Merge branch 'tracing/ftrace' into auto-ftrace-next

22 files changed, 524 insertions, 27 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index bf07b6f50fa1..c3a4c03c0800 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -23,6 +23,8 @@ config X86
         select HAVE_OPROFILE
         select HAVE_KPROBES
         select HAVE_KRETPROBES
+        select HAVE_DYNAMIC_FTRACE
+        select HAVE_FTRACE
         select HAVE_KVM if ((X86_32 && !X86_VOYAGER && !X86_VISWS && !X86_NUMAQ) || X86_64)
         select HAVE_ARCH_KGDB if !X86_VOYAGER
 
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index 18363374d51a..f395fd537c5c 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -172,6 +172,14 @@ config IOMMU_LEAK
           Add a simple leak tracer to the IOMMU code. This is useful when you
           are debugging a buggy device driver that leaks IOMMU mappings.
 
+config PAGE_FAULT_HANDLERS
+        bool "Custom page fault handlers"
+        depends on DEBUG_KERNEL
+        help
+          Allow the use of custom page fault handlers. A kernel module may
+          register a function that is called on every page fault. Custom
+          handlers are used by some debugging and reverse engineering tools.
+
 #
 # IO delay types:
 #
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 77807d4769c9..5ff67208d4ae 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -6,6 +6,13 @@ extra-y                := head_$(BITS).o head$(BITS).o init_task.o vmlinux.lds
 
 CPPFLAGS_vmlinux.lds += -U$(UTS_MACHINE)
 
+ifdef CONFIG_FTRACE
+# Do not profile debug utilities
+CFLAGS_REMOVE_tsc_64.o = -pg
+CFLAGS_REMOVE_tsc_32.o = -pg
+CFLAGS_REMOVE_rtc.o = -pg
+endif
+
 #
 # vsyscalls (which work on the user stack) should have
 # no stack-protector checks:
@@ -56,6 +63,7 @@ obj-$(CONFIG_X86_MPPARSE)	+= mpparse.o
 obj-$(CONFIG_X86_LOCAL_APIC)    += apic_$(BITS).o nmi_$(BITS).o
 obj-$(CONFIG_X86_IO_APIC)       += io_apic_$(BITS).o
 obj-$(CONFIG_X86_REBOOTFIXUPS)  += reboot_fixups_32.o
+obj-$(CONFIG_DYNAMIC_FTRACE)    += ftrace.o
 obj-$(CONFIG_KEXEC)             += machine_kexec_$(BITS).o
 obj-$(CONFIG_KEXEC)             += relocate_kernel_$(BITS).o crash.o
 obj-$(CONFIG_CRASH_DUMP)        += crash_dump_$(BITS).o
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 65c7857a90dd..2763cb37b553 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -1,6 +1,6 @@
 #include <linux/module.h>
 #include <linux/sched.h>
-#include <linux/spinlock.h>
+#include <linux/mutex.h>
 #include <linux/list.h>
 #include <linux/kprobes.h>
 #include <linux/mm.h>
@@ -143,7 +143,7 @@ static const unsigned char *const p6_nops[ASM_NOP_MAX+1] = {
 #ifdef CONFIG_X86_64
 
 extern char __vsyscall_0;
-static inline const unsigned char*const * find_nop_table(void)
+const unsigned char *const *find_nop_table(void)
 {
         return boot_cpu_data.x86_vendor != X86_VENDOR_INTEL ||
                boot_cpu_data.x86 < 6 ? k8_nops : p6_nops;
@@ -162,7 +162,7 @@ static const struct nop {
         { -1, NULL }
 };
 
-static const unsigned char*const * find_nop_table(void)
+const unsigned char *const *find_nop_table(void)
 {
         const unsigned char *const *noptable = intel_nops;
         int i;
@@ -279,7 +279,7 @@ struct smp_alt_module {
         struct list_head next;
 };
 static LIST_HEAD(smp_alt_modules);
-static DEFINE_SPINLOCK(smp_alt);
+static DEFINE_MUTEX(smp_alt);
 static int smp_mode = 1;        /* protected by smp_alt */
 
 void alternatives_smp_module_add(struct module *mod, char *name,
@@ -312,12 +312,12 @@ void alternatives_smp_module_add(struct module *mod, char *name,
                 __func__, smp->locks, smp->locks_end,
                 smp->text, smp->text_end, smp->name);
 
