perf: Fix arch_perf_out_copy_user default

The arch_perf_output_copy_user() default of
__copy_from_user_inatomic() returns bytes not copied, while all other
argument functions given DEFINE_OUTPUT_COPY() return bytes copied.

Since copy_from_user_nmi() is the odd duck out by returning bytes
copied where all other *copy_{to,from}* functions return bytes not
copied, change it over and ammend DEFINE_OUTPUT_COPY() to expect bytes
not copied.

Oddly enough DEFINE_OUTPUT_COPY() already returned bytes not copied
while expecting its worker functions to return bytes copied.

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Acked-by: will.deacon@arm.com
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Link: http://lkml.kernel.org/r/20131030201622.GR16117@laptop.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/kernel/cpu/perf_event.c

@@ -1989,7 +1989,7 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
 		frame.return_address = 0;
 
 		bytes = copy_from_user_nmi(&frame, fp, sizeof(frame));
-		if (bytes != sizeof(frame))
+		if (bytes != 0)
 			break;
 
 		if (!valid_user_frame(fp, sizeof(frame)))
@@ -2041,7 +2041,7 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 		frame.return_address = 0;
 
 		bytes = copy_from_user_nmi(&frame, fp, sizeof(frame));
-		if (bytes != sizeof(frame))
+		if (bytes != 0)
 			break;
 
 		if (!valid_user_frame(fp, sizeof(frame)))

arch/x86/kernel/cpu/perf_event_intel_ds.c

@@ -789,7 +789,7 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
 
 		size = ip - to; /* Must fit our buffer, see above */
 		bytes = copy_from_user_nmi(buf, (void __user *)to, size);
-		if (bytes != size)
+		if (bytes != 0)
 			return 0;
 
 		kaddr = buf;

arch/x86/kernel/cpu/perf_event_intel_lbr.c

@@ -491,7 +491,7 @@ static int branch_type(unsigned long from, unsigned long to, int abort)
 
 		/* may fail if text not present */
 		bytes = copy_from_user_nmi(buf, (void __user *)from, size);
-		if (bytes != size)
+		if (bytes != 0)
 			return X86_BR_NONE;
 
 		addr = buf;

arch/x86/lib/usercopy.c

@@ -31,6 +31,6 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
 	ret = __copy_from_user_inatomic(to, from, n);
 	pagefault_enable();
 
-	return n - ret;
+	return ret;
 }
 EXPORT_SYMBOL_GPL(copy_from_user_nmi);

arch/x86/oprofile/backtrace.c

@@ -47,7 +47,7 @@ dump_user_backtrace_32(struct stack_frame_ia32 *head)
 	unsigned long bytes;
 
 	bytes = copy_from_user_nmi(bufhead, head, sizeof(bufhead));
-	if (bytes != sizeof(bufhead))
+	if (bytes != 0)
 		return NULL;
 
 	fp = (struct stack_frame_ia32 *) compat_ptr(bufhead[0].next_frame);
@@ -93,7 +93,7 @@ static struct stack_frame *dump_user_backtrace(struct stack_frame *head)
 	unsigned long bytes;
 
 	bytes = copy_from_user_nmi(bufhead, head, sizeof(bufhead));
-	if (bytes != sizeof(bufhead))
+	if (bytes != 0)
 		return NULL;
 
 	oprofile_add_trace(bufhead[0].return_address);

kernel/events/internal.h

@@ -82,16 +82,16 @@ static inline unsigned long perf_data_size(struct ring_buffer *rb)
 }
 
 #define DEFINE_OUTPUT_COPY(func_name, memcpy_func)			\
-static inline unsigned int						\
+static inline unsigned long						\
 func_name(struct perf_output_handle *handle,				\
-	  const void *buf, unsigned int len)				\
+	  const void *buf, unsigned long len)				\
 {									\
 	unsigned long size, written;					\
 									\
 	do {								\
-		size = min_t(unsigned long, handle->size, len);		\
-									\
+		size    = min(handle->size, len);			\
 		written = memcpy_func(handle->addr, buf, size);		\
+		written = size - written;				\
 									\
 		len -= written;						\
 		handle->addr += written;				\
@@ -110,20 +110,37 @@ func_name(struct perf_output_handle *handle,				\
 	return len;							\
 }
 
-static inline int memcpy_common(void *dst, const void *src, size_t n)
+static inline unsigned long
+memcpy_common(void *dst, const void *src, unsigned long n)
 {
 	memcpy(dst, src, n);
-	return n;
+	return 0;
 }
 
 DEFINE_OUTPUT_COPY(__output_copy, memcpy_common)
 
-#define MEMCPY_SKIP(dst, src, n) (n)
+static inline unsigned long
+memcpy_skip(void *dst, const void *src, unsigned long n)
+{
+	return 0;
+}
 
-DEFINE_OUTPUT_COPY(__output_skip, MEMCPY_SKIP)
+DEFINE_OUTPUT_COPY(__output_skip, memcpy_skip)
 
 #ifndef arch_perf_out_copy_user
-#define arch_perf_out_copy_user __copy_from_user_inatomic
+#define arch_perf_out_copy_user arch_perf_out_copy_user
+
+static inline unsigned long
+arch_perf_out_copy_user(void *dst, const void *src, unsigned long n)
+{
+	unsigned long ret;
+
+	pagefault_disable();
+	ret = __copy_from_user_inatomic(dst, src, n);
+	pagefault_enable();
+
+	return ret;
+}
 #endif
 
 DEFINE_OUTPUT_COPY(__output_copy_user, arch_perf_out_copy_user)