diff options
Diffstat (limited to 'fs')
38 files changed, 486 insertions, 227 deletions
diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c index fc783e264420..0fb15bbbe43c 100644 --- a/fs/cifs/cifsacl.c +++ b/fs/cifs/cifsacl.c @@ -225,6 +225,13 @@ sid_to_str(struct cifs_sid *sidptr, char *sidstr) } static void +cifs_copy_sid(struct cifs_sid *dst, const struct cifs_sid *src) +{ + memcpy(dst, src, sizeof(*dst)); + dst->num_subauth = min_t(u8, src->num_subauth, NUM_SUBAUTHS); +} + +static void id_rb_insert(struct rb_root *root, struct cifs_sid *sidptr, struct cifs_sid_id **psidid, char *typestr) { @@ -248,7 +255,7 @@ id_rb_insert(struct rb_root *root, struct cifs_sid *sidptr, } } - memcpy(&(*psidid)->sid, sidptr, sizeof(struct cifs_sid)); + cifs_copy_sid(&(*psidid)->sid, sidptr); (*psidid)->time = jiffies - (SID_MAP_RETRY + 1); (*psidid)->refcount = 0; @@ -354,7 +361,7 @@ id_to_sid(unsigned long cid, uint sidtype, struct cifs_sid *ssid) * any fields of the node after a reference is put . */ if (test_bit(SID_ID_MAPPED, &psidid->state)) { - memcpy(ssid, &psidid->sid, sizeof(struct cifs_sid)); + cifs_copy_sid(ssid, &psidid->sid); psidid->time = jiffies; /* update ts for accessing */ goto id_sid_out; } @@ -370,14 +377,14 @@ id_to_sid(unsigned long cid, uint sidtype, struct cifs_sid *ssid) if (IS_ERR(sidkey)) { rc = -EINVAL; cFYI(1, "%s: Can't map and id to a SID", __func__); + } else if (sidkey->datalen < sizeof(struct cifs_sid)) { + rc = -EIO; + cFYI(1, "%s: Downcall contained malformed key " + "(datalen=%hu)", __func__, sidkey->datalen); } else { lsid = (struct cifs_sid *)sidkey->payload.data; - memcpy(&psidid->sid, lsid, - sidkey->datalen < sizeof(struct cifs_sid) ? - sidkey->datalen : sizeof(struct cifs_sid)); - memcpy(ssid, &psidid->sid, - sidkey->datalen < sizeof(struct cifs_sid) ? - sidkey->datalen : sizeof(struct cifs_sid)); + cifs_copy_sid(&psidid->sid, lsid); + cifs_copy_sid(ssid, &psidid->sid); set_bit(SID_ID_MAPPED, &psidid->state); key_put(sidkey); kfree(psidid->sidstr); @@ -396,7 +403,7 @@ id_to_sid(unsigned long cid, uint sidtype, struct cifs_sid *ssid) return rc; } if (test_bit(SID_ID_MAPPED, &psidid->state)) - memcpy(ssid, &psidid->sid, sizeof(struct cifs_sid)); + cifs_copy_sid(ssid, &psidid->sid); else rc = -EINVAL; } @@ -675,8 +682,6 @@ int compare_sids(const struct cifs_sid *ctsid, const struct cifs_sid *cwsid) static void copy_sec_desc(const struct cifs_ntsd *pntsd, struct cifs_ntsd *pnntsd, __u32 sidsoffset) { - int i; - struct cifs_sid *owner_sid_ptr, *group_sid_ptr; struct cifs_sid *nowner_sid_ptr, *ngroup_sid_ptr; @@ -692,26 +697,14 @@ static void copy_sec_desc(const struct cifs_ntsd *pntsd, owner_sid_ptr = (struct cifs_sid *)((char *)pntsd + le32_to_cpu(pntsd->osidoffset)); nowner_sid_ptr = (struct cifs_sid *)((char *)pnntsd + sidsoffset); - - nowner_sid_ptr->revision = owner_sid_ptr->revision; - nowner_sid_ptr->num_subauth = owner_sid_ptr->num_subauth; - for (i = 0; i < 6; i++) - nowner_sid_ptr->authority[i] = owner_sid_ptr->authority[i]; - for (i = 0; i < 5; i++) - nowner_sid_ptr->sub_auth[i] = owner_sid_ptr->sub_auth[i]; + cifs_copy_sid(nowner_sid_ptr, owner_sid_ptr); /* copy group sid */ group_sid_ptr = (struct cifs_sid *)((char *)pntsd + le32_to_cpu(pntsd->gsidoffset)); ngroup_sid_ptr = (struct cifs_sid *)((char *)pnntsd + sidsoffset + sizeof(struct cifs_sid)); - - ngroup_sid_ptr->revision = group_sid_ptr->revision; - ngroup_sid_ptr->num_subauth = group_sid_ptr->num_subauth; - for (i = 0; i < 6; i++) - ngroup_sid_ptr->authority[i] = group_sid_ptr->authority[i]; - for (i = 0; i < 5; i++) - ngroup_sid_ptr->sub_auth[i] = group_sid_ptr->sub_auth[i]; + cifs_copy_sid(ngroup_sid_ptr, group_sid_ptr); return; } @@ -1120,8 +1113,7 @@ static int build_sec_desc(struct cifs_ntsd *pntsd, struct cifs_ntsd *pnntsd, kfree(nowner_sid_ptr); return rc; } - memcpy(owner_sid_ptr, nowner_sid_ptr, - sizeof(struct cifs_sid)); + cifs_copy_sid(owner_sid_ptr, nowner_sid_ptr); kfree(nowner_sid_ptr); *aclflag = CIFS_ACL_OWNER; } @@ -1139,8 +1131,7 @@ static int build_sec_desc(struct cifs_ntsd *pntsd, struct cifs_ntsd *pnntsd, kfree(ngroup_sid_ptr); return rc; } - memcpy(group_sid_ptr, ngroup_sid_ptr, - sizeof(struct cifs_sid)); + cifs_copy_sid(group_sid_ptr, ngroup_sid_ptr); kfree(ngroup_sid_ptr); *aclflag = CIFS_ACL_GROUP; } diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index 7c0a81283645..d3671f2acb29 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -398,7 +398,16 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry, * in network traffic in the other paths. */ if (!(oflags & O_CREAT)) { - struct dentry *res = cifs_lookup(inode, direntry, 0); + struct dentry *res; + + /* + * Check for hashed negative dentry. We have already revalidated + * the dentry and it is fine. No need to perform another lookup. + */ + if (!d_unhashed(direntry)) + return -ENOENT; + + res = cifs_lookup(inode, direntry, 0); if (IS_ERR(res)) return PTR_ERR(res); diff --git a/fs/eventpoll.c b/fs/eventpoll.c index da72250ddc1c..cd96649bfe62 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -346,7 +346,7 @@ static inline struct epitem *ep_item_from_epqueue(poll_table *p) /* Tells if the epoll_ctl(2) operation needs an event copy from userspace */ static inline int ep_op_has_event(int op) { - return op == EPOLL_CTL_ADD || op == EPOLL_CTL_MOD; + return op != EPOLL_CTL_DEL; } /* Initialize the poll safe wake up structure */ @@ -676,34 +676,6 @@ static int ep_remove(struct eventpoll *ep, struct epitem *epi) return 0; } -/* - * Disables a "struct epitem" in the eventpoll set. Returns -EBUSY if the item - * had no event flags set, indicating that another thread may be currently - * handling that item's events (in the case that EPOLLONESHOT was being - * used). Otherwise a zero result indicates that the item has been disabled - * from receiving events. A disabled item may be re-enabled via - * EPOLL_CTL_MOD. Must be called with "mtx" held. - */ -static int ep_disable(struct eventpoll *ep, struct epitem *epi) -{ - int result = 0; - unsigned long flags; - - spin_lock_irqsave(&ep->lock, flags); - if (epi->event.events & ~EP_PRIVATE_BITS) { - if (ep_is_linked(&epi->rdllink)) - list_del_init(&epi->rdllink); - /* Ensure ep_poll_callback will not add epi back onto ready - list: */ - epi->event.events &= EP_PRIVATE_BITS; - } - else - result = -EBUSY; - spin_unlock_irqrestore(&ep->lock, flags); - - return result; -} - static void