freebsd-skq/usr.bin/procstat/procstat_files.c
John Baldwin 6bc1e9cd84 Rework the lifetime management of the kernel implementation of POSIX
semaphores.  Specifically, semaphores are now represented as new file
descriptor type that is set to close on exec.  This removes the need for
all of the manual process reference counting (and fork, exec, and exit
event handlers) as the normal file descriptor operations handle all of
that for us nicely.  It is also suggested as one possible implementation
in the spec and at least one other OS (OS X) uses this approach.

Some bugs that were fixed as a result include:
- References to a named semaphore whose name is removed still work after
  the sem_unlink() operation.  Prior to this patch, if a semaphore's name
  was removed, valid handles from sem_open() would get EINVAL errors from
  sem_getvalue(), sem_post(), etc.  This fixes that.
- Unnamed semaphores created with sem_init() were not cleaned up when a
  process exited or exec'd.  They were only cleaned up if the process
  did an explicit sem_destroy().  This could result in a leak of semaphore
  objects that could never be cleaned up.
- On the other hand, if another process guessed the id (kernel pointer to
  'struct ksem' of an unnamed semaphore (created via sem_init)) and had
  write access to the semaphore based on UID/GID checks, then that other
  process could manipulate the semaphore via sem_destroy(), sem_post(),
  sem_wait(), etc.
- As part of the permission check (UID/GID), the umask of the proces
  creating the semaphore was not honored.  Thus if your umask denied group
  read/write access but the explicit mode in the sem_init() call allowed
  it, the semaphore would be readable/writable by other users in the
  same group, for example.  This includes access via the previous bug.
- If the module refused to unload because there were active semaphores,
  then it might have deregistered one or more of the semaphore system
  calls before it noticed that there was a problem.  I'm not sure if
  this actually happened as the order that modules are discovered by the
  kernel linker depends on how the actual .ko file is linked.  One can
  make the order deterministic by using a single module with a mod_event
  handler that explicitly registers syscalls (and deregisters during
  unload after any checks).  This also fixes a race where even if the
  sem_module unloaded first it would have destroyed locks that the
  syscalls might be trying to access if they are still executing when
  they are unloaded.

  XXX: By the way, deregistering system calls doesn't do any blocking
  to drain any threads from the calls.
- Some minor fixes to errno values on error.  For example, sem_init()
  isn't documented to return ENFILE or EMFILE if we run out of semaphores
  the way that sem_open() can.  Instead, it should return ENOSPC in that
  case.

Other changes:
- Kernel semaphores now use a hash table to manage the namespace of
  named semaphores nearly in a similar fashion to the POSIX shared memory
  object file descriptors.  Kernel semaphores can now also have names
  longer than 14 chars (up to MAXPATHLEN) and can include subdirectories
  in their pathname.
- The UID/GID permission checks for access to a named semaphore are now
  done via vaccess() rather than a home-rolled set of checks.
- Now that kernel semaphores have an associated file object, the various
  MAC checks for POSIX semaphores accept both a file credential and an
  active credential.  There is also a new posixsem_check_stat() since it
  is possible to fstat() a semaphore file descriptor.
- A small set of regression tests (using the ksem API directly) is present
  in src/tools/regression/posixsem.

Reported by:	kris (1)
Tested by:	kris
Reviewed by:	rwatson (lightly)
MFC after:	1 month
2008-06-27 05:39:04 +00:00

