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

18 files changed, 1633 insertions, 0 deletions

diff --git a/tools/lib/api/Build b/tools/lib/api/Build
new file mode 100644
index 000000000..6e2373db5
--- /dev/null
+++ b/tools/lib/api/Build
@@ -0,0 +1,9 @@
+libapi-y += fd/
+libapi-y += fs/
+libapi-y += cpu.o
+libapi-y += debug.o
+libapi-y += str_error_r.o
+
+$(OUTPUT)str_error_r.o: ../str_error_r.c FORCE
+	$(call rule_mkdir)
+	$(call if_changed_dep,cc_o_c)
diff --git a/tools/lib/api/Makefile b/tools/lib/api/Makefile
new file mode 100644
index 000000000..a228fdb5a
--- /dev/null
+++ b/tools/lib/api/Makefile
@@ -0,0 +1,125 @@
+# SPDX-License-Identifier: GPL-2.0
+include ../../scripts/Makefile.include
+include ../../scripts/utilities.mak		# QUIET_CLEAN
+
+ifeq ($(srctree),)
+srctree := $(patsubst %/,%,$(dir $(CURDIR)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+#$(info Determined 'srctree' to be $(srctree))
+endif
+
+MAKEFLAGS += --no-print-directory
+
+INSTALL = install
+
+
+# Use DESTDIR for installing into a different root directory.
+# This is useful for building a package. The program will be
+# installed in this directory as if it was the root directory.
+# Then the build tool can move it later.
+DESTDIR ?=
+DESTDIR_SQ = '$(subst ','\'',$(DESTDIR))'
+
+LIBFILE = $(OUTPUT)libapi.a
+
+CFLAGS := $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
+CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -U_FORTIFY_SOURCE -fPIC
+
+ifeq ($(DEBUG),0)
+  CFLAGS += -O3
+endif
+
+ifeq ($(DEBUG),0)
+  CFLAGS += -D_FORTIFY_SOURCE
+endif
+
+# Treat warnings as errors unless directed not to
+ifneq ($(WERROR),0)
+  CFLAGS += -Werror
+endif
+
+CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64
+CFLAGS += -I$(srctree)/tools/lib/api
+CFLAGS += -I$(srctree)/tools/include
+
+RM = rm -f
+
+API_IN := $(OUTPUT)libapi-in.o
+
+ifeq ($(LP64), 1)
+  libdir_relative = lib64
+else
+  libdir_relative = lib
+endif
+
+prefix ?=
+libdir = $(prefix)/$(libdir_relative)
+
+# Shell quotes
+libdir_SQ = $(subst ','\'',$(libdir))
+
+all:
+
+export srctree OUTPUT CC LD CFLAGS V
+include $(srctree)/tools/build/Makefile.include
+include $(srctree)/tools/scripts/Makefile.include
+
+all: fixdep $(LIBFILE)
+
+$(API_IN): FORCE
+	@$(MAKE) $(build)=libapi
+
+$(LIBFILE): $(API_IN)
+	$(QUIET_AR)$(RM) $@ && $(AR) rcs $@ $(API_IN)
+
+define do_install_mkdir
+	if [ ! -d '$(DESTDIR_SQ)$1' ]; then             \
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$1'; \
+	fi
+endef
+
+define do_install
+	if [ ! -d '$2' ]; then             \
+		$(INSTALL) -d -m 755 '$2'; \
+	fi;                                \
+	$(INSTALL) $1 $(if $3,-m $3,) '$2'
+endef
+
+install_lib: $(LIBFILE)
+	$(call QUIET_INSTALL, $(LIBFILE)) \
+		$(call do_install_mkdir,$(libdir_SQ)); \
+		cp -fpR $(LIBFILE) $(DESTDIR)$(libdir_SQ)
+
+HDRS := cpu.h debug.h io.h io_dir.h
+FD_HDRS := fd/array.h
+FS_HDRS := fs/fs.h fs/tracing_path.h
+INSTALL_HDRS_PFX := $(DESTDIR)$(prefix)/include/api
+INSTALL_HDRS := $(addprefix $(INSTALL_HDRS_PFX)/, $(HDRS))
+INSTALL_FD_HDRS := $(addprefix $(INSTALL_HDRS_PFX)/, $(FD_HDRS))
+INSTALL_FS_HDRS := $(addprefix $(INSTALL_HDRS_PFX)/, $(FS_HDRS))
+
+$(INSTALL_HDRS): $(INSTALL_HDRS_PFX)/%.h: %.h
+	$(call QUIET_INSTALL, $@) \
+		$(call do_install,$<,$(INSTALL_HDRS_PFX)/,644)
+
+$(INSTALL_FD_HDRS): $(INSTALL_HDRS_PFX)/fd/%.h: fd/%.h
+	$(call QUIET_INSTALL, $@) \
+		$(call do_install,$<,$(INSTALL_HDRS_PFX)/fd/,644)
+
+$(INSTALL_FS_HDRS): $(INSTALL_HDRS_PFX)/fs/%.h: fs/%.h
+	$(call QUIET_INSTALL, $@) \
+		$(call do_install,$<,$(INSTALL_HDRS_PFX)/fs/,644)
+
+install_headers: $(INSTALL_HDRS) $(INSTALL_FD_HDRS) $(INSTALL_FS_HDRS)
+	$(call QUIET_INSTALL, libapi_headers)
+
+install: install_lib install_headers
+
+clean:
+	$(call QUIET_CLEAN, libapi) $(RM) $(LIBFILE); \
+	find $(or $(OUTPUT),.) -name \*.o -or -name \*.o.cmd -or -name \*.o.d | xargs $(RM)
+
+FORCE:
+
+.PHONY: clean FORCE
diff --git a/tools/lib/api/cpu.c b/tools/lib/api/cpu.c
new file mode 100644
index 000000000..4af6d4b7a
--- /dev/null
+++ b/tools/lib/api/cpu.c
@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdio.h>
+
+#include "cpu.h"
+#include "fs/fs.h"
+
+int cpu__get_max_freq(unsigned long long *freq)
+{
+	char entry[PATH_MAX];
+	int cpu;
+
+	if (sysfs__read_int("devices/system/cpu/online", &cpu) < 0)
+		return -1;
+
+	snprintf(entry, sizeof(entry),
+		 "devices/system/cpu/cpu%d/cpufreq/cpuinfo_max_freq", cpu);
+
+	return sysfs__read_ull(entry, freq);
+}
diff --git a/tools/lib/api/cpu.h b/tools/lib/api/cpu.h
new file mode 100644
index 000000000..90a102fb2
--- /dev/null
+++ b/tools/lib/api/cpu.h
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __API_CPU__
+#define __API_CPU__
+
+int cpu__get_max_freq(unsigned long long *freq);
+
+#endif /* __API_CPU__ */
diff --git a/tools/lib/api/debug-internal.h b/tools/lib/api/debug-internal.h
new file mode 100644
index 000000000..5a5820c11
--- /dev/null
+++ b/tools/lib/api/debug-internal.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __API_DEBUG_INTERNAL_H__
+#define __API_DEBUG_INTERNAL_H__
+
+#include "debug.h"
+
+#define __pr(func, fmt, ...)	\
+do {				\
+	if ((func))		\
+		(func)("libapi: " fmt, ##__VA_ARGS__); \
+} while (0)
+
+extern libapi_print_fn_t __pr_warn;
+extern libapi_print_fn_t __pr_info;
+extern libapi_print_fn_t __pr_debug;
+
+#define pr_warn(fmt, ...)	__pr(__pr_warn, fmt, ##__VA_ARGS__)
+#define pr_info(fmt, ...)	__pr(__pr_info, fmt, ##__VA_ARGS__)
+#define pr_debug(fmt, ...)	__pr(__pr_debug, fmt, ##__VA_ARGS__)
+
+#endif /* __API_DEBUG_INTERNAL_H__ */
diff --git a/tools/lib/api/debug.c b/tools/lib/api/debug.c
new file mode 100644
index 000000000..7708f0558
--- /dev/null
+++ b/tools/lib/api/debug.c
@@ -0,0 +1,29 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdio.h>
+#include <stdarg.h>
+#include "debug.h"
+#include "debug-internal.h"
+
+static int __base_pr(const char *format, ...)