ep_free(struct eventpoll *ep) { struct rb_node *rbp; @@ -1048,6 +1020,8 @@ static void ep_rbtree_insert(struct eventpoll *ep, struct epitem *epi) rb_insert_color(&epi->rbn, &ep->rbr); } + + #define PATH_ARR_SIZE 5 /* * These are the number paths of length 1 to 5, that we are allowing to emanate @@ -1813,12 +1787,6 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, } else error = -ENOENT; break; - case EPOLL_CTL_DISABLE: - if (epi) - error = ep_disable(ep, epi); - else - error = -ENOENT; - break; } mutex_unlock(&ep->mtx); diff --git a/fs/ext3/balloc.c b/fs/ext3/balloc.c index 7320a66e958f..22548f56197b 100644 --- a/fs/ext3/balloc.c +++ b/fs/ext3/balloc.c @@ -2101,8 +2101,9 @@ int ext3_trim_fs(struct super_block *sb, struct fstrim_range *range) end = start + (range->len >> sb->s_blocksize_bits) - 1; minlen = range->minlen >> sb->s_blocksize_bits; - if (unlikely(minlen > EXT3_BLOCKS_PER_GROUP(sb)) || - unlikely(start >= max_blks)) + if (minlen > EXT3_BLOCKS_PER_GROUP(sb) || + start >= max_blks || + range->len < sb->s_blocksize) return -EINVAL; if (end >= max_blks) end = max_blks - 1; diff --git a/fs/file.c b/fs/file.c index 708d997a7748..7cb71b992603 100644 --- a/fs/file.c +++ b/fs/file.c @@ -685,7 +685,6 @@ void do_close_on_exec(struct files_struct *files) struct fdtable *fdt; /* exec unshares first */ - BUG_ON(atomic_read(&files->count) != 1); spin_lock(&files->file_lock); for (i = 0; ; i++) { unsigned long set; diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 0def0504afc1..e056b4ce4877 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -516,15 +516,13 @@ static int gfs2_mmap(struct file *file, struct vm_area_struct *vma) struct gfs2_holder i_gh; int error; - gfs2_holder_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &i_gh); - error = gfs2_glock_nq(&i_gh); - if (error == 0) { - file_accessed(file); - gfs2_glock_dq(&i_gh); - } - gfs2_holder_uninit(&i_gh); + error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, + &i_gh); if (error) return error; + /* grab lock to update inode */ + gfs2_glock_dq_uninit(&i_gh); + file_accessed(file); } vma->vm_ops = &gfs2_vm_ops; @@ -677,10 +675,8 @@ static ssize_t gfs2_file_aio_write(struct kiocb *iocb, const struct iovec *iov, size_t writesize = iov_length(iov, nr_segs); struct dentry *dentry = file->f_dentry; struct gfs2_inode *ip = GFS2_I(dentry->d_inode); - struct gfs2_sbd *sdp; int ret; - sdp = GFS2_SB(file->f_mapping->host); ret = gfs2_rs_alloc(ip); if (ret) return ret; diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index 8ff95a2d54ee..9ceccb1595a3 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -393,12 +393,10 @@ static void buf_lo_add(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd) struct gfs2_meta_header *mh; struct gfs2_trans *tr; - lock_buffer(bd->bd_bh); - gfs2_log_lock(sdp); tr = current->journal_info; tr->tr_touched = 1; if (!list_empty(&bd->bd_list)) - goto out; + return; set_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags); set_bit(GLF_DIRTY, &bd->bd_gl->gl_flags); mh = (struct gfs2_meta_header *)bd->bd_bh->b_data; @@ -414,9 +412,6 @@ static void buf_lo_add(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd) sdp->sd_log_num_buf++; list_add(&bd->bd_list, &sdp->sd_log_le_buf); tr->tr_num_buf_new++; -out: - gfs2_log_unlock(sdp); - unlock_buffer(bd->bd_bh); } static void gfs2_check_magic(struct buffer_head *bh) @@ -621,7 +616,6 @@ static void revoke_lo_add(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd) static void revoke_lo_before_commit(struct gfs2_sbd *sdp) { - struct gfs2_log_descriptor *ld; struct gfs2_meta_header *mh; unsigned int offset; struct list_head *head = &sdp->sd_log_le_revoke; @@ -634,7 +628,6 @@ static void revoke_lo_before_commit(struct gfs2_sbd *sdp) length = gfs2_struct2blk(sdp, sdp->sd_log_num_revoke, sizeof(u64)); page = gfs2_get_log_desc(sdp, GFS2_LOG_DESC_REVOKE, length, sdp->sd_log_num_revoke); - ld = page_address(page); offset = sizeof(struct gfs2_log_descriptor); list_for_each_entry(bd, head, bd_list) { @@ -777,12 +770,10 @@ static void databuf_lo_add(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd) struct address_space *mapping = bd->bd_bh->b_page->mapping; struct gfs2_inode *ip = GFS2_I(mapping->host); - lock_buffer(bd->bd_bh); - gfs2_log_lock(sdp); if (tr) tr->tr_touched = 1; if (!list_empty(&bd->bd_list)) - goto out; + return; set_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags); set_bit(GLF_DIRTY, &bd->bd_gl->gl_flags); if (gfs2_is_jdata(ip)) { @@ -793,9 +784,6 @@ static void databuf_lo_add(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd) } else { list_add_tail(&bd->bd_list, &sdp->sd_log_le_ordered); } -out: - gfs2_log_unlock(sdp); - unlock_buffer(bd->bd_bh); } /** diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index 40c4b0d42fa8..c5af8e18f27a 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -497,8 +497,11 @@ int gfs2_quota_hold(struct gfs2_inode *ip, u32 uid, u32 gid) struct gfs2_quota_data **qd; int error; - if (ip->i_res == NULL) - gfs2_rs_alloc(ip); + if (ip->i_res == NULL) { + error = gfs2_rs_alloc(ip); + if (error) + return error; + } qd = ip->i_res->rs_qa_qd; diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index 3cc402ce6fea..38fe18f2f055 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -553,7 +553,6 @@ void gfs2_free_clones(struct gfs2_rgrpd *rgd) */ int gfs2_rs_alloc(struct gfs2_inode *ip) { - int error = 0; struct gfs2_blkreserv *res; if (ip->i_res) @@ -561,7 +560,7 @@ int gfs2_rs_alloc(struct gfs2_inode *ip) res = kmem_cache_zalloc(gfs2_rsrv_cachep, GFP_NOFS); if (!res) - error = -ENOMEM; + return -ENOMEM; RB_CLEAR_NODE(&res->rs_node); @@ -571,7 +570,7 @@ int gfs2_rs_alloc(struct gfs2_inode *ip) else ip->i_res = res; up_write(&ip->i_rw_mutex); - return error; + return 0; } static void dump_rs(struct seq_file *seq, const struct gfs2_blkreserv *rs) @@ -1263,7 +1262,9 @@ int gfs2_fitrim(struct file *filp, void __user *argp) int ret = 0; u64 amt; u64 trimmed = 0; + u64 start, end, minlen; unsigned int x; + unsigned bs_shift = sdp->sd_sb.sb_bsize_shift; if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -1271,19 +1272,25 @@ int gfs2_fitrim(struct file *filp, void __user *argp) if (!blk_queue_discard(q)) return -EOPNOTSUPP; - if (argp == NULL) { - r.start = 0; - r.len = ULLONG_MAX; - r.minlen = 0; - } else if (copy_from_user(&r, argp, sizeof(r))) + if (copy_from_user(&r, argp, sizeof(r))) return -EFAULT; ret = gfs2_rindex_update(sdp); if (ret) return ret; - rgd = gfs2_blk2rgrpd(sdp, r.start, 0); - rgd_end = gfs2_blk2rgrpd(sdp, r.start + r.len, 0); + start = r.start >> bs_shift; + end = start + (r.len >> bs_shift); + minlen = max_t(u64, r.minlen, + q->limits.discard_granularity) >> bs_shift; + + rgd = gfs2_blk2rgrpd(sdp, start, 0); + rgd_end = gfs2_blk2rgrpd(sdp, end - 1, 0); + + if (end <= start || + minlen > sdp->sd_max_rg_data || + start > rgd_end->rd_data0 + rgd_end->rd_data) + return -EINVAL; while (1) { @@ -1295,7 +1302,9 @@ int gfs2_fitrim(struct file *filp, void __user *argp) /* Trim each bitmap in the rgrp */ for (x = 0; x < rgd->rd_length; x++) { struct gfs2_bitmap *bi = rgd->rd_bits + x; - ret = gfs2_rgrp_send_discards(sdp, rgd->rd_data0, NULL, bi, r.minlen, &amt); + ret = gfs2_rgrp_send_discards(sdp, + rgd->rd_data0, NULL, bi, minlen, + &amt); if (ret) { gfs2_glock_dq_uninit(&gh); goto out; @@ -1324,7 +1333,7 @@ int gfs2_fitrim(struct file *filp, void __user *argp) out: r.len = trimmed << 9; - if (argp && copy_to_user(argp, &r, sizeof(r))) + if (copy_to_user(argp, &r, sizeof(r))) return -EFAULT; return ret; diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index bc737261f234..d6488674d916 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -810,7 +810,8 @@ static void gfs2_dirty_inode(struct inode *inode, int flags) return; } need_unlock = 1; - } + } else if (WARN_ON_ONCE(ip->i_gl->gl_state != LM_ST_EXCLUSIVE)) + return; if (current->journal_info == NULL) { ret = gfs2_trans_begin(sdp, RES_DINODE, 0); diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c index adbd27875ef9..413627072f36 100644 --- a/fs/gfs2/trans.c +++ b/fs/gfs2/trans.c @@ -155,14 +155,22 @@ void gfs2_trans_add_bh(struct gfs2_glock *gl, struct buffer_head *bh, int meta) struct gfs2_sbd *sdp = gl->gl_sbd; struct gfs2_bufdata *bd; + lock_buffer(bh); + gfs2_log_lock(sdp); bd = bh->b_private; if (bd) gfs2_assert(sdp, bd->bd_gl == gl); else { + gfs2_log_unlock(sdp); + unlock_buffer(bh); gfs2_attach_bufdata(gl, bh, meta); bd = bh->b_private; + lock_buffer(bh); + gfs2_log_lock(sdp); } lops_add(sdp, bd); + gfs2_log_unlock(sdp); + unlock_buffer(bh); } void gfs2_trans_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd) diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c index 60ef3fb707ff..1506673c087e 100644 --- a/fs/jffs2/file.c +++ b/fs/jffs2/file.c @@ -138,33 +138,39 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, struct page *pg; struct inode *inode = mapping->host; struct jffs2_inode_info *f = JFFS2_INODE_INFO(inode); + struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb); + struct jffs2_raw_inode ri; + uint32_t alloc_len = 0; pgoff_t index = pos >> PAGE_CACHE_SHIFT; uint32_t pageofs = index << PAGE_CACHE_SHIFT; int ret = 0; + jffs2_dbg(1, "%s()\n", __func__); + + if (pageofs > inode->i_size) { + ret = jffs2_reserve_space(c, sizeof(ri), &alloc_len, + ALLOC_NORMAL, JFFS2_SUMMARY_INODE_SIZE); + if (ret) + return ret; + } + + mutex_lock(&f->sem); pg = grab_cache_page_write_begin(mapping, index, flags); - if (!pg) + if (!pg) { + if (alloc_len) + jffs2_complete_reservation(c); + mutex_unlock(&f->sem); return -ENOMEM; + } *pagep = pg; - jffs2_dbg(1, "%s()\n", __func__); - - if (pageofs > inode->i_size) { + if (alloc_len) { /* Make new hole frag from old EOF to new page */ - struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb); - struct jffs2_raw_inode ri; struct jffs2_full_dnode *fn; - uint32_t alloc_len; jffs2_dbg(1, "Writing new hole frag 0x%x-0x%x between current EOF and new page\n", (unsigned int)inode->i_size, pageofs); - ret = jffs2_reserve_space(c, sizeof(ri), &alloc_len, - ALLOC_NORMAL, JFFS2_SUMMARY_INODE_SIZE); - if (ret) - goto out_page; - - mutex_lock(&f->sem); memset(&ri, 0, sizeof(ri)); ri.magic = cpu_to_je16(JFFS2_MAGIC_BITMASK); @@ -191,7 +197,6 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, if (IS_ERR(fn)) { ret = PTR_ERR(fn); jffs2_complete_reservation(c); - mutex_unlock(&f->sem); goto out_page; } ret = jffs2_add_full_dnode_to_inode(c, f, fn); @@ -206,12 +211,10 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, jffs2_mark_node_obsolete(c, fn->raw); jffs2_free_full_dnode(fn); jffs2_complete_reservation(c); - mutex_unlock(&f->sem); goto out_page; } jffs2_complete_reservation(c); inode->i_size = pageofs; - mutex_unlock(&f->sem); } /* @@ -220,18 +223,18 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, * case of a short-copy. */ if (!PageUptodate(pg)) { - mutex_lock(&f->sem); ret = jffs2_do_readpage_nolock(inode, pg); - mutex_unlock(&f->sem); if (ret) goto out_page; } + mutex_unlock(&f->sem); jffs2_dbg(1, "end write_begin(). pg->flags %lx\n", pg->flags); return ret; out_page: unlock_page(pg); page_cache_release(pg); + mutex_unlock(&f->sem); return ret; } diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index f35794b97e8e..a50636025364 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -21,6 +21,7 @@ static bool should_merge(struct fsnotify_event *old, struct fsnotify_event *new) if ((old->path.mnt == new->path.mnt) && (old->path.dentry == new->path.dentry)) return true; + break; case (FSNOTIFY_EVENT_NONE): return true; default: diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 721d692fa8d4..6fcaeb8c902e 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -258,7 +258,8 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group, if (ret) goto out_close_fd; - fd_install(fd, f); + if (fd != FAN_NOFD) + fd_install(fd, f); return fanotify_event_metadata.event_len; out_close_fd: diff --git a/fs/proc/base.c b/fs/proc/base.c index 144a96732dd7..3c231adf8450 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -873,6 +873,113 @@ static const struct file_operations proc_environ_operations = { .release = mem_release, }; +static ssize_t oom_adj_read(struct file *file, char __user *buf, size_t count, + loff_t *ppos) +{ + struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode); + char buffer[PROC_NUMBUF]; + int oom_adj = OOM_ADJUST_MIN; + size_t len; + unsigned long flags; + + if (!task) + return -ESRCH; + if (lock_task_sighand(task, &flags)) { + if (task->signal->oom_score_adj == OOM_SCORE_ADJ_MAX) + oom_adj = OOM_ADJUST_MAX; + else + oom_adj = (task->signal->oom_score_adj * -OOM_DISABLE) / + OOM_SCORE_ADJ_MAX; + unlock_task_sighand(task, &flags); + } + put_task_struct(task); + len = snprintf(buffer, sizeof(buffer), "%d\n", oom_adj); + return