Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/…

…linux/kernel/git/tip/tip

Pull perf fixes from Ingo Molnar:
 "Assorted standalone fixes"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf/x86/intel: Add model number for Avoton Silvermont
  perf: Fix capabilities bitfield compatibility in 'struct perf_event_mmap_page'
  perf/x86/intel/uncore: Don't use smp_processor_id() in validate_group()
  perf: Update ABI comment
  tools lib lk: Uninclude linux/magic.h in debugfs.c
  perf tools: Fix old GCC build error in trace-event-parse.c:parse_proc_kallsyms()
  perf probe: Fix finder to find lines of given function
  perf session: Check for SIGINT in more loops
  perf tools: Fix compile with libelf without get_phdrnum
  perf tools: Fix buildid cache handling of kallsyms with kcore
  perf annotate: Fix objdump line parsing offset validation
  perf tools: Fill in new definitions for madvise()/mmap() flags
  perf tools: Sharpen the libaudit dependencies test

arch/x86/kernel/cpu/perf_event.c

@@ -1883,9 +1883,9 @@ static struct pmu pmu = {
 
 void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
 {
-	userpg->cap_usr_time = 0;
-	userpg->cap_usr_time_zero = 0;
-	userpg->cap_usr_rdpmc = x86_pmu.attr_rdpmc;
+	userpg->cap_user_time = 0;
+	userpg->cap_user_time_zero = 0;
+	userpg->cap_user_rdpmc = x86_pmu.attr_rdpmc;
 	userpg->pmc_width = x86_pmu.cntval_bits;
 
 	if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
@@ -1894,13 +1894,13 @@ void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
 	if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
 		return;
 
-	userpg->cap_usr_time = 1;
+	userpg->cap_user_time = 1;
 	userpg->time_mult = this_cpu_read(cyc2ns);
 	userpg->time_shift = CYC2NS_SCALE_FACTOR;
 	userpg->time_offset = this_cpu_read(cyc2ns_offset) - now;
 
 	if (sched_clock_stable && !check_tsc_disabled()) {
-		userpg->cap_usr_time_zero = 1;
+		userpg->cap_user_time_zero = 1;
 		userpg->time_zero = this_cpu_read(cyc2ns_offset);
 	}
 }

arch/x86/kernel/cpu/perf_event_intel.c

@@ -2325,6 +2325,7 @@ __init int intel_pmu_init(void)
 		break;
 
 	case 55: /* Atom 22nm "Silvermont" */
+	case 77: /* Avoton "Silvermont" */
 		memcpy(hw_cache_event_ids, slm_hw_cache_event_ids,
 			sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, slm_hw_cache_extra_regs,

arch/x86/kernel/cpu/perf_event_intel_uncore.c

@@ -2706,14 +2706,14 @@ static void uncore_pmu_init_hrtimer(struct intel_uncore_box *box)
 	box->hrtimer.function = uncore_pmu_hrtimer;
 }
 
-struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, int cpu)
+static struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, int node)
 {
 	struct intel_uncore_box *box;
 	int i, size;
 
 	size = sizeof(*box) + type->num_shared_regs * sizeof(struct intel_uncore_extra_reg);
 
-	box = kzalloc_node(size, GFP_KERNEL, cpu_to_node(cpu));
+	box = kzalloc_node(size, GFP_KERNEL, node);
 	if (!box)
 		return NULL;
 
@@ -3031,7 +3031,7 @@ static int uncore_validate_group(struct intel_uncore_pmu *pmu,
 	struct intel_uncore_box *fake_box;
 	int ret = -EINVAL, n;
 
-	fake_box = uncore_alloc_box(pmu->type, smp_processor_id());
+	fake_box = uncore_alloc_box(pmu->type, NUMA_NO_NODE);
 	if (!fake_box)
 		return -ENOMEM;
 
@@ -3294,7 +3294,7 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id
 	}
 
 	type = pci_uncores[UNCORE_PCI_DEV_TYPE(id->driver_data)];
-	box = uncore_alloc_box(type, 0);
+	box = uncore_alloc_box(type, NUMA_NO_NODE);
 	if (!box)
 		return -ENOMEM;
 
@@ -3499,7 +3499,7 @@ static int uncore_cpu_prepare(int cpu, int phys_id)
 			if (pmu->func_id < 0)
 				pmu->func_id = j;
 
