From 95099d4622f8cb224d94e314c7a8e0df60b13f87 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Sat, 09 Dec 2023 08:38:01 +0000
Subject: [PATCH] enable docker ppp
---
kernel/fs/xfs/xfs_super.c | 2106 ++++++++++++++++++++++++++++++----------------------------
1 files changed, 1,092 insertions(+), 1,014 deletions(-)
diff --git a/kernel/fs/xfs/xfs_super.c b/kernel/fs/xfs/xfs_super.c
index dce8114..a21abc4 100644
--- a/kernel/fs/xfs/xfs_super.c
+++ b/kernel/fs/xfs/xfs_super.c
@@ -11,18 +11,15 @@
#include "xfs_trans_resv.h"
#include "xfs_sb.h"
#include "xfs_mount.h"
-#include "xfs_da_format.h"
#include "xfs_inode.h"
#include "xfs_btree.h"
#include "xfs_bmap.h"
#include "xfs_alloc.h"
-#include "xfs_error.h"
#include "xfs_fsops.h"
#include "xfs_trans.h"
#include "xfs_buf_item.h"
#include "xfs_log.h"
#include "xfs_log_priv.h"
-#include "xfs_da_btree.h"
#include "xfs_dir2.h"
#include "xfs_extfree_item.h"
#include "xfs_mru_cache.h"
@@ -39,417 +36,119 @@
#include "xfs_bmap_item.h"
#include "xfs_reflink.h"
-#include <linux/namei.h>
-#include <linux/dax.h>
-#include <linux/init.h>
-#include <linux/slab.h>
-#include <linux/mount.h>
-#include <linux/mempool.h>
-#include <linux/writeback.h>
-#include <linux/kthread.h>
-#include <linux/freezer.h>
-#include <linux/parser.h>
+#include <linux/magic.h>
+#include <linux/fs_context.h>
+#include <linux/fs_parser.h>
static const struct super_operations xfs_super_operations;
-struct bio_set xfs_ioend_bioset;
static struct kset *xfs_kset; /* top-level xfs sysfs dir */
#ifdef DEBUG
static struct xfs_kobj xfs_dbg_kobj; /* global debug sysfs attrs */
#endif
+enum xfs_dax_mode {
+ XFS_DAX_INODE = 0,
+ XFS_DAX_ALWAYS = 1,
+ XFS_DAX_NEVER = 2,
+};
+
+static void
+xfs_mount_set_dax_mode(
+ struct xfs_mount *mp,
+ enum xfs_dax_mode mode)
+{
+ switch (mode) {
+ case XFS_DAX_INODE:
+ mp->m_flags &= ~(XFS_MOUNT_DAX_ALWAYS | XFS_MOUNT_DAX_NEVER);
+ break;
+ case XFS_DAX_ALWAYS:
+ mp->m_flags |= XFS_MOUNT_DAX_ALWAYS;
+ mp->m_flags &= ~XFS_MOUNT_DAX_NEVER;
+ break;
+ case XFS_DAX_NEVER:
+ mp->m_flags |= XFS_MOUNT_DAX_NEVER;
+ mp->m_flags &= ~XFS_MOUNT_DAX_ALWAYS;
+ break;
+ }
+}
+
+static const struct constant_table dax_param_enums[] = {
+ {"inode", XFS_DAX_INODE },
+ {"always", XFS_DAX_ALWAYS },
+ {"never", XFS_DAX_NEVER },
+ {}
+};
+
/*
* Table driven mount option parser.
*/
enum {
- Opt_logbufs, Opt_logbsize, Opt_logdev, Opt_rtdev, Opt_biosize,
+ Opt_logbufs, Opt_logbsize, Opt_logdev, Opt_rtdev,
Opt_wsync, Opt_noalign, Opt_swalloc, Opt_sunit, Opt_swidth, Opt_nouuid,
- Opt_mtpt, Opt_grpid, Opt_nogrpid, Opt_bsdgroups, Opt_sysvgroups,
+ Opt_grpid, Opt_nogrpid, Opt_bsdgroups, Opt_sysvgroups,
Opt_allocsize, Opt_norecovery, Opt_inode64, Opt_inode32, Opt_ikeep,
Opt_noikeep, Opt_largeio, Opt_nolargeio, Opt_attr2, Opt_noattr2,
Opt_filestreams, Opt_quota, Opt_noquota, Opt_usrquota, Opt_grpquota,
Opt_prjquota, Opt_uquota, Opt_gquota, Opt_pquota,
Opt_uqnoenforce, Opt_gqnoenforce, Opt_pqnoenforce, Opt_qnoenforce,
- Opt_discard, Opt_nodiscard, Opt_dax, Opt_err,
+ Opt_discard, Opt_nodiscard, Opt_dax, Opt_dax_enum,
};
-static const match_table_t tokens = {
- {Opt_logbufs, "logbufs=%u"}, /* number of XFS log buffers */
- {Opt_logbsize, "logbsize=%s"}, /* size of XFS log buffers */
- {Opt_logdev, "logdev=%s"}, /* log device */
- {Opt_rtdev, "rtdev=%s"}, /* realtime I/O device */
- {Opt_biosize, "biosize=%u"}, /* log2 of preferred buffered io size */
- {Opt_wsync, "wsync"}, /* safe-mode nfs compatible mount */
- {Opt_noalign, "noalign"}, /* turn off stripe alignment */
- {Opt_swalloc, "swalloc"}, /* turn on stripe width allocation */
- {Opt_sunit, "sunit=%u"}, /* data volume stripe unit */
- {Opt_swidth, "swidth=%u"}, /* data volume stripe width */
- {Opt_nouuid, "nouuid"}, /* ignore filesystem UUID */
- {Opt_mtpt, "mtpt"}, /* filesystem mount point */
- {Opt_grpid, "grpid"}, /* group-ID from parent directory */
- {Opt_nogrpid, "nogrpid"}, /* group-ID from current process */
- {Opt_bsdgroups, "bsdgroups"}, /* group-ID from parent directory */
- {Opt_sysvgroups,"sysvgroups"}, /* group-ID from current process */
- {Opt_allocsize, "allocsize=%s"},/* preferred allocation size */
- {Opt_norecovery,"norecovery"}, /* don't run XFS recovery */
- {Opt_inode64, "inode64"}, /* inodes can be allocated anywhere */
- {Opt_inode32, "inode32"}, /* inode allocation limited to
- * XFS_MAXINUMBER_32 */
- {Opt_ikeep, "ikeep"}, /* do not free empty inode clusters */
- {Opt_noikeep, "noikeep"}, /* free empty inode clusters */
- {Opt_largeio, "largeio"}, /* report large I/O sizes in stat() */
- {Opt_nolargeio, "nolargeio"}, /* do not report large I/O sizes
- * in stat(). */
- {Opt_attr2, "attr2"}, /* do use attr2 attribute format */
- {Opt_noattr2, "noattr2"}, /* do not use attr2 attribute format */
- {Opt_filestreams,"filestreams"},/* use filestreams allocator */
- {Opt_quota, "quota"}, /* disk quotas (user) */
- {Opt_noquota, "noquota"}, /* no quotas */
- {Opt_usrquota, "usrquota"}, /* user quota enabled */
- {Opt_grpquota, "grpquota"}, /* group quota enabled */
- {Opt_prjquota, "prjquota"}, /* project quota enabled */
- {Opt_uquota, "uquota"}, /* user quota (IRIX variant) */
- {Opt_gquota, "gquota"}, /* group quota (IRIX variant) */
- {Opt_pquota, "pquota"}, /* project quota (IRIX variant) */
- {Opt_uqnoenforce,"uqnoenforce"},/* user quota limit enforcement */
- {Opt_gqnoenforce,"gqnoenforce"},/* group quota limit enforcement */
- {Opt_pqnoenforce,"pqnoenforce"},/* project quota limit enforcement */
- {Opt_qnoenforce, "qnoenforce"}, /* same as uqnoenforce */
- {Opt_discard, "discard"}, /* Discard unused blocks */
- {Opt_nodiscard, "nodiscard"}, /* Do not discard unused blocks */
- {Opt_dax, "dax"}, /* Enable direct access to bdev pages */
- {Opt_err, NULL},
+static const struct fs_parameter_spec xfs_fs_parameters[] = {
+ fsparam_u32("logbufs", Opt_logbufs),
+ fsparam_string("logbsize", Opt_logbsize),
+ fsparam_string("logdev", Opt_logdev),
+ fsparam_string("rtdev", Opt_rtdev),
+ fsparam_flag("wsync", Opt_wsync),
+ fsparam_flag("noalign", Opt_noalign),
+ fsparam_flag("swalloc", Opt_swalloc),
+ fsparam_u32("sunit", Opt_sunit),
+ fsparam_u32("swidth", Opt_swidth),
+ fsparam_flag("nouuid", Opt_nouuid),
+ fsparam_flag("grpid", Opt_grpid),
+ fsparam_flag("nogrpid", Opt_nogrpid),
+ fsparam_flag("bsdgroups", Opt_bsdgroups),
+ fsparam_flag("sysvgroups", Opt_sysvgroups),
+ fsparam_string("allocsize", Opt_allocsize),
+ fsparam_flag("norecovery", Opt_norecovery),
+ fsparam_flag("inode64", Opt_inode64),
+ fsparam_flag("inode32", Opt_inode32),
+ fsparam_flag("ikeep", Opt_ikeep),
+ fsparam_flag("noikeep", Opt_noikeep),
+ fsparam_flag("largeio", Opt_largeio),
+ fsparam_flag("nolargeio", Opt_nolargeio),
+ fsparam_flag("attr2", Opt_attr2),
+ fsparam_flag("noattr2", Opt_noattr2),
+ fsparam_flag("filestreams", Opt_filestreams),
+ fsparam_flag("quota", Opt_quota),
+ fsparam_flag("noquota", Opt_noquota),
+ fsparam_flag("usrquota", Opt_usrquota),
+ fsparam_flag("grpquota", Opt_grpquota),
+ fsparam_flag("prjquota", Opt_prjquota),
+ fsparam_flag("uquota", Opt_uquota),
+ fsparam_flag("gquota", Opt_gquota),
+ fsparam_flag("pquota", Opt_pquota),
+ fsparam_flag("uqnoenforce", Opt_uqnoenforce),
+ fsparam_flag("gqnoenforce", Opt_gqnoenforce),
+ fsparam_flag("pqnoenforce", Opt_pqnoenforce),
+ fsparam_flag("qnoenforce", Opt_qnoenforce),
+ fsparam_flag("discard", Opt_discard),
+ fsparam_flag("nodiscard", Opt_nodiscard),
+ fsparam_flag("dax", Opt_dax),
+ fsparam_enum("dax", Opt_dax_enum, dax_param_enums),
+ {}
};
-
-
-STATIC int
-suffix_kstrtoint(const substring_t *s, unsigned int base, int *res)
-{
- int last, shift_left_factor = 0, _res;
- char *value;
- int ret = 0;
-
- value = match_strdup(s);
- if (!value)
- return -ENOMEM;
-
- last = strlen(value) - 1;
- if (value[last] == 'K' || value[last] == 'k') {
- shift_left_factor = 10;
- value[last] = '\0';
- }
- if (value[last] == 'M' || value[last] == 'm') {
- shift_left_factor = 20;
- value[last] = '\0';
- }
- if (value[last] == 'G' || value[last] == 'g') {
- shift_left_factor = 30;
- value[last] = '\0';
- }
-
- if (kstrtoint(value, base, &_res))
- ret = -EINVAL;
- kfree(value);
- *res = _res << shift_left_factor;
- return ret;
-}
-
-/*
- * This function fills in xfs_mount_t fields based on mount args.
- * Note: the superblock has _not_ yet been read in.
- *
- * Note that this function leaks the various device name allocations on
- * failure. The caller takes care of them.
- *
- * *sb is const because this is also used to test options on the remount
- * path, and we don't want this to have any side effects at remount time.
- * Today this function does not change *sb, but just to future-proof...
- */
-STATIC int
-xfs_parseargs(
- struct xfs_mount *mp,
- char *options)
-{
- const struct super_block *sb = mp->m_super;
- char *p;
- substring_t args[MAX_OPT_ARGS];
- int dsunit = 0;
- int dswidth = 0;
- int iosize = 0;
- uint8_t iosizelog = 0;
-
- /*
- * set up the mount name first so all the errors will refer to the
- * correct device.
