diff options
Diffstat (limited to 'fs')
62 files changed, 1197 insertions, 771 deletions
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 0236de711989..1204c8ef6f32 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -7466,6 +7466,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root, int err = 0; int ret; int level; + bool root_dropped = false; path = btrfs_alloc_path(); if (!path) { @@ -7523,6 +7524,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root, while (1) { btrfs_tree_lock(path->nodes[level]); btrfs_set_lock_blocking(path->nodes[level]); + path->locks[level] = BTRFS_WRITE_LOCK_BLOCKING; ret = btrfs_lookup_extent_info(trans, root, path->nodes[level]->start, @@ -7538,6 +7540,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root, break; btrfs_tree_unlock(path->nodes[level]); + path->locks[level] = 0; WARN_ON(wc->refs[level] != 1); level--; } @@ -7552,11 +7555,6 @@ int btrfs_drop_snapshot(struct btrfs_root *root, wc->reada_count = BTRFS_NODEPTRS_PER_BLOCK(root); while (1) { - if (!for_reloc && btrfs_need_cleaner_sleep(root)) { - pr_debug("btrfs: drop snapshot early exit\n"); - err = -EAGAIN; - goto out_end_trans; - } ret = walk_down_tree(trans, root, path, wc); if (ret < 0) { @@ -7584,7 +7582,8 @@ int btrfs_drop_snapshot(struct btrfs_root *root, } BUG_ON(wc->level == 0); - if (btrfs_should_end_transaction(trans, tree_root)) { + if (btrfs_should_end_transaction(trans, tree_root) || + (!for_reloc && btrfs_need_cleaner_sleep(root))) { ret = btrfs_update_root(trans, tree_root, &root->root_key, root_item); @@ -7595,6 +7594,12 @@ int btrfs_drop_snapshot(struct btrfs_root *root, } btrfs_end_transaction_throttle(trans, tree_root); + if (!for_reloc && btrfs_need_cleaner_sleep(root)) { + pr_debug("btrfs: drop snapshot early exit\n"); + err = -EAGAIN; + goto out_free; + } + trans = btrfs_start_transaction(tree_root, 0); if (IS_ERR(trans)) { err = PTR_ERR(trans); @@ -7639,12 +7644,22 @@ int btrfs_drop_snapshot(struct btrfs_root *root, free_extent_buffer(root->commit_root); btrfs_put_fs_root(root); } + root_dropped = true; out_end_trans: btrfs_end_transaction_throttle(trans, tree_root); out_free: kfree(wc); btrfs_free_path(path); out: + /* + * So if we need to stop dropping the snapshot for whatever reason we + * need to make sure to add it back to the dead root list so that we + * keep trying to do the work later. This also cleans up roots if we + * don't have it in the radix (like when we recover after a power fail + * or unmount) so we don't leak memory. + */ + if (root_dropped == false) + btrfs_add_dead_root(root); if (err) btrfs_std_error(root->fs_info, err); return err; diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 4ba2a69a60ad..64a157becbe5 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -2495,7 +2495,7 @@ again: ret = scrub_extent(sctx, extent_logical, extent_len, extent_physical, extent_dev, flags, generation, extent_mirror_num, - extent_physical); + extent_logical - logical + physical); if (ret) goto out; diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c index 3d8bf941d126..45e57cc38200 100644 --- a/fs/cifs/cifsencrypt.c +++ b/fs/cifs/cifsencrypt.c @@ -1,7 +1,7 @@ /* * fs/cifs/cifsencrypt.c * - * Copyright (C) International Business Machines Corp., 2005,2006 + * Copyright (C) International Business Machines Corp., 2005,2013 * Author(s): Steve French (sfrench@us.ibm.com) * * This library is free software; you can redistribute it and/or modify @@ -31,6 +31,36 @@ #include <linux/random.h> #include <linux/highmem.h> +static int +cifs_crypto_shash_md5_allocate(struct TCP_Server_Info *server) +{ + int rc; + unsigned int size; + + if (server->secmech.sdescmd5 != NULL) + return 0; /* already allocated */ + + server->secmech.md5 = crypto_alloc_shash("md5", 0, 0); + if (IS_ERR(server->secmech.md5)) { + cifs_dbg(VFS, "could not allocate crypto md5\n"); + return PTR_ERR(server->secmech.md5); + } + + size = sizeof(struct shash_desc) + + crypto_shash_descsize(server->secmech.md5); + server->secmech.sdescmd5 = kmalloc(size, GFP_KERNEL); + if (!server->secmech.sdescmd5) { + rc = -ENOMEM; + crypto_free_shash(server->secmech.md5); + server->secmech.md5 = NULL; + return rc; + } + server->secmech.sdescmd5->shash.tfm = server->secmech.md5; + server->secmech.sdescmd5->shash.flags = 0x0; + + return 0; +} + /* * Calculate and return the CIFS signature based on the mac key and SMB PDU. * The 16 byte signature must be allocated by the caller. Note we only use the @@ -50,8 +80,11 @@ static int cifs_calc_signature(struct smb_rqst *rqst, return -EINVAL; if (!server->secmech.sdescmd5) { - cifs_dbg(VFS, "%s: Can't generate signature\n", __func__); - return -1; + rc = cifs_crypto_shash_md5_allocate(server); + if (rc) { + cifs_dbg(VFS, "%s: Can't alloc md5 crypto\n", __func__); + return -1; + } } rc = crypto_shash_init(&server->secmech.sdescmd5->shash); @@ -556,6 +589,33 @@ CalcNTLMv2_response(const struct cifs_ses *ses, char *ntlmv2_hash) return rc; } +static int crypto_hmacmd5_alloc(struct TCP_Server_Info *server) +{ + unsigned int size; + + /* check if already allocated */ + if (server->secmech.sdeschmacmd5) + return 0; + + server->secmech.hmacmd5 = crypto_alloc_shash("hmac(md5)", 0, 0); + if (IS_ERR(server->secmech.hmacmd5)) { + cifs_dbg(VFS, "could not allocate crypto hmacmd5\n"); + return PTR_ERR(server->secmech.hmacmd5); + } + + size = sizeof(struct shash_desc) + + crypto_shash_descsize(server->secmech.hmacmd5); + server->secmech.sdeschmacmd5 = kmalloc(size, GFP_KERNEL); + if (!server->secmech.sdeschmacmd5) { + crypto_free_shash(server->secmech.hmacmd5); + server->secmech.hmacmd5 = NULL; + return -ENOMEM; + } + server->secmech.sdeschmacmd5->shash.tfm = server->secmech.hmacmd5; + server->secmech.sdeschmacmd5->shash.flags = 0x0; + + return 0; +} int setup_ntlmv2_rsp(struct cifs_ses *ses, const struct nls_table *nls_cp) @@ -606,6 +666,12 @@ setup_ntlmv2_rsp(struct cifs_ses *ses, const struct nls_table *nls_cp) memcpy(ses->auth_key.response + baselen, tiblob, tilen); + rc = crypto_hmacmd5_alloc(ses->server); + if (rc) { + cifs_dbg(VFS, "could not crypto alloc hmacmd5 rc %d\n", rc); + goto setup_ntlmv2_rsp_ret; + } + /* calculate ntlmv2_hash */ rc = calc_ntlmv2_hash(ses, ntlmv2_hash, nls_cp); if (rc) { @@ -705,123 +771,32 @@ calc_seckey(struct cifs_ses *ses) void cifs_crypto_shash_release(struct TCP_Server_Info *server) { - if (server->secmech.cmacaes) + if (server->secmech.cmacaes) { crypto_free_shash(server->secmech.cmacaes); + server->secmech.cmacaes = NULL; + } - if (server->secmech.hmacsha256) + if (server->secmech.hmacsha256) { crypto_free_shash(server->secmech.hmacsha256); + server->secmech.hmacsha256 = NULL; + } - if (server->secmech.md5) + if (server->secmech.md5) { crypto_free_shash(server->secmech.md5); + server->secmech.md5 = NULL; + } - if (server->secmech.hmacmd5) + if (server->secmech.hmacmd5) { crypto_free_shash(server->secmech.hmacmd5); + server->secmech.hmacmd5 = NULL; + } kfree(server->secmech.sdesccmacaes); - + server->secmech.sdesccmacaes = NULL; kfree(server->secmech.sdeschmacsha256); - + server->secmech.sdeschmacsha256 = NULL; kfree(server->secmech.sdeschmacmd5); - + server->secmech.sdeschmacmd5 = NULL; kfree(server->secmech.sdescmd5); -} - -int -cifs_crypto_shash_allocate(struct TCP_Server_Info *server) -{ - int rc; - unsigned int size; - - server->secmech.hmacmd5 = crypto_alloc_shash("hmac(md5)", 0, 0); - if (IS_ERR(server->secmech.hmacmd5)) { - cifs_dbg(VFS, "could not allocate crypto hmacmd5\n"); - return PTR_ERR(server->secmech.hmacmd5); - } - - server->secmech.md5 = crypto_alloc_shash("md5", 0, 0); - if (IS_ERR(server->secmech.md5)) { - cifs_dbg(VFS, "could not allocate crypto md5\n"); - rc = PTR_ERR(server->secmech.md5); - goto crypto_allocate_md5_fail; - } - - server->secmech.hmacsha256 = crypto_alloc_shash("hmac(sha256)", 0, 0); - if (IS_ERR(server->secmech.hmacsha256)) { - cifs_dbg(VFS, "could not allocate crypto hmacsha256\n"); - rc = PTR_ERR(server->secmech.hmacsha256); - goto crypto_allocate_hmacsha256_fail; - } - - server->secmech.cmacaes = crypto_alloc_shash("cmac(aes)", 0, 0); - if (IS_ERR(server->secmech.cmacaes)) { - cifs_dbg(VFS, "could not allocate crypto cmac-aes"); - rc = PTR_ERR(server->secmech.cmacaes); - goto crypto_allocate_cmacaes_fail; - } - - size = sizeof(struct shash_desc) + - crypto_shash_descsize(server->secmech.hmacmd5); - server->secmech.sdeschmacmd5 = kmalloc(size, GFP_KERNEL); - if (!server->secmech.sdeschmacmd5) { - rc = -ENOMEM; - goto crypto_allocate_hmacmd5_sdesc_fail; - } - server->secmech.sdeschmacmd5->shash.tfm = server->secmech.hmacmd5; - server->secmech.sdeschmacmd5->shash.flags = 0x0; - - size = sizeof(struct shash_desc) + - crypto_shash_descsize(server->secmech.md5); - server->secmech.sdescmd5 = kmalloc(size, GFP_KERNEL); - if (!server->secmech.sdescmd5) { - rc = -ENOMEM; - goto crypto_allocate_md5_sdesc_fail; - } - server->secmech.sdescmd5->shash.tfm = server->secmech.md5; - server->secmech.sdescmd5->shash.flags = 0x0; - - size = sizeof(struct shash_desc) + - crypto_shash_descsize(server->secmech.hmacsha256); - server->secmech.sdeschmacsha256 = kmalloc(size, GFP_KERNEL); - if (!server->secmech.sdeschmacsha256) { - rc = -ENOMEM; - goto crypto_allocate_hmacsha256_sdesc_fail; - } - server->secmech.sdeschmacsha256->shash.tfm = server->secmech.hmacsha256; - server->secmech.sdeschmacsha256->shash.flags = 0x0; - - size = sizeof(struct shash_desc) + - crypto_shash_descsize(server->secmech.cmacaes); - server->secmech.sdesccmacaes = kmalloc(size, GFP_KERNEL); - if (!server->secmech.sdesccmacaes) { - cifs_dbg(VFS, "%s: Can't alloc cmacaes\n", __func__); - rc = -ENOMEM; - goto crypto_allocate_cmacaes_sdesc_fail; - } - server->secmech.sdesccmacaes->shash.tfm = server->secmech.cmacaes; - server->secmech.sdesccmacaes->shash.flags = 0x0; - - return 0; - -crypto_allocate_cmacaes_sdesc_fail: - kfree(server->secmech.sdeschmacsha256); - -crypto_allocate_hmacsha256_sdesc_fail: - kfree(server->secmech.sdescmd5); - -crypto_allocate_md5_sdesc_fail: - kfree(server->secmech.sdeschmacmd5); - -crypto_allocate_hmacmd5_sdesc_fail: - crypto_free_shash(server->secmech.cmacaes); - -crypto_allocate_cmacaes_fail: - crypto_free_shash(server->secmech.hmacsha256); - -crypto_allocate_hmacsha256_fail: - crypto_free_shash(server->secmech.md5); - -crypto_allocate_md5_fail: - crypto_free_shash(server->secmech.hmacmd5); - - return rc; + server->secmech.sdescmd5 = NULL; } diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index e66b08882548..1fdc37041057 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -194,6 +194,7 @@ struct cifs_writedata; struct cifs_io_parms; struct cifs_search_info; struct cifsInodeInfo; +struct cifs_open_parms; struct smb_version_operations { int (*send_cancel)(struct TCP_Server_Info *, void *, @@ -307,9 +308,8 @@ struct smb_version_operations { const char *, const char *, struct cifs_sb_info *); /* open a file for non-posix mounts */ - int (*open)(const unsigned int, struct cifs_tcon *, const char *, int, - int, int, struct cifs_fid *, __u32 *, FILE_ALL_INFO *, - struct cifs_sb_info *); + int (*open)(const unsigned int, struct cifs_open_parms *, + __u32 *, FILE_ALL_INFO *); /* set fid protocol-specific info */ void (*set_fid)(struct cifsFileInfo *, struct cifs_fid *, __u32); /* close a file */ @@ -912,6 +912,17 @@ struct cifs_search_info { bool smallBuf:1; /* so we know which buf_release function to call */ }; +struct cifs_open_parms { + struct cifs_tcon *tcon; + struct cifs_sb_info *cifs_sb; + int disposition; + int desired_access; + int create_options; + const char *path; + struct cifs_fid *fid; + bool reconnect:1; +}; + struct cifs_fid { __u16 netfid; #ifdef CONFIG_CIFS_SMB2 diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index c8ff018fae68..f7e584d047e2 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -433,7 +433,6 @@ extern int SMBNTencrypt(unsigned char *, unsigned char *, unsigned char *, const struct nls_table *); extern int setup_ntlm_response(struct cifs_ses *, const struct nls_table *); extern int setup_ntlmv2_rsp(struct cifs_ses *, const struct nls_table *); -extern int cifs_crypto_shash_allocate(struct TCP_Server_Info *); extern void cifs_crypto_shash_release(struct TCP_Server_Info *); extern int calc_seckey(struct cifs_ses *); extern void generate_smb3signingkey(struct TCP_Server_Info *); diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index afcb8a1a33b7..fa68813396b5 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -2108,12 +2108,6 @@ cifs_get_tcp_session(struct smb_vol *volume_info) goto out_err; } - rc = cifs_crypto_shash_allocate(tcp_ses); - if (rc) { - cifs_dbg(VFS, "could not setup hash structures rc %d\n", rc); - goto out_err; - } - tcp_ses->ops = volume_info->ops; tcp_ses->vals = volume_info->vals; cifs_set_net_ns(tcp_ses, get_net(current->nsproxy->net_ns)); diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index 5175aebf6737..d62ce0d48141 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -204,6 +204,7 @@ cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned int xid, struct inode *newinode = NULL; int disposition; struct TCP_Server_Info *server = tcon->ses->server; + struct cifs_open_parms oparms; *oplock = 0; if (tcon->ses->server->oplocks) @@ -319,9 +320,16 @@ cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned int xid, if (backup_cred(cifs_sb)) create_options |= CREATE_OPEN_BACKUP_INTENT; - rc = server->ops->open(xid, tcon, full_path, disposition, - desired_access, create_options, fid, oplock, - buf, cifs_sb); + oparms.tcon = tcon; + oparms.cifs_sb = cifs_sb; + oparms.desired_access = desired_access; + oparms.create_options = create_options; + oparms.disposition = disposition; + oparms.path = full_path; + oparms.fid = fid; + oparms.reconnect = false; + + rc = server->ops->open(xid, &oparms, oplock, buf); if (rc) { cifs_dbg(FYI, "cifs_create returned 0x%x\n", rc); goto out; diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 91d8629e69a2..1e57f36ea1b2 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -183,6 +183,7 @@ cifs_nt_open(char *full_path, struct inode *inode, struct cifs_sb_info *cifs_sb, int create_options = CREATE_NOT_DIR; FILE_ALL_INFO *buf; struct TCP_Server_Info *server = tcon->ses->server; + struct cifs_open_parms oparms; if (!server->ops->open) return -ENOSYS; @@ -224,9 +225,16 @@ cifs_nt_open(char *full_path, struct inode *inode, struct cifs_sb_info *cifs_sb, if (backup_cred(cifs_sb)) create_options |= CREATE_OPEN_BACKUP_INTENT; - rc = server->ops->open(xid, tcon, full_path, disposition, - desired_access, create_options, fid, oplock, buf, - cifs_sb); + oparms.tcon = tcon; + oparms.cifs_sb = cifs_sb; + oparms.desired_access = desired_access; + oparms.create_options = create_options; + oparms.disposition = disposition; + oparms.path = full_path; + oparms.fid = fid; + oparms.reconnect = false; + + rc = server->ops->open(xid, &oparms, oplock, buf); if (rc) goto out; @@ -553,11 +561,10 @@ cifs_relock_file(struct cifsFileInfo *cfile) struct cifs_tcon *tcon = tlink_tcon(cfile->tlink); int rc = 0; - /* we are going to update can_cache_brlcks