-			box = uncore_alloc_box(type, cpu);
+			box = uncore_alloc_box(type, cpu_to_node(cpu));
 			if (!box)
 				return -ENOMEM;
 

include/uapi/linux/perf_event.h

@@ -380,10 +380,13 @@ struct perf_event_mmap_page {
 	union {
 		__u64	capabilities;
 		struct {
-			__u64	cap_usr_time		: 1,
-				cap_usr_rdpmc		: 1,
-				cap_usr_time_zero	: 1,
-				cap_____res		: 61;
+			__u64	cap_bit0		: 1, /* Always 0, deprecated, see commit 860f085b74e9 */
+				cap_bit0_is_deprecated	: 1, /* Always 1, signals that bit 0 is zero */
+
+				cap_user_rdpmc		: 1, /* The RDPMC instruction can be used to read counts */
+				cap_user_time		: 1, /* The time_* fields are used */
+				cap_user_time_zero	: 1, /* The time_zero field is used */
+				cap_____res		: 59;
 		};
 	};
 
@@ -442,12 +445,13 @@ struct perf_event_mmap_page {
 	 *               ((rem * time_mult) >> time_shift);
 	 */
 	__u64	time_zero;
+	__u32	size;			/* Header size up to __reserved[] fields. */
 
 		/*
 		 * Hole for extension of the self monitor capabilities
 		 */
 
-	__u64	__reserved[119];	/* align to 1k */
+	__u8	__reserved[118*8+4];	/* align to 1k. */
 
 	/*
 	 * Control data for the mmap() data buffer.
@@ -528,6 +532,7 @@ enum perf_event_type {
 	 *	u64				len;
 	 *	u64				pgoff;
 	 *	char				filename[];
+	 * 	struct sample_id		sample_id;
 	 * };
 	 */
 	PERF_RECORD_MMAP			= 1,

kernel/events/core.c

@@ -3660,6 +3660,26 @@ static void calc_timer_values(struct perf_event *event,
 	*running = ctx_time - event->tstamp_running;
 }
 
+static void perf_event_init_userpage(struct perf_event *event)
+{
+	struct perf_event_mmap_page *userpg;
+	struct ring_buffer *rb;
+
+	rcu_read_lock();
+	rb = rcu_dereference(event->rb);
+	if (!rb)
+		goto unlock;
+
+	userpg = rb->user_page;
+
+	/* Allow new userspace to detect that bit 0 is deprecated */
+	userpg->cap_bit0_is_deprecated = 1;
+	userpg->size = offsetof(struct perf_event_mmap_page, __reserved);
+
+unlock:
+	rcu_read_unlock();
+}
+
 void __weak arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
 {
 }
@@ -4044,6 +4064,7 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 	ring_buffer_attach(event, rb);
 	rcu_assign_pointer(event->rb, rb);
 
+	perf_event_init_userpage(event);
 	perf_event_update_userpage(event);
 
 unlock:

tools/lib/lk/debugfs.c

@@ -5,7 +5,6 @@
 #include <stdbool.h>
 #include <sys/vfs.h>
 #include <sys/mount.h>
-#include <linux/magic.h>
 #include <linux/kernel.h>
 
 #include "debugfs.h"

tools/perf/arch/x86/util/tsc.c

@@ -32,7 +32,7 @@ u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc)
 int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc,
 			     struct perf_tsc_conversion *tc)
 {
-	bool cap_usr_time_zero;
+	bool cap_user_time_zero;
 	u32 seq;
 	int i = 0;
 
@@ -42,7 +42,7 @@ int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc,
 		tc->time_mult = pc->time_mult;
 		tc->time_shift = pc->time_shift;
 		tc->time_zero = pc->time_zero;
-		cap_usr_time_zero = pc->cap_usr_time_zero;
+		cap_user_time_zero = pc->cap_user_time_zero;
 		rmb();
 		if (pc->lock == seq && !(seq & 1))
 			break;
@@ -52,7 +52,7 @@ int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc,
 		}
 	}
 
-	if (!cap_usr_time_zero)
+	if (!cap_user_time_zero)
 		return -EOPNOTSUPP;
 
 	return 0;

tools/perf/builtin-inject.c

@@ -321,8 +321,6 @@ static int perf_inject__sched_stat(struct perf_tool *tool,
 	return perf_event__repipe(tool, event_sw, &sample_sw, machine);
 }
 
-extern volatile int session_done;
-
 static void sig_handler(int sig __maybe_unused)
 {
 	session_done = 1;

tools/perf/builtin-report.c

@@ -401,8 +401,6 @@ static int perf_report__setup_sample_type(struct perf_report *rep)
 	return 0;
 }
 
-extern volatile int session_done;
-
 static void sig_handler(int sig __maybe_unused)
 {
 	session_done = 1;
@@ -568,6 +566,9 @@ static int __cmd_report(struct perf_report *rep)
 		}
 	}
 
+	if (session_done())
+		return 0;
+
 	if (nr_samples == 0) {
 		ui__error("The %s file has no samples!\n", session->filename);
 		return 0;

tools/perf/builtin-script.c

@@ -553,8 +553,6 @@ static struct perf_tool perf_script = {
 	.ordering_requires_timestamps = true,
 };
 
