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, 437 insertions, 0 deletions

diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
new file mode 100644
index 000000000..2ea83fdf8
--- /dev/null
+++ b/tools/perf/util/event.h
@@ -0,0 +1,437 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PERF_RECORD_H
+#define __PERF_RECORD_H
+/*
+ * The linux/stddef.h isn't need here, but is needed for __always_inline used
+ * in files included from uapi/linux/perf_event.h such as
+ * /usr/include/linux/swab.h and /usr/include/linux/byteorder/little_endian.h,
+ * detected in at least musl libc, used in Alpine Linux. -acme
+ */
+#include <stdio.h>
+#include <linux/stddef.h>
+#include <perf/event.h>
+#include <linux/types.h>
+
+struct dso;
+struct machine;
+struct perf_event_attr;
+struct perf_sample;
+
+#ifdef __LP64__
+/*
+ * /usr/include/inttypes.h uses just 'lu' for PRIu64, but we end up defining
+ * __u64 as long long unsigned int, and then -Werror=format= kicks in and
+ * complains of the mismatched types, so use these two special extra PRI
+ * macros to overcome that.
+ */
+#define PRI_lu64 "l" PRIu64
+#define PRI_lx64 "l" PRIx64
+#define PRI_ld64 "l" PRId64
+#else
+#define PRI_lu64 PRIu64
+#define PRI_lx64 PRIx64
+#define PRI_ld64 PRId64
+#endif
+
+#define PERF_SAMPLE_MASK				\
+	(PERF_SAMPLE_IP | PERF_SAMPLE_TID |		\
+	 PERF_SAMPLE_TIME | PERF_SAMPLE_ADDR |		\
+	PERF_SAMPLE_ID | PERF_SAMPLE_STREAM_ID |	\
+	 PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD |		\
+	 PERF_SAMPLE_IDENTIFIER)
+
+/* perf sample has 16 bits size limit */
+#define PERF_SAMPLE_MAX_SIZE (1 << 16)
+
+struct ip_callchain {
+	u64 nr;
+	u64 ips[];
+};
+
+struct branch_stack;
+
+enum {
+	PERF_IP_FLAG_BRANCH		= 1ULL << 0,
+	PERF_IP_FLAG_CALL		= 1ULL << 1,
+	PERF_IP_FLAG_RETURN		= 1ULL << 2,
+	PERF_IP_FLAG_CONDITIONAL	= 1ULL << 3,
+	PERF_IP_FLAG_SYSCALLRET		= 1ULL << 4,
+	PERF_IP_FLAG_ASYNC		= 1ULL << 5,
+	PERF_IP_FLAG_INTERRUPT		= 1ULL << 6,
+	PERF_IP_FLAG_TX_ABORT		= 1ULL << 7,
+	PERF_IP_FLAG_TRACE_BEGIN	= 1ULL << 8,
+	PERF_IP_FLAG_TRACE_END		= 1ULL << 9,
+	PERF_IP_FLAG_IN_TX		= 1ULL << 10,
+	PERF_IP_FLAG_VMENTRY		= 1ULL << 11,
+	PERF_IP_FLAG_VMEXIT		= 1ULL << 12,
+	PERF_IP_FLAG_INTR_DISABLE	= 1ULL << 13,
+	PERF_IP_FLAG_INTR_TOGGLE	= 1ULL << 14,
+	PERF_IP_FLAG_BRANCH_MISS	= 1ULL << 15,
+	PERF_IP_FLAG_NOT_TAKEN		= 1ULL << 16,
+};
+
+#define PERF_IP_FLAG_CHARS "bcrosyiABExghDtmn"
+
+#define PERF_ADDITIONAL_STATE_MASK	\
+	(PERF_IP_FLAG_IN_TX |		\
+	 PERF_IP_FLAG_INTR_DISABLE |	\
+	 PERF_IP_FLAG_INTR_TOGGLE)
+
+#define PERF_BRANCH_MASK		(\
+	PERF_IP_FLAG_BRANCH		|\
+	PERF_IP_FLAG_CALL		|\
+	PERF_IP_FLAG_RETURN		|\
+	PERF_IP_FLAG_CONDITIONAL	|\
+	PERF_IP_FLAG_SYSCALLRET		|\
+	PERF_IP_FLAG_ASYNC		|\
+	PERF_IP_FLAG_INTERRUPT		|\
+	PERF_IP_FLAG_TX_ABORT		|\
+	PERF_IP_FLAG_TRACE_BEGIN	|\
+	PERF_IP_FLAG_TRACE_END		|\
+	PERF_IP_FLAG_VMENTRY		|\
+	PERF_IP_FLAG_VMEXIT)
+
+#define PERF_IP_FLAG_BRANCH_EVENT_MASK	\
+	(PERF_IP_FLAG_BRANCH_MISS |	\
+	 PERF_IP_FLAG_NOT_TAKEN)
+
+#define PERF_MEM_DATA_SRC_NONE \
+	(PERF_MEM_S(OP, NA) |\
+	 PERF_MEM_S(LVL, NA) |\
