Merge branch 'core' of git://git.kernel.org/pub/scm/linux/kernel/git/rric/oprofile into perf/core

8 files changed, 254 insertions, 19 deletions

diff --git a/arch/mips/include/asm/stacktrace.h b/arch/mips/include/asm/stacktrace.h
index 0bf82818aa5..780ee2c2a2a 100644
--- a/arch/mips/include/asm/stacktrace.h
+++ b/arch/mips/include/asm/stacktrace.h
@@ -7,6 +7,10 @@
 extern int raw_show_trace;
 extern unsigned long unwind_stack(struct task_struct *task, unsigned long *sp,
 				  unsigned long pc, unsigned long *ra);
+extern unsigned long unwind_stack_by_address(unsigned long stack_page,
+					     unsigned long *sp,
+					     unsigned long pc,
+					     unsigned long *ra);
 #else
 #define raw_show_trace 1
 static inline unsigned long unwind_stack(struct task_struct *task,
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index d2112d3cf11..c28fbe6107b 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -373,18 +373,18 @@ unsigned long thread_saved_pc(struct task_struct *tsk)
 
 
 #ifdef CONFIG_KALLSYMS
-/* used by show_backtrace() */
-unsigned long unwind_stack(struct task_struct *task, unsigned long *sp,
-			   unsigned long pc, unsigned long *ra)
+/* generic stack unwinding function */
+unsigned long notrace unwind_stack_by_address(unsigned long stack_page,
+					      unsigned long *sp,
+					      unsigned long pc,
+					      unsigned long *ra)
 {
-	unsigned long stack_page;
 	struct mips_frame_info info;
 	unsigned long size, ofs;
 	int leaf;
 	extern void ret_from_irq(void);
 	extern void ret_from_exception(void);
 
-	stack_page = (unsigned long)task_stack_page(task);
 	if (!stack_page)
 		return 0;
 
@@ -443,6 +443,15 @@ unsigned long unwind_stack(struct task_struct *task, unsigned long *sp,
 	*ra = 0;
 	return __kernel_text_address(pc) ? pc : 0;
 }
+EXPORT_SYMBOL(unwind_stack_by_address);
+
+/* used by show_backtrace() */
+unsigned long unwind_stack(struct task_struct *task, unsigned long *sp,
+			   unsigned long pc, unsigned long *ra)
+{
+	unsigned long stack_page = (unsigned long)task_stack_page(task);
+	return unwind_stack_by_address(stack_page, sp, pc, ra);
+}
 #endif
 
 /*
diff --git a/arch/mips/oprofile/Makefile b/arch/mips/oprofile/Makefile
index 4b9d7044e26..29f2f13eb31 100644
--- a/arch/mips/oprofile/Makefile
+++ b/arch/mips/oprofile/Makefile
@@ -8,7 +8,7 @@ DRIVER_OBJS = $(addprefix ../../../drivers/oprofile/, \
 		oprofilefs.o oprofile_stats.o \
 		timer_int.o )
 
-oprofile-y				:= $(DRIVER_OBJS) common.o
+oprofile-y				:= $(DRIVER_OBJS) common.o backtrace.o
 