simple_read_from_buffer(buf, count, ppos, buffer, len); +} + +static ssize_t oom_adj_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct task_struct *task; + char buffer[PROC_NUMBUF]; + int oom_adj; + unsigned long flags; + int err; + + memset(buffer, 0, sizeof(buffer)); + if (count > sizeof(buffer) - 1) + count = sizeof(buffer) - 1; + if (copy_from_user(buffer, buf, count)) { + err = -EFAULT; + goto out; + } + + err = kstrtoint(strstrip(buffer), 0, &oom_adj); + if (err) + goto out; + if ((oom_adj < OOM_ADJUST_MIN || oom_adj > OOM_ADJUST_MAX) && + oom_adj != OOM_DISABLE) { + err = -EINVAL; + goto out; + } + + task = get_proc_task(file->f_path.dentry->d_inode); + if (!task) { + err = -ESRCH; + goto out; + } + + task_lock(task); + if (!task->mm) { + err = -EINVAL; + goto err_task_lock; + } + + if (!lock_task_sighand(task, &flags)) { + err = -ESRCH; + goto err_task_lock; + } + + /* + * Scale /proc/pid/oom_score_adj appropriately ensuring that a maximum + * value is always attainable. + */ + if (oom_adj == OOM_ADJUST_MAX) + oom_adj = OOM_SCORE_ADJ_MAX; + else + oom_adj = (oom_adj * OOM_SCORE_ADJ_MAX) / -OOM_DISABLE; + + if (oom_adj < task->signal->oom_score_adj && + !capable(CAP_SYS_RESOURCE)) { + err = -EACCES; + goto err_sighand; + } + + /* + * /proc/pid/oom_adj is provided for legacy purposes, ask users to use + * /proc/pid/oom_score_adj instead. + */ + printk_once(KERN_WARNING "%s (%d): /proc/%d/oom_adj is deprecated, please use /proc/%d/oom_score_adj instead.\n", + current->comm, task_pid_nr(current), task_pid_nr(task), + task_pid_nr(task)); + + task->signal->oom_score_adj = oom_adj; + trace_oom_score_adj_update(task); +err_sighand: + unlock_task_sighand(task, &flags); +err_task_lock: + task_unlock(task); + put_task_struct(task); +out: + return err < 0 ? err : count; +} + +static const struct file_operations proc_oom_adj_operations = { + .read = oom_adj_read, + .write = oom_adj_write, + .llseek = generic_file_llseek, +}; + static ssize_t oom_score_adj_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { @@ -2598,6 +2705,7 @@ static const struct pid_entry tgid_base_stuff[] = { REG("cgroup", S_IRUGO, proc_cgroup_operations), #endif INF("oom_score", S_IRUGO, proc_oom_score), + REG("oom_adj", S_IRUGO|S_IWUSR, proc_oom_adj_operations), REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations), #ifdef CONFIG_AUDITSYSCALL REG("loginuid", S_IWUSR|S_IRUGO, proc_loginuid_operations), @@ -2964,6 +3072,7 @@ static const struct pid_entry tid_base_stuff[] = { REG("cgroup", S_IRUGO, proc_cgroup_operations), #endif INF("oom_score", S_IRUGO, proc_oom_score), + REG("oom_adj", S_IRUGO|S_IWUSR, proc_oom_adj_operations), REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations), #ifdef CONFIG_AUDITSYSCALL REG("loginuid", S_IWUSR|S_IRUGO, proc_loginuid_operations), diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index a40da07e93d6..947fbe06c3b1 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -161,6 +161,7 @@ static void pstore_console_write(struct console *con, const char *s, unsigned c) while (s < e) { unsigned long flags; + u64 id; if (c > psinfo->bufsize) c = psinfo->bufsize; @@ -172,7 +173,7 @@ static void pstore_console_write(struct console *con, const char *s, unsigned c) spin_lock_irqsave(&psinfo->buf_lock, flags); } memcpy(psinfo->buf, s, c); - psinfo->write(PSTORE_TYPE_CONSOLE, 0, NULL, 0, c, psinfo); + psinfo->write(PSTORE_TYPE_CONSOLE, 0, &id, 0, c, psinfo); spin_unlock_irqrestore(&psinfo->buf_lock, flags); s += c; c = e - s; diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index f27f01a98aa2..d83736fbc26c 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -1782,8 +1782,9 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th, BUG_ON(!th->t_trans_id); - dquot_initialize(inode); + reiserfs_write_unlock(inode->i_sb); err = dquot_alloc_inode(inode); + reiserfs_write_lock(inode->i_sb); if (err) goto out_end_trans; if (!dir->i_nlink) { @@ -1979,8 +1980,10 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th, out_end_trans: journal_end(th, th->t_super, th->t_blocks_allocated); + reiserfs_write_unlock(inode->i_sb); /* Drop can be outside and it needs more credits so it's better to have it outside */ dquot_drop(inode); + reiserfs_write_lock(inode->i_sb); inode->i_flags |= S_NOQUOTA; make_bad_inode(inode); @@ -3103,10 +3106,9 @@ int reiserfs_setattr(struct dentry *dentry, struct iattr *attr) /* must be turned off for recursive notify_change calls */ ia_valid = attr->ia_valid &= ~(ATTR_KILL_SUID|ATTR_KILL_SGID); - depth = reiserfs_write_lock_once(inode->i_sb); if (is_quota_modification(inode, attr)) dquot_initialize(inode); - + depth = reiserfs_write_lock_once(inode->i_sb); if (attr->ia_valid & ATTR_SIZE) { /* version 2 items will be caught by the s_maxbytes check ** done for us in vmtruncate @@ -3170,7 +3172,9 @@ int reiserfs_setattr(struct dentry *dentry, struct iattr *attr) error = journal_begin(&th, inode->i_sb, jbegin_count); if (error) goto out; + reiserfs_write_unlock_once(inode->i_sb, depth); error = dquot_transfer(inode, attr); + depth = reiserfs_write_lock_once(inode->i_sb); if (error) { journal_end(&th, inode->i_sb, jbegin_count); goto out; diff --git a/fs/reiserfs/stree.c b/fs/reiserfs/stree.c index f8afa4b162b8..2f40a4c70a4d 100644 --- a/fs/reiserfs/stree.c +++ b/fs/reiserfs/stree.c @@ -1968,7 +1968,9 @@ int reiserfs_paste_into_item(struct reiserfs_transaction_handle *th, struct tree key2type(&(key->on_disk_key))); #endif + reiserfs_write_unlock(inode->i_sb); retval = dquot_alloc_space_nodirty(inode, pasted_size); + reiserfs_write_lock(inode->i_sb); if (retval) { pathrelse(search_path); return retval; @@ -2061,9 +2063,11 @@ int reiserfs_insert_item(struct reiserfs_transaction_handle *th, "reiserquota insert_item(): allocating %u id=%u type=%c", quota_bytes, inode->i_uid, head2type(ih)); #endif + reiserfs_write_unlock(inode->i_sb); /* We can't dirty inode here. It would be immediately written but * appropriate stat item isn't inserted yet... */ retval = dquot_alloc_space_nodirty(inode, quota_bytes); + reiserfs_write_lock(inode->i_sb); if (retval) { pathrelse(path); return retval; diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index 1078ae179993..418bdc3a57da 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -298,7 +298,9 @@ static int finish_unfinished(struct super_block *s) retval = remove_save_link_only(s, &save_link_key, 0); continue; } + reiserfs_write_unlock(s); dquot_initialize(inode); + reiserfs_write_lock(s); if (truncate && S_ISDIR(inode->i_mode)) { /* We got a truncate request for a dir which is impossible. @@ -1335,7 +1337,7 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) kfree(qf_names[i]); #endif err = -EINVAL; - goto out_err; + goto out_unlock; } #ifdef CONFIG_QUOTA handle_quota_files(s, qf_names, &qfmt); @@ -1379,7 +1381,7 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) if (blocks) { err = reiserfs_resize(s, blocks); if (err != 0) - goto out_err; + goto out_unlock; } if (*mount_flags & MS_RDONLY) { @@ -1389,9 +1391,15 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) /* it is read-only already */ goto out_ok; + /* + * Drop write lock. Quota will retake it when needed and lock + * ordering requires calling dquot_suspend() without it. + */ + reiserfs_write_unlock(s); err = dquot_suspend(s, -1); if (err < 0) goto out_err; + reiserfs_write_lock(s); /* try to remount file system with read-only permissions */ if (sb_umount_state(rs) == REISERFS_VALID_FS @@ -1401,7 +1409,7 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) err = journal_begin(&th, s, 10); if (err) - goto out_err; + goto out_unlock; /* Mounting a rw partition read-only. */ reiserfs_prepare_for_journal(s, SB_BUFFER_WITH_SB(s), 1); @@ -1416,7 +1424,7 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) if (reiserfs_is_journal_aborted(journal)) { err = journal->j_errno; - goto out_err; + goto out_unlock; } handle_data_mode(s, mount_options); @@ -1425,7 +1433,7 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) s->s_flags &= ~MS_RDONLY; /* now it is safe to call journal_begin */ err = journal_begin(&th, s, 10); if (err) - goto out_err; + goto out_unlock; /* Mount a partition which is read-only, read-write */ reiserfs_prepare_for_journal(s, SB_BUFFER_WITH_SB(s), 1); @@ -1442,10 +1450,16 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) SB_JOURNAL(s)->j_must_wait = 1; err = journal_end(&th, s, 10); if (err) - goto out_err; + goto out_unlock; if (!(*mount_flags & MS_RDONLY)) { + /* + * Drop write lock. Quota will retake it when needed and lock + * ordering requires calling dquot_resume() without it. + */ + reiserfs_write_unlock(s); dquot_resume(s, -1); + reiserfs_write_lock(s); finish_unfinished(s); reiserfs_xattr_init(s, *mount_flags); } @@ -1455,9 +1469,10 @@ out_ok: reiserfs_write_unlock(s); return 0; +out_unlock: + reiserfs_write_unlock(s); out_err: kfree(new_opts); - reiserfs_write_unlock(s); return err; } @@ -2095,13 +2110,15 @@ static int reiserfs_write_dquot(struct dquot *dquot) REISERFS_QUOTA_TRANS_BLOCKS(dquot->dq_sb)); if (ret) goto out; + reiserfs_write_unlock(dquot->dq_sb); ret = dquot_commit(dquot); + reiserfs_write_lock(dquot->dq_sb); err = journal_end(&th, dquot->dq_sb, REISERFS_QUOTA_TRANS_BLOCKS(dquot->dq_sb)); if (!ret && err) ret = err; - out: +out: reiserfs_write_unlock(dquot->dq_sb); return ret; } @@ -2117,13 +2134,15 @@ static int reiserfs_acquire_dquot(struct dquot *dquot) REISERFS_QUOTA_INIT_BLOCKS(dquot->dq_sb)); if (ret) goto out; + reiserfs_write_unlock(dquot->dq_sb); ret = dquot_acquire(dquot); + reiserfs_write_lock(dquot->dq_sb); err = journal_end(&th, dquot->dq_sb, REISERFS_QUOTA_INIT_BLOCKS(dquot->dq_sb)); if (!ret && err) ret = err; - out: +out: reiserfs_write_unlock(dquot->dq_sb); return ret; } @@ -2137,19 +2156,21 @@ static int reiserfs_release_dquot(struct dquot *dquot) ret = journal_begin(&th, dquot->dq_sb, REISERFS_QUOTA_DEL_BLOCKS(dquot->dq_sb)); + reiserfs_write_unlock(dquot->dq_sb); if (ret) { /* Release dquot anyway to avoid endless cycle in dqput() */ dquot_release(dquot); goto out; } ret = dquot_release(dquot); + reiserfs_write_lock(dquot->dq_sb); err = journal_end(&th, dquot->dq_sb, REISERFS_QUOTA_DEL_BLOCKS(dquot->dq_sb)); if (!ret && err) ret = err; - out: reiserfs_write_unlock(dquot->dq_sb); +out: return ret; } @@ -2174,11 +2195,13 @@ static int reiserfs_write_info(struct super_block *sb, int type) ret = journal_begin(&th, sb, 2); if (ret) goto out; + reiserfs_write_unlock(sb); ret = dquot_commit_info(sb, type); + reiserfs_write_lock(sb); err = journal_end(&th, sb, 2); if (!ret && err) ret = err; - out: +out: reiserfs_write_unlock(sb); return ret; } @@ -2203,8 +2226,11 @@ static int reiserfs_quota_on(struct super_block *sb, int type, int format_id, struct reiserfs_transaction_handle th; int opt = type == USRQUOTA ? REISERFS_USRQUOTA : REISERFS_GRPQUOTA; - if (!(REISERFS_SB(sb)->s_mount_opt & (1 << opt))) - return -EINVAL; + reiserfs_write_lock(sb); + if (!(REISERFS_SB(sb)->s_mount_opt & (1 << opt))) { + err = -EINVAL; + goto out; + } /* Quotafile not on the same filesystem? */ if (path->dentry->d_sb != sb) { @@ -2246,8 +2272,10 @@ static int reiserfs_quota_on(struct super_block *sb, int type, int format_id, if (err) goto out; } - err = dquot_quota_on(sb, type, format_id, path); + reiserfs_write_unlock(sb); + return dquot_quota_on(sb, type, format_id, path); out: + reiserfs_write_unlock(sb); return err; } @@ -2320,7 +2348,9 @@ static ssize_t reiserfs_quota_write(struct super_block *sb, int type, tocopy = sb->s_blocksize - offset < towrite ? sb->s_blocksize - offset : towrite; tmp_bh.b_state = 0; + reiserfs_write_lock(sb); err = reiserfs_get_block(inode, blk, &tmp_bh, GET_BLOCK_CREATE); + reiserfs_write_unlock(sb); if (err) goto out; if (offset || tocopy != sb->s_blocksize) @@ -2336,10 +2366,12 @@ static ssize_t reiserfs_quota_write(struct super_block *sb, int type, flush_dcache_page(bh->b_page); set_buffer_uptodate(bh); unlock_buffer(bh); + reiserfs_write_lock(sb); reiserfs_prepare_for_journal(sb, bh, 1); journal_mark_dirty(current->journal_info, sb, bh); if (!journal_quota) reiserfs_add_ordered_list(inode, bh); + reiserfs_write_unlock(sb); brelse(bh); offset = 0; towrite -= tocopy; diff --git a/fs/ubifs/find.c b/fs/ubifs/find.c index 28ec13af28d9..2dcf3d473fec 100644 --- a/fs/ubifs/find.c +++ b/fs/ubifs/find.c @@ -681,8 +681,16 @@ int ubifs_find_free_leb_for_idx(struct ubifs_info *c) if (!lprops) { lprops = ubifs_fast_find_freeable(c); if (!lprops) { - ubifs_assert(c->freeable_cnt == 0); - if (c->lst.empty_lebs - c->lst.taken_empty_lebs > 0) { + /* + * The first condition means the following: go scan the + * LPT if there are uncategorized lprops, which means + * there may be freeable LEBs there (UBIFS does not + * store the information about freeable LEBs in the + * master node). + */ + if (c->in_a_category_cnt != c->main_lebs || + c->lst.empty_lebs - c->lst.taken_empty_lebs > 0) { + ubifs_assert(c->freeable_cnt == 0); lprops = scan_for_leb_for_idx(c); if (IS_ERR(lprops)) { err = PTR_ERR(lprops); diff --git a/fs/ubifs/lprops.c b/fs/ubifs/lprops.c index e5a2a35a46dc..46190a7c42a6 100644 --- a/fs/ubifs/lprops.c +++ b/fs/ubifs/lprops.c @@ -300,8 +300,11 @@ void ubifs_add_to_cat(struct ubifs_info *c, struct ubifs_lprops *lprops, default: ubifs_assert(0); } + lprops->flags &= ~LPROPS_CAT_MASK; lprops->flags |= cat; + c->in_a_category_cnt += 1; + ubifs_assert(c->in_a_category_cnt <= c->main_lebs); } /** @@ -334,6 +337,9 @@ static void ubifs_remove_from_cat(struct ubifs_info *c, default: ubifs_assert(0); } + + c->in_a_category_cnt -= 1; + ubifs_assert(c->in_a_category_cnt >= 0); } /** diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index 5486346d0a3f..d133c276fe05 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -1183,6 +1183,8 @@ struct ubifs_debug_info; * @freeable_list: list of freeable non-index LEBs (free + dirty == @leb_size) * @frdi_idx_list: list of freeable index LEBs (free + dirty == @leb_size) * @freeable_cnt: number of freeable LEBs in @freeable_list + * @in_a_category_cnt: count of lprops which are in a certain category, which + * basically meants that they were loaded from the flash * * @ltab_lnum: LEB number of LPT's own lprops table * @ltab_offs: offset of LPT's own lprops table @@ -1412,6 +1414,7 @@ struct ubifs_info { struct list_head freeable_list; struct list_head frdi_idx_list; int freeable_cnt; + int in_a_category_cnt; int ltab_lnum; int ltab_offs; diff --git a/fs/xfs/xfs_alloc.c b/fs/xfs/xfs_alloc.c index 4f33c32affe3..335206a9c698 100644 --- a/fs/xfs/xfs_alloc.c +++ b/fs/xfs/xfs_alloc.c @@ -1866,6 +1866,7 @@ xfs_alloc_fix_freelist( /* * Initialize the args structure. */ + memset(&targs, 0, sizeof(targs)); targs.tp = tp; targs.mp = mp; targs.agbp = agbp; @@ -2207,7 +2208,7 @@ xfs_alloc_read_agf( * group or loop over the allocation groups to find the result. */ int /* error */ -__xfs_alloc_vextent( +xfs_alloc_vextent( xfs_alloc_arg_t *args) /* allocation argument structure */ { xfs_agblock_t agsize; /* allocation group size */ @@ -2417,46 +2418,6 @@ error0: return error; } -static void -xfs_alloc_vextent_worker( - struct work_struct *work) -{ - struct xfs_alloc_arg *args = container_of(work, - struct xfs_alloc_arg, work); - unsigned long pflags; - - /* we are in a transaction context here */ - current_set_flags_nested(&pflags, PF_FSTRANS); - - args->result = __xfs_alloc_vextent(args); - complete(args->done); - - current_restore_flags_nested(&pflags, PF_FSTRANS); -} - -/* - * Data allocation requests often come in with little stack to work on. Push - * them off to a worker thread so there is lots of stack to use. Metadata - * requests, OTOH, are generally from low stack usage paths, so avoid the - * context switch overhead here. - */ -int -xfs_alloc_vextent( - struct xfs_alloc_arg *args) -{ - DECLARE_COMPLETION_ONSTACK(done); - - if (!args->userdata) - return __xfs_alloc_vextent(args); - - - args->done = &done; - INIT_WORK_ONSTACK(&args->work, xfs_alloc_vextent_worker); - queue_work(xfs_alloc_wq, &args->work); - wait_for_completion(&done); - return args->result; -} - /* * Free an extent. * Just break up the extent address and hand off to xfs_free_ag_extent diff --git a/fs/xfs/xfs_alloc.h b/fs/xfs/xfs_alloc.h index 93be4a667ca1..feacb061bab7 100644 --- a/fs/xfs/xfs_alloc.h +++ b/fs/xfs/xfs_alloc.h @@ -120,9 +120,6 @@ typedef struct xfs_alloc_arg { char isfl; /* set if is freelist blocks - !acctg */ char userdata; /* set if this is user data */ xfs_fsblock_t firstblock; /* io first block allocated */ - struct completion *done; - struct work_struct work; - int result; } xfs_alloc_arg_t; /* diff --git a/fs/xfs/xfs_alloc_btree.c b/fs/xfs/xfs_alloc_btree.c index f1647caace8f..f7876c6d6165 100644 --- a/fs/xfs/xfs_alloc_btree.c +++ b/fs/xfs/xfs_alloc_btree.c @@ -121,6 +121,8 @@ xfs_allocbt_free_block( xfs_extent_busy_insert(cur->bc_tp, be32_to_cpu(agf->agf_seqno), bno, 1, XFS_EXTENT_BUSY_SKIP_DISCARD); xfs_trans_agbtree_delta(cur->bc_tp, -1); + + xfs_trans_binval(cur->bc_tp, bp); return 0; } diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index e562dd43f41f..e57e2daa357c 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -481,11 +481,17 @@ static inline int bio_add_buffer(struct bio *bio, struct buffer_head *bh) * * The fix is two passes across the ioend list - one to start writeback on the * buffer_heads, and then submit them for I/O on the second pass. + * + * If @fail is non-zero, it means that we have a situation where some part of + * the submission process has failed after we have marked paged for writeback + * and unlocked them. In this situation, we need to fail the ioend chain rather + * than submit it to IO. This typically only happens on a filesystem shutdown. */ STATIC void xfs_submit_ioend( struct writeback_control *wbc, - xfs_ioend_t *ioend) + xfs_ioend_t *ioend, + int fail) { xfs_ioend_t *head = ioend; xfs_ioend_t *next; @@ -506,6 +512,18 @@ xfs_submit_ioend( next = ioend->io_list; bio = NULL; + /* + * If we are failing the IO now, just mark the ioend with an + * error and finish it. This will run IO completion immediately + * as there is only one reference to the ioend at this point in + * time. + */ + if (fail) { + ioend->io_error = -fail; + xfs_finish_ioend(ioend); + continue; + } + for (bh = ioend->io_buffer_head; bh; bh = bh->b_private) { if (!bio) { @@ -1060,7 +1078,18 @@ xfs_vm_writepage( xfs_start_page_writeback(page, 1, count); - if (ioend && imap_valid) { + /* if there is no IO to be submitted for this page, we are done */ + if (!ioend) + return 0; + + ASSERT(iohead); + + /* + * Any errors from this point onwards need tobe reported through the IO + * completion path as we have marked the initial page as under writeback + * and unlocked it. + */ + if (imap_valid) { xfs_off_t end_index; end_index = imap.br_startoff + imap.br_blockcount; @@ -1079,20 +1108,15 @@ xfs_vm_writepage( wbc, end_index); } - if (iohead) { - /* - * Reserve log space if we might write beyond the on-disk - * inode size. - */ - if (ioend->io_type != XFS_IO_UNWRITTEN && - xfs_ioend_is_append(ioend)) { - err = xfs_setfilesize_trans_alloc(ioend); - if (err) - goto error; - } - xfs_submit_ioend(wbc, iohead); - } + /* + * Reserve log space if we might write beyond the on-disk inode size. + */ + err = 0; + if (ioend->io_type != XFS_IO_UNWRITTEN && xfs_ioend_is_append(ioend)) + err = xfs_setfilesize_trans_alloc(ioend); + + xfs_submit_ioend(wbc, iohead, err); return 0; diff --git a/fs/xfs/xfs_attr_leaf.c b/fs/xfs/xfs_attr_leaf.c index d330111ca738..70eec1829776 100644 --- a/fs/xfs/xfs_attr_leaf.c +++ b/fs/xfs/xfs_attr_leaf.c @@ -1291,6 +1291,7 @@ xfs_attr_leaf_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1, leaf2 = blk2->bp->b_addr; ASSERT(leaf1->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC)); ASSERT(leaf2->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC)); + ASSERT(leaf2->hdr.count == 0); args = state->args; trace_xfs_attr_leaf_rebalance(args); @@ -1361,6 +1362,7 @@ xfs_attr_leaf_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1, * I assert that since all callers pass in an empty * second buffer, this code should never execute. */ + ASSERT(0); /* * Figure the total bytes to be added to the destination leaf. @@ -1422,10 +1424,24 @@ xfs_attr_leaf_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1, args->index2 = 0; args->blkno2 = blk2->blkno; } else { + /* + * On a double leaf split, the original attr location + * is already stored in blkno2/index2, so don't + * overwrite it overwise we corrupt the tree. + */ blk2->index = blk1->index - be16_to_cpu(leaf1->hdr.count); - args->index = args->index2 = blk2->index; - args->blkno = args->blkno2 = blk2->blkno; + args->index = blk2->index; + args->blkno = blk2->blkno; + if (!state->extravalid) { + /* + * set the new attr location to match the old + * one and let the higher level split code + * decide where in the leaf to place it. + */ + args->index2 = blk2->index; + args->blkno2 = blk2->blkno; + } } } else { ASSERT(state->inleaf == 1); diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c index 848ffa77707b..83d0cf3df930 100644 --- a/fs/xfs/xfs_bmap.c +++ b/fs/xfs/xfs_bmap.c @@ -2437,6 +2437,7 @@ xfs_bmap_btalloc( * Normal allocation, done through xfs_alloc_vextent. */ tryagain = isaligned = 0; + memset(&args, 0, sizeof(args)); args.tp = ap->tp; args.mp = mp; args.fsbno = ap->blkno; @@ -3082,6 +3083,7 @@ xfs_bmap_extents_to_btree( * Convert to a btree with two levels, one record in root. */ XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_BTREE); + memset(&args, 0, sizeof(args)); args.tp = tp; args.mp = mp; args.firstblock = *firstblock; @@ -3237,6 +3239,7 @@ xfs_bmap_local_to_extents( xfs_buf_t *bp; /* buffer for extent block */ xfs_bmbt_rec_host_t *ep;/* extent record pointer */ + memset(&args, 0, sizeof(args)); args.tp = tp; args.mp = ip->i_mount; args.firstblock = *firstblock; @@ -4616,12 +4619,11 @@ xfs_bmapi_delay( STATIC int -xfs_bmapi_allocate( - struct xfs_bmalloca *bma, - int flags) +__xfs_bmapi_allocate( + struct xfs_bmalloca *bma) { struct xfs_mount *mp = bma->ip->i_mount; - int whichfork = (flags & XFS_BMAPI_ATTRFORK) ? + int whichfork = (bma->flags & XFS_BMAPI_ATTRFORK) ? XFS_ATTR_FORK : XFS_DATA_FORK; struct xfs_ifork *ifp = XFS_IFORK_PTR(bma->ip, whichfork); int tmp_logflags = 0; @@ -4654,24 +4656,27 @@ xfs_bmapi_allocate( * Indicate if this is the first user data in the file, or just any * user data. */ - if (!(flags & XFS_BMAPI_METADATA)) { + if (!(bma->flags & XFS_BMAPI_METADATA)) { bma->userdata = (bma->offset == 0) ? XFS_ALLOC_INITIAL_USER_DATA : XFS_ALLOC_USERDATA; } - bma->minlen = (flags & XFS_BMAPI_CONTIG) ? bma->length : 1; + bma->minlen = (bma->flags & XFS_BMAPI_CONTIG) ? bma->length : 1; /* * Only want to do the alignment at the eof if it is userdata and * allocation length is larger than a stripe unit. */ if (mp->m_dalign && bma->length >= mp->m_dalign && - !(flags & XFS_BMAPI_METADATA) && whichfork == XFS_DATA_FORK) { + !(bma->flags & XFS_BMAPI_METADATA) && whichfork == XFS_DATA_FORK) { error = xfs_bmap_isaeof(bma, whichfork); if (error) return error; } + if (bma->flags & XFS_BMAPI_STACK_SWITCH) + bma->stack_switch = 1; + error = xfs_bmap_alloc(bma); if (error) return error; @@ -4706,7 +4711,7 @@ xfs_bmapi_allocate( * A wasdelay extent has been initialized, so shouldn't be flagged * as unwritten. */ - if (!bma->wasdel && (flags & XFS_BMAPI_PREALLOC) && + if (!bma->wasdel && (bma->flags & XFS_BMAPI_PREALLOC) && xfs_sb_version_hasextflgbit(&mp->m_sb)) bma->got.br_state = XFS_EXT_UNWRITTEN; @@ -4734,6 +4739,45 @@ xfs_bmapi_allocate( return 0; } +static void +xfs_bmapi_allocate_worker( + struct work_struct *work) +{ + struct xfs_bmalloca *args = container_of(work, + struct xfs_bmalloca, work); + unsigned long pflags; + + /* we are in a transaction context here */ + current_set_flags_nested(&pflags, PF_FSTRANS); + + args->result = __xfs_bmapi_allocate(args); + complete(args->done); + + current_restore_flags_nested(&pflags, PF_FSTRANS); +} + +/* + * Some allocation requests often come in with little stack to work on. Push + * them off to a worker thread so there is lots of stack to use. Otherwise just + * call directly to avoid the context switch overhead here. + */ +int +xfs_bmapi_allocate( + struct xfs_bmalloca *args) +{ + DECLARE_COMPLETION_ONSTACK(done); + + if (!args->stack_switch) + return __xfs_bmapi_allocate(args); + + + args->done = &done; + INIT_WORK_ONSTACK(&args->work, xfs_bmapi_allocate_worker); + queue_work(xfs_alloc_wq, &args->work); + wait_for_completion(&done); + return args->result; +} + STATIC int xfs_bmapi_convert_unwritten( struct xfs_bmalloca *bma, @@ -4919,6 +4963,7 @@ xfs_bmapi_write( bma.conv = !!(flags & XFS_BMAPI_CONVERT); bma.wasdel = wasdelay; bma.offset = bno; + bma.flags = flags; /* * There's a 32/64 bit type mismatch between the @@ -4934,7 +4979,7 @@ xfs_bmapi_write( ASSERT(len > 0); ASSERT(bma.length > 0); - error = xfs_bmapi_allocate(&bma, flags); + error = xfs_bmapi_allocate(&bma); if (error) goto error0; if (bma.blkno == NULLFSBLOCK) diff --git a/fs/xfs/xfs_bmap.h b/fs/xfs/xfs_bmap.h index 803b56d7ce16..5f469c3516eb 100644 --- a/fs/xfs/xfs_bmap.h +++ b/fs/xfs/xfs_bmap.h @@ -77,6 +77,7 @@ typedef struct xfs_bmap_free * from written to unwritten, otherwise convert from unwritten to written. */ #define XFS_BMAPI_CONVERT 0x040 +#define XFS_BMAPI_STACK_SWITCH 0x080 #define XFS_BMAPI_FLAGS \ { XFS_BMAPI_ENTIRE, "ENTIRE" }, \ @@ -85,7 +86,8 @@ typedef struct xfs_bmap_free { XFS_BMAPI_PREALLOC, "PREALLOC" }, \ { XFS_BMAPI_IGSTATE, "IGSTATE" }, \ { XFS_BMAPI_CONTIG, "CONTIG" }, \ - { XFS_BMAPI_CONVERT, "CONVERT" } + { XFS_BMAPI_CONVERT, "CONVERT" }, \ + { XFS_BMAPI_STACK_SWITCH, "STACK_SWITCH" } static