+{
+	va_list args;
+	int err;
+
+	va_start(args, format);
+	err = vfprintf(stderr, format, args);
+	va_end(args);
+	return err;
+}
+
+libapi_print_fn_t __pr_warn    = __base_pr;
+libapi_print_fn_t __pr_info    = __base_pr;
+libapi_print_fn_t __pr_debug;
+
+void libapi_set_print(libapi_print_fn_t warn,
+		      libapi_print_fn_t info,
+		      libapi_print_fn_t debug)
+{
+	__pr_warn    = warn;
+	__pr_info    = info;
+	__pr_debug   = debug;
+}
diff --git a/tools/lib/api/debug.h b/tools/lib/api/debug.h
new file mode 100644
index 000000000..3684dd6e0
--- /dev/null
+++ b/tools/lib/api/debug.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __API_DEBUG_H__
+#define __API_DEBUG_H__
+
+typedef int (*libapi_print_fn_t)(const char *, ...);
+
+void libapi_set_print(libapi_print_fn_t warn,
+		      libapi_print_fn_t info,
+		      libapi_print_fn_t debug);
+
+#endif /* __API_DEBUG_H__ */
diff --git a/tools/lib/api/fd/Build b/tools/lib/api/fd/Build
new file mode 100644
index 000000000..605d99f6d
--- /dev/null
+++ b/tools/lib/api/fd/Build
@@ -0,0 +1 @@
+libapi-y += array.o
diff --git a/tools/lib/api/fd/array.c b/tools/lib/api/fd/array.c
new file mode 100644
index 000000000..67b73481d
--- /dev/null
+++ b/tools/lib/api/fd/array.c
@@ -0,0 +1,158 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2014, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ */
+#include "array.h"
+#include <errno.h>
+#include <fcntl.h>
+#include <poll.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <string.h>
+
+void fdarray__init(struct fdarray *fda, int nr_autogrow)
+{
+	fda->entries	 = NULL;
+	fda->priv	 = NULL;
+	fda->nr		 = fda->nr_alloc = 0;
+	fda->nr_autogrow = nr_autogrow;
+}
+
+int fdarray__grow(struct fdarray *fda, int nr)
+{
+	struct priv *priv;
+	int nr_alloc = fda->nr_alloc + nr;
+	size_t psize = sizeof(fda->priv[0]) * nr_alloc;
+	size_t size  = sizeof(struct pollfd) * nr_alloc;
+	struct pollfd *entries = realloc(fda->entries, size);
+
+	if (entries == NULL)
+		return -ENOMEM;
+
+	priv = realloc(fda->priv, psize);
+	if (priv == NULL) {
+		/* this will be freed by fdarray__exit() */
+		fda->entries = entries;
+		return -ENOMEM;
+	}
+
+	memset(&entries[fda->nr_alloc], 0, sizeof(struct pollfd) * nr);
+	memset(&priv[fda->nr_alloc], 0, sizeof(fda->priv[0]) * nr);
+
+	fda->nr_alloc = nr_alloc;
+	fda->entries  = entries;
+	fda->priv     = priv;
+	return 0;
+}
+
+struct fdarray *fdarray__new(int nr_alloc, int nr_autogrow)
+{
+	struct fdarray *fda = calloc(1, sizeof(*fda));
+
+	if (fda != NULL) {
+		if (fdarray__grow(fda, nr_alloc)) {
+			fdarray__delete(fda);
+			fda = NULL;
+		} else {
+			fda->nr_autogrow = nr_autogrow;
+		}
+	}
+
+	return fda;
+}
+
+void fdarray__exit(struct fdarray *fda)
+{
+	free(fda->entries);
+	free(fda->priv);
+	fdarray__init(fda, 0);
+}
+
+void fdarray__delete(struct fdarray *fda)
+{
+	fdarray__exit(fda);
+	free(fda);
+}
+
+int fdarray__add(struct fdarray *fda, int fd, short revents, enum fdarray_flags flags)
+{
+	int pos = fda->nr;
+
+	if (fda->nr == fda->nr_alloc &&
+	    fdarray__grow(fda, fda->nr_autogrow) < 0)
+		return -ENOMEM;
+
+	fda->entries[fda->nr].fd     = fd;
+	fda->entries[fda->nr].events = revents;
+	fda->priv[fda->nr].flags = flags;
+	fda->nr++;
+	return pos;
+}
+
+int fdarray__dup_entry_from(struct fdarray *fda, int pos, struct fdarray *from)
+{
+	struct pollfd *entry;
+	int npos;
+
+	if (pos >= from->nr)
+		return -EINVAL;
+
+	entry = &from->entries[pos];
+
+	npos = fdarray__add(fda, entry->fd, entry->events, from->priv[pos].flags);
+	if (npos >= 0)
+		fda->priv[npos] = from->priv[pos];
+
+	return npos;
+}
+
+int fdarray__filter(struct fdarray *fda, short revents,
+		    void (*entry_destructor)(struct fdarray *fda, int fd, void *arg),
+		    void *arg)
+{
+	int fd, nr = 0;
+
+	if (fda->nr == 0)
+		return 0;
+
+	for (fd = 0; fd < fda->nr; ++fd) {
+		if (fda->priv[fd].flags & fdarray_flag__nonfilterable)
+			continue;
+
+		if (!fda->entries[fd].events)
+			continue;
+
+		if (fda->entries[fd].revents & revents) {
+			if (entry_destructor)
+				entry_destructor(fda, fd, arg);
+
+			/*
+			 * Set fd to -1 so poll() ignores this entry; otherwise
+			 * POLLHUP/POLLERR are still reported for events=0 fds
+			 * (POSIX: always checked), causing a poll storm.
