diff options
Diffstat (limited to 'fs/gfs2')
| -rw-r--r-- | fs/gfs2/Kconfig | 1 | ||||
| -rw-r--r-- | fs/gfs2/Makefile | 5 | ||||
| -rw-r--r-- | fs/gfs2/aops.c (renamed from fs/gfs2/ops_address.c) | 21 | ||||
| -rw-r--r-- | fs/gfs2/bmap.c | 15 | ||||
| -rw-r--r-- | fs/gfs2/dentry.c (renamed from fs/gfs2/ops_dentry.c) | 0 | ||||
| -rw-r--r-- | fs/gfs2/dir.c | 11 | ||||
| -rw-r--r-- | fs/gfs2/eattr.c | 14 | ||||
| -rw-r--r-- | fs/gfs2/export.c (renamed from fs/gfs2/ops_export.c) | 0 | ||||
| -rw-r--r-- | fs/gfs2/file.c (renamed from fs/gfs2/ops_file.c) | 36 | ||||
| -rw-r--r-- | fs/gfs2/glock.c | 33 | ||||
| -rw-r--r-- | fs/gfs2/glops.c | 20 | ||||
| -rw-r--r-- | fs/gfs2/incore.h | 27 | ||||
| -rw-r--r-- | fs/gfs2/inode.c | 150 | ||||
| -rw-r--r-- | fs/gfs2/inode.h | 52 | ||||
| -rw-r--r-- | fs/gfs2/log.c | 17 | ||||
| -rw-r--r-- | fs/gfs2/lops.c | 17 | ||||
| -rw-r--r-- | fs/gfs2/main.c | 8 | ||||
| -rw-r--r-- | fs/gfs2/meta_io.c | 105 | ||||
| -rw-r--r-- | fs/gfs2/mount.c | 185 | ||||
| -rw-r--r-- | fs/gfs2/ops_address.h | 23 | ||||
| -rw-r--r-- | fs/gfs2/ops_fstype.c | 74 | ||||
| -rw-r--r-- | fs/gfs2/ops_inode.c | 146 | ||||
| -rw-r--r-- | fs/gfs2/ops_super.c | 723 | ||||
| -rw-r--r-- | fs/gfs2/quota.c | 1 | ||||
| -rw-r--r-- | fs/gfs2/recovery.c | 102 | ||||
| -rw-r--r-- | fs/gfs2/recovery.h | 2 | ||||
| -rw-r--r-- | fs/gfs2/rgrp.c | 152 | ||||
| -rw-r--r-- | fs/gfs2/rgrp.h | 47 | ||||
| -rw-r--r-- | fs/gfs2/super.c | 890 | ||||
| -rw-r--r-- | fs/gfs2/sys.c | 245 | ||||
| -rw-r--r-- | fs/gfs2/trace_gfs2.h | 407 | ||||
| -rw-r--r-- | fs/gfs2/trans.c | 9 |
32 files changed, 1953 insertions, 1585 deletions
diff --git a/fs/gfs2/Kconfig b/fs/gfs2/Kconfig index 3a981b7f64ca..cad957cdb1e5 100644 --- a/fs/gfs2/Kconfig +++ b/fs/gfs2/Kconfig @@ -7,6 +7,7 @@ config GFS2_FS select IP_SCTP if DLM_SCTP select FS_POSIX_ACL select CRC32 + select SLOW_WORK help A cluster filesystem. diff --git a/fs/gfs2/Makefile b/fs/gfs2/Makefile index a851ea4bdf70..3da2f1f4f738 100644 --- a/fs/gfs2/Makefile +++ b/fs/gfs2/Makefile @@ -1,8 +1,9 @@ +EXTRA_CFLAGS := -I$(src) obj-$(CONFIG_GFS2_FS) += gfs2.o gfs2-y := acl.o bmap.o dir.o eaops.o eattr.o glock.o \ glops.o inode.o log.o lops.o main.o meta_io.o \ - mount.o ops_address.o ops_dentry.o ops_export.o ops_file.o \ - ops_fstype.o ops_inode.o ops_super.o quota.o \ + aops.o dentry.o export.o file.o \ + ops_fstype.o ops_inode.o quota.o \ recovery.o rgrp.o super.o sys.o trans.o util.o gfs2-$(CONFIG_GFS2_FS_LOCKING_DLM) += lock_dlm.o diff --git a/fs/gfs2/ops_address.c b/fs/gfs2/aops.c index a6dde1751e17..03ebb439ace0 100644 --- a/fs/gfs2/ops_address.c +++ b/fs/gfs2/aops.c @@ -28,7 +28,6 @@ #include "inode.h" #include "log.h" #include "meta_io.h" -#include "ops_address.h" #include "quota.h" #include "trans.h" #include "rgrp.h" @@ -781,10 +780,12 @@ static int gfs2_stuffed_write_end(struct inode *inode, struct buffer_head *dibh, unlock_page(page); page_cache_release(page); - if (inode->i_size < to) { - i_size_write(inode, to); - ip->i_disksize = inode->i_size; - di->di_size = cpu_to_be64(inode->i_size); + if (copied) { + if (inode->i_size < to) { + i_size_write(inode, to); + ip->i_disksize = inode->i_size; + } + gfs2_dinode_out(ip, di); mark_inode_dirty(inode); } @@ -824,7 +825,6 @@ static int gfs2_write_end(struct file *file, struct address_space *mapping, struct gfs2_sbd *sdp = GFS2_SB(inode); struct buffer_head *dibh; struct gfs2_alloc *al = ip->i_alloc; - struct gfs2_dinode *di; unsigned int from = pos & (PAGE_CACHE_SIZE - 1); unsigned int to = from + len; int ret; @@ -847,11 +847,10 @@ static int gfs2_write_end(struct file *file, struct address_space *mapping, gfs2_page_add_databufs(ip, page, from, to); ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata); - - if (likely(ret >= 0) && (inode->i_size > ip->i_disksize)) { - di = (struct gfs2_dinode *)dibh->b_data; - ip->i_disksize = inode->i_size; - di->di_size = cpu_to_be64(inode->i_size); + if (ret > 0) { + if (inode->i_size > ip->i_disksize) + ip->i_disksize = inode->i_size; + gfs2_dinode_out(ip, dibh->b_data); mark_inode_dirty(inode); } diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 3a5d3f883e10..6d47379e794b 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -25,7 +25,7 @@ #include "trans.h" #include "dir.h" #include "util.h" -#include "ops_address.h" +#include "trace_gfs2.h" /* This doesn't need to be that large as max 64 bit pointers in a 4k * block is 512, so __u16 is fine for that. It saves stack space to @@ -136,7 +136,9 @@ int gfs2_unstuff_dinode(struct gfs2_inode *ip, struct page *page) and write it out to disk */ unsigned int n = 1; - block = gfs2_alloc_block(ip, &n); + error = gfs2_alloc_block(ip, &block, &n); + if (error) + goto out_brelse; if (isdir) { gfs2_trans_add_unrevoke(GFS2_SB(&ip->i_inode), block, 1); error = gfs2_dir_get_new_buffer(ip, block, &bh); @@ -476,8 +478,11 @@ static int gfs2_bmap_alloc(struct inode *inode, const sector_t lblock, blks = dblks + iblks; i = sheight; do { + int error; n = blks - alloced; - bn = gfs2_alloc_block(ip, &n); + error = gfs2_alloc_block(ip, &bn, &n); + if (error) + return error; alloced += n; if (state != ALLOC_DATA || gfs2_is_jdata(ip)) gfs2_trans_add_unrevoke(sdp, bn, n); @@ -585,6 +590,7 @@ int gfs2_block_map(struct inode *inode, sector_t lblock, clear_buffer_mapped(bh_map); clear_buffer_new(bh_map); clear_buffer_boundary(bh_map); + trace_gfs2_bmap(ip, bh_map, lblock, create, 1); if (gfs2_is_dir(ip)) { bsize = sdp->sd_jbsize; arr = sdp->sd_jheightsize; @@ -619,6 +625,7 @@ int gfs2_block_map(struct inode *inode, sector_t lblock, ret = 0; out: release_metapath(&mp); + trace_gfs2_bmap(ip, bh_map, lblock, create, ret); bmap_unlock(ip, create); return ret; @@ -1008,7 +1015,7 @@ static int gfs2_block_truncate_page(struct address_space *mapping) gfs2_trans_add_bh(ip->i_gl, bh, 0); zero_user(page, offset, length); - + mark_buffer_dirty(bh); unlock: unlock_page(page); page_cache_release(page); diff --git a/fs/gfs2/ops_dentry.c b/fs/gfs2/dentry.c index 022c66cd5606..022c66cd5606 100644 --- a/fs/gfs2/ops_dentry.c +++ b/fs/gfs2/dentry.c diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c index aef4d0c06748..297d7e5cebad 100644 --- a/fs/gfs2/dir.c +++ b/fs/gfs2/dir.c @@ -803,13 +803,20 @@ static struct gfs2_leaf *new_leaf(struct inode *inode, struct buffer_head **pbh, { struct gfs2_inode *ip = GFS2_I(inode); unsigned int n = 1; - u64 bn = gfs2_alloc_block(ip, &n); - struct buffer_head *bh = gfs2_meta_new(ip->i_gl, bn); + u64 bn; + int error; + struct buffer_head *bh; struct gfs2_leaf *leaf; struct gfs2_dirent *dent; struct qstr name = { .name = "", .len = 0, .hash = 0 }; + + error = gfs2_alloc_block(ip, &bn, &n); + if (error) + return NULL; + bh = gfs2_meta_new(ip->i_gl, bn); if (!bh) return NULL; + gfs2_trans_add_unrevoke(GFS2_SB(inode), bn, 1); gfs2_trans_add_bh(ip->i_gl, bh, 1); gfs2_metatype_set(bh, GFS2_METATYPE_LF, GFS2_FORMAT_LF); diff --git a/fs/gfs2/eattr.c b/fs/gfs2/eattr.c index 899763aed217..07ea9529adda 100644 --- a/fs/gfs2/eattr.c +++ b/fs/gfs2/eattr.c @@ -582,8 +582,11 @@ static int ea_alloc_blk(struct gfs2_inode *ip, struct buffer_head **bhp) struct gfs2_ea_header *ea; unsigned int n = 1; u64 block; + int error; - block = gfs2_alloc_block(ip, &n); + error = gfs2_alloc_block(ip, &block, &n); + if (error) + return error; gfs2_trans_add_unrevoke(sdp, block, 1); *bhp = gfs2_meta_new(ip->i_gl, block); gfs2_trans_add_bh(ip->i_gl, *bhp, 1); @@ -617,6 +620,7 @@ static int ea_write(struct gfs2_inode *ip, struct gfs2_ea_header *ea, struct gfs2_ea_request *er) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); + int error; ea->ea_data_len = cpu_to_be32(er->er_data_len); ea->ea_name_len = er->er_name_len; @@ -642,7 +646,9 @@ static int ea_write(struct gfs2_inode *ip, struct gfs2_ea_header *ea, int mh_size = sizeof(struct gfs2_meta_header); unsigned int n = 1; - block = gfs2_alloc_block(ip, &n); + error = gfs2_alloc_block(ip, &block, &n); + if (error) + return error; gfs2_trans_add_unrevoke(sdp, block, 1); bh = gfs2_meta_new(ip->i_gl, block); gfs2_trans_add_bh(ip->i_gl, bh, 1); @@ -963,7 +969,9 @@ static int ea_set_block(struct gfs2_inode *ip, struct gfs2_ea_request *er, } else { u64 blk; unsigned int n = 1; - blk = gfs2_alloc_block(ip, &n); + error = gfs2_alloc_block(ip, &blk, &n); + if (error) + return error; gfs2_trans_add_unrevoke(sdp, blk, 1); indbh = gfs2_meta_new(ip->i_gl, blk); gfs2_trans_add_bh(ip->i_gl, indbh, 1); diff --git a/fs/gfs2/ops_export.c b/fs/gfs2/export.c index 9200ef221716..9200ef221716 100644 --- a/fs/gfs2/ops_export.c +++ b/fs/gfs2/export.c diff --git a/fs/gfs2/ops_file.c b/fs/gfs2/file.c index 5d82e91887e3..73318a3ce6f1 100644 --- a/fs/gfs2/ops_file.c +++ b/fs/gfs2/file.c @@ -39,7 +39,6 @@ #include "trans.h" #include "util.h" #include "eaops.h" -#include "ops_address.h" /** * gfs2_llseek - seek to a location in a file @@ -425,33 +424,36 @@ static struct vm_operations_struct gfs2_vm_ops = { .page_mkwrite = gfs2_page_mkwrite, }; - /** * gfs2_mmap - * @file: The file to map * @vma: The VMA which described the mapping * - * Returns: 0 or error code + * There is no need to get a lock here unless we should be updating + * atime. We ignore any locking errors since the only consequence is + * a missed atime update (which will just be deferred until later). + * + * Returns: 0 */ static int gfs2_mmap(struct file *file, struct vm_area_struct *vma) { struct gfs2_inode *ip = GFS2_I(file->f_mapping->host); - struct gfs2_holder i_gh; - int error; - gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &i_gh); - error = gfs2_glock_nq(&i_gh); - if (error) { - gfs2_holder_uninit(&i_gh); - return error; - } + if (!(file->f_flags & O_NOATIME)) { + struct gfs2_holder i_gh; + int error; + gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &i_gh); + error = gfs2_glock_nq(&i_gh); + file_accessed(file); + if (error == 0) + gfs2_glock_dq_uninit(&i_gh); + } vma->vm_ops = &gfs2_vm_ops; + vma->vm_flags |= VM_CAN_NONLINEAR; - gfs2_glock_dq_uninit(&i_gh); - - return error; + return 0; } /** @@ -692,12 +694,10 @@ static void do_unflock(struct file *file, struct file_lock *fl) static int gfs2_flock(struct file *file, int cmd, struct file_lock *fl) { - struct gfs2_inode *ip = GFS2_I(file->f_mapping->host); - if (!(fl->fl_flags & FL_FLOCK)) return -ENOLCK; - if (__mandatory_lock(&ip->i_inode)) - return -ENOLCK; + if (fl->fl_type & LOCK_MAND) + return -EOPNOTSUPP; if (fl->fl_type == F_UNLCK) { do_unflock(file, fl); diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index ff4981090489..297421c0427a 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -39,6 +39,8 @@ #include "super.h" #include "util.h" #include "bmap.h" +#define CREATE_TRACE_POINTS +#include "trace_gfs2.h" struct gfs2_gl_hash_bucket { struct hlist_head hb_list; @@ -155,7 +157,7 @@ static void glock_free(struct gfs2_glock *gl) if (aspace) gfs2_aspace_put(aspace); - + trace_gfs2_glock_put(gl); sdp->sd_lockstruct.ls_ops->lm_put_lock(gfs2_glock_cachep, gl); } @@ -317,14 +319,17 @@ restart: return 2; gh->gh_error = ret; list_del_init(&gh->gh_list); + trace_gfs2_glock_queue(gh, 0); gfs2_holder_wake(gh); goto restart; } set_bit(HIF_HOLDER, &gh->gh_iflags); + trace_gfs2_promote(gh, 1); gfs2_holder_wake(gh); goto restart; } set_bit(HIF_HOLDER, &gh->gh_iflags); + trace_gfs2_promote(gh, 0); gfs2_holder_wake(gh); continue; } @@ -354,6 +359,7 @@ static inline void do_error(struct gfs2_glock *gl, const int ret) else continue; list_del_init(&gh->gh_list); + trace_gfs2_glock_queue(gh, 0); gfs2_holder_wake(gh); } } @@ -422,6 +428,7 @@ static void finish_xmote(struct gfs2_glock *gl, unsigned int ret) int rv; spin_lock(&gl->gl_spin); + trace_gfs2_glock_state_change(gl, state); state_change(gl, state); gh = find_first_waiter(gl); @@ -796,22 +803,37 @@ void gfs2_holder_uninit(struct gfs2_holder *gh) gh->gh_ip = 0; } -static int just_schedule(void *word) +/** + * gfs2_glock_holder_wait + * @word: unused + * + * This function and gfs2_glock_demote_wait both show up in the WCHAN + * field. Thus I've separated these otherwise identical functions in + * order to be more informative to the user. + */ + +static int gfs2_glock_holder_wait(void *word) { schedule(); return 0; } +static int gfs2_glock_demote_wait(void *word) +{ + schedule(); + return 0; +} + static void wait_on_holder(struct gfs2_holder *gh) { might_sleep(); - wait_on_bit(&gh->gh_iflags, HIF_WAIT, just_schedule, TASK_UNINTERRUPTIBLE); + wait_on_bit(&gh->gh_iflags, HIF_WAIT, gfs2_glock_holder_wait, TASK_UNINTERRUPTIBLE); } static void wait_on_demote(struct gfs2_glock *gl) { might_sleep(); - wait_on_bit(&gl->gl_flags, GLF_DEMOTE, just_schedule, TASK_UNINTERRUPTIBLE); + wait_on_bit(&gl->gl_flags, GLF_DEMOTE, gfs2_glock_demote_wait, TASK_UNINTERRUPTIBLE); } /** @@ -836,6 +858,7 @@ static void handle_callback(struct gfs2_glock *gl, unsigned int state, gl->gl_demote_state != state) { gl->gl_demote_state = LM_ST_UNLOCKED; } + trace_gfs2_demote_rq(gl); } /** @@ -921,6 +944,7 @@ fail: goto do_cancel; return; } + trace_gfs2_glock_queue(gh, 1); list_add_tail(&gh->gh_list, insert_pt); do_cancel: gh = list_entry(gl->gl_holders.next, struct gfs2_holder, gh_list); @@ -1017,6 +1041,7 @@ void gfs2_glock_dq(struct gfs2_holder *gh) !test_bit(GLF_DEMOTE, &gl->gl_flags)) fast_path = 1; } + trace_gfs2_glock_queue(gh, 0); spin_unlock(&gl->gl_spin); if (likely(fast_path)) return; diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index 70f87f43afa2..d5e4ab155ca0 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -310,24 +310,6 @@ static void rgrp_go_unlock(struct gfs2_holder *gh) } /** - * rgrp_go_dump - print out an rgrp - * @seq: The iterator - * @gl: The glock in question - * - */ - -static int rgrp_go_dump(struct seq_file *seq, const struct gfs2_glock *gl) -{ - const struct gfs2_rgrpd *rgd = gl->gl_object; - if (rgd == NULL) - return 0; - gfs2_print_dbg(seq, " R: n:%llu f:%02x b:%u/%u i:%u\n", - (unsigned long long)rgd->rd_addr, rgd->rd_flags, - rgd->rd_free, rgd->rd_free_clone, rgd->rd_dinodes); - return 0; -} - -/** * trans_go_sync - promote/demote the transaction glock * @gl: the glock * @state: the requested state @@ -410,7 +392,7 @@ const struct gfs2_glock_operations gfs2_rgrp_glops = { .go_demote_ok = rgrp_go_demote_ok, .go_lock = rgrp_go_lock, .go_unlock = rgrp_go_unlock, - .go_dump = rgrp_go_dump, + .go_dump = gfs2_rgrp_dump, .go_type = LM_TYPE_RGRP, .go_min_hold_time = HZ / 5, }; diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h index 399d1b978049..225347fbff3c 100644 --- a/fs/gfs2/incore.h +++ b/fs/gfs2/incore.h @@ -12,6 +12,7 @@ #include <linux/fs.h> #include <linux/workqueue.h> +#include <linux/slow-work.h> #include <linux/dlm.h> #include <linux/buffer_head.h> @@ -63,9 +64,12 @@ struct gfs2_log_element { const struct gfs2_log_operations *le_ops; }; +#define GBF_FULL 1 + struct gfs2_bitmap { struct buffer_head *bi_bh; char *bi_clone; + unsigned long bi_flags; u32 bi_offset; u32 bi_start; u32 bi_len; @@ -90,10 +94,11 @@ struct gfs2_rgrpd { struct gfs2_sbd *rd_sbd; unsigned int rd_bh_count; u32 rd_last_alloc; - unsigned char rd_flags; -#define GFS2_RDF_CHECK 0x01 /* Need to check for unlinked inodes */ -#define GFS2_RDF_NOALLOC 0x02 /* rg prohibits allocation */ -#define GFS2_RDF_UPTODATE 0x04 /* rg is up to date */ + u32 rd_flags; +#define GFS2_RDF_CHECK 0x10000000 /* check for unlinked inodes */ +#define GFS2_RDF_UPTODATE 0x20000000 /* rg is up to date */ +#define GFS2_RDF_ERROR 0x40000000 /* error in rg */ +#define GFS2_RDF_MASK 0xf0000000 /* mask for internal flags */ }; enum gfs2_state_bits { @@ -376,11 +381,11 @@ struct gfs2_journal_extent { struct gfs2_jdesc { struct list_head jd_list; struct list_head extent_list; - + struct