 oprofile-$(CONFIG_CPU_MIPS32)		+= op_model_mipsxx.o
 oprofile-$(CONFIG_CPU_MIPS64)		+= op_model_mipsxx.o
diff --git a/arch/mips/oprofile/backtrace.c b/arch/mips/oprofile/backtrace.c
new file mode 100644
index 00000000000..6854ed5097d
--- /dev/null
+++ b/arch/mips/oprofile/backtrace.c
@@ -0,0 +1,175 @@
+#include <linux/oprofile.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/uaccess.h>
+#include <asm/ptrace.h>
+#include <asm/stacktrace.h>
+#include <linux/stacktrace.h>
+#include <linux/kernel.h>
+#include <asm/sections.h>
+#include <asm/inst.h>
+
+struct stackframe {
+	unsigned long sp;
+	unsigned long pc;
+	unsigned long ra;
+};
+
+static inline int get_mem(unsigned long addr, unsigned long *result)
+{
+	unsigned long *address = (unsigned long *) addr;
+	if (!access_ok(VERIFY_READ, addr, sizeof(unsigned long)))
+		return -1;
+	if (__copy_from_user_inatomic(result, address, sizeof(unsigned long)))
+		return -3;
+	return 0;
+}
+
+/*
+ * These two instruction helpers were taken from process.c
+ */
+static inline int is_ra_save_ins(union mips_instruction *ip)
+{
+	/* sw / sd $ra, offset($sp) */
+	return (ip->i_format.opcode == sw_op || ip->i_format.opcode == sd_op)
+		&& ip->i_format.rs == 29 && ip->i_format.rt == 31;
+}
+
+static inline int is_sp_move_ins(union mips_instruction *ip)
+{
+	/* addiu/daddiu sp,sp,-imm */
+	if (ip->i_format.rs != 29 || ip->i_format.rt != 29)
+		return 0;
+	if (ip->i_format.opcode == addiu_op || ip->i_format.opcode == daddiu_op)
+		return 1;
+	return 0;
+}
+
+/*
+ * Looks for specific instructions that mark the end of a function.
+ * This usually means we ran into the code area of the previous function.
+ */
+static inline int is_end_of_function_marker(union mips_instruction *ip)
+{
+	/* jr ra */
+	if (ip->r_format.func == jr_op && ip->r_format.rs == 31)
+		return 1;
+	/* lui gp */
+	if (ip->i_format.opcode == lui_op && ip->i_format.rt == 28)
+		return 1;
+	return 0;
+}
+
+/*
+ * TODO for userspace stack unwinding:
+ * - handle cases where the stack is adjusted inside a function
+ *     (generally doesn't happen)
+ * - find optimal value for max_instr_check
+ * - try to find a way to handle leaf functions
+ */
+
+static inline int unwind_user_frame(struct stackframe *old_frame,
+				    const unsigned int max_instr_check)
+{
+	struct stackframe new_frame = *old_frame;
+	off_t ra_offset = 0;
+	size_t stack_size = 0;
+	unsigned long addr;
+
+	if (old_frame->pc == 0 || old_frame->sp == 0 || old_frame->ra == 0)
+		return -9;
+
+	for (addr = new_frame.pc; (addr + max_instr_check > new_frame.pc)
+		&& (!ra_offset || !stack_size); --addr) {
+		union mips_instruction ip;
+
+		if (get_mem(addr, (unsigned long *) &ip))
+			return -11;
+
+		if (is_sp_move_ins(&ip)) {
+			int stack_adjustment = ip.i_format.simmediate;
+			if (stack_adjustment > 0)
+				/* This marks the end of the previous function,
+				   which means we overran. */
+				break;
+			stack_size = (unsigned) stack_adjustment;
+		} else if (is_ra_save_ins(&ip)) {
+			int ra_slot = ip.i_format.simmediate;
+			if (ra_slot < 0)
+				/* This shouldn't happen. */
+				break;
+			ra_offset = ra_slot;
+		} else if (is_end_of_function_marker(&ip))
+			break;
+	}
+
+	if (!ra_offset || !stack_size)
+		return -1;
+
+	if (ra_offset) {
+		new_frame.ra = old_frame->sp + ra_offset;
+		if (get_mem(new_frame.ra, &(new_frame.ra)))
+			return -13;
+	}
+
+	if (stack_size) {
+		new_frame.sp = old_frame->sp + stack_size;
+		if (get_mem(new_frame.sp, &(new_frame.sp)))
+			return -14;
+	}
+
+	if (new_frame.sp > old_frame->sp)
+		return -2;
+
+	new_frame.pc = old_frame->ra;
+	*old_frame = new_frame;
+
+	return 0;
+}
+
+static inline void do_user_backtrace(unsigned long low_addr,
+				     struct stackframe *frame,
+				     unsigned int depth)
+{
+	const unsigned int max_instr_check = 512;
+	const unsigned long high_addr = low_addr + THREAD_SIZE;
+
+	while (depth-- && !unwind_user_frame(frame, max_instr_check)) {
+		oprofile_add_trace(frame->ra);
+		if (frame->sp < low_addr || frame->sp > high_addr)
+			break;
+	}
+}
+
+#ifndef CONFIG_KALLSYMS
+static inline void do_kernel_backtrace(unsigned long low_addr,
+				       struct stackframe *frame,
+				       unsigned int depth) { }
+#else
+static inline void do_kernel_backtrace(unsigned long low_addr,
+				       struct stackframe *frame,
+				       unsigned int depth)
+{
+	while (depth-- && frame->pc) {
+		frame->pc = unwind_stack_by_address(low_addr,
+						    &(frame->sp),
+						    frame->pc,
+						    &(frame->ra));
+		oprofile_add_trace(frame->ra);
+	}
+}
+#endif
+
+void notrace op_mips_backtrace(struct pt_regs *const regs, unsigned int depth)
+{
+	struct stackframe frame = { .sp = regs->regs[29],
+				    .pc = regs->cp0_epc,
+				    .ra = regs->regs[31] };
+	const int userspace = user_mode(regs);
+	const unsigned long low_addr = ALIGN(frame.sp, THREAD_SIZE);
+
+	if (userspace)
+		do_user_backtrace(low_addr, &frame, depth);
+	else
+		do_kernel_backtrace(low_addr, &frame, depth);
+}
diff --git a/arch/mips/oprofile/common.c b/arch/mips/oprofile/common.c
index f9eb1aba634..d1f2d4c52d4 100644
--- a/arch/mips/oprofile/common.c
+++ b/arch/mips/oprofile/common.c
@@ -115,6 +115,7 @@ int __init oprofile_arch_init(struct oprofile_operations *ops)
 	ops->start		= op_mips_start;
 	ops->stop		= op_mips_stop;
 	ops->cpu_type		= lmodel->cpu_type;
+	ops->backtrace		= op_mips_backtrace;
 