-        spin_lock(&smp_alt);
+        mutex_lock(&smp_alt);
         list_add_tail(&smp->next, &smp_alt_modules);
         if (boot_cpu_has(X86_FEATURE_UP))
                 alternatives_smp_unlock(smp->locks, smp->locks_end,
                                         smp->text, smp->text_end);
-        spin_unlock(&smp_alt);
+        mutex_unlock(&smp_alt);
 }
 
 void alternatives_smp_module_del(struct module *mod)
@@ -327,17 +327,17 @@ void alternatives_smp_module_del(struct module *mod)
         if (smp_alt_once || noreplace_smp)
                 return;
 
-        spin_lock(&smp_alt);
+        mutex_lock(&smp_alt);
         list_for_each_entry(item, &smp_alt_modules, next) {
                 if (mod != item->mod)
                         continue;
                 list_del(&item->next);
-                spin_unlock(&smp_alt);
+                mutex_unlock(&smp_alt);
                 DPRINTK("%s: %s\n", __func__, item->name);
                 kfree(item);
                 return;
         }
-        spin_unlock(&smp_alt);
+        mutex_unlock(&smp_alt);
 }
 
 void alternatives_smp_switch(int smp)
@@ -359,7 +359,7 @@ void alternatives_smp_switch(int smp)
                 return;
         BUG_ON(!smp && (num_online_cpus() > 1));
 
-        spin_lock(&smp_alt);
+        mutex_lock(&smp_alt);
 
         /*
          * Avoid unnecessary switches because it forces JIT based VMs to
@@ -383,7 +383,7 @@ void alternatives_smp_switch(int smp)
                                                 mod->text, mod->text_end);
         }
         smp_mode = smp;
-        spin_unlock(&smp_alt);
+        mutex_unlock(&smp_alt);
 }
 
 #endif
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index c778e4fa55a2..95e6bbe3665e 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -51,6 +51,7 @@
 #include <asm/percpu.h>
 #include <asm/dwarf2.h>
 #include <asm/processor-flags.h>
+#include <asm/ftrace.h>
 #include "irq_vectors.h"
 
 /*
@@ -1110,6 +1111,77 @@ ENDPROC(xen_failsafe_callback)
 
 #endif  /* CONFIG_XEN */
 
+#ifdef CONFIG_FTRACE
+#ifdef CONFIG_DYNAMIC_FTRACE
+
+ENTRY(mcount)
+        pushl %eax
+        pushl %ecx
+        pushl %edx
+        movl 0xc(%esp), %eax
+        subl $MCOUNT_INSN_SIZE, %eax
+
+.globl mcount_call
+mcount_call:
+        call ftrace_stub
+
+        popl %edx
+        popl %ecx
+        popl %eax
+
+        ret
+END(mcount)
+
+ENTRY(ftrace_caller)
+        pushl %eax
+        pushl %ecx
+        pushl %edx
+        movl 0xc(%esp), %eax
+        movl 0x4(%ebp), %edx
+        subl $MCOUNT_INSN_SIZE, %eax
+
+.globl ftrace_call
+ftrace_call:
+        call ftrace_stub
+
+        popl %edx
+        popl %ecx
+        popl %eax
+
+.globl ftrace_stub
+ftrace_stub:
+        ret
+END(ftrace_caller)
+
+#else /* ! CONFIG_DYNAMIC_FTRACE */
+
+ENTRY(mcount)
+        cmpl $ftrace_stub, ftrace_trace_function
+        jnz trace
+.globl ftrace_stub
+ftrace_stub:
+        ret
+
+        /* taken from glibc */
+trace:
+        pushl %eax
+        pushl %ecx
+        pushl %edx
+        movl 0xc(%esp), %eax
+        movl 0x4(%ebp), %edx
+        subl $MCOUNT_INSN_SIZE, %eax
+
+        call *ftrace_trace_function
+
+        popl %edx
+        popl %ecx
+        popl %eax
+
+        jmp ftrace_stub
+END(mcount)
+#endif /* CONFIG_DYNAMIC_FTRACE */
+#endif /* CONFIG_FTRACE */
+
 .section .rodata,"a"
 #include "syscall_table_32.S"
 
