11 files changed, 115 insertions, 151 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 9c39095b33fc..8fc9a847cf48 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -34,6 +34,7 @@ config X86
         select HAVE_FUNCTION_TRACER
         select HAVE_FUNCTION_GRAPH_TRACER
         select HAVE_FUNCTION_TRACE_MCOUNT_TEST
+        select HAVE_FTRACE_NMI_ENTER if DYNAMIC_FTRACE
         select HAVE_KVM if ((X86_32 && !X86_VOYAGER && !X86_VISWS && !X86_NUMAQ) || X86_64)
         select HAVE_ARCH_KGDB if !X86_VOYAGER
         select HAVE_ARCH_TRACEHOOK
diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h
index 2f8466540fb5..6145063cfe0e 100644
--- a/arch/x86/include/asm/cacheflush.h
+++ b/arch/x86/include/asm/cacheflush.h
@@ -104,6 +104,11 @@ void clflush_cache_range(void *addr, unsigned int size);
 #ifdef CONFIG_DEBUG_RODATA
 void mark_rodata_ro(void);
 extern const int rodata_test_data;
+void set_kernel_text_rw(void);
+void set_kernel_text_ro(void);
+#else
+static inline void set_kernel_text_rw(void) { }
+static inline void set_kernel_text_ro(void) { }
 #endif
 
 #ifdef CONFIG_DEBUG_RODATA_TEST
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index b55b4a7fbefd..db24c2278be0 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -55,29 +55,4 @@ struct dyn_arch_ftrace {
 #endif /* __ASSEMBLY__ */
 #endif /* CONFIG_FUNCTION_TRACER */
 
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-
-#ifndef __ASSEMBLY__
-
-/*
- * Stack of return addresses for functions
- * of a thread.
- * Used in struct thread_info
- */
-struct ftrace_ret_stack {
-        unsigned long ret;
-        unsigned long func;
-        unsigned long long calltime;
-};
-
-/*
- * Primary handler of a function return.
- * It relays on ftrace_return_to_handler.
- * Defined in entry_32/64.S
- */
-extern void return_to_handler(void);
-
-#endif /* __ASSEMBLY__ */
-#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
-
 #endif /* _ASM_X86_FTRACE_H */
diff --git a/arch/x86/include/asm/ptrace-abi.h b/arch/x86/include/asm/ptrace-abi.h
index 8e0f8d199e05..86723035a515 100644
--- a/arch/x86/include/asm/ptrace-abi.h
+++ b/arch/x86/include/asm/ptrace-abi.h
@@ -80,8 +80,6 @@
 
 #define PTRACE_SINGLEBLOCK      33      /* resume execution until next branch */
 
-#ifdef CONFIG_X86_PTRACE_BTS
-
 #ifndef __ASSEMBLY__
 #include <linux/types.h>
 
@@ -140,6 +138,5 @@ struct ptrace_bts_config {
    BTS records are read from oldest to newest.
    Returns number of BTS records drained.
 */
-#endif /* CONFIG_X86_PTRACE_BTS */
 
 #endif /* _ASM_X86_PTRACE_ABI_H */
diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
index 4b1c319d30c3..c5d737cdb365 100644
--- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -33,7 +33,7 @@
 #include <linux/cpufreq.h>
 #include <linux/compiler.h>
 #include <linux/dmi.h>
-#include <linux/ftrace.h>
+#include <trace/power.h>
 
 #include <linux/acpi.h>
 #include <acpi/processor.h>
@@ -70,6 +70,8 @@ struct acpi_cpufreq_data {
 
 static DEFINE_PER_CPU(struct acpi_cpufreq_data *, drv_data);
 
+DEFINE_TRACE(power_mark);
+
 /* acpi_perf_data is a pointer to percpu data. */
 static struct acpi_processor_performance *acpi_perf_data;
 
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 6b1f6f6f8661..4325165753d8 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -10,10 +10,12 @@
 #include <linux/kdebug.h>
 #include <linux/module.h>
 #include <linux/ptrace.h>
+#include <linux/ftrace.h>
 #include <linux/kexec.h>
 #include <linux/bug.h>
 #include <linux/nmi.h>
 #include <linux/sysfs.h>
+#include <linux/ftrace.h>
 
 #include <asm/stacktrace.h>
 
@@ -195,6 +197,11 @@ unsigned __kprobes long oops_begin(void)
         int cpu;
         unsigned long flags;
 
+        /* notify the hw-branch tracer so it may disable tracing and
+           add the last trace to the trace buffer -
+           the earlier this happens, the more useful the trace. */
+        trace_hw_branch_oops();
+
         oops_enter();
 
         /* racy, but better than risking deadlock. */
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 231bdd3c5b1c..3925ec0184b1 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -18,6 +18,7 @@
 #include <linux/init.h>
 #include <linux/list.h>
 
