8 files changed, 180 insertions, 83 deletions

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index c611ad64137f..145cce75cda7 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -66,7 +66,8 @@ obj-$(CONFIG_X86_MPPARSE)	+= mpparse.o
 obj-y				+= apic/
 obj-$(CONFIG_X86_REBOOTFIXUPS)	+= reboot_fixups_32.o
 obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
-obj-$(CONFIG_FUNCTION_GRAPH_TRACER)	+= ftrace.o
+obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o
+obj-$(CONFIG_FTRACE_SYSCALLS)	+= 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 4c80f1557433..f57658702571 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -5,6 +5,7 @@
 #include <linux/kprobes.h>
 #include <linux/mm.h>
 #include <linux/vmalloc.h>
+#include <linux/memory.h>
 #include <asm/alternative.h>
 #include <asm/sections.h>
 #include <asm/pgtable.h>
@@ -12,7 +13,9 @@
 #include <asm/nmi.h>
 #include <asm/vsyscall.h>
 #include <asm/cacheflush.h>
+#include <asm/tlbflush.h>
 #include <asm/io.h>
+#include <asm/fixmap.h>
 
 #define MAX_PATCH_LEN (255-1)
 
@@ -226,6 +229,7 @@ static void alternatives_smp_lock(u8 **start, u8 **end, u8 *text, u8 *text_end)
 {
 	u8 **ptr;
 
+	mutex_lock(&text_mutex);
 	for (ptr = start; ptr < end; ptr++) {
 		if (*ptr < text)
 			continue;
@@ -234,6 +238,7 @@ static void alternatives_smp_lock(u8 **start, u8 **end, u8 *text, u8 *text_end)
 		/* turn DS segment override prefix into lock prefix */
 		text_poke(*ptr, ((unsigned char []){0xf0}), 1);
 	};
+	mutex_unlock(&text_mutex);
 }
 
 static void alternatives_smp_unlock(u8 **start, u8 **end, u8 *text, u8 *text_end)
@@ -243,6 +248,7 @@ static void alternatives_smp_unlock(u8 **start, u8 **end, u8 *text, u8 *text_end
 	if (noreplace_smp)
 		return;
 
+	mutex_lock(&text_mutex);
 	for (ptr = start; ptr < end; ptr++) {
 		if (*ptr < text)
 			continue;
@@ -251,6 +257,7 @@ static void alternatives_smp_unlock(u8 **start, u8 **end, u8 *text, u8 *text_end
 		/* turn lock prefix into DS segment override prefix */
 		text_poke(*ptr, ((unsigned char []){0x3E}), 1);
 	};
+	mutex_unlock(&text_mutex);
 }
 
 struct smp_alt_module {
@@ -500,15 +507,16 @@ void *text_poke_early(void *addr, const void *opcode, size_t len)
  * It means the size must be writable atomically and the address must be aligned
  * in a way that permits an atomic write. It also makes sure we fit on a single
  * page.
+ *
+ * Note: Must be called under text_mutex.
  */
 void *__kprobes text_poke(void *addr, const void *opcode, size_t len)
 {
+	unsigned long flags;
 	char *vaddr;
-	int nr_pages = 2;
 	struct page *pages[2];
 	int i;
 
-	might_sleep();
 	if (!core_kernel_text((unsigned long)addr)) {
 		pages[0] = vmalloc_to_page(addr);
 		pages[1] = vmalloc_to_page(addr + PAGE_SIZE);
@@ -518,18 +526,21 @@ void *__kprobes text_poke(void *addr, const void *opcode, size_t len)
 		pages[1] = virt_to_page(addr + PAGE_SIZE);
 	}
 	BUG_ON(!pages[0]);
-	if (!pages[1])
-		nr_pages = 1;
-	vaddr = vmap(pages, nr_pages, VM_MAP, PAGE_KERNEL);
-	BUG_ON(!vaddr);
-	local_irq_disable();
+	local_irq_save(flags);
+	set_fixmap(FIX_TEXT_POKE0, page_to_phys(pages[0]));
+	if (pages[1])
+		set_fixmap(FIX_TEXT_POKE1, page_to_phys(pages[1]));
+	vaddr = (char *)fix_to_virt(FIX_TEXT_POKE0);
 	memcpy(&vaddr[(unsigned long)addr & ~PAGE_MASK], opcode, len);
-	local_irq_enable();
-	vunmap(vaddr);
+	clear_fixmap(FIX_TEXT_POKE0);
+	if (pages[1])
+		clear_fixmap(FIX_TEXT_POKE1);
+	local_flush_tlb();
 	sync_core();
 	/* Could also do a CLFLUSH here to speed up CPU recovery; but
 	   that causes hangs on some VIA CPUs. */
 	for (i = 0; i < len; i++)
 		BUG_ON(((char *)addr)[i] != ((char *)opcode)[i]);
+	local_irq_restore(flags);
 	return addr;
 }
diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
index 23da96e57b17..05209b5cc6ca 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 <linux/io.h>
@@ -72,6 +72,8 @@ 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 dd2130b0fb3e..95ea5fa7d444 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -15,6 +15,7 @@
 #include <linux/bug.h>
 #include <linux/nmi.h>
 #include <linux/sysfs.h>
+#include <linux/ftrace.h>
 
