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, 917 insertions, 0 deletions

diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c
new file mode 100644
index 000000000..83005b30b
--- /dev/null
+++ b/tools/perf/util/jitdump.c
@@ -0,0 +1,917 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <sys/sysmacros.h>
+#include <sys/types.h>
+#include <errno.h>
+#include <libgen.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <fcntl.h>
+#include <unistd.h>
+#include <inttypes.h>
+#include <byteswap.h>
+#include <sys/stat.h>
+#include <sys/mman.h>
+#include <linux/stringify.h>
+
+#include "event.h"
+#include "debug.h"
+#include "dso.h"
+#include "evlist.h"
+#include "namespaces.h"
+#include "symbol.h"
+#include <elf.h>
+
+#include "tsc.h"
+#include "session.h"
+#include "jit.h"
+#include "jitdump.h"
+#include "genelf.h"
+#include "thread.h"
+
+#include <linux/ctype.h>
+#include <linux/zalloc.h>
+
+struct jit_buf_desc {
+	struct perf_data *output;
+	struct perf_session *session;
+	struct machine *machine;
+	struct nsinfo  *nsi;
+	union jr_entry   *entry;
+	void             *buf;
+	uint64_t	 sample_type;
+	size_t           bufsize;
+	FILE             *in;
+	bool		 needs_bswap; /* handles cross-endianness */
+	bool		 use_arch_timestamp;
+	void		 *debug_data;
+	void		 *unwinding_data;
+	uint64_t	 unwinding_size;
+	uint64_t	 unwinding_mapped_size;
+	uint64_t         eh_frame_hdr_size;
+	size_t		 nr_debug_entries;
+	uint32_t         code_load_count;
+	u64		 bytes_written;
+	struct rb_root   code_root;
+	char		 dir[PATH_MAX];
+};
+
+struct jit_tool {
+	struct perf_tool tool;
+	struct perf_data	output;
+	struct perf_data	input;
+	u64 bytes_written;
+};
+
+#define hmax(a, b) ((a) > (b) ? (a) : (b))
+#define get_jit_tool(t) (container_of(tool, struct jit_tool, tool))
+
+static int
+jit_emit_elf(struct jit_buf_desc *jd,
+	     char *filename,
+	     const char *sym,
+	     uint64_t code_addr,
+	     const void *code,
+	     int csize,
+	     void *debug,
+	     int nr_debug_entries,
+	     void *unwinding,
+	     uint32_t unwinding_header_size,
+	     uint32_t unwinding_size)
+{
+	int ret, fd, saved_errno;
+	struct nscookie nsc;
+
+	if (verbose > 0)
+		fprintf(stderr, "write ELF image %s\n", filename);
+
+	nsinfo__mountns_enter(jd->nsi, &nsc);
+	fd = open(filename, O_CREAT|O_TRUNC|O_WRONLY, 0644);
+	saved_errno = errno;
+	nsinfo__mountns_exit(&nsc);
+	if (fd == -1) {
+		errno = saved_errno;
+		pr_warning("cannot create jit ELF %s: %m\n", filename);
+		return -1;
+	}
+
+	ret = jit_write_elf(fd, code_addr, sym, (const void *)code, csize, debug, nr_debug_entries,
+			    unwinding, unwinding_header_size, unwinding_size);
+
+        close(fd);
+
+	if (ret) {
+		nsinfo__mountns_enter(jd->nsi, &nsc);
+		unlink(filename);
+		nsinfo__mountns_exit(&nsc);
+	}
+
+	return ret;
+}
+
+static void
+jit_close(struct jit_buf_desc *jd)
+{
+	if (!(jd && jd->in))
+		return;
+	funlockfile(jd->in);
+	fclose(jd->in);
+	jd->in = NULL;
+}
+
+static int
+jit_validate_events(struct perf_session *session)
+{
+	struct evsel *evsel;
+
+	/*
+	 * check that all events use CLOCK_MONOTONIC
+	 */
+	evlist__for_each_entry(session->evlist, evsel) {
+		if (evsel->core.attr.use_clockid == 0 || evsel->core.attr.clockid != CLOCK_MONOTONIC)
+			return -1;
+	}
+	return 0;
+}
+
+static int
+jit_open(struct jit_buf_desc *jd, const char *name)
+{
+	struct jitheader header;
+	struct nscookie nsc;
+	struct jr_prefix *prefix;
+	ssize_t bs, bsz = 0;
