freebsd-skq/lib/libufs/cgroup.c

317 lines
7.5 KiB
C
Raw Permalink Normal View History

/*-
* SPDX-License-Identifier: BSD-2-Clause-FreeBSD
*
* Copyright (c) 2003 Juli Mallett. All rights reserved.
*
* This software was written by Juli Mallett <jmallett@FreeBSD.org> for the
* FreeBSD project. Redistribution and use in source and binary forms, with
* or without modification, are permitted provided that the following
* conditions are met:
*
* 1. Redistribution of source code must retain the above copyright notice,
* this list of conditions and the following disclaimer.
* 2. Redistribution 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 ``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 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.
*/
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
#include <sys/param.h>
#include <sys/mount.h>
#include <sys/disklabel.h>
#include <sys/stat.h>
#include <ufs/ufs/extattr.h>
#include <ufs/ufs/quota.h>
#include <ufs/ufs/ufsmount.h>
#include <ufs/ufs/dinode.h>
#include <ufs/ffs/fs.h>
#include <errno.h>
#include <fcntl.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <libufs.h>
ufs2_daddr_t
cgballoc(struct uufsd *disk)
{
u_int8_t *blksfree;
struct cg *cgp;
struct fs *fs;
long bno;
fs = &disk->d_fs;
cgp = &disk->d_cg;
blksfree = cg_blksfree(cgp);
for (bno = 0; bno < fs->fs_fpg / fs->fs_frag; bno++)
if (ffs_isblock(fs, blksfree, bno))
goto gotit;
return (0);
gotit:
fs->fs_cs(fs, cgp->cg_cgx).cs_nbfree--;
ffs_clrblock(fs, blksfree, (long)bno);
ffs_clusteracct(fs, cgp, bno, -1);
cgp->cg_cs.cs_nbfree--;
fs->fs_cstotal.cs_nbfree--;
fs->fs_fmod = 1;
return (cgbase(fs, cgp->cg_cgx) + blkstofrags(fs, bno));
}
int
cgbfree(struct uufsd *disk, ufs2_daddr_t bno, long size)
{
u_int8_t *blksfree;
struct fs *fs;
struct cg *cgp;
ufs1_daddr_t fragno, cgbno;
int i, cg, blk, frags, bbase;
fs = &disk->d_fs;
cg = dtog(fs, bno);
if (cgread1(disk, cg) != 1)
return (-1);
cgp = &disk->d_cg;
cgbno = dtogd(fs, bno);
blksfree = cg_blksfree(cgp);
if (size == fs->fs_bsize) {
fragno = fragstoblks(fs, cgbno);
ffs_setblock(fs, blksfree, fragno);
ffs_clusteracct(fs, cgp, fragno, 1);
cgp->cg_cs.cs_nbfree++;
fs->fs_cstotal.cs_nbfree++;
fs->fs_cs(fs, cg).cs_nbfree++;
} else {
bbase = cgbno - fragnum(fs, cgbno);
/*
* decrement the counts associated with the old frags
*/
blk = blkmap(fs, blksfree, bbase);
ffs_fragacct(fs, blk, cgp->cg_frsum, -1);
/*
* deallocate the fragment
*/
frags = numfrags(fs, size);
for (i = 0; i < frags; i++)
setbit(blksfree, cgbno + i);
cgp->cg_cs.cs_nffree += i;
fs->fs_cstotal.cs_nffree += i;
fs->fs_cs(fs, cg).cs_nffree += i;
/*
* add back in counts associated with the new frags
*/
blk = blkmap(fs, blksfree, bbase);
ffs_fragacct(fs, blk, cgp->cg_frsum, 1);
/*
* if a complete block has been reassembled, account for it
*/
fragno = fragstoblks(fs, bbase);
if (ffs_isblock(fs, blksfree, fragno)) {
cgp->cg_cs.cs_nffree -= fs->fs_frag;
fs->fs_cstotal.cs_nffree -= fs->fs_frag;
fs->fs_cs(fs, cg).cs_nffree -= fs->fs_frag;
ffs_clusteracct(fs, cgp, fragno, 1);
cgp->cg_cs.cs_nbfree++;
fs->fs_cstotal.cs_nbfree++;
fs->fs_cs(fs, cg).cs_nbfree++;
}
}
return cgwrite(disk);
}
ino_t
cgialloc(struct uufsd *disk)
{
struct ufs2_dinode *dp2;
u_int8_t *inosused;
struct cg *cgp;
struct fs *fs;
ino_t ino;
int i;
fs = &disk->d_fs;
cgp = &disk->d_cg;
inosused = cg_inosused(cgp);
for (ino = 0; ino < fs->fs_ipg; ino++)
if (isclr(inosused, ino))
goto gotit;
return (0);
gotit:
if (fs->fs_magic == FS_UFS2_MAGIC &&
ino + INOPB(fs) > cgp->cg_initediblk &&
cgp->cg_initediblk < cgp->cg_niblk) {
char block[MAXBSIZE];
bzero(block, (int)fs->fs_bsize);
dp2 = (struct ufs2_dinode *)&block;
for (i = 0; i < INOPB(fs); i++) {
dp2->di_gen = arc4random();
dp2++;
}
if (bwrite(disk, ino_to_fsba(fs,
cgp->cg_cgx * fs->fs_ipg + cgp->cg_initediblk),
block, fs->fs_bsize))
return (0);
cgp->cg_initediblk += INOPB(fs);
}
setbit(inosused, ino);
cgp->cg_irotor = ino;
cgp->cg_cs.cs_nifree--;
fs->fs_cstotal.cs_nifree--;
fs->fs_cs(fs, cgp->cg_cgx).cs_nifree--;
fs->fs_fmod = 1;
return (ino + (cgp->cg_cgx * fs->fs_ipg));
}
int
cgread(struct uufsd *disk)
{
if (disk->d_ccg >= disk->d_fs.fs_ncg)
return (0);
return (cgread1(disk, disk->d_ccg++));
}
/* Short read/write error messages from cgget()/cgput() */