- */
- mp->m_fsname = kstrndup(sb->s_id, MAXNAMELEN, GFP_KERNEL);
- if (!mp->m_fsname)
- return -ENOMEM;
- mp->m_fsname_len = strlen(mp->m_fsname) + 1;
-
- /*
- * Copy binary VFS mount flags we are interested in.
- */
- if (sb_rdonly(sb))
- mp->m_flags |= XFS_MOUNT_RDONLY;
- if (sb->s_flags & SB_DIRSYNC)
- mp->m_flags |= XFS_MOUNT_DIRSYNC;
- if (sb->s_flags & SB_SYNCHRONOUS)
- mp->m_flags |= XFS_MOUNT_WSYNC;
-
- /*
- * Set some default flags that could be cleared by the mount option
- * parsing.
- */
- mp->m_flags |= XFS_MOUNT_COMPAT_IOSIZE;
-
- /*
- * These can be overridden by the mount option parsing.
- */
- mp->m_logbufs = -1;
- mp->m_logbsize = -1;
-
- if (!options)
- goto done;
-
- while ((p = strsep(&options, ",")) != NULL) {
- int token;
-
- if (!*p)
- continue;
-
- token = match_token(p, tokens, args);
- switch (token) {
- case Opt_logbufs:
- if (match_int(args, &mp->m_logbufs))
- return -EINVAL;
- break;
- case Opt_logbsize:
- if (suffix_kstrtoint(args, 10, &mp->m_logbsize))
- return -EINVAL;
- break;
- case Opt_logdev:
- kfree(mp->m_logname);
- mp->m_logname = match_strdup(args);
- if (!mp->m_logname)
- return -ENOMEM;
- break;
- case Opt_mtpt:
- xfs_warn(mp, "%s option not allowed on this system", p);
- return -EINVAL;
- case Opt_rtdev:
- kfree(mp->m_rtname);
- mp->m_rtname = match_strdup(args);
- if (!mp->m_rtname)
- return -ENOMEM;
- break;
- case Opt_allocsize:
- case Opt_biosize:
- if (suffix_kstrtoint(args, 10, &iosize))
- return -EINVAL;
- iosizelog = ffs(iosize) - 1;
- break;
- case Opt_grpid:
- case Opt_bsdgroups:
- mp->m_flags |= XFS_MOUNT_GRPID;
- break;
- case Opt_nogrpid:
- case Opt_sysvgroups:
- mp->m_flags &= ~XFS_MOUNT_GRPID;
- break;
- case Opt_wsync:
- mp->m_flags |= XFS_MOUNT_WSYNC;
- break;
- case Opt_norecovery:
- mp->m_flags |= XFS_MOUNT_NORECOVERY;
- break;
- case Opt_noalign:
- mp->m_flags |= XFS_MOUNT_NOALIGN;
- break;
- case Opt_swalloc:
- mp->m_flags |= XFS_MOUNT_SWALLOC;
- break;
- case Opt_sunit:
- if (match_int(args, &dsunit))
- return -EINVAL;
- break;
- case Opt_swidth:
- if (match_int(args, &dswidth))
- return -EINVAL;
- break;
- case Opt_inode32:
- mp->m_flags |= XFS_MOUNT_SMALL_INUMS;
- break;
- case Opt_inode64:
- mp->m_flags &= ~XFS_MOUNT_SMALL_INUMS;
- break;
- case Opt_nouuid:
- mp->m_flags |= XFS_MOUNT_NOUUID;
- break;
- case Opt_ikeep:
- mp->m_flags |= XFS_MOUNT_IKEEP;
- break;
- case Opt_noikeep:
- mp->m_flags &= ~XFS_MOUNT_IKEEP;
- break;
- case Opt_largeio:
- mp->m_flags &= ~XFS_MOUNT_COMPAT_IOSIZE;
- break;
- case Opt_nolargeio:
- mp->m_flags |= XFS_MOUNT_COMPAT_IOSIZE;
- break;
- case Opt_attr2:
- mp->m_flags |= XFS_MOUNT_ATTR2;
- break;
- case Opt_noattr2:
- mp->m_flags &= ~XFS_MOUNT_ATTR2;
- mp->m_flags |= XFS_MOUNT_NOATTR2;
- break;
- case Opt_filestreams:
- mp->m_flags |= XFS_MOUNT_FILESTREAMS;
- break;
- case Opt_noquota:
- mp->m_qflags &= ~XFS_ALL_QUOTA_ACCT;
- mp->m_qflags &= ~XFS_ALL_QUOTA_ENFD;
- mp->m_qflags &= ~XFS_ALL_QUOTA_ACTIVE;
- break;
- case Opt_quota:
- case Opt_uquota:
- case Opt_usrquota:
- mp->m_qflags |= (XFS_UQUOTA_ACCT | XFS_UQUOTA_ACTIVE |
- XFS_UQUOTA_ENFD);
- break;
- case Opt_qnoenforce:
- case Opt_uqnoenforce:
- mp->m_qflags |= (XFS_UQUOTA_ACCT | XFS_UQUOTA_ACTIVE);
- mp->m_qflags &= ~XFS_UQUOTA_ENFD;
- break;
- case Opt_pquota:
- case Opt_prjquota:
- mp->m_qflags |= (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE |
- XFS_PQUOTA_ENFD);
- break;
- case Opt_pqnoenforce:
- mp->m_qflags |= (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE);
- mp->m_qflags &= ~XFS_PQUOTA_ENFD;
- break;
- case Opt_gquota:
- case Opt_grpquota:
- mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE |
- XFS_GQUOTA_ENFD);
- break;
- case Opt_gqnoenforce:
- mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE);
- mp->m_qflags &= ~XFS_GQUOTA_ENFD;
- break;
- case Opt_discard:
- mp->m_flags |= XFS_MOUNT_DISCARD;
- break;
- case Opt_nodiscard:
- mp->m_flags &= ~XFS_MOUNT_DISCARD;
- break;
-#ifdef CONFIG_FS_DAX
- case Opt_dax:
- mp->m_flags |= XFS_MOUNT_DAX;
- break;
-#endif
- default:
- xfs_warn(mp, "unknown mount option [%s].", p);
- return -EINVAL;
- }
- }
-
- /*
- * no recovery flag requires a read-only mount
- */
- if ((mp->m_flags & XFS_MOUNT_NORECOVERY) &&
- !(mp->m_flags & XFS_MOUNT_RDONLY)) {
- xfs_warn(mp, "no-recovery mounts must be read-only.");
- return -EINVAL;
- }
-
- if ((mp->m_flags & XFS_MOUNT_NOALIGN) && (dsunit || dswidth)) {
- xfs_warn(mp,
- "sunit and swidth options incompatible with the noalign option");
- return -EINVAL;
- }
-
-#ifndef CONFIG_XFS_QUOTA
- if (XFS_IS_QUOTA_RUNNING(mp)) {
- xfs_warn(mp, "quota support not available in this kernel.");
- return -EINVAL;
- }
-#endif
-
- if ((dsunit && !dswidth) || (!dsunit && dswidth)) {
- xfs_warn(mp, "sunit and swidth must be specified together");
- return -EINVAL;
- }
-
- if (dsunit && (dswidth % dsunit != 0)) {
- xfs_warn(mp,
- "stripe width (%d) must be a multiple of the stripe unit (%d)",
- dswidth, dsunit);
- return -EINVAL;
- }
-
-done:
- if (dsunit && !(mp->m_flags & XFS_MOUNT_NOALIGN)) {
- /*
- * At this point the superblock has not been read
- * in, therefore we do not know the block size.
- * Before the mount call ends we will convert
- * these to FSBs.
- */
- mp->m_dalign = dsunit;
- mp->m_swidth = dswidth;
- }
-
- if (mp->m_logbufs != -1 &&
- mp->m_logbufs != 0 &&
- (mp->m_logbufs < XLOG_MIN_ICLOGS ||
- mp->m_logbufs > XLOG_MAX_ICLOGS)) {
- xfs_warn(mp, "invalid logbufs value: %d [not %d-%d]",
- mp->m_logbufs, XLOG_MIN_ICLOGS, XLOG_MAX_ICLOGS);
- return -EINVAL;
- }
- if (mp->m_logbsize != -1 &&
- mp->m_logbsize != 0 &&
- (mp->m_logbsize < XLOG_MIN_RECORD_BSIZE ||
- mp->m_logbsize > XLOG_MAX_RECORD_BSIZE ||
- !is_power_of_2(mp->m_logbsize))) {
- xfs_warn(mp,
- "invalid logbufsize: %d [not 16k,32k,64k,128k or 256k]",
- mp->m_logbsize);
- return -EINVAL;
- }
-
- if (iosizelog) {
- if (iosizelog > XFS_MAX_IO_LOG ||
- iosizelog < XFS_MIN_IO_LOG) {
- xfs_warn(mp, "invalid log iosize: %d [not %d-%d]",
- iosizelog, XFS_MIN_IO_LOG,
- XFS_MAX_IO_LOG);
- return -EINVAL;
- }
-
- mp->m_flags |= XFS_MOUNT_DFLT_IOSIZE;
- mp->m_readio_log = iosizelog;
- mp->m_writeio_log = iosizelog;
- }
-
- return 0;
-}
struct proc_xfs_info {
uint64_t flag;
char *str;
};
-STATIC int
-xfs_showargs(
- struct xfs_mount *mp,
- struct seq_file *m)
+static int
+xfs_fs_show_options(
+ struct seq_file *m,
+ struct dentry *root)
{
static struct proc_xfs_info xfs_info_set[] = {
/* the few simple ones we can get from the mount struct */
@@ -463,30 +162,25 @@
{ XFS_MOUNT_FILESTREAMS, ",filestreams" },
{ XFS_MOUNT_GRPID, ",grpid" },
{ XFS_MOUNT_DISCARD, ",discard" },
- { XFS_MOUNT_SMALL_INUMS, ",inode32" },
- { XFS_MOUNT_DAX, ",dax" },
+ { XFS_MOUNT_LARGEIO, ",largeio" },
+ { XFS_MOUNT_DAX_ALWAYS, ",dax=always" },
+ { XFS_MOUNT_DAX_NEVER, ",dax=never" },
{ 0, NULL }
};
- static struct proc_xfs_info xfs_info_unset[] = {
- /* the few simple ones we can get from the mount struct */
- { XFS_MOUNT_COMPAT_IOSIZE, ",largeio" },
- { XFS_MOUNT_SMALL_INUMS, ",inode64" },
- { 0, NULL }
- };
+ struct xfs_mount *mp = XFS_M(root->d_sb);
struct proc_xfs_info *xfs_infop;
for (xfs_infop = xfs_info_set; xfs_infop->flag; xfs_infop++) {
if (mp->m_flags & xfs_infop->flag)
seq_puts(m, xfs_infop->str);
}
- for (xfs_infop = xfs_info_unset; xfs_infop->flag; xfs_infop++) {
- if (!(mp->m_flags & xfs_infop->flag))
- seq_puts(m, xfs_infop->str);
- }
- if (mp->m_flags & XFS_MOUNT_DFLT_IOSIZE)
+ seq_printf(m, ",inode%d",
+ (mp->m_flags & XFS_MOUNT_SMALL_INUMS) ? 32 : 64);
+
+ if (mp->m_flags & XFS_MOUNT_ALLOCSIZE)
seq_printf(m, ",allocsize=%dk",
- (int)(1 << mp->m_writeio_log) >> 10);
+ (1 << mp->m_allocsize_log) >> 10);
if (mp->m_logbufs > 0)
seq_printf(m, ",logbufs=%d", mp->m_logbufs);
@@ -505,10 +199,12 @@
seq_printf(m, ",swidth=%d",
(int)XFS_FSB_TO_BB(mp, mp->m_swidth));
- if (mp->m_qflags & (XFS_UQUOTA_ACCT|XFS_UQUOTA_ENFD))
- seq_puts(m, ",usrquota");
- else if (mp->m_qflags & XFS_UQUOTA_ACCT)
- seq_puts(m, ",uqnoenforce");
+ if (mp->m_qflags & XFS_UQUOTA_ACCT) {
+ if (mp->m_qflags & XFS_UQUOTA_ENFD)
+ seq_puts(m, ",usrquota");
+ else
+ seq_puts(m, ",uqnoenforce");
+ }
if (mp->m_qflags & XFS_PQUOTA_ACCT) {
if (mp->m_qflags & XFS_PQUOTA_ENFD)
@@ -527,39 +223,6 @@
seq_puts(m, ",noquota");
return 0;
-}
-static uint64_t
-xfs_max_file_offset(
- unsigned int blockshift)
-{
- unsigned int pagefactor = 1;
- unsigned int bitshift = BITS_PER_LONG - 1;
-
- /* Figure out maximum filesize, on Linux this can depend on
- * the filesystem blocksize (on 32 bit platforms).