+	 PERF_MEM_S(SNOOP, NA) |\
+	 PERF_MEM_S(LOCK, NA) |\
+	 PERF_MEM_S(TLB, NA) |\
+	 PERF_MEM_S(LVLNUM, NA))
+
+/* Attribute type for custom synthesized events */
+#define PERF_TYPE_SYNTH		(INT_MAX + 1U)
+
+/* Attribute config for custom synthesized events */
+enum perf_synth_id {
+	PERF_SYNTH_INTEL_PTWRITE,
+	PERF_SYNTH_INTEL_MWAIT,
+	PERF_SYNTH_INTEL_PWRE,
+	PERF_SYNTH_INTEL_EXSTOP,
+	PERF_SYNTH_INTEL_PWRX,
+	PERF_SYNTH_INTEL_CBR,
+	PERF_SYNTH_INTEL_PSB,
+	PERF_SYNTH_INTEL_EVT,
+	PERF_SYNTH_INTEL_IFLAG_CHG,
+	PERF_SYNTH_POWERPC_VPA_DTL,
+};
+
+/*
+ * Raw data formats for synthesized events. Note that 4 bytes of padding are
+ * present to match the 'size' member of PERF_SAMPLE_RAW data which is always
+ * 8-byte aligned. That means we must dereference raw_data with an offset of 4.
+ * Refer perf_sample__synth_ptr() and perf_synth__raw_data().  It also means the
+ * structure sizes are 4 bytes bigger than the raw_size, refer
+ * perf_synth__raw_size().
+ */
+
+struct perf_synth_intel_ptwrite {
+	u32 padding;
+	union {
+		struct {
+			u32	ip		:  1,
+				reserved	: 31;
+		};
+		u32	flags;
+	};
+	u64	payload;
+};
+
+struct perf_synth_intel_mwait {
+	u32 padding;
+	u32 reserved;
+	union {
+		struct {
+			u64	hints		:  8,
+				reserved1	: 24,
+				extensions	:  2,
+				reserved2	: 30;
+		};
+		u64	payload;
+	};
+};
+
+struct perf_synth_intel_pwre {
+	u32 padding;
+	u32 reserved;
+	union {
+		struct {
+			u64	reserved1	:  7,
+				hw		:  1,
+				subcstate	:  4,
+				cstate		:  4,
+				reserved2	: 48;
+		};
+		u64	payload;
+	};
+};
+
+struct perf_synth_intel_exstop {
+	u32 padding;
+	union {
+		struct {
+			u32	ip		:  1,
+				reserved	: 31;
+		};
+		u32	flags;
+	};
+};
+
+struct perf_synth_intel_pwrx {
+	u32 padding;
+	u32 reserved;
+	union {
+		struct {
+			u64	deepest_cstate	:  4,
+				last_cstate	:  4,
+				wake_reason	:  4,
+				reserved1	: 52;
+		};
+		u64	payload;
+	};
+};
+
+struct perf_synth_intel_cbr {
+	u32 padding;
+	union {
+		struct {
+			u32	cbr		:  8,
+				reserved1	:  8,
+				max_nonturbo	:  8,
+				reserved2	:  8;
+		};
+		u32	flags;
+	};
+	u32 freq;
+	u32 reserved3;
+};
+
+struct perf_synth_intel_psb {
+	u32 padding;
+	u32 reserved;
+	u64 offset;
+};
+
+struct perf_synth_intel_evd {
+	union {
+		struct {
+			u8	evd_type;
+			u8	reserved[7];
+		};
+		u64	et;
+	};
+	u64	payload;
+};
+
+/* Intel PT Event Trace */
+struct perf_synth_intel_evt {
+	u32 padding;
+	union {
+		struct {
+			u32	type		:  5,
+				reserved	:  2,
+				ip		:  1,
+				vector		:  8,
+				evd_cnt		: 16;
+		};
+		u32	cfe;
+	};
+	struct perf_synth_intel_evd evd[0];
+};
+
+struct perf_synth_intel_iflag_chg {
+	u32 padding;
+	union {
+		struct {
+			u32	iflag		:  1,
+				via_branch	:  1;
+		};
+		u32	flags;
+	};
+	u64	branch_ip; /* If via_branch */
+};
+
+/*
+ * The powerpc VPA DTL entries are of below format
+ */
+struct powerpc_vpadtl_entry {
+	u8      dispatch_reason;
+	u8      preempt_reason;
+	u16     processor_id;
+	u32     enqueue_to_dispatch_time;
+	u32     ready_to_enqueue_time;
+	u32     waiting_to_ready_time;
+	u64     timebase;