-extern volatile int session_done;
-
 static void sig_handler(int sig __maybe_unused)
 {
 	session_done = 1;

tools/perf/builtin-trace.c

@@ -16,6 +16,23 @@
 #include <sys/mman.h>
 #include <linux/futex.h>
 
+/* For older distros: */
+#ifndef MAP_STACK
+# define MAP_STACK		0x20000
+#endif
+
+#ifndef MADV_HWPOISON
+# define MADV_HWPOISON		100
+#endif
+
+#ifndef MADV_MERGEABLE
+# define MADV_MERGEABLE		12
+#endif
+
+#ifndef MADV_UNMERGEABLE
+# define MADV_UNMERGEABLE	13
+#endif
+
 static size_t syscall_arg__scnprintf_hex(char *bf, size_t size,
 					 unsigned long arg,
 					 u8 arg_idx __maybe_unused,

tools/perf/config/Makefile

@@ -180,6 +180,9 @@ FLAGS_LIBELF=$(CFLAGS) $(LDFLAGS) $(EXTLIBS)
 ifeq ($(call try-cc,$(SOURCE_ELF_MMAP),$(FLAGS_LIBELF),-DLIBELF_MMAP),y)
   CFLAGS += -DLIBELF_MMAP
 endif
+ifeq ($(call try-cc,$(SOURCE_ELF_GETPHDRNUM),$(FLAGS_LIBELF),-DHAVE_ELF_GETPHDRNUM),y)
+  CFLAGS += -DHAVE_ELF_GETPHDRNUM
+endif
 
 # include ARCH specific config
 -include $(src-perf)/arch/$(ARCH)/Makefile

tools/perf/config/feature-tests.mak

@@ -61,6 +61,15 @@ int main(void)
 }
 endef
 
+define SOURCE_ELF_GETPHDRNUM
+#include <libelf.h>
+int main(void)
+{
+	size_t dst;
+	return elf_getphdrnum(0, &dst);
+}
+endef
+
 ifndef NO_SLANG
 define SOURCE_SLANG
 #include <slang.h>
@@ -210,6 +219,7 @@ define SOURCE_LIBAUDIT
 
 int main(void)
 {
+	printf(\"error message: %s\n\", audit_errno_to_name(0));
 	return audit_open();
 }
 endef

tools/perf/util/annotate.c

@@ -809,7 +809,7 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map,
 		    end = map__rip_2objdump(map, sym->end);
 
 		offset = line_ip - start;
-		if (offset < 0 || (u64)line_ip > end)
+		if ((u64)line_ip < start || (u64)line_ip > end)
 			offset = -1;
 		else
 			parsed_line = tmp2 + 1;

tools/perf/util/dwarf-aux.c

@@ -262,6 +262,21 @@ bool die_is_signed_type(Dwarf_Die *tp_die)
 		ret == DW_ATE_signed_fixed);
 }
 
+/**
+ * die_is_func_def - Ensure that this DIE is a subprogram and definition
+ * @dw_die: a DIE
+ *
+ * Ensure that this DIE is a subprogram and NOT a declaration. This
+ * returns true if @dw_die is a function definition.
+ **/
+bool die_is_func_def(Dwarf_Die *dw_die)
+{
+	Dwarf_Attribute attr;
+
+	return (dwarf_tag(dw_die) == DW_TAG_subprogram &&
+		dwarf_attr(dw_die, DW_AT_declaration, &attr) == NULL);
+}
+
 /**
  * die_get_data_member_location - Get the data-member offset
  * @mb_die: a DIE of a member of a data structure
@@ -392,6 +407,10 @@ static int __die_search_func_cb(Dwarf_Die *fn_die, void *data)
 {
 	struct __addr_die_search_param *ad = data;
 
+	/*
+	 * Since a declaration entry doesn't has given pc, this always returns
+	 * function definition entry.
+	 */
 	if (dwarf_tag(fn_die) == DW_TAG_subprogram &&
 	    dwarf_haspc(fn_die, ad->addr)) {
 		memcpy(ad->die_mem, fn_die, sizeof(Dwarf_Die));

tools/perf/util/dwarf-aux.h

@@ -38,6 +38,9 @@ extern int cu_find_lineinfo(Dwarf_Die *cudie, unsigned long addr,
 extern int cu_walk_functions_at(Dwarf_Die *cu_die, Dwarf_Addr addr,
 			int (*callback)(Dwarf_Die *, void *), void *data);
 
+/* Ensure that this DIE is a subprogram and definition (not declaration) */
+extern bool die_is_func_def(Dwarf_Die *dw_die);
+
 /* Compare diename and tname */
 extern bool die_compare_name(Dwarf_Die *dw_die, const char *tname);