+	void *n, *buf = NULL;
+	int ret, retval = -1;
+
+	nsinfo__mountns_enter(jd->nsi, &nsc);
+	jd->in = fopen(name, "r");
+	nsinfo__mountns_exit(&nsc);
+	if (!jd->in)
+		return -1;
+
+	bsz = hmax(sizeof(header), sizeof(*prefix));
+
+	buf = malloc(bsz);
+	if (!buf)
+		goto error;
+
+	/*
+	 * protect from writer modifying the file while we are reading it
+	 */
+	flockfile(jd->in);
+
+	ret = fread(buf, sizeof(header), 1, jd->in);
+	if (ret != 1)
+		goto error;
+
+	memcpy(&header, buf, sizeof(header));
+
+	if (header.magic != JITHEADER_MAGIC) {
+		if (header.magic != JITHEADER_MAGIC_SW)
+			goto error;
+		jd->needs_bswap = true;
+	}
+
+	if (jd->needs_bswap) {
+		header.version    = bswap_32(header.version);
+		header.total_size = bswap_32(header.total_size);
+		header.pid	  = bswap_32(header.pid);
+		header.elf_mach   = bswap_32(header.elf_mach);
+		header.timestamp  = bswap_64(header.timestamp);
+		header.flags      = bswap_64(header.flags);
+	}
+
+	jd->use_arch_timestamp = header.flags & JITDUMP_FLAGS_ARCH_TIMESTAMP;
+
+	if (verbose > 2)
+		pr_debug("version=%u\nhdr.size=%u\nts=0x%llx\npid=%d\nelf_mach=%d\nuse_arch_timestamp=%d\n",
+			header.version,
+			header.total_size,
+			(unsigned long long)header.timestamp,
+			header.pid,
+			header.elf_mach,
+			jd->use_arch_timestamp);
+
+	if (header.version > JITHEADER_VERSION) {
+		pr_err("wrong jitdump version %u, expected " __stringify(JITHEADER_VERSION),
+			header.version);
+		goto error;
+	}
+
+	if (header.flags & JITDUMP_FLAGS_RESERVED) {
+		pr_err("jitdump file contains invalid or unsupported flags 0x%llx\n",
+		       (unsigned long long)header.flags & JITDUMP_FLAGS_RESERVED);
+		goto error;
+	}
+
+	if (jd->use_arch_timestamp && !jd->session->time_conv.time_mult) {
+		pr_err("jitdump file uses arch timestamps but there is no timestamp conversion\n");
+		goto error;
+	}
+
+	/*
+	 * validate event is using the correct clockid
+	 */
+	if (!jd->use_arch_timestamp && jit_validate_events(jd->session)) {
+		pr_err("error, jitted code must be sampled with perf record -k 1\n");
+		goto error;
+	}
+
+	bs = header.total_size - sizeof(header);
+
+	if (bs > bsz) {
+		n = realloc(buf, bs);
+		if (!n)
+			goto error;
+		bsz = bs;
+		buf = n;
+		/* read extra we do not know about */
+		ret = fread(buf, bs - bsz, 1, jd->in);
+		if (ret != 1)
+			goto error;
+	}
+	/*
+	 * keep dirname for generating files and mmap records
+	 */
+	strncpy(jd->dir, name, PATH_MAX - 1);
+	jd->dir[PATH_MAX - 1] = '\0';
+	dirname(jd->dir);
+	free(buf);
+
+	return 0;
+error:
+	free(buf);
+	funlockfile(jd->in);
+	fclose(jd->in);
+	return retval;
+}
+
+static union jr_entry *
+jit_get_next_entry(struct jit_buf_desc *jd)
+{
+	struct jr_prefix *prefix;
+	union jr_entry *jr;
+	void *addr;
+	size_t bs, size;
+	int id, ret;
+
+	if (!(jd && jd->in))
+		return NULL;
+
+	if (jd->buf == NULL) {
+		size_t sz = getpagesize();
+		if (sz < sizeof(*prefix))
+			sz = sizeof(*prefix);
+
+		jd->buf = malloc(sz);
+		if (jd->buf == NULL)
+			return NULL;
+
+		jd->bufsize = sz;
+	}
+
+	prefix = jd->buf;
+
+	/*
+	 * file is still locked at this point
+	 */
+	ret = fread(prefix, sizeof(*prefix), 1, jd->in);
+	if (ret  != 1)
+		return NULL;
+
+	if (jd->needs_bswap) {
+		prefix->id   	   = bswap_32(prefix->id);
+		prefix->total_size = bswap_32(prefix->total_size);
+		prefix->timestamp  = bswap_64(prefix->timestamp);
+	}
+	id   = prefix->id;
+	size = prefix->total_size;
+
+	bs = (size_t)size;
+	if (bs < sizeof(*prefix))