 	printk(KERN_INFO "oprofile: using %s performance monitoring.\n",
 	       lmodel->cpu_type);
diff --git a/arch/mips/oprofile/op_impl.h b/arch/mips/oprofile/op_impl.h
index f04b54fb37d..7c2da27ece0 100644
--- a/arch/mips/oprofile/op_impl.h
+++ b/arch/mips/oprofile/op_impl.h
@@ -36,4 +36,6 @@ struct op_mips_model {
 	unsigned char num_counters;
 };
 
+void op_mips_backtrace(struct pt_regs * const regs, unsigned int depth);
+
 #endif
diff --git a/arch/x86/oprofile/backtrace.c b/arch/x86/oprofile/backtrace.c
index a5b64ab4cd6..32f78eb4674 100644
--- a/arch/x86/oprofile/backtrace.c
+++ b/arch/x86/oprofile/backtrace.c
@@ -11,10 +11,12 @@
 #include <linux/oprofile.h>
 #include <linux/sched.h>
 #include <linux/mm.h>
+#include <linux/compat.h>
+#include <linux/highmem.h>
+
 #include <asm/ptrace.h>
 #include <asm/uaccess.h>
 #include <asm/stacktrace.h>
-#include <linux/compat.h>
 
 static int backtrace_stack(void *data, char *name)
 {
@@ -36,17 +38,53 @@ static struct stacktrace_ops backtrace_ops = {
 	.walk_stack	= print_context_stack,
 };
 
