perfcounters: provide expansion room in the ABI

Impact: ABI change

This expands several fields in the perf_counter_hw_event struct and adds
a "flags" argument to the perf_counter_open system call, in order that
features can be added in future without ABI changes.

In particular the record_type field is expanded to 64 bits, and the
space for flag bits has been expanded from 32 to 64 bits.

This also adds some new fields:

* read_format (64 bits) is intended to provide a way to specify what
  userspace wants to get back when it does a read() on a simple
  (non-interrupting) counter;

* exclude_idle (1 bit) provides a way for userspace to ask that events
  that occur when the cpu is idle be excluded;

* extra_config_len will provide a way for userspace to supply an
  arbitrary amount of extra machine-specific PMU configuration data
  immediately following the perf_counter_hw_event struct, to allow
  sophisticated users to program things such as instruction matching
  CAMs and address range registers;

* __reserved_3 and __reserved_4 provide space for future expansion.
Signed-off-by: Paul Mackerras <paulus@samba.org>

include/linux/perf_counter.h

@@ -69,9 +69,10 @@ struct perf_counter_hw_event {
 	__s64			type;
 
 	__u64			irq_period;
-	__u32			record_type;
+	__u64			record_type;
+	__u64			read_format;
 
-	__u32			disabled       :  1, /* off by default        */
+	__u64			disabled       :  1, /* off by default        */
 				nmi	       :  1, /* NMI sampling          */
 				raw	       :  1, /* raw event type        */
 				inherit	       :  1, /* children inherit it   */
@@ -80,10 +81,15 @@ struct perf_counter_hw_event {
 				exclude_user   :  1, /* don't count user      */
 				exclude_kernel :  1, /* ditto kernel          */
 				exclude_hv     :  1, /* ditto hypervisor      */
+				exclude_idle   :  1, /* don't count when idle */
 
-				__reserved_1 : 23;
+				__reserved_1 : 55;
+
+	__u32			extra_config_len;
+	__u32			__reserved_4;
 
 	__u64			__reserved_2;
+	__u64			__reserved_3;
 };
 
 /*

include/linux/syscalls.h

@@ -698,5 +698,5 @@ int kernel_execve(const char *filename, char *const argv[], char *const envp[]);
 
 asmlinkage long sys_perf_counter_open(
 		const struct perf_counter_hw_event __user *hw_event_uptr,
-		pid_t pid, int cpu, int group_fd);
+		pid_t pid, int cpu, int group_fd, unsigned long flags);
 #endif

kernel/perf_counter.c

@@ -1683,16 +1683,16 @@ perf_counter_alloc(struct perf_counter_hw_event *hw_event,
 }
 
 /**
- * sys_perf_task_open - open a performance counter, associate it to a task/cpu
+ * sys_perf_counter_open - open a performance counter, associate it to a task/cpu
  *
  * @hw_event_uptr:	event type attributes for monitoring/sampling
  * @pid:		target pid
  * @cpu:		target cpu
  * @group_fd:		group leader counter fd
  */
-SYSCALL_DEFINE4(perf_counter_open,
+SYSCALL_DEFINE5(perf_counter_open,
 		const struct perf_counter_hw_event __user *, hw_event_uptr,
-		pid_t, pid, int, cpu, int, group_fd)
+		pid_t, pid, int, cpu, int, group_fd, unsigned long, flags)
 {
 	struct perf_counter *counter, *group_leader;
 	struct perf_counter_hw_event hw_event;
@@ -1703,6 +1703,10 @@ SYSCALL_DEFINE4(perf_counter_open,
 	int fput_needed2 = 0;
 	int ret;
 
+	/* for future expandability... */
+	if (flags)
+		return -EINVAL;
+
 	if (copy_from_user(&hw_event, hw_event_uptr, sizeof(hw_event)) != 0)
 		return -EFAULT;