- * __block_write_begin does this in an [unsigned] long...
- * page->index << (PAGE_SHIFT - bbits)
- * So, for page sized blocks (4K on 32 bit platforms),
- * this wraps at around 8Tb (hence MAX_LFS_FILESIZE which is
- * (((u64)PAGE_SIZE << (BITS_PER_LONG-1))-1)
- * but for smaller blocksizes it is less (bbits = log2 bsize).
- * Note1: get_block_t takes a long (implicit cast from above)
- * Note2: The Large Block Device (LBD and HAVE_SECTOR_T) patch
- * can optionally convert the [unsigned] long from above into
- * an [unsigned] long long.
- */
-
-#if BITS_PER_LONG == 32
-# if defined(CONFIG_LBDAF)
- ASSERT(sizeof(sector_t) == 8);
- pagefactor = PAGE_SIZE;
- bitshift = BITS_PER_LONG;
-# else
- pagefactor = PAGE_SIZE >> (PAGE_SHIFT - blockshift);
-# endif
-#endif
-
- return (((uint64_t)pagefactor) << bitshift) - 1;
}
/*
@@ -593,7 +256,7 @@
* Calculate how much should be reserved for inodes to meet
* the max inode percentage. Used only for inode32.
*/
- if (mp->m_maxicount) {
+ if (M_IGEO(mp)->maxicount) {
uint64_t icount;
icount = sbp->sb_dblocks * sbp->sb_imax_pct;
@@ -606,7 +269,7 @@
}
/* Get the last possible inode in the filesystem */
- agino = XFS_OFFBNO_TO_AGINO(mp, sbp->sb_agblocks - 1, 0);
+ agino = XFS_AGB_TO_AGINO(mp, sbp->sb_agblocks - 1);
ino = XFS_AGINO_TO_INO(mp, agcount - 1, agino);
/*
@@ -679,7 +342,7 @@
xfs_blkdev_issue_flush(
xfs_buftarg_t *buftarg)
{
- blkdev_issue_flush(buftarg->bt_bdev, GFP_NOFS, NULL);
+ blkdev_issue_flush(buftarg->bt_bdev, GFP_NOFS);
}
STATIC void
@@ -832,43 +495,33 @@
struct xfs_mount *mp)
{
mp->m_buf_workqueue = alloc_workqueue("xfs-buf/%s",
- WQ_MEM_RECLAIM|WQ_FREEZABLE, 1, mp->m_fsname);
+ WQ_MEM_RECLAIM|WQ_FREEZABLE, 1, mp->m_super->s_id);
if (!mp->m_buf_workqueue)
goto out;
- mp->m_data_workqueue = alloc_workqueue("xfs-data/%s",
- WQ_MEM_RECLAIM|WQ_FREEZABLE, 0, mp->m_fsname);
- if (!mp->m_data_workqueue)
+ mp->m_unwritten_workqueue = alloc_workqueue("xfs-conv/%s",
+ WQ_MEM_RECLAIM|WQ_FREEZABLE, 0, mp->m_super->s_id);
+ if (!mp->m_unwritten_workqueue)
goto out_destroy_buf;
- mp->m_unwritten_workqueue = alloc_workqueue("xfs-conv/%s",
- WQ_MEM_RECLAIM|WQ_FREEZABLE, 0, mp->m_fsname);
- if (!mp->m_unwritten_workqueue)
- goto out_destroy_data_iodone_queue;
-
mp->m_cil_workqueue = alloc_workqueue("xfs-cil/%s",
- WQ_MEM_RECLAIM|WQ_FREEZABLE, 0, mp->m_fsname);
+ WQ_MEM_RECLAIM | WQ_FREEZABLE | WQ_UNBOUND,
+ 0, mp->m_super->s_id);
if (!mp->m_cil_workqueue)
goto out_destroy_unwritten;
mp->m_reclaim_workqueue = alloc_workqueue("xfs-reclaim/%s",
- WQ_MEM_RECLAIM|WQ_FREEZABLE, 0, mp->m_fsname);
+ WQ_MEM_RECLAIM|WQ_FREEZABLE, 0, mp->m_super->s_id);
if (!mp->m_reclaim_workqueue)
goto out_destroy_cil;
- mp->m_log_workqueue = alloc_workqueue("xfs-log/%s",
- WQ_MEM_RECLAIM|WQ_FREEZABLE|WQ_HIGHPRI, 0,
- mp->m_fsname);
- if (!mp->m_log_workqueue)
+ mp->m_eofblocks_workqueue = alloc_workqueue("xfs-eofblocks/%s",
+ WQ_MEM_RECLAIM|WQ_FREEZABLE, 0, mp->m_super->s_id);
+ if (!mp->m_eofblocks_workqueue)
goto out_destroy_reclaim;
- mp->m_eofblocks_workqueue = alloc_workqueue("xfs-eofblocks/%s",
- WQ_MEM_RECLAIM|WQ_FREEZABLE, 0, mp->m_fsname);
- if (!mp->m_eofblocks_workqueue)
- goto out_destroy_log;
-
mp->m_sync_workqueue = alloc_workqueue("xfs-sync/%s", WQ_FREEZABLE, 0,
- mp->m_fsname);
+ mp->m_super->s_id);
if (!mp->m_sync_workqueue)
goto out_destroy_eofb;
@@ -876,16 +529,12 @@
out_destroy_eofb:
destroy_workqueue(mp->m_eofblocks_workqueue);
-out_destroy_log:
- destroy_workqueue(mp->m_log_workqueue);
out_destroy_reclaim:
destroy_workqueue(mp->m_reclaim_workqueue);
out_destroy_cil:
destroy_workqueue(mp->m_cil_workqueue);
out_destroy_unwritten:
destroy_workqueue(mp->m_unwritten_workqueue);
-out_destroy_data_iodone_queue:
- destroy_workqueue(mp->m_data_workqueue);
out_destroy_buf:
destroy_workqueue(mp->m_buf_workqueue);
out:
@@ -898,12 +547,24 @@
{
destroy_workqueue(mp->m_sync_workqueue);
destroy_workqueue(mp->m_eofblocks_workqueue);
- destroy_workqueue(mp->m_log_workqueue);
destroy_workqueue(mp->m_reclaim_workqueue);
destroy_workqueue(mp->m_cil_workqueue);
- destroy_workqueue(mp->m_data_workqueue);
destroy_workqueue(mp->m_unwritten_workqueue);
destroy_workqueue(mp->m_buf_workqueue);
+}
+
+static void
+xfs_flush_inodes_worker(
+ struct work_struct *work)
+{
+ struct xfs_mount *mp = container_of(work, struct xfs_mount,
+ m_flush_inodes_work);
+ struct super_block *sb = mp->m_super;
+
+ if (down_read_trylock(&sb->s_umount)) {
+ sync_inodes_sb(sb);
+ up_read(&sb->s_umount);
+ }
}
/*
@@ -916,12 +577,15 @@
xfs_flush_inodes(
struct xfs_mount *mp)
{
- struct super_block *sb = mp->m_super;
+ /*
+ * If flush_work() returns true then that means we waited for a flush
+ * which was already in progress. Don't bother running another scan.
+ */
+ if (flush_work(&mp->m_flush_inodes_work))
+ return;
- if (down_read_trylock(&sb->s_umount)) {
- sync_inodes_sb(sb);
- up_read(&sb->s_umount);
- }
+ queue_work(mp->m_sync_workqueue, &mp->m_flush_inodes_work);
+ flush_work(&mp->m_flush_inodes_work);
}
/* Catch misguided souls that try to use this interface on XFS */
@@ -932,6 +596,32 @@
BUG();
return NULL;
}
+
+#ifdef DEBUG
+static void
+xfs_check_delalloc(
+ struct xfs_inode *ip,
+ int whichfork)
+{
+ struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork);
+ struct xfs_bmbt_irec got;
+ struct xfs_iext_cursor icur;
+
+ if (!ifp || !xfs_iext_lookup_extent(ip, ifp, 0, &icur, &got))
+ return;
+ do {
+ if (isnullstartblock(got.br_startblock)) {
+ xfs_warn(ip->i_mount,
+ "ino %llx %s fork has delalloc extent at [0x%llx:0x%llx]",
+ ip->i_ino,
+ whichfork == XFS_DATA_FORK ? "data" : "cow",
+ got.br_startoff, got.br_blockcount);
+ }
+ } while (xfs_iext_next_extent(ifp, &icur, &got));
+}
+#else
+#define xfs_check_delalloc(ip, whichfork) do { } while (0)
+#endif
/*
* Now that the generic code is guaranteed not to be accessing
@@ -951,7 +641,12 @@
xfs_inactive(ip);
- ASSERT(XFS_FORCED_SHUTDOWN(ip->i_mount) || ip->i_delayed_blks == 0);
+ if (!XFS_FORCED_SHUTDOWN(ip->i_mount) && ip->i_delayed_blks) {
+ xfs_check_delalloc(ip, XFS_DATA_FORK);
+ xfs_check_delalloc(ip, XFS_COW_FORK);
+ ASSERT(0);
+ }
+
XFS_STATS_INC(ip->i_mount, vn_reclaim);
/*
@@ -961,11 +656,11 @@
ASSERT_ALWAYS(!xfs_iflags_test(ip, XFS_IRECLAIM));
/*
- * We always use background reclaim here because even if the
- * inode is clean, it still may be under IO and hence we have
- * to take the flush lock. The background reclaim path handles
- * this more efficiently than we can here, so simply let background
- * reclaim tear down all inodes.
+ * We always use background reclaim here because even if the inode is
+ * clean, it still may be under IO and hence we have wait for IO
+ * completion to occur before we can reclaim the inode. The background
+ * reclaim path handles this more efficiently than we can here, so
+ * simply let background reclaim tear down all inodes.
*/
xfs_inode_set_reclaim_tag(ip);
}
@@ -1044,16 +739,16 @@
return 0;
}
- return generic_drop_inode(inode) || (ip->i_flags & XFS_IDONTCACHE);
+ return generic_drop_inode(inode);
}
-STATIC void
-xfs_free_fsname(
+static void
+xfs_mount_free(
struct xfs_mount *mp)
{
- kfree(mp->m_fsname);
kfree(mp->m_rtname);
kfree(mp->m_logname);
+ kmem_free(mp);
}
STATIC int
@@ -1062,6 +757,7 @@
int wait)
{
struct xfs_mount *mp = XFS_M(sb);
+ int error;
/*
* Doing anything during the async pass would be counterproductive.
@@ -1069,7 +765,10 @@
if (!wait)
return 0;
- xfs_log_force(mp, XFS_LOG_SYNC);
+ error = xfs_log_force(mp, XFS_LOG_SYNC);
+ if (error)
+ return error;
+
if (laptop_mode) {
/*
* The disk must be active because we're syncing.