slow_work jd_work; struct inode *jd_inode; + unsigned long jd_flags; +#define JDF_RECOVERY 1 unsigned int jd_jid; - int jd_dirty; - unsigned int jd_blocks; }; @@ -390,9 +395,6 @@ struct gfs2_statfs_change_host { s64 sc_dinodes; }; -#define GFS2_GLOCKD_DEFAULT 1 -#define GFS2_GLOCKD_MAX 16 - #define GFS2_QUOTA_DEFAULT GFS2_QUOTA_OFF #define GFS2_QUOTA_OFF 0 #define GFS2_QUOTA_ACCOUNT 1 @@ -418,6 +420,7 @@ struct gfs2_args { unsigned int ar_data:2; /* ordered/writeback */ unsigned int ar_meta:1; /* mount metafs */ unsigned int ar_discard:1; /* discard requests */ + int ar_commit; /* Commit interval */ }; struct gfs2_tune { @@ -426,7 +429,6 @@ struct gfs2_tune { unsigned int gt_incore_log_blocks; unsigned int gt_log_flush_secs; - unsigned int gt_recoverd_secs; unsigned int gt_logd_secs; unsigned int gt_quota_simul_sync; /* Max quotavals to sync at once */ @@ -447,6 +449,7 @@ enum { SDF_JOURNAL_LIVE = 1, SDF_SHUTDOWN = 2, SDF_NOBARRIERS = 3, + SDF_NORECOVERY = 4, }; #define GFS2_FSNAME_LEN 256 @@ -493,7 +496,6 @@ struct lm_lockstruct { unsigned long ls_flags; dlm_lockspace_t *ls_dlm; - int ls_recover_jid; int ls_recover_jid_done; int ls_recover_jid_status; }; @@ -582,7 +584,6 @@ struct gfs2_sbd { /* Daemon stuff */ - struct task_struct *sd_recoverd_process; struct task_struct *sd_logd_process; struct task_struct *sd_quotad_process; diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 5a31d426116f..2f94bd723698 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -30,7 +30,6 @@ #include "inode.h" #include "log.h" #include "meta_io.h" -#include "ops_address.h" #include "quota.h" #include "rgrp.h" #include "trans.h" @@ -1047,154 +1046,7 @@ fail: return ERR_PTR(error); } -/** - * gfs2_rmdiri - Remove a directory - * @dip: The parent directory of the directory to be removed - * @name: The name of the directory to be removed - * @ip: The GFS2 inode of the directory to be removed - * - * Assumes Glocks on dip and ip are held - * - * Returns: errno - */ - -int gfs2_rmdiri(struct gfs2_inode *dip, const struct qstr *name, - struct gfs2_inode *ip) -{ - struct qstr dotname; - int error; - - if (ip->i_entries != 2) { - if (gfs2_consist_inode(ip)) - gfs2_dinode_print(ip); - return -EIO; - } - - error = gfs2_dir_del(dip, name); - if (error) - return error; - - error = gfs2_change_nlink(dip, -1); - if (error) - return error; - - gfs2_str2qstr(&dotname, "."); - error = gfs2_dir_del(ip, &dotname); - if (error) - return error; - - gfs2_str2qstr(&dotname, ".."); - error = gfs2_dir_del(ip, &dotname); - if (error) - return error; - - /* It looks odd, but it really should be done twice */ - error = gfs2_change_nlink(ip, -1); - if (error) - return error; - - error = gfs2_change_nlink(ip, -1); - if (error) - return error; - - return error; -} - -/* - * gfs2_unlink_ok - check to see that a inode is still in a directory - * @dip: the directory - * @name: the name of the file - * @ip: the inode - * - * Assumes that the lock on (at least) @dip is held. - * - * Returns: 0 if the parent/child relationship is correct, errno if it isn't - */ - -int gfs2_unlink_ok(struct gfs2_inode *dip, const struct qstr *name, - const struct gfs2_inode *ip) -{ - int error; - - if (IS_IMMUTABLE(&ip->i_inode) || IS_APPEND(&ip->i_inode)) - return -EPERM; - - if ((dip->i_inode.i_mode & S_ISVTX) && - dip->i_inode.i_uid != current_fsuid() && - ip->i_inode.i_uid != current_fsuid() && !capable(CAP_FOWNER)) - return -EPERM; - - if (IS_APPEND(&dip->i_inode)) - return -EPERM; - - error = gfs2_permission(&dip->i_inode, MAY_WRITE | MAY_EXEC); - if (error) - return error; - - error = gfs2_dir_check(&dip->i_inode, name, ip); - if (error) - return error; - - return 0; -} - -/** - * gfs2_readlinki - return the contents of a symlink - * @ip: the symlink's inode - * @buf: a pointer to the buffer to be filled - * @len: a pointer to the length of @buf - * - * If @buf is too small, a piece of memory is kmalloc()ed and needs - * to be freed by the caller. - * - * Returns: errno - */ - -int gfs2_readlinki(struct gfs2_inode *ip, char **buf, unsigned int *len) -{ - struct gfs2_holder i_gh; - struct buffer_head *dibh; - unsigned int x; - int error; - - gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &i_gh); - error = gfs2_glock_nq(&i_gh); - if (error) { - gfs2_holder_uninit(&i_gh); - return error; - } - - if (!ip->i_disksize) { - gfs2_consist_inode(ip); - error = -EIO; - goto out; - } - - error = gfs2_meta_inode_buffer(ip, &dibh); - if (error) - goto out; - - x = ip->i_disksize + 1; - if (x > *len) { - *buf = kmalloc(x, GFP_NOFS); - if (!*buf) { - error = -ENOMEM; - goto out_brelse; - } - } - - memcpy(*buf, dibh->b_data + sizeof(struct gfs2_dinode), x); - *len = x; - -out_brelse: - brelse(dibh); -out: - gfs2_glock_dq_uninit(&i_gh); - return error; -} - -static int -__gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr) +static int __gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr) { struct buffer_head *dibh; int error; diff --git a/fs/gfs2/inode.h b/fs/gfs2/inode.h index c30be2b66580..c341aaf67adb 100644 --- a/fs/gfs2/inode.h +++ b/fs/gfs2/inode.h @@ -11,8 +11,16 @@ #define __INODE_DOT_H__ #include <linux/fs.h> +#include <linux/buffer_head.h> +#include <linux/mm.h> #include "util.h" +extern int gfs2_releasepage(struct page *page, gfp_t gfp_mask); +extern int gfs2_internal_read(struct gfs2_inode *ip, + struct file_ra_state *ra_state, + char *buf, loff_t *pos, unsigned size); +extern void gfs2_set_aops(struct inode *inode); + static inline int gfs2_is_stuffed(const struct gfs2_inode *ip) { return !ip->i_height; @@ -73,30 +81,26 @@ static inline void gfs2_inum_out(const struct gfs2_inode *ip, } -void gfs2_set_iop(struct inode *inode); -struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned type, - u64 no_addr, u64 no_formal_ino, - int skip_freeing); -struct inode *gfs2_ilookup(struct super_block *sb, u64 no_addr); - -int gfs2_inode_refresh(struct gfs2_inode *ip); - -int gfs2_dinode_dealloc(struct gfs2_inode *inode); -int gfs2_change_nlink(struct gfs2_inode *ip, int diff); -struct inode *gfs2_lookupi(struct inode *dir, const struct qstr *name, - int is_root); -struct inode *gfs2_createi(struct gfs2_holder *ghs, const struct qstr *name, - unsigned int mode, dev_t dev); -int gfs2_rmdiri(struct gfs2_inode *dip, const struct qstr *name, - struct gfs2_inode *ip); -int gfs2_unlink_ok(struct gfs2_inode *dip, const struct qstr *name, - const struct gfs2_inode *ip); -int gfs2_permission(struct inode *inode, int mask); -int gfs2_readlinki(struct gfs2_inode *ip, char **buf, unsigned int *len); -int gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr); -struct inode *gfs2_lookup_simple(struct inode *dip, const char *name); -void gfs2_dinode_out(const struct gfs2_inode *ip, void *buf); -void gfs2_dinode_print(const struct gfs2_inode *ip); +extern void gfs2_set_iop(struct inode *inode); +extern struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned type, + u64 no_addr, u64 no_formal_ino, + int skip_freeing); +extern struct inode *gfs2_ilookup(struct super_block *sb, u64 no_addr); + +extern int gfs2_inode_refresh(struct gfs2_inode *ip); + +extern int gfs2_dinode_dealloc(struct gfs2_inode *inode); +extern int gfs2_change_nlink(struct gfs2_inode *ip, int diff); +extern struct inode *gfs2_lookupi(struct inode *dir, const struct qstr *name, + int is_root); +extern struct inode *gfs2_createi(struct gfs2_holder *ghs, + const struct qstr *name, + unsigned int mode, dev_t dev); +extern int gfs2_permission(struct inode *inode, int mask); +extern int gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr); +extern struct inode *gfs2_lookup_simple(struct inode *dip, const char *name); +extern void gfs2_dinode_out(const struct gfs2_inode *ip, void *buf); +extern void gfs2_dinode_print(const struct gfs2_inode *ip); extern const struct inode_operations gfs2_file_iops; extern const struct inode_operations gfs2_dir_iops; diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 98918a756410..13c6237c5f67 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -28,6 +28,7 @@ #include "meta_io.h" #include "util.h" #include "dir.h" +#include "trace_gfs2.h" #define PULL 1 @@ -120,7 +121,7 @@ __acquires(&sdp->sd_log_lock) lock_buffer(bh); if (test_clear_buffer_dirty(bh)) { bh->b_end_io = end_buffer_write_sync; - submit_bh(WRITE, bh); + submit_bh(WRITE_SYNC_PLUG, bh); } else { unlock_buffer(bh); brelse(bh); @@ -313,6 +314,7 @@ int gfs2_log_reserve(struct gfs2_sbd *sdp, unsigned int blks) gfs2_log_lock(sdp); } atomic_sub(blks, &sdp->sd_log_blks_free); + trace_gfs2_log_blocks(sdp, -blks); gfs2_log_unlock(sdp); mutex_unlock(&sdp->sd_log_reserve_mutex); @@ -333,6 +335,7 @@ void gfs2_log_release(struct gfs2_sbd *sdp, unsigned int blks) gfs2_log_lock(sdp); atomic_add(blks, &sdp->sd_log_blks_free); + trace_gfs2_log_blocks(sdp, blks); gfs2_assert_withdraw(sdp, atomic_read(&sdp->sd_log_blks_free) <= sdp->sd_jdesc->jd_blocks); gfs2_log_unlock(sdp); @@ -558,6 +561,7 @@ static void log_pull_tail(struct gfs2_sbd *sdp, unsigned int new_tail) gfs2_log_lock(sdp); atomic_add(dist, &sdp->sd_log_blks_free); + trace_gfs2_log_blocks(sdp, dist); gfs2_assert_withdraw(sdp, atomic_read(&sdp->sd_log_blks_free) <= sdp->sd_jdesc->jd_blocks); gfs2_log_unlock(sdp); @@ -604,7 +608,7 @@ static void log_write_header(struct gfs2_sbd *sdp, u32 flags, int pull) if (test_bit(SDF_NOBARRIERS, &sdp->sd_flags)) goto skip_barrier; get_bh(bh); - submit_bh(WRITE_BARRIER | (1 << BIO_RW_META), bh); + submit_bh(WRITE_SYNC | (1 << BIO_RW_BARRIER) | (1 << BIO_RW_META), bh); wait_on_buffer(bh); if (buffer_eopnotsupp(bh)) { clear_buffer_eopnotsupp(bh); @@ -664,7 +668,7 @@ static void gfs2_ordered_write(struct gfs2_sbd *sdp) lock_buffer(bh); if (buffer_mapped(bh) && test_clear_buffer_dirty(bh)) { bh->b_end_io = end_buffer_write_sync; - submit_bh(WRITE, bh); + submit_bh(WRITE_SYNC_PLUG, bh); } else { unlock_buffer(bh); brelse(bh); @@ -715,6 +719,7 @@ void __gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl) up_write(&sdp->sd_log_flush_lock); return; } + trace_gfs2_log_flush(sdp, 1); ai = kzalloc(sizeof(struct gfs2_ail), GFP_NOFS | __GFP_NOFAIL); INIT_LIST_HEAD(&ai->ai_ail1_list); @@ -746,6 +751,7 @@ void __gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl) else if (sdp->sd_log_tail != current_tail(sdp) && !sdp->sd_log_idle){ gfs2_log_lock(sdp); atomic_dec(&sdp->sd_log_blks_free); /* Adjust for unreserved buffer */ + trace_gfs2_log_blocks(sdp, -1); gfs2_log_unlock(sdp); log_write_header(sdp, 0, PULL); } @@ -763,8 +769,7 @@ void __gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl) ai = NULL; } gfs2_log_unlock(sdp); - - sdp->sd_vfs->s_dirt = 0; + trace_gfs2_log_flush(sdp, 0); up_write(&sdp->sd_log_flush_lock); kfree(ai); @@ -788,6 +793,7 @@ static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr) gfs2_assert_withdraw(sdp, sdp->sd_log_blks_reserved + tr->tr_reserved >= reserved); unused = sdp->sd_log_blks_reserved - reserved + tr->tr_reserved; atomic_add(unused, &sdp->sd_log_blks_free); + trace_gfs2_log_blocks(sdp, unused); gfs2_assert_withdraw(sdp, atomic_read(&sdp->sd_log_blks_free) <= sdp->sd_jdesc->jd_blocks); sdp->sd_log_blks_reserved = reserved; @@ -823,7 +829,6 @@ void gfs2_log_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr) log_refund(sdp, tr); buf_lo_incore_commit(sdp, tr); - sdp->sd_vfs->s_dirt = 1; up_read(&sdp->sd_log_flush_lock); gfs2_log_lock(sdp); diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index 80e4f5f898bb..9969ff062c5b 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -13,6 +13,8 @@ #include <linux/completion.h> #include <linux/buffer_head.h> #include <linux/gfs2_ondisk.h> +#include <linux/bio.h> +#include <linux/fs.h> #include "gfs2.h" #include "incore.h" @@ -25,6 +27,7 @@ #include "rgrp.h" #include "trans.h" #include "util.h" +#include "trace_gfs2.h" /** * gfs2_pin - Pin a buffer in memory @@ -51,6 +54,7 @@ static void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh) if (bd->bd_ail) list_move(&bd->bd_ail_st_list, &bd->bd_ail->ai_ail2_list); get_bh(bh); + trace_gfs2_pin(bd, 1); } /** @@ -87,6 +91,7 @@ static void gfs2_unpin(struct gfs2_sbd *sdp, struct buffer_head *bh, bd->bd_ail = ai; list_add(&bd->bd_ail_st_list, &ai->ai_ail1_list); clear_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags); + trace_gfs2_pin(bd, 0); gfs2_log_unlock(sdp); unlock_buffer(bh); } @@ -189,7 +194,7 @@ static void buf_lo_before_commit(struct gfs2_sbd *sdp) } gfs2_log_unlock(sdp); - submit_bh(WRITE, bh); + submit_bh(WRITE_SYNC_PLUG, bh); gfs2_log_lock(sdp); n = 0; @@ -199,7 +204,7 @@ static void buf_lo_before_commit(struct gfs2_sbd *sdp) gfs2_log_unlock(sdp); lock_buffer(bd2->bd_bh); bh = gfs2_log_fake_buf(sdp, bd2->bd_bh); - submit_bh(WRITE, bh); + submit_bh(WRITE_SYNC_PLUG, bh); gfs2_log_lock(sdp); if (++n >= num) break; @@ -341,7 +346,7 @@ static void revoke_lo_before_commit(struct gfs2_sbd *sdp) sdp->sd_log_num_revoke--; if (offset + sizeof(u64) > sdp->sd_sb.sb_bsize) { - submit_bh(WRITE, bh); + submit_bh(WRITE_SYNC_PLUG, bh); bh = gfs2_log_get_buf(sdp); mh = (struct gfs2_meta_header *)bh->b_data; @@ -358,7 +363,7 @@ static void revoke_lo_before_commit(struct gfs2_sbd *sdp) } gfs2_assert_withdraw(sdp, !sdp->sd_log_num_revoke); - submit_bh(WRITE, bh); + submit_bh(WRITE_SYNC_PLUG, bh); } static void revoke_lo_before_scan(struct gfs2_jdesc *jd, @@ -560,7 +565,7 @@ static void gfs2_write_blocks(struct gfs2_sbd *sdp, struct buffer_head *bh, ptr = bh_log_ptr(bh); get_bh(bh); - submit_bh(WRITE, bh); + submit_bh(WRITE_SYNC_PLUG, bh); gfs2_log_lock(sdp); while(!list_empty(list)) { bd = list_entry(list->next, struct gfs2_bufdata, bd_le.le_list); @@ -586,7 +591,7 @@ static void gfs2_write_blocks(struct gfs2_sbd *sdp, struct buffer_head *bh, } else { bh1 = gfs2_log_fake_buf(sdp, bd->bd_bh); } - submit_bh(WRITE, bh1); + submit_bh(WRITE_SYNC_PLUG, bh1); gfs2_log_lock(sdp); ptr += 2; } diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c index a6892ed0840a..eacd78a5d082 100644 --- a/fs/gfs2/main.c +++ b/fs/gfs2/main.c @@ -15,6 +15,7 @@ #include <linux/init.h> #include <linux/gfs2_ondisk.h> #include <asm/atomic.h> +#include <linux/slow-work.h> #include "gfs2.h" #include "incore.h" @@ -113,12 +114,18 @@ static int __init init_gfs2_fs(void) if (error) goto fail_unregister; + error = slow_work_register_user(); + if (error) + goto fail_slow; + gfs2_register_debugfs(); printk("GFS2 (built %s %s) installed\n", __DATE__, __TIME__); return 0; +fail_slow: + unregister_filesystem(&gfs2meta_fs_type); fail_unregister: unregister_filesystem(&gfs2_fs_type); fail: @@ -156,6 +163,7 @@ static void __exit exit_gfs2_fs(void) gfs2_unregister_debugfs(); unregister_filesystem(&gfs2_fs_type); unregister_filesystem(&gfs2meta_fs_type); + slow_work_unregister_user(); kmem_cache_destroy(gfs2_quotad_cachep); kmem_cache_destroy(gfs2_rgrpd_cachep); diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index 8d6f13256b26..cb8d7a93d5ec 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -31,19 +31,66 @@ #include "rgrp.h" #include "trans.h" #include "util.h" -#include "ops_address.h" -static int aspace_get_block(struct inode *inode, sector_t lblock, - struct buffer_head *bh_result, int create) +static int gfs2_aspace_writepage(struct page *page, struct writeback_control *wbc) { - gfs2_assert_warn(inode->i_sb->s_fs_info, 0); - return -EOPNOTSUPP; -} + int err; + struct buffer_head *bh, *head; + int nr_underway = 0; + int write_op = (1 << BIO_RW_META) | ((wbc->sync_mode == WB_SYNC_ALL ? + WRITE_SYNC_PLUG : WRITE)); + + BUG_ON(!PageLocked(page)); + BUG_ON(!page_has_buffers(page)); + + head = page_buffers(page); + bh = head; + + do { + if (!buffer_mapped(bh)) + continue; + /* + * If it's a fully non-blocking write attempt and we cannot + * lock the buffer then redirty the page. Note that this can + * potentially cause a busy-wait loop from pdflush and kswapd + * activity, but those code paths have their own higher-level + * throttling. + */ + if (wbc->sync_mode != WB_SYNC_NONE || !wbc->nonblocking) { + lock_buffer(bh); + } else if (!trylock_buffer(bh)) { + redirty_page_for_writepage(wbc, page); + continue; + } + if (test_clear_buffer_dirty(bh)) { + mark_buffer_async_write(bh); + } else { + unlock_buffer(bh); + } + } while ((bh = bh->b_this_page) != head); + + /* + * The page and its buffers are protected by PageWriteback(), so we can + * drop the bh refcounts early. + */ + BUG_ON(PageWriteback(page)); + set_page_writeback(page); + + do { + struct buffer_head *next = bh->b_this_page; + if (buffer_async_write(bh)) { + submit_bh(write_op, bh); + nr_underway++; + } + bh = next; + } while (bh != head); + unlock_page(page); -static int gfs2_aspace_writepage(struct page *page, - struct writeback_control *wbc) -{ - return block_write_full_page(page, aspace_get_block, wbc); + err = 0; + if (nr_underway == 0) + end_page_writeback(page); + + return err; } static const struct address_space_operations aspace_aops = { @@ -201,16 +248,32 @@ struct buffer_head *gfs2_meta_new(struct gfs2_glock *gl, u64 blkno) int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags, struct buffer_head **bhp) { - *bhp = gfs2_getbuf(gl, blkno, CREATE); - if (!buffer_uptodate(*bhp)) { - ll_rw_block(READ_META, 1, bhp); - if (flags & DIO_WAIT) { - int error = gfs2_meta_wait(gl->gl_sbd, *bhp); - if (error) { - brelse(*bhp); - return error; - } - } + struct gfs2_sbd *sdp = gl->gl_sbd; + struct buffer_head *bh; + + if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) + return -EIO; + + *bhp = bh = gfs2_getbuf(gl, blkno, CREATE); + + lock_buffer(bh); + if (buffer_uptodate(bh)) { + unlock_buffer(bh); + return 0; + } + bh->b_end_io = end_buffer_read_sync; + get_bh(bh); + submit_bh(READ_SYNC | (1 << BIO_RW_META), bh); + if (!