static const char *failmsg;
int
cgread1(struct uufsd *disk, int c)
{
if (cgget(disk->d_fd, &disk->d_fs, c, &disk->d_cg) == 0) {
disk->d_lcg = c;
return (1);
}
ERROR(disk, NULL);
if (failmsg != NULL) {
ERROR(disk, failmsg);
return (-1);
}
switch (errno) {
case EINTEGRITY:
ERROR(disk, "cylinder group checks failed");
break;
case EIO:
ERROR(disk, "read error from block device");
break;
default:
ERROR(disk, strerror(errno));
break;
}
return (-1);
}
int
cgget(int devfd, struct fs *fs, int cg, struct cg *cgp)
{
uint32_t cghash, calchash;
size_t cnt;
failmsg = NULL;
if ((cnt = pread(devfd, cgp, fs->fs_cgsize,
fsbtodb(fs, cgtod(fs, cg)) * (fs->fs_fsize / fsbtodb(fs,1)))) < 0)
return (-1);
if (cnt == 0) {
failmsg = "end of file from block device";
errno = EIO;
return (-1);
}
if (cnt != fs->fs_cgsize) {
failmsg = "short read from block device";
errno = EIO;
return (-1);
}
calchash = cgp->cg_ckhash;
if ((fs->fs_metackhash & CK_CYLGRP) != 0) {
cghash = cgp->cg_ckhash;
cgp->cg_ckhash = 0;
calchash = calculate_crc32c(~0L, (void *)cgp, fs->fs_cgsize);
cgp->cg_ckhash = cghash;
}
if (cgp->cg_ckhash != calchash || !cg_chkmagic(cgp) ||
cgp->cg_cgx != cg) {
errno = EINTEGRITY;
return (-1);
}
return (0);
}
int
cgwrite(struct uufsd *disk)
{
return (cgwrite1(disk, disk->d_cg.cg_cgx));
}
int
cgwrite1(struct uufsd *disk, int cg)
{
static char errmsg[BUFSIZ];
if (cg == disk->d_cg.cg_cgx) {
if (cgput(disk->d_fd, &disk->d_fs, &disk->d_cg) == 0)
return (0);
ERROR(disk, NULL);
if (failmsg != NULL) {
ERROR(disk, failmsg);
return (-1);
}
switch (errno) {
case EIO:
ERROR(disk, "unable to write cylinder group");
break;
default:
ERROR(disk, strerror(errno));
break;
}
return (-1);
}
snprintf(errmsg, BUFSIZ, "Cylinder group %d in buffer does not match "
"the cylinder group %d that cgwrite1 requested",
disk->d_cg.cg_cgx, cg);
ERROR(disk, errmsg);
errno = EDOOFUS;
return (-1);
}
int
cgput(int devfd, struct fs *fs, struct cg *cgp)
{
size_t cnt;
Continuing efforts to provide hardening of FFS, this change adds a check hash to cylinder groups. If a check hash fails when a cylinder group is read, no further allocations are attempted in that cylinder group until it has been fixed by fsck. This avoids a class of filesystem panics related to corrupted cylinder group maps. The hash is done using crc32c. Check hases are added only to UFS2 and not to UFS1 as UFS1 is primarily used in embedded systems with small memories and low-powered processors which need as light-weight a filesystem as possible. Specifics of the changes: sys/sys/buf.h: Add BX_FSPRIV to reserve a set of eight b_xflags that may be used by individual filesystems for their own purpose. Their specific definitions are found in the header files for each filesystem that uses them. Also add fields to struct buf as noted below. sys/kern/vfs_bio.c: It is only necessary to compute a check hash for a cylinder group when it is actually read from disk. When calling bread, you do not know whether the buffer was found in the cache or read. So a new flag (GB_CKHASH) and a pointer to a function to perform the hash has been added to breadn_flags to say that the function should be called to calculate a hash if the data has been read. The check hash is placed in b_ckhash and the B_CKHASH flag is set to indicate that a read was done and a check hash calculated. Though a rather elaborate mechanism, it should also work for check hashing other metadata in the future. A kernel internal API change was to change breada into a static fucntion and add flags and a function pointer to a check-hash function. sys/ufs/ffs/fs.h: Add flags for types of check hashes; stored in a new word in the superblock. Define corresponding BX_ flags for the different types of check hashes. Add a check hash word in the cylinder group. sys/ufs/ffs/ffs_alloc.c: In ffs_getcg do the dance with breadn_flags to get a check hash and if one is provided, check it. sys/ufs/ffs/ffs_vfsops.c: Copy across the BX_FFSTYPES flags in background writes. Update the check hash when writing out buffers that need them. sys/ufs/ffs/ffs_snapshot.c: Recompute check hash when updating snapshot cylinder groups. sys/libkern/crc32.c: lib/libufs/Makefile: lib/libufs/libufs.h: lib/libufs/cgroup.c: Include libkern/crc32.c