@@ -1097,12 +796,11 @@
xfs_extlen_t lsize;
int64_t ffree;
- statp->f_type = XFS_SB_MAGIC;
+ statp->f_type = XFS_SUPER_MAGIC;
statp->f_namelen = MAXNAMELEN - 1;
id = huge_encode_dev(mp->m_ddev_targp->bt_dev);
- statp->f_fsid.val[0] = (u32)id;
- statp->f_fsid.val[1] = (u32)(id >> 32);
+ statp->f_fsid = u64_to_fsid(id);
icount = percpu_counter_sum(&mp->m_icount);
ifree = percpu_counter_sum(&mp->m_ifree);
@@ -1114,15 +812,16 @@
statp->f_blocks = sbp->sb_dblocks - lsize;
spin_unlock(&mp->m_sb_lock);
- statp->f_bfree = fdblocks - mp->m_alloc_set_aside;
+ /* make sure statp->f_bfree does not underflow */
+ statp->f_bfree = max_t(int64_t, fdblocks - mp->m_alloc_set_aside, 0);
statp->f_bavail = statp->f_bfree;
- fakeinos = statp->f_bfree << sbp->sb_inopblog;
+ fakeinos = XFS_FSB_TO_INO(mp, statp->f_bfree);
statp->f_files = min(icount + fakeinos, (uint64_t)XFS_MAXINUMBER);
- if (mp->m_maxicount)
+ if (M_IGEO(mp)->maxicount)
statp->f_files = min_t(typeof(statp->f_files),
statp->f_files,
- mp->m_maxicount);
+ M_IGEO(mp)->maxicount);
/* If sb_icount overshot maxicount, report actual allocation */
statp->f_files = max_t(typeof(statp->f_files),
@@ -1180,8 +879,10 @@
* there is no log replay required to write the inodes to disk - this is the
* primary difference between a sync and a quiesce.
*
- * Note: xfs_log_quiesce() stops background log work - the callers must ensure
- * it is started again when appropriate.
+ * We cancel log work early here to ensure all transactions the log worker may
+ * run have finished before we clean up and log the superblock and write an
+ * unmount record. The unfreeze process is responsible for restarting the log
+ * worker correctly.
*/
void
xfs_quiesce_attr(
@@ -1189,204 +890,18 @@
{
int error = 0;
- /* wait for all modifications to complete */
- while (atomic_read(&mp->m_active_trans) > 0)
- delay(100);
+ cancel_delayed_work_sync(&mp->m_log->l_work);
/* force the log to unpin objects from the now complete transactions */
xfs_log_force(mp, XFS_LOG_SYNC);
- /* reclaim inodes to do any IO before the freeze completes */
- xfs_reclaim_inodes(mp, 0);
- xfs_reclaim_inodes(mp, SYNC_WAIT);
/* Push the superblock and write an unmount record */
error = xfs_log_sbcount(mp);
if (error)
xfs_warn(mp, "xfs_attr_quiesce: failed to log sb changes. "
"Frozen image may not be consistent.");
- /*
- * Just warn here till VFS can correctly support
- * read-only remount without racing.
- */
- WARN_ON(atomic_read(&mp->m_active_trans) != 0);
-
xfs_log_quiesce(mp);
-}
-
-STATIC int
-xfs_test_remount_options(
- struct super_block *sb,
- char *options)
-{
- int error = 0;
- struct xfs_mount *tmp_mp;
-
- tmp_mp = kmem_zalloc(sizeof(*tmp_mp), KM_MAYFAIL);
- if (!tmp_mp)
- return -ENOMEM;
-
- tmp_mp->m_super = sb;
- error = xfs_parseargs(tmp_mp, options);
- xfs_free_fsname(tmp_mp);
- kmem_free(tmp_mp);
-
- return error;
-}
-
-STATIC int
-xfs_fs_remount(
- struct super_block *sb,
- int *flags,
- char *options)
-{
- struct xfs_mount *mp = XFS_M(sb);
- xfs_sb_t *sbp = &mp->m_sb;
- substring_t args[MAX_OPT_ARGS];
- char *p;
- int error;
-
- /* First, check for complete junk; i.e. invalid options */
- error = xfs_test_remount_options(sb, options);
- if (error)
- return error;
-
- sync_filesystem(sb);
- while ((p = strsep(&options, ",")) != NULL) {
- int token;
-
- if (!*p)
- continue;
-
- token = match_token(p, tokens, args);
- switch (token) {
- case Opt_inode64:
- mp->m_flags &= ~XFS_MOUNT_SMALL_INUMS;
- mp->m_maxagi = xfs_set_inode_alloc(mp, sbp->sb_agcount);
- break;
- case Opt_inode32:
- mp->m_flags |= XFS_MOUNT_SMALL_INUMS;
- mp->m_maxagi = xfs_set_inode_alloc(mp, sbp->sb_agcount);
- break;
- default:
- /*
- * Logically we would return an error here to prevent
- * users from believing they might have changed
- * mount options using remount which can't be changed.
- *
- * But unfortunately mount(8) adds all options from
- * mtab and fstab to the mount arguments in some cases
- * so we can't blindly reject options, but have to
- * check for each specified option if it actually
- * differs from the currently set option and only
- * reject it if that's the case.
- *
- * Until that is implemented we return success for
- * every remount request, and silently ignore all
- * options that we can't actually change.
- */
-#if 0
- xfs_info(mp,
- "mount option \"%s\" not supported for remount", p);
- return -EINVAL;
-#else
- break;
-#endif
- }
- }
-
- /* ro -> rw */
- if ((mp->m_flags & XFS_MOUNT_RDONLY) && !(*flags & SB_RDONLY)) {
- if (mp->m_flags & XFS_MOUNT_NORECOVERY) {
- xfs_warn(mp,
- "ro->rw transition prohibited on norecovery mount");
- return -EINVAL;
- }
-
- if (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5 &&
- xfs_sb_has_ro_compat_feature(sbp,
- XFS_SB_FEAT_RO_COMPAT_UNKNOWN)) {
- xfs_warn(mp,
-"ro->rw transition prohibited on unknown (0x%x) ro-compat filesystem",
- (sbp->sb_features_ro_compat &
- XFS_SB_FEAT_RO_COMPAT_UNKNOWN));
- return -EINVAL;
- }
-
- mp->m_flags &= ~XFS_MOUNT_RDONLY;
-
- /*
- * If this is the first remount to writeable state we
- * might have some superblock changes to update.
- */
- if (mp->m_update_sb) {
- error = xfs_sync_sb(mp, false);
- if (error) {
- xfs_warn(mp, "failed to write sb changes");
- return error;
- }
- mp->m_update_sb = false;
- }
-
- /*
- * Fill out the reserve pool if it is empty. Use the stashed
- * value if it is non-zero, otherwise go with the default.
- */
- xfs_restore_resvblks(mp);
- xfs_log_work_queue(mp);
-
- /* Recover any CoW blocks that never got remapped. */
- error = xfs_reflink_recover_cow(mp);
- if (error) {
- xfs_err(mp,
- "Error %d recovering leftover CoW allocations.", error);
- xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
- return error;
- }
- xfs_icache_enable_reclaim(mp);
-
- /* Create the per-AG metadata reservation pool .*/
- error = xfs_fs_reserve_ag_blocks(mp);
- if (error && error != -ENOSPC)
- return error;
- }
-
- /* rw -> ro */
- if (!(mp->m_flags & XFS_MOUNT_RDONLY) && (*flags & SB_RDONLY)) {
- /*
- * Cancel background eofb scanning so it cannot race with the
- * final log force+buftarg wait and deadlock the remount.
- */
- xfs_icache_disable_reclaim(mp);
-
- /* Get rid of any leftover CoW reservations... */
- error = xfs_icache_free_cowblocks(mp, NULL);
- if (error) {
- xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
- return error;
- }
-
- /* Free the per-AG metadata reservation pool. */
- error = xfs_fs_unreserve_ag_blocks(mp);
- if (error) {
- xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
- return error;
- }
-
- /*
- * Before we sync the metadata, we need to free up the reserve
- * block pool so that the used block count in the superblock on
- * disk is correct at the end of the remount. Stash the current
- * reserve pool size so that if we get remounted rw, we can
- * return it to the same size.
- */
- xfs_save_resvblks(mp);
-
- xfs_quiesce_attr(mp);
- mp->m_flags |= XFS_MOUNT_RDONLY;
- }
-
- return 0;
}
/*
@@ -1400,11 +915,21 @@
struct super_block *sb)
{
struct xfs_mount *mp = XFS_M(sb);
+ unsigned int flags;
+ int ret;
- xfs_icache_disable_reclaim(mp);
+ /*
+ * The filesystem is now frozen far enough that memory reclaim
+ * cannot safely operate on the filesystem. Hence we need to
+ * set a GFP_NOFS context here to avoid recursion deadlocks.
+ */
+ flags = memalloc_nofs_save();
+ xfs_stop_block_reaping(mp);
xfs_save_resvblks(mp);
xfs_quiesce_attr(mp);
- return xfs_sync_sb(mp, true);
+ ret = xfs_sync_sb(mp, true);
+ memalloc_nofs_restore(flags);
+ return ret;
}
STATIC int
@@ -1415,16 +940,8 @@
xfs_restore_resvblks(mp);
xfs_log_work_queue(mp);
- xfs_icache_enable_reclaim(mp);
+ xfs_start_block_reaping(mp);
return 0;
-}
-
-STATIC int
-xfs_fs_show_options(
- struct seq_file *m,
- struct dentry *root)
-{
- return xfs_showargs(XFS_M(root->d_sb), m);
}
/*
@@ -1513,8 +1030,14 @@
if (error)
goto free_ifree;
+ error = percpu_counter_init(&mp->m_delalloc_blks, 0, GFP_KERNEL);
+ if (error)
+ goto free_fdblocks;
+
return 0;
+free_fdblocks:
+ percpu_counter_destroy(&mp->m_fdblocks);
free_ifree:
percpu_counter_destroy(&mp->m_ifree);
free_icount:
@@ -1538,228 +1061,12 @@
percpu_counter_destroy(&mp->m_icount);
percpu_counter_destroy(&mp->m_ifree);
percpu_counter_destroy(&mp->m_fdblocks);
+ ASSERT(XFS_FORCED_SHUTDOWN(mp) ||
+ percpu_counter_sum(&mp->m_delalloc_blks) == 0);
+ percpu_counter_destroy(&mp->m_delalloc_blks);
}
-static struct xfs_mount *
-xfs_mount_alloc(
- struct super_block *sb)
-{
- struct xfs_mount *mp;
-
- mp = kzalloc(sizeof(struct xfs_mount), GFP_KERNEL);
- if (!mp)
- return NULL;
-
- mp->m_super = sb;
- spin_lock_init(&mp->m_sb_lock);
- spin_lock_init(&mp->m_agirotor_lock);
- INIT_RADIX_TREE(&mp->m_perag_tree, GFP_ATOMIC);
- spin_lock_init(&mp->m_perag_lock);
- mutex_init(&mp->m_growlock);
- atomic_set(&mp->m_active_trans, 0);
- INIT_DELAYED_WORK(&mp->m_reclaim_work, xfs_reclaim_worker);
- INIT_DELAYED_WORK(&mp->m_eofblocks_work, xfs_eofblocks_worker);
- INIT_DELAYED_WORK(&mp->m_cowblocks_work, xfs_cowblocks_worker);
- mp->m_kobj.kobject.kset = xfs_kset;
- /*
- * We don't create the finobt per-ag space reservation until after log
- * recovery, so we must set this to true so that an ifree transaction
- * started during log recovery will not depend on space reservations
- * for finobt expansion.
- */
- mp->m_finobt_nores = true;
- return mp;
-}
-
-
-STATIC int
-xfs_fs_fill_super(
- struct super_block *sb,
- void *data,
- int silent)
-{
- struct inode *root;
- struct xfs_mount *mp = NULL;
- int flags = 0, error = -ENOMEM;
-
- /*
- * allocate mp and do all low-level struct initializations before we
- * attach it to the super
- */
- mp = xfs_mount_alloc(sb);
- if (!mp)
- goto out;
- sb->s_fs_info = mp;
-
- error = xfs_parseargs(mp, (char *)data);
- if (error)
- goto out_free_fsname;
-
- sb_min_blocksize(sb, BBSIZE);
- sb->s_xattr = xfs_xattr_handlers;
- sb->s_export_op = &xfs_export_operations;
-#ifdef CONFIG_XFS_QUOTA
- sb->s_qcop = &xfs_quotactl_operations;
- sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP | QTYPE_MASK_PRJ;
-#endif
- sb->s_op = &xfs_super_operations;
-
- /*
- * Delay mount work if the debug hook is set. This is debug
- * instrumention to coordinate simulation of xfs mount failures with
- * VFS superblock operations
- */
- if (xfs_globals.mount_delay) {
- xfs_notice(mp, "Delaying mount for %d seconds.",
- xfs_globals.mount_delay);
- msleep(xfs_globals.mount_delay * 1000);
- }
-
- if (silent)
- flags |= XFS_MFSI_QUIET;
-
- error = xfs_open_devices(mp);
- if (error)
- goto out_free_fsname;
-
- error = xfs_init_mount_workqueues(mp);
- if (error)
- goto out_close_devices;
-
- error = xfs_init_percpu_counters(mp);
- if (error)
- goto out_destroy_workqueues;
-
- /* Allocate stats memory before we do operations that might use it */
- mp->m_stats.xs_stats = alloc_percpu(struct xfsstats);
- if (!mp->m_stats.xs_stats) {
- error = -ENOMEM;
- goto out_destroy_counters;
- }
-
- error = xfs_readsb(mp, flags);
- if (error)
- goto out_free_stats;
-
- error = xfs_finish_flags(mp);
- if (error)
- goto out_free_sb;
-
- error = xfs_setup_devices(mp);
- if (error)
- goto out_free_sb;
-
- error = xfs_filestream_mount(mp);
- if (error)
- goto out_free_sb;
-
- /*
- * we must configure the block size in the superblock before we run the
- * full mount process as the mount process can lookup and cache inodes.