+	u64     fault_addr;
+	u64     srr0;
+	u64     srr1;
+};
+
+extern const char *dispatch_reasons[11];
+extern const char *preempt_reasons[10];
+
+static inline void *perf_synth__raw_data(void *p)
+{
+	return p + 4;
+}
+
+#define perf_synth__raw_size(d) (sizeof(d) - 4)
+
+#define perf_sample__bad_synth_size(s, d) ((s)->raw_size < sizeof(d) - 4)
+
+enum {
+	PERF_STAT_ROUND_TYPE__INTERVAL	= 0,
+	PERF_STAT_ROUND_TYPE__FINAL	= 1,
+};
+
+void perf_event__print_totals(void);
+
+struct perf_cpu_map;
+struct perf_record_stat_config;
+struct perf_stat_config;
+struct perf_tool;
+
+void perf_event__read_stat_config(struct perf_stat_config *config,
+				  struct perf_record_stat_config *event);
+
+int perf_event__process_comm(const struct perf_tool *tool,
+			     union perf_event *event,
+			     struct perf_sample *sample,
+			     struct machine *machine);
+int perf_event__process_lost(const struct perf_tool *tool,
+			     union perf_event *event,
+			     struct perf_sample *sample,
+			     struct machine *machine);
+int perf_event__process_lost_samples(const struct perf_tool *tool,
+				     union perf_event *event,
+				     struct perf_sample *sample,
+				     struct machine *machine);
+int perf_event__process_aux(const struct perf_tool *tool,
+			    union perf_event *event,
+			    struct perf_sample *sample,
+			    struct machine *machine);
+int perf_event__process_itrace_start(const struct perf_tool *tool,
+				     union perf_event *event,
+				     struct perf_sample *sample,
+				     struct machine *machine);
+int perf_event__process_aux_output_hw_id(const struct perf_tool *tool,
+					 union perf_event *event,
+					 struct perf_sample *sample,
+					 struct machine *machine);
+int perf_event__process_switch(const struct perf_tool *tool,
+			       union perf_event *event,
+			       struct perf_sample *sample,
+			       struct machine *machine);
+int perf_event__process_namespaces(const struct perf_tool *tool,
+				   union perf_event *event,
+				   struct perf_sample *sample,
+				   struct machine *machine);
+int perf_event__process_cgroup(const struct perf_tool *tool,
+			       union perf_event *event,
+			       struct perf_sample *sample,
+			       struct machine *machine);
+int perf_event__process_mmap(const struct perf_tool *tool,
+			     union perf_event *event,
+			     struct perf_sample *sample,
+			     struct machine *machine);
+int perf_event__process_mmap2(const struct perf_tool *tool,
+			     union perf_event *event,
+			     struct perf_sample *sample,
+			     struct machine *machine);
+int perf_event__process_fork(const struct perf_tool *tool,
+			     union perf_event *event,
+			     struct perf_sample *sample,
+			     struct machine *machine);
+int perf_event__process_exit(const struct perf_tool *tool,
+			     union perf_event *event,
+			     struct perf_sample *sample,
+			     struct machine *machine);
+int perf_event__exit_del_thread(const struct perf_tool *tool,
+				union perf_event *event,
+				struct perf_sample *sample,
+				struct machine *machine);
