Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Fix error output of boot instance creation failure

   Currently if a boot instance creation fails, instead of printing out
   the name of the instance that failed, it prints "(null)". That is
   because it prints "cur_str" that had already been processed by
   strsep(). Print the saved name instead.

   While at it, print the error code of the failure.

 - Fix use-after-free for same named historgrams

   Histograms can be named so that they can be used in multiple events.
   But if the named histogram has a variable attached, the second event
   that uses the named histogram which duplicates it and needs to free
   the original after duplication leaves the old variable in place and
   still visible. If another histogram uses than variable, it will use
   the stale one which will try to reference the freed duplicate
   histogram and crash the kernel.

   Free the duplicate variables along with the duplicated histogram
   data.

 - Check return value of kthread_run() in event self test

   The events self tests uses a kthread for testing but does not check
   if it succeeded in creating a kthread. If the kthread creation were
   to fail, the code will still try to call kthread_stop() on the error
   returned.

 - Fix race between reading trace_pipe and updating subbuffer size

   If a user is reading the trace_pipe file at the same time they update
   the ring buffer sub-buffer size, can cause the trace_pipe read to
   read stale data. Add trace_access_lock() around updating the ring
   buffer sub-buffer size.

 - Fix eventfs_inode on failure path in creation of the events directory

   In the creation of the "events" directory, if after allocating the
   eventfs_inode a failure is detected, it calls cleanup_ei() which
   calls free_ei(). The free_ei() will test if eventfs_inode being freed
   has no children. It is a bug if it does. But on the failure case of
   the creation of the "events" directory, the children lists have not
   yet been initialized and the free will trigger a warning because
   list_empty() on an uninitialized list returns false.

   Move the initialization into init_ei() where it makes more sense and
   makes sure that a created eventfs_inode has its lists initialized
   upon creation.

 - Check return value of kthread_run() in ftrace direct sample code

   The sample code that shows how to use the ftrace direct calls does
   not test the return of kthread_run() to see if it succeeds. Return a
   failure if the kthread_run() doesn't succeed.

 - Clear user events state on fork in case of alloc failure

   On fork, the child gets a pointer to the parent's user events state.
   It makes a copy of it then updates the child's pointer to it. But if
   the allocation fails, the duplication function leaves the child with
   a pointer to its parent's descriptor. When the child cleans up its
   data, it will free the parent's descriptor while the parent is still
   using it.

   In the duplication function, set the child's user_event_mm to NULL
   before testing if the allocation succeeded, and when it exits it will
   not free the parent's descriptor.

 - Fix retry exhaustion in simple ring buffer reader swap

   simple_ring_buffer_swap_reader_page() starts with retry set to 8 and
   post-decrements it only after a failed link replacement. On the final
   attempt, a successful replacement leaves retry at zero, while a
   failed replacement leaves it at -1.

   But the check for success expects the retry value to be non-zero and
   exits with an error on zero. This is the opposite result. Fix it.

 - Fail nicely when the remote swap_reader_page() returns an error

   Currently, if the swap_reader_page() of a remote buffer fails, it
   triggers a WARN_ON_ONCE() and continues normally. Instead, have it
   exit with an error and a pr_warn() print instead of a full WARNING.

* tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  ring-buffer: Stop remote reader update when page swap fails
  tracing: Fix retry exhaustion in simple ring buffer reader swap
  tracing/user_events: Clear copied tracing state before fork duplication
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify
  eventfs: Initialize ei->children and ei->list in init_ei()
  tracing: Fix use-after-free in trace_pipe read on sub-buffer order change
  tracing: Fix crash passing ERR_PTR to kthread_stop()
  tracing: Fix use-after-free with same-name named triggers
  tracing: Fix logged instance name on creation failure