+			 */
+			fda->entries[fd].fd = -1;
+			fda->entries[fd].revents = fda->entries[fd].events = 0;
+			continue;
+		}
+
+		++nr;
+	}
+
+	return nr;
+}
+
+int fdarray__poll(struct fdarray *fda, int timeout)
+{
+	return poll(fda->entries, fda->nr, timeout);
+}
+
+int fdarray__fprintf(struct fdarray *fda, FILE *fp)
+{
+	int fd, printed = fprintf(fp, "%d [ ", fda->nr);
+
+	for (fd = 0; fd < fda->nr; ++fd)
+		printed += fprintf(fp, "%s%d", fd ? ", " : "", fda->entries[fd].fd);
+
+	return printed + fprintf(fp, " ]");
+}
diff --git a/tools/lib/api/fd/array.h b/tools/lib/api/fd/array.h
new file mode 100644
index 000000000..5c01f7b05
--- /dev/null
+++ b/tools/lib/api/fd/array.h
@@ -0,0 +1,59 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __API_FD_ARRAY__
+#define __API_FD_ARRAY__
+
+#include <stdio.h>
+
+struct pollfd;
+
+/**
+ * struct fdarray: Array of file descriptors
+ *
+ * @priv: Per array entry priv area, users should access just its contents,
+ *	  not set it to anything, as it is kept in synch with @entries, being
+ *	  realloc'ed, * for instance, in fdarray__{grow,filter}.
+ *
+ *	  I.e. using 'fda->priv[N].idx = * value' where N < fda->nr is ok,
+ *	  but doing 'fda->priv = malloc(M)' is not allowed.
+ */
+struct fdarray {
+	int	       nr;
+	int	       nr_alloc;
+	int	       nr_autogrow;
+	struct pollfd *entries;
+	struct priv {
+		union {
+			int    idx;
+			void   *ptr;
+		};
+		unsigned int flags;
+	} *priv;
+};
+
+enum fdarray_flags {
+	fdarray_flag__default		= 0x00000000,
+	fdarray_flag__nonfilterable	= 0x00000001,
+	fdarray_flag__non_perf_event	= 0x00000002,
+};
+
+void fdarray__init(struct fdarray *fda, int nr_autogrow);
+void fdarray__exit(struct fdarray *fda);
+
+struct fdarray *fdarray__new(int nr_alloc, int nr_autogrow);
+void fdarray__delete(struct fdarray *fda);
+
+int fdarray__add(struct fdarray *fda, int fd, short revents, enum fdarray_flags flags);
+int fdarray__dup_entry_from(struct fdarray *fda, int pos, struct fdarray *from);
+int fdarray__poll(struct fdarray *fda, int timeout);
+int fdarray__filter(struct fdarray *fda, short revents,
+		    void (*entry_destructor)(struct fdarray *fda, int fd, void *arg),
+		    void *arg);
+int fdarray__grow(struct fdarray *fda, int extra);
+int fdarray__fprintf(struct fdarray *fda, FILE *fp);
+
+static inline int fdarray__available_entries(struct fdarray *fda)
+{
+	return fda->nr_alloc - fda->nr;
+}
+
+#endif /* __API_FD_ARRAY__ */
diff --git a/tools/lib/api/fs/Build b/tools/lib/api/fs/Build
new file mode 100644
index 000000000..0f75b2865
--- /dev/null
+++ b/tools/lib/api/fs/Build
@@ -0,0 +1,3 @@
+libapi-y += fs.o
+libapi-y += tracing_path.o
+libapi-y += cgroup.o
diff --git a/tools/lib/api/fs/cgroup.c b/tools/lib/api/fs/cgroup.c
new file mode 100644
index 000000000..250629a09
--- /dev/null
+++ b/tools/lib/api/fs/cgroup.c
@@ -0,0 +1,107 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/stringify.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include "fs.h"
+
+struct cgroupfs_cache_entry {
+	char	subsys[32];
+	char	mountpoint[PATH_MAX];
+};
+
+/* just cache last used one */
+static struct cgroupfs_cache_entry *cached;
+
+int cgroupfs_find_mountpoint(char *buf, size_t maxlen, const char *subsys)
+{
+	FILE *fp;
+	char *line = NULL;
+	size_t len = 0;
+	char *p, *path;
+	char mountpoint[PATH_MAX];
+
+	if (cached && !strcmp(cached->subsys, subsys)) {
+		if (strlen(cached->mountpoint) < maxlen) {
+			strcpy(buf, cached->mountpoint);
+			return 0;
+		}
+		return -1;
+	}
+
+	fp = fopen("/proc/mounts", "r");
+	if (!fp)
+		return -1;
+
+	/*
+	 * in order to handle split hierarchy, we need to scan /proc/mounts
+	 * and inspect every cgroupfs mount point to find one that has
+	 * the given subsystem.  If we found v1, just use it.  If not we can
+	 * use v2 path as a fallback.
+	 */
+	mountpoint[0] = '\0';
+
+	/*
+	 * The /proc/mounts has the follow format:
+	 *
+	 *   <devname> <mount point> <fs type> <options> ...