here - need a write access */ - down_write(&cinode->lock_sem); + down_read(&cinode->lock_sem); if (cinode->can_cache_brlcks) { - /* can cache locks - no need to push them */ - up_write(&cinode->lock_sem); + /* can cache locks - no need to relock */ + up_read(&cinode->lock_sem); return rc; } @@ -568,7 +575,7 @@ cifs_relock_file(struct cifsFileInfo *cfile) else rc = tcon->ses->server->ops->push_mand_locks(cfile); - up_write(&cinode->lock_sem); + up_read(&cinode->lock_sem); return rc; } @@ -587,7 +594,7 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush) int desired_access; int disposition = FILE_OPEN; int create_options = CREATE_NOT_DIR; - struct cifs_fid fid; + struct cifs_open_parms oparms; xid = get_xid(); mutex_lock(&cfile->fh_mutex); @@ -637,7 +644,7 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush) rc = cifs_posix_open(full_path, NULL, inode->i_sb, cifs_sb->mnt_file_mode /* ignored */, - oflags, &oplock, &fid.netfid, xid); + oflags, &oplock, &cfile->fid.netfid, xid); if (rc == 0) { cifs_dbg(FYI, "posix reopen succeeded\n"); goto reopen_success; @@ -654,7 +661,16 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush) create_options |= CREATE_OPEN_BACKUP_INTENT; if (server->ops->get_lease_key) - server->ops->get_lease_key(inode, &fid); + server->ops->get_lease_key(inode, &cfile->fid); + + oparms.tcon = tcon; + oparms.cifs_sb = cifs_sb; + oparms.desired_access = desired_access; + oparms.create_options = create_options; + oparms.disposition = disposition; + oparms.path = full_path; + oparms.fid = &cfile->fid; + oparms.reconnect = true; /* * Can not refresh inode by passing in file_info buf to be returned by @@ -663,9 +679,14 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush) * version of file size can be stale. If we knew for sure that inode was * not dirty locally we could do this. */ - rc = server->ops->open(xid, tcon, full_path, disposition, - desired_access, create_options, &fid, &oplock, - NULL, cifs_sb); + rc = server->ops->open(xid, &oparms, &oplock, NULL); + if (rc == -ENOENT && oparms.reconnect == false) { + /* durable handle timeout is expired - open the file again */ + rc = server->ops->open(xid, &oparms, &oplock, NULL); + /* indicate that we need to relock the file */ + oparms.reconnect = true; + } + if (rc) { mutex_unlock(&cfile->fh_mutex); cifs_dbg(FYI, "cifs_reopen returned 0x%x\n", rc); @@ -696,8 +717,9 @@ reopen_success: * to the server to get the new inode info. */ - server->ops->set_fid(cfile, &fid, oplock); - cifs_relock_file(cfile); + server->ops->set_fid(cfile, &cfile->fid, oplock); + if (oparms.reconnect) + cifs_relock_file(cfile); reopen_error_exit: kfree(full_path); diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 20efd81266c6..449b6cf09b09 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -558,6 +558,11 @@ cifs_all_info_to_fattr(struct cifs_fattr *fattr, FILE_ALL_INFO *info, fattr->cf_mode &= ~(S_IWUGO); fattr->cf_nlink = le32_to_cpu(info->NumberOfLinks); + if (fattr->cf_nlink < 1) { + cifs_dbg(1, "replacing bogus file nlink value %u\n", + fattr->cf_nlink); + fattr->cf_nlink = 1; + } } fattr->cf_uid = cifs_sb->mnt_uid; diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c index e813f04511d8..6457690731a2 100644 --- a/fs/cifs/smb1ops.c +++ b/fs/cifs/smb1ops.c @@ -674,20 +674,23 @@ cifs_mkdir_setinfo(struct inode *inode, const char *full_path, } static int -cifs_open_file(const unsigned int xid, struct cifs_tcon *tcon, const char *path, - int disposition, int desired_access, int create_options, - struct cifs_fid *fid, __u32 *oplock, FILE_ALL_INFO *buf, - struct cifs_sb_info *cifs_sb) -{ - if (!(tcon->ses->capabilities & CAP_NT_SMBS)) - return SMBLegacyOpen(xid, tcon, path, disposition, - desired_access, create_options, - &fid->netfid, oplock, buf, - cifs_sb->local_nls, cifs_sb->mnt_cifs_flags +cifs_open_file(const unsigned int xid, struct cifs_open_parms *oparms, + __u32 *oplock, FILE_ALL_INFO *buf) +{ + if (!(oparms->tcon->ses->capabilities & CAP_NT_SMBS)) + return SMBLegacyOpen(xid, oparms->tcon, oparms->path, + oparms->disposition, + oparms->desired_access, + oparms->create_options, + &oparms->fid->netfid, oplock, buf, + oparms->cifs_sb->local_nls, + oparms->cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR); - return CIFSSMBOpen(xid, tcon, path, disposition, desired_access, - create_options, &fid->netfid, oplock, buf, - cifs_sb->local_nls, cifs_sb->mnt_cifs_flags & + return CIFSSMBOpen(xid, oparms->tcon, oparms->path, + oparms->disposition, oparms->desired_access, + oparms->create_options, &oparms->fid->netfid, oplock, + buf, oparms->cifs_sb->local_nls, + oparms->cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR); } diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c index 5da1b55a2258..04a81a4142c3 100644 --- a/fs/cifs/smb2file.c +++ b/fs/cifs/smb2file.c @@ -40,7 +40,8 @@ smb2_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock) oplock &= 0xFF; if (oplock == SMB2_OPLOCK_LEVEL_NOCHANGE) return; - if (oplock == SMB2_OPLOCK_LEVEL_EXCLUSIVE) { + if (oplock == SMB2_OPLOCK_LEVEL_EXCLUSIVE || + oplock == SMB2_OPLOCK_LEVEL_BATCH) { cinode->clientCanCacheAll = true; cinode->clientCanCacheRead = true; cifs_dbg(FYI, "Exclusive Oplock granted on inode %p\n", @@ -57,17 +58,16 @@ smb2_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock) } int -smb2_open_file(const unsigned int xid, struct cifs_tcon *tcon, const char *path, - int disposition, int desired_access, int create_options, - struct cifs_fid *fid, __u32 *oplock, FILE_ALL_INFO *buf, - struct cifs_sb_info *cifs_sb) +smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, + __u32 *oplock, FILE_ALL_INFO *buf) { int rc; __le16 *smb2_path; struct smb2_file_all_info *smb2_data = NULL; __u8 smb2_oplock[17]; + struct cifs_fid *fid = oparms->fid; - smb2_path = cifs_convert_path_to_utf16(path, cifs_sb); + smb2_path = cifs_convert_path_to_utf16(oparms->path, oparms->cifs_sb); if (smb2_path == NULL) { rc = -ENOMEM; goto out; @@ -80,21 +80,19 @@ smb2_open_file(const unsigned int xid, struct cifs_tcon *tcon, const char *path, goto out; } - desired_access |= FILE_READ_ATTRIBUTES; - *smb2_oplock = SMB2_OPLOCK_LEVEL_EXCLUSIVE; + oparms->desired_access |= FILE_READ_ATTRIBUTES; + *smb2_oplock = SMB2_OPLOCK_LEVEL_BATCH; - if (tcon->ses->server->capabilities & SMB2_GLOBAL_CAP_LEASING) + if (oparms->tcon->ses->server->capabilities & SMB2_GLOBAL_CAP_LEASING) memcpy(smb2_oplock + 1, fid->lease_key, SMB2_LEASE_KEY_SIZE); - rc = SMB2_open(xid, tcon, smb2_path, &fid->persistent_fid, - &fid->volatile_fid, desired_access, disposition, - 0, 0, smb2_oplock, smb2_data); + rc = SMB2_open(xid, oparms, smb2_path, smb2_oplock, smb2_data); if (rc) goto out; if (buf) { /* open response does not have IndexNumber field - get it */ - rc = SMB2_get_srv_num(xid, tcon, fid->persistent_fid, + rc = SMB2_get_srv_num(xid, oparms->tcon, fid->persistent_fid, fid->volatile_fid, &smb2_data->IndexNumber); if (rc) { diff --git a/fs/cifs/smb2inode.c b/fs/cifs/smb2inode.c index fff6dfba6204..c6ec1633309a 100644 --- a/fs/cifs/smb2inode.c +++ b/fs/cifs/smb2inode.c @@ -41,21 +41,26 @@ static int smb2_open_op_close(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_sb_info *cifs_sb, const char *full_path, __u32 desired_access, __u32 create_disposition, - __u32 file_attributes, __u32 create_options, - void *data, int command) + __u32 create_options, void *data, int command) { int rc, tmprc = 0; - u64 persistent_fid, volatile_fid; __le16 *utf16_path; __u8 oplock = SMB2_OPLOCK_LEVEL_NONE; + struct cifs_open_parms oparms; + struct cifs_fid fid; utf16_path = cifs_convert_path_to_utf16(full_path, cifs_sb); if (!utf16_path) return -ENOMEM; - rc = SMB2_open(xid, tcon, utf16_path, &persistent_fid, &volatile_fid, - desired_access, create_disposition, file_attributes, - create_options, &oplock, NULL); + oparms.tcon = tcon; + oparms.desired_access = desired_access; + oparms.disposition = create_disposition; + oparms.create_options = create_options; + oparms.fid = &fid; + oparms.reconnect = false; + + rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL); if (rc) { kfree(utf16_path); return rc; @@ -65,8 +70,8 @@ smb2_open_op_close(const unsigned int xid, struct cifs_tcon *tcon, case SMB2_OP_DELETE: break; case SMB2_OP_QUERY_INFO: - tmprc = SMB2_query_info(xid, tcon, persistent_fid, - volatile_fid, + tmprc = SMB2_query_info(xid, tcon, fid.persistent_fid, + fid.volatile_fid, (struct smb2_file_all_info *)data); break; case SMB2_OP_MKDIR: @@ -76,19 +81,21 @@ smb2_open_op_close(const unsigned int xid, struct cifs_tcon *tcon, */ break; case SMB2_OP_RENAME: - tmprc = SMB2_rename(xid, tcon, persistent_fid, volatile_fid, - (__le16 *)data); + tmprc = SMB2_rename(xid, tcon, fid.persistent_fid, + fid.volatile_fid, (__le16 *)data); break; case SMB2_OP_HARDLINK: - tmprc = SMB2_set_hardlink(xid, tcon, persistent_fid, - volatile_fid, (__le16 *)data); + tmprc = SMB2_set_hardlink(xid, tcon, fid.persistent_fid, + fid.volatile_fid, (__le16 *)data); break; case SMB2_OP_SET_EOF: - tmprc = SMB2_set_eof(xid, tcon, persistent_fid, volatile_fid, - current->tgid, (__le64 *)data); + tmprc = SMB2_set_eof(xid, tcon, fid.persistent_fid, + fid.volatile_fid, current->tgid, + (__le64 *)data); break; case SMB2_OP_SET_INFO: - tmprc = SMB2_set_info(xid, tcon, persistent_fid, volatile_fid, + tmprc = SMB2_set_info(xid, tcon, fid.persistent_fid, + fid.volatile_fid, (FILE_BASIC_INFO *)data); break; default: @@ -96,7 +103,7 @@ smb2_open_op_close(const unsigned int xid, struct cifs_tcon *tcon, break; } - rc = SMB2_close(xid, tcon, persistent_fid, volatile_fid); + rc = SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid); if (tmprc) rc = tmprc; kfree(utf16_path); @@ -129,8 +136,8 @@ smb2_query_path_info(const unsigned int xid, struct cifs_tcon *tcon, return -ENOMEM; rc = smb2_open_op_close(xid, tcon, cifs_sb, full_path, - FILE_READ_ATTRIBUTES, FILE_OPEN, 0, 0, - smb2_data, SMB2_OP_QUERY_INFO); + FILE_READ_ATTRIBUTES, FILE_OPEN, 0, smb2_data, + SMB2_OP_QUERY_INFO); if (rc) goto out; @@ -145,7 +152,7 @@ smb2_mkdir(const unsigned int xid, struct cifs_tcon *tcon, const char *name, struct cifs_sb_info *cifs_sb) { return smb2_open_op_close(xid, tcon, cifs_sb, name, - FILE_WRITE_ATTRIBUTES, FILE_CREATE, 0, + FILE_WRITE_ATTRIBUTES, FILE_CREATE, CREATE_NOT_FILE, NULL, SMB2_OP_MKDIR); } @@ -164,7 +171,7 @@ smb2_mkdir_setinfo(struct inode *inode, const char *name, dosattrs = cifs_i->cifsAttrs | ATTR_READONLY; data.Attributes = cpu_to_le32(dosattrs); tmprc = smb2_open_op_close(xid, tcon, cifs_sb, name, - FILE_WRITE_ATTRIBUTES, FILE_CREATE, 0, + FILE_WRITE_ATTRIBUTES, FILE_CREATE, CREATE_NOT_FILE, &data, SMB2_OP_SET_INFO); if (tmprc == 0) cifs_i->cifsAttrs = dosattrs; @@ -175,7 +182,7 @@ smb2_rmdir(const unsigned int xid, struct cifs_tcon *tcon, const char *name, struct cifs_sb_info *cifs_sb) { return smb2_open_op_close(xid, tcon, cifs_sb, name, DELETE, FILE_OPEN, - 0, CREATE_NOT_FILE | CREATE_DELETE_ON_CLOSE, + CREATE_NOT_FILE | CREATE_DELETE_ON_CLOSE, NULL, SMB2_OP_DELETE); } @@ -184,7 +191,7 @@ smb2_unlink(const unsigned int xid, struct cifs_tcon *tcon, const char *name, struct cifs_sb_info *cifs_sb) { return smb2_open_op_close(xid, tcon, cifs_sb, name, DELETE, FILE_OPEN, - 0, CREATE_DELETE_ON_CLOSE, NULL, + CREATE_DELETE_ON_CLOSE, NULL, SMB2_OP_DELETE); } @@ -203,7 +210,7 @@ smb2_set_path_attr(const unsigned int xid, struct cifs_tcon *tcon, } rc = smb2_open_op_close(xid, tcon, cifs_sb, from_name, access, - FILE_OPEN, 0, 0, smb2_to_name, command); + FILE_OPEN, 0, smb2_to_name, command); smb2_rename_path: kfree(smb2_to_name); return rc; @@ -234,7 +241,7 @@ smb2_set_path_size(const unsigned int xid, struct cifs_tcon *tcon, { __le64 eof = cpu_to_le64(size); return smb2_open_op_close(xid, tcon, cifs_sb, full_path, - FILE_WRITE_DATA, FILE_OPEN, 0, 0, &eof, + FILE_WRITE_DATA, FILE_OPEN, 0, &eof, SMB2_OP_SET_EOF); } @@ -250,7 +257,7 @@ smb2_set_file_info(struct inode *inode, const char *full_path, if (IS_ERR(tlink)) return PTR_ERR(tlink); rc = smb2_open_op_close(xid, tlink_tcon(tlink), cifs_sb, full_path, - FILE_WRITE_ATTRIBUTES, FILE_OPEN, 0, 0, buf, + FILE_WRITE_ATTRIBUTES, FILE_OPEN, 0, buf, SMB2_OP_SET_INFO); cifs_put_tlink(tlink); return rc; diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 6d15cab95b99..f259e6cc8357 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -213,22 +213,29 @@ smb2_is_path_accessible(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_sb_info *cifs_sb, const char *full_path) { int rc; - __u64 persistent_fid, volatile_fid; __le16 *utf16_path; __u8 oplock = SMB2_OPLOCK_LEVEL_NONE; + struct cifs_open_parms oparms; + struct cifs_fid fid; utf16_path = cifs_convert_path_to_utf16(full_path, cifs_sb); if (!utf16_path) return -ENOMEM; - rc = SMB2_open(xid, tcon, utf16_path, &persistent_fid, &volatile_fid, - FILE_READ_ATTRIBUTES, FILE_OPEN, 0, 0, &oplock, NULL); + oparms.tcon = tcon; + oparms.desired_access = FILE_READ_ATTRIBUTES; + oparms.disposition = FILE_OPEN; + oparms.create_options = 0; + oparms.fid = &fid; + oparms.reconnect = false; + + rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL); if (rc) { kfree(utf16_path); return rc; } - rc = SMB2_close(xid, tcon, persistent_fid, volatile_fid); + rc = SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid); kfree(utf16_path); return rc; } @@ -443,15 +450,20 @@ smb2_query_dir_first(const unsigned int xid, struct cifs_tcon *tcon, __le16 *utf16_path; int rc; __u8 oplock = SMB2_OPLOCK_LEVEL_NONE; - __u64 persistent_fid, volatile_fid; + struct cifs_open_parms oparms; utf16_path = cifs_convert_path_to_utf16(path, cifs_sb); if (!utf16_path) return -ENOMEM; - rc = SMB2_open(xid, tcon, utf16_path, &persistent_fid, &volatile_fid, - FILE_READ_ATTRIBUTES | FILE_READ_DATA, FILE_OPEN, 0, 0, - &oplock, NULL); + oparms.tcon = tcon; + oparms.desired_access = FILE_READ_ATTRIBUTES | FILE_READ_DATA; + oparms.disposition = FILE_OPEN; + oparms.create_options = 0; + oparms.fid = fid; + oparms.reconnect = false; + + rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL); kfree(utf16_path); if (rc) { cifs_dbg(VFS, "open dir failed\n"); @@ -460,14 +472,12 @@ smb2_query_dir_first(const unsigned int xid, struct cifs_tcon *tcon, srch_inf->entries_in_buffer = 0; srch_inf->index_of_last_entry = 0; - fid->persistent_fid = persistent_fid; - fid->volatile_fid = volatile_fid; - rc = SMB2_query_directory(xid, tcon, persistent_fid, volatile_fid, 0, - srch_inf); + rc = SMB2_query_directory(xid, tcon, fid->persistent_fid, + fid->volatile_fid, 0, srch_inf); if (rc) { cifs_dbg(VFS, "query directory failed\n"); - SMB2_close(xid, tcon, persistent_fid, volatile_fid); + SMB2_close(xid, tcon, fid->persistent_fid, fid->volatile_fid); } return rc; } @@ -528,17 +538,25 @@ smb2_queryfs(const unsigned int xid, struct cifs_tcon *tcon, struct kstatfs *buf) { int rc; - u64 persistent_fid, volatile_fid; __le16 srch_path = 0; /* Null - open root of share */ u8 oplock = SMB2_OPLOCK_LEVEL_NONE; + struct cifs_open_parms oparms; + struct cifs_fid fid; + + oparms.tcon = tcon; + oparms.desired_access = FILE_READ_ATTRIBUTES; + oparms.disposition = FILE_OPEN; + oparms.create_options = 0; + oparms.fid = &fid; + oparms.reconnect = false; - rc = SMB2_open(xid, tcon, &srch_path, &persistent_fid, &volatile_fid, - FILE_READ_ATTRIBUTES, FILE_OPEN, 0, 0, &oplock, NULL); + rc = SMB2_open(xid, &oparms, &srch_path, &oplock, NULL); if (rc) return rc; buf->f_type = SMB2_MAGIC_NUMBER; - rc = SMB2_QFS_info(xid, tcon, persistent_fid, volatile_fid, buf); - SMB2_close(xid, tcon, persistent_fid, volatile_fid); + rc = SMB2_QFS_info(xid, tcon, fid.persistent_fid, fid.volatile_fid, + buf); + SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid); return rc; } diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 2b312e4eeaa6..abc9c2809b51 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -847,29 +847,76 @@ create_lease_buf(u8 *lease_key, u8 oplock) return buf; } +static struct create_durable * +create_durable_buf(void) +{ + struct create_durable *buf; + + buf = kzalloc(sizeof(struct create_durable), GFP_KERNEL); + if (!buf) + return NULL; + + buf->ccontext.DataOffset = cpu_to_le16(offsetof + (struct create_durable, Data)); + buf->ccontext.DataLength = cpu_to_le32(16); + buf->ccontext.NameOffset = cpu_to_le16(offsetof + (struct create_durable, Name)); + buf->ccontext.NameLength = cpu_to_le16(4); + buf->Name[0] = 'D'; + buf->Name[1] = 'H'; + buf->Name[2] = 'n'; + buf->Name[3] = 'Q'; + return buf; +} + +static struct create_durable * +create_reconnect_durable_buf(struct cifs_fid *fid) +{ + struct create_durable *buf; + + buf = kzalloc(sizeof(struct create_durable), GFP_KERNEL); + if (!buf) + return NULL; + + buf->ccontext.DataOffset = cpu_to_le16(offsetof + (struct create_durable, Data)); + buf->ccontext.DataLength = cpu_to_le32(16); + buf->ccontext.NameOffset = cpu_to_le16(offsetof + (struct create_durable, Name)); + buf->ccontext.NameLength = cpu_to_le16(4); + buf->Data.Fid.PersistentFileId = fid->persistent_fid; + buf->Data.Fid.VolatileFileId = fid->volatile_fid; + buf->Name[0] = 'D'; + buf->Name[1] = 'H'; + buf->Name[2] = 'n'; + buf->Name[3] = 'C'; + return buf; +} + static __u8 parse_lease_state(struct smb2_create_rsp *rsp) { char *data_offset; struct create_lease *lc; bool found = false; + unsigned int next = 0; + char *name; - data_offset = (char *)rsp; - data_offset += 4 + le32_to_cpu(rsp->CreateContextsOffset); + data_offset = (char *)rsp + 4 + le32_to_cpu(rsp->CreateContextsOffset); lc = (struct create_lease *)data_offset; do { - char *name = le16_to_cpu(lc->ccontext.NameOffset) + (char *)lc; + lc = (struct create_lease *)((char *)lc + next); + name = le16_to_cpu(lc->ccontext.NameOffset) + (char *)lc; if (le16_to_cpu(lc->ccontext.NameLength) != 4 || strncmp(name, "RqLs", 4)) { - lc = (struct create_lease *)((char *)lc - + le32_to_cpu(lc->ccontext.Next)); + next = le32_to_cpu(lc->ccontext.Next); continue; } if (lc->lcontext.LeaseFlags & SMB2_LEASE_FLAG_BREAK_IN_PROGRESS) return SMB2_OPLOCK_LEVEL_NOCHANGE; found = true; break; - } while (le32_to_cpu(lc->ccontext.Next) != 0); + } while (next != 0); if (!found) return 0; @@ -877,23 +924,74 @@ parse_lease_state(struct smb2_create_rsp *rsp) return smb2_map_lease_to_oplock(lc->lcontext.LeaseState); } +static int +add_lease_context(struct kvec *iov, unsigned int *num_iovec, __u8 *oplock) +{ + struct smb2_create_req *req = iov[0].iov_base; + unsigned int num = *num_iovec; + + iov[num].iov_base = create_lease_buf(oplock+1, *oplock); + if (iov[num].iov_base == NULL) + return -ENOMEM; + iov[num].iov_len = sizeof(struct create_lease); + req->RequestedOplockLevel = SMB2_OPLOCK_LEVEL_LEASE; + if (!req->CreateContextsOffset) + req->CreateContextsOffset = cpu_to_le32( + sizeof(struct smb2_create_req) - 4 + + iov[num - 1].iov_len); + req->CreateContextsLength = cpu_to_le32( + le32_to_cpu(req->CreateContextsLength) + + sizeof(struct create_lease)); + inc_rfc1001_len(&req->hdr, sizeof(struct create_lease)); + *num_iovec = num + 1; + return 0; +} + +static int +add_durable_context(struct kvec *iov, unsigned int *num_iovec, + struct cifs_open_parms *oparms) +{ + struct smb2_create_req *req = iov[0].iov_base; + unsigned int num = *num_iovec; + + if (oparms->reconnect) { + iov[num].iov_base = create_reconnect_durable_buf(oparms->fid); + /* indicate that we don't need to relock the file */ + oparms->reconnect = false; + } else + iov[num].iov_base = create_durable_buf(); + if (iov[num].iov_base == NULL) + return -ENOMEM; + iov[num].iov_len = sizeof(struct create_durable); + if (!req->CreateContextsOffset) + req->CreateContextsOffset = + cpu_to_le32(sizeof(struct smb2_create_req) - 4 + + iov[1].iov_len); + req->CreateContextsLength = + cpu_to_le32(le32_to_cpu(req->CreateContextsLength) + + sizeof(struct create_durable)); + inc_rfc1001_len(&req->hdr, sizeof(struct create_durable)); + *num_iovec = num + 1; + return 0; +} + int -SMB2_open(const unsigned int xid, struct cifs_tcon *tcon, __le16 *path, - u64 *persistent_fid, u64 *volatile_fid, __u32 desired_access, - __u32 create_disposition, __u32 file_attributes, __u32 create_options, +SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, __u8 *oplock, struct smb2_file_all_info *buf) { struct smb2_create_req *req; struct smb2_create_rsp *rsp; struct TCP_Server_Info *server; + struct cifs_tcon *tcon = oparms->tcon; struct cifs_ses *ses = tcon->ses; - struct kvec iov[3]; + struct kvec iov[4]; int resp_buftype; int uni_path_len; __le16 *copy_path = NULL; int copy_size; int rc = 0; - int num_iovecs = 2; + unsigned int num_iovecs = 2; + __u32 file_attributes = 0; cifs_dbg(FYI, "create/open\n"); @@ -906,55 +1004,47 @@ SMB2_open(const unsigned int xid, struct cifs_tcon *tcon, __le16 *path, if (rc) return rc; + if (oparms->create_options & CREATE_OPTION_READONLY) + file_attributes |= ATTR_READONLY; + req->ImpersonationLevel = IL_IMPERSONATION; - req->DesiredAccess = cpu_to_le32(desired_access); + req->DesiredAccess = cpu_to_le32(oparms->desired_access); /* File attributes ignored on open (used in create though) */ req->FileAttributes = cpu_to_le32(file_attributes); req->ShareAccess = FILE_SHARE_ALL_LE; - req->CreateDisposition = cpu_to_le32(create_disposition); - req->CreateOptions = cpu_to_le32(create_options); + req->CreateDisposition = cpu_to_le32(oparms->disposition); + req->CreateOptions = cpu_to_le32(oparms->create_options & CREATE_OPTIONS_MASK); uni_path_len = (2 * UniStrnlen((wchar_t *)path, PATH_MAX)) + 2; - req->NameOffset = cpu_to_le16(sizeof(struct smb2_create_req) - - 8 /* pad */ - 4 /* do not count rfc1001 len field */); + /* do not count rfc1001 len field */ + req->NameOffset = cpu_to_le16(sizeof(struct smb2_create_req) - 4); iov[0].iov_base = (char *)req; /* 4 for rfc1002 length field */ iov[0].iov_len = get_rfc1002_length(req) + 4; /* MUST set path len (NameLength) to 0 opening root of share */ - if (uni_path_len >= 4) { - req->NameLength = cpu_to_le16(uni_path_len - 2); - /* -1 since last byte is buf[0] which is sent below (path) */ - iov[0].iov_len--; - if (uni_path_len % 8 != 0) { - copy_size = uni_path_len / 8 * 8; - if (copy_size < uni_path_len) - copy_size += 8; - - copy_path = kzalloc(copy_size, GFP_KERNEL); - if (!copy_path) - return -ENOMEM; - memcpy((char *)copy_path, (const char *)path, - uni_path_len); - uni_path_len = copy_size; - path = copy_path; - } - - iov[1].iov_len = uni_path_len; - iov[1].iov_base = path; - /* - * -1 since last byte is buf[0] which was counted in - * smb2_buf_len. - */ - inc_rfc1001_len(req, uni_path_len - 1); - } else { - iov[0].iov_len += 7; - req->hdr.smb2_buf_length = cpu_to_be32(be32_to_cpu( - req->hdr.smb2_buf_length) + 8 - 1); - num_iovecs = 1; - req->NameLength = 0; + req->NameLength = cpu_to_le16(uni_path_len - 2); + /* -1 since last byte is buf[0] which is sent below (path) */ + iov[0].iov_len--; + if (uni_path_len % 8 != 0) { + copy_size = uni_path_len / 8 * 8; + if (copy_size < uni_path_len) + copy_size += 8; + + copy_path = kzalloc(copy_size, GFP_KERNEL); + if (!copy_path) + return -ENOMEM; + memcpy((char *)copy_path, (const char *)path, + uni_path_len); + uni_path_len = copy_size; + path = copy_path; } + iov[1].iov_len = uni_path_len; + iov[1].iov_base = path; + /* -1 since last byte is buf[0] which was counted in smb2_buf_len */ + inc_rfc1001_len(req, uni_path_len - 1); + if (!server->oplocks) *oplock = SMB2_OPLOCK_LEVEL_NONE; @@ -962,21 +1052,29 @@ SMB2_open(const unsigned int xid, struct cifs_tcon *tcon, __le16 *path, *oplock == SMB2_OPLOCK_LEVEL_NONE) req->RequestedOplockLevel = *oplock; else { - iov[num_iovecs].iov_base = create_lease_buf(oplock+1, *oplock); - if (iov[num_iovecs].iov_base == NULL) { + rc = add_lease_context(iov, &num_iovecs, oplock); + if (rc) { cifs_small_buf_release(req); kfree(copy_path); - return -ENOMEM; + return rc; + } + } + + if (*oplock == SMB2_OPLOCK_LEVEL_BATCH) { + /* need to set Next field of lease context if we request it */ + if (tcon->ses->server->capabilities & SMB2_GLOBAL_CAP_LEASING) { + struct create_context *ccontext = + (struct create_context *)iov[num_iovecs-1].iov_base; + ccontext->Next = + cpu_to_le32(sizeof(struct create_lease)); + } + rc = add_durable_context(iov, &num_iovecs, oparms); + if (rc) { + cifs_small_buf_release(req); + kfree(copy_path); + kfree(iov[num_iovecs-1].iov_base); + return rc; } - iov[num_iovecs].iov_len = sizeof(struct create_lease); - req->RequestedOplockLevel = SMB2_OPLOCK_LEVEL_LEASE; - req->CreateContextsOffset = cpu_to_le32( - sizeof(struct smb2_create_req) - 4 - 8 + - iov[num_iovecs-1].iov_len); - req->CreateContextsLength = cpu_to_le32( - sizeof(struct create_lease)); - inc_rfc1001_len(&req->hdr, sizeof(struct create_lease)); - num_iovecs++; } rc = SendReceive2(xid, ses, iov, num_iovecs, &resp_buftype, 0); @@ -987,8 +1085,8 @@ SMB2_open(const unsigned int xid, struct cifs_tcon *tcon, __le16 *path, goto creat_exit; } - *persistent_fid = rsp->PersistentFileId; - *volatile_fid = rsp->VolatileFileId; + oparms->fid->persistent_fid = rsp->PersistentFileId; + oparms->fid->volatile_fid = rsp->VolatileFileId; if (buf) { memcpy(buf, &rsp->CreationTime, 32); diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index f31043b26bd3..36b0d37ea69b 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -428,7 +428,7 @@ struct smb2_create_req { __le16 NameLength; __le32 CreateContextsOffset; __le32 CreateContextsLength; - __u8 Buffer[8]; + __u8 Buffer[0]; } __packed; struct smb2_create_rsp { @@ -485,6 +485,18 @@ struct create_lease { struct lease_context lcontext; } __packed; +struct create_durable { + struct create_context ccontext; + __u8 Name[8]; + union { + __u8 Reserved[16]; + struct { + __u64 PersistentFileId; + __u64 VolatileFileId; + } Fid; + } Data; +} __packed; + /* this goes in the ioctl buffer when doing a copychunk request */ struct copychunk_ioctl { char SourceKey[24]; diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h index d4e1eb807457..1a5ecbed40ed 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/cifs/smb2proto.h @@ -84,11 +84,9 @@ extern int smb2_create_hardlink(const unsigned int xid, struct cifs_tcon *tcon, const char *from_name, const char *to_name, struct cifs_sb_info *cifs_sb); -extern int smb2_open_file(const unsigned int xid, struct cifs_tcon *tcon, - const char *full_path, int disposition, - int desired_access, int create_options, - struct cifs_fid *fid, __u32 *oplock, - FILE_ALL_INFO *buf, struct cifs_sb_info *cifs_sb); +extern int smb2_open_file(const unsigned int xid, + struct cifs_open_parms *oparms, + __u32 *oplock, FILE_ALL_INFO *buf); extern void smb2_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock); extern int smb2_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock, const unsigned int xid); @@ -106,11 +104,9 @@ extern int SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree, struct cifs_tcon *tcon, const struct nls_table *); extern int SMB2_tdis(const unsigned int xid, struct cifs_tcon *tcon); -extern int SMB2_open(const unsigned int xid, struct cifs_tcon *tcon, - __le16 *path, u64 *persistent_fid, u64 *volatile_fid, - __u32 desired_access, __u32 create_disposition, - __u32 file_attributes, __u32 create_options, - __u8 *oplock, struct smb2_file_all_info *buf); +extern int SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, + __le16 *path, __u8 *oplock, + struct smb2_file_all_info *buf); extern int SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, u32 opcode, bool is_fsctl, char *in_data, u32 indatalen, diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c index 09b4fbaadeb6..301b191270b9 100644 --- a/fs/cifs/smb2transport.c +++ b/fs/cifs/smb2transport.c @@ -39,6 +39,77 @@ #include "smb2status.h" #include "smb2glob.h" +static int +smb2_crypto_shash_allocate(struct TCP_Server_Info *server) +{ + unsigned int size; + + if (server->secmech.sdeschmacsha256 != NULL) + return 0; /* already allocated */ + + server->secmech.hmacsha256 = crypto_alloc_shash("hmac(sha256)", 0, 0); + if (IS_ERR(server->secmech.hmacsha256)) { + cifs_dbg(VFS, "could not allocate crypto hmacsha256\n"); + return PTR_ERR(server->secmech.hmacsha256); + } + + size = sizeof(struct shash_desc) + + crypto_shash_descsize(server->secmech.hmacsha256); + server->secmech.sdeschmacsha256 = kmalloc(size, GFP_KERNEL); + if (!server->secmech.sdeschmacsha256) { + crypto_free_shash(server->secmech.hmacsha256); + server->secmech.hmacsha256 = NULL; + return -ENOMEM; + } + server->secmech.sdeschmacsha256->shash.tfm = server->secmech.hmacsha256; + server->secmech.sdeschmacsha256->shash.flags = 0x0; + + return 0; +} + +static int +smb3_crypto_shash_allocate(struct TCP_Server_Info *server) +{ + unsigned int size; + int rc; + + if (server->secmech.sdesccmacaes != NULL) + return 0; /* already allocated */ + + rc = smb2_crypto_shash_allocate(server); + if (rc) + return rc; + + server->secmech.cmacaes = crypto_alloc_shash("cmac(aes)", 0, 0); + if (IS_ERR(server->secmech.cmacaes)) { + cifs_dbg(VFS, "could not allocate crypto cmac-aes"); + kfree(server->secmech.sdeschmacsha256); + server->secmech.sdeschmacsha256 = NULL; + crypto_free_shash(server->secmech.hmacsha256); + server->secmech.hmacsha256 = NULL; + return PTR_ERR(server->secmech.cmacaes); + } + + size = sizeof(struct shash_desc) + + crypto_shash_descsize(server->secmech.cmacaes); + server->secmech.sdesccmacaes = kmalloc(size, GFP_KERNEL); + if (!server->secmech.sdesccmacaes) { + cifs_dbg(VFS, "%s: Can't alloc cmacaes\n", __func__); + kfree(server->secmech.sdeschmacsha256); + server->secmech.sdeschmacsha256 = NULL; + crypto_free_shash(server->secmech.hmacsha256); + crypto_free_shash(server->secmech.cmacaes); + server->secmech.hmacsha256 = NULL; + server->secmech.cmacaes = NULL; + return -ENOMEM; + } + server->secmech.sdesccmacaes->shash.tfm = server->secmech.cmacaes; + server->secmech.sdesccmacaes->shash.flags = 0x0; + + return 0; +} + + int smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) { @@ -52,6 +123,12 @@ smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) memset(smb2_signature, 0x0, SMB2_HMACSHA256_SIZE); memset(smb2_pdu->Signature, 0x0, SMB2_SIGNATURE_SIZE); + rc = smb2_crypto_shash_allocate(server); + if (rc) { + cifs_dbg(VFS, "%s: shah256 alloc