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, 232 insertions, 0 deletions

diff --git a/tools/perf/util/kvm-stat.h b/tools/perf/util/kvm-stat.h
new file mode 100644
index 000000000..8eee8d073
--- /dev/null
+++ b/tools/perf/util/kvm-stat.h
@@ -0,0 +1,232 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PERF_KVM_STAT_H
+#define __PERF_KVM_STAT_H
+
+#include "tool.h"
+#include "sort.h"
+#include "stat.h"
+#include "symbol.h"
+#include "record.h"
+
+#include <errno.h>
+#include <stdlib.h>
+#include <linux/zalloc.h>
+
+#define KVM_EVENT_NAME_LEN	40
+
+struct evsel;
+struct evlist;
+struct perf_session;
+
+struct event_key {
+	#define INVALID_KEY     (~0ULL)
+	u64 key;
+	int info;
+	struct exit_reasons_table *exit_reasons;
+};
+
+struct kvm_info {
+	char name[KVM_EVENT_NAME_LEN];
+	refcount_t refcnt;
+};
+
+struct kvm_event_stats {
+	u64 time;
+	struct stats stats;
+};
+
+struct perf_kvm_stat;
+
+struct kvm_event {
+	struct list_head hash_entry;
+
+	struct perf_kvm_stat *perf_kvm;
+	struct event_key key;
+
+	struct kvm_event_stats total;
+
+	#define DEFAULT_VCPU_NUM 8
+	int max_vcpu;
+	struct kvm_event_stats *vcpu;
+
+	struct hist_entry he;
+};
+
+struct child_event_ops {
+	void (*get_key)(struct perf_sample *sample,
+			struct event_key *key);
+	const char *name;
+};
+
+struct kvm_events_ops {
+	bool (*is_begin_event)(struct perf_sample *sample,
+			       struct event_key *key);
+	bool (*is_end_event)(struct perf_sample *sample, struct event_key *key);
+	const struct child_event_ops *child_ops;
+	void (*decode_key)(struct perf_kvm_stat *kvm, struct event_key *key,
+			   char *decode);
+	const char *name;
+};
+
+struct exit_reasons_table {
+	u64 exit_code;
+	const char *reason;
+};
+
+struct perf_kvm_stat {
+	struct perf_tool    tool;
+	struct record_opts  opts;
+	struct evlist  *evlist;
+	struct perf_session *session;
+
+	const char *file_name;
+	const char *report_event;
+	const char *sort_key;
+	int trace_vcpu;
+
+	/* Used when process events */
+	struct addr_location al;
+
+	struct exit_reasons_table *exit_reasons;
+	const char *exit_reasons_isa;
+
+	const struct kvm_events_ops *events_ops;
+
+	u64 total_time;
+	u64 total_count;
+	u64 lost_events;
+	u64 duration;
+
+	struct intlist *pid_list;
+
+	int timerfd;
+	unsigned int display_time;
+	bool live;
+	bool force;
+	bool use_stdio;
+};
+
+struct kvm_reg_events_ops {
+	const char *name;
+	const struct kvm_events_ops *ops;
+};
+
+#ifdef HAVE_LIBTRACEEVENT
+
+void exit_event_get_key(struct perf_sample *sample,
+			struct event_key *key);
+bool exit_event_begin(struct perf_sample *sample,
+		      struct event_key *key);
+bool exit_event_end(struct perf_sample *sample,
+		    struct event_key *key);
+void exit_event_decode_key(struct perf_kvm_stat *kvm,
+			   struct event_key *key,
+			   char *decode);
+
+bool kvm_exit_event(struct evsel *evsel);
+bool kvm_entry_event(struct evsel *evsel);
+
+#define define_exit_reasons_table(name, symbols)	\
+	static struct exit_reasons_table name[] = {	\
+		symbols, { -1, NULL }			\
+	}
+
+/*
+ * arch specific callbacks and data structures
+ */
+int setup_kvm_events_tp(struct perf_kvm_stat *kvm, uint16_t e_machine);
+int __setup_kvm_events_tp_powerpc(struct perf_kvm_stat *kvm);
+