+	 *
+	 */
+	while (getline(&line, &len, fp) != -1) {
+		/* skip devname */
+		p = strchr(line, ' ');
+		if (p == NULL)
+			continue;
+
+		/* save the mount point */
+		path = ++p;
+		p = strchr(p, ' ');
+		if (p == NULL)
+			continue;
+
+		*p++ = '\0';
+
+		/* check filesystem type */
+		if (strncmp(p, "cgroup", 6))
+			continue;
+
+		if (p[6] == '2') {
+			/* save cgroup v2 path */
+			strcpy(mountpoint, path);
+			continue;
+		}
+
+		/* now we have cgroup v1, check the options for subsystem */
+		p += 7;
+
+		p = strstr(p, subsys);
+		if (p == NULL)
+			continue;
+
+		/* sanity check: it should be separated by a space or a comma */
+		if (!strchr(" ,", p[-1]) || !strchr(" ,", p[strlen(subsys)]))
+			continue;
+
+		strcpy(mountpoint, path);
+		break;
+	}
+	free(line);
+	fclose(fp);
+
+	if (!cached)
+		cached = calloc(1, sizeof(*cached));
+
+	if (cached) {
+		strncpy(cached->subsys, subsys, sizeof(cached->subsys) - 1);
+		strcpy(cached->mountpoint, mountpoint);
+	}
+
+	if (mountpoint[0] && strlen(mountpoint) < maxlen) {
+		strcpy(buf, mountpoint);
+		return 0;
+	}
+	return -1;
+}
diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c
new file mode 100644
index 000000000..cbd8eab0d
--- /dev/null
+++ b/tools/lib/api/fs/fs.c
@@ -0,0 +1,515 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <assert.h>
+#include <ctype.h>
+#include <errno.h>
+#include <limits.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/vfs.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <pthread.h>
+#include <unistd.h>
+#include <sys/mount.h>
+
+#include "fs.h"
+#include "../io.h"
+#include "debug-internal.h"
+
+#define _STR(x) #x
+#define STR(x) _STR(x)
+
+#ifndef SYSFS_MAGIC
+#define SYSFS_MAGIC            0x62656572
+#endif
+
+#ifndef PROC_SUPER_MAGIC
+#define PROC_SUPER_MAGIC       0x9fa0
+#endif
+
+#ifndef DEBUGFS_MAGIC
+#define DEBUGFS_MAGIC          0x64626720
+#endif
+
+#ifndef TRACEFS_MAGIC
+#define TRACEFS_MAGIC          0x74726163
+#endif
+
+#ifndef HUGETLBFS_MAGIC
+#define HUGETLBFS_MAGIC        0x958458f6
+#endif
+
+#ifndef BPF_FS_MAGIC
+#define BPF_FS_MAGIC           0xcafe4a11
+#endif
+
+static const char * const sysfs__known_mountpoints[] = {
+	"/sys",
+	0,
+};
+
+static const char * const procfs__known_mountpoints[] = {
+	"/proc",
+	0,
+};
+
+#ifndef DEBUGFS_DEFAULT_PATH
+#define DEBUGFS_DEFAULT_PATH "/sys/kernel/debug"
+#endif
+
+static const char * const debugfs__known_mountpoints[] = {
+	DEBUGFS_DEFAULT_PATH,
+	"/debug",
+	0,
+};
+
+
+#ifndef TRACEFS_DEFAULT_PATH
+#define TRACEFS_DEFAULT_PATH "/sys/kernel/tracing"
+#endif
+
+static const char * const tracefs__known_mountpoints[] = {
+	TRACEFS_DEFAULT_PATH,
+	"/sys/kernel/debug/tracing",
+	"/tracing",
+	"/trace",
+	0,
+};
+
+static const char * const hugetlbfs__known_mountpoints[] = {
+	0,
+};
+
+static const char * const bpf_fs__known_mountpoints[] = {
+	"/sys/fs/bpf",
+	0,
+};
+
+struct fs {
+	const char *		 const name;
+	const char * const *	 const mounts;
+	char			*path;
+	pthread_mutex_t		 mount_mutex;
+	const long		 magic;
+};
+
+#ifndef TRACEFS_MAGIC
+#define TRACEFS_MAGIC 0x74726163
+#endif
+
+static void fs__init_once(struct fs *fs);
+static const char *fs__mountpoint(const struct fs *fs);
+static const char *fs__mount(struct fs *fs);
+
+#define FS(lower_name, fs_name, upper_name)		\
+static struct fs fs__##lower_name = {			\
+	.name = #fs_name,				\
+	.mounts = lower_name##__known_mountpoints,	\
+	.magic = upper_name##_MAGIC,			\
+	.mount_mutex = PTHREAD_MUTEX_INITIALIZER,	\
+};							\
+							\
+static void lower_name##_init_once(void)		\
+{							\
+	struct fs *fs = &fs__##lower_name;		\
+							\
+	fs__init_once(fs);				\
+}							\
+							\
+const char *lower_name##__mountpoint(void)		\
+{							\
+	static pthread_once_t init_once = PTHREAD_ONCE_INIT;	\
+	struct fs *fs = &fs__##lower_name;		\
+							\
+	pthread_once(&init_once, lower_name##_init_once);	\
+	return fs__mountpoint(fs);			\
+}							\
+							\
+const char *lower_name##__mount(void)			\
+{							\
+	const char *mountpoint = lower_name##__mountpoint();	\
+	struct fs *fs = &fs__##lower_name;		\
+							\
+	if (mountpoint)					\
+		return mountpoint;			\
+							\
+	return fs__mount(fs);				\
+}							\
+							\
+bool lower_name##__configured(void)			\
+{							\
+	return lower_name##__mountpoint() != NULL;	\
+}
+
+FS(sysfs, sysfs, SYSFS);
+FS(procfs, procfs, PROC_SUPER);
+FS(debugfs, debugfs, DEBUGFS);
+FS(tracefs, tracefs, TRACEFS);
+FS(hugetlbfs, hugetlbfs, HUGETLBFS);
+FS(bpf_fs, bpf, BPF_FS);
+
+static bool fs__read_mounts(struct fs *fs)
+{
+	char type[100];
+	FILE *fp;
+	char path[PATH_MAX + 1];
+
+	fp = fopen("/proc/mounts", "r");
+	if (fp == NULL)
+		return false;
+
+	while (fscanf(fp, "%*s %" STR(PATH_MAX) "s %99s %*s %*d %*d\n",
+		      path, type) == 2) {
+
+		if (strcmp(type, fs->name) == 0) {
+			fs->path = strdup(path);
+			fclose(fp);
+			return fs->path != NULL;
+		}
+	}
+	fclose(fp);
+	return false;
+}
+
+static int fs__valid_mount(const char *fs, long magic)
+{
+	struct statfs st_fs;
+
+	if (statfs(fs, &st_fs) < 0)
+		return -ENOENT;
+	else if ((long)st_fs.f_type != magic)
+		return -ENOENT;
+
+	return 0;
+}
+
+static bool fs__check_mounts(struct fs *fs)
+{
+	const char * const *ptr;
+
+	ptr = fs->mounts;
+	while (*ptr) {
+		if (fs__valid_mount(*ptr, fs->magic) == 0) {
+			fs->path = strdup(*ptr);
+			if (!fs->path)
+				return false;
+			return true;
+		}
+		ptr++;
+	}
+
+	return false;
+}
+
+static void mem_toupper(char *f, size_t len)
+{
+	while (len) {
+		*f = toupper(*f);
+		f++;
+		len--;
+	}
+}
+
+/*
+ * Check for "NAME_PATH" environment variable to override fs location (for
+ * testing). This matches the recommendation in Documentation/admin-guide/sysfs-rules.rst
+ * for SYSFS_PATH.