(flags & DIO_WAIT)) + return 0; + + wait_on_buffer(bh); + if (unlikely(!buffer_uptodate(bh))) { + struct gfs2_trans *tr = current->journal_info; + if (tr && tr->tr_touched) + gfs2_io_error_bh(sdp, bh); + brelse(bh); + return -EIO; } return 0; @@ -404,7 +467,7 @@ struct buffer_head *gfs2_meta_ra(struct gfs2_glock *gl, u64 dblock, u32 extlen) if (buffer_uptodate(first_bh)) goto out; if (!buffer_locked(first_bh)) - ll_rw_block(READ_META, 1, &first_bh); + ll_rw_block(READ_SYNC | (1 << BIO_RW_META), 1, &first_bh); dblock++; extlen--; diff --git a/fs/gfs2/mount.c b/fs/gfs2/mount.c deleted file mode 100644 index f7e8527a21e0..000000000000 --- a/fs/gfs2/mount.c +++ /dev/null @@ -1,185 +0,0 @@ -/* - * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. - */ - -#include <linux/slab.h> -#include <linux/spinlock.h> -#include <linux/completion.h> -#include <linux/buffer_head.h> -#include <linux/gfs2_ondisk.h> -#include <linux/parser.h> - -#include "gfs2.h" -#include "incore.h" -#include "super.h" -#include "sys.h" -#include "util.h" - -enum { - Opt_lockproto, - Opt_locktable, - Opt_hostdata, - Opt_spectator, - Opt_ignore_local_fs, - Opt_localflocks, - Opt_localcaching, - Opt_debug, - Opt_nodebug, - Opt_upgrade, - Opt_acl, - Opt_noacl, - Opt_quota_off, - Opt_quota_account, - Opt_quota_on, - Opt_quota, - Opt_noquota, - Opt_suiddir, - Opt_nosuiddir, - Opt_data_writeback, - Opt_data_ordered, - Opt_meta, - Opt_discard, - Opt_nodiscard, - Opt_err, -}; - -static const match_table_t tokens = { - {Opt_lockproto, "lockproto=%s"}, - {Opt_locktable, "locktable=%s"}, - {Opt_hostdata, "hostdata=%s"}, - {Opt_spectator, "spectator"}, - {Opt_ignore_local_fs, "ignore_local_fs"}, - {Opt_localflocks, "localflocks"}, - {Opt_localcaching, "localcaching"}, - {Opt_debug, "debug"}, - {Opt_nodebug, "nodebug"}, - {Opt_upgrade, "upgrade"}, - {Opt_acl, "acl"}, - {Opt_noacl, "noacl"}, - {Opt_quota_off, "quota=off"}, - {Opt_quota_account, "quota=account"}, - {Opt_quota_on, "quota=on"}, - {Opt_quota, "quota"}, - {Opt_noquota, "noquota"}, - {Opt_suiddir, "suiddir"}, - {Opt_nosuiddir, "nosuiddir"}, - {Opt_data_writeback, "data=writeback"}, - {Opt_data_ordered, "data=ordered"}, - {Opt_meta, "meta"}, - {Opt_discard, "discard"}, - {Opt_nodiscard, "nodiscard"}, - {Opt_err, NULL} -}; - -/** - * gfs2_mount_args - Parse mount options - * @sdp: - * @data: - * - * Return: errno - */ - -int gfs2_mount_args(struct gfs2_sbd *sdp, struct gfs2_args *args, char *options) -{ - char *o; - int token; - substring_t tmp[MAX_OPT_ARGS]; - - /* Split the options into tokens with the "," character and - process them */ - - while (1) { - o = strsep(&options, ","); - if (o == NULL) - break; - if (*o == '\0') - continue; - - token = match_token(o, tokens, tmp); - switch (token) { - case Opt_lockproto: - match_strlcpy(args->ar_lockproto, &tmp[0], - GFS2_LOCKNAME_LEN); - break; - case Opt_locktable: - match_strlcpy(args->ar_locktable, &tmp[0], - GFS2_LOCKNAME_LEN); - break; - case Opt_hostdata: - match_strlcpy(args->ar_hostdata, &tmp[0], - GFS2_LOCKNAME_LEN); - break; - case Opt_spectator: - args->ar_spectator = 1; - break; - case Opt_ignore_local_fs: - args->ar_ignore_local_fs = 1; - break; - case Opt_localflocks: - args->ar_localflocks = 1; - break; - case Opt_localcaching: - args->ar_localcaching = 1; - break; - case Opt_debug: - args->ar_debug = 1; - break; - case Opt_nodebug: - args->ar_debug = 0; - break; - case Opt_upgrade: - args->ar_upgrade = 1; - break; - case Opt_acl: - args->ar_posix_acl = 1; - break; - case Opt_noacl: - args->ar_posix_acl = 0; - break; - case Opt_quota_off: - case Opt_noquota: - args->ar_quota = GFS2_QUOTA_OFF; - break; - case Opt_quota_account: - args->ar_quota = GFS2_QUOTA_ACCOUNT; - break; - case Opt_quota_on: - case Opt_quota: - args->ar_quota = GFS2_QUOTA_ON; - break; - case Opt_suiddir: - args->ar_suiddir = 1; - break; - case Opt_nosuiddir: - args->ar_suiddir = 0; - break; - case Opt_data_writeback: - args->ar_data = GFS2_DATA_WRITEBACK; - break; - case Opt_data_ordered: - args->ar_data = GFS2_DATA_ORDERED; - break; - case Opt_meta: - args->ar_meta = 1; - break; - case Opt_discard: - args->ar_discard = 1; - break; - case Opt_nodiscard: - args->ar_discard = 0; - break; - case Opt_err: - default: - fs_info(sdp, "invalid mount option: %s\n", o); - return -EINVAL; - } - } - - return 0; -} - diff --git a/fs/gfs2/ops_address.h b/fs/gfs2/ops_address.h deleted file mode 100644 index 5da21285bba4..000000000000 --- a/fs/gfs2/ops_address.h +++ /dev/null @@ -1,23 +0,0 @@ -/* - * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2007 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. - */ - -#ifndef __OPS_ADDRESS_DOT_H__ -#define __OPS_ADDRESS_DOT_H__ - -#include <linux/fs.h> -#include <linux/buffer_head.h> -#include <linux/mm.h> - -extern int gfs2_releasepage(struct page *page, gfp_t gfp_mask); -extern int gfs2_internal_read(struct gfs2_inode *ip, - struct file_ra_state *ra_state, - char *buf, loff_t *pos, unsigned size); -extern void gfs2_set_aops(struct inode *inode); - -#endif /* __OPS_ADDRESS_DOT_H__ */ diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index 1ff9473ea753..7bc3c45cd676 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -17,6 +17,7 @@ #include <linux/namei.h> #include <linux/mount.h> #include <linux/gfs2_ondisk.h> +#include <linux/slow-work.h> #include "gfs2.h" #include "incore.h" @@ -32,6 +33,7 @@ #include "log.h" #include "quota.h" #include "dir.h" +#include "trace_gfs2.h" #define DO 0 #define UNDO 1 @@ -55,8 +57,6 @@ static void gfs2_tune_init(struct gfs2_tune *gt) spin_lock_init(>->gt_spin); gt->gt_incore_log_blocks = 1024; - gt->gt_log_flush_secs = 60; - gt->gt_recoverd_secs = 60; gt->gt_logd_secs = 1; gt->gt_quota_simul_sync = 64; gt->gt_quota_warn_period = 10; @@ -526,11 +526,11 @@ static int init_sb(struct gfs2_sbd *sdp, int silent) } /* Set up the buffer cache and SB for real */ - if (sdp->sd_sb.sb_bsize < bdev_hardsect_size(sb->s_bdev)) { + if (sdp->sd_sb.sb_bsize < bdev_logical_block_size(sb->s_bdev)) { ret = -EINVAL; fs_err(sdp, "FS block size (%u) is too small for device " "block size (%u)\n", - sdp->sd_sb.sb_bsize, bdev_hardsect_size(sb->s_bdev)); + sdp->sd_sb.sb_bsize, bdev_logical_block_size(sb->s_bdev)); goto out; } if (sdp->sd_sb.sb_bsize > PAGE_SIZE) { @@ -676,6 +676,7 @@ static int gfs2_jindex_hold(struct gfs2_sbd *sdp, struct gfs2_holder *ji_gh) break; INIT_LIST_HEAD(&jd->extent_list); + slow_work_init(&jd->jd_work, &gfs2_recover_ops); jd->jd_inode = gfs2_lookupi(sdp->sd_jindex, &name, 1); if (!jd->jd_inode || IS_ERR(jd->jd_inode)) { if (!jd->jd_inode) @@ -701,14 +702,13 @@ static int init_journal(struct gfs2_sbd *sdp, int undo) { struct inode *master = sdp->sd_master_dir->d_inode; struct gfs2_holder ji_gh; - struct task_struct *p; struct gfs2_inode *ip; int jindex = 1; int error = 0; if (undo) { jindex = 0; - goto fail_recoverd; + goto fail_jinode_gh; } sdp->sd_jindex = gfs2_lookup_simple(master, "jindex"); @@ -776,6 +776,7 @@ static int init_journal(struct gfs2_sbd *sdp, int undo) /* Map the extents for this journal's blocks */ map_journal_extents(sdp); } + trace_gfs2_log_blocks(sdp, atomic_read(&sdp->sd_log_blks_free)); if (sdp->sd_lockstruct.ls_first) { unsigned int x; @@ -801,18 +802,8 @@ static int init_journal(struct gfs2_sbd *sdp, int undo) gfs2_glock_dq_uninit(&ji_gh); jindex = 0; - p = kthread_run(gfs2_recoverd, sdp, "gfs2_recoverd"); - error = IS_ERR(p); - if (error) { - fs_err(sdp, "can't start recoverd thread: %d\n", error); - goto fail_jinode_gh; - } - sdp->sd_recoverd_process = p; - return 0; -fail_recoverd: - kthread_stop(sdp->sd_recoverd_process); fail_jinode_gh: if (!sdp->sd_args.ar_spectator) gfs2_glock_dq_uninit(&sdp->sd_jinode_gh); @@ -1165,6 +1156,7 @@ static int fill_super(struct super_block *sb, void *data, int silent) sdp->sd_args.ar_quota = GFS2_QUOTA_DEFAULT; sdp->sd_args.ar_data = GFS2_DATA_DEFAULT; + sdp->sd_args.ar_commit = 60; error = gfs2_mount_args(sdp, &sdp->sd_args, data); if (error) { @@ -1172,8 +1164,10 @@ static int fill_super(struct super_block *sb, void *data, int silent) goto fail; } - if (sdp->sd_args.ar_spectator) + if (sdp->sd_args.ar_spectator) { sb->s_flags |= MS_RDONLY; + set_bit(SDF_NORECOVERY, &sdp->sd_flags); + } if (sdp->sd_args.ar_posix_acl) sb->s_flags |= MS_POSIXACL; @@ -1191,6 +1185,8 @@ static int fill_super(struct super_block *sb, void *data, int silent) GFS2_BASIC_BLOCK_SHIFT; sdp->sd_fsb2bb = 1 << sdp->sd_fsb2bb_shift; + sdp->sd_tune.gt_log_flush_secs = sdp->sd_args.ar_commit; + error = init_names(sdp, silent); if (error) goto fail; @@ -1279,9 +1275,22 @@ static int gfs2_get_sb(struct file_system_type *fs_type, int flags, return get_sb_bdev(fs_type, flags, dev_name, data, fill_super, mnt); } -static struct super_block *get_gfs2_sb(const char *dev_name) +static int test_meta_super(struct super_block *s, void *ptr) +{ + struct block_device *bdev = ptr; + return (bdev == s->s_bdev); +} + +static int set_meta_super(struct super_block *s, void *ptr) { - struct super_block *sb; + return -EINVAL; +} + +static int gfs2_get_sb_meta(struct file_system_type *fs_type, int flags, + const char *dev_name, void *data, struct vfsmount *mnt) +{ + struct super_block *s; + struct gfs2_sbd *sdp; struct path path; int error; @@ -1289,30 +1298,17 @@ static struct super_block *get_gfs2_sb(const char *dev_name) if (error) { printk(KERN_WARNING "GFS2: path_lookup on %s returned error %d\n", dev_name, error); - return NULL; + return error; } - sb = path.dentry->d_inode->i_sb; - if (sb && (sb->s_type == &gfs2_fs_type)) - atomic_inc(&sb->s_active); - else - sb = NULL; + s = sget(&gfs2_fs_type, test_meta_super, set_meta_super, + path.dentry->d_inode->i_sb->s_bdev); path_put(&path); - return sb; -} - -static int gfs2_get_sb_meta(struct file_system_type *fs_type, int flags, - const char *dev_name, void *data, struct vfsmount *mnt) -{ - struct super_block *sb = NULL; - struct gfs2_sbd *sdp; - - sb = get_gfs2_sb(dev_name); - if (!sb) { + if (IS_ERR(s)) { printk(KERN_WARNING "GFS2: gfs2 mount does not exist\n"); - return -ENOENT; + return PTR_ERR(s); } - sdp = sb->s_fs_info; - mnt->mnt_sb = sb; + sdp = s->s_fs_info; + mnt->mnt_sb = s; mnt->mnt_root = dget(sdp->sd_master_dir); return 0; } diff --git a/fs/gfs2/ops_inode.c b/fs/gfs2/ops_inode.c index 1c70fa5168d6..f8bd20baf99c 100644 --- a/fs/gfs2/ops_inode.c +++ b/fs/gfs2/ops_inode.c @@ -262,6 +262,44 @@ out_parent: return error; } +/* + * gfs2_unlink_ok - check to see that a inode is still in a directory + * @dip: the directory + * @name: the name of the file + * @ip: the inode + * + * Assumes that the lock on (at least) @dip is held. + * + * Returns: 0 if the parent/child relationship is correct, errno if it isn't + */ + +static int gfs2_unlink_ok(struct gfs2_inode *dip, const struct qstr *name, + const struct gfs2_inode *ip) +{ + int error; + + if (IS_IMMUTABLE(&ip->i_inode) || IS_APPEND(&ip->i_inode)) + return -EPERM; + + if ((dip->i_inode.i_mode & S_ISVTX) && + dip->i_inode.i_uid != current_fsuid() && + ip->i_inode.i_uid != current_fsuid() && !capable(CAP_FOWNER)) + return -EPERM; + + if (IS_APPEND(&dip->i_inode)) + return -EPERM; + + error = gfs2_permission(&dip->i_inode, MAY_WRITE | MAY_EXEC); + if (error) + return error; + + error = gfs2_dir_check(&dip->i_inode, name, ip); + if (error) + return error; + + return 0; +} + /** * gfs2_unlink - Unlink a file * @dir: The inode of the directory containing the file to unlink @@ -473,6 +511,59 @@ static int gfs2_mkdir(struct inode *dir, struct dentry *dentry, int mode) } /** + * gfs2_rmdiri - Remove a directory + * @dip: The parent directory of the directory to be removed + * @name: The name of the directory to be removed + * @ip: The GFS2 inode of the directory to be removed + * + * Assumes Glocks on dip and ip are held + * + * Returns: errno + */ + +static int gfs2_rmdiri(struct gfs2_inode *dip, const struct qstr *name, + struct gfs2_inode *ip) +{ + struct qstr dotname; + int error; + + if (ip->i_entries != 2) { + if (gfs2_consist_inode(ip)) + gfs2_dinode_print(ip); + return -EIO; + } + + error = gfs2_dir_del(dip, name); + if (error) + return error; + + error = gfs2_change_nlink(dip, -1); + if (error) + return error; + + gfs2_str2qstr(&dotname, "."); + error = gfs2_dir_del(ip, &dotname); + if (error) + return error; + + gfs2_str2qstr(&dotname, ".."); + error = gfs2_dir_del(ip, &dotname); + if (error) + return error; + + /* It looks odd, but it really should be done twice */ + error = gfs2_change_nlink(ip, -1); + if (error) + return error; + + error = gfs2_change_nlink(ip, -1); + if (error) + return error; + + return error; +} + +/** * gfs2_rmdir - Remove a directory * @dir: The parent directory of the directory to be removed * @dentry: The dentry of the directory to remove @@ -885,6 +976,61 @@ out: } /** + * gfs2_readlinki - return the contents of a symlink + * @ip: the symlink's inode + * @buf: a pointer to the buffer to be filled + * @len: a pointer to the length of @buf + * + * If @buf is too small, a piece of memory is kmalloc()ed and needs + * to be freed by the caller. + * + * Returns: errno + */ + +static int gfs2_readlinki(struct gfs2_inode *ip, char **buf, unsigned int *len) +{ + struct gfs2_holder i_gh; + struct buffer_head *dibh; + unsigned int x; + int error; + + gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &i_gh); + error = gfs2_glock_nq(&i_gh); + if (error) { + gfs2_holder_uninit(&i_gh); + return error; + } + + if (!ip->i_disksize) { + gfs2_consist_inode(ip); + error = -EIO; + goto out; + } + + error = gfs2_meta_inode_buffer(ip, &dibh); + if (error) + goto out; + + x = ip->i_disksize + 1; + if (x > *len) { + *buf = kmalloc(x, GFP_NOFS); + if (!