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, 245 insertions, 0 deletions

diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
new file mode 100644
index 000000000..7acca39b4
--- /dev/null
+++ b/tools/perf/util/env.h
@@ -0,0 +1,245 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PERF_ENV_H
+#define __PERF_ENV_H
+
+#include <linux/types.h>
+#include <linux/rbtree.h>
+#include "cpumap.h"
+#include "rwsem.h"
+#include "mutex.h"
+
+struct perf_cpu_map;
+
+struct cpu_topology_map {
+	int	socket_id;
+	int	die_id;
+	int	cluster_id;
+	int	core_id;
+};
+
+struct cpu_cache_level {
+	u32	level;
+	u32	line_size;
+	u32	sets;
+	u32	ways;
+	char	*type;
+	char	*size;
+	char	*map;
+};
+
+struct numa_node {
+	u32		 node;
+	u64		 mem_total;
+	u64		 mem_free;
+	struct perf_cpu_map	*map;
+};
+
+struct memory_node {
+	u64		 node;
+	u64		 size;
+	unsigned long	*set;
+};
+
+struct hybrid_node {
+	char	*pmu_name;
+	char	*cpus;
+};
+
+struct pmu_caps {
+	int		nr_caps;
+	unsigned int    max_branches;
+	unsigned int	br_cntr_nr;
+	unsigned int	br_cntr_width;
+
+	char            **caps;
+	char            *pmu_name;
+};
+
+struct domain_info {
+	u32	domain;
+	char	*dname;
+	char	*cpumask;
+	char	*cpulist;
+};
+
+struct cpu_domain_map {
+	u32			cpu;
+	u32			nr_domains;
+	struct domain_info	**domains;
+};
+
+struct perf_env {
+	char			*hostname;
+	char			*os_release;
+	char			*version;
+	char			*arch;
+	/* e_machine expanded from 16 to 32-bits for alignment. */
+	u32			e_machine;
+	u32			e_flags;
+	int			nr_cpus_online;
+	int			nr_cpus_avail;
+	char			*cpu_desc;
+	char			*cpuid;
+	unsigned long long	total_mem;
+	unsigned int		msr_pmu_type;
+	unsigned int		max_branches;
+	unsigned int		br_cntr_nr;
+	unsigned int		br_cntr_width;
+	unsigned int		schedstat_version;
+	unsigned int		max_sched_domains;
+	int			kernel_is_64_bit;
+
+	int			nr_cmdline;
+	int			nr_sibling_cores;
+	int			nr_sibling_dies;
+	int			nr_sibling_threads;
+	int			nr_numa_nodes;
+	int			nr_memory_nodes;
+	int			nr_pmu_mappings;
+	int			nr_groups;
+	int			nr_cpu_pmu_caps;
+	int			nr_hybrid_nodes;
+	int			nr_pmus_with_caps;
+	char			*cmdline;
+	const char		**cmdline_argv;
+	char			*sibling_cores;
+	char			*sibling_dies;
+	char			*sibling_threads;
+	char			*pmu_mappings;
+	char			**cpu_pmu_caps;
+	struct cpu_topology_map	*cpu;
+	struct cpu_cache_level	*caches;
+	struct cpu_domain_map	**cpu_domain;
+	int			 caches_cnt;
+	unsigned int		cln_size;
+	u32			comp_ratio;
+	u32			comp_ver;
+	u32			comp_type;
+	u32			comp_level;
+	u32			comp_mmap_len;
+	struct numa_node	*numa_nodes;
+	struct memory_node	*memory_nodes;
+	unsigned long long	 memory_bsize;
+	struct hybrid_node	*hybrid_nodes;
+	struct pmu_caps		*pmu_caps;
+#ifdef HAVE_LIBBPF_SUPPORT
+	/*
+	 * bpf_info_lock protects bpf rbtrees. This is needed because the
+	 * trees are accessed by different threads in perf-top
+	 */
+	struct {
+		struct rw_semaphore	lock;
+		struct rb_root		infos;
+		u32			infos_cnt;
+		struct rb_root		btfs;
+		u32			btfs_cnt;
+	} bpf_progs;
+#endif // HAVE_LIBBPF_SUPPORT
+	/* same reason as above (for perf-top) */
+	struct {
+		struct rw_semaphore	lock;
+		struct rb_root		tree;
+	} cgroups;
+
+	/* For fast cpu to numa node lookup via perf_env__numa_node */
+	int			*numa_map;
+	int			 nr_numa_map;
+
+	/* For real clock time reference. */
+	struct {
+		u64	tod_ns;
+		u64	clockid_ns;
+		u64     clockid_res_ns;
+		int	clockid;
+		/*
+		 * enabled is valid for report mode, and is true if above