failed\n", __func__); + return rc; + } + rc = crypto_shash_setkey(server->secmech.hmacsha256, server->session_key.response, SMB2_NTLMV2_SESSKEY_SIZE); if (rc) { @@ -61,7 +138,7 @@ smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) rc = crypto_shash_init(&server->secmech.sdeschmacsha256->shash); if (rc) { - cifs_dbg(VFS, "%s: Could not init md5\n", __func__); + cifs_dbg(VFS, "%s: Could not init sha256", __func__); return rc; } @@ -129,6 +206,12 @@ generate_smb3signingkey(struct TCP_Server_Info *server) memset(prfhash, 0x0, SMB2_HMACSHA256_SIZE); memset(server->smb3signingkey, 0x0, SMB3_SIGNKEY_SIZE); + rc = smb3_crypto_shash_allocate(server); + if (rc) { + cifs_dbg(VFS, "%s: crypto alloc failed\n", __func__); + goto smb3signkey_ret; + } + rc = crypto_shash_setkey(server->secmech.hmacsha256, server->session_key.response, SMB2_NTLMV2_SESSKEY_SIZE); if (rc) { @@ -210,6 +293,11 @@ smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) return rc; } + /* + * we already allocate sdesccmacaes when we init smb3 signing key, + * so unlike smb2 case we do not have to check here if secmech are + * initialized + */ rc = crypto_shash_init(&server->secmech.sdesccmacaes->shash); if (rc) { cifs_dbg(VFS, "%s: Could not init cmac aes\n", __func__); diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index 5e7c60c1cb63..277bd1be21fd 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -660,19 +660,15 @@ static int create_default_group(struct config_group *parent_group, struct config_group *group) { int ret; - struct qstr name; struct configfs_dirent *sd; /* We trust the caller holds a reference to parent */ struct dentry *child, *parent = parent_group->cg_item.ci_dentry; if (!group->cg_item.ci_name) group->cg_item.ci_name = group->cg_item.ci_namebuf; - name.name = group->cg_item.ci_name; - name.len = strlen(name.name); - name.hash = full_name_hash(name.name, name.len); ret = -ENOMEM; - child = d_alloc(parent, &name); + child = d_alloc_name(parent, group->cg_item.ci_name); if (child) { d_add(child, NULL); @@ -1650,7 +1646,6 @@ int configfs_register_subsystem(struct configfs_subsystem *subsys) { int err; struct config_group *group = &subsys->su_group; - struct qstr name; struct dentry *dentry; struct dentry *root; struct configfs_dirent *sd; @@ -1667,12 +1662,8 @@ int configfs_register_subsystem(struct configfs_subsystem *subsys) mutex_lock_nested(&root->d_inode->i_mutex, I_MUTEX_PARENT); - name.name = group->cg_item.ci_name; - name.len = strlen(name.name); - name.hash = full_name_hash(name.name, name.len); - err = -ENOMEM; - dentry = d_alloc(root, &name); + dentry = d_alloc_name(root, group->cg_item.ci_name); if (dentry) { d_add(dentry, NULL); diff --git a/fs/efivarfs/inode.c b/fs/efivarfs/inode.c index 7e787fb90293..07ab49745e31 100644 --- a/fs/efivarfs/inode.c +++ b/fs/efivarfs/inode.c @@ -155,20 +155,8 @@ static int efivarfs_unlink(struct inode *dir, struct dentry *dentry) return 0; }; -/* - * Handle negative dentry. - */ -static struct dentry *efivarfs_lookup(struct inode *dir, struct dentry *dentry, - unsigned int flags) -{ - if (dentry->d_name.len > NAME_MAX) - return ERR_PTR(-ENAMETOOLONG); - d_add(dentry, NULL); - return NULL; -} - const struct inode_operations efivarfs_dir_inode_operations = { - .lookup = efivarfs_lookup, + .lookup = simple_lookup, .unlink = efivarfs_unlink, .create = efivarfs_create, }; diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c index 998ea111e537..1194b1f0f839 100644 --- a/fs/ext3/namei.c +++ b/fs/ext3/namei.c @@ -1780,11 +1780,11 @@ retry: inode->i_op = &ext3_file_inode_operations; inode->i_fop = &ext3_file_operations; ext3_set_aops(inode); + d_tmpfile(dentry, inode); err = ext3_orphan_add(handle, inode); if (err) goto err_drop_inode; mark_inode_dirty(inode); - d_tmpfile(dentry, inode); unlock_new_inode(inode); } ext3_journal_stop(handle); diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 58339393fa6e..ddd715e42a5c 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -38,8 +38,8 @@ ext4_group_t ext4_get_group_number(struct super_block *sb, ext4_group_t group; if (test_opt2(sb, STD_GROUP_SIZE)) - group = (le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block) + - block) >> + group = (block - + le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block)) >> (EXT4_BLOCK_SIZE_BITS(sb) + EXT4_CLUSTER_BITS(sb) + 3); else ext4_get_group_no_and_offset(sb, block, &group, NULL); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 7097b0f680e6..a61873808f76 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -2835,6 +2835,9 @@ again: err = -EIO; break; } + /* Yield here to deal with large extent trees. + * Should be a no-op if we did IO above. */ + cond_resched(); if (WARN_ON(i + 1 > depth)) { err = -EIO; break; @@ -4261,8 +4264,8 @@ got_allocated_blocks: /* not a good idea to call discard here directly, * but otherwise we'd need to call it every free() */ ext4_discard_preallocations(inode); - ext4_free_blocks(handle, inode, NULL, ext4_ext_pblock(&newex), - ext4_ext_get_actual_len(&newex), fb_flags); + ext4_free_blocks(handle, inode, NULL, newblock, + EXT4_C2B(sbi, allocated_clusters), fb_flags); goto out2; } @@ -4382,8 +4385,9 @@ out2: } out3: - trace_ext4_ext_map_blocks_exit(inode, flags, map, err ? err : allocated); - + trace_ext4_ext_map_blocks_exit(inode, flags, map, + err ? err : allocated); + ext4_es_lru_add(inode); return err ? err : allocated; } @@ -4405,9 +4409,20 @@ void ext4_ext_truncate(handle_t *handle, struct inode *inode) last_block = (inode->i_size + sb->s_blocksize - 1) >> EXT4_BLOCK_SIZE_BITS(sb); +retry: err = ext4_es_remove_extent(inode, last_block, EXT_MAX_BLOCKS - last_block); + if (err == ENOMEM) { + cond_resched(); + congestion_wait(BLK_RW_ASYNC, HZ/50); + goto retry; + } + if (err) { + ext4_std_error(inode->i_sb, err); + return; + } err = ext4_ext_remove_space(inode, last_block, EXT_MAX_BLOCKS - 1); + ext4_std_error(inode->i_sb, err); } static void ext4_falloc_update_inode(struct inode *inode, diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c index ee018d5f397e..91cb110da1b4 100644 --- a/fs/ext4/extents_status.c +++ b/fs/ext4/extents_status.c @@ -148,6 +148,8 @@ static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t end); static int __es_try_to_reclaim_extents(struct ext4_inode_info *ei, int nr_to_scan); +static int __ext4_es_shrink(struct ext4_sb_info *sbi, int nr_to_scan, + struct ext4_inode_info *locked_ei); int __init ext4_init_es(void) { @@ -439,7 +441,7 @@ static void ext4_es_insert_extent_ext_check(struct inode *inode, */ if (!ext4_es_is_written(es) && !ext4_es_is_unwritten(es)) { if (in_range(es->es_lblk, ee_block, ee_len)) { - pr_warn("ES insert assertation failed for " + pr_warn("ES insert assertion failed for " "inode: %lu we can find an extent " "at block [%d/%d/%llu/%c], but we " "want to add an delayed/hole extent " @@ -458,7 +460,7 @@ static void ext4_es_insert_extent_ext_check(struct inode *inode, */ if (es->es_lblk < ee_block || ext4_es_pblock(es) != ee_start + es->es_lblk - ee_block) { - pr_warn("ES insert assertation failed for inode: %lu " + pr_warn("ES insert assertion failed for inode: %lu " "ex_status [%d/%d/%llu/%c] != " "es_status [%d/%d/%llu/%c]\n", inode->i_ino, ee_block, ee_len, ee_start, @@ -468,7 +470,7 @@ static void ext4_es_insert_extent_ext_check(struct inode *inode, } if (ee_status ^ es_status) { - pr_warn("ES insert assertation failed for inode: %lu " + pr_warn("ES insert assertion failed for inode: %lu " "ex_status [%d/%d/%llu/%c] != " "es_status [%d/%d/%llu/%c]\n", inode->i_ino, ee_block, ee_len, ee_start, @@ -481,7 +483,7 @@ static void ext4_es_insert_extent_ext_check(struct inode *inode, * that we don't want to add an written/unwritten extent. */ if (!ext4_es_is_delayed(es) && !ext4_es_is_hole(es)) { - pr_warn("ES insert assertation failed for inode: %lu " + pr_warn("ES insert assertion failed for inode: %lu " "can't find an extent at block %d but we want " "to add an written/unwritten extent " "[%d/%d/%llu/%llx]\n", inode->i_ino, @@ -519,7 +521,7 @@ static void ext4_es_insert_extent_ind_check(struct inode *inode, * We want to add a delayed/hole extent but this * block has been allocated. */ - pr_warn("ES insert assertation failed for inode: %lu " + pr_warn("ES insert assertion failed for inode: %lu " "We can find blocks but we want to add a " "delayed/hole extent [%d/%d/%llu/%llx]\n", inode->i_ino, es->es_lblk, es->es_len, @@ -527,13 +529,13 @@ static void ext4_es_insert_extent_ind_check(struct inode *inode, return; } else if (ext4_es_is_written(es)) { if (retval != es->es_len) { - pr_warn("ES insert assertation failed for " + pr_warn("ES insert assertion failed for " "inode: %lu retval %d != es_len %d\n", inode->i_ino, retval, es->es_len); return; } if (map.m_pblk != ext4_es_pblock(es)) { - pr_warn("ES insert assertation failed for " + pr_warn("ES insert assertion failed for " "inode: %lu m_pblk %llu != " "es_pblk %llu\n", inode->i_ino, map.m_pblk, @@ -549,7 +551,7 @@ static void ext4_es_insert_extent_ind_check(struct inode *inode, } } else if (retval == 0) { if (ext4_es_is_written(es)) { - pr_warn("ES insert assertation failed for inode: %lu " + pr_warn("ES insert assertion failed for inode: %lu " "We can't find the block but we want to add " "an written extent [%d/%d/%llu/%llx]\n", inode->i_ino, es->es_lblk, es->es_len, @@ -632,10 +634,8 @@ out: } /* - * ext4_es_insert_extent() adds a space to a extent status tree. - * - * ext4_es_insert_extent is called by ext4_da_write_begin and - * ext4_es_remove_extent. + * ext4_es_insert_extent() adds information to an inode's extent + * status tree. * * Return 0 on success, error code on failure. */ @@ -667,7 +667,13 @@ int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk, err = __es_remove_extent(inode, lblk, end); if (err != 0) goto error; +retry: err = __es_insert_extent(inode, &newes); + if (err == -ENOMEM && __ext4_es_shrink(EXT4_SB(inode->i_sb), 1, + EXT4_I(inode))) + goto retry; + if (err == -ENOMEM && !ext4_es_is_delayed(&newes)) + err = 0; error: write_unlock(&EXT4_I(inode)->i_es_lock); @@ -746,8 +752,10 @@ static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk, struct extent_status orig_es; ext4_lblk_t len1, len2; ext4_fsblk_t block; - int err = 0; + int err; +retry: + err = 0; es = __es_tree_search(&tree->root, lblk); if (!es) goto out; @@ -782,6 +790,10 @@ static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk, if (err) { es->es_lblk = orig_es.es_lblk; es->es_len = orig_es.es_len; + if ((err == -ENOMEM) && + __ext4_es_shrink(EXT4_SB(inode->i_sb), 1, + EXT4_I(inode))) + goto retry; goto out; } } else { @@ -891,22 +903,14 @@ static int ext4_inode_touch_time_cmp(void *priv, struct list_head *a, return -1; } -static int ext4_es_shrink(struct shrinker *shrink, struct shrink_control *sc) +static int __ext4_es_shrink(struct ext4_sb_info *sbi, int nr_to_scan, + struct ext4_inode_info *locked_ei) { - struct ext4_sb_info *sbi = container_of(shrink, - struct ext4_sb_info, s_es_shrinker); struct ext4_inode_info *ei; struct list_head *cur, *tmp; LIST_HEAD(skiped); - int nr_to_scan = sc->nr_to_scan; int ret, nr_shrunk = 0; - ret = percpu_counter_read_positive(&sbi->s_extent_cache_cnt); - trace_ext4_es_shrink_enter(sbi->s_sb, nr_to_scan, ret); - - if (!nr_to_scan) - return ret; - spin_lock(&sbi->s_es_lru_lock); /* @@ -935,7 +939,7 @@ static int ext4_es_shrink(struct shrinker *shrink, struct shrink_control *sc) continue; } - if (ei->i_es_lru_nr == 0) + if (ei->i_es_lru_nr == 0 || ei == locked_ei) continue; write_lock(&ei->i_es_lock); @@ -954,6 +958,27 @@ static int ext4_es_shrink(struct shrinker *shrink, struct shrink_control *sc) list_splice_tail(&skiped, &sbi->s_es_lru); spin_unlock(&sbi->s_es_lru_lock); + if (locked_ei && nr_shrunk == 0) + nr_shrunk = __es_try_to_reclaim_extents(ei, nr_to_scan); + + return nr_shrunk; +} + +static int ext4_es_shrink(struct shrinker *shrink, struct shrink_control *sc) +{ + struct ext4_sb_info *sbi = container_of(shrink, + struct ext4_sb_info, s_es_shrinker); + int nr_to_scan = sc->nr_to_scan; + int ret, nr_shrunk; + + ret = percpu_counter_read_positive(&sbi->s_extent_cache_cnt); + trace_ext4_es_shrink_enter(sbi->s_sb, nr_to_scan, ret); + + if (!nr_to_scan) + return ret; + + nr_shrunk = __ext4_es_shrink(sbi, nr_to_scan, NULL); + ret = percpu_counter_read_positive(&sbi->s_extent_cache_cnt); trace_ext4_es_shrink_exit(sbi->s_sb, nr_shrunk, ret); return ret; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 0188e65e1f58..ba33c67d6e48 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -465,7 +465,7 @@ static void ext4_map_blocks_es_recheck(handle_t *handle, if (es_map->m_lblk != map->m_lblk || es_map->m_flags != map->m_flags || es_map->m_pblk != map->m_pblk) { - printk("ES cache assertation failed for inode: %lu " + printk("ES cache assertion failed for inode: %lu " "es_cached ex [%d/%d/%llu/%x] != " "found ex [%d/%d/%llu/%x] retval %d flags %x\n", inode->i_ino, es_map->m_lblk, es_map->m_len, @@ -514,10 +514,9 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode, "logical block %lu\n", inode->i_ino, flags, map->m_len, (unsigned long) map->m_lblk); - ext4_es_lru_add(inode); - /* Lookup extent status tree firstly */ if (ext4_es_lookup_extent(inode, map->m_lblk, &es)) { + ext4_es_lru_add(inode); if (ext4_es_is_written(&es) || ext4_es_is_unwritten(&es)) { map->m_pblk = ext4_es_pblock(&es) + map->m_lblk - es.es_lblk; @@ -558,7 +557,7 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode, #ifdef ES_AGGRESSIVE_TEST if (retval != map->m_len) { - printk("ES len assertation failed for inode: %lu " + printk("ES len assertion failed for inode: %lu " "retval %d != map->m_len %d " "in %s (lookup)\n", inode->i_ino, retval, map->m_len, __func__); @@ -659,7 +658,7 @@ found: #ifdef ES_AGGRESSIVE_TEST if (retval != map->m_len) { - printk("ES len assertation failed for inode: %lu " + printk("ES len assertion failed for inode: %lu " "retval %d != map->m_len %d " "in %s (allocation)\n", inode->i_ino, retval, map->m_len, __func__); @@ -1529,11 +1528,9 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock, "logical block %lu\n", inode->i_ino, map->m_len, (unsigned long) map->m_lblk); - ext4_es_lru_add(inode); - /* Lookup extent status tree firstly */ if (ext4_es_lookup_extent(inode, iblock, &es)) { - + ext4_es_lru_add(inode); if (ext4_es_is_hole(&es)) { retval = 0; down_read((&EXT4_I(inode)->i_data_sem)); @@ -1642,7 +1639,7 @@ add_delayed: #ifdef ES_AGGRESSIVE_TEST if (retval != map->m_len) { - printk("ES len assertation failed for inode: %lu " + printk("ES len assertion failed for inode: %lu " "retval %d != map->m_len %d " "in %s (lookup)\n", inode->i_ino, retval, map->m_len, __func__); @@ -2163,7 +2160,7 @@ static int mpage_map_and_submit_extent(handle_t *handle, mpd->io_submit.io_end->offset = ((loff_t)map->m_lblk) << inode->i_blkbits; - while (map->m_len) { + do { err = mpage_map_one_extent(handle, mpd); if (err < 0) { struct super_block *sb = inode->i_sb; @@ -2201,7 +2198,7 @@ static int mpage_map_and_submit_extent(handle_t *handle, err = mpage_map_and_submit_buffers(mpd); if (err < 0) return err; - } + } while (map->m_len); /* Update on-disk size after IO is submitted */ disksize = ((loff_t)mpd->first_page) << PAGE_CACHE_SHIFT; diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index a9ff5e5137ca..4bbbf13bd743 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -4740,11 +4740,16 @@ do_more: * blocks being freed are metadata. these blocks shouldn't * be used until this transaction is committed */ + retry: new_entry = kmem_cache_alloc(ext4_free_data_cachep, GFP_NOFS); if (!new_entry) { - ext4_mb_unload_buddy(&e4b); - err = -ENOMEM; - goto error_return; + /* + * We use a retry loop because + * ext4_free_blocks() is not allowed to fail. + */ + cond_resched(); + congestion_wait(BLK_RW_ASYNC, HZ/50); + goto retry; } new_entry->efd_start_cluster = bit; new_entry->efd_group = block_group; diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 234b834d5a97..35f55a0dbc4b 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2316,11 +2316,11 @@ retry: inode->i_op = &ext4_file_inode_operations; inode->i_fop = &ext4_file_operations; ext4_set_aops(inode); + d_tmpfile(dentry, inode); err = ext4_orphan_add(handle, inode); if (err) goto err_drop_inode; mark_inode_dirty(inode); - d_tmpfile(dentry, inode); unlock_new_inode(inode); } if (handle) diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 48786cdb5e6c..6625d210fb45 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -25,6 +25,7 @@ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/mm.h> +#include <linux/ratelimit.h> #include "ext4_jbd2.h" #include "xattr.h" @@ -55,7 +56,7 @@ void ext4_exit_pageio(void) static void buffer_io_error(struct buffer_head *bh) { char b[BDEVNAME_SIZE]; - printk(KERN_ERR "Buffer I/O error on device %s, logical block %llu\n", + printk_ratelimited(KERN_ERR "Buffer I/O error on device %s, logical block %llu\n", bdevname(bh->b_bdev, b), (unsigned long long)bh->b_blocknr); } @@ -308,6 +309,7 @@ ext4_io_end_t *ext4_get_io_end(ext4_io_end_t *io_end) return io_end; } +/* BIO completion function for page writeback */ static void ext4_end_bio(struct bio *bio, int error) { ext4_io_end_t *io_end = bio->bi_private; @@ -318,18 +320,6 @@ static void ext4_end_bio(struct bio *bio, int error) if (test_bit(BIO_UPTODATE, &bio->bi_flags)) error = 0; - if (io_end->flag & EXT4_IO_END_UNWRITTEN) { - /* - * Link bio into list hanging from io_end. We have to do it - * atomically as bio completions can be racing against each - * other. - */ - bio->bi_private = xchg(&io_end->bio, bio); - } else { - ext4_finish_bio(bio); - bio_put(bio); - } - if (error) { struct inode *inode = io_end->inode; @@ -341,7 +331,24 @@ static void ext4_end_bio(struct bio *bio, int error) (unsigned long long) bi_sector >> (inode->i_blkbits - 9)); } - ext4_put_io_end_defer(io_end); + + if (io_end->flag & EXT4_IO_END_UNWRITTEN) { + /* + * Link bio into list hanging from io_end. We have to do it + * atomically as bio completions can be racing against each + * other. + */ + bio->bi_private = xchg(&io_end->bio, bio); + ext4_put_io_end_defer(io_end); + } else { + /* + * Drop io_end reference early. Inode can get freed once + * we finish the bio. + */ + ext4_put_io_end_defer(io_end); + ext4_finish_bio(bio); + bio_put(bio); + } } void ext4_io_submit(struct ext4_io_submit *io) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 85b3dd60169b..bca26f34edf4 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1702,12 +1702,6 @@ static inline void ext4_show_quota_options(struct seq_file *seq, if (sbi->s_qf_names[GRPQUOTA]) seq_printf(seq, ",grpjquota=%s", sbi->s_qf_names[GRPQUOTA]); - - if (test_opt(sb, USRQUOTA)) - seq_puts(seq, ",usrquota"); - - if (test_opt(sb, GRPQUOTA)) - seq_puts(seq, ",grpquota"); #endif } @@ -3624,10 +3618,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_addr_per_block_bits = ilog2(EXT4_ADDR_PER_BLOCK(sb)); sbi->s_desc_per_block_bits = ilog2(EXT4_DESC_PER_BLOCK(sb)); - /* Do we have standard group size of blocksize * 8 blocks ? */ - if (sbi->s_blocks_per_group == blocksize << 3) - set_opt2(sb, STD_GROUP_SIZE); - for (i = 0; i < 4; i++) sbi->s_hash_seed[i] = le32_to_cpu(es->s_hash_seed[i]); sbi->s_def_hash_version = es->s_def_hash_version; @@ -3697,6 +3687,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount; } + /* Do we have standard group size of clustersize * 8 blocks ? */ + if (sbi->s_blocks_per_group == clustersize << 3) + set_opt2(sb, STD_GROUP_SIZE); + /* * Test whether we have more sectors than will fit in sector_t, * and whether the max offset is addressable by the page cache. diff --git a/fs/file_table.c b/fs/file_table.c index 08e719b884ca..b44e4c559786 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -265,18 +265,15 @@ static void __fput(struct file *file) mntput(mnt); } -static DEFINE_SPINLOCK(delayed_fput_lock); -static LIST_HEAD(delayed_fput_list); +static LLIST_HEAD(delayed_fput_list); static void delayed_fput(struct work_struct *unused) { - LIST_HEAD(head); - spin_lock_irq(&delayed_fput_lock); - list_splice_init(&delayed_fput_list, &head); - spin_unlock_irq(&delayed_fput_lock); - while (!list_empty(&head)) { - struct file *f = list_first_entry(&head, struct file, f_u.fu_list); - list_del_init(&f->f_u.fu_list); - __fput(f); + struct llist_node *node = llist_del_all(&delayed_fput_list); + struct llist_node *next; + + for (; node; node = next) { + next = llist_next(node); + __fput(llist_entry(node, struct file, f_u.fu_llist)); } } @@ -306,18 +303,22 @@ void fput(struct file *file) { if (atomic_long_dec_and_test(&file->f_count)) { struct task_struct *task = current; - unsigned long flags; file_sb_list_del(file); if (likely(!in_interrupt() && !(task->flags & PF_KTHREAD))) { init_task_work(&file->f_u.fu_rcuhead, ____fput); if (!task_work_add(task, &file->f_u.fu_rcuhead, true)) return; + /* + * After this task has run exit_task_work(), + * task_work_add() will fail. free_ipc_ns()-> + * shm_destroy() can do this. Fall through to delayed + * fput to avoid leaking *file. + */ } - spin_lock_irqsave(&delayed_fput_lock, flags); - list_add(&file->f_u.fu_list, &delayed_fput_list); - schedule_work(&delayed_fput_work); - spin_unlock_irqrestore(&delayed_fput_lock, flags); + + if (llist_add(&file->f_u.fu_llist, &delayed_fput_list)) + schedule_work(&delayed_fput_work); } } diff --git a/fs/libfs.c b/fs/libfs.c index c3a0837fb861..3a3a9b53bf5a 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -61,7 +61,8 @@ struct dentry *simple_lookup(struct inode *dir, struct dentry *dentry, unsigned if (dentry->d_name.len > NAME_MAX) return ERR_PTR(-ENAMETOOLONG); - d_set_d_op(dentry, &simple_dentry_operations); + if (!dentry->d_sb->s_d_op) + d_set_d_op(dentry, &simple_dentry_operations); d_add(dentry, NULL); return NULL; } diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c index 067778b0ccc9..e066a3902973 100644 --- a/fs/lockd/svclock.c +++ b/fs/lockd/svclock.c @@ -951,6 +951,7 @@ nlmsvc_retry_blocked(void) unsigned long timeout = MAX_SCHEDULE_TIMEOUT; struct nlm_block *block; + spin_lock(&nlm_blocked_lock); while (!list_empty(&nlm_blocked) && !kthread_should_stop()) { block = list_entry(nlm_blocked.next, struct nlm_block, b_list); @@ -960,6 +961,7 @@ nlmsvc_retry_blocked(void) timeout = block->b_when - jiffies; break; } + spin_unlock(&nlm_blocked_lock); dprintk("nlmsvc_retry_blocked(%p, when=%ld)\n", block, block->b_when); @@ -969,7 +971,9 @@ nlmsvc_retry_blocked(void) retry_deferred_block(block); } else nlmsvc_grant_blocked(block); + spin_lock(&nlm_blocked_lock); } + spin_unlock(&nlm_blocked_lock); return timeout; } diff --git a/fs/namei.c b/fs/namei.c index b2beee7a733f..8b61d103a8a7 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -2977,7 +2977,7 @@ static struct file *path_openat(int dfd, struct filename *pathname, file->f_flags = op->open_flag; - if (unlikely(file->f_flags & O_TMPFILE)) { + if (unlikely(file->f_flags & __O_TMPFILE)) { error = do_tmpfile(dfd, pathname, nd, flags, op, file, &opened); goto out; } diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 0abfb8466e79..c74d6168db99 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -999,6 +999,7 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, __be32 *p; __be32 *q; int len; + uint32_t bmval_len = 2; uint32_t bmval0 = 0; uint32_t bmval1 = 0; uint32_t bmval2 = 0; @@ -1010,7 +1011,7 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, * = 40 bytes, plus any contribution from variable-length fields * such as owner/group. */ - len = 20; + len = 8; /* Sigh */ if (iap->ia_valid & ATTR_SIZE) @@ -1040,8 +1041,6 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, } len += 4 + (XDR_QUADLEN(owner_grouplen) << 2); } - if (label) - len += 4 + 4 + 4 + (XDR_QUADLEN(label->len) << 2); if (iap->ia_valid & ATTR_ATIME_SET) len += 16; else if (iap->ia_valid & ATTR_ATIME) @@ -1050,15 +1049,22 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, len += 16; else if (iap->ia_valid & ATTR_MTIME) len += 4; + if (label) { + len += 4 + 4 + 4 + (XDR_QUADLEN(label->len) << 2); + bmval_len = 3; + } + + len += bmval_len << 2; p = reserve_space(xdr, len); /* * We write the bitmap length now, but leave the bitmap and the attribute * buffer length to be backfilled at the end of this routine. */ - *p++ = cpu_to_be32(3); + *p++ = cpu_to_be32(bmval_len); q = p; - p += 4; + /* Skip bitmap entries + attrlen */ + p += bmval_len + 1; if (iap->ia_valid & ATTR_SIZE) { bmval0 |= FATTR4_WORD0_SIZE; @@ -1112,10 +1118,11 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, len, ((char *)p - (char *)q) + 4); BUG(); } - len = (char *)p - (char *)q - 16; + len = (char *)p - (char *)q - (bmval_len << 2); *q++ = htonl(bmval0); *q++ = htonl(bmval1); - *q++ = htonl(bmval2); + if (bmval_len == 3) + *q++ = htonl(bmval2); *q = htonl(len); /* out: */ diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index a7cee864e7b2..0d4c410e4589 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1293,7 +1293,7 @@ nfsd4_proc_compound(struct svc_rqst *rqstp, * According to RFC3010, this takes precedence over all other errors. */ status = nfserr_minor_vers_mismatch; - if (args->minorversion > nfsd_supported_minorversion) + if (nfsd_minorversion(args->minorversion, NFSD_TEST) <= 0) goto out; status = nfs41_check_op_ordering(args); diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index 2bbd94e51efc..30f34ab02137 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -53,7 +53,6 @@ struct readdir_cd { extern struct svc_program nfsd_program; extern struct svc_version nfsd_version2, nfsd_version3, nfsd_version4; -extern u32 nfsd_supported_minorversion; extern struct mutex nfsd_mutex; extern spinlock_t nfsd_drc_lock; extern unsigned long nfsd_drc_max_mem; diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 6b9f48ca4c25..760c85a6f534 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -116,7 +116,10 @@ struct svc_program nfsd_program = { }; -u32 nfsd_supported_minorversion = 1; +static bool nfsd_supported_minorversions[NFSD_SUPPORTED_MINOR_VERSION + 1] = { + [0] = 1, + [1] = 1, +}; int nfsd_vers(int vers, enum vers_op change) { @@ -151,15 +154,13 @@ int nfsd_minorversion(u32 minorversion, enum vers_op change) return -1; switch(change) { case NFSD_SET: - nfsd_supported_minorversion = minorversion; + nfsd_supported_minorversions[minorversion] = true; break; case NFSD_CLEAR: - if (minorversion == 0) - return -1; - nfsd_supported_minorversion = minorversion - 1; + nfsd_supported_minorversions[minorversion] = false; break; case NFSD_TEST: - return minorversion <= nfsd_supported_minorversion; + return nfsd_supported_minorversions[minorversion]; case NFSD_AVAIL: return minorversion <= NFSD_SUPPORTED_MINOR_VERSION; } diff --git a/fs/open.c b/fs/open.c index fca72c4d3f17..d53e29895082 100644 --- a/fs/open.c +++ b/fs/open.c @@ -840,10 +840,12 @@ static inline int build_open_flags(int flags, umode_t mode, struct open_flags *o if (flags & __O_SYNC) flags |= O_DSYNC; - if (flags & O_TMPFILE) { - if (!(flags & O_CREAT)) + if (flags & __O_TMPFILE) { + if ((flags & O_TMPFILE_MASK) != O_TMPFILE) return -EINVAL; acc_mode = MAY_OPEN | ACC_MODE(flags); + if (!(acc_mode & MAY_WRITE)) + return -EINVAL; } else if (flags & O_PATH) { /* * If we have O_PATH in the open flag. Then we diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index 28503172f2e4..a1a16eb97c7b 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -223,7 +223,7 @@ static inline char *alloc_elfnotes_buf(size_t notes_sz) * regions in the 1st kernel pointed to by PT_LOAD entries) into * virtually contiguous user-space in ELF layout. */ -#ifdef CONFIG_MMU +#if defined(CONFIG_MMU) && !defined(CONFIG_S390) static int mmap_vmcore(struct file *file, struct vm_area_struct *vma) { size_t size = vma->vm_end - vma->vm_start; diff --git a/fs/select.c b/fs/select.c index f9f49c40cfd4..35d4adc749d9 100644 --- a/fs/select.c +++ b/fs/select.c @@ -28,7 +28,7 @@ #include <linux/hrtimer.h> #include <linux/sched/rt.h> #include <linux/freezer.h> -#include <net/ll_poll.h> +#include <net/busy_poll.h> #include <asm/uaccess.h> diff --git a/fs/super.c b/fs/super.c index 7465d4364208..68307c029228 100644 --- a/fs/super.c +++ b/fs/super.c @@ -336,19 +336,19 @@ EXPORT_SYMBOL(deactivate_super); * and want to turn it into a full-blown active reference. grab_super() * is called with sb_lock held and drops it. Returns 1 in case of * success, 0 if we had failed (superblock contents was already dead or - * dying when grab_super() had been called). + * dying when grab_super() had been called). Note that this is only + * called for superblocks not in rundown mode (== ones still on ->fs_supers + * of their type), so increment of ->s_count is OK here. */ static int grab_super(struct super_block *s) __releases(sb_lock) { - if (atomic_inc_not_zero(&s->s_active)) { - spin_unlock(&sb_lock); - return 1; - } - /* it's going away */ s->s_count++; spin_unlock(&sb_lock); - /* wait for it to die */ down_write(&s->s_umount); + if ((s->s_flags & MS_BORN) && atomic_inc_not_zero(&s->s_active)) { + put_super(s); + return 1; + } up_write(&s->s_umount); put_super(s); return 0; @@ -463,11 +463,6 @@ retry: destroy_super(s); s = NULL; } - down_write(&old->s_umount); - if (unlikely(!