+		return NULL;
+
+	if (id >= JIT_CODE_MAX) {
+		pr_warning("next_entry: unknown record type %d, skipping\n", id);
+	}
+	if (bs > jd->bufsize) {
+		void *n;
+		n = realloc(jd->buf, bs);
+		if (!n)
+			return NULL;
+		jd->buf = n;
+		jd->bufsize = bs;
+	}
+
+	addr = ((void *)jd->buf) + sizeof(*prefix);
+
+	ret = fread(addr, bs - sizeof(*prefix), 1, jd->in);
+	if (ret != 1)
+		return NULL;
+
+	jr = (union jr_entry *)jd->buf;
+
+	switch(id) {
+	case JIT_CODE_DEBUG_INFO:
+		if (jd->needs_bswap) {
+			uint64_t n;
+			jr->info.code_addr = bswap_64(jr->info.code_addr);
+			jr->info.nr_entry  = bswap_64(jr->info.nr_entry);
+			for (n = 0 ; n < jr->info.nr_entry; n++) {
+				jr->info.entries[n].addr    = bswap_64(jr->info.entries[n].addr);
+				jr->info.entries[n].lineno  = bswap_32(jr->info.entries[n].lineno);
+				jr->info.entries[n].discrim = bswap_32(jr->info.entries[n].discrim);
+			}
+		}
+		break;
+	case JIT_CODE_UNWINDING_INFO:
+		if (jd->needs_bswap) {
+			jr->unwinding.unwinding_size = bswap_64(jr->unwinding.unwinding_size);
+			jr->unwinding.eh_frame_hdr_size = bswap_64(jr->unwinding.eh_frame_hdr_size);
+			jr->unwinding.mapped_size = bswap_64(jr->unwinding.mapped_size);
+		}
+		break;
+	case JIT_CODE_CLOSE:
+		break;
+	case JIT_CODE_LOAD:
+		if (jd->needs_bswap) {
+			jr->load.pid       = bswap_32(jr->load.pid);
+			jr->load.tid       = bswap_32(jr->load.tid);
+			jr->load.vma       = bswap_64(jr->load.vma);
+			jr->load.code_addr = bswap_64(jr->load.code_addr);
+			jr->load.code_size = bswap_64(jr->load.code_size);
+			jr->load.code_index= bswap_64(jr->load.code_index);
+		}
+		jd->code_load_count++;
+		break;
+	case JIT_CODE_MOVE:
+		if (jd->needs_bswap) {
+			jr->move.pid           = bswap_32(jr->move.pid);
+			jr->move.tid           = bswap_32(jr->move.tid);
+			jr->move.vma           = bswap_64(jr->move.vma);
+			jr->move.old_code_addr = bswap_64(jr->move.old_code_addr);
+			jr->move.new_code_addr = bswap_64(jr->move.new_code_addr);
+			jr->move.code_size     = bswap_64(jr->move.code_size);
+			jr->move.code_index    = bswap_64(jr->move.code_index);
+		}
+		break;
+	case JIT_CODE_MAX:
+	default:
+		/* skip unknown record (we have read them) */
+		break;
+	}
+	return jr;
+}
+
+static int
+jit_inject_event(struct jit_buf_desc *jd, union perf_event *event)
+{
+	ssize_t size;
+
+	size = perf_data__write(jd->output, event, event->header.size);
+	if (size < 0)
+		return -1;
+
+	jd->bytes_written += size;
+	return 0;
+}
+
+static pid_t jr_entry_pid(struct jit_buf_desc *jd, union jr_entry *jr)
+{
+	if (jd->nsi && nsinfo__in_pidns(jd->nsi))
+		return nsinfo__tgid(jd->nsi);
+	return jr->load.pid;
+}
+
+static pid_t jr_entry_tid(struct jit_buf_desc *jd, union jr_entry *jr)
+{
+	if (jd->nsi && nsinfo__in_pidns(jd->nsi))
+		return nsinfo__pid(jd->nsi);
+	return jr->load.tid;
+}
+
+static uint64_t convert_timestamp(struct jit_buf_desc *jd, uint64_t timestamp)
+{
+	struct perf_tsc_conversion tc = { .time_shift = 0, };
+	struct perf_record_time_conv *time_conv = &jd->session->time_conv;
+
+	if (!jd->use_arch_timestamp)
+		return timestamp;
+
+	tc.time_shift = time_conv->time_shift;
+	tc.time_mult  = time_conv->time_mult;
+	tc.time_zero  = time_conv->time_zero;
+
+	/*
+	 * The event TIME_CONV was extended for the fields from "time_cycles"
+	 * when supported cap_user_time_short, for backward compatibility,
+	 * checks the event size and assigns these extended fields if these
+	 * fields are contained in the event.
