Werror -O6 -fstack-protector-all -D_FORTIFY_SOURCE=2 $(EXTRA_WARNINGS)
+CFLAGS = $(MBITS) -ggdb3 -Wall -Wextra -std=gnu99 -Werror -O6 -fstack-protector-all -D_FORTIFY_SOURCE=2 $(EXTRA_WARNINGS)
 LDFLAGS = -lpthread -lrt -lelf -lm
 ALL_CFLAGS = $(CFLAGS)
 ALL_LDFLAGS = $(LDFLAGS)
@@ -416,7 +423,7 @@ ifeq ($(uname_S),Darwin)
 endif
 
 ifneq ($(shell sh -c "(echo '\#include <libelf.h>'; echo 'int main(void) { Elf * elf = elf_begin(0, ELF_C_READ_MMAP, 0); return (long)elf; }') | $(CC) -x c - $(ALL_CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -o /dev/null $(ALL_LDFLAGS) > /dev/null 2>&1 && echo y"), y)
-        msg := $(error No libelf.h/libelf found, please install libelf-dev/elfutils-libelf-devel);
+        msg := $(error No libelf.h/libelf found, please install libelf-dev/elfutils-libelf-devel and glibc-dev[el]);
 endif
 
 ifdef NO_DEMANGLE
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index ea9c15c0cdfe..ce2d5be4f30e 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -1287,7 +1287,7 @@ static struct sort_dimension *available_sorts[] = {
 
 static LIST_HEAD(sort_list);
 
-static int sort_dimension__add(char *tok, struct list_head *list)
+static int sort_dimension__add(const char *tok, struct list_head *list)
 {
         int i;
 
@@ -1917,7 +1917,7 @@ static void setup_sorting(void)
 
         free(str);
 
-        sort_dimension__add((char *)"pid", &cmp_pid);
+        sort_dimension__add("pid", &cmp_pid);
 }
 
 static const char *record_args[] = {
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 87c424de79ee..8cfb48cbbea0 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -691,7 +691,10 @@ static void store_event_type(const char *orgname)
         FILE *file;
         int id;
 
-        sprintf(filename, "/sys/kernel/debug/tracing/events/%s/id", orgname);
+        sprintf(filename, "%s/", debugfs_path);
+        strncat(filename, orgname, strlen(orgname));
+        strcat(filename, "/id");
+
         c = strchr(filename, ':');
         if (c)
                 *c = '/';
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index 55b41b9e3834..55c9659a56e2 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -618,7 +618,7 @@ static int test_type(enum event_type type, enum event_type expect)
 }
 
 static int test_type_token(enum event_type type, char *token,
-                    enum event_type expect, char *expect_tok)
+                    enum event_type expect, const char *expect_tok)
 {
         if (type != expect) {
                 die("Error: expected type %d but read %d",
@@ -650,7 +650,7 @@ static int read_expect_type(enum event_type expect, char **tok)
         return __read_expect_type(expect, tok, 1);
 }
 
-static int __read_expected(enum event_type expect, char *str, int newline_ok)
+static int __read_expected(enum event_type expect, const char *str, int newline_ok)
 {
         enum event_type type;
         char *token;
@@ -668,12 +668,12 @@ static int __read_expected(enum event_type expect, char *str, int newline_ok)
         return 0;
 }
 
-static int read_expected(enum event_type expect, char *str)
+static int read_expected(enum event_type expect, const char *str)
 {
         return __read_expected(expect, str, 1);
 }
 
-static int read_expected_item(enum event_type expect, char *str)
+static int read_expected_item(enum event_type expect, const char *str)
 {
         return __read_expected(expect, str, 0);
 }