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 556a8df522a7..b0f7308f78a6 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -51,9 +51,115 @@
 #include <asm/page.h>
 #include <asm/irqflags.h>
 #include <asm/paravirt.h>
+#include <asm/ftrace.h>
 
         .code64
 
+#ifdef CONFIG_FTRACE
+#ifdef CONFIG_DYNAMIC_FTRACE
+ENTRY(mcount)
+
+        subq $0x38, %rsp
+        movq %rax, (%rsp)
+        movq %rcx, 8(%rsp)
+        movq %rdx, 16(%rsp)
+        movq %rsi, 24(%rsp)
+        movq %rdi, 32(%rsp)
+        movq %r8, 40(%rsp)
+        movq %r9, 48(%rsp)
+
+        movq 0x38(%rsp), %rdi
+        subq $MCOUNT_INSN_SIZE, %rdi
+
+.globl mcount_call
+mcount_call:
+        call ftrace_stub
+
+        movq 48(%rsp), %r9
+        movq 40(%rsp), %r8
+        movq 32(%rsp), %rdi
+        movq 24(%rsp), %rsi
+        movq 16(%rsp), %rdx
+        movq 8(%rsp), %rcx
+        movq (%rsp), %rax
+        addq $0x38, %rsp
+
+        retq
+END(mcount)
+
+ENTRY(ftrace_caller)
+
+        /* taken from glibc */
+        subq $0x38, %rsp
+        movq %rax, (%rsp)
+        movq %rcx, 8(%rsp)
+        movq %rdx, 16(%rsp)
+        movq %rsi, 24(%rsp)
+        movq %rdi, 32(%rsp)
+        movq %r8, 40(%rsp)
+        movq %r9, 48(%rsp)
+
+        movq 0x38(%rsp), %rdi
+        movq 8(%rbp), %rsi
+        subq $MCOUNT_INSN_SIZE, %rdi
+
+.globl ftrace_call
+ftrace_call:
+        call ftrace_stub
+
+        movq 48(%rsp), %r9
+        movq 40(%rsp), %r8
+        movq 32(%rsp), %rdi
+        movq 24(%rsp), %rsi
+        movq 16(%rsp), %rdx
+        movq 8(%rsp), %rcx
+        movq (%rsp), %rax
+        addq $0x38, %rsp
+
+.globl ftrace_stub
+ftrace_stub:
+        retq
+END(ftrace_caller)
+
+#else /* ! CONFIG_DYNAMIC_FTRACE */
+ENTRY(mcount)
+        cmpq $ftrace_stub, ftrace_trace_function
+        jnz trace
+.globl ftrace_stub
+ftrace_stub:
+        retq
+
+trace:
+        /* taken from glibc */
+        subq $0x38, %rsp
+        movq %rax, (%rsp)
+        movq %rcx, 8(%rsp)
+        movq %rdx, 16(%rsp)
+        movq %rsi, 24(%rsp)
+        movq %rdi, 32(%rsp)
+        movq %r8, 40(%rsp)
+        movq %r9, 48(%rsp)
+
+        movq 0x38(%rsp), %rdi
+        movq 8(%rbp), %rsi
+        subq $MCOUNT_INSN_SIZE, %rdi
+
+        call   *ftrace_trace_function
+
+        movq 48(%rsp), %r9
+        movq 40(%rsp), %r8
+        movq 32(%rsp), %rdi
+        movq 24(%rsp), %rsi
+        movq 16(%rsp), %rdx
+        movq 8(%rsp), %rcx
+        movq (%rsp), %rax
+        addq $0x38, %rsp
+
+        jmp ftrace_stub
+END(mcount)
+#endif /* CONFIG_DYNAMIC_FTRACE */
+#endif /* CONFIG_FTRACE */
+
 #ifndef CONFIG_PREEMPT
 #define retint_kernel retint_restore_args
 #endif  
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
new file mode 100644
index 000000000000..ab115cd15fdf
--- /dev/null
+++ b/arch/x86/kernel/ftrace.c
@@ -0,0 +1,141 @@
+/*
+ * Code for replacing ftrace calls with jumps.
+ *
+ * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com>
+ *
+ * Thanks goes to Ingo Molnar, for suggesting the idea.
+ * Mathieu Desnoyers, for suggesting postponing the modifications.
+ * Arjan van de Ven, for keeping me straight, and explaining to me
+ * the dangers of modifying code on the run.
+ */
+
+#include <linux/spinlock.h>
+#include <linux/hardirq.h>
+#include <linux/ftrace.h>
+#include <linux/percpu.h>
+#include <linux/init.h>
+#include <linux/list.h>
+
+#include <asm/alternative.h>
+#include <asm/ftrace.h>
+
+
+/* Long is fine, even if it is only 4 bytes ;-) */
+static long *ftrace_nop;
+
+union ftrace_code_union {
+        char code[MCOUNT_INSN_SIZE];
+        struct {
+                char e8;