+		 * values are set, it's set in process_clock_data
+		 */
+		bool	enabled;
+	} clock;
+	/* Protects lazy environment initialization (e.g. os_release, e_machine). */
+	struct mutex		lock;
+};
+
+enum perf_compress_type {
+	PERF_COMP_NONE = 0,
+	PERF_COMP_ZSTD,
+	PERF_COMP_MAX
+};
+
+struct bpf_prog_info_node;
+struct btf_node;
+
+int perf_env__read_core_pmu_caps(struct perf_env *env);
+void free_cpu_domain_info(struct cpu_domain_map **cd_map, u32 schedstat_version, u32 nr);
+void perf_env__exit(struct perf_env *env);
+
+int perf_env__kernel_is_64_bit(struct perf_env *env);
+bool perf_arch_is_big_endian(const char *arch);
+const char *perf_env__os_release(struct perf_env *env);
+
+int perf_env__set_cmdline(struct perf_env *env, int argc, const char *argv[]);
+
+int perf_env__read_cpuid(struct perf_env *env);
+int perf_env__read_pmu_mappings(struct perf_env *env);
+int perf_env__nr_pmu_mappings(struct perf_env *env);
+const char *perf_env__pmu_mappings(struct perf_env *env);
+
+int perf_env__read_cpu_topology_map(struct perf_env *env);
+
+/*
+ * Safe accessor for env->cpu[] topology array.  env->cpu can be NULL when
+ * reading old-format perf.data that predates topology information —
+ * process_cpu_topology() in header.c frees it while nr_cpus_avail remains
+ * set, so callers must not index env->cpu[] without this check.
+ */
+static inline struct cpu_topology_map *
+perf_env__get_cpu_topology(struct perf_env *env, struct perf_cpu cpu)
+{
+	if (env->cpu && cpu.cpu >= 0 && cpu.cpu < env->nr_cpus_avail)
+		return &env->cpu[cpu.cpu];
+	return NULL;
+}
+
+void cpu_cache_level__free(struct cpu_cache_level *cache);
+
+uint16_t perf_env__e_machine_nocache(struct perf_env *env, uint32_t *e_flags);
+uint16_t perf_env__e_machine(struct perf_env *env, uint32_t *e_flags);
+const char *perf_env__arch(struct perf_env *env);
+const char *perf_env__arch_strerrno(uint16_t e_machine, int err);
+const char *perf_env__cpuid(struct perf_env *env);
+int perf_env__nr_cpus_avail(struct perf_env *env);
+
+void perf_env__init(struct perf_env *env);
+#ifdef HAVE_LIBBPF_SUPPORT
+bool __perf_env__insert_bpf_prog_info(struct perf_env *env,
+				      struct bpf_prog_info_node *info_node);
+bool perf_env__insert_bpf_prog_info(struct perf_env *env,
+				    struct bpf_prog_info_node *info_node);
+struct bpf_prog_info_node *perf_env__find_bpf_prog_info(struct perf_env *env,
+							__u32 prog_id);
+void perf_env__iterate_bpf_prog_info(struct perf_env *env,
+				     void (*cb)(struct bpf_prog_info_node *node,
+						void *data),
+				     void *data);
+bool perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node);
+bool __perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node);
+struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id);
+struct btf_node *__perf_env__find_btf(struct perf_env *env, __u32 btf_id);
+#endif // HAVE_LIBBPF_SUPPORT
+
+int perf_env__numa_node(struct perf_env *env, struct perf_cpu cpu);
+char *perf_env__find_pmu_cap(struct perf_env *env, const char *pmu_name,
+			     const char *cap);
+
+bool perf_env__has_pmu_mapping(struct perf_env *env, const char *pmu_name);
+void perf_env__find_br_cntr_info(struct perf_env *env,
+				 unsigned int *nr,
+				 unsigned int *width);
+
+bool x86__is_amd_cpu(void);
+bool perf_env__is_x86_amd_cpu(struct perf_env *env);
+bool x86__is_intel_cpu(void);
+bool perf_env__is_x86_intel_cpu(struct perf_env *env);
+
+#endif /* __PERF_ENV_H */