1 files changed, 318 insertions, 0 deletions

diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
new file mode 100644
index 000000000..fb0279810
--- /dev/null
+++ b/tools/perf/util/map.h
@@ -0,0 +1,318 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PERF_MAP_H
+#define __PERF_MAP_H
+
+#include <stdbool.h>
+#include <stdio.h>
+#include <string.h>
+
+#include <linux/refcount.h>
+#include <linux/types.h>
+
+#include <internal/rc_check.h>
+
+struct dso;
+struct maps;
+struct machine;
+
+enum mapping_type {
+	/* map__map_ip/map__unmap_ip are given as offsets in the DSO. */
+	MAPPING_TYPE__DSO,
+	/* map__map_ip/map__unmap_ip are just the given ip value. */
+	MAPPING_TYPE__IDENTITY,
+};
+
+DECLARE_RC_STRUCT(map) {
+	u64			start;
+	u64			end;
+	u64			pgoff;
+	u64			reloc;
+	struct dso		*dso;
+	refcount_t		refcnt;
+	u32			prot;
+	u32			flags;
+	enum mapping_type	mapping_type:8;
+	bool			erange_warned;
+	bool			priv;
+	bool			hit;
+};
+
+struct kmap;
+
+struct kmap *__map__kmap(struct map *map);
+struct kmap *map__kmap(struct map *map);
+struct maps *map__kmaps(struct map *map);
+
+static inline struct dso *map__dso(const struct map *map)
+{
+	return RC_CHK_ACCESS(map)->dso;
+}
+
+static inline u64 map__start(const struct map *map)
+{
+	return RC_CHK_ACCESS(map)->start;
+}
+
+static inline u64 map__end(const struct map *map)
+{
+	return RC_CHK_ACCESS(map)->end;
+}
+
+static inline u64 map__pgoff(const struct map *map)
+{
+	return RC_CHK_ACCESS(map)->pgoff;
+}
+
+static inline u64 map__reloc(const struct map *map)
+{
+	return RC_CHK_ACCESS(map)->reloc;
+}
+
+static inline u32 map__flags(const struct map *map)
+{
+	return RC_CHK_ACCESS(map)->flags;
+}
+
+static inline u32 map__prot(const struct map *map)
+{
+	return RC_CHK_ACCESS(map)->prot;
+}
+
+static inline bool map__priv(const struct map *map)
+{
+	return RC_CHK_ACCESS(map)->priv;
+}
+
+static inline bool map__hit(const struct map *map)
+{
+	return RC_CHK_ACCESS(map)->hit;
+}
+
+static inline refcount_t *map__refcnt(struct map *map)
+{
+	return &RC_CHK_ACCESS(map)->refcnt;
+}
+
+static inline bool map__erange_warned(struct map *map)
+{
+	return RC_CHK_ACCESS(map)->erange_warned;
+}
+
+static inline size_t map__size(const struct map *map)
+{
+	return map__end(map) - map__start(map);
+}
+
+/* ip -> dso rip */
+static inline u64 map__dso_map_ip(const struct map *map, u64 ip)
+{
+	return ip - map__start(map) + map__pgoff(map);
+}
+
+/* dso rip -> ip */
+static inline u64 map__dso_unmap_ip(const struct map *map, u64 rip)
+{
+	return rip + map__start(map) - map__pgoff(map);
+}
+
+static inline u64 map__map_ip(const struct map *map, u64 ip_or_rip)
+{
+	if ((RC_CHK_ACCESS(map)->mapping_type) == MAPPING_TYPE__DSO)
+		return map__dso_map_ip(map, ip_or_rip);
+	else
+		return ip_or_rip;
+}
+
+static inline u64 map__unmap_ip(const struct map *map, u64 ip_or_rip)
+{
+	if ((RC_CHK_ACCESS(map)->mapping_type) == MAPPING_TYPE__DSO)
+		return map__dso_unmap_ip(map, ip_or_rip);
+	else
+		return ip_or_rip;
+}
+
+/* rip/ip <-> addr suitable for passing to `objdump --start-address=` */
+u64 map__rip_2objdump(const struct map *map, u64 rip);
+
+/* objdump address -> memory address */
+u64 map__objdump_2mem(const struct map *map, u64 ip);
+
+/* objdump address -> rip */
+u64 map__objdump_2rip(const struct map *map, u64 ip);
+
+struct symbol;
+struct thread;
+
+/* map__for_each_symbol - iterate over the symbols in the given map
+ *
+ * @map: the 'struct map *' in which symbols are iterated
+ * @pos: the 'struct symbol *' to use as a loop cursor
+ * @n: the 'struct rb_node *' to use as a temporary storage
+ * Note: caller must ensure map->dso is not NULL (map is loaded).
+ */
+#define map__for_each_symbol(map, pos, n)	\
+	dso__for_each_symbol(map__dso(map), pos, n)
+
+/* map__for_each_symbol_with_name - iterate over the symbols in the given map
+ *                                  that have the given name
+ *
+ * @map: the 'struct map *' in which symbols are iterated
+ * @sym_name: the symbol name
+ * @pos: the 'struct symbol *' to use as a loop cursor
+ * @idx: the cursor index in the symbol names array
+ */
+#define __map__for_each_symbol_by_name(map, sym_name, pos, idx)		\
+	for (pos = map__find_symbol_by_name_idx(map, sym_name, &idx);	\
+	     pos &&						\
+	     !symbol__match_symbol_name(pos->name, sym_name,	\