 #include <asm/stacktrace.h>
 
@@ -196,6 +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 76f7141e0f91..61df77532120 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 {
@@ -66,11 +79,11 @@ static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
  *
  * 1) Put the instruction pointer into the IP buffer
  *    and the new code into the "code" buffer.
- * 2) Set a flag that says we are modifying code
- * 3) Wait for any running NMIs to finish.
- * 4) Write the code
- * 5) clear the flag.
- * 6) Wait for any running NMIs to finish.
+ * 2) Wait for any running NMIs to finish and set a flag that says
+ *    we are modifying code, it is done in an atomic operation.
+ * 3) Write the code
+ * 4) clear the flag.
+ * 5) Wait for any running NMIs to finish.
  *
  * If an NMI is executed, the first thing it does is to call
  * "ftrace_nmi_enter". This will check if the flag is set to write
@@ -82,9 +95,9 @@ 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);
+#define MOD_CODE_WRITE_FLAG (1 << 31)	/* set when NMI should do the write */
+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 */
 static void *mod_code_newcode;		/* holds the text to write to the IP */
 
@@ -101,6 +114,20 @@ int ftrace_arch_read_dyn_info(char *buf, int size)
 	return r;
 }
 
+static void clear_mod_flag(void)
+{
+	int old = atomic_read(&nmi_running);
+
+	for (;;) {
+		int new = old & ~MOD_CODE_WRITE_FLAG;
+
+		if (old == new)
+			break;
+
+		old = atomic_cmpxchg(&nmi_running, old, new);
+	}
+}
+
 static void ftrace_mod_code(void)
 {
 	/*
@@ -111,37 +138,52 @@ 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)
+		clear_mod_flag();
 }
 
 void ftrace_nmi_enter(void)
 {
-	atomic_inc(&in_nmi);
-	/* Must have in_nmi seen before reading write flag */
-	smp_mb();
-	if (mod_code_write) {
+	if (atomic_inc_return(&nmi_running) & MOD_CODE_WRITE_FLAG) {
+		smp_rmb();
 		ftrace_mod_code();
 		atomic_inc(&nmi_update_count);
 	}
+	/* Must have previous changes seen before executions */
+	smp_mb();
 }
 
 void ftrace_nmi_exit(void)
 {
-	/* Finish all executions before clearing in_nmi */
-	smp_wmb();
-	atomic_dec(&in_nmi);
+	/* Finish all executions before clearing nmi_running */
+	smp_mb();
+	atomic_dec(&nmi_running);
+}
+
+static void wait_for_nmi_and_set_mod_flag(void)
+{
+	if (!atomic_cmpxchg(&nmi_running, 0, MOD_CODE_WRITE_FLAG))
+		return;
+
+	do {
+		cpu_relax();
+	} while (atomic_cmpxchg(&nmi_running, 0, MOD_CODE_WRITE_FLAG));
+
+	nmi_wait_count++;
 }
 
 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
@@ -151,14 +193,9 @@ do_ftrace_mod_code(unsigned long ip, void *new_code)
 	mod_code_newcode = new_code;
 
 	/* The buffers need to be visible before we let NMIs write them */
-	smp_wmb();
-
-	mod_code_write = 1;
-
-	/* Make sure write bit is visible before we wait on NMIs */
 	smp_mb();
 
-	wait_for_nmi();
+	wait_for_nmi_and_set_mod_flag();
 
 	/* Make sure all running NMIs have finished before we write the code */
 	smp_mb();
@@ -166,13 +203,9 @@ do_ftrace_mod_code(unsigned long ip, void *new_code)
 	ftrace_mod_code();
 
 	/* Make sure the write happens before clearing the bit */
-	smp_wmb();
-
-	mod_code_write = 0;
-
-	/* make sure NMIs see the cleared bit */
 	smp_mb();
 
+	clear_mod_flag();
 	wait_for_nmi();
 
 	return mod_code_status;
@@ -368,25 +401,6 @@ 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 */
 