+                int offset;
+        } __attribute__((packed));
+};
+
+
+static int notrace ftrace_calc_offset(long ip, long addr)
+{
+        return (int)(addr - ip);
+}
+
+notrace unsigned char *ftrace_nop_replace(void)
+{
+        return (char *)ftrace_nop;
+}
+
+notrace unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
+{
+        static union ftrace_code_union calc;
+
+        calc.e8         = 0xe8;
+        calc.offset     = ftrace_calc_offset(ip + MCOUNT_INSN_SIZE, addr);
+
+        /*
+         * No locking needed, this must be called via kstop_machine
+         * which in essence is like running on a uniprocessor machine.
+         */
+        return calc.code;
+}
+
+notrace int
+ftrace_modify_code(unsigned long ip, unsigned char *old_code,
+                   unsigned char *new_code)
+{
+        unsigned replaced;
+        unsigned old = *(unsigned *)old_code; /* 4 bytes */
+        unsigned new = *(unsigned *)new_code; /* 4 bytes */
+        unsigned char newch = new_code[4];
+        int faulted = 0;
+
+        /*
+         * Note: Due to modules and __init, code can
+         *  disappear and change, we need to protect against faulting
+         *  as well as code changing.
+         *
+         * No real locking needed, this code is run through
+         * kstop_machine.
+         */
+        asm volatile (
+                "1: lock\n"
+                "   cmpxchg %3, (%2)\n"
+                "   jnz 2f\n"
+                "   movb %b4, 4(%2)\n"
+                "2:\n"
+                ".section .fixup, \"ax\"\n"
+                "3:     movl $1, %0\n"
+                "       jmp 2b\n"
+                ".previous\n"
+                _ASM_EXTABLE(1b, 3b)
+                : "=r"(faulted), "=a"(replaced)
+                : "r"(ip), "r"(new), "c"(newch),
+                  "0"(faulted), "a"(old)
+                : "memory");
+        sync_core();
+
+        if (replaced != old && replaced != new)
+                faulted = 2;
+
+        return faulted;
+}
+
+notrace int ftrace_update_ftrace_func(ftrace_func_t func)
+{
+        unsigned long ip = (unsigned long)(&ftrace_call);
+        unsigned char old[MCOUNT_INSN_SIZE], *new;
+        int ret;
+
+        memcpy(old, &ftrace_call, MCOUNT_INSN_SIZE);
+        new = ftrace_call_replace(ip, (unsigned long)func);
+        ret = ftrace_modify_code(ip, old, new);
+
+        return ret;
+}
+
+notrace int ftrace_mcount_set(unsigned long *data)
+{
+        unsigned long ip = (long)(&mcount_call);
+        unsigned long *addr = data;
+        unsigned char old[MCOUNT_INSN_SIZE], *new;
+
+        /*
+         * Replace the mcount stub with a pointer to the
+         * ip recorder function.
+         */
+        memcpy(old, &mcount_call, MCOUNT_INSN_SIZE);
+        new = ftrace_call_replace(ip, *addr);
+        *addr = ftrace_modify_code(ip, old, new);
+
+        return 0;
+}
+
+int __init ftrace_dyn_arch_init(void *data)
+{
+        const unsigned char *const *noptable = find_nop_table();
+
+        /* This is running in kstop_machine */
+
+        ftrace_mcount_set(data);
+
+        ftrace_nop = (unsigned long *)noptable[MCOUNT_INSN_SIZE];
+
+        return 0;
+}
diff --git a/arch/x86/kernel/i386_ksyms_32.c b/arch/x86/kernel/i386_ksyms_32.c
index deb43785e923..dd7ebee446af 100644
--- a/arch/x86/kernel/i386_ksyms_32.c
+++ b/arch/x86/kernel/i386_ksyms_32.c
@@ -1,7 +1,14 @@
 #include <linux/module.h>
+
 #include <asm/checksum.h>
-#include <asm/desc.h>
 #include <asm/pgtable.h>
+#include <asm/desc.h>
+#include <asm/ftrace.h>
+
+#ifdef CONFIG_FTRACE
+/* mcount is defined in assembly */
+EXPORT_SYMBOL(mcount);
+#endif
 