+ */
+static bool fs__env_override(struct fs *fs)
+{
+	char *override_path;
+	size_t name_len = strlen(fs->name);
+	/* name + "_PATH" + '\0' */
+	char upper_name[name_len + 5 + 1];
+
+	memcpy(upper_name, fs->name, name_len);
+	mem_toupper(upper_name, name_len);
+	strcpy(&upper_name[name_len], "_PATH");
+
+	override_path = getenv(upper_name);
+	if (!override_path)
+		return false;
+
+	fs->path = strdup(override_path);
+	if (!fs->path)
+		return false;
+	return true;
+}
+
+static void fs__init_once(struct fs *fs)
+{
+	if (!fs__env_override(fs) &&
+	    !fs__check_mounts(fs) &&
+	    !fs__read_mounts(fs)) {
+		assert(!fs->path);
+	} else {
+		assert(fs->path);
+	}
+}
+
+static const char *fs__mountpoint(const struct fs *fs)
+{
+	return fs->path;
+}
+
+static const char *mount_overload(struct fs *fs)
+{
+	size_t name_len = strlen(fs->name);
+	/* "PERF_" + name + "_ENVIRONMENT" + '\0' */
+	char upper_name[5 + name_len + 12 + 1];
+
+	snprintf(upper_name, sizeof(upper_name), "PERF_%s_ENVIRONMENT", fs->name);
+	mem_toupper(upper_name, strlen(upper_name));
+
+	return getenv(upper_name) ?: *fs->mounts;
+}
+
+static const char *fs__mount(struct fs *fs)
+{
+	const char *mountpoint;
+
+	pthread_mutex_lock(&fs->mount_mutex);
+
+	/* Check if path found inside the mutex to avoid races with other callers of mount. */
+	mountpoint = fs__mountpoint(fs);
+	if (mountpoint)
+		goto out;
+
+	mountpoint = mount_overload(fs);
+
+	if (mount(NULL, mountpoint, fs->name, 0, NULL) == 0 &&
+	    fs__valid_mount(mountpoint, fs->magic) == 0) {
+		fs->path = strdup(mountpoint);
+		mountpoint = fs->path;
+	}
+out:
+	pthread_mutex_unlock(&fs->mount_mutex);
+	return mountpoint;
+}
+
+int filename__read_int(const char *filename, int *value)
+{
+	char line[64];
+	int fd = open(filename, O_RDONLY), err = -1;
+	ssize_t n;
+
+	if (fd < 0)
+		return -errno;
+
+	n = read(fd, line, sizeof(line) - 1);
+	if (n > 0) {
+		line[n] = '\0';
+		*value = atoi(line);
+		err = 0;
+	}
+
+	close(fd);
+	return err;
+}
+
+static int filename__read_ull_base(const char *filename,
+				   unsigned long long *value, int base)
+{
+	char line[64];
+	int fd = open(filename, O_RDONLY), err = -1;
+	ssize_t n;
+
+	if (fd < 0)
+		return -errno;
+
+	n = read(fd, line, sizeof(line) - 1);
+	if (n > 0) {
+		line[n] = '\0';
+		*value = strtoull(line, NULL, base);
+		if (*value != ULLONG_MAX)
+			err = 0;
+	}
+
+	close(fd);
+	return err;
+}
+
+/*
+ * Parses @value out of @filename with strtoull.
+ * By using 16 for base to treat the number as hex.
+ */
+int filename__read_xll(const char *filename, unsigned long long *value)
+{
+	return filename__read_ull_base(filename, value, 16);
+}
+
+/*
+ * Parses @value out of @filename with strtoull.
+ * By using 0 for base, the strtoull detects the
+ * base automatically (see man strtoull).
+ */
+int filename__read_ull(const char *filename, unsigned long long *value)
+{
+	return filename__read_ull_base(filename, value, 0);
+}
+
+int filename__read_str(const char *filename, char **buf, size_t *sizep)
+{
+	struct io io;
+	char bf[128];
+	int err;
+
+	io.fd = open(filename, O_RDONLY);
+	if (io.fd < 0)
+		return -errno;
+	io__init(&io, io.fd, bf, sizeof(bf));
+	*buf = NULL;
+	err = io__getdelim(&io, buf, sizep, /*delim=*/-1);
+	if (err < 0) {
+		free(*buf);
+		*buf = NULL;
+	} else
+		err = 0;
+	close(io.fd);
+	return err;
+}
+
+int filename__write_int(const char *filename, int value)
+{
+	int fd = open(filename, O_WRONLY), err = -1;
+	char buf[64];
+	int len;
+
+	if (fd < 0)
+		return -errno;
+
+	len = sprintf(buf, "%d", value);
+	if (write(fd, buf, len) == len)
+		err = 0;
+
+	close(fd);
+	return err;
+}
+
+int procfs__read_str(const char *entry, char **buf, size_t *sizep)
+{
+	char path[PATH_MAX];
+	const char *procfs = procfs__mountpoint();
+
+	if (!procfs)
+		return -1;
+
+	snprintf(path, sizeof(path), "%s/%s", procfs, entry);
+
+	return filename__read_str(path, buf, sizep);
+}
+
+static int sysfs__read_ull_base(const char *entry,
+				unsigned long long *value, int base)
+{
+	char path[PATH_MAX];
+	const char *sysfs = sysfs__mountpoint();
+
+	if (!sysfs)
+		return -1;
+
+	snprintf(path, sizeof(path), "%s/%s", sysfs, entry);
+
+	return filename__read_ull_base(path, value, base);
+}
+
+int sysfs__read_xll(const char *entry, unsigned long long *value)
+{
+	return sysfs__read_ull_base(entry, value, 16);
+}
+
+int sysfs__read_ull(const char *entry, unsigned long long *value)
+{
+	return sysfs__read_ull_base(entry, value, 0);
+}
+
+int sysfs__read_int(const char *entry, int *value)
+{
+	char path[PATH_MAX];
+	const char *sysfs = sysfs__mountpoint();
+
+	if (!sysfs)
+		return -1;
+
+	snprintf(path, sizeof(path), "%s/%s", sysfs, entry);
+
+	return filename__read_int(path, value);
+}
+
+int sysfs__read_str(const char *entry, char **buf, size_t *sizep)
+{
+	char path[PATH_MAX];
+	const char *sysfs = sysfs__mountpoint();
+
+	if (!sysfs)
+		return -1;
+
+	snprintf(path, sizeof(path), "%s/%s", sysfs, entry);
+
+	return filename__read_str(path, buf, sizep);
+}
+
+int sysfs__read_bool(const char *entry, bool *value)
+{
+	struct io io;
+	char bf[16];
+	int ret = 0;
+	char path[PATH_MAX];
+	const char *sysfs = sysfs__mountpoint();
+
+	if (!sysfs)
+		return -1;
+
+	snprintf(path, sizeof(path), "%s/%s", sysfs, entry);
+	io.fd = open(path, O_RDONLY);
+	if (io.fd < 0)
+		return -errno;
+
+	io__init(&io, io.fd, bf, sizeof(bf));
+	switch (io__get_char(&io)) {
+	case '1':
+	case 'y':
+	case 'Y':
+		*value = true;