- */
- sb->s_magic = XFS_SB_MAGIC;
- sb->s_blocksize = mp->m_sb.sb_blocksize;
- sb->s_blocksize_bits = ffs(sb->s_blocksize) - 1;
- sb->s_maxbytes = xfs_max_file_offset(sb->s_blocksize_bits);
- sb->s_max_links = XFS_MAXLINK;
- sb->s_time_gran = 1;
- set_posix_acl_flag(sb);
-
- /* version 5 superblocks support inode version counters. */
- if (XFS_SB_VERSION_NUM(&mp->m_sb) == XFS_SB_VERSION_5)
- sb->s_flags |= SB_I_VERSION;
-
- if (mp->m_flags & XFS_MOUNT_DAX) {
- bool rtdev_is_dax = false, datadev_is_dax;
-
- xfs_warn(mp,
- "DAX enabled. Warning: EXPERIMENTAL, use at your own risk");
-
- datadev_is_dax = bdev_dax_supported(mp->m_ddev_targp->bt_bdev,
- sb->s_blocksize);
- if (mp->m_rtdev_targp)
- rtdev_is_dax = bdev_dax_supported(
- mp->m_rtdev_targp->bt_bdev, sb->s_blocksize);
- if (!rtdev_is_dax && !datadev_is_dax) {
- xfs_alert(mp,
- "DAX unsupported by block device. Turning off DAX.");
- mp->m_flags &= ~XFS_MOUNT_DAX;
- }
- if (xfs_sb_version_hasreflink(&mp->m_sb)) {
- xfs_alert(mp,
- "DAX and reflink cannot be used together!");
- error = -EINVAL;
- goto out_filestream_unmount;
- }
- }
-
- if (mp->m_flags & XFS_MOUNT_DISCARD) {
- struct request_queue *q = bdev_get_queue(sb->s_bdev);
-
- if (!blk_queue_discard(q)) {
- xfs_warn(mp, "mounting with \"discard\" option, but "
- "the device does not support discard");
- mp->m_flags &= ~XFS_MOUNT_DISCARD;
- }
- }
-
- if (xfs_sb_version_hasreflink(&mp->m_sb) && mp->m_sb.sb_rblocks) {
- xfs_alert(mp,
- "reflink not compatible with realtime device!");
- error = -EINVAL;
- goto out_filestream_unmount;
- }
-
- if (xfs_sb_version_hasrmapbt(&mp->m_sb) && mp->m_sb.sb_rblocks) {
- xfs_alert(mp,
- "reverse mapping btree not compatible with realtime device!");
- error = -EINVAL;
- goto out_filestream_unmount;
- }
-
- error = xfs_mountfs(mp);
- if (error)
- goto out_filestream_unmount;
-
- root = igrab(VFS_I(mp->m_rootip));
- if (!root) {
- error = -ENOENT;
- goto out_unmount;
- }
- sb->s_root = d_make_root(root);
- if (!sb->s_root) {
- error = -ENOMEM;
- goto out_unmount;
- }
-
- return 0;
-
- out_filestream_unmount:
- xfs_filestream_unmount(mp);
- out_free_sb:
- xfs_freesb(mp);
- out_free_stats:
- free_percpu(mp->m_stats.xs_stats);
- out_destroy_counters:
- xfs_destroy_percpu_counters(mp);
- out_destroy_workqueues:
- xfs_destroy_mount_workqueues(mp);
- out_close_devices:
- xfs_close_devices(mp);
- out_free_fsname:
- sb->s_fs_info = NULL;
- xfs_free_fsname(mp);
- kfree(mp);
- out:
- return error;
-
- out_unmount:
- xfs_filestream_unmount(mp);
- xfs_unmountfs(mp);
- goto out_free_sb;
-}
-
-STATIC void
+static void
xfs_fs_put_super(
struct super_block *sb)
{
@@ -1780,18 +1087,7 @@
xfs_close_devices(mp);
sb->s_fs_info = NULL;
- xfs_free_fsname(mp);
- kfree(mp);
-}
-
-STATIC struct dentry *
-xfs_fs_mount(
- struct file_system_type *fs_type,
- int flags,
- const char *dev_name,
- void *data)
-{
- return mount_bdev(fs_type, flags, dev_name, data, xfs_fs_fill_super);
+ xfs_mount_free(mp);
}
static long
@@ -1823,16 +1119,790 @@
.freeze_fs = xfs_fs_freeze,
.unfreeze_fs = xfs_fs_unfreeze,
.statfs = xfs_fs_statfs,
- .remount_fs = xfs_fs_remount,
.show_options = xfs_fs_show_options,
.nr_cached_objects = xfs_fs_nr_cached_objects,
.free_cached_objects = xfs_fs_free_cached_objects,
};
+static int
+suffix_kstrtoint(
+ const char *s,
+ unsigned int base,
+ int *res)
+{
+ int last, shift_left_factor = 0, _res;
+ char *value;
+ int ret = 0;
+
+ value = kstrdup(s, GFP_KERNEL);
+ if (!value)
+ return -ENOMEM;
+
+ last = strlen(value) - 1;
+ if (value[last] == 'K' || value[last] == 'k') {
+ shift_left_factor = 10;
+ value[last] = '\0';
+ }
+ if (value[last] == 'M' || value[last] == 'm') {
+ shift_left_factor = 20;
+ value[last] = '\0';
+ }
+ if (value[last] == 'G' || value[last] == 'g') {
+ shift_left_factor = 30;
+ value[last] = '\0';
+ }
+
+ if (kstrtoint(value, base, &_res))
+ ret = -EINVAL;
+ kfree(value);
+ *res = _res << shift_left_factor;
+ return ret;
+}
+
+static inline void
+xfs_fs_warn_deprecated(
+ struct fs_context *fc,
+ struct fs_parameter *param,
+ uint64_t flag,
+ bool value)
+{
+ /* Don't print the warning if reconfiguring and current mount point
+ * already had the flag set
+ */
+ if ((fc->purpose & FS_CONTEXT_FOR_RECONFIGURE) &&
+ !!(XFS_M(fc->root->d_sb)->m_flags & flag) == value)
+ return;
+ xfs_warn(fc->s_fs_info, "%s mount option is deprecated.", param->key);
+}
+
+/*
+ * Set mount state from a mount option.
+ *
+ * NOTE: mp->m_super is NULL here!
+ */
+static int
+xfs_fc_parse_param(
+ struct fs_context *fc,
+ struct fs_parameter *param)
+{
+ struct xfs_mount *parsing_mp = fc->s_fs_info;
+ struct fs_parse_result result;
+ int size = 0;
+ int opt;
+
+ opt = fs_parse(fc, xfs_fs_parameters, param, &result);
+ if (opt < 0)
+ return opt;
+
+ switch (opt) {
+ case Opt_logbufs:
+ parsing_mp->m_logbufs = result.uint_32;
+ return 0;
+ case Opt_logbsize:
+ if (suffix_kstrtoint(param->string, 10, &parsing_mp->m_logbsize))
+ return -EINVAL;
+ return 0;
+ case Opt_logdev:
+ kfree(parsing_mp->m_logname);
+ parsing_mp->m_logname = kstrdup(param->string, GFP_KERNEL);
+ if (!parsing_mp->m_logname)
+ return -ENOMEM;
+ return 0;
+ case Opt_rtdev:
+ kfree(parsing_mp->m_rtname);
+ parsing_mp->m_rtname = kstrdup(param->string, GFP_KERNEL);
+ if (!parsing_mp->m_rtname)
+ return -ENOMEM;
+ return 0;
+ case Opt_allocsize:
+ if (suffix_kstrtoint(param->string, 10, &size))
+ return -EINVAL;
+ parsing_mp->m_allocsize_log = ffs(size) - 1;
+ parsing_mp->m_flags |= XFS_MOUNT_ALLOCSIZE;
+ return 0;
+ case Opt_grpid:
+ case Opt_bsdgroups:
+ parsing_mp->m_flags |= XFS_MOUNT_GRPID;
+ return 0;
+ case Opt_nogrpid:
+ case Opt_sysvgroups:
+ parsing_mp->m_flags &= ~XFS_MOUNT_GRPID;
+ return 0;
+ case Opt_wsync:
+ parsing_mp->m_flags |= XFS_MOUNT_WSYNC;
+ return 0;
+ case Opt_norecovery:
+ parsing_mp->m_flags |= XFS_MOUNT_NORECOVERY;
+ return 0;
+ case Opt_noalign:
+ parsing_mp->m_flags |= XFS_MOUNT_NOALIGN;
+ return 0;
+ case Opt_swalloc:
+ parsing_mp->m_flags |= XFS_MOUNT_SWALLOC;
+ return 0;
+ case Opt_sunit:
+ parsing_mp->m_dalign = result.uint_32;
+ return 0;
+ case Opt_swidth:
+ parsing_mp->m_swidth = result.uint_32;
+ return 0;
+ case Opt_inode32:
+ parsing_mp->m_flags |= XFS_MOUNT_SMALL_INUMS;
+ return 0;
+ case Opt_inode64:
+ parsing_mp->m_flags &= ~XFS_MOUNT_SMALL_INUMS;
+ return 0;
+ case Opt_nouuid:
+ parsing_mp->m_flags |= XFS_MOUNT_NOUUID;
+ return 0;
+ case Opt_largeio:
+ parsing_mp->m_flags |= XFS_MOUNT_LARGEIO;
+ return 0;
+ case Opt_nolargeio:
+ parsing_mp->m_flags &= ~XFS_MOUNT_LARGEIO;
+ return 0;
+ case Opt_filestreams:
+ parsing_mp->m_flags |= XFS_MOUNT_FILESTREAMS;
+ return 0;
+ case Opt_noquota:
+ parsing_mp->m_qflags &= ~XFS_ALL_QUOTA_ACCT;
+ parsing_mp->m_qflags &= ~XFS_ALL_QUOTA_ENFD;
+ parsing_mp->m_qflags &= ~XFS_ALL_QUOTA_ACTIVE;
+ return 0;
+ case Opt_quota:
+ case Opt_uquota:
+ case Opt_usrquota:
+ parsing_mp->m_qflags |= (XFS_UQUOTA_ACCT | XFS_UQUOTA_ACTIVE |
+ XFS_UQUOTA_ENFD);
+ return 0;
+ case Opt_qnoenforce:
+ case Opt_uqnoenforce:
+ parsing_mp->m_qflags |= (XFS_UQUOTA_ACCT | XFS_UQUOTA_ACTIVE);
+ parsing_mp->m_qflags &= ~XFS_UQUOTA_ENFD;
+ return 0;
+ case Opt_pquota:
+ case Opt_prjquota:
+ parsing_mp->m_qflags |= (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE |
+ XFS_PQUOTA_ENFD);
+ return 0;
+ case Opt_pqnoenforce:
+ parsing_mp->m_qflags |= (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE);
+ parsing_mp->m_qflags &= ~XFS_PQUOTA_ENFD;
+ return 0;
+ case Opt_gquota:
+ case Opt_grpquota:
+ parsing_mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE |
+ XFS_GQUOTA_ENFD);
+ return 0;
+ case Opt_gqnoenforce:
+ parsing_mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE);
+ parsing_mp->m_qflags &= ~XFS_GQUOTA_ENFD;
+ return 0;
+ case Opt_discard:
+ parsing_mp->m_flags |= XFS_MOUNT_DISCARD;
+ return 0;
+ case Opt_nodiscard:
+ parsing_mp->m_flags &= ~XFS_MOUNT_DISCARD;
+ return 0;
+#ifdef CONFIG_FS_DAX
+ case Opt_dax:
+ xfs_mount_set_dax_mode(parsing_mp, XFS_DAX_ALWAYS);
+ return 0;
+ case Opt_dax_enum:
+ xfs_mount_set_dax_mode(parsing_mp, result.uint_32);
+ return 0;
+#endif
+ /* Following mount options will be removed in September 2025 */
+ case Opt_ikeep:
+ xfs_fs_warn_deprecated(fc, param, XFS_MOUNT_IKEEP, true);
+ parsing_mp->m_flags |= XFS_MOUNT_IKEEP;
+ return 0;
+ case Opt_noikeep:
+ xfs_fs_warn_deprecated(fc, param, XFS_MOUNT_IKEEP, false);
+ parsing_mp->m_flags &= ~XFS_MOUNT_IKEEP;
+ return 0;
+ case Opt_attr2:
+ xfs_fs_warn_deprecated(fc, param, XFS_MOUNT_ATTR2, true);
+ parsing_mp->m_flags |= XFS_MOUNT_ATTR2;
+ return 0;
+ case Opt_noattr2:
+ xfs_fs_warn_deprecated(fc, param, XFS_MOUNT_NOATTR2, true);
+ parsing_mp->m_flags &= ~XFS_MOUNT_ATTR2;
+ parsing_mp->m_flags |= XFS_MOUNT_NOATTR2;
+ return 0;
+ default:
+ xfs_warn(parsing_mp, "unknown mount option [%s].", param->key);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int
+xfs_fc_validate_params(