 /* Networking helper routines. */
 EXPORT_SYMBOL(csum_partial_copy_generic);
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index d0b234c9fc31..88923fd7a6fc 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -11,6 +11,8 @@
 #include <linux/delay.h>
 #include <linux/init.h>
 #include <linux/numa.h>
+#include <linux/ftrace.h>
+
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
@@ -107,6 +109,8 @@ NORET_TYPE void machine_kexec(struct kimage *image)
         unsigned long page_list[PAGES_NR];
         void *control_page;
 
+        tracer_disable();
+
         /* Interrupts aren't acceptable while we reboot */
         local_irq_disable();
 
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 576a03db4511..1558fdc174f9 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -11,6 +11,8 @@
 #include <linux/string.h>
 #include <linux/reboot.h>
 #include <linux/numa.h>
+#include <linux/ftrace.h>
+
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 #include <asm/mmu_context.h>
@@ -184,6 +186,8 @@ NORET_TYPE void machine_kexec(struct kimage *image)
         unsigned long page_list[PAGES_NR];
         void *control_page;
 
+        tracer_disable();
+
         /* Interrupts aren't acceptable while we reboot */
         local_irq_disable();
 
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index e2db9ac5c61c..347a7aba8b16 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -185,7 +185,10 @@ void cpu_idle(void)
 
                         local_irq_disable();
                         __get_cpu_var(irq_stat).idle_timestamp = jiffies;
+                        /* Don't trace irqs off for idle */
+                        stop_critical_timings();
                         idle();
+                        start_critical_timings();
                 }
                 tick_nohz_restart_sched_tick();
                 preempt_enable_no_resched();
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index c6eb5c91e5f6..ea090e6cfe39 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -165,7 +165,10 @@ void cpu_idle(void)
                          */
                         local_irq_disable();
                         enter_idle();
+                        /* Don't trace irqs off for idle */
+                        stop_critical_timings();
                         idle();
+                        start_critical_timings();
                         /* In many cases the interrupt that ended idle
                            has already called exit_idle. But some idle
                            loops can be woken up without interrupt. */
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index 61efa2f7d564..4063dfa2a02d 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -42,7 +42,8 @@
 #include <asm/topology.h>
 #include <asm/vgtod.h>
 
-#define __vsyscall(nr) __attribute__ ((unused,__section__(".vsyscall_" #nr)))
+#define __vsyscall(nr) \
+                __attribute__ ((unused, __section__(".vsyscall_" #nr))) notrace
 #define __syscall_clobber "r11","cx","memory"
 
 /*
diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c
index f6c05d0410fb..16ff4bf418d9 100644
--- a/arch/x86/kernel/x8664_ksyms_64.c
+++ b/arch/x86/kernel/x8664_ksyms_64.c
@@ -2,13 +2,20 @@
    All C exports should go in the respective C files. */
 