+#include <asm/cacheflush.h>
 #include <asm/ftrace.h>
 #include <linux/ftrace.h>
 #include <asm/nops.h>
@@ -26,6 +27,18 @@
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 
+int ftrace_arch_code_modify_prepare(void)
+{
+        set_kernel_text_rw();
+        return 0;
+}
+
+int ftrace_arch_code_modify_post_process(void)
+{
+        set_kernel_text_ro();
+        return 0;
+}
+
 union ftrace_code_union {
         char code[MCOUNT_INSN_SIZE];
         struct {
@@ -82,7 +95,7 @@ static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
  * are the same as what exists.
  */
 
-static atomic_t in_nmi = ATOMIC_INIT(0);
+static atomic_t nmi_running = ATOMIC_INIT(0);
 static int mod_code_status;             /* holds return value of text write */
 static int mod_code_write;              /* set when NMI should do the write */
 static void *mod_code_ip;               /* holds the IP to write to */
@@ -111,12 +124,16 @@ static void ftrace_mod_code(void)
          */
         mod_code_status = probe_kernel_write(mod_code_ip, mod_code_newcode,
                                              MCOUNT_INSN_SIZE);
+
+        /* if we fail, then kill any new writers */
+        if (mod_code_status)
+                mod_code_write = 0;
 }
 
 void ftrace_nmi_enter(void)
 {
-        atomic_inc(&in_nmi);
-        /* Must have in_nmi seen before reading write flag */
+        atomic_inc(&nmi_running);
+        /* Must have nmi_running seen before reading write flag */
         smp_mb();
         if (mod_code_write) {
                 ftrace_mod_code();
@@ -126,22 +143,21 @@ void ftrace_nmi_enter(void)
 
 void ftrace_nmi_exit(void)
 {
-        /* Finish all executions before clearing in_nmi */
+        /* Finish all executions before clearing nmi_running */
         smp_wmb();
-        atomic_dec(&in_nmi);
+        atomic_dec(&nmi_running);
 }
 
 static void wait_for_nmi(void)
 {
-        int waited = 0;
+        if (!atomic_read(&nmi_running))
+                return;
 
-        while (atomic_read(&in_nmi)) {
-                waited = 1;
+        do {
                 cpu_relax();
-        }
+        } while (atomic_read(&nmi_running));
 
-        if (waited)
-                nmi_wait_count++;
+        nmi_wait_count++;
 }
 
 static int
@@ -368,100 +384,8 @@ int ftrace_disable_ftrace_graph_caller(void)
         return ftrace_mod_jmp(ip, old_offset, new_offset);
 }
 
-#else /* CONFIG_DYNAMIC_FTRACE */
-
-/*
- * These functions are picked from those used on
- * this page for dynamic ftrace. They have been
- * simplified to ignore all traces in NMI context.
- */
-static atomic_t in_nmi;
-
-void ftrace_nmi_enter(void)
-{
-        atomic_inc(&in_nmi);
-}
-
-void ftrace_nmi_exit(void)
-{
-        atomic_dec(&in_nmi);
-}
-
 #endif /* !CONFIG_DYNAMIC_FTRACE */
 
-/* Add a function return address to the trace stack on thread info.*/
-static int push_return_trace(unsigned long ret, unsigned long long time,
-                                unsigned long func, int *depth)
-{
-        int index;
-
-        if (!current->ret_stack)
-                return -EBUSY;
-
-        /* The return trace stack is full */
-        if (current->curr_ret_stack == FTRACE_RETFUNC_DEPTH - 1) {
-                atomic_inc(&current->trace_overrun);
-                return -EBUSY;
-        }
-
-        index = ++current->curr_ret_stack;
-        barrier();
-        current->ret_stack[index].ret = ret;
-        current->ret_stack[index].func = func;
-        current->ret_stack[index].calltime = time;
-        *depth = index;
-
-        return 0;
-}
-
-/* Retrieve a function return address to the trace stack on thread info.*/
-static void pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret)
-{
-        int index;
-
-        index = current->curr_ret_stack;
-
-        if (unlikely(index < 0)) {
-                ftrace_graph_stop();
-                WARN_ON(1);
-                /* Might as well panic, otherwise we have no where to go */
-                *ret = (unsigned long)panic;
-                return;
-        }
-
-        *ret = current->ret_stack[index].ret;
-        trace->func = current->ret_stack[index].func;
-        trace->calltime = current->ret_stack[index].calltime;
-        trace->overrun = atomic_read(&current->trace_overrun);
-        trace->depth = index;
-        barrier();
-        current->curr_ret_stack--;
-
-}
-
-/*
- * Send the trace to the ring-buffer.
- * @return the original return address.
- */
-unsigned long ftrace_return_to_handler(void)
-{
-        struct ftrace_graph_ret trace;
-        unsigned long ret;
-
-        pop_return_trace(&trace, &ret);
-        trace.rettime = cpu_clock(raw_smp_processor_id());
-        ftrace_graph_return(&trace);
-
-        if (unlikely(!ret)) {
-                ftrace_graph_stop();
-                WARN_ON(1);
-                /* Might as well panic. What else to do? */
-                ret = (unsigned long)panic;
-        }
-
-        return ret;
-}
-
 /*
  * Hook the return address and push it in the stack of return addrs
  * in current thread info.
@@ -476,7 +400,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
                                 &return_to_handler;
 