+					SYMBOL_TAG_INCLUDE__DEFAULT_ONLY); \
+	     pos = dso__next_symbol_by_name(map__dso(map), &idx))
+
+#define map__for_each_symbol_by_name(map, sym_name, pos, idx)	\
+	__map__for_each_symbol_by_name(map, sym_name, (pos), idx)
+
+struct dso_id;
+
+struct map *map__new(struct machine *machine, u64 start, u64 len,
+		     u64 pgoff, const struct dso_id *id, u32 prot, u32 flags,
+		     char *filename, struct thread *thread);
+struct map *map__new2(u64 start, struct dso *dso);
+void map__delete(struct map *map);
+struct map *map__clone(struct map *map);
+
+static inline struct map *map__get(struct map *map)
+{
+	struct map *result;
+
+	if (RC_CHK_GET(result, map))
+		refcount_inc(map__refcnt(map));
+
+	return result;
+}
+
+void map__put(struct map *map);
+
+static inline void __map__zput(struct map **map)
+{
+	map__put(*map);
+	*map = NULL;
+}
+
+#define map__zput(map) __map__zput(&map)
+
+size_t map__fprintf(struct map *map, FILE *fp);
+size_t map__fprintf_dsoname(struct map *map, FILE *fp);
+size_t map__fprintf_dsoname_dsoff(struct map *map, bool print_off, u64 addr, FILE *fp);
+char *map__srcline(struct map *map, u64 addr, struct symbol *sym);
+int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix,
+			 FILE *fp);
+
+int map__load(struct map *map);
+struct symbol *map__find_symbol(struct map *map, u64 addr);
+struct symbol *map__find_symbol_by_name(struct map *map, const char *name);
+struct symbol *map__find_symbol_by_name_idx(struct map *map, const char *name, size_t *idx);
+void map__fixup_start(struct map *map);
+void map__fixup_end(struct map *map);
+
+int map__set_kallsyms_ref_reloc_sym(struct map *map, const char *symbol_name,
+				    u64 addr);
+
+bool __map__is_kernel(const struct map *map);
+bool __map__is_extra_kernel_map(const struct map *map);
+bool __map__is_bpf_prog(const struct map *map);
+bool __map__is_bpf_image(const struct map *map);
+bool __map__is_ool(const struct map *map);
+
+static inline bool __map__is_kmodule(const struct map *map)
+{
+	return !__map__is_kernel(map) && !__map__is_extra_kernel_map(map) &&
+	       !__map__is_bpf_prog(map) && !__map__is_ool(map) &&
+	       !__map__is_bpf_image(map);
+}
+
+bool map__has_symbols(const struct map *map);
+
+bool map__contains_symbol(const struct map *map, const struct symbol *sym);
+
+#define ENTRY_TRAMPOLINE_NAME "__entry_SYSCALL_64_trampoline"
+
+static inline bool is_entry_trampoline(const char *name)
+{
+	return !strcmp(name, ENTRY_TRAMPOLINE_NAME);
+}
+
+static inline bool is_bpf_image(const char *name)
+{
+	return strncmp(name, "bpf_trampoline_", sizeof("bpf_trampoline_") - 1) == 0 ||
+	       strncmp(name, "bpf_dispatcher_", sizeof("bpf_dispatcher_") - 1) == 0;
+}
+
+static inline int is_anon_memory(const char *filename)
+{
+	return !strcmp(filename, "//anon") ||
+	       !strncmp(filename, "/dev/zero", sizeof("/dev/zero") - 1) ||
+	       !strncmp(filename, "/anon_hugepage", sizeof("/anon_hugepage") - 1);
+}
+
+static inline int is_no_dso_memory(const char *filename)
+{
+	return !strncmp(filename, "[stack", 6) ||
+	       !strncmp(filename, "/SYSV", 5)  ||
+	       !strcmp(filename, "[heap]");
+}
+
+static inline void map__set_start(struct map *map, u64 start)
+{
+	RC_CHK_ACCESS(map)->start = start;
+}
+
+static inline void map__set_end(struct map *map, u64 end)
+{
+	RC_CHK_ACCESS(map)->end = end;
+}
+
+static inline void map__set_pgoff(struct map *map, u64 pgoff)
+{
+	RC_CHK_ACCESS(map)->pgoff = pgoff;
+}
+
+static inline void map__add_pgoff(struct map *map, u64 inc)
+{
+	RC_CHK_ACCESS(map)->pgoff += inc;
+}
+
+static inline void map__set_reloc(struct map *map, u64 reloc)
+{
+	RC_CHK_ACCESS(map)->reloc = reloc;
+}
+
+static inline void map__set_priv(struct map *map)
+{
+	RC_CHK_ACCESS(map)->priv = true;
+}
+
+static inline void map__set_hit(struct map *map)
+{
+	RC_CHK_ACCESS(map)->hit = true;
+}
+
+static inline void map__set_erange_warned(struct map *map)
+{
+	RC_CHK_ACCESS(map)->erange_warned = true;
+}
+
+static inline void map__set_dso(struct map *map, struct dso *dso)
+{
+	RC_CHK_ACCESS(map)->dso = dso;
+}
+
+static inline void map__set_mapping_type(struct map *map, enum mapping_type type)
+{
+	RC_CHK_ACCESS(map)->mapping_type = type;
+}
+
+static inline enum mapping_type map__mapping_type(struct map *map)
+{
+	return RC_CHK_ACCESS(map)->mapping_type;
+}
+#endif /* __PERF_MAP_H */