+		break;
+	case '0':
+	case 'n':
+	case 'N':
+		*value = false;
+		break;
+	default:
+		ret = -1;
+	}
+	close(io.fd);
+
+	return ret;
+}
+int sysctl__read_int(const char *sysctl, int *value)
+{
+	char path[PATH_MAX];
+	const char *procfs = procfs__mountpoint();
+
+	if (!procfs)
+		return -1;
+
+	snprintf(path, sizeof(path), "%s/sys/%s", procfs, sysctl);
+
+	return filename__read_int(path, value);
+}
+
+int sysfs__write_int(const char *entry, int value)
+{
+	char path[PATH_MAX];
+	const char *sysfs = sysfs__mountpoint();
+
+	if (!sysfs)
+		return -1;
+
+	if (snprintf(path, sizeof(path), "%s/%s", sysfs, entry) >= PATH_MAX)
+		return -1;
+
+	return filename__write_int(path, value);
+}
diff --git a/tools/lib/api/fs/fs.h b/tools/lib/api/fs/fs.h
new file mode 100644
index 000000000..aa222ca30
--- /dev/null
+++ b/tools/lib/api/fs/fs.h
@@ -0,0 +1,62 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __API_FS__
+#define __API_FS__
+
+#include <stdbool.h>
+#include <unistd.h>
+
+/*
+ * On most systems <limits.h> would have given us this, but  not on some systems
+ * (e.g. GNU/Hurd).
+ */
+#ifndef PATH_MAX
+#define PATH_MAX 4096
+#endif
+
+#define FS(name)				\
+	const char *name##__mountpoint(void);	\
+	const char *name##__mount(void);	\
+	bool name##__configured(void);		\
+
+/*
+ * The xxxx__mountpoint() entry points find the first match mount point for each
+ * filesystems listed below, where xxxx is the filesystem type.
+ *
+ * The interface is as follows:
+ *
+ * - If a mount point is found on first call, it is cached and used for all
+ *   subsequent calls.
+ *
+ * - If a mount point is not found, NULL is returned on first call and all
+ *   subsequent calls.
+ */
+FS(sysfs)
+FS(procfs)
+FS(debugfs)
+FS(tracefs)
+FS(hugetlbfs)
+FS(bpf_fs)
+
+#undef FS
+
+
+int cgroupfs_find_mountpoint(char *buf, size_t maxlen, const char *subsys);
+
+int filename__read_int(const char *filename, int *value);
+int filename__read_ull(const char *filename, unsigned long long *value);
+int filename__read_xll(const char *filename, unsigned long long *value);
+int filename__read_str(const char *filename, char **buf, size_t *sizep);
+
+int filename__write_int(const char *filename, int value);
+
+int procfs__read_str(const char *entry, char **buf, size_t *sizep);
+
+int sysctl__read_int(const char *sysctl, int *value);
+int sysfs__read_int(const char *entry, int *value);
+int sysfs__read_ull(const char *entry, unsigned long long *value);
+int sysfs__read_xll(const char *entry, unsigned long long *value);
+int sysfs__read_str(const char *entry, char **buf, size_t *sizep);
+int sysfs__read_bool(const char *entry, bool *value);
+
+int sysfs__write_int(const char *entry, int value);
+#endif /* __API_FS__ */
diff --git a/tools/lib/api/fs/tracing_path.c b/tools/lib/api/fs/tracing_path.c
new file mode 100644
index 000000000..834fd64c7
--- /dev/null
+++ b/tools/lib/api/fs/tracing_path.c
@@ -0,0 +1,178 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef _GNU_SOURCE
+# define _GNU_SOURCE
+#endif
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <linux/string.h>
+#include <errno.h>
+#include <unistd.h>
+#include "fs.h"
+
+#include "tracing_path.h"
+
+static char tracing_path[PATH_MAX]        = "/sys/kernel/tracing";
+
+static void __tracing_path_set(const char *tracing, const char *mountpoint)
+{
+	snprintf(tracing_path, sizeof(tracing_path), "%s/%s",
+		 mountpoint, tracing);
+}
+
+static const char *tracing_path_tracefs_mount(void)
+{
+	const char *mnt;
+
+	mnt = tracefs__mount();
+	if (!mnt)
+		return NULL;
+
+	__tracing_path_set("", mnt);
+
+	return tracing_path;
+}
+
+static const char *tracing_path_debugfs_mount(void)
+{
+	const char *mnt;
+
+	mnt = debugfs__mount();
+	if (!mnt)
+		return NULL;
+
+	__tracing_path_set("tracing/", mnt);
+
+	return tracing_path;
+}
+
+const char *tracing_path_mount(void)
+{
+	const char *mnt;
+
+	mnt = tracing_path_tracefs_mount();
+	if (mnt)
+		return mnt;
+
+	mnt = tracing_path_debugfs_mount();
+
+	return mnt;
+}
+
+void tracing_path_set(const char *mntpt)
+{
+	__tracing_path_set("tracing/", mntpt);
+}
+
+char *get_tracing_file(const char *name)
+{
+	char *file;
+
+	if (asprintf(&file, "%s%s", tracing_path_mount(), name) < 0)
+		return NULL;
+
+	return file;
+}
+
+void put_tracing_file(char *file)
+{
+	free(file);
+}
+
+char *get_events_file(const char *name)
+{
+	char *file;
+
+	if (asprintf(&file, "%s/events/%s", tracing_path_mount(), name) < 0)
+		return NULL;
+
+	return file;
+}
+
+void put_events_file(char *file)
+{
+	free(file);
+}
+
+DIR *tracing_events__opendir(void)
+{
+	DIR *dir = NULL;
+	char *path = get_tracing_file("events");
+
+	if (path) {
+		dir = opendir(path);
+		put_events_file(path);
+	}
+
+	return dir;
+}
+
+int tracing_events__scandir_alphasort(struct dirent ***namelist)
+{
+	char *path = get_tracing_file("events");
+	int ret;
+
+	if (!path) {
+		*namelist = NULL;
+		return 0;
+	}
+
+	ret = scandir(path, namelist, NULL, alphasort);
+	put_events_file(path);
+
+	return ret;
+}
+
+int tracing_path__strerror_open_tp(int err, char *buf, size_t size,
+				   const char *sys, const char *name)
+{
+	char sbuf[128];
+	char filename[PATH_MAX];
+
+	snprintf(filename, PATH_MAX, "%s/%s", sys, name ?: "*");
+
+	switch (err) {
+	case ENOENT:
+		/*
+		 * We will get here if we can't find the tracepoint, but one of
+		 * debugfs or tracefs is configured, which means you probably
+		 * want some tracepoint which wasn't compiled in your kernel.
