perf/core: Add support for PERF_SAMPLE_CODE_PAGE_SIZE

When studying code layout, it is useful to capture the page size of the
sampled code address.

Add a new sample type for code page size.
The new sample type requires collecting the ip. The code page size can
be calculated from the NMI-safe perf_get_page_size().

For large PEBS, it's very unlikely that the mapping is gone for the
earlier PEBS records. Enable the feature for the large PEBS. The worst
case is that page-size '0' is returned.
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20201001135749.2804-5-kan.liang@linux.intel.com

arch/x86/events/perf_event.h

@@ -132,7 +132,7 @@ struct amd_nb {
 	PERF_SAMPLE_DATA_SRC | PERF_SAMPLE_IDENTIFIER | \
 	PERF_SAMPLE_TRANSACTION | PERF_SAMPLE_PHYS_ADDR | \
 	PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER | \
-	PERF_SAMPLE_PERIOD)
+	PERF_SAMPLE_PERIOD | PERF_SAMPLE_CODE_PAGE_SIZE)
 
 #define PEBS_GP_REGS			\
 	((1ULL << PERF_REG_X86_AX)    | \

include/linux/perf_event.h

@@ -1035,6 +1035,7 @@ struct perf_sample_data {
 	u64				phys_addr;
 	u64				cgroup;
 	u64				data_page_size;
+	u64				code_page_size;
 } ____cacheline_aligned;
 
 /* default value for data source */

include/uapi/linux/perf_event.h

@@ -144,8 +144,9 @@ enum perf_event_sample_format {
 	PERF_SAMPLE_AUX				= 1U << 20,
 	PERF_SAMPLE_CGROUP			= 1U << 21,
 	PERF_SAMPLE_DATA_PAGE_SIZE		= 1U << 22,
+	PERF_SAMPLE_CODE_PAGE_SIZE		= 1U << 23,
 
-	PERF_SAMPLE_MAX = 1U << 23,		/* non-ABI */
+	PERF_SAMPLE_MAX = 1U << 24,		/* non-ABI */
 
 	__PERF_SAMPLE_CALLCHAIN_EARLY		= 1ULL << 63, /* non-ABI; internal use */
 };
@@ -898,6 +899,7 @@ enum perf_event_type {
 	 *	{ u64			size;
 	 *	  char			data[size]; } && PERF_SAMPLE_AUX
 	 *	{ u64			data_page_size;} && PERF_SAMPLE_DATA_PAGE_SIZE
+	 *	{ u64			code_page_size;} && PERF_SAMPLE_CODE_PAGE_SIZE
 	 * };
 	 */
 	PERF_RECORD_SAMPLE			= 9,

kernel/events/core.c

@@ -1898,6 +1898,9 @@ static void __perf_event_header_size(struct perf_event *event, u64 sample_type)
 	if (sample_type & PERF_SAMPLE_DATA_PAGE_SIZE)
 		size += sizeof(data->data_page_size);
 
+	if (sample_type & PERF_SAMPLE_CODE_PAGE_SIZE)
+		size += sizeof(data->code_page_size);
+
 	event->header_size = size;
 }
 
@@ -6945,6 +6948,9 @@ void perf_output_sample(struct perf_output_handle *handle,
 	if (sample_type & PERF_SAMPLE_DATA_PAGE_SIZE)
 		perf_output_put(handle, data->data_page_size);
 
+	if (sample_type & PERF_SAMPLE_CODE_PAGE_SIZE)
+		perf_output_put(handle, data->code_page_size);
+
 	if (sample_type & PERF_SAMPLE_AUX) {
 		perf_output_put(handle, data->aux_size);
 
@@ -7125,7 +7131,7 @@ void perf_prepare_sample(struct perf_event_header *header,
 
 	__perf_event_header__init_id(header, data, event);
 
-	if (sample_type & PERF_SAMPLE_IP)
+	if (sample_type & (PERF_SAMPLE_IP | PERF_SAMPLE_CODE_PAGE_SIZE))
 		data->ip = perf_instruction_pointer(regs);
 
 	if (sample_type & PERF_SAMPLE_CALLCHAIN) {
@@ -7253,6 +7259,9 @@ void perf_prepare_sample(struct perf_event_header *header,
 	if (sample_type & PERF_SAMPLE_DATA_PAGE_SIZE)
 		data->data_page_size = perf_get_page_size(data->addr);
 
+	if (sample_type & PERF_SAMPLE_CODE_PAGE_SIZE)
+		data->code_page_size = perf_get_page_size(data->ip);
+
 	if (sample_type & PERF_SAMPLE_AUX) {
 		u64 size;