perf fixes

index 04cd688..e1f3a17 100644
@@ -33,9 +33,8 @@
 #define segment_eq(a, b)	((a).seg == (b).seg)
 
 #define user_addr_max() (current_thread_info()->addr_limit.seg)
-#define __addr_ok(addr)					\
-	((unsigned long __force)(addr) <		\
-	 (current_thread_info()->addr_limit.seg))
+#define __addr_ok(addr) 	\
+	((unsigned long __force)(addr) < user_addr_max())
 
 /*
  * Test whether a block of memory is a valid user space address.

@@ -47,14 +46,14 @@
  * This needs 33-bit (65-bit for x86_64) arithmetic. We have a carry...
  */
 
-#define __range_not_ok(addr, size)					\
+#define __range_not_ok(addr, size, limit)				\
 ({									\
 	unsigned long flag, roksum;					\
 	__chk_user_ptr(addr);						\
 	asm("add %3,%1 ; sbb %0,%0 ; cmp %1,%4 ; sbb $0,%0"		\
 	    : "=&r" (flag), "=r" (roksum)				\
 	    : "1" (addr), "g" ((long)(size)),				\
-	      "rm" (current_thread_info()->addr_limit.seg));		\
+	      "rm" (limit));						\
 	flag;								\
 })
 

@@ -77,7 +76,8 @@
  * checks that the pointer is in the user space range - after calling
  * this function, memory access functions may still return -EFAULT.
  */
-#define access_ok(type, addr, size) (likely(__range_not_ok(addr, size) == 0))
+#define access_ok(type, addr, size) \
+	(likely(__range_not_ok(addr, size, user_addr_max()) == 0))
 
 /*
  * The exception table consists of pairs of addresses relative to the

index e049d6d..c4706cf 100644
@@ -1496,6 +1496,7 @@ static struct cpu_hw_events *allocate_fake_cpuc(void)
 		if (!cpuc->shared_regs)
 			goto error;
 	}
+	cpuc->is_fake = 1;
 	return cpuc;
 error:
 	free_fake_cpuc(cpuc);

@@ -1756,6 +1757,12 @@ perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
 	dump_trace(NULL, regs, NULL, 0, &backtrace_ops, entry);
 }
 
+static inline int
+valid_user_frame(const void __user *fp, unsigned long size)
+{
+	return (__range_not_ok(fp, size, TASK_SIZE) == 0);
+}
+
 #ifdef CONFIG_COMPAT
 
 #include <asm/compat.h>

@@ -1780,7 +1787,7 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
 		if (bytes != sizeof(frame))
 			break;
 
-		if (fp < compat_ptr(regs->sp))
+		if (!valid_user_frame(fp, sizeof(frame)))
 			break;
 
 		perf_callchain_store(entry, frame.return_address);

@@ -1826,7 +1833,7 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 		if (bytes != sizeof(frame))
 			break;
 
-		if ((unsigned long)fp < regs->sp)
+		if (!valid_user_frame(fp, sizeof(frame)))
 			break;
 
 		perf_callchain_store(entry, frame.return_address);

index 6638aaf..7241e2f 100644
@@ -117,6 +117,7 @@ struct cpu_hw_events {
 	struct perf_event	*event_list[X86_PMC_IDX_MAX]; /* in enabled order */
 
 	unsigned int		group_flag;
+	int			is_fake;
 
 	/*
 	 * Intel DebugStore bits

@@ -364,6 +365,7 @@ struct x86_pmu {
 	int		pebs_record_size;
 	void		(*drain_pebs)(struct pt_regs *regs);
 	struct event_constraint *pebs_constraints;
+	void		(*pebs_aliases)(struct perf_event *event);
 