(old->s_flags & MS_BORN))) { - deactivate_locked_super(old); - goto retry; - } return old; } } @@ -660,10 +655,10 @@ restart: if (hlist_unhashed(&sb->s_instances)) continue; if (sb->s_bdev == bdev) { - if (grab_super(sb)) /* drops sb_lock */ - return sb; - else + if (!grab_super(sb)) goto restart; + up_write(&sb->s_umount); + return sb; } } spin_unlock(&sb_lock); diff --git a/fs/sysfs/group.c b/fs/sysfs/group.c index aec3d5c98c94..09a1a25cd145 100644 --- a/fs/sysfs/group.c +++ b/fs/sysfs/group.c @@ -20,38 +20,64 @@ static void remove_files(struct sysfs_dirent *dir_sd, struct kobject *kobj, const struct attribute_group *grp) { struct attribute *const* attr; - int i; + struct bin_attribute *const* bin_attr; - for (i = 0, attr = grp->attrs; *attr; i++, attr++) - sysfs_hash_and_remove(dir_sd, NULL, (*attr)->name); + if (grp->attrs) + for (attr = grp->attrs; *attr; attr++) + sysfs_hash_and_remove(dir_sd, NULL, (*attr)->name); + if (grp->bin_attrs) + for (bin_attr = grp->bin_attrs; *bin_attr; bin_attr++) + sysfs_remove_bin_file(kobj, *bin_attr); } static int create_files(struct sysfs_dirent *dir_sd, struct kobject *kobj, const struct attribute_group *grp, int update) { struct attribute *const* attr; + struct bin_attribute *const* bin_attr; int error = 0, i; - for (i = 0, attr = grp->attrs; *attr && !error; i++, attr++) { - umode_t mode = 0; + if (grp->attrs) { + for (i = 0, attr = grp->attrs; *attr && !error; i++, attr++) { + umode_t mode = 0; + + /* + * In update mode, we're changing the permissions or + * visibility. Do this by first removing then + * re-adding (if required) the file. + */ + if (update) + sysfs_hash_and_remove(dir_sd, NULL, + (*attr)->name); + if (grp->is_visible) { + mode = grp->is_visible(kobj, *attr, i); + if (!mode) + continue; + } + error = sysfs_add_file_mode(dir_sd, *attr, + SYSFS_KOBJ_ATTR, + (*attr)->mode | mode); + if (unlikely(error)) + break; + } + if (error) { + remove_files(dir_sd, kobj, grp); + goto exit; + } + } - /* in update mode, we're changing the permissions or - * visibility. Do this by first removing then - * re-adding (if required) the file */ - if (update) - sysfs_hash_and_remove(dir_sd, NULL, (*attr)->name); - if (grp->is_visible) { - mode = grp->is_visible(kobj, *attr, i); - if (!mode) - continue; + if (grp->bin_attrs) { + for (bin_attr = grp->bin_attrs; *bin_attr; bin_attr++) { + if (update) + sysfs_remove_bin_file(kobj, *bin_attr); + error = sysfs_create_bin_file(kobj, *bin_attr); + if (error) + break; } - error = sysfs_add_file_mode(dir_sd, *attr, SYSFS_KOBJ_ATTR, - (*attr)->mode | mode); - if (unlikely(error)) - break; + if (error) + remove_files(dir_sd, kobj, grp); } - if (error) - remove_files(dir_sd, kobj, grp); +exit: return error; } @@ -67,8 +93,8 @@ static int internal_create_group(struct kobject *kobj, int update, /* Updates may happen before the object has been instantiated */ if (unlikely(update && !kobj->sd)) return -EINVAL; - if (!grp->attrs) { - WARN(1, "sysfs: attrs not set by subsystem for group: %s/%s\n", + if (!grp->attrs && !grp->bin_attrs) { + WARN(1, "sysfs: (bin_)attrs not set by subsystem for group: %s/%s\n", kobj->name, grp->name ? "" : grp->name); return -EINVAL; } diff --git a/fs/xfs/xfs_attr_leaf.c b/fs/xfs/xfs_attr_leaf.c index 31d3cd129269..b800fbcafc7f 100644 --- a/fs/xfs/xfs_attr_leaf.c +++ b/fs/xfs/xfs_attr_leaf.c @@ -690,6 +690,8 @@ xfs_attr_shortform_to_leaf(xfs_da_args_t *args) sf = (xfs_attr_shortform_t *)tmpbuffer; xfs_idata_realloc(dp, -size, XFS_ATTR_FORK); + xfs_bmap_local_to_extents_empty(dp, XFS_ATTR_FORK); + bp = NULL; error = xfs_da_grow_inode(args, &blkno); if (error) { diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c index 89042848f9ec..05c698ccb238 100644 --- a/fs/xfs/xfs_bmap.c +++ b/fs/xfs/xfs_bmap.c @@ -1161,6 +1161,24 @@ xfs_bmap_extents_to_btree( * since the file data needs to get logged so things will stay consistent. * (The bmap-level manipulations are ok, though). */ +void +xfs_bmap_local_to_extents_empty( + struct xfs_inode *ip, + int whichfork) +{ + struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); + + ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_LOCAL); + ASSERT(ifp->if_bytes == 0); + ASSERT(XFS_IFORK_NEXTENTS(ip, whichfork) == 0); + + xfs_bmap_forkoff_reset(ip->i_mount, ip, whichfork); + ifp->if_flags &= ~XFS_IFINLINE; + ifp->if_flags |= XFS_IFEXTENTS; + XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_EXTENTS); +} + + STATIC int /* error */ xfs_bmap_local_to_extents( xfs_trans_t *tp, /* transaction pointer */ @@ -1174,9 +1192,12 @@ xfs_bmap_local_to_extents( struct xfs_inode *ip, struct xfs_ifork *ifp)) { - int error; /* error return value */ + int error = 0; int flags; /* logging flags returned */ xfs_ifork_t *ifp; /* inode fork pointer */ + xfs_alloc_arg_t args; /* allocation arguments */ + xfs_buf_t *bp; /* buffer for extent block */ + xfs_bmbt_rec_host_t *ep; /* extent record pointer */ /* * We don't want to deal with the case of keeping inode data inline yet. @@ -1185,68 +1206,65 @@ xfs_bmap_local_to_extents( ASSERT(!(S_ISREG(ip->i_d.di_mode) && whichfork == XFS_DATA_FORK)); ifp = XFS_IFORK_PTR(ip, whichfork); ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_LOCAL); + + if (!ifp->if_bytes) { + xfs_bmap_local_to_extents_empty(ip, whichfork); + flags = XFS_ILOG_CORE; + goto done; + } + flags = 0; error = 0; - if (ifp->if_bytes) { - xfs_alloc_arg_t args; /* allocation arguments */ - xfs_buf_t *bp; /* buffer for extent block */ - xfs_bmbt_rec_host_t *ep;/* extent record pointer */ - - ASSERT((ifp->if_flags & - (XFS_IFINLINE|XFS_IFEXTENTS|XFS_IFEXTIREC)) == XFS_IFINLINE); - memset(&args, 0, sizeof(args)); - args.tp = tp; - args.mp = ip->i_mount; - args.firstblock = *firstblock; - /* - * Allocate a block. We know we need only one, since the - * file currently fits in an inode. - */ - if (*firstblock == NULLFSBLOCK) { - args.fsbno = XFS_INO_TO_FSB(args.mp, ip->i_ino); - args.type = XFS_ALLOCTYPE_START_BNO; - } else { - args.fsbno = *firstblock; - args.type = XFS_ALLOCTYPE_NEAR_BNO; - } - args.total = total; - args.minlen = args.maxlen = args.prod = 1; - error = xfs_alloc_vextent(&args); - if (error) - goto done; - - /* Can't fail, the space was reserved. */ - ASSERT(args.fsbno != NULLFSBLOCK); - ASSERT(args.len == 1); - *firstblock = args.fsbno; - bp = xfs_btree_get_bufl(args.mp, tp, args.fsbno, 0); - - /* initialise the block and copy the data */ - init_fn(tp, bp, ip, ifp); - - /* account for the change in fork size and log everything */ - xfs_trans_log_buf(tp, bp, 0, ifp->if_bytes - 1); - xfs_bmap_forkoff_reset(args.mp, ip, whichfork); - xfs_idata_realloc(ip, -ifp->if_bytes, whichfork); - xfs_iext_add(ifp, 0, 1); - ep = xfs_iext_get_ext(ifp, 0); - xfs_bmbt_set_allf(ep, 0, args.fsbno, 1, XFS_EXT_NORM); - trace_xfs_bmap_post_update(ip, 0, - whichfork == XFS_ATTR_FORK ? BMAP_ATTRFORK : 0, - _THIS_IP_); - XFS_IFORK_NEXT_SET(ip, whichfork, 1); - ip->i_d.di_nblocks = 1; - xfs_trans_mod_dquot_byino(tp, ip, - XFS_TRANS_DQ_BCOUNT, 1L); - flags |= xfs_ilog_fext(whichfork); + ASSERT((ifp->if_flags & (XFS_IFINLINE|XFS_IFEXTENTS|XFS_IFEXTIREC)) == + XFS_IFINLINE); + memset(&args, 0, sizeof(args)); + args.tp = tp; + args.mp = ip->i_mount; + args.firstblock = *firstblock; + /* + * Allocate a block. We know we need only one, since the + * file currently fits in an inode. + */ + if (*firstblock == NULLFSBLOCK) { + args.fsbno = XFS_INO_TO_FSB(args.mp, ip->i_ino); + args.type = XFS_ALLOCTYPE_START_BNO; } else { - ASSERT(XFS_IFORK_NEXTENTS(ip, whichfork) == 0); - xfs_bmap_forkoff_reset(ip->i_mount, ip, whichfork); + args.fsbno = *firstblock; + args.type = XFS_ALLOCTYPE_NEAR_BNO; } - ifp->if_flags &= ~XFS_IFINLINE; - ifp->if_flags |= XFS_IFEXTENTS; - XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_EXTENTS); + args.total = total; + args.minlen = args.maxlen = args.prod = 1; + error = xfs_alloc_vextent(&args); + if (error) + goto done; + + /* Can't fail, the space was reserved. */ + ASSERT(args.fsbno != NULLFSBLOCK); + ASSERT(args.len == 1); + *firstblock = args.fsbno; + bp = xfs_btree_get_bufl(args.mp, tp, args.fsbno, 0); + + /* initialise the block and copy the data */ + init_fn(tp, bp, ip, ifp); + + /* account for the change in fork size and log everything */ + xfs_trans_log_buf(tp, bp, 0, ifp->if_bytes - 1); + xfs_idata_realloc(ip, -ifp->if_bytes, whichfork); + xfs_bmap_local_to_extents_empty(ip, whichfork); flags |= XFS_ILOG_CORE; + + xfs_iext_add(ifp, 0, 1); + ep = xfs_iext_get_ext(ifp, 0); + xfs_bmbt_set_allf(ep, 0, args.fsbno, 1, XFS_EXT_NORM); + trace_xfs_bmap_post_update(ip, 0, + whichfork == XFS_ATTR_FORK ? BMAP_ATTRFORK : 0, + _THIS_IP_); + XFS_IFORK_NEXT_SET(ip, whichfork, 1); + ip->i_d.di_nblocks = 1; + xfs_trans_mod_dquot_byino(tp, ip, + XFS_TRANS_DQ_BCOUNT, 1L); + flags |= xfs_ilog_fext(whichfork); + done: *logflagsp = flags; return error; @@ -1323,25 +1341,6 @@ xfs_bmap_add_attrfork_extents( } /* - * Block initialisation function for local to extent format conversion. - * - * This shouldn't actually be called by anyone, so make sure debug kernels cause - * a noticable failure. - */ -STATIC void -xfs_bmap_local_to_extents_init_fn( - struct xfs_trans *tp, - struct xfs_buf *bp, - struct xfs_inode *ip, - struct xfs_ifork *ifp) -{ - ASSERT(0); - bp->b_ops = &xfs_bmbt_buf_ops; - memcpy(bp->b_addr, ifp->if_u1.if_data, ifp->if_bytes); - xfs_trans_buf_set_type(tp, bp, XFS_BLFT_BTREE_BUF); -} - -/* * Called from xfs_bmap_add_attrfork to handle local format files. Each * different data fork content type needs a different callout to do the * conversion. Some are basic and only require special block initialisation @@ -1381,9 +1380,9 @@ xfs_bmap_add_attrfork_local( flags, XFS_DATA_FORK, xfs_symlink_local_to_remote); - return xfs_bmap_local_to_extents(tp, ip, firstblock, 1, flags, - XFS_DATA_FORK, - xfs_bmap_local_to_extents_init_fn); + /* should only be called for types that support local format data */ + ASSERT(0); + return EFSCORRUPTED; } /* @@ -4907,20 +4906,19 @@ xfs_bmapi_write( orig_mval = mval; orig_nmap = *nmap; #endif + whichfork = (flags & XFS_BMAPI_ATTRFORK) ? + XFS_ATTR_FORK : XFS_DATA_FORK; ASSERT(*nmap >= 1); ASSERT(*nmap <= XFS_BMAP_MAX_NMAP); ASSERT(!(flags & XFS_BMAPI_IGSTATE)); ASSERT(tp != NULL); ASSERT(len > 0); - - whichfork = (flags & XFS_BMAPI_ATTRFORK) ? - XFS_ATTR_FORK : XFS_DATA_FORK; + ASSERT(XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_LOCAL); if (unlikely(XFS_TEST_ERROR( (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS && - XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE && - XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_LOCAL), + XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE), mp, XFS_ERRTAG_BMAPIFORMAT, XFS_RANDOM_BMAPIFORMAT))) { XFS_ERROR_REPORT("xfs_bmapi_write", XFS_ERRLEVEL_LOW, mp); return XFS_ERROR(EFSCORRUPTED); @@ -4933,37 +4931,6 @@ xfs_bmapi_write( XFS_STATS_INC(xs_blk_mapw); - if (XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_LOCAL) { - /* - * XXX (dgc): This assumes we are only called for inodes that - * contain content neutral data in local format. Anything that - * contains caller-specific data in local format that needs - * transformation to move to a block format needs to do the - * conversion to extent format itself. - * - * Directory data forks and attribute forks handle this - * themselves, but with the addition of metadata verifiers every - * data fork in local format now contains caller specific data - * and as such conversion through this function is likely to be - * broken. - * - * The only likely user of this branch is for remote symlinks, - * but we cannot overwrite the data fork contents of the symlink - * (EEXIST occurs higher up the stack) and so it will never go - * from local format to extent format here. Hence I don't think - * this branch is ever executed intentionally and we should - * consider removing it and asserting that xfs_bmapi_write() - * cannot be called directly on local format forks. i.e. callers - * are completely responsible for local to extent format - * conversion, not xfs_bmapi_write(). - */ - error = xfs_bmap_local_to_extents(tp, ip, firstblock, total, - &bma.logflags, whichfork, - xfs_bmap_local_to_extents_init_fn); - if (error) - goto error0; - } - if (*firstblock == NULLFSBLOCK) { if (XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_BTREE) bma.minleft = be16_to_cpu(ifp->if_broot->bb_level) + 1; diff --git a/fs/xfs/xfs_bmap.h b/fs/xfs/xfs_bmap.h index 5f469c3516eb..1cf1292d29b7 100644 --- a/fs/xfs/xfs_bmap.h +++ b/fs/xfs/xfs_bmap.h @@ -172,6 +172,7 @@ void xfs_bmap_trace_exlist(struct xfs_inode *ip, xfs_extnum_t cnt, #endif int xfs_bmap_add_attrfork(struct xfs_inode *ip, int size, int rsvd); +void xfs_bmap_local_to_extents_empty(struct xfs_inode *ip, int whichfork); void xfs_bmap_add_free(xfs_fsblock_t bno, xfs_filblks_t len, struct xfs_bmap_free *flist, struct xfs_mount *mp); void xfs_bmap_cancel(struct xfs_bmap_free *flist); diff --git a/fs/xfs/xfs_dinode.h b/fs/xfs/xfs_dinode.h index f7a0e95d197a..07d735a80a0f 100644 --- a/fs/xfs/xfs_dinode.h +++ b/fs/xfs/xfs_dinode.h @@ -132,9 +132,6 @@ typedef enum xfs_dinode_fmt { #define XFS_LITINO(mp, version) \ ((int)(((mp)->m_sb.sb_inodesize) - xfs_dinode_size(version))) -#define XFS_BROOT_SIZE_ADJ(ip) \ - (XFS_BMBT_BLOCK_LEN((ip)->i_mount) - sizeof(xfs_bmdr_block_t)) - /* * Inode data & attribute fork sizes, per inode. */ diff --git a/fs/xfs/xfs_dir2_block.c b/fs/xfs/xfs_dir2_block.c index 09aea0247d96..5e7fbd72cf52 100644 --- a/fs/xfs/xfs_dir2_block.c +++ b/fs/xfs/xfs_dir2_block.c @@ -29,6 +29,7 @@ #include "xfs_dinode.h" #include "xfs_inode.h" #include "xfs_inode_item.h" +#include "xfs_bmap.h" #include "xfs_buf_item.h" #include "xfs_dir2.h" #include "xfs_dir2_format.h" @@ -1164,13 +1165,15 @@ xfs_dir2_sf_to_block( __be16 *tagp; /* end of data entry */ xfs_trans_t *tp; /* transaction pointer */ struct xfs_name name; + struct xfs_ifork *ifp; trace_xfs_dir2_sf_to_block(args); dp = args->dp; tp = args->trans; mp = dp->i_mount; - ASSERT(dp->i_df.if_flags & XFS_IFINLINE); + ifp = XFS_IFORK_PTR(dp, XFS_DATA_FORK); + ASSERT(ifp->if_flags & XFS_IFINLINE); /* * Bomb out if the shortform directory is way too short. */ @@ -1179,22 +1182,23 @@ xfs_dir2_sf_to_block( return XFS_ERROR(EIO); } - oldsfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; + oldsfp = (xfs_dir2_sf_hdr_t *)ifp->if_u1.if_data; - ASSERT(dp->i_df.if_bytes == dp->i_d.di_size); - ASSERT(dp->i_df.if_u1.if_data != NULL); + ASSERT(ifp->if_bytes == dp->i_d.di_size); + ASSERT(ifp->if_u1.if_data != NULL); ASSERT(dp->i_d.di_size >= xfs_dir2_sf_hdr_size(oldsfp->i8count)); + ASSERT(dp->i_d.di_nextents == 0); /* * Copy the directory into a temporary buffer. * Then pitch the incore inode data so we can make extents. */ - sfp = kmem_alloc(dp->i_df.if_bytes, KM_SLEEP); - memcpy(sfp, oldsfp, dp->i_df.if_bytes); + sfp = kmem_alloc(ifp->if_bytes, KM_SLEEP); + memcpy(sfp, oldsfp, ifp->if_bytes); - xfs_idata_realloc(dp, -dp->i_df.if_bytes, XFS_DATA_FORK); + xfs_idata_realloc(dp, -ifp->if_bytes, XFS_DATA_FORK); + xfs_bmap_local_to_extents_empty(dp, XFS_DATA_FORK); dp->i_d.di_size = 0; - xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE); /* * Add block 0 to the inode. diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c index f01012de06d0..0adf27ecf3f1 100644 --- a/fs/xfs/xfs_dquot.c +++ b/fs/xfs/xfs_dquot.c @@ -936,6 +936,7 @@ xfs_qm_dqput_final( { struct xfs_quotainfo *qi = dqp->q_mount->m_quotainfo; struct xfs_dquot *gdqp; + struct xfs_dquot *pdqp; trace_xfs_dqput_free(dqp); @@ -949,21 +950,29 @@ xfs_qm_dqput_final( /* * If we just added a udquot to the freelist, then we want to release - * the gdquot reference that it (probably) has. Otherwise it'll keep - * the gdquot from getting reclaimed. + * the gdquot/pdquot reference that it (probably) has. Otherwise it'll + * keep the gdquot/pdquot from getting reclaimed. */ gdqp = dqp->q_gdquot; if (gdqp) { xfs_dqlock(gdqp); dqp->q_gdquot = NULL; } + + pdqp = dqp->q_pdquot; + if (pdqp) { + xfs_dqlock(pdqp); + dqp->q_pdquot = NULL; + } xfs_dqunlock(dqp); /* - * If