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

Conflicts:

	arch/x86/kernel/entry_32.S
	arch/x86/kernel/process_32.c
	arch/x86/kernel/process_64.c
	arch/x86/lib/Makefile
	include/asm-x86/irqflags.h
	kernel/Makefile
	kernel/sched.c

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

12 files changed, 371 insertions, 15 deletions

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 55ff016e9f69..5112c84f5421 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -6,6 +6,13 @@ extra-y                := head_$(BITS).o head$(BITS).o head.o init_task.o vmlinu
 
 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:
@@ -57,6 +64,7 @@ obj-$(CONFIG_X86_MPPARSE)	+= mpparse.o
 obj-$(CONFIG_X86_LOCAL_APIC)    += apic_$(BITS).o nmi.o
 obj-$(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 cfe28a715434..6bc07f0f1202 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 <asm/irq_vectors.h>
 
 /*
@@ -1111,6 +1112,77 @@ 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 bb4e22f4892f..ba41bf42748d 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 f4960171bc66..8864230d55af 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 7830dc4a8380..9dd9262693a3 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 9a139f6c9df3..0c3927accb00 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -142,7 +142,10 @@ 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();
                         pm_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 db5eb963e4df..a8e53626ac9a 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -134,7 +134,10 @@ void cpu_idle(void)
                          */
                         local_irq_disable();
                         enter_idle();
+                        /* Don't trace irqs off for idle */
+                        stop_critical_timings();
                         pm_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 c87cbd84c3e5..e50740d32314 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 2f306a826897..b545f371b5f5 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);