 	/*
 	 * Intel LBR

228 lines not on this page · raw message

index 5a3edc2..35e2192 100644
@@ -400,14 +400,7 @@ struct event_constraint intel_snb_pebs_event_constraints[] = {
 	INTEL_EVENT_CONSTRAINT(0xc4, 0xf),    /* BR_INST_RETIRED.* */
 	INTEL_EVENT_CONSTRAINT(0xc5, 0xf),    /* BR_MISP_RETIRED.* */
 	INTEL_EVENT_CONSTRAINT(0xcd, 0x8),    /* MEM_TRANS_RETIRED.* */
-	INTEL_UEVENT_CONSTRAINT(0x11d0, 0xf), /* MEM_UOP_RETIRED.STLB_MISS_LOADS */
-	INTEL_UEVENT_CONSTRAINT(0x12d0, 0xf), /* MEM_UOP_RETIRED.STLB_MISS_STORES */
-	INTEL_UEVENT_CONSTRAINT(0x21d0, 0xf), /* MEM_UOP_RETIRED.LOCK_LOADS */
-	INTEL_UEVENT_CONSTRAINT(0x22d0, 0xf), /* MEM_UOP_RETIRED.LOCK_STORES */
-	INTEL_UEVENT_CONSTRAINT(0x41d0, 0xf), /* MEM_UOP_RETIRED.SPLIT_LOADS */
-	INTEL_UEVENT_CONSTRAINT(0x42d0, 0xf), /* MEM_UOP_RETIRED.SPLIT_STORES */
-	INTEL_UEVENT_CONSTRAINT(0x81d0, 0xf), /* MEM_UOP_RETIRED.ANY_LOADS */
-	INTEL_UEVENT_CONSTRAINT(0x82d0, 0xf), /* MEM_UOP_RETIRED.ANY_STORES */
+	INTEL_EVENT_CONSTRAINT(0xd0, 0xf),    /* MEM_UOP_RETIRED.* */
 	INTEL_EVENT_CONSTRAINT(0xd1, 0xf),    /* MEM_LOAD_UOPS_RETIRED.* */
 	INTEL_EVENT_CONSTRAINT(0xd2, 0xf),    /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
 	INTEL_UEVENT_CONSTRAINT(0x02d4, 0xf), /* MEM_LOAD_UOPS_MISC_RETIRED.LLC_MISS */

index f61ee67..677b1ed 100644
@@ -8,6 +8,7 @@
 #include <linux/module.h>
 
 #include <asm/word-at-a-time.h>
+#include <linux/sched.h>
 
 /*
  * best effort, GUP based copy_from_user() that is NMI-safe

@@ -21,6 +22,9 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
 	void *map;
 	int ret;
 
+	if (__range_not_ok(from, n, TASK_SIZE) == 0)
+		return len;
+
 	do {
 		ret = __get_user_pages_fast(addr, 1, 0, &page);
 		if (!ret)

index f325786..45db49f 100644
@@ -555,6 +555,8 @@ enum perf_event_type {
 	PERF_RECORD_MAX,			/* non-ABI */
 };
 
+#define PERF_MAX_STACK_DEPTH		127
+
 enum perf_callchain_context {
 	PERF_CONTEXT_HV			= (__u64)-32,
 	PERF_CONTEXT_KERNEL		= (__u64)-128,

@@ -609,8 +611,6 @@ struct perf_guest_info_callbacks {
 #include <linux/sysfs.h>
 #include <asm/local.h>
 
-#define PERF_MAX_STACK_DEPTH		255
-
 struct perf_callchain_entry {
 	__u64				nr;
 	__u64				ip[PERF_MAX_STACK_DEPTH];

index 5b06cbb..f85c015 100644
@@ -3181,7 +3181,6 @@ static void perf_event_for_each(struct perf_event *event,
 	event = event->group_leader;
 
 	perf_event_for_each_child(event, func);
-	func(event);
 	list_for_each_entry(sibling, &event->sibling_list, group_entry)
 		perf_event_for_each_child(sibling, func);
 	mutex_unlock(&ctx->mutex);

index 8c767c6..25249f7 100644
@@ -152,7 +152,7 @@ static int perf_evsel__add_hist_entry(struct perf_evsel *evsel,
 
 	if (symbol_conf.use_callchain) {
 		err = callchain_append(he->callchain,
-				       &evsel->hists.callchain_cursor,
+				       &callchain_cursor,
 				       sample->period);
 		if (err)
 			return err;