in libufs and use it to compute check hashes when updating cylinder groups. Four utilities are affected: sbin/newfs/mkfs.c: Add the check hashes when building the cylinder groups. sbin/fsck_ffs/fsck.h: sbin/fsck_ffs/fsutil.c: Verify and update check hashes when checking and writing cylinder groups. sbin/fsck_ffs/pass5.c: Offer to add check hashes to existing filesystems. Precompute check hashes when rebuilding cylinder group (although this will be done when it is written in fsutil.c it is necessary to do it early before comparing with the old cylinder group) sbin/dumpfs/dumpfs.c Print out the new check hash flag(s) sbin/fsdb/Makefile: Needs to add libufs now used by pass5.c imported from fsck_ffs. Reviewed by: kib Tested by: Peter Holm (pho)
2017-09-22 12:45:15 +00:00
if ((fs->fs_metackhash & CK_CYLGRP) != 0) {
cgp->cg_ckhash = 0;
cgp->cg_ckhash =
calculate_crc32c(~0L, (void *)cgp, fs->fs_cgsize);
Continuing efforts to provide hardening of FFS, this change adds a check hash to cylinder groups. If a check hash fails when a cylinder group is read, no further allocations are attempted in that cylinder group until it has been fixed by fsck. This avoids a class of filesystem panics related to corrupted cylinder group maps. The hash is done using crc32c. Check hases are added only to UFS2 and not to UFS1 as UFS1 is primarily used in embedded systems with small memories and low-powered processors which need as light-weight a filesystem as possible. Specifics of the changes: sys/sys/buf.h: Add BX_FSPRIV to reserve a set of eight b_xflags that may be used by individual filesystems for their own purpose. Their specific definitions are found in the header files for each filesystem that uses them. Also add fields to struct buf as noted below. sys/kern/vfs_bio.c: It is only necessary to compute a check hash for a cylinder group when it is actually read from disk. When calling bread, you do not know whether the buffer was found in the cache or read. So a new flag (GB_CKHASH) and a pointer to a function to perform the hash has been added to breadn_flags to say that the function should be called to calculate a hash if the data has been read. The check hash is placed in b_ckhash and the B_CKHASH flag is set to indicate that a read was done and a check hash calculated. Though a rather elaborate mechanism, it should also work for check hashing other metadata in the future. A kernel internal API change was to change breada into a static fucntion and add flags and a function pointer to a check-hash function. sys/ufs/ffs/fs.h: Add flags for types of check hashes; stored in a new word in the superblock. Define corresponding BX_ flags for the different types of check hashes. Add a check hash word in the cylinder group. sys/ufs/ffs/ffs_alloc.c: In ffs_getcg do the dance with breadn_flags to get a check hash and if one is provided, check it. sys/ufs/ffs/ffs_vfsops.c: Copy across the BX_FFSTYPES flags in background writes. Update the check hash when writing out buffers that need them. sys/ufs/ffs/ffs_snapshot.c: Recompute check hash when updating snapshot cylinder groups. sys/libkern/crc32.c: lib/libufs/Makefile: lib/libufs/libufs.h: lib/libufs/cgroup.c: Include libkern/crc32.c in libufs and use it to compute check hashes when updating cylinder groups. Four utilities are affected: sbin/newfs/mkfs.c: Add the check hashes when building the cylinder groups. sbin/fsck_ffs/fsck.h: sbin/fsck_ffs/fsutil.c: Verify and update check hashes when checking and writing cylinder groups. sbin/fsck_ffs/pass5.c: Offer to add check hashes to existing filesystems. Precompute check hashes when rebuilding cylinder group (although this will be done when it is written in fsutil.c it is necessary to do it early before comparing with the old cylinder group) sbin/dumpfs/dumpfs.c Print out the new check hash flag(s) sbin/fsdb/Makefile: Needs to add libufs now used by pass5.c imported from fsck_ffs. Reviewed by: kib Tested by: Peter Holm (pho)
2017-09-22 12:45:15 +00:00
}
failmsg = NULL;
if ((cnt = pwrite(devfd, cgp, fs->fs_cgsize,
fsbtodb(fs, cgtod(fs, cgp->cg_cgx)) *
(fs->fs_fsize / fsbtodb(fs,1)))) < 0)
return (-1);
if (cnt != fs->fs_cgsize) {
failmsg = "short write to block device";
return (-1);
}
return (0);
}