perf: Improve the perf_sample_data struct layout

This patch reorders fields in the perf_sample_data struct in order to
minimize the number of cachelines touched in perf_sample_data_init().
It also removes some intializations which are redundant with the code
in kernel/events/core.c

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1411559322-16548-7-git-send-email-eranian@google.com
Cc: cebbert.lkml@gmail.com
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: jolsa@redhat.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 68d46d5..486e84c 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -580,35 +580,40 @@
 
 
 struct perf_sample_data {
-	u64				type;
+	/*
+	 * Fields set by perf_sample_data_init(), group so as to
+	 * minimize the cachelines touched.
+	 */
+	u64				addr;
+	struct perf_raw_record		*raw;
+	struct perf_branch_stack	*br_stack;
+	u64				period;
+	u64				weight;
+	u64				txn;
+	union  perf_mem_data_src	data_src;
 
+	/*
+	 * The other fields, optionally {set,used} by
+	 * perf_{prepare,output}_sample().
+	 */
+	u64				type;
 	u64				ip;
 	struct {
 		u32	pid;
 		u32	tid;
 	}				tid_entry;
 	u64				time;
-	u64				addr;
 	u64				id;
 	u64				stream_id;
 	struct {
 		u32	cpu;
 		u32	reserved;
 	}				cpu_entry;
-	u64				period;
-	union  perf_mem_data_src	data_src;
 	struct perf_callchain_entry	*callchain;
-	struct perf_raw_record		*raw;
-	struct perf_branch_stack	*br_stack;
 	struct perf_regs		regs_user;
 	struct perf_regs		regs_intr;
 	u64				stack_user_size;
-	u64				weight;
-	/*
-	 * Transaction flags for abort events:
-	 */
-	u64				txn;
-};
+} ____cacheline_aligned;
 
 /* default value for data source */
 #define PERF_MEM_NA (PERF_MEM_S(OP, NA)   |\
@@ -625,14 +630,9 @@
 	data->raw  = NULL;
 	data->br_stack = NULL;
 	data->period = period;
-	data->regs_user.abi = PERF_SAMPLE_REGS_ABI_NONE;
-	data->regs_user.regs = NULL;
-	data->stack_user_size = 0;
 	data->weight = 0;
 	data->data_src.val = PERF_MEM_NA;
 	data->txn = 0;
-	data->regs_intr.abi = PERF_SAMPLE_REGS_ABI_NONE;
-	data->regs_intr.regs = NULL;
 }
 
 extern void perf_output_sample(struct perf_output_handle *handle,
diff --git a/kernel/events/core.c b/kernel/events/core.c
index c2be159..3e19d3e 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4471,8 +4471,11 @@
 	}
 
 	if (regs) {
-		regs_user->regs = regs;
 		regs_user->abi  = perf_reg_abi(current);
+		regs_user->regs = regs;
+	} else {
+		regs_user->abi = PERF_SAMPLE_REGS_ABI_NONE;
+		regs_user->regs = NULL;
 	}
 }
 
@@ -4947,12 +4950,13 @@
 		header->size += size;
 	}
 
+	if (sample_type & (PERF_SAMPLE_REGS_USER | PERF_SAMPLE_STACK_USER))
+		perf_sample_regs_user(&data->regs_user, regs);
+
 	if (sample_type & PERF_SAMPLE_REGS_USER) {
 		/* regs dump ABI info */
 		int size = sizeof(u64);
 
-		perf_sample_regs_user(&data->regs_user, regs);
-
 		if (data->regs_user.regs) {
 			u64 mask = event->attr.sample_regs_user;
 			size += hweight64(mask) * sizeof(u64);
@@ -4968,15 +4972,11 @@
 		 * in case new sample type is added, because we could eat
 		 * up the rest of the sample size.
 		 */
-		struct perf_regs *uregs = &data->regs_user;
 		u16 stack_size = event->attr.sample_stack_user;
 		u16 size = sizeof(u64);
 
-		if (!uregs->abi)
-			perf_sample_regs_user(uregs, regs);
-
 		stack_size = perf_sample_ustack_size(stack_size, header->size,
-						     uregs->regs);
+						     data->regs_user.regs);
 
 		/*
 		 * If there is something to dump, add space for the dump