         /* Nmi's are currently unsupported */
-        if (unlikely(atomic_read(&in_nmi)))
+        if (unlikely(in_nmi()))
                 return;
 
         if (unlikely(atomic_read(&current->tracing_graph_pause)))
@@ -512,16 +436,9 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
                 return;
         }
 
-        if (unlikely(!__kernel_text_address(old))) {
-                ftrace_graph_stop();
-                *parent = old;
-                WARN_ON(1);
-                return;
-        }
-
         calltime = cpu_clock(raw_smp_processor_id());
 
-        if (push_return_trace(old, calltime,
+        if (ftrace_push_return_trace(old, calltime,
                                 self_addr, &trace.depth) == -EBUSY) {
                 *parent = old;
                 return;
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 6d12f7e37f8c..23b328edc2b3 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -8,7 +8,7 @@
 #include <linux/module.h>
 #include <linux/pm.h>
 #include <linux/clockchips.h>
-#include <linux/ftrace.h>
+#include <trace/power.h>
 #include <asm/system.h>
 #include <asm/apic.h>
 
@@ -19,6 +19,9 @@ EXPORT_SYMBOL(idle_nomwait);
 
 struct kmem_cache *task_xstate_cachep;
 
+DEFINE_TRACE(power_start);
+DEFINE_TRACE(power_end);
+
 int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 {
         *dst = *src;
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index b81125f0bdee..c7da3683f4c5 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -55,7 +55,8 @@ config KVM_AMD
 
 config KVM_TRACE
         bool "KVM trace support"
-        depends on KVM && MARKERS && SYSFS
+        depends on KVM && SYSFS
+        select MARKERS
         select RELAY
         select DEBUG_FS
         default n
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 2cef05074413..3eb2ed188a4c 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -1155,17 +1155,47 @@ static noinline int do_test_wp_bit(void)
 const int rodata_test_data = 0xC3;
 EXPORT_SYMBOL_GPL(rodata_test_data);
 
+static int kernel_set_to_readonly;
+
+void set_kernel_text_rw(void)
+{
+        unsigned long start = PFN_ALIGN(_text);
+        unsigned long size = PFN_ALIGN(_etext) - start;
+
+        if (!kernel_set_to_readonly)
+                return;
+
+        pr_debug("Set kernel text: %lx - %lx for read write\n",
+                 start, start+size);
+
+        set_pages_rw(virt_to_page(start), size >> PAGE_SHIFT);
+}
+
+void set_kernel_text_ro(void)
+{
+        unsigned long start = PFN_ALIGN(_text);
+        unsigned long size = PFN_ALIGN(_etext) - start;
+
+        if (!kernel_set_to_readonly)
+                return;
+
+        pr_debug("Set kernel text: %lx - %lx for read only\n",
+                 start, start+size);
+
+        set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT);
+}
+
 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);
 
+        kernel_set_to_readonly = 1;
+
 #ifdef CONFIG_CPA_DEBUG
         printk(KERN_INFO "Testing CPA: Reverting %lx-%lx\n",
                 start, start+size);
@@ -1174,7 +1204,6 @@ 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;
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index e6d36b490250..63fdc531601d 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -986,21 +986,48 @@ void free_initmem(void)
 const int rodata_test_data = 0xC3;
 EXPORT_SYMBOL_GPL(rodata_test_data);
 
+static int kernel_set_to_readonly;
+
+void set_kernel_text_rw(void)
+{
+        unsigned long start = PFN_ALIGN(_stext);
+        unsigned long end = PFN_ALIGN(__start_rodata);
+
+        if (!kernel_set_to_readonly)
+                return;
+
+        pr_debug("Set kernel text: %lx - %lx for read write\n",
+                 start, end);
+
+        set_memory_rw(start, (end - start) >> PAGE_SHIFT);
+}
+
+void set_kernel_text_ro(void)
+{
+        unsigned long start = PFN_ALIGN(_stext);
+        unsigned long end = PFN_ALIGN(__start_rodata);
+
+        if (!kernel_set_to_readonly)
+                return;
+
+        pr_debug("Set kernel text: %lx - %lx for read only\n",
+                 start, end);
+
+        set_memory_ro(start, (end - start) >> PAGE_SHIFT);
+}
+
 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);
         set_memory_ro(start, (end - start) >> PAGE_SHIFT);
 
+        kernel_set_to_readonly = 1;
+
         /*
          * The rodata section (but not the kernel text!) should also be
          * not-executable.