@@ -162,7 +162,7 @@ static int perf_evsel__add_hist_entry(struct perf_evsel *evsel,
 	 * so we don't allocated the extra space needed because the stdio
 	 * code will not use it.
 	 */
-	if (al->sym != NULL && use_browser > 0) {
+	if (he->ms.sym != NULL && use_browser > 0) {
 		struct annotation *notes = symbol__annotation(he->ms.sym);
 
 		assert(evsel != NULL);

index 62ae30d..2625899 100644
@@ -1129,7 +1129,7 @@ static int add_default_attributes(void)
 		return 0;
 
 	if (!evsel_list->nr_entries) {
-		if (perf_evlist__add_attrs_array(evsel_list, default_attrs) < 0)
+		if (perf_evlist__add_default_attrs(evsel_list, default_attrs) < 0)
 			return -1;
 	}
 

@@ -1139,21 +1139,21 @@ static int add_default_attributes(void)
 		return 0;
 
 	/* Append detailed run extra attributes: */
-	if (perf_evlist__add_attrs_array(evsel_list, detailed_attrs) < 0)
+	if (perf_evlist__add_default_attrs(evsel_list, detailed_attrs) < 0)
 		return -1;
 
 	if (detailed_run < 2)
 		return 0;
 
 	/* Append very detailed run extra attributes: */
-	if (perf_evlist__add_attrs_array(evsel_list, very_detailed_attrs) < 0)
+	if (perf_evlist__add_default_attrs(evsel_list, very_detailed_attrs) < 0)
 		return -1;
 
 	if (detailed_run < 3)
 		return 0;
 
 	/* Append very, very detailed run extra attributes: */
-	return perf_evlist__add_attrs_array(evsel_list, very_very_detailed_attrs);
+	return perf_evlist__add_default_attrs(evsel_list, very_very_detailed_attrs);
 }
 
 int cmd_stat(int argc, const char **argv, const char *prefix __used)

index 871b540..6bb0277 100644
@@ -787,7 +787,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
 		}
 
 		if (symbol_conf.use_callchain) {
-			err = callchain_append(he->callchain, &evsel->hists.callchain_cursor,
+			err = callchain_append(he->callchain, &callchain_cursor,
 					       sample->period);
 			if (err)
 				return;

index 4deea6a..34b1c46 100644
@@ -668,7 +668,7 @@ static int annotate_browser__run(struct annotate_browser *browser, int evidx,
 		"q/ESC/CTRL+C  Exit\n\n"
 		"->            Go to target\n"
 		"<-            Exit\n"
-		"h             Cycle thru hottest instructions\n"
+		"H             Cycle thru hottest instructions\n"
 		"j             Toggle showing jump to target arrows\n"
 		"J             Toggle showing number of jump sources on targets\n"
 		"n             Search next string\n"

index 9f7106a..3a6bff4 100644
@@ -18,6 +18,8 @@
 #include "util.h"
 #include "callchain.h"
 
+__thread struct callchain_cursor callchain_cursor;
+
 bool ip_callchain__valid(struct ip_callchain *chain,
 			 const union perf_event *event)
 {

index 7f9c0f1..3bdb407 100644
@@ -76,6 +76,8 @@ struct callchain_cursor {
 	struct callchain_cursor_node	*curr;
 };
 
+extern __thread struct callchain_cursor callchain_cursor;
+
 static inline void callchain_init(struct callchain_root *root)
 {
 	INIT_LIST_HEAD(&root->node.siblings);

index 4ac5f5a..7400fb3 100644
@@ -159,6 +159,17 @@ out_delete_partial_list:
 	return -1;
 }
 