+ struct xfs_mount *mp)
+{
+ /*
+ * no recovery flag requires a read-only mount
+ */
+ if ((mp->m_flags & XFS_MOUNT_NORECOVERY) &&
+ !(mp->m_flags & XFS_MOUNT_RDONLY)) {
+ xfs_warn(mp, "no-recovery mounts must be read-only.");
+ return -EINVAL;
+ }
+
+ if ((mp->m_flags & XFS_MOUNT_NOALIGN) &&
+ (mp->m_dalign || mp->m_swidth)) {
+ xfs_warn(mp,
+ "sunit and swidth options incompatible with the noalign option");
+ return -EINVAL;
+ }
+
+ if (!IS_ENABLED(CONFIG_XFS_QUOTA) && mp->m_qflags != 0) {
+ xfs_warn(mp, "quota support not available in this kernel.");
+ return -EINVAL;
+ }
+
+ if ((mp->m_dalign && !mp->m_swidth) ||
+ (!mp->m_dalign && mp->m_swidth)) {
+ xfs_warn(mp, "sunit and swidth must be specified together");
+ return -EINVAL;
+ }
+
+ if (mp->m_dalign && (mp->m_swidth % mp->m_dalign != 0)) {
+ xfs_warn(mp,
+ "stripe width (%d) must be a multiple of the stripe unit (%d)",
+ mp->m_swidth, mp->m_dalign);
+ return -EINVAL;
+ }
+
+ if (mp->m_logbufs != -1 &&
+ mp->m_logbufs != 0 &&
+ (mp->m_logbufs < XLOG_MIN_ICLOGS ||
+ mp->m_logbufs > XLOG_MAX_ICLOGS)) {
+ xfs_warn(mp, "invalid logbufs value: %d [not %d-%d]",
+ mp->m_logbufs, XLOG_MIN_ICLOGS, XLOG_MAX_ICLOGS);
+ return -EINVAL;
+ }
+
+ if (mp->m_logbsize != -1 &&
+ mp->m_logbsize != 0 &&
+ (mp->m_logbsize < XLOG_MIN_RECORD_BSIZE ||
+ mp->m_logbsize > XLOG_MAX_RECORD_BSIZE ||
+ !is_power_of_2(mp->m_logbsize))) {
+ xfs_warn(mp,
+ "invalid logbufsize: %d [not 16k,32k,64k,128k or 256k]",
+ mp->m_logbsize);
+ return -EINVAL;
+ }
+
+ if ((mp->m_flags & XFS_MOUNT_ALLOCSIZE) &&
+ (mp->m_allocsize_log > XFS_MAX_IO_LOG ||
+ mp->m_allocsize_log < XFS_MIN_IO_LOG)) {
+ xfs_warn(mp, "invalid log iosize: %d [not %d-%d]",
+ mp->m_allocsize_log, XFS_MIN_IO_LOG, XFS_MAX_IO_LOG);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int
+xfs_fc_fill_super(
+ struct super_block *sb,
+ struct fs_context *fc)
+{
+ struct xfs_mount *mp = sb->s_fs_info;
+ struct inode *root;
+ int flags = 0, error;
+
+ mp->m_super = sb;
+
+ error = xfs_fc_validate_params(mp);
+ if (error)
+ goto out_free_names;
+
+ sb_min_blocksize(sb, BBSIZE);
+ sb->s_xattr = xfs_xattr_handlers;
+ sb->s_export_op = &xfs_export_operations;
+#ifdef CONFIG_XFS_QUOTA
+ sb->s_qcop = &xfs_quotactl_operations;
+ sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP | QTYPE_MASK_PRJ;
+#endif
+ sb->s_op = &xfs_super_operations;
+
+ /*
+ * Delay mount work if the debug hook is set. This is debug
+ * instrumention to coordinate simulation of xfs mount failures with
+ * VFS superblock operations
+ */
+ if (xfs_globals.mount_delay) {
+ xfs_notice(mp, "Delaying mount for %d seconds.",
+ xfs_globals.mount_delay);
+ msleep(xfs_globals.mount_delay * 1000);
+ }
+
+ if (fc->sb_flags & SB_SILENT)
+ flags |= XFS_MFSI_QUIET;
+
+ error = xfs_open_devices(mp);
+ if (error)
+ goto out_free_names;
+
+ error = xfs_init_mount_workqueues(mp);
+ if (error)
+ goto out_close_devices;
+
+ error = xfs_init_percpu_counters(mp);
+ if (error)
+ goto out_destroy_workqueues;
+
+ /* Allocate stats memory before we do operations that might use it */
+ mp->m_stats.xs_stats = alloc_percpu(struct xfsstats);
+ if (!mp->m_stats.xs_stats) {
+ error = -ENOMEM;
+ goto out_destroy_counters;
+ }
+
+ error = xfs_readsb(mp, flags);
+ if (error)
+ goto out_free_stats;
+
+ error = xfs_finish_flags(mp);
+ if (error)
+ goto out_free_sb;
+
+ error = xfs_setup_devices(mp);
+ if (error)
+ goto out_free_sb;
+
+ /* V4 support is undergoing deprecation. */
+ if (!xfs_sb_version_hascrc(&mp->m_sb)) {
+#ifdef CONFIG_XFS_SUPPORT_V4
+ xfs_warn_once(mp,
+ "Deprecated V4 format (crc=0) will not be supported after September 2030.");
+#else
+ xfs_warn(mp,
+ "Deprecated V4 format (crc=0) not supported by kernel.");
+ error = -EINVAL;
+ goto out_free_sb;
+#endif
+ }
+
+ /*
+ * XFS block mappings use 54 bits to store the logical block offset.
+ * This should suffice to handle the maximum file size that the VFS
+ * supports (currently 2^63 bytes on 64-bit and ULONG_MAX << PAGE_SHIFT
+ * bytes on 32-bit), but as XFS and VFS have gotten the s_maxbytes
+ * calculation wrong on 32-bit kernels in the past, we'll add a WARN_ON
+ * to check this assertion.
+ *
+ * Avoid integer overflow by comparing the maximum bmbt offset to the
+ * maximum pagecache offset in units of fs blocks.
+ */
+ if (XFS_B_TO_FSBT(mp, MAX_LFS_FILESIZE) > XFS_MAX_FILEOFF) {
+ xfs_warn(mp,
+"MAX_LFS_FILESIZE block offset (%llu) exceeds extent map maximum (%llu)!",
+ XFS_B_TO_FSBT(mp, MAX_LFS_FILESIZE),
+ XFS_MAX_FILEOFF);
+ error = -EINVAL;
+ goto out_free_sb;
+ }
+
+ error = xfs_filestream_mount(mp);
+ if (error)
+ goto out_free_sb;
+
+ /*
+ * we must configure the block size in the superblock before we run the
+ * full mount process as the mount process can lookup and cache inodes.
+ */
+ sb->s_magic = XFS_SUPER_MAGIC;
+ sb->s_blocksize = mp->m_sb.sb_blocksize;
+ sb->s_blocksize_bits = ffs(sb->s_blocksize) - 1;
+ sb->s_maxbytes = MAX_LFS_FILESIZE;
+ sb->s_max_links = XFS_MAXLINK;
+ sb->s_time_gran = 1;
+ if (xfs_sb_version_hasbigtime(&mp->m_sb)) {
+ sb->s_time_min = xfs_bigtime_to_unix(XFS_BIGTIME_TIME_MIN);
+ sb->s_time_max = xfs_bigtime_to_unix(XFS_BIGTIME_TIME_MAX);
+ } else {
+ sb->s_time_min = XFS_LEGACY_TIME_MIN;
+ sb->s_time_max = XFS_LEGACY_TIME_MAX;
+ }
+ trace_xfs_inode_timestamp_range(mp, sb->s_time_min, sb->s_time_max);
+ sb->s_iflags |= SB_I_CGROUPWB;
+
+ set_posix_acl_flag(sb);
+
+ /* version 5 superblocks support inode version counters. */
+ if (XFS_SB_VERSION_NUM(&mp->m_sb) == XFS_SB_VERSION_5)
+ sb->s_flags |= SB_I_VERSION;
+
+ if (xfs_sb_version_hasbigtime(&mp->m_sb))
+ xfs_warn(mp,
+ "EXPERIMENTAL big timestamp feature in use. Use at your own risk!");
+
+ if (mp->m_flags & XFS_MOUNT_DAX_ALWAYS) {
+ bool rtdev_is_dax = false, datadev_is_dax;
+
+ xfs_warn(mp,
+ "DAX enabled. Warning: EXPERIMENTAL, use at your own risk");
+
+ datadev_is_dax = bdev_dax_supported(mp->m_ddev_targp->bt_bdev,
+ sb->s_blocksize);
+ if (mp->m_rtdev_targp)
+ rtdev_is_dax = bdev_dax_supported(
+ mp->m_rtdev_targp->bt_bdev, sb->s_blocksize);
+ if (!rtdev_is_dax && !datadev_is_dax) {
+ xfs_alert(mp,
+ "DAX unsupported by block device. Turning off DAX.");
+ xfs_mount_set_dax_mode(mp, XFS_DAX_NEVER);
+ }
+ if (xfs_sb_version_hasreflink(&mp->m_sb)) {
+ xfs_alert(mp,
+ "DAX and reflink cannot be used together!");
+ error = -EINVAL;
+ goto out_filestream_unmount;
+ }
+ }
+
+ if (mp->m_flags & XFS_MOUNT_DISCARD) {
+ struct request_queue *q = bdev_get_queue(sb->s_bdev);
+
+ if (!blk_queue_discard(q)) {
+ xfs_warn(mp, "mounting with \"discard\" option, but "
+ "the device does not support discard");
+ mp->m_flags &= ~XFS_MOUNT_DISCARD;
+ }
+ }
+
+ if (xfs_sb_version_hasreflink(&mp->m_sb)) {
+ if (mp->m_sb.sb_rblocks) {
+ xfs_alert(mp,
+ "reflink not compatible with realtime device!");
+ error = -EINVAL;
+ goto out_filestream_unmount;
+ }
+
+ if (xfs_globals.always_cow) {
+ xfs_info(mp, "using DEBUG-only always_cow mode.");
+ mp->m_always_cow = true;
+ }
+ }
+
+ if (xfs_sb_version_hasrmapbt(&mp->m_sb) && mp->m_sb.sb_rblocks) {
+ xfs_alert(mp,
+ "reverse mapping btree not compatible with realtime device!");
+ error = -EINVAL;
+ goto out_filestream_unmount;
+ }
+
+ if (xfs_sb_version_hasinobtcounts(&mp->m_sb))
+ xfs_warn(mp,
+ "EXPERIMENTAL inode btree counters feature in use. Use at your own risk!");
+
+ error = xfs_mountfs(mp);
+ if (error)
+ goto out_filestream_unmount;
+
+ root = igrab(VFS_I(mp->m_rootip));
+ if (!root) {
+ error = -ENOENT;
+ goto out_unmount;
+ }
+ sb->s_root = d_make_root(root);
+ if (!sb->s_root) {
+ error = -ENOMEM;
+ goto out_unmount;
+ }
+
+ return 0;
+
+ out_filestream_unmount:
+ xfs_filestream_unmount(mp);
+ out_free_sb:
+ xfs_freesb(mp);
+ out_free_stats:
+ free_percpu(mp->m_stats.xs_stats);
+ out_destroy_counters:
+ xfs_destroy_percpu_counters(mp);
+ out_destroy_workqueues:
+ xfs_destroy_mount_workqueues(mp);
+ out_close_devices:
+ xfs_close_devices(mp);
+ out_free_names:
+ sb->s_fs_info = NULL;
+ xfs_mount_free(mp);
+ return error;
+
+ out_unmount:
+ xfs_filestream_unmount(mp);
+ xfs_unmountfs(mp);
+ goto out_free_sb;
+}
+
+static int
+xfs_fc_get_tree(
+ struct fs_context *fc)
+{
+ return get_tree_bdev(fc, xfs_fc_fill_super);
+}
+
+static int
+xfs_remount_rw(
+ struct xfs_mount *mp)
+{
+ struct xfs_sb *sbp = &mp->m_sb;
+ int error;
+
+ if (mp->m_flags & XFS_MOUNT_NORECOVERY) {
+ xfs_warn(mp,
+ "ro->rw transition prohibited on norecovery mount");
+ return -EINVAL;
+ }
+
+ if (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5 &&
+ xfs_sb_has_ro_compat_feature(sbp, XFS_SB_FEAT_RO_COMPAT_UNKNOWN)) {
+ xfs_warn(mp,
+ "ro->rw transition prohibited on unknown (0x%x) ro-compat filesystem",
+ (sbp->sb_features_ro_compat &
+ XFS_SB_FEAT_RO_COMPAT_UNKNOWN));
+ return -EINVAL;
+ }
+
+ mp->m_flags &= ~XFS_MOUNT_RDONLY;
+
+ /*
+ * If this is the first remount to writeable state we might have some
+ * superblock changes to update.