 #include <linux/module.h>
-#include <net/checksum.h>
 #include <linux/smp.h>
 
+#include <net/checksum.h>
+
 #include <asm/processor.h>
-#include <asm/uaccess.h>
 #include <asm/pgtable.h>
+#include <asm/uaccess.h>
 #include <asm/desc.h>
+#include <asm/ftrace.h>
+
+#ifdef CONFIG_FTRACE
+/* mcount is defined in assembly */
+EXPORT_SYMBOL(mcount);
+#endif
 
 EXPORT_SYMBOL(kernel_thread);
 
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 76f60f52a885..84aa2883fe15 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -5,6 +5,7 @@
 obj-$(CONFIG_SMP) := msr-on-cpu.o
 
 lib-y := delay_$(BITS).o
+lib-y += thunk_$(BITS).o
 lib-y += usercopy_$(BITS).o getuser_$(BITS).o putuser_$(BITS).o
 lib-y += memcpy_$(BITS).o
 
diff --git a/arch/x86/lib/thunk_32.S b/arch/x86/lib/thunk_32.S
new file mode 100644
index 000000000000..650b11e00ecc
--- /dev/null
+++ b/arch/x86/lib/thunk_32.S
@@ -0,0 +1,47 @@
+/*
+ * Trampoline to trace irqs off. (otherwise CALLER_ADDR1 might crash)
+ * Copyright 2008 by Steven Rostedt, Red Hat, Inc
+ *  (inspired by Andi Kleen's thunk_64.S)
+ * Subject to the GNU public license, v.2. No warranty of any kind.
+ */
+
+        #include <linux/linkage.h>
+
+#define ARCH_TRACE_IRQS_ON                      \
+        pushl %eax;                             \
+        pushl %ecx;                             \
+        pushl %edx;                             \
+        call trace_hardirqs_on;                 \
+        popl %edx;                              \
+        popl %ecx;                              \
+        popl %eax;
+
+#define ARCH_TRACE_IRQS_OFF                     \
+        pushl %eax;                             \
+        pushl %ecx;                             \
+        pushl %edx;                             \
+        call trace_hardirqs_off;                \
+        popl %edx;                              \
+        popl %ecx;                              \
+        popl %eax;
+
+#ifdef CONFIG_TRACE_IRQFLAGS
+        /* put return address in eax (arg1) */
+        .macro thunk_ra name,func
+        .globl \name
+\name:
+        pushl %eax
+        pushl %ecx
+        pushl %edx
+        /* Place EIP in the arg1 */
+        movl 3*4(%esp), %eax
+        call \func
+        popl %edx
+        popl %ecx
+        popl %eax
+        ret
+        .endm
+
+        thunk_ra trace_hardirqs_on_thunk,trace_hardirqs_on_caller
+        thunk_ra trace_hardirqs_off_thunk,trace_hardirqs_off_caller
+#endif
diff --git a/arch/x86/lib/thunk_64.S b/arch/x86/lib/thunk_64.S
index e009251d4e9f..bf9a7d5a5428 100644
--- a/arch/x86/lib/thunk_64.S
+++ b/arch/x86/lib/thunk_64.S
@@ -2,6 +2,7 @@
  * Save registers before calling assembly functions. This avoids
  * disturbance of register allocation in some inline assembly constructs.
  * Copyright 2001,2002 by Andi Kleen, SuSE Labs.
+ * Added trace_hardirqs callers - Copyright 2007 Steven Rostedt, Red Hat, Inc.
  * Subject to the GNU public license, v.2. No warranty of any kind.
  */
 