+int __perf_evlist__add_default_attrs(struct perf_evlist *evlist,
+				     struct perf_event_attr *attrs, size_t nr_attrs)
+{
+	size_t i;
+
+	for (i = 0; i < nr_attrs; i++)
+		event_attr_init(attrs + i);
+
+	return perf_evlist__add_attrs(evlist, attrs, nr_attrs);
+}
+
 static int trace_event__id(const char *evname)
 {
 	char *filename, *colon;

@@ -263,7 +274,8 @@ void perf_evlist__disable(struct perf_evlist *evlist)
 	for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
 		list_for_each_entry(pos, &evlist->entries, node) {
 			for (thread = 0; thread < evlist->threads->nr; thread++)
-				ioctl(FD(pos, cpu, thread), PERF_EVENT_IOC_DISABLE);
+				ioctl(FD(pos, cpu, thread),
+				      PERF_EVENT_IOC_DISABLE, 0);
 		}
 	}
 }

@@ -276,7 +288,8 @@ void perf_evlist__enable(struct perf_evlist *evlist)
 	for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
 		list_for_each_entry(pos, &evlist->entries, node) {
 			for (thread = 0; thread < evlist->threads->nr; thread++)
-				ioctl(FD(pos, cpu, thread), PERF_EVENT_IOC_ENABLE);
+				ioctl(FD(pos, cpu, thread),
+				      PERF_EVENT_IOC_ENABLE, 0);
 		}
 	}
 }

index 58abb63..989bee9 100644
@@ -54,6 +54,8 @@ void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry);
 int perf_evlist__add_default(struct perf_evlist *evlist);
 int perf_evlist__add_attrs(struct perf_evlist *evlist,
 			   struct perf_event_attr *attrs, size_t nr_attrs);
+int __perf_evlist__add_default_attrs(struct perf_evlist *evlist,
+				     struct perf_event_attr *attrs, size_t nr_attrs);
 int perf_evlist__add_tracepoints(struct perf_evlist *evlist,
 				 const char *tracepoints[], size_t nr_tracepoints);
 int perf_evlist__set_tracepoints_handlers(struct perf_evlist *evlist,

@@ -62,6 +64,8 @@ int perf_evlist__set_tracepoints_handlers(struct perf_evlist *evlist,
 
 #define perf_evlist__add_attrs_array(evlist, array) \
 	perf_evlist__add_attrs(evlist, array, ARRAY_SIZE(array))
+#define perf_evlist__add_default_attrs(evlist, array) \
+	__perf_evlist__add_default_attrs(evlist, array, ARRAY_SIZE(array))
 
 #define perf_evlist__add_tracepoints_array(evlist, array) \
 	perf_evlist__add_tracepoints(evlist, array, ARRAY_SIZE(array))

index 91d1913..9f6cebd 100644
@@ -494,16 +494,24 @@ int perf_evsel__open_per_thread(struct perf_evsel *evsel,
 }
 
 static int perf_event__parse_id_sample(const union perf_event *event, u64 type,
-				       struct perf_sample *sample)
+				       struct perf_sample *sample,
+				       bool swapped)
 {
 	const u64 *array = event->sample.array;
+	union u64_swap u;
 
 	array += ((event->header.size -
 		   sizeof(event->header)) / sizeof(u64)) - 1;
 
 	if (type & PERF_SAMPLE_CPU) {
-		u32 *p = (u32 *)array;
-		sample->cpu = *p;
+		u.val64 = *array;
+		if (swapped) {
+			/* undo swap of u64, then swap on individual u32s */
+			u.val64 = bswap_64(u.val64);
+			u.val32[0] = bswap_32(u.val32[0]);
+		}
+
+		sample->cpu = u.val32[0];
 		array--;
 	}
 