+	 */
+	if (event_contains(*time_conv, cap_user_time_short)) {
+		tc.time_cycles	       = time_conv->time_cycles;
+		tc.time_mask	       = time_conv->time_mask;
+		tc.cap_user_time_zero  = time_conv->cap_user_time_zero;
+		tc.cap_user_time_short = time_conv->cap_user_time_short;
+
+		if (!tc.cap_user_time_zero)
+			return 0;
+	}
+
+	return tsc_to_perf_time(timestamp, &tc);
+}
+
+static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr)
+{
+	struct perf_sample sample;
+	union perf_event *event;
+	const struct perf_tool *tool = jd->session->tool;
+	uint64_t code, addr;
+	uintptr_t uaddr;
+	char *filename;
+	struct stat st;
+	size_t size;
+	u16 idr_size;
+	const char *sym;
+	uint64_t count;
+	int ret, csize, usize;
+	pid_t nspid, pid, tid;
+	struct {
+		u32 pid, tid;
+		u64 time;
+	} *id;
+
+	nspid = jr->load.pid;
+	pid   = jr_entry_pid(jd, jr);
+	tid   = jr_entry_tid(jd, jr);
+	csize = jr->load.code_size;
+	usize = jd->unwinding_mapped_size;
+	addr  = jr->load.code_addr;
+	sym   = (void *)((unsigned long)jr + sizeof(jr->load));
+	code  = (unsigned long)jr + jr->load.p.total_size - csize;
+	count = jr->load.code_index;
+	idr_size = jd->machine->id_hdr_size;
+
+	event = calloc(1, sizeof(*event) + idr_size);
+	if (!event)
+		return -1;
+
+	filename = event->mmap2.filename;
+	size = snprintf(filename, PATH_MAX, "%s/jitted-%d-%" PRIu64 ".so",
+			jd->dir,
+			nspid,
+			count);
+
+	size++; /* for \0 */
+
+	size = PERF_ALIGN(size, sizeof(u64));
+	uaddr = (uintptr_t)code;
+	ret = jit_emit_elf(jd, filename, sym, addr, (const void *)uaddr, csize, jd->debug_data, jd->nr_debug_entries,
+			   jd->unwinding_data, jd->eh_frame_hdr_size, jd->unwinding_size);
+
+	if (jd->debug_data && jd->nr_debug_entries) {
+		zfree(&jd->debug_data);
+		jd->nr_debug_entries = 0;
+	}
+
+	if (jd->unwinding_data && jd->eh_frame_hdr_size) {
+		zfree(&jd->unwinding_data);
+		jd->eh_frame_hdr_size = 0;
+		jd->unwinding_mapped_size = 0;
+		jd->unwinding_size = 0;
+	}
+
+	if (ret) {
+		free(event);
+		return -1;
+	}
+	if (nsinfo__stat(filename, &st, jd->nsi))
+		memset(&st, 0, sizeof(st));
+
+	event->mmap2.header.type = PERF_RECORD_MMAP2;
+	event->mmap2.header.misc = PERF_RECORD_MISC_USER;
+	event->mmap2.header.size = (sizeof(event->mmap2) -
+			(sizeof(event->mmap2.filename) - size) + idr_size);
+
+	event->mmap2.pgoff = GEN_ELF_TEXT_OFFSET;
+	event->mmap2.start = addr;
+	event->mmap2.len   = usize ? ALIGN_8(csize) + usize : csize;
+	event->mmap2.pid   = pid;
+	event->mmap2.tid   = tid;
+	event->mmap2.ino   = st.st_ino;
+	event->mmap2.maj   = major(st.st_dev);
+	event->mmap2.min   = minor(st.st_dev);
+	event->mmap2.prot  = st.st_mode;
+	event->mmap2.flags = MAP_SHARED;
+	event->mmap2.ino_generation = 1;
+
+	id = (void *)((unsigned long)event + event->mmap.header.size - idr_size);
+	if (jd->sample_type & PERF_SAMPLE_TID) {
+		id->pid  = pid;
+		id->tid  = tid;
+	}
+	if (jd->sample_type & PERF_SAMPLE_TIME)
+		id->time = convert_timestamp(jd, jr->load.p.timestamp);
+
+	/*
+	 * create pseudo sample to induce dso hit increment
+	 * use first address as sample address
+	 */
+	perf_sample__init(&sample, /*all=*/true);
+	sample.cpumode = PERF_RECORD_MISC_USER;