+int perf_event__process_ksymbol(const struct perf_tool *tool,
+				union perf_event *event,
+				struct perf_sample *sample,
+				struct machine *machine);
+int perf_event__process_bpf(const struct perf_tool *tool,
+			    union perf_event *event,
+			    struct perf_sample *sample,
+			    struct machine *machine);
+int perf_event__process_text_poke(const struct perf_tool *tool,
+				  union perf_event *event,
+				  struct perf_sample *sample,
+				  struct machine *machine);
+int perf_event__process(const struct perf_tool *tool,
+			union perf_event *event,
+			struct perf_sample *sample,
+			struct machine *machine);
+
+bool is_bts_event(struct perf_event_attr *attr);
+bool sample_addr_correlates_sym(struct perf_event_attr *attr);
+
+const char *perf_event__name(unsigned int id);
+
+size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_task(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_aux(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_aux_output_hw_id(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_switch(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_thread_map(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_cpu_map(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_namespaces(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_cgroup(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_ksymbol(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_bpf(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_bpf_metadata(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_text_poke(union perf_event *event, struct machine *machine,FILE *fp);
+size_t perf_event__fprintf_schedstat_cpu(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_schedstat_domain(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf(union perf_event *event, struct machine *machine, FILE *fp);
+
+int kallsyms__get_function_start(const char *kallsyms_filename,
+				 const char *symbol_name, u64 *addr);
+int kallsyms__get_symbol_start(const char *kallsyms_filename,
+			       const char *symbol_name, u64 *addr);
+
+void event_attr_init(struct perf_event_attr *attr);
+
+int perf_event_paranoid(void);
+bool perf_event_paranoid_check(int max_level);
+
+extern int sysctl_perf_event_max_stack;
+extern int sysctl_perf_event_max_contexts_per_stack;
+extern unsigned int proc_map_timeout;
+
+#define PAGE_SIZE_NAME_LEN	32
+char *get_page_size_name(u64 size, char *str);
+
+static inline bool perf_event_header__cpumode_is_guest(u8 cpumode)
+{
+	return cpumode == PERF_RECORD_MISC_GUEST_KERNEL ||
+	       cpumode == PERF_RECORD_MISC_GUEST_USER;
+}
+
+static inline bool perf_event_header__misc_is_guest(u16 misc)
+{
+	return perf_event_header__cpumode_is_guest(misc & PERF_RECORD_MISC_CPUMODE_MASK);
+}
+
+static inline bool perf_event_header__is_guest(const struct perf_event_header *header)
+{
+	return perf_event_header__misc_is_guest(header->misc);
+}
+
+static inline bool perf_event__is_guest(const union perf_event *event)
+{
+	return perf_event_header__is_guest(&event->header);
+}
+
+#endif /* __PERF_RECORD_H */