@@ -523,9 +531,16 @@ static int perf_event__parse_id_sample(const union perf_event *event, u64 type,
 	}
 
 	if (type & PERF_SAMPLE_TID) {
-		u32 *p = (u32 *)array;
-		sample->pid = p[0];
-		sample->tid = p[1];
+		u.val64 = *array;
+		if (swapped) {
+			/* undo swap of u64, then swap on individual u32s */
+			u.val64 = bswap_64(u.val64);
+			u.val32[0] = bswap_32(u.val32[0]);
+			u.val32[1] = bswap_32(u.val32[1]);
+		}
+
+		sample->pid = u.val32[0];
+		sample->tid = u.val32[1];
 	}
 
 	return 0;

@@ -562,7 +577,7 @@ int perf_event__parse_sample(const union perf_event *event, u64 type,
 	if (event->header.type != PERF_RECORD_SAMPLE) {
 		if (!sample_id_all)
 			return 0;
-		return perf_event__parse_id_sample(event, type, data);
+		return perf_event__parse_id_sample(event, type, data, swapped);
 	}
 
 	array = event->sample.array;

index 1293b5e..514e2a4 100644
@@ -378,7 +378,7 @@ void hist_entry__free(struct hist_entry *he)
  * collapse the histogram
  */
 
-static bool hists__collapse_insert_entry(struct hists *hists,
+static bool hists__collapse_insert_entry(struct hists *hists __used,
 					 struct rb_root *root,
 					 struct hist_entry *he)
 {

@@ -397,8 +397,9 @@ static bool hists__collapse_insert_entry(struct hists *hists,
 			iter->period += he->period;
 			iter->nr_events += he->nr_events;
 			if (symbol_conf.use_callchain) {
-				callchain_cursor_reset(&hists->callchain_cursor);
-				callchain_merge(&hists->callchain_cursor, iter->callchain,
+				callchain_cursor_reset(&callchain_cursor);
+				callchain_merge(&callchain_cursor,
+						iter->callchain,
 						he->callchain);
 			}
 			hist_entry__free(he);

index cfc64e2..34bb556 100644
@@ -67,8 +67,6 @@ struct hists {
 	struct events_stats	stats;
 	u64			event_stream;
 	u16			col_len[HISTC_NR_COLS];
-	/* Best would be to reuse the session callchain cursor */
-	struct callchain_cursor	callchain_cursor;
 };
 
 struct hist_entry *__hists__add_entry(struct hists *self,

index 1915de2..3322b84 100644
@@ -57,6 +57,10 @@ void setup_pager(void)
 	}
 	if (!pager)
 		pager = getenv("PAGER");
+	if (!pager) {
+		if (!access("/usr/bin/pager", X_OK))
+			pager = "/usr/bin/pager";
+	}
 	if (!pager)
 		pager = "less";
 	else if (!*pager || !strcmp(pager, "cat"))

index 59dccc9..0dda25d 100644
@@ -2164,16 +2164,12 @@ int del_perf_probe_events(struct strlist *dellist)
 
 error:
 	if (kfd >= 0) {
-		if (namelist)
-			strlist__delete(namelist);
-
+		strlist__delete(namelist);
 		close(kfd);
 	}
 
 	if (ufd >= 0) {
-		if (unamelist)
-			strlist__delete(unamelist);
-
+		strlist__delete(unamelist);
 		close(ufd);
 	}
 

216 lines not on this page · raw message

index e2ba885..3e2e5ea 100644
@@ -323,6 +323,7 @@ struct dso *dso__new(const char *name)
 		dso->sorted_by_name = 0;
 		dso->has_build_id = 0;
 		dso->kernel = DSO_TYPE_USER;
+		dso->needs_swap = DSO_SWAP__UNSET;
 		INIT_LIST_HEAD(&dso->node);
 	}
 

@@ -1156,6 +1157,33 @@ static size_t elf_addr_to_index(Elf *elf, GElf_Addr addr)
 	return -1;
 }
 