+int cpu_isa_init(struct perf_kvm_stat *kvm, uint16_t e_machine, const char *cpuid);
+int __cpu_isa_init_arm64(struct perf_kvm_stat *kvm);
+int __cpu_isa_init_loongarch(struct perf_kvm_stat *kvm);
+int __cpu_isa_init_powerpc(struct perf_kvm_stat *kvm);
+int __cpu_isa_init_riscv(struct perf_kvm_stat *kvm);
+int __cpu_isa_init_s390(struct perf_kvm_stat *kvm, const char *cpuid);
+int __cpu_isa_init_x86(struct perf_kvm_stat *kvm, const char *cpuid);
+
+const char *vcpu_id_str(uint16_t e_machine);
+const char *kvm_exit_reason(uint16_t e_machine);
+const char *kvm_entry_trace(uint16_t e_machine);
+const char *kvm_exit_trace(uint16_t e_machine);
+
+const char * const *kvm_events_tp(uint16_t e_machine);
+const char * const *__kvm_events_tp_arm64(void);
+const char * const *__kvm_events_tp_loongarch(void);
+const char * const *__kvm_events_tp_powerpc(void);
+const char * const *__kvm_events_tp_riscv(void);
+const char * const *__kvm_events_tp_s390(void);
+const char * const *__kvm_events_tp_x86(void);
+
+const struct kvm_reg_events_ops *kvm_reg_events_ops(uint16_t e_machine);
+const struct kvm_reg_events_ops *__kvm_reg_events_ops_arm64(void);
+const struct kvm_reg_events_ops *__kvm_reg_events_ops_loongarch(void);
+const struct kvm_reg_events_ops *__kvm_reg_events_ops_powerpc(void);
+const struct kvm_reg_events_ops *__kvm_reg_events_ops_riscv(void);
+const struct kvm_reg_events_ops *__kvm_reg_events_ops_s390(void);
+const struct kvm_reg_events_ops *__kvm_reg_events_ops_x86(void);
+
+const char * const *kvm_skip_events(uint16_t e_machine);
+const char * const *__kvm_skip_events_arm64(void);
+const char * const *__kvm_skip_events_loongarch(void);
+const char * const *__kvm_skip_events_powerpc(void);
+const char * const *__kvm_skip_events_riscv(void);
+const char * const *__kvm_skip_events_s390(void);
+const char * const *__kvm_skip_events_x86(void);
+
+bool kvm_need_default_arch_event(uint16_t e_machine, int argc, const char **argv);
+int kvm_add_default_arch_event(uint16_t e_machine, int *argc, const char **argv);
+int __kvm_add_default_arch_event_powerpc(int *argc, const char **argv);
+int __kvm_add_default_arch_event_x86(int *argc, const char **argv);
+
+#else /* !HAVE_LIBTRACEEVENT */
+
+static inline bool kvm_need_default_arch_event(uint16_t e_machine __maybe_unused,
+					       int argc __maybe_unused,
+					       const char **argv __maybe_unused)
+{
+	return false;
+}
+
+static inline int kvm_add_default_arch_event(uint16_t e_machine __maybe_unused,
+					     int *argc __maybe_unused,
+					     const char **argv __maybe_unused)
+{
+	return 0;
+}
+
+#endif /* HAVE_LIBTRACEEVENT */
+
+static inline struct kvm_info *kvm_info__get(struct kvm_info *ki)
+{
+	if (ki)
+		refcount_inc(&ki->refcnt);
+	return ki;
+}
+
+static inline void kvm_info__put(struct kvm_info *ki)
+{
+	if (ki && refcount_dec_and_test(&ki->refcnt))
+		free(ki);
+}
+
+static inline void __kvm_info__zput(struct kvm_info **ki)
+{
+	kvm_info__put(*ki);
+	*ki = NULL;
+}
+
+#define kvm_info__zput(ki) __kvm_info__zput(&ki)
+
+static inline struct kvm_info *kvm_info__new(void)
+{
+	struct kvm_info *ki;
+
+	ki = zalloc(sizeof(*ki));
+	if (ki)
+		refcount_set(&ki->refcnt, 1);
+
+	return ki;
+}
+
+#endif /* __PERF_KVM_STAT_H */