we had a group quota hint, release it now. + * If we had a group/project quota hint, release it now. */ if (gdqp) xfs_qm_dqput(gdqp); + if (pdqp) + xfs_qm_dqput(pdqp); } /* diff --git a/fs/xfs/xfs_dquot.h b/fs/xfs/xfs_dquot.h index b596626249b8..55abbca2883d 100644 --- a/fs/xfs/xfs_dquot.h +++ b/fs/xfs/xfs_dquot.h @@ -53,6 +53,7 @@ typedef struct xfs_dquot { xfs_fileoff_t q_fileoffset; /* offset in quotas file */ struct xfs_dquot*q_gdquot; /* group dquot, hint only */ + struct xfs_dquot*q_pdquot; /* project dquot, hint only */ xfs_disk_dquot_t q_core; /* actual usage & quotas */ xfs_dq_logitem_t q_logitem; /* dquot log item */ xfs_qcnt_t q_res_bcount; /* total regular nblks used+reserved */ @@ -118,8 +119,9 @@ static inline int xfs_this_quota_on(struct xfs_mount *mp, int type) case XFS_DQ_USER: return XFS_IS_UQUOTA_ON(mp); case XFS_DQ_GROUP: + return XFS_IS_GQUOTA_ON(mp); case XFS_DQ_PROJ: - return XFS_IS_OQUOTA_ON(mp); + return XFS_IS_PQUOTA_ON(mp); default: return 0; } @@ -131,8 +133,9 @@ static inline xfs_dquot_t *xfs_inode_dquot(struct xfs_inode *ip, int type) case XFS_DQ_USER: return ip->i_udquot; case XFS_DQ_GROUP: - case XFS_DQ_PROJ: return ip->i_gdquot; + case XFS_DQ_PROJ: + return ip->i_pdquot; default: return NULL; } diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index 9560dc1f15a9..3f90e1ceb8d6 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -337,6 +337,7 @@ xfs_iget_cache_miss( iflags |= XFS_IDONTCACHE; ip->i_udquot = NULL; ip->i_gdquot = NULL; + ip->i_pdquot = NULL; xfs_iflags_set(ip, iflags); /* insert the new inode */ diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 9ecfe1e559fc..b78481f99d9d 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -2156,8 +2156,8 @@ xfs_iroot_realloc( np = (char *)XFS_BMAP_BROOT_PTR_ADDR(mp, ifp->if_broot, 1, (int)new_size); ifp->if_broot_bytes = (int)new_size; - ASSERT(ifp->if_broot_bytes <= - XFS_IFORK_SIZE(ip, whichfork) + XFS_BROOT_SIZE_ADJ(ip)); + ASSERT(XFS_BMAP_BMDR_SPACE(ifp->if_broot) <= + XFS_IFORK_SIZE(ip, whichfork)); memmove(np, op, cur_max * (uint)sizeof(xfs_dfsbno_t)); return; } @@ -2210,8 +2210,9 @@ xfs_iroot_realloc( kmem_free(ifp->if_broot); ifp->if_broot = new_broot; ifp->if_broot_bytes = (int)new_size; - ASSERT(ifp->if_broot_bytes <= - XFS_IFORK_SIZE(ip, whichfork) + XFS_BROOT_SIZE_ADJ(ip)); + if (ifp->if_broot) + ASSERT(XFS_BMAP_BMDR_SPACE(ifp->if_broot) <= + XFS_IFORK_SIZE(ip, whichfork)); return; } @@ -2522,9 +2523,8 @@ xfs_iflush_fork( if ((iip->ili_fields & brootflag[whichfork]) && (ifp->if_broot_bytes > 0)) { ASSERT(ifp->if_broot != NULL); - ASSERT(ifp->if_broot_bytes <= - (XFS_IFORK_SIZE(ip, whichfork) + - XFS_BROOT_SIZE_ADJ(ip))); + ASSERT(XFS_BMAP_BMDR_SPACE(ifp->if_broot) <= + XFS_IFORK_SIZE(ip, whichfork)); xfs_bmbt_to_bmdr(mp, ifp->if_broot, ifp->if_broot_bytes, (xfs_bmdr_block_t *)cp, XFS_DFORK_SIZE(dip, mp, whichfork)); diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index 91129794aaec..b55fd347ab5b 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -250,6 +250,7 @@ typedef struct xfs_inode { struct xfs_mount *i_mount; /* fs mount struct ptr */ struct xfs_dquot *i_udquot; /* user dquot */ struct xfs_dquot *i_gdquot; /* group dquot */ + struct xfs_dquot *i_pdquot; /* project dquot */ /* Inode location stuff */ xfs_ino_t i_ino; /* inode number (agno/agino)*/ diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 5e999680094a..6e2bca5d44d6 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -248,7 +248,7 @@ xfs_open_by_handle( goto out_dput; } - fd = get_unused_fd(); + fd = get_unused_fd_flags(0); if (fd < 0) { error = fd; goto out_dput; @@ -928,7 +928,7 @@ xfs_ioctl_setattr( struct xfs_trans *tp; unsigned int lock_flags = 0; struct xfs_dquot *udqp = NULL; - struct xfs_dquot *gdqp = NULL; + struct xfs_dquot *pdqp = NULL; struct xfs_dquot *olddquot = NULL; int code; @@ -957,7 +957,7 @@ xfs_ioctl_setattr( if (XFS_IS_QUOTA_ON(mp) && (mask & FSX_PROJID)) { code = xfs_qm_vop_dqalloc(ip, ip->i_d.di_uid, ip->i_d.di_gid, fa->fsx_projid, - XFS_QMOPT_PQUOTA, &udqp, &gdqp); + XFS_QMOPT_PQUOTA, &udqp, NULL, &pdqp); if (code) return code; } @@ -994,8 +994,8 @@ xfs_ioctl_setattr( XFS_IS_PQUOTA_ON(mp) && xfs_get_projid(ip) != fa->fsx_projid) { ASSERT(tp); - code = xfs_qm_vop_chown_reserve(tp, ip, udqp, gdqp, - capable(CAP_FOWNER) ? + code = xfs_qm_vop_chown_reserve(tp, ip, udqp, NULL, + pdqp, capable(CAP_FOWNER) ? XFS_QMOPT_FORCE_RES : 0); if (code) /* out of quota */ goto error_return; @@ -1113,7 +1113,7 @@ xfs_ioctl_setattr( if (xfs_get_projid(ip) != fa->fsx_projid) { if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_PQUOTA_ON(mp)) { olddquot = xfs_qm_vop_chown(tp, ip, - &ip->i_gdquot, gdqp); + &ip->i_pdquot, pdqp); } xfs_set_projid(ip, fa->fsx_projid); @@ -1160,13 +1160,13 @@ xfs_ioctl_setattr( */ xfs_qm_dqrele(olddquot); xfs_qm_dqrele(udqp); - xfs_qm_dqrele(gdqp); + xfs_qm_dqrele(pdqp); return code; error_return: xfs_qm_dqrele(udqp); - xfs_qm_dqrele(gdqp); + xfs_qm_dqrele(pdqp); xfs_trans_cancel(tp, 0); if (lock_flags) xfs_iunlock(ip, lock_flags); diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index c69bbc493cb0..96dda62d497b 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -467,9 +467,6 @@ xfs_setattr_mode( ASSERT(tp); ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); - if (!in_group_p(inode->i_gid) && !capable(CAP_FSETID)) - mode &= ~S_ISGID; - ip->i_d.di_mode &= S_IFMT; ip->i_d.di_mode |= mode & ~S_IFMT; @@ -495,15 +492,18 @@ xfs_setattr_nonsize( trace_xfs_setattr(ip); - if (mp->m_flags & XFS_MOUNT_RDONLY) - return XFS_ERROR(EROFS); + /* If acls are being inherited, we already have this checked */ + if (!(flags & XFS_ATTR_NOACL)) { + if (mp->m_flags & XFS_MOUNT_RDONLY) + return XFS_ERROR(EROFS); - if (XFS_FORCED_SHUTDOWN(mp)) - return XFS_ERROR(EIO); + if (XFS_FORCED_SHUTDOWN(mp)) + return XFS_ERROR(EIO); - error = -inode_change_ok(inode, iattr); - if (error) - return XFS_ERROR(error); + error = -inode_change_ok(inode, iattr); + if (error) + return XFS_ERROR(error); + } ASSERT((mask & ATTR_SIZE) == 0); @@ -539,7 +539,7 @@ xfs_setattr_nonsize( ASSERT(udqp == NULL); ASSERT(gdqp == NULL); error = xfs_qm_vop_dqalloc(ip, uid, gid, xfs_get_projid(ip), - qflags, &udqp, &gdqp); + qflags, &udqp, &gdqp, NULL); if (error) return error; } @@ -575,7 +575,7 @@ xfs_setattr_nonsize( (XFS_IS_GQUOTA_ON(mp) && igid != gid))) { ASSERT(tp); error = xfs_qm_vop_chown_reserve(tp, ip, udqp, gdqp, - capable(CAP_FOWNER) ? + NULL, capable(CAP_FOWNER) ? XFS_QMOPT_FORCE_RES : 0); if (error) /* out of quota */ goto out_trans_cancel; diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c index bc92c5306a17..b93e14b86754 100644 --- a/fs/xfs/xfs_itable.c +++ b/fs/xfs/xfs_itable.c @@ -221,7 +221,6 @@ xfs_bulkstat( char __user *ubufp; /* pointer into user's buffer */ int ubelem; /* spaces used in user's buffer */ int ubused; /* bytes used by formatter */ - xfs_buf_t *bp; /* ptr to on-disk inode cluster buf */ /* * Get the last inode value, see if there's nothing to do. @@ -263,7 +262,6 @@ xfs_bulkstat( rval = 0; while (XFS_BULKSTAT_UBLEFT(ubleft) && agno < mp->m_sb.sb_agcount) { cond_resched(); - bp = NULL; error = xfs_ialloc_read_agi(mp, NULL, agno, &agbp); if (error) { /* @@ -436,27 +434,7 @@ xfs_bulkstat( irbp->ir_freecount < XFS_INODES_PER_CHUNK; chunkidx++, clustidx++, agino++) { ASSERT(chunkidx < XFS_INODES_PER_CHUNK); - /* - * Recompute agbno if this is the - * first inode of the cluster. - * - * Careful with clustidx. There can be - * multiple clusters per chunk, a single - * cluster per chunk or a cluster that has - * inodes represented from several different - * chunks (if blocksize is large). - * - * Because of this, the starting clustidx is - * initialized to zero in this loop but must - * later be reset after reading in the cluster - * buffer. - */ - if ((chunkidx & (nicluster - 1)) == 0) { - agbno = XFS_AGINO_TO_AGBNO(mp, - irbp->ir_startino) + - ((chunkidx & nimask) >> - mp->m_sb.sb_inopblog); - } + ino = XFS_AGINO_TO_INO(mp, agno, agino); /* * Skip if this inode is free. @@ -502,10 +480,6 @@ xfs_bulkstat( cond_resched(); } - - if (bp) - xfs_buf_relse(bp); - /* * Set up for the next loop iteration. */ diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index 7a3e007b49f4..d320794d03ce 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -137,6 +137,7 @@ xfs_qm_dqpurge( struct xfs_mount *mp = dqp->q_mount; struct xfs_quotainfo *qi = mp->m_quotainfo; struct xfs_dquot *gdqp = NULL; + struct xfs_dquot *pdqp = NULL; xfs_dqlock(dqp); if ((dqp->dq_flags & XFS_DQ_FREEING) || dqp->q_nrefs != 0) { @@ -145,8 +146,7 @@ xfs_qm_dqpurge( } /* - * If this quota has a group hint attached, prepare for releasing it - * now. + * If this quota has a hint attached, prepare for releasing it now. */ gdqp = dqp->q_gdquot; if (gdqp) { @@ -154,6 +154,12 @@ xfs_qm_dqpurge( dqp->q_gdquot = NULL; } + pdqp = dqp->q_pdquot; + if (pdqp) { + xfs_dqlock(pdqp); + dqp->q_pdquot = NULL; + } + dqp->dq_flags |= XFS_DQ_FREEING; xfs_dqflock(dqp); @@ -208,6 +214,8 @@ xfs_qm_dqpurge( if (gdqp) xfs_qm_dqput(gdqp); + if (pdqp) + xfs_qm_dqput(pdqp); return 0; } @@ -364,6 +372,10 @@ xfs_qm_unmount_quotas( IRELE(mp->m_quotainfo->qi_gquotaip); mp->m_quotainfo->qi_gquotaip = NULL; } + if (mp->m_quotainfo->qi_pquotaip) { + IRELE(mp->m_quotainfo->qi_pquotaip); + mp->m_quotainfo->qi_pquotaip = NULL; + } } } @@ -410,7 +422,10 @@ xfs_qm_dqattach_one( * be reclaimed as long as we have a ref from inode and we * hold the ilock. */ - dqp = udqhint->q_gdquot; + if (type == XFS_DQ_GROUP) + dqp = udqhint->q_gdquot; + else + dqp = udqhint->q_pdquot; if (dqp && be32_to_cpu(dqp->q_core.d_id) == id) { ASSERT(*IO_idqpp == NULL); @@ -453,28 +468,42 @@ xfs_qm_dqattach_one( /* - * Given a udquot and gdquot, attach a ptr to the group dquot in the - * udquot as a hint for future lookups. + * Given a udquot and group/project type, attach the group/project + * dquot pointer to the udquot as a hint for future lookups. */ STATIC void -xfs_qm_dqattach_grouphint( - xfs_dquot_t *udq, - xfs_dquot_t *gdq) +xfs_qm_dqattach_hint( + struct xfs_inode *ip, + int type) { - xfs_dquot_t *tmp; + struct xfs_dquot **dqhintp; + struct xfs_dquot *dqp; + struct xfs_dquot *udq = ip->i_udquot; + + ASSERT(type == XFS_DQ_GROUP || type == XFS_DQ_PROJ); xfs_dqlock(udq); - tmp = udq->q_gdquot; - if (tmp) { - if (tmp == gdq) + if (type == XFS_DQ_GROUP) { + dqp = ip->i_gdquot; + dqhintp = &udq->q_gdquot; + } else { + dqp = ip->i_pdquot; + dqhintp = &udq->q_pdquot; + } + + if (*dqhintp) { + struct xfs_dquot *tmp; + + if (*dqhintp == dqp) goto done; - udq->q_gdquot = NULL; + tmp = *dqhintp; + *dqhintp = NULL; xfs_qm_dqrele(tmp); } - udq->q_gdquot = xfs_qm_dqhold(gdq); + *dqhintp = xfs_qm_dqhold(dqp); done: xfs_dqunlock(udq); } @@ -527,12 +556,8 @@ xfs_qm_dqattach_locked( } ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); - if (XFS_IS_OQUOTA_ON(mp)) { - error = XFS_IS_GQUOTA_ON(mp) ? - xfs_qm_dqattach_one(ip, ip->i_d.di_gid, XFS_DQ_GROUP, - flags & XFS_QMOPT_DQALLOC, - ip->i_udquot, &ip->i_gdquot) : - xfs_qm_dqattach_one(ip, xfs_get_projid(ip), XFS_DQ_PROJ, + if (XFS_IS_GQUOTA_ON(mp)) { + error = xfs_qm_dqattach_one(ip, ip->i_d.di_gid, XFS_DQ_GROUP, flags & XFS_QMOPT_DQALLOC, ip->i_udquot, &ip->i_gdquot); /* @@ -544,14 +569,28 @@ xfs_qm_dqattach_locked( nquotas++; } + ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); + if (XFS_IS_PQUOTA_ON(mp)) { + error = xfs_qm_dqattach_one(ip, xfs_get_projid(ip), XFS_DQ_PROJ, + flags & XFS_QMOPT_DQALLOC, + ip->i_udquot, &ip->i_pdquot); + /* + * Don't worry about the udquot that we may have + * attached above. It'll get detached, if not already. + */ + if (error) + goto done; + nquotas++; + } + /* - * Attach this group quota to the user quota as a hint. + * Attach this group/project quota to the user quota as a hint. * This WON'T, in general, result in a thrash. */ - if (nquotas == 2) { + if (nquotas > 1 && ip->i_udquot) { ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); - ASSERT(ip->i_udquot); - ASSERT(ip->i_gdquot); + ASSERT(ip->i_gdquot || !XFS_IS_GQUOTA_ON(mp)); + ASSERT(ip->i_pdquot || !XFS_IS_PQUOTA_ON(mp)); /* * We do not have i_udquot locked at this point, but this check @@ -560,7 +599,10 @@ xfs_qm_dqattach_locked( * succeed in general. */ if (ip->i_udquot->q_gdquot != ip->i_gdquot) - xfs_qm_dqattach_grouphint(ip->i_udquot, ip->i_gdquot); + xfs_qm_dqattach_hint(ip, XFS_DQ_GROUP); + + if (ip->i_udquot->q_pdquot != ip->i_pdquot) + xfs_qm_dqattach_hint(ip, XFS_DQ_PROJ); } done: @@ -568,8 +610,10 @@ xfs_qm_dqattach_locked( if (!error) { if (XFS_IS_UQUOTA_ON(mp)) ASSERT(ip->i_udquot); - if (XFS_IS_OQUOTA_ON(mp)) + if (XFS_IS_GQUOTA_ON(mp)) ASSERT(ip->i_gdquot); + if (XFS_IS_PQUOTA_ON(mp)) + ASSERT(ip->i_pdquot); } ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); #endif @@ -602,7 +646,7 @@ void xfs_qm_dqdetach( xfs_inode_t *ip) { - if (!(ip->i_udquot || ip->i_gdquot)) + if (!