*buf) { + error = -ENOMEM; + goto out_brelse; + } + } + + memcpy(*buf, dibh->b_data + sizeof(struct gfs2_dinode), x); + *len = x; + +out_brelse: + brelse(dibh); +out: + gfs2_glock_dq_uninit(&i_gh); + return error; +} + +/** * gfs2_readlink - Read the value of a symlink * @dentry: the symlink * @buf: the buffer to read the symlink data into diff --git a/fs/gfs2/ops_super.c b/fs/gfs2/ops_super.c deleted file mode 100644 index 458019569dcb..000000000000 --- a/fs/gfs2/ops_super.c +++ /dev/null @@ -1,723 +0,0 @@ -/* - * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. - */ - -#include <linux/sched.h> -#include <linux/slab.h> -#include <linux/spinlock.h> -#include <linux/completion.h> -#include <linux/buffer_head.h> -#include <linux/statfs.h> -#include <linux/seq_file.h> -#include <linux/mount.h> -#include <linux/kthread.h> -#include <linux/delay.h> -#include <linux/gfs2_ondisk.h> -#include <linux/crc32.h> -#include <linux/time.h> - -#include "gfs2.h" -#include "incore.h" -#include "glock.h" -#include "inode.h" -#include "log.h" -#include "quota.h" -#include "recovery.h" -#include "rgrp.h" -#include "super.h" -#include "sys.h" -#include "util.h" -#include "trans.h" -#include "dir.h" -#include "eattr.h" -#include "bmap.h" -#include "meta_io.h" - -#define args_neq(a1, a2, x) ((a1)->ar_##x != (a2)->ar_##x) - -/** - * gfs2_write_inode - Make sure the inode is stable on the disk - * @inode: The inode - * @sync: synchronous write flag - * - * Returns: errno - */ - -static int gfs2_write_inode(struct inode *inode, int sync) -{ - struct gfs2_inode *ip = GFS2_I(inode); - struct gfs2_sbd *sdp = GFS2_SB(inode); - struct gfs2_holder gh; - struct buffer_head *bh; - struct timespec atime; - struct gfs2_dinode *di; - int ret = 0; - - /* Check this is a "normal" inode, etc */ - if (!test_bit(GIF_USER, &ip->i_flags) || - (current->flags & PF_MEMALLOC)) - return 0; - ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh); - if (ret) - goto do_flush; - ret = gfs2_trans_begin(sdp, RES_DINODE, 0); - if (ret) - goto do_unlock; - ret = gfs2_meta_inode_buffer(ip, &bh); - if (ret == 0) { - di = (struct gfs2_dinode *)bh->b_data; - atime.tv_sec = be64_to_cpu(di->di_atime); - atime.tv_nsec = be32_to_cpu(di->di_atime_nsec); - if (timespec_compare(&inode->i_atime, &atime) > 0) { - gfs2_trans_add_bh(ip->i_gl, bh, 1); - gfs2_dinode_out(ip, bh->b_data); - } - brelse(bh); - } - gfs2_trans_end(sdp); -do_unlock: - gfs2_glock_dq_uninit(&gh); -do_flush: - if (sync != 0) - gfs2_log_flush(GFS2_SB(inode), ip->i_gl); - return ret; -} - -/** - * gfs2_make_fs_ro - Turn a Read-Write FS into a Read-Only one - * @sdp: the filesystem - * - * Returns: errno - */ - -static int gfs2_make_fs_ro(struct gfs2_sbd *sdp) -{ - struct gfs2_holder t_gh; - int error; - - gfs2_quota_sync(sdp); - gfs2_statfs_sync(sdp); - - error = gfs2_glock_nq_init(sdp->sd_trans_gl, LM_ST_SHARED, GL_NOCACHE, - &t_gh); - if (error && !test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) - return error; - - gfs2_meta_syncfs(sdp); - gfs2_log_shutdown(sdp); - - clear_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags); - - if (t_gh.gh_gl) - gfs2_glock_dq_uninit(&t_gh); - - gfs2_quota_cleanup(sdp); - - return error; -} - -/** - * gfs2_put_super - Unmount the filesystem - * @sb: The VFS superblock - * - */ - -static void gfs2_put_super(struct super_block *sb) -{ - struct gfs2_sbd *sdp = sb->s_fs_info; - int error; - - /* Unfreeze the filesystem, if we need to */ - - mutex_lock(&sdp->sd_freeze_lock); - if (sdp->sd_freeze_count) - gfs2_glock_dq_uninit(&sdp->sd_freeze_gh); - mutex_unlock(&sdp->sd_freeze_lock); - - kthread_stop(sdp->sd_quotad_process); - kthread_stop(sdp->sd_logd_process); - kthread_stop(sdp->sd_recoverd_process); - - if (!(sb->s_flags & MS_RDONLY)) { - error = gfs2_make_fs_ro(sdp); - if (error) - gfs2_io_error(sdp); - } - /* At this point, we're through modifying the disk */ - - /* Release stuff */ - - iput(sdp->sd_jindex); - iput(sdp->sd_inum_inode); - iput(sdp->sd_statfs_inode); - iput(sdp->sd_rindex); - iput(sdp->sd_quota_inode); - - gfs2_glock_put(sdp->sd_rename_gl); - gfs2_glock_put(sdp->sd_trans_gl); - - if (!sdp->sd_args.ar_spectator) { - gfs2_glock_dq_uninit(&sdp->sd_journal_gh); - gfs2_glock_dq_uninit(&sdp->sd_jinode_gh); - gfs2_glock_dq_uninit(&sdp->sd_ir_gh); - gfs2_glock_dq_uninit(&sdp->sd_sc_gh); - gfs2_glock_dq_uninit(&sdp->sd_qc_gh); - iput(sdp->sd_ir_inode); - iput(sdp->sd_sc_inode); - iput(sdp->sd_qc_inode); - } - - gfs2_glock_dq_uninit(&sdp->sd_live_gh); - gfs2_clear_rgrpd(sdp); - gfs2_jindex_free(sdp); - /* Take apart glock structures and buffer lists */ - gfs2_gl_hash_clear(sdp); - /* Unmount the locking protocol */ - gfs2_lm_unmount(sdp); - - /* At this point, we're through participating in the lockspace */ - gfs2_sys_fs_del(sdp); -} - -/** - * gfs2_write_super - * @sb: the superblock - * - */ - -static void gfs2_write_super(struct super_block *sb) -{ - sb->s_dirt = 0; -} - -/** - * gfs2_sync_fs - sync the filesystem - * @sb: the superblock - * - * Flushes the log to disk. - */ - -static int gfs2_sync_fs(struct super_block *sb, int wait) -{ - sb->s_dirt = 0; - if (wait && sb->s_fs_info) - gfs2_log_flush(sb->s_fs_info, NULL); - return 0; -} - -/** - * gfs2_freeze - prevent further writes to the filesystem - * @sb: the VFS structure for the filesystem - * - */ - -static int gfs2_freeze(struct super_block *sb) -{ - struct gfs2_sbd *sdp = sb->s_fs_info; - int error; - - if (test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) - return -EINVAL; - - for (;;) { - error = gfs2_freeze_fs(sdp); - if (!error) - break; - - switch (error) { - case -EBUSY: - fs_err(sdp, "waiting for recovery before freeze\n"); - break; - - default: - fs_err(sdp, "error freezing FS: %d\n", error); - break; - } - - fs_err(sdp, "retrying...\n"); - msleep(1000); - } - return 0; -} - -/** - * gfs2_unfreeze - reallow writes to the filesystem - * @sb: the VFS structure for the filesystem - * - */ - -static int gfs2_unfreeze(struct super_block *sb) -{ - gfs2_unfreeze_fs(sb->s_fs_info); - return 0; -} - -/** - * statfs_fill - fill in the sg for a given RG - * @rgd: the RG - * @sc: the sc structure - * - * Returns: 0 on success, -ESTALE if the LVB is invalid - */ - -static int statfs_slow_fill(struct gfs2_rgrpd *rgd, - struct gfs2_statfs_change_host *sc) -{ - gfs2_rgrp_verify(rgd); - sc->sc_total += rgd->rd_data; - sc->sc_free += rgd->rd_free; - sc->sc_dinodes += rgd->rd_dinodes; - return 0; -} - -/** - * gfs2_statfs_slow - Stat a filesystem using asynchronous locking - * @sdp: the filesystem - * @sc: the sc info that will be returned - * - * Any error (other than a signal) will cause this routine to fall back - * to the synchronous version. - * - * FIXME: This really shouldn't busy wait like this. - * - * Returns: errno - */ - -static int gfs2_statfs_slow(struct gfs2_sbd *sdp, struct gfs2_statfs_change_host *sc) -{ - struct gfs2_holder ri_gh; - struct gfs2_rgrpd *rgd_next; - struct gfs2_holder *gha, *gh; - unsigned int slots = 64; - unsigned int x; - int done; - int error = 0, err; - - memset(sc, 0, sizeof(struct gfs2_statfs_change_host)); - gha = kcalloc(slots, sizeof(struct gfs2_holder), GFP_KERNEL); - if (!gha) - return -ENOMEM; - - error = gfs2_rindex_hold(sdp, &ri_gh); - if (error) - goto out; - - rgd_next = gfs2_rgrpd_get_first(sdp); - - for (;;) { - done = 1; - - for (x = 0; x < slots; x++) { - gh = gha + x; - - if (gh->gh_gl && gfs2_glock_poll(gh)) { - err = gfs2_glock_wait(gh); - if (err) { - gfs2_holder_uninit(gh); - error = err; - } else { - if (!error) - error = statfs_slow_fill( - gh->gh_gl->gl_object, sc); - gfs2_glock_dq_uninit(gh); - } - } - - if (gh->gh_gl) - done = 0; - else if (rgd_next && !error) { - error = gfs2_glock_nq_init(rgd_next->rd_gl, - LM_ST_SHARED, - GL_ASYNC, - gh); - rgd_next = gfs2_rgrpd_get_next(rgd_next); - done = 0; - } - - if (signal_pending(current)) - error = -ERESTARTSYS; - } - - if (done) - break; - - yield(); - } - - gfs2_glock_dq_uninit(&ri_gh); - -out: - kfree(gha); - return error; -} - -/** - * gfs2_statfs_i - Do a statfs - * @sdp: the filesystem - * @sg: the sg structure - * - * Returns: errno - */ - -static int gfs2_statfs_i(struct gfs2_sbd *sdp, struct gfs2_statfs_change_host *sc) -{ - struct gfs2_statfs_change_host *m_sc = &sdp->sd_statfs_master; - struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local; - - spin_lock(&sdp->sd_statfs_spin); - - *sc = *m_sc; - sc->sc_total += l_sc->sc_total; - sc->sc_free += l_sc->sc_free; - sc->sc_dinodes += l_sc->sc_dinodes; - - spin_unlock(&sdp->sd_statfs_spin); - - if (sc->sc_free < 0) - sc->sc_free = 0; - if (sc->sc_free > sc->sc_total) - sc->sc_free = sc->sc_total; - if (sc->sc_dinodes < 0) - sc->sc_dinodes = 0; - - return 0; -} - -/** - * gfs2_statfs - Gather and return stats about the filesystem - * @sb: The superblock - * @statfsbuf: The buffer - * - * Returns: 0 on success or error code - */ - -static int gfs2_statfs(struct dentry *dentry, struct kstatfs *buf) -{ - struct super_block *sb = dentry->d_inode->i_sb; - struct gfs2_sbd *sdp = sb->s_fs_info; - struct gfs2_statfs_change_host sc; - int error; - - if (gfs2_tune_get(sdp, gt_statfs_slow)) - error = gfs2_statfs_slow(sdp, &sc); - else - error = gfs2_statfs_i(sdp, &sc); - - if (error) - return error; - - buf->f_type = GFS2_MAGIC; - buf->f_bsize = sdp->sd_sb.sb_bsize; - buf->f_blocks = sc.sc_total; - buf->f_bfree = sc.sc_free; - buf->f_bavail = sc.sc_free; - buf->f_files = sc.sc_dinodes + sc.sc_free; - buf->f_ffree = sc.sc_free; - buf->f_namelen = GFS2_FNAMESIZE; - - return 0; -} - -/** - * gfs2_remount_fs - called when the FS is remounted - * @sb: the filesystem - * @flags: the remount flags - * @data: extra data passed in (not used right now) - * - * Returns: errno - */ - -static int gfs2_remount_fs(struct super_block *sb, int *flags, char *data) -{ - struct gfs2_sbd *sdp = sb->s_fs_info; - struct gfs2_args args = sdp->sd_args; /* Default to current settings */ - int error; - - error = gfs2_mount_args(sdp, &args, data); - if (error) - return error; - - /* Not allowed to change locking details */ - if (strcmp(args.ar_lockproto, sdp->sd_args.ar_lockproto) || - strcmp(args.ar_locktable, sdp->sd_args.ar_locktable) || - strcmp(args.ar_hostdata, sdp->sd_args.ar_hostdata)) - return -EINVAL; - - /* Some flags must not be changed */ - if (args_neq(&args, &sdp->sd_args, spectator) || - args_neq(&args, &sdp->sd_args, ignore_local_fs) || - args_neq(&args, &sdp->sd_args, localflocks) || - args_neq(&args, &sdp->sd_args, localcaching) || - args_neq(&args, &sdp->sd_args, meta)) - return -EINVAL; - - if (sdp->sd_args.ar_spectator) - *flags |= MS_RDONLY; - - if ((sb->s_flags ^ *flags) & MS_RDONLY) { - if (*flags & MS_RDONLY) - error = gfs2_make_fs_ro(sdp); - else - error = gfs2_make_fs_rw(sdp); - if (error) - return error; - } - - sdp->sd_args = args; - if (sdp->sd_args.ar_posix_acl) - sb->s_flags |= MS_POSIXACL; - else - sb->s_flags &= ~MS_POSIXACL; - return 0; -} - -/** - * gfs2_drop_inode - Drop an inode (test for remote unlink) - * @inode: The inode to drop - * - * If we've received a callback on an iopen lock then its because a - * remote node tried to deallocate the inode but failed due to this node - * still having the inode open. Here we mark the link count zero - * since we know that it must have reached zero if the GLF_DEMOTE flag - * is set on the iopen glock. If we didn't do a disk read since the - * remote node removed the final link then we might otherwise miss - * this event. This check ensures that this node will deallocate the - * inode's blocks, or alternatively pass the baton on to another - * node for later deallocation. - */ - -static void gfs2_drop_inode(struct inode *inode) -{ - struct gfs2_inode *ip = GFS2_I(inode); - - if (test_bit(GIF_USER, &ip->i_flags) && inode->i_nlink) { - struct gfs2_glock *gl = ip->i_iopen_gh.gh_gl; - if (gl && test_bit(GLF_DEMOTE, &gl->gl_flags)) - clear_nlink(inode); - } - generic_drop_inode(inode); -} - -/** - * gfs2_clear_inode - Deallocate an inode when VFS is done with it - * @inode: The VFS inode - * - */ - -static void gfs2_clear_inode(struct inode *inode) -{ - struct gfs2_inode *ip = GFS2_I(inode); - - /* This tells us its a "real" inode and not one which only - * serves to contain an address space (see rgrp.c, meta_io.c) - * which therefore doesn't have its own glocks. - */ - if (test_bit(GIF_USER, &ip->i_flags)) { - ip->i_gl->gl_object = NULL; - gfs2_glock_put(ip->i_gl); - ip->i_gl = NULL; - if (ip->i_iopen_gh.gh_gl) { - ip->i_iopen_gh.gh_gl->gl_object = NULL; - gfs2_glock_dq_uninit(&ip->i_iopen_gh); - } - } -} - -static int is_ancestor(const struct dentry *d1, const struct dentry *d2) -{ - do { - if (d1 == d2) - return 1; - d1 = d1->d_parent; - } while (!IS_ROOT(d1)); - return 0; -} - -/** - * gfs2_show_options - Show mount options for /proc/mounts - * @s: seq_file structure - * @mnt: vfsmount - * - * Returns: 0 on success or error code - */ - -static int gfs2_show_options(struct seq_file *s, struct vfsmount *mnt) -{ - struct gfs2_sbd *sdp = mnt->mnt_sb->s_fs_info; - struct gfs2_args *args = &sdp->sd_args; - - if (is_ancestor(mnt->mnt_root, sdp->sd_master_dir)) - seq_printf(s, ",meta"); - if (args->ar_lockproto[0]) - seq_printf(s, ",lockproto=%s", args->ar_lockproto); - if (args->ar_locktable[0]) - seq_printf(s, ",locktable=%s", args->ar_locktable); - if (args->ar_hostdata[0]) - seq_printf(s, ",hostdata=%s", args->ar_hostdata); - if (args->ar_spectator) - seq_printf(s, ",spectator"); - if (args->ar_ignore_local_fs) - seq_printf(s, ",ignore_local_fs"); - if (args->ar_localflocks) - seq_printf(s, ",localflocks"); - if (args->ar_localcaching) - seq_printf(s, ",localcaching"); - if (args->ar_debug) - seq_printf(s, ",debug"); - if (args->ar_upgrade) - seq_printf(s, ",upgrade"); - if (args->ar_posix_acl) - seq_printf(s, ",acl"); - if (args->ar_quota != GFS2_QUOTA_DEFAULT) { - char *state; - switch (args->ar_quota) { - case GFS2_QUOTA_OFF: - state = "off"; - break; - case GFS2_QUOTA_ACCOUNT: - state = "account"; - break; - case GFS2_QUOTA_ON: - state = "on"; - break; - default: - state = "unknown"; - break; - } - seq_printf(s, ",quota=%s", state); - } - if (args->ar_suiddir) - seq_printf(s, ",suiddir"); - if (args->ar_data != GFS2_DATA_DEFAULT) { - char *state; - switch (args->ar_data) { - case GFS2_DATA_WRITEBACK: - state = "writeback"; - break; - case GFS2_DATA_ORDERED: - state = "ordered"; - break; - default: - state = "unknown"; - break; - } - seq_printf(s, ",data=%s", state); - } - if (args->ar_discard) - seq_printf(s, ",discard"); - - return 0; -} - -/* - * We have to (at the moment) hold the inodes main lock to cover - * the gap between unlocking the shared lock on the iopen lock and - * taking the exclusive lock. I'd rather do a shared -> exclusive - * conversion on the iopen lock, but we can change that later. This - * is safe, just less efficient. - */ - -static void gfs2_delete_inode(struct inode *inode) -{ - struct gfs2_sbd *sdp = inode->i_sb->s_fs_info; - struct gfs2_inode *ip = GFS2_I(inode); - struct gfs2_holder gh; - int error; - - if (!test_bit(GIF_USER, &ip->i_flags)) - goto out; - - error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh); - if (unlikely(error)) { - gfs2_glock_dq_uninit(&ip->i_iopen_gh); - goto out; - } - - gfs2_glock_dq_wait(&ip->i_iopen_gh); - gfs2_holder_reinit(LM_ST_EXCLUSIVE, LM_FLAG_TRY_1CB | GL_NOCACHE, &ip->i_iopen_gh); - error = gfs2_glock_nq(&ip->i_iopen_gh); - if (error) - goto out_truncate; - - if (S_ISDIR(inode->i_mode) && - (ip->i_diskflags & GFS2_DIF_EXHASH)) { - error = gfs2_dir_exhash_dealloc(ip); - if (error) - goto out_unlock; - } - - if (ip->i_eattr) { - error = gfs2_ea_dealloc(ip); - if (error) - goto out_unlock; - } - - if (!gfs2_is_stuffed(ip)) { - error = gfs2_file_dealloc(ip); - if (error) - goto out_unlock; - } - - error = gfs2_dinode_dealloc(ip); - if (error) - goto out_unlock; - -out_truncate: - error = gfs2_trans_begin(sdp, 0, sdp->sd_jdesc->jd_blocks); - if (error) - goto out_unlock; - /* Needs to be done before glock release & also in a transaction */ - truncate_inode_pages(&inode->i_data, 0); - gfs2_trans_end(sdp); - -out_unlock: - if (test_bit(HIF_HOLDER, &ip->i_iopen_gh.gh_iflags)) - gfs2_glock_dq(&ip->i_iopen_gh); - gfs2_holder_uninit(&ip->i_iopen_gh); - gfs2_glock_dq_uninit(&gh); - if (error && error != GLR_TRYFAILED) - fs_warn(sdp, "gfs2_delete_inode: %d\n", error); -out: - truncate_inode_pages(&inode->i_data, 0); - clear_inode(inode); -} - -static struct inode *gfs2_alloc_inode(struct super_block *sb) -{ - struct gfs2_inode *ip; - - ip = kmem_cache_alloc(gfs2_inode_cachep, GFP_KERNEL); - if (ip) { - ip->i_flags = 0; - ip->i_gl = NULL; - } - return &ip->i_inode; -} - -static void gfs2_destroy_inode(struct inode *inode) -{ - kmem_cache_free(gfs2_inode_cachep, inode); -} - -const struct super_operations gfs2_super_ops = { - .alloc_inode = gfs2_alloc_inode, - .destroy_inode = gfs2_destroy_inode, - .write_inode = gfs2_write_inode, - .delete_inode = gfs2_delete_inode, - .put_super = gfs2_put_super, - .write_super = gfs2_write_super, - .sync_fs = gfs2_sync_fs, - .freeze_fs = gfs2_freeze, - .unfreeze_fs = gfs2_unfreeze, - .statfs = gfs2_statfs, - .remount_fs = gfs2_remount_fs, - .clear_inode = gfs2_clear_inode, - .drop_inode = gfs2_drop_inode, - .show_options = gfs2_show_options, -}; - diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index 152e6c4a0dca..2e9b9326bfc9 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -60,7 +60,6 @@ #include "super.h" #include "trans.h" #include "inode.h" -#include "ops_address.h" #include "util.h" #define QUOTA_USER 1 diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c index 247e8f7d6b3d..59d2695509d3 100644 --- a/fs/gfs2/recovery.c +++ b/fs/gfs2/recovery.c @@ -13,8 +13,7 @@ #include <linux/buffer_head.h> #include <linux/gfs2_ondisk.h> #include <linux/crc32.h> -#include <linux/kthread.h> -#include <linux/freezer.h> +#include <linux/slow-work.h> #include "gfs2.h" #include "incore.h" @@ -441,18 +440,25 @@ static void gfs2_recovery_done(struct gfs2_sbd *sdp, unsigned int jid, kobject_uevent_env(&sdp->sd_kobj, KOBJ_CHANGE, envp); } -/** - * gfs2_recover_journal - recover a given journal - * @jd: the struct gfs2_jdesc describing the journal - * - * Acquire the journal's lock, check to see if the journal is clean, and - * do recovery if necessary. - * - * Returns: errno - */ +static int gfs2_recover_get_ref(struct slow_work *work) +{ + struct gfs2_jdesc *jd = container_of(work, struct gfs2_jdesc, jd_work); + if (test_and_set_bit(JDF_RECOVERY, &jd->jd_flags)) + return -EBUSY; + return 0; +} -int gfs2_recover_journal(struct gfs2_jdesc *jd) +static void gfs2_recover_put_ref(struct slow_work *work) +{ + struct gfs2_jdesc *jd = container_of(work, struct gfs2_jdesc, jd_work); + clear_bit(JDF_RECOVERY, &jd->jd_flags); + smp_mb__after_clear_bit(); + wake_up_bit(&jd->jd_flags, JDF_RECOVERY); +} + +static void gfs2_recover_work(struct slow_work *work) { + struct gfs2_jdesc *jd = container_of(work, struct gfs2_jdesc, jd_work); struct gfs2_inode *ip = GFS2_I(jd->jd_inode); struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode); struct gfs2_log_header_host head; @@ -569,7 +575,7 @@ int gfs2_recover_journal(struct gfs2_jdesc *jd) gfs2_glock_dq_uninit(&j_gh); fs_info(sdp, "jid=%u: Done\n", jd->jd_jid); - return 0; + return; fail_gunlock_tr: gfs2_glock_dq_uninit(&t_gh); @@ -584,70 +590,28 @@ fail_gunlock_j: fail: gfs2_recovery_done(sdp, jd->jd_jid, LM_RD_GAVEUP); - return error; } -static struct gfs2_jdesc *gfs2_jdesc_find_dirty(struct gfs2_sbd *sdp) -{ - struct gfs2_jdesc *jd; - int found = 0; - - spin_lock(&sdp->sd_jindex_spin); +struct slow_work_ops gfs2_recover_ops = { + .get_ref = gfs2_recover_get_ref, + .put_ref = gfs2_recover_put_ref, + .execute = gfs2_recover_work, +}; - list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) { - if (jd->jd_dirty) { - jd->jd_dirty = 0; - found = 1; - break; - } - } - spin_unlock(&sdp->sd_jindex_spin); - - if (!found) - jd = NULL; - return jd; -} - -/** - * gfs2_check_journals - Recover any dirty journals - * @sdp: the filesystem - * - */ - -static void gfs2_check_journals(struct gfs2_sbd *sdp) +static int gfs2_recovery_wait(void *word) { - struct gfs2_jdesc *jd; - - for (;;) { - jd = gfs2_jdesc_find_dirty(sdp); - if (!jd) - break; - - if (jd != sdp->sd_jdesc) - gfs2_recover_journal(jd); - } + schedule(); + return 0; } -/** - * gfs2_recoverd - Recover dead machine's journals - * @sdp: Pointer to GFS2 superblock - * - */ - -int gfs2_recoverd(void *data) +int gfs2_recover_journal(struct gfs2_jdesc *jd) { - struct gfs2_sbd *sdp = data; - unsigned long t; - - while (!kthread_should_stop()) { - gfs2_check_journals(sdp); - t = gfs2_tune_get(sdp, gt_recoverd_secs) * HZ; - if (freezing(current)) - refrigerator(); - schedule_timeout_interruptible(t); - } - + int rv; + rv = slow_work_enqueue(&jd->jd_work); + if (rv) + return rv; + wait_on_bit(&jd->jd_flags, JDF_RECOVERY, gfs2_recovery_wait, TASK_UNINTERRUPTIBLE); return 0; } diff --git a/fs/gfs2/recovery.h b/fs/gfs2/recovery.h index a8218ea15b57..1616ac22569a 100644 --- a/fs/gfs2/recovery.h +++ b/fs/gfs2/recovery.h @@ -28,7 +28,7 @@ extern void gfs2_revoke_clean(struct gfs2_sbd *sdp); extern int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head); extern int gfs2_recover_journal(struct gfs2_jdesc *gfs2_jd); -extern int gfs2_recoverd(void *data); +extern struct slow_work_ops gfs2_recover_ops; #endif /* __RECOVERY_DOT_H__ */ diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index 565038243fa2..daa4ae341a29 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -29,7 +29,7 @@ #include "util.h" #include "log.h" #include "inode.h" -#include "ops_address.h" +#include "trace_gfs2.h" #define BFITNOENT ((u32)~0) #define NO_BLOCK ((u64)~0) @@ -442,6 +442,7 @@ static int compute_bitstructs(struct gfs2_rgrpd *rgd) for (x = 0; x < length; x++) { bi = rgd->rd_bits + x; + bi->bi_flags = 0; /* small rgrp; bitmap stored completely in header block */ if (length == 1) { bytes = bytes_left; @@ -580,7 +581,6 @@ static int read_rindex_entry(struct gfs2_inode *ip, rgd->rd_gl->gl_object = rgd; rgd->rd_flags &= ~GFS2_RDF_UPTODATE; - rgd->rd_flags |= GFS2_RDF_CHECK; return error; } @@ -701,10 +701,9 @@ static void gfs2_rgrp_in(struct gfs2_rgrpd *rgd, const void *buf) u32 rg_flags; rg_flags = be32_to_cpu(str->rg_flags); - if (rg_flags & GFS2_RGF_NOALLOC) - rgd->rd_flags |= GFS2_RDF_NOALLOC; - else - rgd->rd_flags &= ~GFS2_RDF_NOALLOC; + rg_flags &= ~GFS2_RDF_MASK; + rgd->rd_flags &= GFS2_RDF_MASK; + rgd->rd_flags |= rg_flags; rgd->rd_free = be32_to_cpu(str->rg_free); rgd->rd_dinodes = be32_to_cpu(str->rg_dinodes); rgd->rd_igeneration = be64_to_cpu(str->rg_igeneration); @@ -713,11 +712,8 @@ static void gfs2_rgrp_in(struct gfs2_rgrpd *rgd, const void *buf) static void gfs2_rgrp_out(struct gfs2_rgrpd *rgd, void *buf) { struct gfs2_rgrp *str = buf; - u32 rg_flags = 0; - if (rgd->rd_flags & GFS2_RDF_NOALLOC) - rg_flags |= GFS2_RGF_NOALLOC; - str->rg_flags = cpu_to_be32(rg_flags); + str->rg_flags = cpu_to_be32(rgd->rd_flags & ~GFS2_RDF_MASK); str->rg_free = cpu_to_be32(rgd->rd_free); str->rg_dinodes = cpu_to_be32(rgd->rd_dinodes); str->__pad = cpu_to_be32(0); @@ -775,8 +771,10 @@ int gfs2_rgrp_bh_get(struct gfs2_rgrpd *rgd) } if (!(rgd->rd_flags & GFS2_RDF_UPTODATE)) { + for (x = 0; x < length; x++) + clear_bit(GBF_FULL, &rgd->rd_bits[x].bi_flags); gfs2_rgrp_in(rgd, (rgd->rd_bits[0].bi_bh)->b_data); - rgd->rd_flags |= GFS2_RDF_UPTODATE; + rgd->rd_flags |= (GFS2_RDF_UPTODATE | GFS2_RDF_CHECK); } spin_lock(&sdp->sd_rindex_spin); @@ -845,7 +843,7 @@ static void gfs2_rgrp_send_discards(struct gfs2_sbd *sdp, u64 offset, struct super_block *sb = sdp->sd_vfs; struct block_device *bdev = sb->s_bdev; const unsigned int sects_per_blk = sdp->sd_sb.sb_bsize / - bdev_hardsect_size(sb->s_bdev); + bdev_logical_block_size(sb->s_bdev); u64 blk; sector_t start = 0; sector_t nr_sects = 0; @@ -903,6 +901,7 @@ void gfs2_rgrp_repolish_clones(struct gfs2_rgrpd *rgd) continue; if (sdp->sd_args.ar_discard) gfs2_rgrp_send_discards(sdp, rgd->rd_data0, bi); + clear_bit(GBF_FULL, &bi->bi_flags); memcpy(bi->bi_clone + bi->bi_offset, bi->bi_bh->b_data + bi->bi_offset, bi->bi_len); } @@ -942,7 +941,7 @@ static int try_rgrp_fit(struct gfs2_rgrpd *rgd, struct gfs2_alloc *al) struct gfs2_sbd *sdp = rgd->rd_sbd; int ret = 0; - if (rgd->rd_flags & GFS2_RDF_NOALLOC) + if (rgd->rd_flags & (GFS2_RGF_NOALLOC | GFS2_RDF_ERROR)) return 0; spin_lock(&sdp->sd_rindex_spin); @@ -1315,30 +1314,37 @@ static u32 rgblk_search(struct gfs2_rgrpd *rgd, u32 goal, { struct gfs2_bitmap *bi = NULL; const u32 length = rgd->rd_length; - u32 blk = 0; + u32 blk = BFITNOENT; unsigned int buf, x; const unsigned int elen = *n; - const u8 *buffer; + const u8 *buffer = NULL; *n = 0; /* Find bitmap block that contains bits for goal block */ for (buf = 0; buf < length; buf++) { bi = rgd->rd_bits + buf; - if (goal < (bi->bi_start + bi->bi_len) * GFS2_NBBY) - break; + /* Convert scope of "goal" from rgrp-wide to within found bit block */ + if (goal < (bi->bi_start + bi->bi_len) * GFS2_NBBY) { + goal -= bi->bi_start * GFS2_NBBY; + goto do_search; + } } + buf = 0; + goal = 0; - gfs2_assert(rgd->rd_sbd, buf < length); - - /* Convert scope of "goal" from rgrp-wide to within found bit block */ - goal -= bi->bi_start * GFS2_NBBY; - +do_search: /* Search (up to entire) bitmap in this rgrp for allocatable block. "x <= length", instead of "x < length", because we typically start the search in the middle of a bit block, but if we can't find an allocatable block anywhere else, we want to be able wrap around and search in the first part of our first-searched bit block. */ for (x = 0; x <= length; x++) { + bi = rgd->rd_bits + buf; + + if (test_bit(GBF_FULL, &bi->bi_flags) && + (old_state == GFS2_BLKST_FREE)) + goto skip; + /* The GFS2_BLKST_UNLINKED state doesn't apply to the clone bitmaps, so we must search the originals for that. */ buffer = bi->bi_bh->b_data + bi->bi_offset; @@ -1349,33 +1355,39 @@ static u32 rgblk_search(struct gfs2_rgrpd *rgd, u32 goal, if (blk != BFITNOENT) break; + if ((goal == 0) && (old_state == GFS2_BLKST_FREE)) + set_bit(GBF_FULL, &bi->bi_flags); + /* Try next bitmap block (wrap back to rgrp header if at end) */ - buf = (buf + 1) % length; - bi = rgd->rd_bits + buf; +skip: + buf++; + buf %= length; goal = 0; } - if (blk != BFITNOENT && old_state != new_state) { - *n = 1; - gfs2_trans_add_bh(rgd->rd_gl, bi->bi_bh, 1); + if (blk == BFITNOENT) + return blk; + *n = 1; + if (old_state == new_state) + goto out; + + gfs2_trans_add_bh(rgd->rd_gl, bi->bi_bh, 1); + gfs2_setbit(rgd, bi->bi_bh->b_data, bi->bi_clone, bi->bi_offset, + bi->bi_len, blk, new_state); + goal = blk; + while (*n < elen) { + goal++; + if (goal >= (bi->bi_len * GFS2_NBBY)) + break; + if (gfs2_testbit(rgd, buffer, bi->bi_len, goal) != + GFS2_BLKST_FREE) + break; gfs2_setbit(rgd, bi->bi_bh->b_data, bi->bi_clone, bi->bi_offset, - bi->bi_len, blk, new_state); - goal = blk; - while (*n < elen) { - goal++; - if (goal >= (bi->bi_len * GFS2_NBBY)) - break; - if (gfs2_testbit(rgd, buffer, bi->bi_len, goal) != - GFS2_BLKST_FREE) - break; - gfs2_setbit(rgd, bi->bi_bh->b_data, bi->bi_clone, - bi->bi_offset, bi->bi_len, goal, - new_state); - (*n)++; - } + bi->bi_len, goal, new_state); + (*n)++; } - - return (blk == BFITNOENT) ? blk : (bi->bi_start * GFS2_NBBY) + blk; +out: + return (bi->bi_start * GFS2_NBBY) + blk; } /** @@ -1435,13 +1447,33 @@ static struct gfs2_rgrpd *rgblk_free(struct gfs2_sbd *sdp, u64 bstart, } /** - * gfs2_alloc_block - Allocate a block + * gfs2_rgrp_dump - print out an rgrp + * @seq: The iterator + * @gl: The glock in question + * + */ + +int gfs2_rgrp_dump(struct seq_file *seq, const struct gfs2_glock *gl) +{ + const struct gfs2_rgrpd *rgd = gl->gl_object; + if (rgd == NULL) + return 0; + gfs2_print_dbg(seq, " R: n:%llu f:%02x b:%u/%u i:%u\n", + (unsigned long long)rgd->rd_addr, rgd->rd_flags, + rgd->rd_free, rgd->rd_free_clone, rgd->rd_dinodes); + return 0; +} + +/** + * gfs2_alloc_block - Allocate one or more blocks * @ip: the inode to allocate the block for + * @bn: Used to return the starting block number + * @n: requested number of blocks/extent length (value/result) * - * Returns: the allocated block + * Returns: 0 or error */ -u64 gfs2_alloc_block(struct gfs2_inode *ip, unsigned int *n) +int gfs2_alloc_block(struct gfs2_inode *ip, u64 *bn, unsigned int *n) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct buffer_head *dibh; @@ -1457,7 +1489,10 @@ u64 gfs2_alloc_block(struct gfs2_inode *ip, unsigned int *n) goal = rgd->rd_last_alloc; blk = rgblk_search(rgd, goal, GFS2_BLKST_FREE, GFS2_BLKST_USED, n); - BUG_ON(blk == BFITNOENT); + + /* Since all blocks are reserved in advance, this shouldn't happen */ + if (blk == BFITNOENT) + goto rgrp_error; rgd->rd_last_alloc = blk; block = rgd->rd_data0 + blk; @@ -1469,7 +1504,9 @@ u64 gfs2_alloc_block(struct gfs2_inode *ip, unsigned int *n) di->di_goal_meta = di->di_goal_data = cpu_to_be64(ip->i_goal); brelse(dibh); } - gfs2_assert_withdraw(sdp, rgd->rd_free >= *n); + if (rgd->rd_free < *n) + goto rgrp_error; + rgd->rd_free -= *n; gfs2_trans_add_bh(rgd->rd_gl, rgd->rd_bits[0].bi_bh, 1); @@ -1483,8 +1520,17 @@ u64 gfs2_alloc_block(struct gfs2_inode *ip, unsigned int *n) spin_lock(&sdp->sd_rindex_spin); rgd->rd_free_clone -= *n; spin_unlock(&sdp->sd_rindex_spin); + trace_gfs2_block_alloc(ip, block, *n, GFS2_BLKST_USED); + *bn = block; + return 0; - return block; +rgrp_error: + fs_warn(sdp, "rgrp %llu has an error, marking it readonly until umount\n", + (unsigned long long)rgd->rd_addr); + fs_warn(sdp, "umount on all nodes and run fsck.gfs2 to fix the error\n"); + gfs2_rgrp_dump(NULL, rgd->rd_gl); + rgd->rd_flags |= GFS2_RDF_ERROR; + return -EIO; } /** @@ -1526,7 +1572,7 @@ u64 gfs2_alloc_di(struct gfs2_inode *dip, u64 *generation) spin_lock(&sdp->sd_rindex_spin); rgd->rd_free_clone--; spin_unlock(&sdp->sd_rindex_spin); - + trace_gfs2_block_alloc(dip, block, 1, GFS2_BLKST_DINODE); return block; } @@ -1546,7 +1592,7 @@ void gfs2_free_data(struct gfs2_inode *ip, u64 bstart, u32 blen) rgd = rgblk_free(sdp, bstart, blen, GFS2_BLKST_FREE); if (!rgd) return; - + trace_gfs2_block_alloc(ip, bstart, blen, GFS2_BLKST_FREE); rgd->rd_free += blen; gfs2_trans_add_bh(rgd->rd_gl, rgd->rd_bits[0].bi_bh, 1); @@ -1574,7 +1620,7 @@ void gfs2_free_meta(struct gfs2_inode *ip, u64 bstart, u32 blen) rgd = rgblk_free(sdp, bstart, blen, GFS2_BLKST_FREE); if (!rgd) return; - + trace_gfs2_block_alloc(ip, bstart, blen, GFS2_BLKST_FREE); rgd->rd_free += blen; gfs2_trans_add_bh(rgd->rd_gl, rgd->rd_bits[0].bi_bh, 1); @@ -1597,6 +1643,7 @@ void gfs2_unlink_di(struct inode *inode) rgd = rgblk_free(sdp, blkno, 1, GFS2_BLKST_UNLINKED); if (!rgd) return; + trace_gfs2_block_alloc(ip, blkno, 1, GFS2_BLKST_UNLINKED); gfs2_trans_add_bh(rgd->rd_gl, rgd->rd_bits[0].bi_bh, 1); gfs2_rgrp_out(rgd, rgd->rd_bits[0].bi_bh->b_data); gfs2_trans_add_rg(rgd); @@ -1628,6 +1675,7 @@ static void gfs2_free_uninit_di(struct gfs2_rgrpd *rgd, u64 blkno) void gfs2_free_di(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip) { gfs2_free_uninit_di(rgd, ip->i_no_addr); + trace_gfs2_block_alloc(ip, ip->i_no_addr, 1, GFS2_BLKST_FREE); gfs2_quota_change(ip, -1, ip->i_inode.i_uid, ip->i_inode.i_gid); gfs2_meta_wipe(ip, ip->i_no_addr, 1); } diff --git a/fs/gfs2/rgrp.h b/fs/gfs2/rgrp.h index 3181c7e624bf..1e76ff0f3e00 100644 --- a/fs/gfs2/rgrp.h +++ b/fs/gfs2/rgrp.h @@ -14,22 +14,22 @@ struct gfs2_rgrpd; struct gfs2_sbd; struct gfs2_holder; -void gfs2_rgrp_verify(struct gfs2_rgrpd *rgd); +extern void gfs2_rgrp_verify(struct gfs2_rgrpd *rgd); struct gfs2_rgrpd *gfs2_blk2rgrpd(struct gfs2_sbd *sdp, u64 blk); struct gfs2_rgrpd *gfs2_rgrpd_get_first(struct gfs2_sbd *sdp); struct gfs2_rgrpd *gfs2_rgrpd_get_next(struct gfs2_rgrpd *rgd); -void gfs2_clear_rgrpd(struct gfs2_sbd *sdp); -int gfs2_rindex_hold(struct gfs2_sbd *sdp, struct gfs2_holder *ri_gh); +extern void gfs2_clear_rgrpd(struct gfs2_sbd *sdp); +extern int gfs2_rindex_hold(struct gfs2_sbd *sdp, struct gfs2_holder *ri_gh); -int gfs2_rgrp_bh_get(struct gfs2_rgrpd *rgd); -void gfs2_rgrp_bh_hold(struct gfs2_rgrpd *rgd); -void gfs2_rgrp_bh_put(struct gfs2_rgrpd *rgd); +extern int gfs2_rgrp_bh_get(struct gfs2_rgrpd *rgd); +extern void gfs2_rgrp_bh_hold(struct gfs2_rgrpd *rgd); +extern void gfs2_rgrp_bh_put(struct gfs2_rgrpd *rgd); -void gfs2_rgrp_repolish_clones(struct gfs2_rgrpd *rgd); +extern void gfs2_rgrp_repolish_clones(struct gfs2_rgrpd *rgd); -struct gfs2_alloc *gfs2_alloc_get(struct gfs2_inode *ip); +extern struct gfs2_alloc *gfs2_alloc_get(struct gfs2_inode *ip); static inline void gfs2_alloc_put(struct gfs2_inode *ip) { BUG_ON(ip->i_alloc == NULL); @@ -37,22 +37,22 @@ static inline void gfs2_alloc_put(struct gfs2_inode *ip) ip->i_alloc = NULL; } -int gfs2_inplace_reserve_i(struct gfs2_inode *ip, - char *file, unsigned int line); +extern int gfs2_inplace_reserve_i(struct gfs2_inode *ip, char *file, + unsigned int line); #define gfs2_inplace_reserve(ip) \ gfs2_inplace_reserve_i((ip), __FILE__, __LINE__) -void gfs2_inplace_release(struct gfs2_inode *ip); +extern void gfs2_inplace_release(struct gfs2_inode *ip); -unsigned char gfs2_get_block_type(struct gfs2_rgrpd *rgd, u64 block); +extern unsigned char gfs2_get_block_type(struct gfs2_rgrpd *rgd, u64 block); -u64 gfs2_alloc_block(struct gfs2_inode *ip, unsigned int *n); -u64 gfs2_alloc_di(struct gfs2_inode *ip, u64 *generation); +extern int gfs2_alloc_block(struct gfs2_inode *ip, u64 *bn, unsigned int *n); +extern u64 gfs2_alloc_di(struct gfs2_inode *ip, u64 *generation); -void gfs2_free_data(struct gfs2_inode *ip, u64 bstart, u32 blen); -void gfs2_free_meta(struct gfs2_inode *ip, u64 bstart, u32 blen); -void gfs2_free_di(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip); -void gfs2_unlink_di(struct inode *inode); +extern void gfs2_free_data(struct gfs2_inode *ip, u64 bstart, u32 blen); +extern void gfs2_free_meta(struct gfs2_inode *ip, u64 bstart, u32 blen); +extern void gfs2_free_di(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip); +extern void gfs2_unlink_di(struct inode *inode); struct gfs2_rgrp_list { unsigned int rl_rgrps; @@ -61,10 +61,11 @@ struct gfs2_rgrp_list { struct gfs2_holder *rl_ghs; }; -void gfs2_rlist_add(struct gfs2_sbd *sdp, struct gfs2_rgrp_list *rlist, - u64 block); -void gfs2_rlist_alloc(struct gfs2_rgrp_list *rlist, unsigned int state); -void gfs2_rlist_free(struct gfs2_rgrp_list *rlist); -u64 gfs2_ri_total(struct gfs2_sbd *sdp); +extern void gfs2_rlist_add(struct gfs2_sbd *sdp, struct gfs2_rgrp_list *rlist, + u64 block); +extern void gfs2_rlist_alloc(struct gfs2_rgrp_list *rlist, unsigned int state); +extern void gfs2_rlist_free(struct gfs2_rgrp_list *rlist); +extern u64 gfs2_ri_total(struct gfs2_sbd *sdp); +extern int gfs2_rgrp_dump(struct seq_file *seq, const struct gfs2_glock *gl); #endif /* __RGRP_DOT_H__ */ diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index 601913e0a482..0a6801336470 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -7,14 +7,20 @@ * of the GNU General Public License version 2. */ +#include <linux/bio.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/completion.h> #include <linux/buffer_head.h> -#include <linux/crc32.h> +#include <linux/statfs.h> +#include <linux/seq_file.h> +#include <linux/mount.h> +#include <linux/kthread.h> +#include <linux/delay.h> #include <linux/gfs2_ondisk.h> -#include <linux/bio.h> +#include <linux/crc32.h> +#include <linux/time.h> #include "gfs2.h" #include "incore.h" @@ -31,6 +37,183 @@ #include "super.h" #include "trans.h" #include "util.h" +#include "sys.h" +#include "eattr.h" + +#define args_neq(a1, a2, x) ((a1)->ar_##x != (a2)->ar_##x) + +enum { + Opt_lockproto, + Opt_locktable, + Opt_hostdata, + Opt_spectator, + Opt_ignore_local_fs, + Opt_localflocks, + Opt_localcaching, + Opt_debug, + Opt_nodebug, + Opt_upgrade, + Opt_acl, + Opt_noacl, + Opt_quota_off, + Opt_quota_account, + Opt_quota_on, + Opt_quota, + Opt_noquota, + Opt_suiddir, + Opt_nosuiddir, + Opt_data_writeback, + Opt_data_ordered, + Opt_meta, + Opt_discard, + Opt_nodiscard, + Opt_commit, + Opt_error, +}; + +static const match_table_t tokens = { + {Opt_lockproto, "lockproto=%s"}, + {Opt_locktable, "locktable=%s"}, + {Opt_hostdata, "hostdata=%s"}, + {Opt_spectator, "spectator"}, + {Opt_ignore_local_fs, "ignore_local_fs"}, + {Opt_localflocks, "localflocks"}, + {Opt_localcaching, "localcaching"}, + {Opt_debug, "debug"}, + {Opt_nodebug, "nodebug"}, + {Opt_upgrade, "upgrade"}, + {Opt_acl, "acl"}, + {Opt_noacl, "noacl"}, + {Opt_quota_off, "quota=off"}, + {Opt_quota_account, "quota=account"}, + {Opt_quota_on, "quota=on"}, + {Opt_quota, "quota"}, + {Opt_noquota, "noquota"}, + {Opt_suiddir, "suiddir"}, + {Opt_nosuiddir, "nosuiddir"}, + {Opt_data_writeback, "data=writeback"}, + {Opt_data_ordered, "data=ordered"}, + {Opt_meta, "meta"}, + {Opt_discard, "discard"}, + {Opt_nodiscard, "nodiscard"}, + {Opt_commit, "commit=%d"}, + {Opt_error, NULL} +}; + +/** + * gfs2_mount_args - Parse mount options + * @sdp: + * @data: + * + * Return: errno + */ + +int gfs2_mount_args(struct gfs2_sbd *sdp, struct gfs2_args *args, char *options) +{ + char *o; + int token; + substring_t tmp[MAX_OPT_ARGS]; + int rv; + + /* Split the options into tokens with the "," character and + process them */ + + while (1) { + o = strsep(&options, ","); + if (o == NULL) + break; + if (*o == '\0') + continue; + + token = match_token(o, tokens, tmp); + switch (token) { + case Opt_lockproto: + match_strlcpy(args->ar_lockproto, &tmp[0], + GFS2_LOCKNAME_LEN); + break; + case Opt_locktable: + match_strlcpy(args->ar_locktable, &tmp[0], + GFS2_LOCKNAME_LEN); + break; + case Opt_hostdata: + match_strlcpy(args->ar_hostdata, &tmp[0], + GFS2_LOCKNAME_LEN); + break; + case Opt_spectator: + args->ar_spectator = 1; + break; + case Opt_ignore_local_fs: + args->ar_ignore_local_fs = 1; + break; + case Opt_localflocks: + args->ar_localflocks = 1; + break; + case Opt_localcaching: + args->ar_localcaching = 1; + break; + case Opt_debug: + args->ar_debug = 1; + break; + case Opt_nodebug: + args->ar_debug = 0; + break; + case Opt_upgrade: + args->ar_upgrade = 1; + break; + case Opt_acl: + args->ar_posix_acl = 1; + break; + case Opt_noacl: + args->ar_posix_acl = 0; + break; + case Opt_quota_off: + case Opt_noquota: + args->ar_quota = GFS2_QUOTA_OFF; + break; + case Opt_quota_account: + args->ar_quota = GFS2_QUOTA_ACCOUNT; + break; + case Opt_quota_on: + case Opt_quota: + args->ar_quota = GFS2_QUOTA_ON; + break; + case Opt_suiddir: + args->ar_suiddir = 1; + break; + case Opt_nosuiddir: + args->ar_suiddir = 0; + break; + case Opt_data_writeback: + args->ar_data = GFS2_DATA_WRITEBACK; + break; + case Opt_data_ordered: + args->ar_data = GFS2_DATA_ORDERED; + break; + case Opt_meta: + args->ar_meta = 1; + break; + case Opt_discard: + args->ar_discard = 1; + break; + case Opt_nodiscard: + args->ar_discard = 0; + break; + case Opt_commit: + rv = match_int(&tmp[0], &args->ar_commit); + if (rv || args->ar_commit <= 0) { + fs_info(sdp, "commit mount option requires a positive numeric argument\n"); + return rv ? rv : -EINVAL; + } + break; + case Opt_error: + default: + fs_info(sdp, "invalid mount option: %s\n", o); + return -EINVAL; + } + } + + return 0; +} /** * gfs2_jindex_free - Clear all the journal index information @@ -436,3 +619,706 @@ void gfs2_unfreeze_fs(struct gfs2_sbd *sdp) mutex_unlock(&sdp->sd_freeze_lock); } + +/** + * gfs2_write_inode - Make sure the inode is stable on the disk + * @inode: The inode + * @sync: synchronous write flag + * + * Returns: errno + */ + +static int gfs2_write_inode(struct inode *inode, int sync) +{ + struct gfs2_inode *ip = GFS2_I(inode); + struct gfs2_sbd *sdp = GFS2_SB(inode); + struct gfs2_holder gh; + struct buffer_head *bh; + struct timespec atime; + struct gfs2_dinode *di; + int ret = 0; + + /* Check this is a "normal" inode, etc */ + if (!test_bit(GIF_USER, &ip->i_flags) || + (current->flags & PF_MEMALLOC)) + return 0; + ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh); + if (ret) + goto do_flush; + ret = gfs2_trans_begin(sdp, RES_DINODE, 0); + if (ret) + goto do_unlock; + ret = gfs2_meta_inode_buffer(ip, &bh); + if (ret == 0) { + di = (struct gfs2_dinode *)bh->b_data; + atime.tv_sec = be64_to_cpu(di->di_atime); + atime.tv_nsec = be32_to_cpu(di->di_atime_nsec); + if (timespec_compare(&inode->i_atime, &atime) > 0) { + gfs2_trans_add_bh(ip->i_gl, bh, 1); + gfs2_dinode_out(ip, bh->b_data); + } + brelse(bh); + } + gfs2_trans_end(sdp); +do_unlock: + gfs2_glock_dq_uninit(&gh); +do_flush: + if (sync != 0) + gfs2_log_flush(GFS2_SB(inode), ip->i_gl); + return ret; +} + +/** + * gfs2_make_fs_ro - Turn a Read-Write FS into a Read-Only one + * @sdp: the filesystem + * + * Returns: errno + */ + +static int gfs2_make_fs_ro(struct gfs2_sbd *sdp) +{ + struct gfs2_holder t_gh; + int error; + + gfs2_quota_sync(sdp); + gfs2_statfs_sync(sdp); + + error = gfs2_glock_nq_init(sdp->sd_trans_gl, LM_ST_SHARED, GL_NOCACHE, + &t_gh); + if (error && !test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) + return error; + + gfs2_meta_syncfs(sdp); + gfs2_log_shutdown(sdp); + + clear_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags); + + if (t_gh.gh_gl) + gfs2_glock_dq_uninit(&t_gh); + + gfs2_quota_cleanup(sdp); + + return error; +} + +static int gfs2_umount_recovery_wait(void *word) +{ + schedule(); + return 0; +} + +/** + * gfs2_put_super - Unmount the filesystem + * @sb: The VFS superblock + * + */ + +static void gfs2_put_super(struct super_block *sb) +{ + struct gfs2_sbd *sdp = sb->s_fs_info; + int error; + struct gfs2_jdesc *jd; + + /* Unfreeze the filesystem, if we need to */ + + mutex_lock(&sdp->sd_freeze_lock); + if (sdp->sd_freeze_count) + gfs2_glock_dq_uninit(&sdp->sd_freeze_gh); + mutex_unlock(&sdp->sd_freeze_lock); + + /* No more recovery requests */ + set_bit(SDF_NORECOVERY, &sdp->sd_flags); + smp_mb(); + + /* Wait on outstanding recovery */ +restart: + spin_lock(&sdp->sd_jindex_spin); + list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) { + if (!test_bit(JDF_RECOVERY, &jd->jd_flags)) + continue; + spin_unlock(&sdp->sd_jindex_spin); + wait_on_bit(&jd->jd_flags, JDF_RECOVERY, + gfs2_umount_recovery_wait, TASK_UNINTERRUPTIBLE); + goto restart; + } + spin_unlock(&sdp->sd_jindex_spin); + + kthread_stop(sdp->sd_quotad_process); + kthread_stop(sdp->sd_logd_process); + + if (!(sb->s_flags & MS_RDONLY)) { + error = gfs2_make_fs_ro(sdp); + if (error) + gfs2_io_error(sdp); + } + /* At this point, we're through modifying the disk */ + + /* Release stuff */ + + iput(sdp->sd_jindex); + iput(sdp->sd_inum_inode); + iput(sdp->sd_statfs_inode); + iput(sdp->sd_rindex); + iput(sdp->sd_quota_inode); + + gfs2_glock_put(sdp->sd_rename_gl); + gfs2_glock_put(sdp->sd_trans_gl); + + if (!sdp->sd_args.ar_spectator) { + gfs2_glock_dq_uninit(&sdp->sd_journal_gh); + gfs2_glock_dq_uninit(&sdp->sd_jinode_gh); + gfs2_glock_dq_uninit(&sdp->sd_ir_gh); + gfs2_glock_dq_uninit(&sdp->sd_sc_gh); + gfs2_glock_dq_uninit(&sdp->sd_qc_gh); + iput(sdp->sd_ir_inode); + iput(sdp->sd_sc_inode); + iput(sdp->sd_qc_inode); + } + + gfs2_glock_dq_uninit(&sdp->sd_live_gh); + gfs2_clear_rgrpd(sdp); + gfs2_jindex_free(sdp); + /* Take apart glock structures and buffer lists */ + gfs2_gl_hash_clear(sdp); + /* Unmount the locking protocol */ + gfs2_lm_unmount(sdp); + + /* At this point, we're through participating in the lockspace */ + gfs2_sys_fs_del(sdp); +} + +/** + * gfs2_sync_fs - sync the filesystem + * @sb: the superblock + * + * Flushes the log to disk. + */ + +static int gfs2_sync_fs(struct super_block *sb, int wait) +{ + if (wait && sb->s_fs_info) + gfs2_log_flush(sb->s_fs_info, NULL); + return 0; +} + +/** + * gfs2_freeze - prevent further writes to the filesystem + * @sb: the VFS structure for the filesystem + * + */ + +static int gfs2_freeze(struct super_block *sb) +{ + struct gfs2_sbd *sdp = sb->s_fs_info; + int error; + + if (test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) + return -EINVAL; + + for (;;) { + error = gfs2_freeze_fs(sdp); + if (!error) + break; + + switch (error) { + case -EBUSY: + fs_err(sdp, "waiting for recovery before freeze\n"); + break; + + default: + fs_err(sdp, "error freezing FS: %d\n", error); + break; + } + + fs_err(sdp, "retrying...\n"); + msleep(1000); + } + return 0; +} + +/** + * gfs2_unfreeze - reallow writes to the filesystem + * @sb: the VFS structure for the filesystem + * + */ + +static int gfs2_unfreeze(struct super_block *sb) +{ + gfs2_unfreeze_fs(sb->s_fs_info); + return 0; +} + +/** + * statfs_fill - fill in the sg for a given RG + * @rgd: the RG + * @sc: the sc structure + * + * Returns: 0 on success, -ESTALE if the LVB is invalid + */ + +static int statfs_slow_fill(struct gfs2_rgrpd *rgd, + struct gfs2_statfs_change_host *sc) +{ + gfs2_rgrp_verify(rgd); + sc->sc_total += rgd->rd_data; + sc->sc_free += rgd->rd_free; + sc->sc_dinodes += rgd->rd_dinodes; + return 0; +} + +/** + * gfs2_statfs_slow - Stat a filesystem using asynchronous locking + * @sdp: the filesystem + * @sc: the sc info that will be returned + * + * Any error (other than a signal) will cause this routine to fall back + * to the synchronous version. + * + * FIXME: This really shouldn't busy wait like this. + * + * Returns: errno + */ + +static int gfs2_statfs_slow(struct gfs2_sbd *sdp, struct gfs2_statfs_change_host *sc) +{ + struct gfs2_holder ri_gh; + struct gfs2_rgrpd *rgd_next; + struct gfs2_holder *gha, *gh; + unsigned int slots = 64; + unsigned int x; + int done; + int error = 0, err; + + memset(sc, 0, sizeof(struct gfs2_statfs_change_host)); + gha = kcalloc(slots, sizeof(struct gfs2_holder), GFP_KERNEL); + if (!gha) + return -ENOMEM; + + error = gfs2_rindex_hold(sdp, &ri_gh); + if (error) + goto out; + + rgd_next = gfs2_rgrpd_get_first(sdp); + + for (;;) { + done = 1; + + for (x = 0; x < slots; x++) { + gh = gha + x; + + if (gh->gh_gl && gfs2_glock_poll(gh)) { + err = gfs2_glock_wait(gh); + if (err) { + gfs2_holder_uninit(gh); + error = err; + } else { + if (!error) + error = statfs_slow_fill( + gh->gh_gl->gl_object, sc); + gfs2_glock_dq_uninit(gh); + } + } + + if (gh->gh_gl) + done = 0; + else if (rgd_next && !error) { + error = gfs2_glock_nq_init(rgd_next->rd_gl, + LM_ST_SHARED, + GL_ASYNC, + gh); + rgd_next = gfs2_rgrpd_get_next(rgd_next); + done = 0; + } + + if (signal_pending(current)) + error = -ERESTARTSYS; + } + + if (done) + break; + + yield(); + } + + gfs2_glock_dq_uninit(&ri_gh); + +out: + kfree(gha); + return error; +} + +/** + * gfs2_statfs_i - Do a statfs + * @sdp: the filesystem + * @sg: the sg structure + * + * Returns: errno + */ + +static int gfs2_statfs_i(struct gfs2_sbd *sdp, struct gfs2_statfs_change_host *sc) +{ + struct gfs2_statfs_change_host *m_sc = &sdp->sd_statfs_master; + struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local; + + spin_lock(&sdp->sd_statfs_spin); + + *sc = *m_sc; + sc->sc_total += l_sc->sc_total; + sc->sc_free += l_sc->sc_free; + sc->sc_dinodes += l_sc->sc_dinodes; + + spin_unlock(&sdp->sd_statfs_spin); + + if (sc->sc_free < 0) + sc->sc_free = 0; + if (sc->sc_free > sc->sc_total) + sc->sc_free = sc->sc_total; + if (sc->sc_dinodes < 0) + sc->sc_dinodes = 0; + + return 0; +} + +/** + * gfs2_statfs - Gather and return stats about the filesystem + * @sb: The superblock + * @statfsbuf: The buffer + * + * Returns: 0 on success or error code + */ + +static int gfs2_statfs(struct dentry *dentry, struct kstatfs *buf) +{ + struct super_block *sb = dentry->d_inode->i_sb; + struct gfs2_sbd *sdp = sb->s_fs_info; + struct gfs2_statfs_change_host sc; + int error; + + if (gfs2_tune_get(sdp, gt_statfs_slow)) + error = gfs2_statfs_slow(sdp, &sc); + else + error = gfs2_statfs_i(sdp, &sc); + + if (error) + return error; + + buf->f_type = GFS2_MAGIC; + buf->f_bsize = sdp->sd_sb.sb_bsize; + buf->f_blocks = sc.sc_total; + buf->f_bfree = sc.sc_free; + buf->f_bavail = sc.sc_free; + buf->f_files = sc.sc_dinodes + sc.sc_free; + buf->f_ffree = sc.sc_free; + buf->f_namelen = GFS2_FNAMESIZE; + + return 0; +} + +/** + * gfs2_remount_fs - called when the FS is remounted + * @sb: the filesystem + * @flags: the remount flags + * @data: extra data passed in (not used right now) + * + * Returns: errno + */ + +static int gfs2_remount_fs(struct super_block *sb, int *flags, char *data) +{ + struct gfs2_sbd *sdp = sb->s_fs_info; + struct gfs2_args args = sdp->sd_args; /* Default to current settings */ + struct gfs2_tune *gt = &sdp->sd_tune; + int error; + + spin_lock(>->gt_spin); + args.ar_commit = gt->gt_log_flush_secs; + spin_unlock(>->gt_spin); + error = gfs2_mount_args(sdp, &args, data); + if (error) + return error; + + /* Not allowed to change locking details */ + if (strcmp(args.ar_lockproto, sdp->sd_args.ar_lockproto) || + strcmp(args.ar_locktable, sdp->sd_args.ar_locktable) || + strcmp(args.ar_hostdata, sdp->sd_args.ar_hostdata)) + return -EINVAL; + + /* Some flags must not be changed */ + if (args_neq(&args, &sdp->sd_args, spectator) || + args_neq(&args, &sdp->sd_args, ignore_local_fs) || + args_neq(&args, &sdp->sd_args, localflocks) || + args_neq(&args, &sdp->sd_args, localcaching) || + args_neq(&args, &sdp->sd_args, meta)) + return -EINVAL; + + if (sdp->sd_args.ar_spectator) + *flags |= MS_RDONLY; + + if ((sb->s_flags ^ *flags) & MS_RDONLY) { + if (*flags & MS_RDONLY) + error = gfs2_make_fs_ro(sdp); + else + error = gfs2_make_fs_rw(sdp); + if (error) + return error; + } + + sdp->sd_args = args; + if (sdp->sd_args.ar_posix_acl) + sb->s_flags |= MS_POSIXACL; + else + sb->s_flags &= ~MS_POSIXACL; + spin_lock(>->gt_spin); + gt->gt_log_flush_secs = args.ar_commit; + spin_unlock(>->gt_spin); + + return 0; +} + +/** + * gfs2_drop_inode - Drop an inode (test for remote unlink) + * @inode: The inode to drop + * + * If we've received a callback on an iopen lock then its because a + * remote node tried to deallocate the inode but failed due to this node + * still having the inode open. Here we mark the link count zero + * since we know that it must have reached zero if the GLF_DEMOTE flag + * is set on the iopen glock. If we didn't do a disk read since the + * remote node removed the final link then we might otherwise miss + * this event. This check ensures that this node will deallocate the + * inode's blocks, or alternatively pass the baton on to another + * node for later deallocation. + */ + +static void gfs2_drop_inode(struct inode *inode) +{ + struct gfs2_inode *ip = GFS2_I(inode); + + if (test_bit(GIF_USER, &ip->i_flags) && inode->i_nlink) { + struct gfs2_glock *gl = ip->i_iopen_gh.gh_gl; + if (gl && test_bit(GLF_DEMOTE, &gl->gl_flags)) + clear_nlink(inode); + } + generic_drop_inode(inode); +} + +/** + * gfs2_clear_inode - Deallocate an inode when VFS is done with it + * @inode: The VFS inode + * + */ + +static void gfs2_clear_inode(struct inode *inode) +{ + struct gfs2_inode *ip = GFS2_I(inode); + + /* This tells us its a "real" inode and not one which only + * serves to contain an address space (see rgrp.c, meta_io.c) + * which therefore doesn't have its own glocks. + */ + if (test_bit(GIF_USER, &ip->i_flags)) { + ip->i_gl->gl_object = NULL; + gfs2_glock_put(ip->i_gl); + ip->i_gl = NULL; + if (ip->i_iopen_gh.gh_gl) { + ip->i_iopen_gh.gh_gl->gl_object = NULL; + gfs2_glock_dq_uninit(&ip->i_iopen_gh); + } + } +} + +static int is_ancestor(const struct dentry *d1, const struct dentry *d2) +{ + do { + if (d1 == d2) + return 1; + d1 = d1->d_parent; + } while (!IS_ROOT(d1)); + return 0; +} + +/** + * gfs2_show_options - Show mount options for /proc/mounts + * @s: seq_file structure + * @mnt: vfsmount + * + * Returns: 0 on success or error code + */ + +static int gfs2_show_options(struct seq_file *s, struct vfsmount *mnt) +{ + struct gfs2_sbd *sdp = mnt->mnt_sb->s_fs_info; + struct gfs2_args *args = &sdp->sd_args; + int lfsecs; + + if (is_ancestor(mnt->mnt_root, sdp->sd_master_dir)) + seq_printf(s, ",meta"); + if (args->ar_lockproto[0]) + seq_printf(s, ",lockproto=%s", args->ar_lockproto); + if (args->ar_locktable[0]) + seq_printf(s, ",locktable=%s", args->ar_locktable); + if (args->ar_hostdata[0]) + seq_printf(s, ",hostdata=%s", args->ar_hostdata); + if (args->ar_spectator) + seq_printf(s, ",spectator"); + if (args->ar_ignore_local_fs) + seq_printf(s, ",ignore_local_fs"); + if (args->ar_localflocks) + seq_printf(s, ",localflocks"); + if (args->ar_localcaching) + seq_printf(s, ",localcaching"); + if (args->ar_debug) + seq_printf(s, ",debug"); + if (args->ar_upgrade) + seq_printf(s, ",upgrade"); + if (args->ar_posix_acl) + seq_printf(s, ",acl"); + if (args->ar_quota != GFS2_QUOTA_DEFAULT) { + char *state; + switch (args->ar_quota) { + case GFS2_QUOTA_OFF: + state = "off"; + break; + case GFS2_QUOTA_ACCOUNT: + state = "account"; + break; + case GFS2_QUOTA_ON: + state = "on"; + break; + default: + state = "unknown"; + break; + } + seq_printf(s, ",quota=%s", state); + } + if (args->ar_suiddir) + seq_printf(s, ",suiddir"); + if (args->ar_data != GFS2_DATA_DEFAULT) { + char *state; + switch (args->ar_data) { + case GFS2_DATA_WRITEBACK: + state = "writeback"; + break; + case GFS2_DATA_ORDERED: + state = "ordered"; + break; + default: + state = "unknown"; + break; + } + seq_printf(s, ",data=%s", state); + } + if (args->ar_discard) + seq_printf(s, ",discard"); + lfsecs = sdp->sd_tune.gt_log_flush_secs; + if (lfsecs != 60) + seq_printf(s, ",commit=%d", lfsecs); + return 0; +} + +/* + * We have to (at the moment) hold the inodes main lock to cover + * the gap between unlocking the shared lock on the iopen lock and + * taking the exclusive lock. I'd rather do a shared -> exclusive + * conversion on the iopen lock, but we can change that later. This + * is safe, just less efficient. + */ + +static void gfs2_delete_inode(struct inode *inode) +{ + struct gfs2_sbd *sdp = inode->i_sb->s_fs_info; + struct gfs2_inode *ip = GFS2_I(inode); + struct gfs2_holder gh; + int error; + + if (!test_bit(GIF_USER, &ip->i_flags)) + goto out; + + error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh); + if (unlikely(error)) { + gfs2_glock_dq_uninit(&ip->i_iopen_gh); + goto out; + } + + gfs2_glock_dq_wait(&ip->i_iopen_gh); + gfs2_holder_reinit(LM_ST_EXCLUSIVE, LM_FLAG_TRY_1CB | GL_NOCACHE, &ip->i_iopen_gh); + error = gfs2_glock_nq(&ip->i_iopen_gh); + if (error) + goto out_truncate; + + if (S_ISDIR(inode->i_mode) && + (ip->i_diskflags & GFS2_DIF_EXHASH)) { + error = gfs2_dir_exhash_dealloc(ip); + if (error) + goto out_unlock; + } + + if (ip->i_eattr) { + error = gfs2_ea_dealloc(ip); + if (error) + goto out_unlock; + } + + if (!gfs2_is_stuffed(ip)) { + error = gfs2_file_dealloc(ip); + if (error) + goto out_unlock; + } + + error = gfs2_dinode_dealloc(ip); + if (error) + goto out_unlock; + +out_truncate: + error = gfs2_trans_begin(sdp, 0, sdp->sd_jdesc->jd_blocks); + if (error) + goto out_unlock; + /* Needs to be done before glock release & also in a transaction */ + truncate_inode_pages(&inode->i_data, 0); + gfs2_trans_end(sdp); + +out_unlock: + if (test_bit(HIF_HOLDER, &ip->i_iopen_gh.gh_iflags)) + gfs2_glock_dq(&ip->i_iopen_gh); + gfs2_holder_uninit(&ip->i_iopen_gh); + gfs2_glock_dq_uninit(&gh); + if (error && error != GLR_TRYFAILED && error != -EROFS) + fs_warn(sdp, "gfs2_delete_inode: %d\n", error); +out: + truncate_inode_pages(&inode->i_data, 0); + clear_inode(inode); +} + +static struct inode *gfs2_alloc_inode(struct super_block *sb) +{ + struct gfs2_inode *ip; + + ip = kmem_cache_alloc(gfs2_inode_cachep, GFP_KERNEL); + if (ip) { + ip->i_flags = 0; + ip->i_gl = NULL; + } + return &ip->i_inode; +} + +static void gfs2_destroy_inode(struct inode *inode) +{ + kmem_cache_free(gfs2_inode_cachep, inode); +} + +const struct super_operations gfs2_super_ops = { + .alloc_inode = gfs2_alloc_inode, + .destroy_inode = gfs2_destroy_inode, + .write_inode = gfs2_write_inode, + .delete_inode = gfs2_delete_inode, + .put_super = gfs2_put_super, + .sync_fs = gfs2_sync_fs, + .freeze_fs = gfs2_freeze, + .unfreeze_fs = gfs2_unfreeze, + .statfs = gfs2_statfs, + .remount_fs = gfs2_remount_fs, + .clear_inode = gfs2_clear_inode, + .drop_inode = gfs2_drop_inode, + .show_options = gfs2_show_options, +}; + diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c index 7655f5025fec..23419dc3027b 100644 --- a/fs/gfs2/sys.c +++ b/fs/gfs2/sys.c @@ -26,6 +26,36 @@ #include "util.h" #include "glops.h" +struct gfs2_attr { + struct attribute attr; + ssize_t (*show)(struct gfs2_sbd *, char *); + ssize_t (*store)(struct gfs2_sbd *, const char *, size_t); +}; + +static ssize_t gfs2_attr_show(struct kobject *kobj, struct attribute *attr, + char *buf) +{ + struct gfs2_sbd *sdp = container_of(kobj, struct gfs2_sbd, sd_kobj); + struct gfs2_attr *a = container_of(attr, struct gfs2_attr, attr); + return a->show ? a->show(sdp, buf) : 0; +} + +static ssize_t gfs2_attr_store(struct kobject *kobj, struct attribute *attr, + const char *buf, size_t len) +{ + struct gfs2_sbd *sdp = container_of(kobj, struct gfs2_sbd, sd_kobj); + struct gfs2_attr *a = container_of(attr, struct gfs2_attr, attr); + return a->store ? a->store(sdp, buf, len) : len; +} + +static struct sysfs_ops gfs2_attr_ops = { + .show = gfs2_attr_show, + .store = gfs2_attr_store, +}; + + +static struct kset *gfs2_kset; + static ssize_t id_show(struct gfs2_sbd *sdp, char *buf) { return snprintf(buf, PAGE_SIZE, "%u:%u\n", @@ -212,11 +242,6 @@ static ssize_t demote_rq_store(struct gfs2_sbd *sdp, const char *buf, size_t len return len; } -struct gfs2_attr { - struct attribute attr; - ssize_t (*show)(struct gfs2_sbd *, char *); - ssize_t (*store)(struct gfs2_sbd *, const char *, size_t); -}; #define GFS2_ATTR(name, mode, show, store) \ static struct gfs2_attr gfs2_attr_##name = __ATTR(name, mode, show, store) @@ -246,58 +271,11 @@ static struct attribute *gfs2_attrs[] = { NULL, }; -static ssize_t gfs2_attr_show(struct kobject *kobj, struct attribute *attr, - char *buf) -{ - struct gfs2_sbd *sdp = container_of(kobj, struct gfs2_sbd, sd_kobj); - struct gfs2_attr *a = container_of(attr, struct gfs2_attr, attr); - return a->show ? a->show(sdp, buf) : 0; -} - -static ssize_t gfs2_attr_store(struct kobject *kobj, struct attribute *attr, - const char *buf, size_t len) -{ - struct gfs2_sbd *sdp = container_of(kobj, struct gfs2_sbd, sd_kobj); - struct gfs2_attr *a = container_of(attr, struct gfs2_attr, attr); - return a->store ? a->store(sdp, buf, len) : len; -} - -static struct sysfs_ops gfs2_attr_ops = { - .show = gfs2_attr_show, - .store = gfs2_attr_store, -}; - static struct kobj_type gfs2_ktype = { .default_attrs = gfs2_attrs, .sysfs_ops = &gfs2_attr_ops, }; -static struct kset *gfs2_kset; - -/* - * display struct lm_lockstruct fields - */ - -struct lockstruct_attr { - struct attribute attr; - ssize_t (*show)(struct gfs2_sbd *, char *); -}; - -#define LOCKSTRUCT_ATTR(name, fmt) \ -static ssize_t name##_show(struct gfs2_sbd *sdp, char *buf) \ -{ \ - return snprintf(buf, PAGE_SIZE, fmt, sdp->sd_lockstruct.ls_##name); \ -} \ -static struct lockstruct_attr lockstruct_attr_##name = __ATTR_RO(name) - -LOCKSTRUCT_ATTR(jid, "%u\n"); -LOCKSTRUCT_ATTR(first, "%u\n"); - -static struct attribute *lockstruct_attrs[] = { - &lockstruct_attr_jid.attr, - &lockstruct_attr_first.attr, - NULL, -}; /* * lock_module. Originally from lock_dlm @@ -359,34 +337,33 @@ static ssize_t first_done_show(struct gfs2_sbd *sdp, char *buf) return sprintf(buf, "%d\n", ls->ls_first_done); } -static ssize_t recover_show(struct gfs2_sbd *sdp, char *buf) -{ - struct lm_lockstruct *ls = &sdp->sd_lockstruct; - return sprintf(buf, "%d\n", ls->ls_recover_jid); -} - -static void gfs2_jdesc_make_dirty(struct gfs2_sbd *sdp, unsigned int jid) +static ssize_t recover_store(struct gfs2_sbd *sdp, const char *buf, size_t len) { + unsigned jid; struct gfs2_jdesc *jd; + int rv; + + rv = sscanf(buf, "%u", &jid); + if (rv != 1) + return -EINVAL; + rv = -ESHUTDOWN; spin_lock(&sdp->sd_jindex_spin); + if (test_bit(SDF_NORECOVERY, &sdp->sd_flags)) + goto out; + rv = -EBUSY; + if (sdp->sd_jdesc->jd_jid == jid) + goto out; + rv = -ENOENT; list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) { if (jd->jd_jid != jid) continue; - jd->jd_dirty = 1; + rv = slow_work_enqueue(&jd->jd_work); break; } +out: spin_unlock(&sdp->sd_jindex_spin); -} - -static ssize_t recover_store(struct gfs2_sbd *sdp, const char *buf, size_t len) -{ - struct lm_lockstruct *ls = &sdp->sd_lockstruct; - ls->ls_recover_jid = simple_strtol(buf, NULL, 0); - gfs2_jdesc_make_dirty(sdp, ls->ls_recover_jid); - if (sdp->sd_recoverd_process) - wake_up_process(sdp->sd_recoverd_process); - return len; + return rv ? rv : len; } static ssize_t recover_done_show(struct gfs2_sbd *sdp, char *buf) @@ -401,31 +378,31 @@ static ssize_t recover_status_show(struct gfs2_sbd *sdp, char *buf) return sprintf(buf, "%d\n", ls->ls_recover_jid_status); } -struct gdlm_attr { - struct attribute attr; - ssize_t (*show)(struct gfs2_sbd *sdp, char *); - ssize_t (*store)(struct gfs2_sbd *sdp, const char *, size_t); -}; +static ssize_t jid_show(struct gfs2_sbd *sdp, char *buf) +{ + return sprintf(buf, "%u\n", sdp->sd_lockstruct.ls_jid); +} #define GDLM_ATTR(_name,_mode,_show,_store) \ -static struct gdlm_attr gdlm_attr_##_name = __ATTR(_name,_mode,_show,_store) - -GDLM_ATTR(proto_name, 0444, proto_name_show, NULL); -GDLM_ATTR(block, 0644, block_show, block_store); -GDLM_ATTR(withdraw, 0644, withdraw_show, withdraw_store); -GDLM_ATTR(id, 0444, lkid_show, NULL); -GDLM_ATTR(first, 0444, lkfirst_show, NULL); -GDLM_ATTR(first_done, 0444, first_done_show, NULL); -GDLM_ATTR(recover, 0644, recover_show, recover_store); -GDLM_ATTR(recover_done, 0444, recover_done_show, NULL); -GDLM_ATTR(recover_status, 0444, recover_status_show, NULL); +static struct gfs2_attr gdlm_attr_##_name = __ATTR(_name,_mode,_show,_store) + +GDLM_ATTR(proto_name, 0444, proto_name_show, NULL); +GDLM_ATTR(block, 0644, block_show, block_store); +GDLM_ATTR(withdraw, 0644, withdraw_show, withdraw_store); +GDLM_ATTR(id, 0444, lkid_show, NULL); +GDLM_ATTR(jid, 0444, jid_show, NULL); +GDLM_ATTR(first, 0444, lkfirst_show, NULL); +GDLM_ATTR(first_done, 0444, first_done_show, NULL); +GDLM_ATTR(recover, 0200, NULL, recover_store); +GDLM_ATTR(recover_done, 0444, recover_done_show, NULL); +GDLM_ATTR(recover_status, 0444, recover_status_show, NULL); static struct attribute *lock_module_attrs[] = { &gdlm_attr_proto_name.attr, &gdlm_attr_block.attr, &gdlm_attr_withdraw.attr, &gdlm_attr_id.attr, - &lockstruct_attr_jid.attr, + &gdlm_attr_jid.attr, &gdlm_attr_first.attr, &gdlm_attr_first_done.attr, &gdlm_attr_recover.attr, @@ -435,53 +412,6 @@ static struct attribute *lock_module_attrs[] = { }; /* - * display struct gfs2_args fields - */ - -struct args_attr { - struct attribute attr; - ssize_t (*show)(struct gfs2_sbd *, char *); -}; - -#define ARGS_ATTR(name, fmt) \ -static ssize_t name##_show(struct gfs2_sbd *sdp, char *buf) \ -{ \ - return snprintf(buf, PAGE_SIZE, fmt, sdp->sd_args.ar_##name); \ -} \ -static struct args_attr args_attr_##name = __ATTR_RO(name) - -ARGS_ATTR(lockproto, "%s\n"); -ARGS_ATTR(locktable, "%s\n"); -ARGS_ATTR(hostdata, "%s\n"); -ARGS_ATTR(spectator, "%d\n"); -ARGS_ATTR(ignore_local_fs, "%d\n"); -ARGS_ATTR(localcaching, "%d\n"); -ARGS_ATTR(localflocks, "%d\n"); -ARGS_ATTR(debug, "%d\n"); -ARGS_ATTR(upgrade, "%d\n"); -ARGS_ATTR(posix_acl, "%d\n"); -ARGS_ATTR(quota, "%u\n"); -ARGS_ATTR(suiddir, "%d\n"); -ARGS_ATTR(data, "%d\n"); - -static struct attribute *args_attrs[] = { - &args_attr_lockproto.attr, - &args_attr_locktable.attr, - &args_attr_hostdata.attr, - &args_attr_spectator.attr, - &args_attr_ignore_local_fs.attr, - &args_attr_localcaching.attr, - &args_attr_localflocks.attr, - &args_attr_debug.attr, - &args_attr_upgrade.attr, - &args_attr_posix_acl.attr, - &args_attr_quota.attr, - &args_attr_suiddir.attr, - &args_attr_data.attr, - NULL, -}; - -/* * get and set struct gfs2_tune fields */ @@ -531,14 +461,8 @@ static ssize_t tune_set(struct gfs2_sbd *sdp, unsigned int *field, return len; } -struct tune_attr { - struct attribute attr; - ssize_t (*show)(struct gfs2_sbd *, char *); - ssize_t (*store)(struct gfs2_sbd *, const char *, size_t); -}; - #define TUNE_ATTR_3(name, show, store) \ -static struct tune_attr tune_attr_##name = __ATTR(name, 0644, show, store) +static struct gfs2_attr tune_attr_##name = __ATTR(name, 0644, show, store) #define TUNE_ATTR_2(name, store) \ static ssize_t name##_show(struct gfs2_sbd *sdp, char *buf) \ @@ -554,15 +478,6 @@ static ssize_t name##_store(struct gfs2_sbd *sdp, const char *buf, size_t len)\ } \ TUNE_ATTR_2(name, name##_store) -#define TUNE_ATTR_DAEMON(name, process) \ -static ssize_t name##_store(struct gfs2_sbd *sdp, const char *buf, size_t len)\ -{ \ - ssize_t r = tune_set(sdp, &sdp->sd_tune.gt_##name, 1, buf, len); \ - wake_up_process(sdp->sd_##process); \ - return r; \ -} \ -TUNE_ATTR_2(name, name##_store) - TUNE_ATTR(incore_log_blocks, 0); TUNE_ATTR(log_flush_secs, 0); TUNE_ATTR(quota_warn_period, 0); @@ -574,8 +489,6 @@ TUNE_ATTR(new_files_jdata, 0); TUNE_ATTR(quota_simul_sync, 1); TUNE_ATTR(stall_secs, 1); TUNE_ATTR(statfs_quantum, 1); -TUNE_ATTR_DAEMON(recoverd_secs, recoverd_process); -TUNE_ATTR_DAEMON(logd_secs, logd_process); TUNE_ATTR_3(quota_scale, quota_scale_show, quota_scale_store); static struct attribute *tune_attrs[] = { @@ -589,23 +502,11 @@ static struct attribute *tune_attrs[] = { &tune_attr_quota_simul_sync.attr, &tune_attr_stall_secs.attr, &tune_attr_statfs_quantum.attr, - &tune_attr_recoverd_secs.attr, - &tune_attr_logd_secs.attr, &tune_attr_quota_scale.attr, &tune_attr_new_files_jdata.attr, NULL, }; -static struct attribute_group lockstruct_group = { - .name = "lockstruct", - .attrs = lockstruct_attrs, -}; - -static struct attribute_group args_group = { - .name = "args", - .attrs = args_attrs, -}; - static struct attribute_group tune_group = { .name = "tune", .attrs = tune_attrs, @@ -626,17 +527,9 @@ int gfs2_sys_fs_add(struct gfs2_sbd *sdp) if (error) goto fail; - error = sysfs_create_group(&sdp->sd_kobj, &lockstruct_group); - if (error) - goto fail_reg; - - error = sysfs_create_group(&sdp->sd_kobj, &args_group); - if (error) - goto fail_lockstruct; - error = sysfs_create_group(&sdp->sd_kobj, &tune_group); if (error) - goto fail_args; + goto fail_reg; error = sysfs_create_group(&sdp->sd_kobj, &lock_module_group); if (error) @@ -647,10 +540,6 @@ int gfs2_sys_fs_add(struct gfs2_sbd *sdp) fail_tune: sysfs_remove_group(&sdp->sd_kobj, &tune_group); -fail_args: - sysfs_remove_group(&sdp->sd_kobj, &args_group); -fail_lockstruct: - sysfs_remove_group(&sdp->sd_kobj, &lockstruct_group); fail_reg: kobject_put(&sdp->sd_kobj); fail: @@ -661,8 +550,6 @@ fail: void gfs2_sys_fs_del(struct gfs2_sbd *sdp) { sysfs_remove_group(&sdp->sd_kobj, &tune_group); - sysfs_remove_group(&sdp->sd_kobj, &args_group); - sysfs_remove_group(&sdp->sd_kobj, &lockstruct_group); sysfs_remove_group(&sdp->sd_kobj, &lock_module_group); kobject_put(&sdp->sd_kobj); } diff --git a/fs/gfs2/trace_gfs2.h b/fs/gfs2/trace_gfs2.h new file mode 100644 index 000000000000..98d6ef1c1dc0 --- /dev/null +++ b/fs/gfs2/trace_gfs2.h @@ -0,0 +1,407 @@ +#if !defined(_TRACE_GFS2_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_GFS2_H + +#include <linux/tracepoint.h> + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM gfs2 +#define TRACE_INCLUDE_FILE trace_gfs2 + +#include <linux/fs.h> +#include <linux/buffer_head.h> +#include <linux/dlmconstants.h> +#include <linux/gfs2_ondisk.h> +#include "incore.h" +#include "glock.h" + +#define dlm_state_name(nn) { DLM_LOCK_##nn, #nn } +#define glock_trace_name(x) __print_symbolic(x, \ + dlm_state_name(IV), \ + dlm_state_name(NL), \ + dlm_state_name(CR), \ + dlm_state_name(CW), \ + dlm_state_name(PR), \ + dlm_state_name(PW), \ + dlm_state_name(EX)) + +#define block_state_name(x) __print_symbolic(x, \ + { GFS2_BLKST_FREE, "free" }, \ + { GFS2_BLKST_USED, "used" }, \ + { GFS2_BLKST_DINODE, "dinode" }, \ + { GFS2_BLKST_UNLINKED, "unlinked" }) + +#define show_glock_flags(flags) __print_flags(flags, "", \ + {(1UL << GLF_LOCK), "l" }, \ + {(1UL << GLF_DEMOTE), "D" }, \ + {(1UL << GLF_PENDING_DEMOTE), "d" }, \ + {(1UL << GLF_DEMOTE_IN_PROGRESS), "p" }, \ + {(1UL << GLF_DIRTY), "y" }, \ + {(1UL << GLF_LFLUSH), "f" }, \ + {(1UL << GLF_INVALIDATE_IN_PROGRESS), "i" }, \ + {(1UL << GLF_REPLY_PENDING), "r" }, \ + {(1UL << GLF_INITIAL), "I" }, \ + {(1UL << GLF_FROZEN), "F" }) + +#ifndef NUMPTY +#define NUMPTY +static inline u8 glock_trace_state(unsigned int state) +{ + switch(state) { + case LM_ST_SHARED: + return DLM_LOCK_PR; + case LM_ST_DEFERRED: + return DLM_LOCK_CW; + case LM_ST_EXCLUSIVE: + return DLM_LOCK_EX; + } + return DLM_LOCK_NL; +} +#endif + +/* Section 1 - Locking + * + * Objectives: + * Latency: Remote demote request to state change + * Latency: Local lock request to state change + * Latency: State change to lock grant + * Correctness: Ordering of local lock state vs. I/O requests + * Correctness: Responses to remote demote requests + */ + +/* General glock state change (DLM lock request completes) */ +TRACE_EVENT(gfs2_glock_state_change, + + TP_PROTO(const struct gfs2_glock *gl, unsigned int new_state), + + TP_ARGS(gl, new_state), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( u64, glnum ) + __field( u32, gltype ) + __field( u8, cur_state ) + __field( u8, new_state ) + __field( u8, dmt_state ) + __field( u8, tgt_state ) + __field( unsigned long, flags ) + ), + + TP_fast_assign( + __entry->dev = gl->gl_sbd->sd_vfs->s_dev; + __entry->glnum = gl->gl_name.ln_number; + __entry->gltype = gl->gl_name.ln_type; + __entry->cur_state = glock_trace_state(gl->gl_state); + __entry->new_state = glock_trace_state(new_state); + __entry->tgt_state = glock_trace_state(gl->gl_target); + __entry->dmt_state = glock_trace_state(gl->gl_demote_state); + __entry->flags = gl->gl_flags; + ), + + TP_printk("%u,%u glock %d:%lld state %s to %s tgt:%s dmt:%s flags:%s", + MAJOR(__entry->dev), MINOR(__entry->dev), __entry->gltype, + (unsigned long long)__entry->glnum, + glock_trace_name(__entry->cur_state), + glock_trace_name(__entry->new_state), + glock_trace_name(__entry->tgt_state), + glock_trace_name(__entry->dmt_state), + show_glock_flags(__entry->flags)) +); + +/* State change -> unlocked, glock is being deallocated */ +TRACE_EVENT(gfs2_glock_put, + + TP_PROTO(const struct gfs2_glock *gl), + + TP_ARGS(gl), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( u64, glnum ) + __field( u32, gltype ) + __field( u8, cur_state ) + __field( unsigned long, flags ) + ), + + TP_fast_assign( + __entry->dev = gl->gl_sbd->sd_vfs->s_dev; + __entry->gltype = gl->gl_name.ln_type; + __entry->glnum = gl->gl_name.ln_number; + __entry->cur_state = glock_trace_state(gl->gl_state); + __entry->flags = gl->gl_flags; + ), + + TP_printk("%u,%u glock %d:%lld state %s => %s flags:%s", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->gltype, (unsigned long long)__entry->glnum, + glock_trace_name(__entry->cur_state), + glock_trace_name(DLM_LOCK_IV), + show_glock_flags(__entry->flags)) + +); + +/* Callback (local or remote) requesting lock demotion */ +TRACE_EVENT(gfs2_demote_rq, + + TP_PROTO(const struct gfs2_glock *gl), + + TP_ARGS(gl), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( u64, glnum ) + __field( u32, gltype ) + __field( u8, cur_state ) + __field( u8, dmt_state ) + __field( unsigned long, flags ) + ), + + TP_fast_assign( + __entry->dev = gl->gl_sbd->sd_vfs->s_dev; + __entry->gltype = gl->gl_name.ln_type; + __entry->glnum = gl->gl_name.ln_number; + __entry->cur_state = glock_trace_state(gl->gl_state); + __entry->dmt_state = glock_trace_state(gl->gl_demote_state); + __entry->flags = gl->gl_flags; + ), + + TP_printk("%u,%u glock %d:%lld demote %s to %s flags:%s", + MAJOR(__entry->dev), MINOR(__entry->dev), __entry->gltype, + (unsigned long long)__entry->glnum, + glock_trace_name(__entry->cur_state), + glock_trace_name(__entry->dmt_state), + show_glock_flags(__entry->flags)) + +); + +/* Promotion/grant of a glock */ +TRACE_EVENT(gfs2_promote, + + TP_PROTO(const struct gfs2_holder *gh, int first), + + TP_ARGS(gh, first), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( u64, glnum ) + __field( u32, gltype ) + __field( int, first ) + __field( u8, state ) + ), + + TP_fast_assign( + __entry->dev = gh->gh_gl->gl_sbd->sd_vfs->s_dev; + __entry->glnum = gh->gh_gl->gl_name.ln_number; + __entry->gltype = gh->gh_gl->gl_name.ln_type; + __entry->first = first; + __entry->state = glock_trace_state(gh->gh_state); + ), + + TP_printk("%u,%u glock %u:%llu promote %s %s", + MAJOR(__entry->dev), MINOR(__entry->dev), __entry->gltype, + (unsigned long long)__entry->glnum, + __entry->first ? "first": "other", + glock_trace_name(__entry->state)) +); + +/* Queue/dequeue a lock request */ +TRACE_EVENT(gfs2_glock_queue, + + TP_PROTO(const struct gfs2_holder *gh, int queue), + + TP_ARGS(gh, queue), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( u64, glnum ) + __field( u32, gltype ) + __field( int, queue ) + __field( u8, state ) + ), + + TP_fast_assign( + __entry->dev = gh->gh_gl->gl_sbd->sd_vfs->s_dev; + __entry->glnum = gh->gh_gl->gl_name.ln_number; + __entry->gltype = gh->gh_gl->gl_name.ln_type; + __entry->queue = queue; + __entry->state = glock_trace_state(gh->gh_state); + ), + + TP_printk("%u,%u glock %u:%llu %squeue %s", + MAJOR(__entry->dev), MINOR(__entry->dev), __entry->gltype, + (unsigned long long)__entry->glnum, + __entry->queue ? "" : "de", + glock_trace_name(__entry->state)) +); + +/* Section 2 - Log/journal + * + * Objectives: + * Latency: Log flush time + * Correctness: pin/unpin vs. disk I/O ordering + * Performance: Log usage stats + */ + +/* Pin/unpin a block in the log */ +TRACE_EVENT(gfs2_pin, + + TP_PROTO(const struct gfs2_bufdata *bd, int pin), + + TP_ARGS(bd, pin), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( int, pin ) + __field( u32, len ) + __field( sector_t, block ) + __field( u64, ino ) + ), + + TP_fast_assign( + __entry->dev = bd->bd_gl->gl_sbd->sd_vfs->s_dev; + __entry->pin = pin; + __entry->len = bd->bd_bh->b_size; + __entry->block = bd->bd_bh->b_blocknr; + __entry->ino = bd->bd_gl->gl_name.ln_number; + ), + + TP_printk("%u,%u log %s %llu/%lu inode %llu", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->pin ? "pin" : "unpin", + (unsigned long long)__entry->block, + (unsigned long)__entry->len, + (unsigned long long)__entry->ino) +); + +/* Flushing the log */ +TRACE_EVENT(gfs2_log_flush, + + TP_PROTO(const struct gfs2_sbd *sdp, int start), + + TP_ARGS(sdp, start), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( int, start ) + __field( u64, log_seq ) + ), + + TP_fast_assign( + __entry->dev = sdp->sd_vfs->s_dev; + __entry->start = start; + __entry->log_seq = sdp->sd_log_sequence; + ), + + TP_printk("%u,%u log flush %s %llu", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->start ? "start" : "end", + (unsigned long long)__entry->log_seq) +); + +/* Reserving/releasing blocks in the log */ +TRACE_EVENT(gfs2_log_blocks, + + TP_PROTO(const struct gfs2_sbd *sdp, int blocks), + + TP_ARGS(sdp, blocks), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( int, blocks ) + ), + + TP_fast_assign( + __entry->dev = sdp->sd_vfs->s_dev; + __entry->blocks = blocks; + ), + + TP_printk("%u,%u log reserve %d", MAJOR(__entry->dev), + MINOR(__entry->dev), __entry->blocks) +); + +/* Section 3 - bmap + * + * Objectives: + * Latency: Bmap request time + * Performance: Block allocator tracing + * Correctness: Test of disard generation vs. blocks allocated + */ + +/* Map an extent of blocks, possibly a new allocation */ +TRACE_EVENT(gfs2_bmap, + + TP_PROTO(const struct gfs2_inode *ip, const struct buffer_head *bh, + sector_t lblock, int create, int errno), + + TP_ARGS(ip, bh, lblock, create, errno), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( sector_t, lblock ) + __field( sector_t, pblock ) + __field( u64, inum ) + __field( unsigned long, state ) + __field( u32, len ) + __field( int, create ) + __field( int, errno ) + ), + + TP_fast_assign( + __entry->dev = ip->i_gl->gl_sbd->sd_vfs->s_dev; + __entry->lblock = lblock; + __entry->pblock = buffer_mapped(bh) ? bh->b_blocknr : 0; + __entry->inum = ip->i_no_addr; + __entry->state = bh->b_state; + __entry->len = bh->b_size; + __entry->create = create; + __entry->errno = errno; + ), + + TP_printk("%u,%u bmap %llu map %llu/%lu to %llu flags:%08lx %s %d", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->inum, + (unsigned long long)__entry->lblock, + (unsigned long)__entry->len, + (unsigned long long)__entry->pblock, + __entry->state, __entry->create ? "create " : "nocreate", + __entry->errno) +); + +/* Keep track of blocks as they are allocated/freed */ +TRACE_EVENT(gfs2_block_alloc, + + TP_PROTO(const struct gfs2_inode *ip, u64 block, unsigned len, + u8 block_state), + + TP_ARGS(ip, block, len, block_state), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( u64, start ) + __field( u64, inum ) + __field( u32, len ) + __field( u8, block_state ) + ), + + TP_fast_assign( + __entry->dev = ip->i_gl->gl_sbd->sd_vfs->s_dev; + __entry->start = block; + __entry->inum = ip->i_no_addr; + __entry->len = len; + __entry->block_state = block_state; + ), + + TP_printk("%u,%u bmap %llu alloc %llu/%lu %s", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->inum, + (unsigned long long)__entry->start, + (unsigned long)__entry->len, + block_state_name(__entry->block_state)) +); + +#endif /* _TRACE_GFS2_H */ + +/* This part must be outside protection */ +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#include <trace/define_trace.h> + diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c index 053752d4b27f..4ef0e9fa3549 100644 --- a/fs/gfs2/trans.c +++ b/fs/gfs2/trans.c @@ -33,6 +33,9 @@ int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks, BUG_ON(current->journal_info); BUG_ON(blocks == 0 && revokes == 0); + if (!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) + return -EROFS; + tr = kzalloc(sizeof(struct gfs2_trans), GFP_NOFS); if (!tr) return -ENOMEM; @@ -54,12 +57,6 @@ int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks, if (error) goto fail_holder_uninit; - if (!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) { - tr->tr_t_gh.gh_flags |= GL_NOCACHE; - error = -EROFS; - goto fail_gunlock; - } - error = gfs2_log_reserve(sdp, tr->tr_reserved); if (error) goto fail_gunlock; |