+ */
+ if (mp->m_update_sb) {
+ error = xfs_sync_sb(mp, false);
+ if (error) {
+ xfs_warn(mp, "failed to write sb changes");
+ return error;
+ }
+ mp->m_update_sb = false;
+ }
+
+ /*
+ * Fill out the reserve pool if it is empty. Use the stashed value if
+ * it is non-zero, otherwise go with the default.
+ */
+ xfs_restore_resvblks(mp);
+ xfs_log_work_queue(mp);
+
+ /* Recover any CoW blocks that never got remapped. */
+ error = xfs_reflink_recover_cow(mp);
+ if (error) {
+ xfs_err(mp,
+ "Error %d recovering leftover CoW allocations.", error);
+ xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
+ return error;
+ }
+ xfs_start_block_reaping(mp);
+
+ /* Create the per-AG metadata reservation pool .*/
+ error = xfs_fs_reserve_ag_blocks(mp);
+ if (error && error != -ENOSPC)
+ return error;
+
+ return 0;
+}
+
+static int
+xfs_remount_ro(
+ struct xfs_mount *mp)
+{
+ struct xfs_eofblocks eofb = {
+ .eof_flags = XFS_EOF_FLAGS_SYNC,
+ };
+ int error;
+
+ /* Flush all the dirty data to disk. */
+ error = sync_filesystem(mp->m_super);
+ if (error)
+ return error;
+
+ /*
+ * Cancel background eofb scanning so it cannot race with the final
+ * log force+buftarg wait and deadlock the remount.
+ */
+ xfs_stop_block_reaping(mp);
+
+ /*
+ * Clear out all remaining COW staging extents and speculative post-EOF
+ * preallocations so that we don't leave inodes requiring inactivation
+ * cleanups during reclaim on a read-only mount. We must process every
+ * cached inode, so this requires a synchronous cache scan.
+ */
+ error = xfs_icache_free_cowblocks(mp, &eofb);
+ if (error) {
+ xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
+ return error;
+ }
+
+ /* Free the per-AG metadata reservation pool. */
+ error = xfs_fs_unreserve_ag_blocks(mp);
+ if (error) {
+ xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
+ return error;
+ }
+
+ /*
+ * Before we sync the metadata, we need to free up the reserve block
+ * pool so that the used block count in the superblock on disk is
+ * correct at the end of the remount. Stash the current* reserve pool
+ * size so that if we get remounted rw, we can return it to the same
+ * size.
+ */
+ xfs_save_resvblks(mp);
+
+ xfs_quiesce_attr(mp);
+ mp->m_flags |= XFS_MOUNT_RDONLY;
+
+ return 0;
+}
+
+/*
+ * Logically we would return an error here to prevent users from believing
+ * they might have changed mount options using remount which can't be changed.
+ *
+ * But unfortunately mount(8) adds all options from mtab and fstab to the mount
+ * arguments in some cases so we can't blindly reject options, but have to
+ * check for each specified option if it actually differs from the currently
+ * set option and only reject it if that's the case.
+ *
+ * Until that is implemented we return success for every remount request, and
+ * silently ignore all options that we can't actually change.
+ */
+static int
+xfs_fc_reconfigure(
+ struct fs_context *fc)
+{
+ struct xfs_mount *mp = XFS_M(fc->root->d_sb);
+ struct xfs_mount *new_mp = fc->s_fs_info;
+ xfs_sb_t *sbp = &mp->m_sb;
+ int flags = fc->sb_flags;
+ int error;
+
+ /* version 5 superblocks always support version counters. */
+ if (XFS_SB_VERSION_NUM(&mp->m_sb) == XFS_SB_VERSION_5)
+ fc->sb_flags |= SB_I_VERSION;
+
+ error = xfs_fc_validate_params(new_mp);
+ if (error)
+ return error;
+
+ /* inode32 -> inode64 */
+ if ((mp->m_flags & XFS_MOUNT_SMALL_INUMS) &&
+ !(new_mp->m_flags & XFS_MOUNT_SMALL_INUMS)) {
+ mp->m_flags &= ~XFS_MOUNT_SMALL_INUMS;
+ mp->m_maxagi = xfs_set_inode_alloc(mp, sbp->sb_agcount);
+ }
+
+ /* inode64 -> inode32 */
+ if (!(mp->m_flags & XFS_MOUNT_SMALL_INUMS) &&
+ (new_mp->m_flags & XFS_MOUNT_SMALL_INUMS)) {
+ mp->m_flags |= XFS_MOUNT_SMALL_INUMS;
+ mp->m_maxagi = xfs_set_inode_alloc(mp, sbp->sb_agcount);
+ }
+
+ /* ro -> rw */
+ if ((mp->m_flags & XFS_MOUNT_RDONLY) && !(flags & SB_RDONLY)) {
+ error = xfs_remount_rw(mp);
+ if (error)
+ return error;
+ }
+
+ /* rw -> ro */
+ if (!(mp->m_flags & XFS_MOUNT_RDONLY) && (flags & SB_RDONLY)) {
+ error = xfs_remount_ro(mp);
+ if (error)
+ return error;
+ }
+
+ return 0;
+}
+
+static void xfs_fc_free(
+ struct fs_context *fc)
+{
+ struct xfs_mount *mp = fc->s_fs_info;
+
+ /*
+ * mp is stored in the fs_context when it is initialized.
+ * mp is transferred to the superblock on a successful mount,
+ * but if an error occurs before the transfer we have to free
+ * it here.
+ */
+ if (mp)
+ xfs_mount_free(mp);
+}
+
+static const struct fs_context_operations xfs_context_ops = {
+ .parse_param = xfs_fc_parse_param,
+ .get_tree = xfs_fc_get_tree,
+ .reconfigure = xfs_fc_reconfigure,
+ .free = xfs_fc_free,
+};
+
+static int xfs_init_fs_context(
+ struct fs_context *fc)
+{
+ struct xfs_mount *mp;
+
+ mp = kmem_alloc(sizeof(struct xfs_mount), KM_ZERO);
+ if (!mp)
+ return -ENOMEM;
+
+ spin_lock_init(&mp->m_sb_lock);
+ spin_lock_init(&mp->m_agirotor_lock);
+ INIT_RADIX_TREE(&mp->m_perag_tree, GFP_ATOMIC);
+ spin_lock_init(&mp->m_perag_lock);
+ mutex_init(&mp->m_growlock);
+ INIT_WORK(&mp->m_flush_inodes_work, xfs_flush_inodes_worker);
+ INIT_DELAYED_WORK(&mp->m_reclaim_work, xfs_reclaim_worker);
+ INIT_DELAYED_WORK(&mp->m_eofblocks_work, xfs_eofblocks_worker);
+ INIT_DELAYED_WORK(&mp->m_cowblocks_work, xfs_cowblocks_worker);
+ mp->m_kobj.kobject.kset = xfs_kset;
+ /*
+ * We don't create the finobt per-ag space reservation until after log
+ * recovery, so we must set this to true so that an ifree transaction
+ * started during log recovery will not depend on space reservations
+ * for finobt expansion.
+ */
+ mp->m_finobt_nores = true;
+
+ /*
+ * These can be overridden by the mount option parsing.
+ */
+ mp->m_logbufs = -1;
+ mp->m_logbsize = -1;
+ mp->m_allocsize_log = 16; /* 64k */
+
+ /*
+ * Copy binary VFS mount flags we are interested in.
+ */
+ if (fc->sb_flags & SB_RDONLY)
+ mp->m_flags |= XFS_MOUNT_RDONLY;
+ if (fc->sb_flags & SB_DIRSYNC)
+ mp->m_flags |= XFS_MOUNT_DIRSYNC;
+ if (fc->sb_flags & SB_SYNCHRONOUS)
+ mp->m_flags |= XFS_MOUNT_WSYNC;
+
+ fc->s_fs_info = mp;
+ fc->ops = &xfs_context_ops;
+
+ return 0;
+}
+
static struct file_system_type xfs_fs_type = {
.owner = THIS_MODULE,
.name = "xfs",
- .mount = xfs_fs_mount,
+ .init_fs_context = xfs_init_fs_context,
+ .parameters = xfs_fs_parameters,
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
@@ -1841,37 +1911,39 @@
STATIC int __init
xfs_init_zones(void)
{
- if (bioset_init(&xfs_ioend_bioset, 4 * (PAGE_SIZE / SECTOR_SIZE),
- offsetof(struct xfs_ioend, io_inline_bio),
- BIOSET_NEED_BVECS))
+ xfs_log_ticket_zone = kmem_cache_create("xfs_log_ticket",
+ sizeof(struct xlog_ticket),
+ 0, 0, NULL);
+ if (!xfs_log_ticket_zone)
goto out;
- xfs_log_ticket_zone = kmem_zone_init(sizeof(xlog_ticket_t),
- "xfs_log_ticket");
- if (!xfs_log_ticket_zone)
- goto out_free_ioend_bioset;
-
- xfs_bmap_free_item_zone = kmem_zone_init(
- sizeof(struct xfs_extent_free_item),
- "xfs_bmap_free_item");
+ xfs_bmap_free_item_zone = kmem_cache_create("xfs_bmap_free_item",
+ sizeof(struct xfs_extent_free_item),
+ 0, 0, NULL);
if (!xfs_bmap_free_item_zone)
goto out_destroy_log_ticket_zone;
- xfs_btree_cur_zone = kmem_zone_init(sizeof(xfs_btree_cur_t),
- "xfs_btree_cur");
+ xfs_btree_cur_zone = kmem_cache_create("xfs_btree_cur",
+ sizeof(struct xfs_btree_cur),
+ 0, 0, NULL);
if (!xfs_btree_cur_zone)
goto out_destroy_bmap_free_item_zone;
- xfs_da_state_zone = kmem_zone_init(sizeof(xfs_da_state_t),
- "xfs_da_state");
+ xfs_da_state_zone = kmem_cache_create("xfs_da_state",
+ sizeof(struct xfs_da_state),
+ 0, 0, NULL);
if (!xfs_da_state_zone)
goto out_destroy_btree_cur_zone;
- xfs_ifork_zone = kmem_zone_init(sizeof(struct xfs_ifork), "xfs_ifork");
+ xfs_ifork_zone = kmem_cache_create("xfs_ifork",
+ sizeof(struct xfs_ifork),
+ 0, 0, NULL);
if (!xfs_ifork_zone)
goto out_destroy_da_state_zone;
- xfs_trans_zone = kmem_zone_init(sizeof(xfs_trans_t), "xfs_trans");
+ xfs_trans_zone = kmem_cache_create("xfs_trans",
+ sizeof(struct xfs_trans),
+ 0, 0, NULL);
if (!xfs_trans_zone)
goto out_destroy_ifork_zone;
@@ -1881,111 +1953,122 @@
* size possible under XFS. This wastes a little bit of memory,
* but it is much faster.