inline int xfs_bmapi_aflag(int w) @@ -133,6 +135,11 @@ typedef struct xfs_bmalloca { char userdata;/* set if is user data */ char aeof; /* allocated space at eof */ char conv; /* overwriting unwritten extents */ + char stack_switch; + int flags; + struct completion *done; + struct work_struct work; + int result; } xfs_bmalloca_t; /* diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 933b7930b863..4b0b8dd1b7b0 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -1197,9 +1197,14 @@ xfs_buf_bio_end_io( { xfs_buf_t *bp = (xfs_buf_t *)bio->bi_private; - xfs_buf_ioerror(bp, -error); + /* + * don't overwrite existing errors - otherwise we can lose errors on + * buffers that require multiple bios to complete. + */ + if (!bp->b_error) + xfs_buf_ioerror(bp, -error); - if (!error && xfs_buf_is_vmapped(bp) && (bp->b_flags & XBF_READ)) + if (!bp->b_error && xfs_buf_is_vmapped(bp) && (bp->b_flags & XBF_READ)) invalidate_kernel_vmap_range(bp->b_addr, xfs_buf_vmap_len(bp)); _xfs_buf_ioend(bp, 1); @@ -1279,6 +1284,11 @@ next_chunk: if (size) goto next_chunk; } else { + /* + * This is guaranteed not to be the last io reference count + * because the caller (xfs_buf_iorequest) holds a count itself. + */ + atomic_dec(&bp->b_io_remaining); xfs_buf_ioerror(bp, EIO); bio_put(bio); } diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index a8d0ed911196..becf4a97efc6 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -526,7 +526,25 @@ xfs_buf_item_unpin( } xfs_buf_relse(bp); } else if (freed && remove) { + /* + * There are currently two references to the buffer - the active + * LRU reference and the buf log item. What we are about to do + * here - simulate a failed IO completion - requires 3 + * references. + * + * The LRU reference is removed by the xfs_buf_stale() call. The + * buf item reference is removed by the xfs_buf_iodone() + * callback that is run by xfs_buf_do_callbacks() during ioend + * processing (via the bp->b_iodone callback), and then finally + * the ioend processing will drop the IO reference if the buffer + * is marked XBF_ASYNC. + * + * Hence we need to take an additional reference here so that IO + * completion processing doesn't free the buffer prematurely. + */ xfs_buf_lock(bp); + xfs_buf_hold(bp); + bp->b_flags |= XBF_ASYNC; xfs_buf_ioerror(bp, EIO); XFS_BUF_UNDONE(bp); xfs_buf_stale(bp); diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index c25b094efbf7..4beaede43277 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -399,9 +399,26 @@ xfs_growfs_data_private( /* update secondary superblocks. */ for (agno = 1; agno < nagcount; agno++) { - error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp, + error = 0; + /* + * new secondary superblocks need to be zeroed, not read from + * disk as the contents of the new area we are growing into is + * completely unknown. + */ + if (agno < oagcount) { + error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp, XFS_AGB_TO_DADDR(mp, agno, XFS_SB_BLOCK(mp)), XFS_FSS_TO_BB(mp, 1), 0, &bp); + } else { + bp = xfs_trans_get_buf(NULL, mp->m_ddev_targp, + XFS_AGB_TO_DADDR(mp, agno, XFS_SB_BLOCK(mp)), + XFS_FSS_TO_BB(mp, 1), 0); + if (bp) + xfs_buf_zero(bp, 0, BBTOB(bp->b_length)); + else + error = ENOMEM; + } + if (error) { xfs_warn(mp, "error %d reading secondary superblock for ag %d", @@ -423,7 +440,7 @@ xfs_growfs_data_private( break; /* no point in continuing */ } } - return 0; + return error; error0: xfs_trans_cancel(tp, XFS_TRANS_ABORT); diff --git a/fs/xfs/xfs_ialloc.c b/fs/xfs/xfs_ialloc.c index 445bf1aef31c..c5c4ef4f2bdb 100644 --- a/fs/xfs/xfs_ialloc.c +++ b/fs/xfs/xfs_ialloc.c @@ -250,6 +250,7 @@ xfs_ialloc_ag_alloc( /* boundary */ struct xfs_perag *pag; + memset(&args, 0, sizeof(args)); args.tp = tp; args.mp = tp->t_mountp; diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 2778258fcfa2..1938b41ee9f5 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -1509,7 +1509,8 @@ xfs_ifree_cluster( * to mark all the active inodes on the buffer stale. */ bp = xfs_trans_get_buf(tp, mp->m_ddev_targp, blkno, - mp->m_bsize * blks_per_cluster, 0); + mp->m_bsize * blks_per_cluster, + XBF_UNMAPPED); if (!bp) return ENOMEM; diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 8305f2ac6773..c1df3c623de2 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -70,7 +70,7 @@ xfs_find_handle( int hsize; xfs_handle_t handle; struct inode *inode; - struct fd f; + struct fd f = {0}; struct path path; int error; struct xfs_inode *ip; diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 973dff6ad935..7f537663365b 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -584,7 +584,9 @@ xfs_iomap_write_allocate( * pointer that the caller gave to us. */ error = xfs_bmapi_write(tp, ip, map_start_fsb, - count_fsb, 0, &first_block, 1, + count_fsb, + XFS_BMAPI_STACK_SWITCH, + &first_block, 1, imap, &nimaps, &free_list); if (error) goto trans_cancel; diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index 7f4f9370d0e7..4dad756962d0 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -2387,14 +2387,27 @@ xlog_state_do_callback( /* - * update the last_sync_lsn before we drop the + * Completion of a iclog IO does not imply that + * a transaction has completed, as transactions + * can be large enough to span many iclogs. We + * cannot change the tail of the log half way + * through a transaction as this may be the only + * transaction in the log and moving th etail to + * point to the middle of it will prevent + * recovery from finding the start of the + * transaction. Hence we should only update the + * last_sync_lsn if this iclog contains + * transaction completion callbacks on it. + * + * We have to do this before we drop the * icloglock to ensure we are the only one that * can update it. */ ASSERT(XFS_LSN_CMP(atomic64_read(&log->l_last_sync_lsn), be64_to_cpu(iclog->ic_header.h_lsn)) <= 0); - atomic64_set(&log->l_last_sync_lsn, - be64_to_cpu(iclog->ic_header.h_lsn)); + if (iclog->ic_callback) + atomic64_set(&log->l_last_sync_lsn, + be64_to_cpu(iclog->ic_header.h_lsn)); } else ioerrors++; diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index 5da3ace352bf..d308749fabf1 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -3541,7 +3541,7 @@ xlog_do_recovery_pass( * - order is important. */ error = xlog_bread_offset(log, 0, - bblks - split_bblks, hbp, + bblks - split_bblks, dbp, offset + BBTOB(split_bblks)); if (error) goto bread_err2; |