perf/core, x86: Add PERF_SAMPLE_PHYS_ADDR

For understanding how the workload maps to memory channels and hardware
behavior, it's very important to collect address maps with physical
addresses. For example, 3D XPoint access can only be found by filtering
the physical address.

Add a new sample type for physical address.

perf already has a facility to collect data virtual address. This patch
introduces a function to convert the virtual address to physical address.
The function is quite generic and can be extended to any architecture as
long as a virtual address is provided.

 - For kernel direct mapping addresses, virt_to_phys is used to convert
   the virtual addresses to physical address.

 - For user virtual addresses, __get_user_pages_fast is used to walk the
   pages tables for user physical address.

 - This does not work for vmalloc addresses right now. These are not
   resolved, but code to do that could be added.

The new sample type requires collecting the virtual address. The
virtual address will not be output unless SAMPLE_ADDR is applied.

For security, the physical address can only be exposed to root or
privileged user.

Tested-by: Madhavan Srinivasan <maddy@linux.vnet.ibm.com>
Signed-off-by: Kan Liang <kan.liang@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: acme@kernel.org
Cc: mpe@ellerman.id.au
Link: http://lkml.kernel.org/r/1503967969-48278-1-git-send-email-kan.liang@intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/powerpc/perf/core-book3s.c

@@ -2039,7 +2039,8 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 
 		perf_sample_data_init(&data, ~0ULL, event->hw.last_period);
 
-		if (event->attr.sample_type & PERF_SAMPLE_ADDR)
+		if (event->attr.sample_type &
+		    (PERF_SAMPLE_ADDR | PERF_SAMPLE_PHYS_ADDR))
 			perf_get_data_addr(regs, &data.addr);
 
 		if (event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK) {

arch/x86/events/intel/ds.c

@@ -1185,7 +1185,7 @@ static void setup_pebs_sample_data(struct perf_event *event,
 	else
 		regs->flags &= ~PERF_EFLAGS_EXACT;
 
-	if ((sample_type & PERF_SAMPLE_ADDR) &&
+	if ((sample_type & (PERF_SAMPLE_ADDR | PERF_SAMPLE_PHYS_ADDR)) &&
 	    x86_pmu.intel_cap.pebs_format >= 1)
 		data->addr = pebs->dla;
 

arch/x86/events/perf_event.h

@@ -91,7 +91,7 @@ struct amd_nb {
 	(PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_ADDR | \
 	PERF_SAMPLE_ID | PERF_SAMPLE_CPU | PERF_SAMPLE_STREAM_ID | \
 	PERF_SAMPLE_DATA_SRC | PERF_SAMPLE_IDENTIFIER | \
-	PERF_SAMPLE_TRANSACTION)
+	PERF_SAMPLE_TRANSACTION | PERF_SAMPLE_PHYS_ADDR)
 
 /*
  * A debug store configuration.

include/linux/perf_event.h

@@ -943,6 +943,8 @@ struct perf_sample_data {
 
 	struct perf_regs		regs_intr;
 	u64				stack_user_size;
+
+	u64				phys_addr;
 } ____cacheline_aligned;
 
 /* default value for data source */

include/uapi/linux/perf_event.h

@@ -139,8 +139,9 @@ enum perf_event_sample_format {
 	PERF_SAMPLE_IDENTIFIER			= 1U << 16,
 	PERF_SAMPLE_TRANSACTION			= 1U << 17,
 	PERF_SAMPLE_REGS_INTR			= 1U << 18,
+	PERF_SAMPLE_PHYS_ADDR			= 1U << 19,
 
-	PERF_SAMPLE_MAX = 1U << 19,		/* non-ABI */
+	PERF_SAMPLE_MAX = 1U << 20,		/* non-ABI */
 };
 
 /*
@@ -814,6 +815,7 @@ enum perf_event_type {
 	 *	{ u64			transaction; } && PERF_SAMPLE_TRANSACTION
 	 *	{ u64			abi; # enum perf_sample_regs_abi
 	 *	  u64			regs[weight(mask)]; } && PERF_SAMPLE_REGS_INTR
+	 *	{ u64			phys_addr;} && PERF_SAMPLE_PHYS_ADDR
 	 * };
 	 */
 	PERF_RECORD_SAMPLE			= 9,

kernel/events/core.c

@@ -1575,6 +1575,9 @@ static void __perf_event_header_size(struct perf_event *event, u64 sample_type)
 	if (sample_type & PERF_SAMPLE_TRANSACTION)
 		size += sizeof(data->txn);
 
+	if (sample_type & PERF_SAMPLE_PHYS_ADDR)
+		size += sizeof(data->phys_addr);
+
 	event->header_size = size;
 }
 
@@ -6017,6 +6020,9 @@ void perf_output_sample(struct perf_output_handle *handle,
 		}
 	}
 
+	if (sample_type & PERF_SAMPLE_PHYS_ADDR)
+		perf_output_put(handle, data->phys_addr);
+
 	if (!event->attr.watermark) {
 		int wakeup_events = event->attr.wakeup_events;
 
@@ -6032,6 +6038,38 @@ void perf_output_sample(struct perf_output_handle *handle,
 	}
 }
 
+static u64 perf_virt_to_phys(u64 virt)
+{
+	u64 phys_addr = 0;
+	struct page *p = NULL;
+
+	if (!virt)
+		return 0;
+
+	if (virt >= TASK_SIZE) {
+		/* If it's vmalloc()d memory, leave phys_addr as 0 */
+		if (virt_addr_valid((void *)(uintptr_t)virt) &&
+		    !(virt >= VMALLOC_START && virt < VMALLOC_END))
+			phys_addr = (u64)virt_to_phys((void *)(uintptr_t)virt);
+	} else {
+		/*
+		 * Walking the pages tables for user address.
+		 * Interrupts are disabled, so it prevents any tear down
+		 * of the page tables.
+		 * Try IRQ-safe __get_user_pages_fast first.
+		 * If failed, leave phys_addr as 0.
+		 */
+		if ((current->mm != NULL) &&
+		    (__get_user_pages_fast(virt, 1, 0, &p) == 1))
+			phys_addr = page_to_phys(p) + virt % PAGE_SIZE;
+
+		if (p)
+			put_page(p);
+	}
+
+	return phys_addr;
+}
+
 void perf_prepare_sample(struct perf_event_header *header,
 			 struct perf_sample_data *data,
 			 struct perf_event *event,
@@ -6150,6 +6188,9 @@ void perf_prepare_sample(struct perf_event_header *header,
 
 		header->size += size;
 	}
+
+	if (sample_type & PERF_SAMPLE_PHYS_ADDR)
+		data->phys_addr = perf_virt_to_phys(data->addr);
 }
 
 static void __always_inline
@@ -9909,6 +9950,11 @@ SYSCALL_DEFINE5(perf_event_open,
 			return -EINVAL;
 	}
 
+	/* Only privileged users can get physical addresses */
+	if ((attr.sample_type & PERF_SAMPLE_PHYS_ADDR) &&
+	    perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
 	if (!attr.sample_max_stack)
 		attr.sample_max_stack = sysctl_perf_event_max_stack;