+		 * - jirka
+		 */
+		if (debugfs__configured() || tracefs__configured()) {
+			/* sdt markers */
+			if (!strncmp(filename, "sdt_", 4)) {
+				snprintf(buf, size,
+					"Error:\tFile %s/events/%s not found.\n"
+					"Hint:\tSDT event cannot be directly recorded on.\n"
+					"\tPlease first use 'perf probe %s:%s' before recording it.\n",
+					tracing_path, filename, sys, name);
+			} else {
+				snprintf(buf, size,
+					 "Error:\tFile %s/events/%s not found.\n"
+					 "Hint:\tPerhaps this kernel misses some CONFIG_ setting to enable this feature?.\n",
+					 tracing_path, filename);
+			}
+			break;
+		}
+		snprintf(buf, size, "%s",
+			 "Error:\tUnable to find debugfs/tracefs\n"
+			 "Hint:\tWas your kernel compiled with debugfs/tracefs support?\n"
+			 "Hint:\tIs the debugfs/tracefs filesystem mounted?\n"
+			 "Hint:\tTry 'sudo mount -t debugfs nodev /sys/kernel/debug'");
+		break;
+	case EACCES: {
+		snprintf(buf, size,
+			 "Error:\tNo permissions to read %s/events/%s\n"
+			 "Hint:\tTry 'sudo mount -o remount,mode=755 %s'\n",
+			 tracing_path, filename, tracing_path_mount());
+	}
+		break;
+	default:
+		snprintf(buf, size, "%s", str_error_r(err, sbuf, sizeof(sbuf)));
+		break;
+	}
+
+	return 0;
+}
diff --git a/tools/lib/api/fs/tracing_path.h b/tools/lib/api/fs/tracing_path.h
new file mode 100644
index 000000000..fc6347c11
--- /dev/null
+++ b/tools/lib/api/fs/tracing_path.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __API_FS_TRACING_PATH_H
+#define __API_FS_TRACING_PATH_H
+
+#include <linux/types.h>
+#include <dirent.h>
+
+DIR *tracing_events__opendir(void);
+int tracing_events__scandir_alphasort(struct dirent ***namelist);
+
+void tracing_path_set(const char *mountpoint);
+const char *tracing_path_mount(void);
+
+char *get_tracing_file(const char *name);
+void put_tracing_file(char *file);
+
+char *get_events_file(const char *name);
+void put_events_file(char *file);
+
+#define zput_events_file(ptr) ({ free(*ptr); *ptr = NULL; })
+
+int tracing_path__strerror_open_tp(int err, char *buf, size_t size, const char *sys, const char *name);
+#endif /* __API_FS_TRACING_PATH_H */
diff --git a/tools/lib/api/io.h b/tools/lib/api/io.h
new file mode 100644
index 000000000..1731996b2
--- /dev/null
+++ b/tools/lib/api/io.h
@@ -0,0 +1,201 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Lightweight buffered reading library.
+ *
+ * Copyright 2019 Google LLC.
+ */
+#ifndef __API_IO__
+#define __API_IO__
+
+#include <errno.h>
+#include <poll.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <linux/types.h>
+
+struct io {
+	/* File descriptor being read/ */
+	int fd;
+	/* Size of the read buffer. */
+	unsigned int buf_len;
+	/* Pointer to storage for buffering read. */
+	char *buf;
+	/* End of the storage. */
+	char *end;
+	/* Currently accessed data pointer. */
+	char *data;
+	/* Read timeout, 0 implies no timeout. */
+	int timeout_ms;
+	/* Set true on when the end of file on read error. */
+	bool eof;
+};
+
+static inline void io__init(struct io *io, int fd,
+			    char *buf, unsigned int buf_len)
+{
+	io->fd = fd;
+	io->buf_len = buf_len;
+	io->buf = buf;
+	io->end = buf;
+	io->data = buf;
+	io->timeout_ms = 0;
+	io->eof = false;
+}
+
+/* Read from fd filling the buffer. Called when io->data == io->end. */
+static inline int io__fill_buffer(struct io *io)
+{
+	ssize_t n;
+
+	if (io->eof)
+		return -1;
+
+	if (io->timeout_ms != 0) {
+		struct pollfd pfds[] = {
+			{
+				.fd = io->fd,
+				.events = POLLIN,
+			},
+		};
+
+		n = poll(pfds, 1, io->timeout_ms);
+		if (n == 0)
+			errno = ETIMEDOUT;
+		if (n > 0 && !(pfds[0].revents & POLLIN)) {
+			errno = EIO;
+			n = -1;
+		}
+		if (n <= 0) {
+			io->eof = true;
+			return -1;
+		}
+	}
+	n = read(io->fd, io->buf, io->buf_len);
+
+	if (n <= 0) {
+		io->eof = true;
+		return -1;
+	}
+	io->data = &io->buf[0];
+	io->end = &io->buf[n];
+	return 0;
+}
+
+/* Reads one character from the "io" file with similar semantics to fgetc. */
+static inline int io__get_char(struct io *io)
+{
+	if (io->data == io->end) {
+		int ret = io__fill_buffer(io);
+
+		if (ret)
+			return ret;
+	}
+	return *io->data++;
+}
+
+/* Read a hexadecimal value with no 0x prefix into the out argument hex. If the
+ * first character isn't hexadecimal returns -2, io->eof returns -1, otherwise
+ * returns the character after the hexadecimal value which may be -1 for eof.
+ * If the read value is larger than a u64 the high-order bits will be dropped.