+	sample.pid  = pid;
+	sample.tid  = tid;
+	sample.time = id->time;
+	sample.ip   = addr;
+
+	ret = perf_event__process_mmap2(tool, event, &sample, jd->machine);
+	if (ret)
+		goto out;
+
+	ret = jit_inject_event(jd, event);
+	/*
+	 * mark dso as use to generate buildid in the header
+	 */
+	if (!ret) {
+		struct dso_id dso_id = {
+			{
+				.maj = event->mmap2.maj,
+				.min = event->mmap2.min,
+				.ino = event->mmap2.ino,
+				.ino_generation = event->mmap2.ino_generation,
+			},
+			.mmap2_valid = true,
+			.mmap2_ino_generation_valid = true,
+		};
+		struct dso *dso = machine__findnew_dso_id(jd->machine, filename, &dso_id);
+
+		if (dso)
+			dso__set_hit(dso);
+
+		dso__put(dso);
+	}
+out:
+	perf_sample__exit(&sample);
+	free(event);
+	return ret;
+}
+
+static int jit_repipe_code_move(struct jit_buf_desc *jd, union jr_entry *jr)
+{
+	struct perf_sample sample;
+	union perf_event *event;
+	const struct perf_tool *tool = jd->session->tool;
+	char *filename;
+	size_t size;
+	struct stat st;
+	int usize;
+	u16 idr_size;
+	int ret;
+	pid_t nspid, pid, tid;
+	struct {
+		u32 pid, tid;
+		u64 time;
+	} *id;
+
+	nspid = jr->load.pid;
+	pid   = jr_entry_pid(jd, jr);
+	tid   = jr_entry_tid(jd, jr);
+	usize = jd->unwinding_mapped_size;
+	idr_size = jd->machine->id_hdr_size;
+
+	/*
+	 * +16 to account for sample_id_all (hack)
+	 */
+	event = calloc(1, sizeof(*event) + 16);
+	if (!event)
+		return -1;
+
+	filename = event->mmap2.filename;
+	size = snprintf(filename, PATH_MAX, "%s/jitted-%d-%" PRIu64 ".so",
+	         jd->dir,
+		 nspid,
+		 jr->move.code_index);
+
+	size++; /* for \0 */
+
+	if (nsinfo__stat(filename, &st, jd->nsi))
+		memset(&st, 0, sizeof(st));
+
+	size = PERF_ALIGN(size, sizeof(u64));
+
+	event->mmap2.header.type = PERF_RECORD_MMAP2;
+	event->mmap2.header.misc = PERF_RECORD_MISC_USER;
+	event->mmap2.header.size = (sizeof(event->mmap2) -
+			(sizeof(event->mmap2.filename) - size) + idr_size);
+	event->mmap2.pgoff = GEN_ELF_TEXT_OFFSET;
+	event->mmap2.start = jr->move.new_code_addr;
+	event->mmap2.len   = usize ? ALIGN_8(jr->move.code_size) + usize
+				   : jr->move.code_size;
+	event->mmap2.pid   = pid;
+	event->mmap2.tid   = tid;
+	event->mmap2.ino   = st.st_ino;
+	event->mmap2.maj   = major(st.st_dev);
+	event->mmap2.min   = minor(st.st_dev);
+	event->mmap2.prot  = st.st_mode;
+	event->mmap2.flags = MAP_SHARED;
+	event->mmap2.ino_generation = 1;
+
+	id = (void *)((unsigned long)event + event->mmap.header.size - idr_size);
+	if (jd->sample_type & PERF_SAMPLE_TID) {
+		id->pid  = pid;
+		id->tid  = tid;
+	}
+	if (jd->sample_type & PERF_SAMPLE_TIME)
+		id->time = convert_timestamp(jd, jr->load.p.timestamp);
+
+	/*
+	 * create pseudo sample to induce dso hit increment
+	 * use first address as sample address
+	 */
+	perf_sample__init(&sample, /*all=*/true);
+	sample.cpumode = PERF_RECORD_MISC_USER;
+	sample.pid  = pid;
+	sample.tid  = tid;
+	sample.time = id->time;
+	sample.ip   = jr->move.new_code_addr;
+
+	ret = perf_event__process_mmap2(tool, event, &sample, jd->machine);
+	if (ret)
+		goto out;
+
+	ret = jit_inject_event(jd, event);
+	if (!ret)
+		build_id__mark_dso_hit(tool, event, &sample, jd->machine);
+out:
+	perf_sample__exit(&sample);
+	return ret;
+}
+
+static int jit_repipe_debug_info(struct jit_buf_desc *jd, union jr_entry *jr)
+{
+	void *data;
+	size_t sz;
+
+	if (!(jd && jr))
+		return -1;
+
+	sz  = jr->prefix.total_size - sizeof(jr->info);
+	data = malloc(sz);
+	if (!data)
+		return -1;
+
+	memcpy(data, &jr->info.entries, sz);
+
+	jd->debug_data       = data;
+
+	/*
+	 * we must use nr_entry instead of size here because
+	 * we cannot distinguish actual entry from padding otherwise
+	 */
+	jd->nr_debug_entries = jr->info.nr_entry;
+
+	return 0;
+}
+
+static int
+jit_repipe_unwinding_info(struct jit_buf_desc *jd, union jr_entry *jr)
+{
+	void *unwinding_data;
+	uint32_t unwinding_data_size;
+
+	if (!(jd && jr))
+		return -1;
+
+	unwinding_data_size  = jr->prefix.total_size - sizeof(jr->unwinding);
+	unwinding_data = malloc(unwinding_data_size);
+	if (!unwinding_data)
+		return -1;
+
+	memcpy(unwinding_data, &jr->unwinding.unwinding_data,
+	       unwinding_data_size);
+
+	jd->eh_frame_hdr_size = jr->unwinding.eh_frame_hdr_size;
+	jd->unwinding_size = jr->unwinding.unwinding_size;
+	jd->unwinding_mapped_size = jr->unwinding.mapped_size;
+	free(jd->unwinding_data);
+	jd->unwinding_data = unwinding_data;
+
+	return 0;
+}
+
+static int
+jit_process_dump(struct jit_buf_desc *jd)
+{
+	union jr_entry *jr;
+	int ret = 0;
+
+	while ((jr = jit_get_next_entry(jd))) {
+		switch(jr->prefix.id) {
+		case JIT_CODE_LOAD:
+			ret = jit_repipe_code_load(jd, jr);
+			break;
+		case JIT_CODE_MOVE:
+			ret = jit_repipe_code_move(jd, jr);
+			break;
+		case JIT_CODE_DEBUG_INFO:
+			ret = jit_repipe_debug_info(jd, jr);
+			break;
+		case JIT_CODE_UNWINDING_INFO:
+			ret = jit_repipe_unwinding_info(jd, jr);
+			break;
+		default:
+			ret = 0;
+			continue;
+		}
+	}
+	return ret;
+}
+
+static int
+jit_inject(struct jit_buf_desc *jd, const char *path)
+{
+	int ret;
+
+	if (verbose > 0)
+		fprintf(stderr, "injecting: %s\n", path);
+
+	ret = jit_open(jd, path);
+	if (ret)
+		return -1;
+
+	ret = jit_process_dump(jd);
+
+	jit_close(jd);
+
+	if (verbose > 0)
+		fprintf(stderr, "injected: %s (%d)\n", path, ret);
+
+	return 0;
+}
+
+/*
+ * File must be with pattern .../jit-XXXX.dump
+ * where XXXX is the PID of the process which did the mmap()
+ * as captured in the RECORD_MMAP record
+ */
+static int
+jit_detect(const char *mmap_name, pid_t pid, struct nsinfo *nsi, bool *in_pidns)
+ {
+	const char *p;
+	char *end = NULL;
+	pid_t pid2;
+
+	if (verbose > 2)
+		fprintf(stderr, "jit marker trying : %s\n", mmap_name);
+	/*
+	 * get file name
+	 */
+	p = strrchr(mmap_name, '/');
+	if (!p)
+		return -1;
+
+	/*
+	 * match prefix
+	 */
+	if (strncmp(p, "/jit-", 5))
+		return -1;
+
+	/*
+	 * skip prefix
+	 */
+	p += 5;
+
+	/*
+	 * must be followed by a pid
+	 */
+	if (!isdigit(*p))
+		return -1;
+
+	pid2 = (int)strtol(p, &end, 10);
+	if (!end)
+		return -1;
+
+	*in_pidns = pid == nsinfo__nstgid(nsi);
+	/*
+	 * pid does not match mmap pid
+	 * pid==0 in system-wide mode (synthesized)
+	 *
+	 * If the pid in the file name is equal to the nstgid, then
+	 * the agent ran inside a container and perf outside the
+	 * container, so record it for further use in jit_inject().