@@ -42,8 +43,22 @@
 #endif  
         
 #ifdef CONFIG_TRACE_IRQFLAGS
-        thunk trace_hardirqs_on_thunk,trace_hardirqs_on
-        thunk trace_hardirqs_off_thunk,trace_hardirqs_off
+        /* put return address in rdi (arg1) */
+        .macro thunk_ra name,func
+        .globl \name
+\name:
+        CFI_STARTPROC
+        SAVE_ARGS
+        /* SAVE_ARGS pushs 9 elements */
+        /* the next element would be the rip */
+        movq 9*8(%rsp), %rdi
+        call \func
+        jmp  restore
+        CFI_ENDPROC
+        .endm
+
+        thunk_ra trace_hardirqs_on_thunk,trace_hardirqs_on_caller
+        thunk_ra trace_hardirqs_off_thunk,trace_hardirqs_off_caller
 #endif
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 8bcb6f40ccb6..42394b353c6a 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -49,6 +49,60 @@
 #define PF_RSVD         (1<<3)
 #define PF_INSTR        (1<<4)
 
+#ifdef CONFIG_PAGE_FAULT_HANDLERS
+static HLIST_HEAD(pf_handlers); /* protected by RCU */
+static DEFINE_SPINLOCK(pf_handlers_writer);
+
+void register_page_fault_handler(struct pf_handler *new_pfh)
+{
+        unsigned long flags;
+        spin_lock_irqsave(&pf_handlers_writer, flags);
+        hlist_add_head_rcu(&new_pfh->hlist, &pf_handlers);
+        spin_unlock_irqrestore(&pf_handlers_writer, flags);
+}
+EXPORT_SYMBOL_GPL(register_page_fault_handler);
+
+/**
+ * unregister_page_fault_handler:
+ * The caller must ensure @old_pfh is not in use anymore before freeing it.
+ * This function does not guarantee it. The list of handlers is protected by
+ * RCU, so you can do this by e.g. calling synchronize_rcu().
+ */
+void unregister_page_fault_handler(struct pf_handler *old_pfh)
+{
+        unsigned long flags;
+        spin_lock_irqsave(&pf_handlers_writer, flags);
+        hlist_del_rcu(&old_pfh->hlist);
+        spin_unlock_irqrestore(&pf_handlers_writer, flags);
+}
+EXPORT_SYMBOL_GPL(unregister_page_fault_handler);
+#endif
+
+/* returns non-zero if do_page_fault() should return */
+static int handle_custom_pf(struct pt_regs *regs, unsigned long error_code,
+                                                        unsigned long address)
+{
+#ifdef CONFIG_PAGE_FAULT_HANDLERS
+        int ret = 0;
+        struct pf_handler *cur;
+        struct hlist_node *ncur;
+
+        if (hlist_empty(&pf_handlers))
+                return 0;
+
+        rcu_read_lock();
+        hlist_for_each_entry_rcu(cur, ncur, &pf_handlers, hlist) {
+                ret = cur->handler(regs, error_code, address);
+                if (ret)
+                        break;
+        }
+        rcu_read_unlock();
+        return ret;
+#else
+        return 0;
+#endif
+}
+
 static inline int notify_page_fault(struct pt_regs *regs)
 {
 #ifdef CONFIG_KPROBES
@@ -606,6 +660,8 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code)
 
         if (notify_page_fault(regs))
                 return;
+        if (handle_custom_pf(regs, error_code, address))
+                return;
 
         /*
          * We fault-in kernel-space virtual memory on-demand. The
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index ec30d10154b6..f96eca21ad8f 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -710,6 +710,8 @@ void mark_rodata_ro(void)
         unsigned long start = PFN_ALIGN(_text);
         unsigned long size = PFN_ALIGN(_etext) - start;
 
+#ifndef CONFIG_DYNAMIC_FTRACE
+        /* Dynamic tracing modifies the kernel text section */
         set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT);
         printk(KERN_INFO "Write protecting the kernel text: %luk\n",
                 size >> 10);
@@ -722,6 +724,8 @@ void mark_rodata_ro(void)
         printk(KERN_INFO "Testing CPA: write protecting again\n");
         set_pages_ro(virt_to_page(start), size>>PAGE_SHIFT);
 #endif
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
         start += size;
         size = (unsigned long)__end_rodata - start;
         set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT);
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 819dad973b13..17c0a6138a53 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -767,6 +767,13 @@ EXPORT_SYMBOL_GPL(rodata_test_data);
 void mark_rodata_ro(void)
 {
         unsigned long start = PFN_ALIGN(_stext), end = PFN_ALIGN(__end_rodata);
+        unsigned long rodata_start =
+                ((unsigned long)__start_rodata + PAGE_SIZE - 1) & PAGE_MASK;
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+        /* Dynamic tracing modifies the kernel text section */
+        start = rodata_start;
+#endif
 
         printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n",
                (end - start) >> 10);
@@ -776,8 +783,7 @@ void mark_rodata_ro(void)
          * The rodata section (but not the kernel text!) should also be
          * not-executable.
          */
-        start = ((unsigned long)__start_rodata + PAGE_SIZE - 1) & PAGE_MASK;
-        set_memory_nx(start, (end - start) >> PAGE_SHIFT);
+        set_memory_nx(rodata_start, (end - rodata_start) >> PAGE_SHIFT);
 
         rodata_test();
 
diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c
index efa2ba7c6005..1ef0f90813d6 100644
--- a/arch/x86/vdso/vclock_gettime.c
+++ b/arch/x86/vdso/vclock_gettime.c
@@ -23,7 +23,7 @@
 
 #define gtod vdso_vsyscall_gtod_data
 
-static long vdso_fallback_gettime(long clock, struct timespec *ts)
+notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
 {
         long ret;
         asm("syscall" : "=a" (ret) :
@@ -31,7 +31,7 @@ static long vdso_fallback_gettime(long clock, struct timespec *ts)
         return ret;
 }
 
-static inline long vgetns(void)
+notrace static inline long vgetns(void)
 {
         long v;
         cycles_t (*vread)(void);
@@ -40,7 +40,7 @@ static inline long vgetns(void)
         return (v * gtod->clock.mult) >> gtod->clock.shift;
 }
 
-static noinline int do_realtime(struct timespec *ts)
+notrace static noinline int do_realtime(struct timespec *ts)
 {
         unsigned long seq, ns;
         do {
@@ -54,7 +54,8 @@ static noinline int do_realtime(struct timespec *ts)
 }
 
 /* Copy of the version in kernel/time.c which we cannot directly access */
-static void vset_normalized_timespec(struct timespec *ts, long sec, long nsec)
+notrace static void
+vset_normalized_timespec(struct timespec *ts, long sec, long nsec)
 {
         while (nsec >= NSEC_PER_SEC) {
                 nsec -= NSEC_PER_SEC;
@@ -68,7 +69,7 @@ static void vset_normalized_timespec(struct timespec *ts, long sec, long nsec)
         ts->tv_nsec = nsec;
 }
 
-static noinline int do_monotonic(struct timespec *ts)
+notrace static noinline int do_monotonic(struct timespec *ts)
 {
         unsigned long seq, ns, secs;
         do {
@@ -82,7 +83,7 @@ static noinline int do_monotonic(struct timespec *ts)
         return 0;
 }
 
-int __vdso_clock_gettime(clockid_t clock, struct timespec *ts)
+notrace int __vdso_clock_gettime(clockid_t clock, struct timespec *ts)
 {
         if (likely(gtod->sysctl_enabled && gtod->clock.vread))
                 switch (clock) {
@@ -96,7 +97,7 @@ int __vdso_clock_gettime(clockid_t clock, struct timespec *ts)
 int clock_gettime(clockid_t, struct timespec *)
         __attribute__((weak, alias("__vdso_clock_gettime")));
 
-int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz)
+notrace int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz)
 {
         long ret;
         if (likely(gtod->sysctl_enabled && gtod->clock.vread)) {
diff --git a/arch/x86/vdso/vgetcpu.c b/arch/x86/vdso/vgetcpu.c
index c8097f17f8a9..9fbc6b20026b 100644
--- a/arch/x86/vdso/vgetcpu.c
+++ b/arch/x86/vdso/vgetcpu.c
@@ -13,7 +13,8 @@
 #include <asm/vgtod.h>
 #include "vextern.h"
 
-long __vdso_getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *unused)
+notrace long
+__vdso_getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *unused)
 {
         unsigned int p;