+ */
+static inline int io__get_hex(struct io *io, __u64 *hex)
+{
+	bool first_read = true;
+
+	*hex = 0;
+	while (true) {
+		int ch = io__get_char(io);
+
+		if (ch < 0)
+			return ch;
+		if (ch >= '0' && ch <= '9')
+			*hex = (*hex << 4) | (ch - '0');
+		else if (ch >= 'a' && ch <= 'f')
+			*hex = (*hex << 4) | (ch - 'a' + 10);
+		else if (ch >= 'A' && ch <= 'F')
+			*hex = (*hex << 4) | (ch - 'A' + 10);
+		else if (first_read)
+			return -2;
+		else
+			return ch;
+		first_read = false;
+	}
+}
+
+/* Read a positive decimal value with out argument dec. If the first character
+ * isn't a decimal returns -2, io->eof returns -1, otherwise returns the
+ * character after the decimal value which may be -1 for eof. If the read value
+ * is larger than a u64 the high-order bits will be dropped.
+ */
+static inline int io__get_dec(struct io *io, __u64 *dec)
+{
+	bool first_read = true;
+
+	*dec = 0;
+	while (true) {
+		int ch = io__get_char(io);
+
+		if (ch < 0)
+			return ch;
+		if (ch >= '0' && ch <= '9')
+			*dec = (*dec * 10) + ch - '0';
+		else if (first_read)
+			return -2;
+		else
+			return ch;
+		first_read = false;
+	}
+}
+
+/* Read up to and including the first delim. */
+static inline ssize_t io__getdelim(struct io *io, char **line_out, size_t *line_len_out, int delim)
+{
+	char buf[128];
+	int buf_pos = 0;
+	char *line = NULL, *temp;
+	size_t line_len = 0;
+	int ch = 0;
+
+	/* TODO: reuse previously allocated memory. */
+	free(*line_out);
+	while (ch != delim) {
+		ch = io__get_char(io);
+
+		if (ch < 0)
+			break;
+
+		if (buf_pos == sizeof(buf)) {
+			temp = realloc(line, line_len + sizeof(buf));
+			if (!temp)
+				goto err_out;
+			line = temp;
+			memcpy(&line[line_len], buf, sizeof(buf));
+			line_len += sizeof(buf);
+			buf_pos = 0;
+		}
+		buf[buf_pos++] = (char)ch;
+	}
+	temp = realloc(line, line_len + buf_pos + 1);
+	if (!temp)
+		goto err_out;
+	line = temp;
+	memcpy(&line[line_len], buf, buf_pos);
+	line[line_len + buf_pos] = '\0';
+	line_len += buf_pos;
+	*line_out = line;
+	*line_len_out = line_len;
+	return line_len;
+err_out:
+	free(line);
+	*line_out = NULL;
+	*line_len_out = 0;
+	return -ENOMEM;
+}
+
+static inline ssize_t io__getline(struct io *io, char **line_out, size_t *line_len_out)
+{
+	return io__getdelim(io, line_out, line_len_out, /*delim=*/'\n');
+}
+
+#endif /* __API_IO__ */
diff --git a/tools/lib/api/io_dir.h b/tools/lib/api/io_dir.h
new file mode 100644
index 000000000..ef83e967e
--- /dev/null
+++ b/tools/lib/api/io_dir.h
@@ -0,0 +1,105 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+/*
+ * Lightweight directory reading library.
+ */
+#ifndef __API_IO_DIR__
+#define __API_IO_DIR__
+
+#include <dirent.h>
+#include <fcntl.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <sys/stat.h>
+#include <sys/syscall.h>
+#include <linux/limits.h>
+
+#if !defined(SYS_getdents64)
+#if defined(__x86_64__) || defined(__arm__)
+  #define SYS_getdents64 217
+#elif defined(__i386__) || defined(__s390x__) || defined(__sh__)
+  #define SYS_getdents64 220
+#elif defined(__alpha__)
+  #define SYS_getdents64 377
+#elif defined(__mips__)
+  #define SYS_getdents64 308
+#elif defined(__powerpc64__) || defined(__powerpc__)
+  #define SYS_getdents64 202
+#elif defined(__sparc64__) || defined(__sparc__)
+  #define SYS_getdents64 154
+#elif defined(__xtensa__)
+  #define SYS_getdents64 60
+#else
+  #define SYS_getdents64 61
+#endif
+#endif /* !defined(SYS_getdents64) */
+
+static inline ssize_t perf_getdents64(int fd, void *dirp, size_t count)
+{
+#ifdef MEMORY_SANITIZER
+	memset(dirp, 0, count);
+#endif
+	return syscall(SYS_getdents64, fd, dirp, count);
+}
+
+struct io_dirent64 {
+	ino64_t        d_ino;    /* 64-bit inode number */
+	off64_t        d_off;    /* 64-bit offset to next structure */
+	unsigned short d_reclen; /* Size of this dirent */
+	unsigned char  d_type;   /* File type */
+	char           d_name[NAME_MAX + 1]; /* Filename (null-terminated) */
+};
+
+struct io_dir {
+	int dirfd;
+	ssize_t available_bytes;
+	struct io_dirent64 *next;
+	struct io_dirent64 buff[4];
+};
+
+static inline void io_dir__init(struct io_dir *iod, int dirfd)
+{
+	iod->dirfd = dirfd;
+	iod->available_bytes = 0;
+}
+
+static inline void io_dir__rewinddir(struct io_dir *iod)
+{
+	lseek(iod->dirfd, 0, SEEK_SET);
+	iod->available_bytes = 0;
+}
+
+static inline struct io_dirent64 *io_dir__readdir(struct io_dir *iod)
+{
+	struct io_dirent64 *entry;
+
+	if (iod->available_bytes <= 0) {
+		ssize_t rc = perf_getdents64(iod->dirfd, iod->buff, sizeof(iod->buff));
+
+		if (rc <= 0)
+			return NULL;
+		iod->available_bytes = rc;
+		iod->next = iod->buff;
+	}
+	entry = iod->next;
+	iod->next = (struct io_dirent64 *)((char *)entry + entry->d_reclen);
+	iod->available_bytes -= entry->d_reclen;
+	return entry;
+}
+
+static inline bool io_dir__is_dir(const struct io_dir *iod, struct io_dirent64 *dent)
+{
+	if (dent->d_type == DT_UNKNOWN) {
+		struct stat st;
+
+		if (fstatat(iod->dirfd, dent->d_name, &st, /*flags=*/0))
+			return false;
+
+		if (S_ISDIR(st.st_mode)) {
+			dent->d_type = DT_DIR;
+			return true;
+		}
+	}
+	return dent->d_type == DT_DIR;
+}
+
+#endif  /* __API_IO_DIR__ */