 /*
@@ -396,14 +410,13 @@ void ftrace_nmi_exit(void)
 void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
 {
 	unsigned long old;
-	unsigned long long calltime;
 	int faulted;
 	struct ftrace_graph_ent trace;
 	unsigned long return_hooker = (unsigned long)
 				&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)))
@@ -439,17 +452,7 @@ 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 (ftrace_push_return_trace(old, calltime,
-				self_addr, &trace.depth) == -EBUSY) {
+	if (ftrace_push_return_trace(old, self_addr, &trace.depth) == -EBUSY) {
 		*parent = old;
 		return;
 	}
@@ -463,3 +466,66 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
 	}
 }
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
+#ifdef CONFIG_FTRACE_SYSCALLS
+
+extern unsigned long __start_syscalls_metadata[];
+extern unsigned long __stop_syscalls_metadata[];
+extern unsigned long *sys_call_table;
+
+static struct syscall_metadata **syscalls_metadata;
+
+static struct syscall_metadata *find_syscall_meta(unsigned long *syscall)
+{
+	struct syscall_metadata *start;
+	struct syscall_metadata *stop;
+	char str[KSYM_SYMBOL_LEN];
+
+
+	start = (struct syscall_metadata *)__start_syscalls_metadata;
+	stop = (struct syscall_metadata *)__stop_syscalls_metadata;
+	kallsyms_lookup((unsigned long) syscall, NULL, NULL, NULL, str);
+
+	for ( ; start < stop; start++) {
+		if (start->name && !strcmp(start->name, str))
+			return start;
+	}
+	return NULL;
+}
+
+struct syscall_metadata *syscall_nr_to_meta(int nr)
+{
+	if (!syscalls_metadata || nr >= FTRACE_SYSCALL_MAX || nr < 0)
+		return NULL;
+
+	return syscalls_metadata[nr];
+}
+
+void 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;
+	}
+
+	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);
+}
+#endif
diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c
index 55b94614e348..7b5169d2b000 100644
--- a/arch/x86/kernel/kprobes.c
+++ b/arch/x86/kernel/kprobes.c
@@ -638,13 +638,13 @@ static void __used __kprobes kretprobe_trampoline_holder(void)
 #else
 			"	pushf\n"
 			/*
-			 * Skip cs, ip, orig_ax.
+			 * Skip cs, ip, orig_ax and gs.
 			 * trampoline_handler() will plug in these values
 			 */
-			"	subl $12, %esp\n"
+			"	subl $16, %esp\n"
 			"	pushl %fs\n"
-			"	pushl %ds\n"
 			"	pushl %es\n"
+			"	pushl %ds\n"
 			"	pushl %eax\n"
 			"	pushl %ebp\n"
 			"	pushl %edi\n"
@@ -655,10 +655,10 @@ static void __used __kprobes kretprobe_trampoline_holder(void)
 			"	movl %esp, %eax\n"
 			"	call trampoline_handler\n"
 			/* Move flags to cs */
-			"	movl 52(%esp), %edx\n"
-			"	movl %edx, 48(%esp)\n"
+			"	movl 56(%esp), %edx\n"
+			"	movl %edx, 52(%esp)\n"
 			/* Replace saved flags with true return address. */
-			"	movl %eax, 52(%esp)\n"
+			"	movl %eax, 56(%esp)\n"
 			"	popl %ebx\n"
 			"	popl %ecx\n"
 			"	popl %edx\n"
@@ -666,8 +666,8 @@ static void __used __kprobes kretprobe_trampoline_holder(void)
 			"	popl %edi\n"
 			"	popl %ebp\n"
 			"	popl %eax\n"
-			/* Skip ip, orig_ax, es, ds, fs */
-			"	addl $20, %esp\n"
+			/* Skip ds, es, fs, gs, orig_ax and ip */
+			"	addl $24, %esp\n"
 			"	popf\n"
 #endif
 			"	ret\n");
@@ -691,6 +691,7 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
 	regs->cs = __KERNEL_CS;
 #else
 	regs->cs = __KERNEL_CS | get_kernel_rpl();
+	regs->gs = 0;
 #endif
 	regs->ip = trampoline_address;
 	regs->orig_ax = ~0UL;
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 156f87582c6c..62fc75b67e45 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>
 #include <asm/idle.h>
@@ -22,6 +22,9 @@ 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/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 19378715f415..5c6e46320db1 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -21,6 +21,7 @@
 #include <linux/audit.h>
 #include <linux/seccomp.h>
 #include <linux/signal.h>
+#include <linux/ftrace.h>
 
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
@@ -1415,6 +1416,9 @@ asmregparm long syscall_trace_enter(struct pt_regs *regs)
 	    tracehook_report_syscall_entry(regs))
 		ret = -1L;
 
+	if (unlikely(test_thread_flag(TIF_SYSCALL_FTRACE)))
+		ftrace_syscall_enter(regs);
+
 	if (unlikely(current->audit_context)) {
 		if (IS_IA32)
 			audit_syscall_entry(AUDIT_ARCH_I386,
@@ -1438,6 +1442,9 @@ asmregparm void syscall_trace_leave(struct pt_regs *regs)
 	if (unlikely(current->audit_context))
 		audit_syscall_exit(AUDITSC_RESULT(regs->ax), regs->ax);
 
+	if (unlikely(test_thread_flag(TIF_SYSCALL_FTRACE)))
+		ftrace_syscall_exit(regs);
+
 	if (test_thread_flag(TIF_SYSCALL_TRACE))
 		tracehook_report_syscall_exit(regs, 0);