+/* from arch/x86/kernel/cpu/perf_event.c: */
+
+/*
+ * best effort, GUP based copy_from_user() that assumes IRQ or NMI context
+ */
+static unsigned long
+copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
+{
+	unsigned long offset, addr = (unsigned long)from;
+	unsigned long size, len = 0;
+	struct page *page;
+	void *map;
+	int ret;
+
+	do {
+		ret = __get_user_pages_fast(addr, 1, 0, &page);
+		if (!ret)
+			break;
+
+		offset = addr & (PAGE_SIZE - 1);
+		size = min(PAGE_SIZE - offset, n - len);
+
+		map = kmap_atomic(page);
+		memcpy(to, map+offset, size);
+		kunmap_atomic(map);
+		put_page(page);
+
+		len  += size;
+		to   += size;
+		addr += size;
+
+	} while (len < n);
+
+	return len;
+}
+
 #ifdef CONFIG_COMPAT
 static struct stack_frame_ia32 *
 dump_user_backtrace_32(struct stack_frame_ia32 *head)
 {
+	/* Also check accessibility of one struct frame_head beyond: */
 	struct stack_frame_ia32 bufhead[2];
 	struct stack_frame_ia32 *fp;
+	unsigned long bytes;
 
-	/* Also check accessibility of one struct frame_head beyond */
-	if (!access_ok(VERIFY_READ, head, sizeof(bufhead)))
-		return NULL;
-	if (__copy_from_user_inatomic(bufhead, head, sizeof(bufhead)))
+	bytes = copy_from_user_nmi(bufhead, head, sizeof(bufhead));
+	if (bytes != sizeof(bufhead))
 		return NULL;
 
 	fp = (struct stack_frame_ia32 *) compat_ptr(bufhead[0].next_frame);
@@ -87,12 +125,12 @@ x86_backtrace_32(struct pt_regs * const regs, unsigned int depth)
 
 static struct stack_frame *dump_user_backtrace(struct stack_frame *head)
 {
+	/* Also check accessibility of one struct frame_head beyond: */
 	struct stack_frame bufhead[2];
+	unsigned long bytes;
 
-	/* Also check accessibility of one struct stack_frame beyond */
-	if (!access_ok(VERIFY_READ, head, sizeof(bufhead)))
-		return NULL;
-	if (__copy_from_user_inatomic(bufhead, head, sizeof(bufhead)))
+	bytes = copy_from_user_nmi(bufhead, head, sizeof(bufhead));
+	if (bytes != sizeof(bufhead))
 		return NULL;
 
 	oprofile_add_trace(bufhead[0].return_address);
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index cf9750004a0..68894fdc034 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -112,8 +112,10 @@ static void nmi_cpu_start(void *dummy)
 static int nmi_start(void)
 {
 	get_online_cpus();
-	on_each_cpu(nmi_cpu_start, NULL, 1);
 	ctr_running = 1;
+	/* make ctr_running visible to the nmi handler: */
+	smp_mb();
+	on_each_cpu(nmi_cpu_start, NULL, 1);
 	put_online_cpus();
 	return 0;
 }
@@ -504,15 +506,18 @@ static int nmi_setup(void)
 
 	nmi_enabled = 0;
 	ctr_running = 0;
-	barrier();
+	/* make variables visible to the nmi handler: */
+	smp_mb();
 	err = register_die_notifier(&profile_exceptions_nb);
 	if (err)
 		goto fail;
 
 	get_online_cpus();
 	register_cpu_notifier(&oprofile_cpu_nb);
-	on_each_cpu(nmi_cpu_setup, NULL, 1);
 	nmi_enabled = 1;
+	/* make nmi_enabled visible to the nmi handler: */
+	smp_mb();
+	on_each_cpu(nmi_cpu_setup, NULL, 1);
 	put_online_cpus();
 
 	return 0;
@@ -531,7 +536,8 @@ static void nmi_shutdown(void)
 	nmi_enabled = 0;
 	ctr_running = 0;
 	put_online_cpus();
-	barrier();
+	/* make variables visible to the nmi handler: */
+	smp_mb();
 	unregister_die_notifier(&profile_exceptions_nb);
 	msrs = &get_cpu_var(cpu_msrs);
 	model->shutdown(msrs);