338 lines
7.2 KiB
C

/*-
* Copyright (c) 2007 Robert N. M. Watson
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
*
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*
* $FreeBSD$
*/
#include <sys/types.h>
#include <sys/socket.h>
#include <sys/sysctl.h>
#include <sys/un.h>
#include <sys/user.h>
#include <netinet/in.h>
#include <arpa/inet.h>
#include <err.h>
#include <inttypes.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include "procstat.h"
static const char *
protocol_to_string(int domain, int type, int protocol)
{
switch (domain) {
case AF_INET:
case AF_INET6:
switch (protocol) {
case IPPROTO_TCP:
return ("TCP");
case IPPROTO_UDP:
return ("UDP");
case IPPROTO_ICMP:
return ("ICM");
case IPPROTO_RAW:
return ("RAW");
case IPPROTO_SCTP:
return ("SCT");
case IPPROTO_DIVERT:
return ("IPD");
default:
return ("IP?");
}
case AF_LOCAL:
switch (type) {
case SOCK_STREAM:
return ("UDS");
case SOCK_DGRAM:
return ("UDD");
default:
return ("UD?");
}
default:
return ("?");
}
}
static void
addr_to_string(struct sockaddr_storage *ss, char *buffer, int buflen)
{
char buffer2[INET6_ADDRSTRLEN];
struct sockaddr_in6 *sin6;
struct sockaddr_in *sin;
struct sockaddr_un *sun;
switch (ss->ss_family) {
case AF_LOCAL:
sun = (struct sockaddr_un *)ss;
if (strlen(sun->sun_path) == 0)
strlcpy(buffer, "-", buflen);
else
strlcpy(buffer, sun->sun_path, buflen);
break;
case AF_INET:
sin = (struct sockaddr_in *)ss;
snprintf(buffer, buflen, "%s:%d", inet_ntoa(sin->sin_addr),
ntohs(sin->sin_port));
break;
case AF_INET6:
sin6 = (struct sockaddr_in6 *)ss;
if (inet_ntop(AF_INET6, &sin6->sin6_addr, buffer2,
sizeof(buffer2)) != NULL)
snprintf(buffer, buflen, "%s.%d", buffer2,
ntohs(sin6->sin6_port));
else
strlcpy(buffer, "-", sizeof(buffer));
break;
default:
strlcpy(buffer, "", buflen);
break;
}
}
static void
print_address(struct sockaddr_storage *ss)
{
char addr[PATH_MAX];
addr_to_string(ss, addr, sizeof(addr));
printf("%s", addr);
}
void
procstat_files(pid_t pid, struct kinfo_proc *kipp)
{
struct kinfo_file *freep, *kif;
int error, name[4];
unsigned int i;
const char *str;
size_t len;
if (!hflag)
printf("%5s %-16s %4s %1s %1s %-8s %3s %7s %-3s %-12s\n",
"PID", "COMM", "FD", "T", "V", "FLAGS", "REF", "OFFSET",
"PRO", "NAME");
name[0] = CTL_KERN;
name[1] = KERN_PROC;
name[2] = KERN_PROC_FILEDESC;
name[3] = pid;
error = sysctl(name, 4, NULL, &len, NULL, 0);
if (error < 0 && errno != ESRCH && errno != EPERM) {
warn("sysctl: kern.proc.filedesc: %d", pid);
return;
}
if (error < 0)
return;
freep = kif = malloc(len);
if (kif == NULL)
err(-1, "malloc");
if (sysctl(name, 4, kif, &len, NULL, 0) < 0) {
warn("sysctl: kern.proc.filedesc %d", pid);
free(freep);
return;
}
for (i = 0; i < len / sizeof(*kif); i++, kif++) {
if (kif->kf_structsize != sizeof(*kif))
errx(-1, "kinfo_file mismatch");
printf("%5d ", pid);
printf("%-16s ", kipp->ki_comm);
switch (kif->kf_fd) {
case KF_FD_TYPE_CWD:
printf(" cwd ");
break;
case KF_FD_TYPE_ROOT:
printf("root ");
break;
case KF_FD_TYPE_JAIL:
printf("jail ");
break;
default:
printf("%4d ", kif->kf_fd);
break;
}
switch (kif->kf_type) {
case KF_TYPE_VNODE:
str = "v";
break;
case KF_TYPE_SOCKET:
str = "s";
break;
case KF_TYPE_PIPE:
str = "p";
break;
case KF_TYPE_FIFO:
str = "f";
break;
case KF_TYPE_KQUEUE:
str = "k";
break;
case KF_TYPE_CRYPTO:
str = "c";
break;
case KF_TYPE_MQUEUE:
str = "m";
break;
case KF_TYPE_SHM:
str = "h";
break;
case KF_TYPE_SEM:
str = "e";
break;
case KF_TYPE_NONE:
case KF_TYPE_UNKNOWN:
default:
str = "?";
break;
}
printf("%1s ", str);
str = "-";
if (kif->kf_type == KF_TYPE_VNODE) {
switch (kif->kf_vnode_type) {
case KF_VTYPE_VREG:
str = "r";
break;
case KF_VTYPE_VDIR:
str = "d";
break;
case KF_VTYPE_VBLK:
str = "b";
break;
case KF_VTYPE_VCHR:
str = "c";
break;
case KF_VTYPE_VLNK:
str = "l";
break;
case KF_VTYPE_VSOCK:
str = "s";
break;
case KF_VTYPE_VFIFO:
str = "f";
break;
case KF_VTYPE_VBAD:
str = "x";
break;
case KF_VTYPE_VNON:
case KF_VTYPE_UNKNOWN:
default:
str = "?";
break;
}
}
printf("%1s ", str);
printf("%s", kif->kf_flags & KF_FLAG_READ ? "r" : "-");
printf("%s", kif->kf_flags & KF_FLAG_WRITE ? "w" : "-");
printf("%s", kif->kf_flags & KF_FLAG_APPEND ? "a" : "-");
printf("%s", kif->kf_flags & KF_FLAG_ASYNC ? "s" : "-");
printf("%s", kif->kf_flags & KF_FLAG_FSYNC ? "f" : "-");
printf("%s", kif->kf_flags & KF_FLAG_NONBLOCK ? "n" : "-");
printf("%s", kif->kf_flags & KF_FLAG_DIRECT ? "d" : "-");
printf("%s ", kif->kf_flags & KF_FLAG_HASLOCK ? "l" : "-");
if (kif->kf_ref_count > -1)
printf("%3d ", kif->kf_ref_count);
else
printf("%3c ", '-');
if (kif->kf_offset > -1)
printf("%7jd ", (intmax_t)kif->kf_offset);
else
printf("%7c ", '-');
switch (kif->kf_type) {
case KF_TYPE_VNODE:
case KF_TYPE_FIFO:
printf("%-3s ", "-");
printf("%-18s", kif->kf_path);
break;
case KF_TYPE_SOCKET:
printf("%-3s ",
protocol_to_string(kif->kf_sock_domain,
kif->kf_sock_type, kif->kf_sock_protocol));
/*
* While generally we like to print two addresses,
* local and peer, for sockets, it turns out to be
* more useful to print the first non-nul address for
* local sockets, as typically they aren't bound and
* connected, and the path strings can get long.
*/
if (kif->kf_sock_domain == AF_LOCAL) {
struct sockaddr_un *sun =
(struct sockaddr_un *)&kif->kf_sa_local;
if (sun->sun_path[0] != 0)
print_address(&kif->kf_sa_local);
else
print_address(&kif->kf_sa_peer);
} else {
print_address(&kif->kf_sa_local);
printf(" ");
print_address(&kif->kf_sa_peer);
}
break;
default:
printf("%-3s ", "-");
printf("%-18s", "-");
}
printf("\n");
}
free(freep);
}