+	 */
+	if (pid && !(pid2 == pid || *in_pidns))
+		return -1;
+	/*
+	 * validate suffix
+	 */
+	if (strcmp(end, ".dump"))
+		return -1;
+
+	if (verbose > 0)
+		fprintf(stderr, "jit marker found: %s\n", mmap_name);
+
+	return 0;
+}
+
+static void jit_add_pid(struct machine *machine, pid_t pid)
+{
+	struct thread *thread = machine__findnew_thread(machine, pid, pid);
+
+	if (!thread) {
+		pr_err("%s: thread %d not found or created\n", __func__, pid);
+		return;
+	}
+
+	thread__set_priv(thread, (void *)true);
+	thread__put(thread);
+}
+
+static bool jit_has_pid(struct machine *machine, pid_t pid)
+{
+	struct thread *thread = machine__find_thread(machine, pid, pid);
+	void *priv;
+
+	if (!thread)
+		return false;
+
+	priv = thread__priv(thread);
+	thread__put(thread);
+	return (bool)priv;
+}
+
+int
+jit_process(struct perf_session *session,
+	    struct perf_data *output,
+	    struct machine *machine,
+	    const char *filename,
+	    pid_t pid,
+	    pid_t tid,
+	    u64 *nbytes)
+{
+	struct thread *thread;
+	struct nsinfo *nsi;
+	struct evsel *first;
+	struct jit_buf_desc jd;
+	bool in_pidns = false;
+	int ret;
+
+	thread = machine__findnew_thread(machine, pid, tid);
+	if (thread == NULL) {
+		pr_err("problem processing JIT mmap event, skipping it.\n");
+		return 0;
+	}
+
+	nsi = nsinfo__get(thread__nsinfo(thread));
+	thread__put(thread);
+
+	/*
+	 * first, detect marker mmap (i.e., the jitdump mmap)
+	 */
+	if (jit_detect(filename, pid, nsi, &in_pidns)) {
+		nsinfo__put(nsi);
+
+		/*
+		 * Strip //anon*, [anon:* and /memfd:* mmaps if we processed a jitdump for this pid
+		 */
+		if (jit_has_pid(machine, pid) &&
+			((strncmp(filename, "//anon", 6) == 0) ||
+			 (strncmp(filename, "[anon:", 6) == 0) ||
+			 (strncmp(filename, "/memfd:", 7) == 0)))
+			return 1;
+
+		return 0;
+	}
+
+	memset(&jd, 0, sizeof(jd));
+
+	jd.session = session;
+	jd.output  = output;
+	jd.machine = machine;
+	jd.nsi = nsi;
+
+	if (in_pidns)
+		nsinfo__set_in_pidns(nsi);
+
+	/*
+	 * track sample_type to compute id_all layout
+	 * perf sets the same sample type to all events as of now
+	 */
+	first = evlist__first(session->evlist);
+	jd.sample_type = first->core.attr.sample_type;
+
+	*nbytes = 0;
+
+	ret = jit_inject(&jd, filename);
+	if (!ret) {
+		jit_add_pid(machine, pid);
+		*nbytes = jd.bytes_written;
+		ret = 1;
+	}
+
+	nsinfo__put(jd.nsi);
+	free(jd.buf);
+
+	return ret;
+}