git/compat/linux/procinfo.c

#include "git-compat-util.h"

#include "strbuf.h"
#include "strvec.h"
#include "trace2.h"

/*
 * We need more complex parsing in stat_parent_pid() and
 * parse_proc_stat() below than a dumb fscanf(). That's because while
 * the statcomm field is surrounded by parentheses, the process itself
 * is free to insert any arbitrary byte sequence its its name. That
 * can include newlines, spaces, closing parentheses etc.
 *
 * See do_task_stat() in fs/proc/array.c in linux.git, this is in
 * contrast with the escaped version of the name found in
 * /proc/%d/status.
 *
 * So instead of using fscanf() we'll read N bytes from it, look for
 * the first "(", and then the last ")", anything in-between is our
 * process name.
 *
 * How much N do we need? On Linux /proc/sys/kernel/pid_max is 2^15 by
 * default, but it can be raised set to values of up to 2^22. So
 * that's 7 digits for a PID. We have 2 PIDs in the first four fields
 * we're interested in, so 2 * 7 = 14.
 *
 * We then have 3 spaces between those four values, and we'd like to
 * get to the space between the 4th and the 5th (the "pgrp" field) to
 * make sure we read the entire "ppid" field. So that brings us up to
 * 14 + 3 + 1 = 18. Add the two parentheses around the "comm" value
 * and it's 20. The "state" value itself is then one character (now at
 * 21).
 *
 * Finally the maximum length of the "comm" name itself is 15
 * characters, e.g. a setting of "123456789abcdefg" will be truncated
 * to "123456789abcdef". See PR_SET_NAME in prctl(2). So all in all
 * we'd need to read 21 + 15 = 36 bytes.
 *
 * Let's just read 2^6 (64) instead for good measure. If PID_MAX ever
 * grows past 2^22 we'll be future-proof. We'll then anchor at the
 * last ")" we find to locate the parent PID.
 */
#define STAT_PARENT_PID_READ_N …

static int parse_proc_stat(struct strbuf *sb, struct strbuf *name,
			    int *statppid)
{ … }

static int stat_parent_pid(pid_t pid, struct strbuf *name, int *statppid)
{ … }

static void push_ancestry_name(struct strvec *names, pid_t pid)
{ … }

void trace2_collect_process_info(enum trace2_process_info_reason reason)
{ … }