+static int dso__swap_init(struct dso *dso, unsigned char eidata)
+{
+	static unsigned int const endian = 1;
+
+	dso->needs_swap = DSO_SWAP__NO;
+
+	switch (eidata) {
+	case ELFDATA2LSB:
+		/* We are big endian, DSO is little endian. */
+		if (*(unsigned char const *)&endian != 1)
+			dso->needs_swap = DSO_SWAP__YES;
+		break;
+
+	case ELFDATA2MSB:
+		/* We are little endian, DSO is big endian. */
+		if (*(unsigned char const *)&endian != 0)
+			dso->needs_swap = DSO_SWAP__YES;
+		break;
+
+	default:
+		pr_err("unrecognized DSO data encoding %d\n", eidata);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int dso__load_sym(struct dso *dso, struct map *map, const char *name,
 			 int fd, symbol_filter_t filter, int kmodule,
 			 int want_symtab)

@@ -1187,6 +1215,9 @@ static int dso__load_sym(struct dso *dso, struct map *map, const char *name,
 		goto out_elf_end;
 	}
 
+	if (dso__swap_init(dso, ehdr.e_ident[EI_DATA]))
+		goto out_elf_end;
+
 	/* Always reject images with a mismatched build-id: */
 	if (dso->has_build_id) {
 		u8 build_id[BUILD_ID_SIZE];

@@ -1272,7 +1303,7 @@ static int dso__load_sym(struct dso *dso, struct map *map, const char *name,
 		if (opdsec && sym.st_shndx == opdidx) {
 			u32 offset = sym.st_value - opdshdr.sh_addr;
 			u64 *opd = opddata->d_buf + offset;
-			sym.st_value = *opd;
+			sym.st_value = DSO__SWAP(dso, u64, *opd);
 			sym.st_shndx = elf_addr_to_index(elf, sym.st_value);
 		}
 

@@ -2786,8 +2817,11 @@ int machine__load_vmlinux_path(struct machine *machine, enum map_type type,
 
 struct map *dso__new_map(const char *name)
 {
+	struct map *map = NULL;
 	struct dso *dso = dso__new(name);
-	struct map *map = map__new2(0, dso, MAP__FUNCTION);
+
+	if (dso)
+		map = map__new2(0, dso, MAP__FUNCTION);
 
 	return map;
 }

index 5649d63..af0752b 100644
@@ -9,6 +9,7 @@
 #include <linux/list.h>
 #include <linux/rbtree.h>
 #include <stdio.h>
+#include <byteswap.h>
 
 #ifdef HAVE_CPLUS_DEMANGLE
 extern char *cplus_demangle(const char *, int);

@@ -160,11 +161,18 @@ enum dso_kernel_type {
 	DSO_TYPE_GUEST_KERNEL
 };
 
+enum dso_swap_type {
+	DSO_SWAP__UNSET,
+	DSO_SWAP__NO,
+	DSO_SWAP__YES,
+};
+
 struct dso {
 	struct list_head node;
 	struct rb_root	 symbols[MAP__NR_TYPES];
 	struct rb_root	 symbol_names[MAP__NR_TYPES];
 	enum dso_kernel_type	kernel;
+	enum dso_swap_type	needs_swap;
 	u8		 adjust_symbols:1;
 	u8		 has_build_id:1;
 	u8		 hit:1;

@@ -182,6 +190,28 @@ struct dso {
 	char		 name[0];
 };
 
+#define DSO__SWAP(dso, type, val)			\
+({							\
+	type ____r = val;				\
+	BUG_ON(dso->needs_swap == DSO_SWAP__UNSET);	\
+	if (dso->needs_swap == DSO_SWAP__YES) {		\
+		switch (sizeof(____r)) {		\
+		case 2:					\
+			____r = bswap_16(val);		\
+			break;				\
+		case 4:					\
+			____r = bswap_32(val);		\
+			break;				\
+		case 8:					\
+			____r = bswap_64(val);		\
+			break;				\
+		default:				\
+			BUG_ON(1);			\
+		}					\
+	}						\
+	____r;						\
+})
+
 struct dso *dso__new(const char *name);
 void dso__delete(struct dso *dso);