*/
- xfs_buf_item_zone = kmem_zone_init(sizeof(struct xfs_buf_log_item),
- "xfs_buf_item");
+ xfs_buf_item_zone = kmem_cache_create("xfs_buf_item",
+ sizeof(struct xfs_buf_log_item),
+ 0, 0, NULL);
if (!xfs_buf_item_zone)
goto out_destroy_trans_zone;
- xfs_efd_zone = kmem_zone_init((sizeof(xfs_efd_log_item_t) +
- ((XFS_EFD_MAX_FAST_EXTENTS - 1) *
- sizeof(xfs_extent_t))), "xfs_efd_item");
+ xfs_efd_zone = kmem_cache_create("xfs_efd_item",
+ (sizeof(struct xfs_efd_log_item) +
+ (XFS_EFD_MAX_FAST_EXTENTS - 1) *
+ sizeof(struct xfs_extent)),
+ 0, 0, NULL);
if (!xfs_efd_zone)
goto out_destroy_buf_item_zone;
- xfs_efi_zone = kmem_zone_init((sizeof(xfs_efi_log_item_t) +
- ((XFS_EFI_MAX_FAST_EXTENTS - 1) *
- sizeof(xfs_extent_t))), "xfs_efi_item");
+ xfs_efi_zone = kmem_cache_create("xfs_efi_item",
+ (sizeof(struct xfs_efi_log_item) +
+ (XFS_EFI_MAX_FAST_EXTENTS - 1) *
+ sizeof(struct xfs_extent)),
+ 0, 0, NULL);
if (!xfs_efi_zone)
goto out_destroy_efd_zone;
- xfs_inode_zone =
- kmem_zone_init_flags(sizeof(xfs_inode_t), "xfs_inode",
- KM_ZONE_HWALIGN | KM_ZONE_RECLAIM | KM_ZONE_SPREAD |
- KM_ZONE_ACCOUNT, xfs_fs_inode_init_once);
+ xfs_inode_zone = kmem_cache_create("xfs_inode",
+ sizeof(struct xfs_inode), 0,
+ (SLAB_HWCACHE_ALIGN |
+ SLAB_RECLAIM_ACCOUNT |
+ SLAB_MEM_SPREAD | SLAB_ACCOUNT),
+ xfs_fs_inode_init_once);
if (!xfs_inode_zone)
goto out_destroy_efi_zone;
- xfs_ili_zone =
- kmem_zone_init_flags(sizeof(xfs_inode_log_item_t), "xfs_ili",
- KM_ZONE_SPREAD, NULL);
+ xfs_ili_zone = kmem_cache_create("xfs_ili",
+ sizeof(struct xfs_inode_log_item), 0,
+ SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD,
+ NULL);
if (!xfs_ili_zone)
goto out_destroy_inode_zone;
- xfs_icreate_zone = kmem_zone_init(sizeof(struct xfs_icreate_item),
- "xfs_icr");
+
+ xfs_icreate_zone = kmem_cache_create("xfs_icr",
+ sizeof(struct xfs_icreate_item),
+ 0, 0, NULL);
if (!xfs_icreate_zone)
goto out_destroy_ili_zone;
- xfs_rud_zone = kmem_zone_init(sizeof(struct xfs_rud_log_item),
- "xfs_rud_item");
+ xfs_rud_zone = kmem_cache_create("xfs_rud_item",
+ sizeof(struct xfs_rud_log_item),
+ 0, 0, NULL);
if (!xfs_rud_zone)
goto out_destroy_icreate_zone;
- xfs_rui_zone = kmem_zone_init(
+ xfs_rui_zone = kmem_cache_create("xfs_rui_item",
xfs_rui_log_item_sizeof(XFS_RUI_MAX_FAST_EXTENTS),
- "xfs_rui_item");
+ 0, 0, NULL);
if (!xfs_rui_zone)
goto out_destroy_rud_zone;
- xfs_cud_zone = kmem_zone_init(sizeof(struct xfs_cud_log_item),
- "xfs_cud_item");
+ xfs_cud_zone = kmem_cache_create("xfs_cud_item",
+ sizeof(struct xfs_cud_log_item),
+ 0, 0, NULL);
if (!xfs_cud_zone)
goto out_destroy_rui_zone;
- xfs_cui_zone = kmem_zone_init(
+ xfs_cui_zone = kmem_cache_create("xfs_cui_item",
xfs_cui_log_item_sizeof(XFS_CUI_MAX_FAST_EXTENTS),
- "xfs_cui_item");
+ 0, 0, NULL);
if (!xfs_cui_zone)
goto out_destroy_cud_zone;
- xfs_bud_zone = kmem_zone_init(sizeof(struct xfs_bud_log_item),
- "xfs_bud_item");
+ xfs_bud_zone = kmem_cache_create("xfs_bud_item",
+ sizeof(struct xfs_bud_log_item),
+ 0, 0, NULL);
if (!xfs_bud_zone)
goto out_destroy_cui_zone;
- xfs_bui_zone = kmem_zone_init(
+ xfs_bui_zone = kmem_cache_create("xfs_bui_item",
xfs_bui_log_item_sizeof(XFS_BUI_MAX_FAST_EXTENTS),
- "xfs_bui_item");
+ 0, 0, NULL);
if (!xfs_bui_zone)
goto out_destroy_bud_zone;
return 0;
out_destroy_bud_zone:
- kmem_zone_destroy(xfs_bud_zone);
+ kmem_cache_destroy(xfs_bud_zone);
out_destroy_cui_zone:
- kmem_zone_destroy(xfs_cui_zone);
+ kmem_cache_destroy(xfs_cui_zone);
out_destroy_cud_zone:
- kmem_zone_destroy(xfs_cud_zone);
+ kmem_cache_destroy(xfs_cud_zone);
out_destroy_rui_zone:
- kmem_zone_destroy(xfs_rui_zone);
+ kmem_cache_destroy(xfs_rui_zone);
out_destroy_rud_zone:
- kmem_zone_destroy(xfs_rud_zone);
+ kmem_cache_destroy(xfs_rud_zone);
out_destroy_icreate_zone:
- kmem_zone_destroy(xfs_icreate_zone);
+ kmem_cache_destroy(xfs_icreate_zone);
out_destroy_ili_zone:
- kmem_zone_destroy(xfs_ili_zone);
+ kmem_cache_destroy(xfs_ili_zone);
out_destroy_inode_zone:
- kmem_zone_destroy(xfs_inode_zone);
+ kmem_cache_destroy(xfs_inode_zone);
out_destroy_efi_zone:
- kmem_zone_destroy(xfs_efi_zone);
+ kmem_cache_destroy(xfs_efi_zone);
out_destroy_efd_zone:
- kmem_zone_destroy(xfs_efd_zone);
+ kmem_cache_destroy(xfs_efd_zone);
out_destroy_buf_item_zone:
- kmem_zone_destroy(xfs_buf_item_zone);
+ kmem_cache_destroy(xfs_buf_item_zone);
out_destroy_trans_zone:
- kmem_zone_destroy(xfs_trans_zone);
+ kmem_cache_destroy(xfs_trans_zone);
out_destroy_ifork_zone:
- kmem_zone_destroy(xfs_ifork_zone);
+ kmem_cache_destroy(xfs_ifork_zone);
out_destroy_da_state_zone:
- kmem_zone_destroy(xfs_da_state_zone);
+ kmem_cache_destroy(xfs_da_state_zone);
out_destroy_btree_cur_zone:
- kmem_zone_destroy(xfs_btree_cur_zone);
+ kmem_cache_destroy(xfs_btree_cur_zone);
out_destroy_bmap_free_item_zone:
- kmem_zone_destroy(xfs_bmap_free_item_zone);
+ kmem_cache_destroy(xfs_bmap_free_item_zone);
out_destroy_log_ticket_zone:
- kmem_zone_destroy(xfs_log_ticket_zone);
- out_free_ioend_bioset:
- bioset_exit(&xfs_ioend_bioset);
+ kmem_cache_destroy(xfs_log_ticket_zone);
out:
return -ENOMEM;
}
@@ -1998,25 +2081,24 @@
* destroy caches.
*/
rcu_barrier();
- kmem_zone_destroy(xfs_bui_zone);
- kmem_zone_destroy(xfs_bud_zone);
- kmem_zone_destroy(xfs_cui_zone);
- kmem_zone_destroy(xfs_cud_zone);
- kmem_zone_destroy(xfs_rui_zone);
- kmem_zone_destroy(xfs_rud_zone);
- kmem_zone_destroy(xfs_icreate_zone);
- kmem_zone_destroy(xfs_ili_zone);
- kmem_zone_destroy(xfs_inode_zone);
- kmem_zone_destroy(xfs_efi_zone);
- kmem_zone_destroy(xfs_efd_zone);
- kmem_zone_destroy(xfs_buf_item_zone);
- kmem_zone_destroy(xfs_trans_zone);
- kmem_zone_destroy(xfs_ifork_zone);
- kmem_zone_destroy(xfs_da_state_zone);
- kmem_zone_destroy(xfs_btree_cur_zone);
- kmem_zone_destroy(xfs_bmap_free_item_zone);
- kmem_zone_destroy(xfs_log_ticket_zone);
- bioset_exit(&xfs_ioend_bioset);
+ kmem_cache_destroy(xfs_bui_zone);
+ kmem_cache_destroy(xfs_bud_zone);
+ kmem_cache_destroy(xfs_cui_zone);
+ kmem_cache_destroy(xfs_cud_zone);
+ kmem_cache_destroy(xfs_rui_zone);
+ kmem_cache_destroy(xfs_rud_zone);
+ kmem_cache_destroy(xfs_icreate_zone);
+ kmem_cache_destroy(xfs_ili_zone);
+ kmem_cache_destroy(xfs_inode_zone);
+ kmem_cache_destroy(xfs_efi_zone);
+ kmem_cache_destroy(xfs_efd_zone);
+ kmem_cache_destroy(xfs_buf_item_zone);
+ kmem_cache_destroy(xfs_trans_zone);
+ kmem_cache_destroy(xfs_ifork_zone);
+ kmem_cache_destroy(xfs_da_state_zone);
+ kmem_cache_destroy(xfs_btree_cur_zone);
+ kmem_cache_destroy(xfs_bmap_free_item_zone);
+ kmem_cache_destroy(xfs_log_ticket_zone);
}
STATIC int __init
@@ -2059,11 +2141,6 @@
printk(KERN_INFO XFS_VERSION_STRING " with "
XFS_BUILD_OPTIONS " enabled\n");
-
- xfs_extent_free_init_defer_op();
- xfs_rmap_update_init_defer_op();
- xfs_refcount_update_init_defer_op();
- xfs_bmap_update_init_defer_op();
xfs_dir_startup();
@@ -2180,3 +2257,4 @@
MODULE_AUTHOR("Silicon Graphics, Inc.");
MODULE_DESCRIPTION(XFS_VERSION_STRING " with " XFS_BUILD_OPTIONS " enabled");
MODULE_LICENSE("GPL");
+MODULE_IMPORT_NS(ANDROID_GKI_VFS_EXPORT_ONLY);
--
Gitblit v1.6.2