(ip->i_udquot || ip->i_gdquot || ip->i_pdquot)) return; trace_xfs_dquot_dqdetach(ip); @@ -616,6 +660,10 @@ xfs_qm_dqdetach( xfs_qm_dqrele(ip->i_gdquot); ip->i_gdquot = NULL; } + if (ip->i_pdquot) { + xfs_qm_dqrele(ip->i_pdquot); + ip->i_pdquot = NULL; + } } int @@ -660,6 +708,7 @@ xfs_qm_init_quotainfo( INIT_RADIX_TREE(&qinf->qi_uquota_tree, GFP_NOFS); INIT_RADIX_TREE(&qinf->qi_gquota_tree, GFP_NOFS); + INIT_RADIX_TREE(&qinf->qi_pquota_tree, GFP_NOFS); mutex_init(&qinf->qi_tree_lock); INIT_LIST_HEAD(&qinf->qi_lru_list); @@ -761,6 +810,10 @@ xfs_qm_destroy_quotainfo( IRELE(qi->qi_gquotaip); qi->qi_gquotaip = NULL; } + if (qi->qi_pquotaip) { + IRELE(qi->qi_pquotaip); + qi->qi_pquotaip = NULL; + } mutex_destroy(&qi->qi_quotaofflock); kmem_free(qi); mp->m_quotainfo = NULL; @@ -1269,13 +1322,14 @@ xfs_qm_quotacheck( LIST_HEAD (buffer_list); struct xfs_inode *uip = mp->m_quotainfo->qi_uquotaip; struct xfs_inode *gip = mp->m_quotainfo->qi_gquotaip; + struct xfs_inode *pip = mp->m_quotainfo->qi_pquotaip; count = INT_MAX; structsz = 1; lastino = 0; flags = 0; - ASSERT(uip || gip); + ASSERT(uip || gip || pip); ASSERT(XFS_IS_QUOTA_RUNNING(mp)); xfs_notice(mp, "Quotacheck needed: Please wait."); @@ -1294,13 +1348,19 @@ xfs_qm_quotacheck( } if (gip) { - error = xfs_qm_dqiterate(mp, gip, XFS_IS_GQUOTA_ON(mp) ? - XFS_QMOPT_GQUOTA : XFS_QMOPT_PQUOTA, + error = xfs_qm_dqiterate(mp, gip, XFS_QMOPT_GQUOTA, &buffer_list); if (error) goto error_return; - flags |= XFS_IS_GQUOTA_ON(mp) ? - XFS_GQUOTA_CHKD : XFS_PQUOTA_CHKD; + flags |= XFS_GQUOTA_CHKD; + } + + if (pip) { + error = xfs_qm_dqiterate(mp, pip, XFS_QMOPT_PQUOTA, + &buffer_list); + if (error) + goto error_return; + flags |= XFS_PQUOTA_CHKD; } do { @@ -1397,6 +1457,7 @@ xfs_qm_init_quotainos( { struct xfs_inode *uip = NULL; struct xfs_inode *gip = NULL; + struct xfs_inode *pip = NULL; int error; __int64_t sbflags = 0; uint flags = 0; @@ -1415,7 +1476,7 @@ xfs_qm_init_quotainos( if (error) return XFS_ERROR(error); } - if (XFS_IS_OQUOTA_ON(mp) && + if (XFS_IS_GQUOTA_ON(mp) && mp->m_sb.sb_gquotino != NULLFSINO) { ASSERT(mp->m_sb.sb_gquotino > 0); error = xfs_iget(mp, NULL, mp->m_sb.sb_gquotino, @@ -1423,6 +1484,15 @@ xfs_qm_init_quotainos( if (error) goto error_rele; } + /* XXX: Use gquotino for now */ + if (XFS_IS_PQUOTA_ON(mp) && + mp->m_sb.sb_gquotino != NULLFSINO) { + ASSERT(mp->m_sb.sb_gquotino > 0); + error = xfs_iget(mp, NULL, mp->m_sb.sb_gquotino, + 0, 0, &pip); + if (error) + goto error_rele; + } } else { flags |= XFS_QMOPT_SBVERSION; sbflags |= (XFS_SB_VERSIONNUM | XFS_SB_UQUOTINO | @@ -1430,7 +1500,7 @@ xfs_qm_init_quotainos( } /* - * Create the two inodes, if they don't exist already. The changes + * Create the three inodes, if they don't exist already. The changes * made above will get added to a transaction and logged in one of * the qino_alloc calls below. If the device is readonly, * temporarily switch to read-write to do this. @@ -1444,17 +1514,27 @@ xfs_qm_init_quotainos( flags &= ~XFS_QMOPT_SBVERSION; } - if (XFS_IS_OQUOTA_ON(mp) && gip == NULL) { - flags |= (XFS_IS_GQUOTA_ON(mp) ? - XFS_QMOPT_GQUOTA : XFS_QMOPT_PQUOTA); + if (XFS_IS_GQUOTA_ON(mp) && gip == NULL) { error = xfs_qm_qino_alloc(mp, &gip, - sbflags | XFS_SB_GQUOTINO, flags); + sbflags | XFS_SB_GQUOTINO, + flags | XFS_QMOPT_GQUOTA); + if (error) + goto error_rele; + + flags &= ~XFS_QMOPT_SBVERSION; + } + if (XFS_IS_PQUOTA_ON(mp) && pip == NULL) { + /* XXX: Use XFS_SB_GQUOTINO for now */ + error = xfs_qm_qino_alloc(mp, &pip, + sbflags | XFS_SB_GQUOTINO, + flags | XFS_QMOPT_PQUOTA); if (error) goto error_rele; } mp->m_quotainfo->qi_uquotaip = uip; mp->m_quotainfo->qi_gquotaip = gip; + mp->m_quotainfo->qi_pquotaip = pip; return 0; @@ -1463,6 +1543,8 @@ error_rele: IRELE(uip); if (gip) IRELE(gip); + if (pip) + IRELE(pip); return XFS_ERROR(error); } @@ -1657,11 +1739,13 @@ xfs_qm_vop_dqalloc( prid_t prid, uint flags, struct xfs_dquot **O_udqpp, - struct xfs_dquot **O_gdqpp) + struct xfs_dquot **O_gdqpp, + struct xfs_dquot **O_pdqpp) { struct xfs_mount *mp = ip->i_mount; struct xfs_dquot *uq = NULL; struct xfs_dquot *gq = NULL; + struct xfs_dquot *pq = NULL; int error; uint lockflags; @@ -1741,24 +1825,25 @@ xfs_qm_vop_dqalloc( ASSERT(ip->i_gdquot); gq = xfs_qm_dqhold(ip->i_gdquot); } - } else if ((flags & XFS_QMOPT_PQUOTA) && XFS_IS_PQUOTA_ON(mp)) { + } + if ((flags & XFS_QMOPT_PQUOTA) && XFS_IS_PQUOTA_ON(mp)) { if (xfs_get_projid(ip) != prid) { xfs_iunlock(ip, lockflags); error = xfs_qm_dqget(mp, NULL, (xfs_dqid_t)prid, XFS_DQ_PROJ, XFS_QMOPT_DQALLOC | XFS_QMOPT_DOWARN, - &gq); + &pq); if (error) { ASSERT(error != ENOENT); goto error_rele; } - xfs_dqunlock(gq); + xfs_dqunlock(pq); lockflags = XFS_ILOCK_SHARED; xfs_ilock(ip, lockflags); } else { - ASSERT(ip->i_gdquot); - gq = xfs_qm_dqhold(ip->i_gdquot); + ASSERT(ip->i_pdquot); + pq = xfs_qm_dqhold(ip->i_pdquot); } } if (uq) @@ -1773,9 +1858,15 @@ xfs_qm_vop_dqalloc( *O_gdqpp = gq; else if (gq) xfs_qm_dqrele(gq); + if (O_pdqpp) + *O_pdqpp = pq; + else if (pq) + xfs_qm_dqrele(pq); return 0; error_rele: + if (gq) + xfs_qm_dqrele(gq); if (uq) xfs_qm_dqrele(uq); return error; @@ -1830,14 +1921,17 @@ xfs_qm_vop_chown_reserve( struct xfs_inode *ip, struct xfs_dquot *udqp, struct xfs_dquot *gdqp, + struct xfs_dquot *pdqp, uint flags) { struct xfs_mount *mp = ip->i_mount; uint delblks, blkflags, prjflags = 0; struct xfs_dquot *udq_unres = NULL; struct xfs_dquot *gdq_unres = NULL; + struct xfs_dquot *pdq_unres = NULL; struct xfs_dquot *udq_delblks = NULL; struct xfs_dquot *gdq_delblks = NULL; + struct xfs_dquot *pdq_delblks = NULL; int error; @@ -1861,24 +1955,28 @@ xfs_qm_vop_chown_reserve( udq_unres = ip->i_udquot; } } - if (XFS_IS_OQUOTA_ON(ip->i_mount) && gdqp) { - if (XFS_IS_PQUOTA_ON(ip->i_mount) && - xfs_get_projid(ip) != be32_to_cpu(gdqp->q_core.d_id)) - prjflags = XFS_QMOPT_ENOSPC; - - if (prjflags || - (XFS_IS_GQUOTA_ON(ip->i_mount) && - ip->i_d.di_gid != be32_to_cpu(gdqp->q_core.d_id))) { - gdq_delblks = gdqp; - if (delblks) { - ASSERT(ip->i_gdquot); - gdq_unres = ip->i_gdquot; - } + if (XFS_IS_GQUOTA_ON(ip->i_mount) && gdqp && + ip->i_d.di_gid != be32_to_cpu(gdqp->q_core.d_id)) { + gdq_delblks = gdqp; + if (delblks) { + ASSERT(ip->i_gdquot); + gdq_unres = ip->i_gdquot; + } + } + + if (XFS_IS_PQUOTA_ON(ip->i_mount) && pdqp && + xfs_get_projid(ip) != be32_to_cpu(pdqp->q_core.d_id)) { + prjflags = XFS_QMOPT_ENOSPC; + pdq_delblks = pdqp; + if (delblks) { + ASSERT(ip->i_pdquot); + pdq_unres = ip->i_pdquot; } } error = xfs_trans_reserve_quota_bydquots(tp, ip->i_mount, - udq_delblks, gdq_delblks, ip->i_d.di_nblocks, 1, + udq_delblks, gdq_delblks, pdq_delblks, + ip->i_d.di_nblocks, 1, flags | blkflags | prjflags); if (error) return error; @@ -1893,16 +1991,17 @@ xfs_qm_vop_chown_reserve( /* * Do the reservations first. Unreservation can't fail. */ - ASSERT(udq_delblks || gdq_delblks); - ASSERT(udq_unres || gdq_unres); + ASSERT(udq_delblks || gdq_delblks || pdq_delblks); + ASSERT(udq_unres || gdq_unres || pdq_unres); error = xfs_trans_reserve_quota_bydquots(NULL, ip->i_mount, - udq_delblks, gdq_delblks, (xfs_qcnt_t)delblks, 0, + udq_delblks, gdq_delblks, pdq_delblks, + (xfs_qcnt_t)delblks, 0, flags | blkflags | prjflags); if (error) return error; xfs_trans_reserve_quota_bydquots(NULL, ip->i_mount, - udq_unres, gdq_unres, -((xfs_qcnt_t)delblks), 0, - blkflags); + udq_unres, gdq_unres, pdq_unres, + -((xfs_qcnt_t)delblks), 0, blkflags); } return (0); @@ -1941,7 +2040,8 @@ xfs_qm_vop_create_dqattach( struct xfs_trans *tp, struct xfs_inode *ip, struct xfs_dquot *udqp, - struct xfs_dquot *gdqp) + struct xfs_dquot *gdqp, + struct xfs_dquot *pdqp) { struct xfs_mount *mp = tp->t_mountp; @@ -1961,13 +2061,18 @@ xfs_qm_vop_create_dqattach( } if (gdqp) { ASSERT(ip->i_gdquot == NULL); - ASSERT(XFS_IS_OQUOTA_ON(mp)); - ASSERT((XFS_IS_GQUOTA_ON(mp) ? - ip->i_d.di_gid : xfs_get_projid(ip)) == - be32_to_cpu(gdqp->q_core.d_id)); - + ASSERT(XFS_IS_GQUOTA_ON(mp)); + ASSERT(ip->i_d.di_gid == be32_to_cpu(gdqp->q_core.d_id)); ip->i_gdquot = xfs_qm_dqhold(gdqp); xfs_trans_mod_dquot(tp, gdqp, XFS_TRANS_DQ_ICOUNT, 1); } + if (pdqp) { + ASSERT(ip->i_pdquot == NULL); + ASSERT(XFS_IS_PQUOTA_ON(mp)); + ASSERT(xfs_get_projid(ip) == be32_to_cpu(pdqp->q_core.d_id)); + + ip->i_pdquot = xfs_qm_dqhold(pdqp); + xfs_trans_mod_dquot(tp, pdqp, XFS_TRANS_DQ_ICOUNT, 1); + } } diff --git a/fs/xfs/xfs_qm.h b/fs/xfs/xfs_qm.h index bdb4f8b95207..579d6a02a5b6 100644 --- a/fs/xfs/xfs_qm.h +++ b/fs/xfs/xfs_qm.h @@ -44,9 +44,11 @@ extern struct kmem_zone *xfs_qm_dqtrxzone; typedef struct xfs_quotainfo { struct radix_tree_root qi_uquota_tree; struct radix_tree_root qi_gquota_tree; + struct radix_tree_root qi_pquota_tree; struct mutex qi_tree_lock; - xfs_inode_t *qi_uquotaip; /* user quota inode */ - xfs_inode_t *qi_gquotaip; /* group quota inode */ + struct xfs_inode *qi_uquotaip; /* user quota inode */ + struct xfs_inode *qi_gquotaip; /* group quota inode */ + struct xfs_inode *qi_pquotaip; /* project quota inode */ struct list_head qi_lru_list; struct mutex qi_lru_lock; int qi_lru_count; @@ -78,8 +80,9 @@ xfs_dquot_tree( case XFS_DQ_USER: return &qi->qi_uquota_tree; case XFS_DQ_GROUP: - case XFS_DQ_PROJ: return &qi->qi_gquota_tree; + case XFS_DQ_PROJ: + return &qi->qi_pquota_tree; default: ASSERT(0); } @@ -93,8 +96,9 @@ xfs_dq_to_quota_inode(struct xfs_dquot *dqp) case XFS_DQ_USER: return dqp->q_mount->m_quotainfo->qi_uquotaip; case XFS_DQ_GROUP: - case XFS_DQ_PROJ: return dqp->q_mount->m_quotainfo->qi_gquotaip; + case XFS_DQ_PROJ: + return dqp->q_mount->m_quotainfo->qi_pquotaip; default: ASSERT(0); } @@ -107,18 +111,20 @@ extern void xfs_trans_mod_dquot(struct xfs_trans *, struct xfs_dquot *, uint, long); extern int xfs_trans_reserve_quota_bydquots(struct xfs_trans *, struct xfs_mount *, struct xfs_dquot *, - struct xfs_dquot *, long, long, uint); + struct xfs_dquot *, struct xfs_dquot *, + long, long, uint); extern void xfs_trans_dqjoin(struct xfs_trans *, struct xfs_dquot *); extern void xfs_trans_log_dquot(struct xfs_trans *, struct xfs_dquot *); /* - * We keep the usr and grp dquots separately so that locking will be easier - * to do at commit time. All transactions that we know of at this point + * We keep the usr, grp, and prj dquots separately so that locking will be + * easier to do at commit time. All transactions that we know of at this point * affect no more than two dquots of one type. Hence, the TRANS_MAXDQS value. */ enum { XFS_QM_TRANS_USR = 0, XFS_QM_TRANS_GRP, + XFS_QM_TRANS_PRJ, XFS_QM_TRANS_DQTYPES }; #define XFS_QM_TRANS_MAXDQS 2 diff --git a/fs/xfs/xfs_qm_bhv.c b/fs/xfs/xfs_qm_bhv.c index 2d02eac1c9a8..437a52d91f6d 100644 --- a/fs/xfs/xfs_qm_bhv.c +++ b/fs/xfs/xfs_qm_bhv.c @@ -112,16 +112,16 @@ xfs_qm_newmount( if (((uquotaondisk && !XFS_IS_UQUOTA_ON(mp)) || (!uquotaondisk && XFS_IS_UQUOTA_ON(mp)) || - (pquotaondisk && !XFS_IS_PQUOTA_ON(mp)) || - (!pquotaondisk && XFS_IS_PQUOTA_ON(mp)) || (gquotaondisk && !XFS_IS_GQUOTA_ON(mp)) || - (!gquotaondisk && XFS_IS_OQUOTA_ON(mp))) && + (!gquotaondisk && XFS_IS_GQUOTA_ON(mp)) || + (pquotaondisk && !XFS_IS_PQUOTA_ON(mp)) || + (!pquotaondisk && XFS_IS_PQUOTA_ON(mp))) && xfs_dev_is_read_only(mp, "changing quota state")) { xfs_warn(mp, "please mount with%s%s%s%s.", (!quotaondisk ? "out quota" : ""), (uquotaondisk ? " usrquota" : ""), - (pquotaondisk ? " prjquota" : ""), - (gquotaondisk ? " grpquota" : "")); + (gquotaondisk ? " grpquota" : ""), + (pquotaondisk ? " prjquota" : "")); return XFS_ERROR(EPERM); } diff --git a/fs/xfs/xfs_qm_syscalls.c b/fs/xfs/xfs_qm_syscalls.c index a08801ae24e2..e4f8b2d6f38b 100644 --- a/fs/xfs/xfs_qm_syscalls.c +++ b/fs/xfs/xfs_qm_syscalls.c @@ -119,7 +119,8 @@ xfs_qm_scall_quotaoff( dqtype |= XFS_QMOPT_GQUOTA; flags |= (XFS_GQUOTA_CHKD | XFS_GQUOTA_ENFD); inactivate_flags |= XFS_GQUOTA_ACTIVE; - } else if (flags & XFS_PQUOTA_ACCT) { + } + if (flags & XFS_PQUOTA_ACCT) { dqtype |= XFS_QMOPT_PQUOTA; flags |= (XFS_PQUOTA_CHKD | XFS_PQUOTA_ENFD); inactivate_flags |= XFS_PQUOTA_ACTIVE; @@ -198,10 +199,9 @@ xfs_qm_scall_quotaoff( } /* - * If quotas is completely disabled, close shop. + * If all quotas are completely turned off, close shop. */ - if (((flags & XFS_MOUNT_QUOTA_ALL) == XFS_MOUNT_QUOTA_SET1) || - ((flags & XFS_MOUNT_QUOTA_ALL) == XFS_MOUNT_QUOTA_SET2)) { + if (mp->m_qflags == 0) { mutex_unlock(&q->qi_quotaofflock); xfs_qm_destroy_quotainfo(mp); return (0); @@ -214,10 +214,14 @@ xfs_qm_scall_quotaoff( IRELE(q->qi_uquotaip); q->qi_uquotaip = NULL; } - if ((dqtype & (XFS_QMOPT_GQUOTA|XFS_QMOPT_PQUOTA)) && q->qi_gquotaip) { + if ((dqtype & XFS_QMOPT_GQUOTA) && q->qi_gquotaip) { IRELE(q->qi_gquotaip); q->qi_gquotaip = NULL; } + if ((dqtype & XFS_QMOPT_PQUOTA) && q->qi_pquotaip) { + IRELE(q->qi_pquotaip); + q->qi_pquotaip = NULL; + } out_unlock: mutex_unlock(&q->qi_quotaofflock); @@ -859,9 +863,11 @@ xfs_dqrele_inode( { /* skip quota inodes */ if (ip == ip->i_mount->m_quotainfo->qi_uquotaip || - ip == ip->i_mount->m_quotainfo->qi_gquotaip) { + ip == ip->i_mount->m_quotainfo->qi_gquotaip || + ip == ip->i_mount->m_quotainfo->qi_pquotaip) { ASSERT(ip->i_udquot == NULL); ASSERT(ip->i_gdquot == NULL); + ASSERT(ip->i_pdquot == NULL); return 0; } @@ -870,10 +876,14 @@ xfs_dqrele_inode( xfs_qm_dqrele(ip->i_udquot); ip->i_udquot = NULL; } - if (flags & (XFS_PQUOTA_ACCT|XFS_GQUOTA_ACCT) && ip->i_gdquot) { + if ((flags & XFS_GQUOTA_ACCT) && ip->i_gdquot) { xfs_qm_dqrele(ip->i_gdquot); ip->i_gdquot = NULL; } + if ((flags & XFS_PQUOTA_ACCT) && ip->i_pdquot) { + xfs_qm_dqrele(ip->i_pdquot); + ip->i_pdquot = NULL; + } xfs_iunlock(ip, XFS_ILOCK_EXCL); return 0; } diff --git a/fs/xfs/xfs_quota.h b/fs/xfs/xfs_quota.h index c3483bab9cde..b14f42c714b6 100644 --- a/fs/xfs/xfs_quota.h +++ b/fs/xfs/xfs_quota.h @@ -108,11 +108,28 @@ typedef struct xfs_dqblk { { XFS_DQ_FREEING, "FREEING" } /* - * In the worst case, when both user and group quotas are on, - * we can have a max of three dquots changing in a single transaction. + * We have the possibility of all three quota types being active at once, and + * hence free space modification requires modification of all three current + * dquots in a single transaction. For this case we need to have a reservation + * of at least 3 dquots. + * + * However, a chmod operation can change both UID and GID in a single + * transaction, resulting in requiring {old, new} x {uid, gid} dquots to be + * modified. Hence for this case we need to reserve space for at least 4 dquots. + * + * And in the worst case, there's a rename operation that can be modifying up to + * 4 inodes with dquots attached to them. In reality, the only inodes that can + * have their dquots modified are the source and destination directory inodes + * due to directory name creation and removal. That can require space allocation + * and/or freeing on both directory inodes, and hence all three dquots on each + * inode can be modified. And if the directories are world writeable, all the + * dquots can be unique and so 6 dquots can be modified.... + * + * And, of course, we also need to take into account the dquot log format item + * used to describe each dquot. */ -#define XFS_DQUOT_LOGRES(mp) (sizeof(xfs_disk_dquot_t) * 3) - +#define XFS_DQUOT_LOGRES(mp) \ + ((sizeof(struct xfs_dq_logformat) + sizeof(struct xfs_disk_dquot)) * 6) /* * These are the structures used to lay out dquots and quotaoff @@ -271,10 +288,10 @@ typedef struct xfs_qoff_logformat { * we didn't have the inode locked, the appropriate dquot(s) will be * attached atomically. */ -#define XFS_NOT_DQATTACHED(mp, ip) ((XFS_IS_UQUOTA_ON(mp) &&\ - (ip)->i_udquot == NULL) || \ - (XFS_IS_OQUOTA_ON(mp) && \ - (ip)->i_gdquot == NULL)) +#define XFS_NOT_DQATTACHED(mp, ip) \ + ((XFS_IS_UQUOTA_ON(mp) && (ip)->i_udquot == NULL) || \ + (XFS_IS_GQUOTA_ON(mp) && (ip)->i_gdquot == NULL) || \ + (XFS_IS_PQUOTA_ON(mp) && (ip)->i_pdquot == NULL)) #define XFS_QM_NEED_QUOTACHECK(mp) \ ((XFS_IS_UQUOTA_ON(mp) && \ @@ -284,14 +301,6 @@ typedef struct xfs_qoff_logformat { (XFS_IS_PQUOTA_ON(mp) && \ (mp->m_sb.sb_qflags & XFS_PQUOTA_CHKD) == 0)) -#define XFS_MOUNT_QUOTA_SET1 (XFS_UQUOTA_ACCT|XFS_UQUOTA_ENFD|\ - XFS_UQUOTA_CHKD|XFS_GQUOTA_ACCT|\ - XFS_GQUOTA_ENFD|XFS_GQUOTA_CHKD) - -#define XFS_MOUNT_QUOTA_SET2 (XFS_UQUOTA_ACCT|XFS_UQUOTA_ENFD|\ - XFS_UQUOTA_CHKD|XFS_PQUOTA_ACCT|\ - XFS_PQUOTA_ENFD|XFS_PQUOTA_CHKD) - #define XFS_MOUNT_QUOTA_ALL (XFS_UQUOTA_ACCT|XFS_UQUOTA_ENFD|\ XFS_UQUOTA_CHKD|XFS_GQUOTA_ACCT|\ XFS_GQUOTA_ENFD|XFS_GQUOTA_CHKD|\ @@ -329,17 +338,18 @@ extern int xfs_trans_reserve_quota_nblks(struct xfs_trans *, struct xfs_inode *, long, long, uint); extern int xfs_trans_reserve_quota_bydquots(struct xfs_trans *, struct xfs_mount *, struct xfs_dquot *, - struct xfs_dquot *, long, long, uint); + struct xfs_dquot *, struct xfs_dquot *, long, long, uint); extern int xfs_qm_vop_dqalloc(struct xfs_inode *, uid_t, gid_t, prid_t, uint, - struct xfs_dquot **, struct xfs_dquot **); + struct xfs_dquot **, struct xfs_dquot **, struct xfs_dquot **); extern void xfs_qm_vop_create_dqattach(struct xfs_trans *, struct xfs_inode *, - struct xfs_dquot *, struct xfs_dquot *); + struct xfs_dquot *, struct xfs_dquot *, struct xfs_dquot *); extern int xfs_qm_vop_rename_dqattach(struct xfs_inode **); extern struct xfs_dquot *xfs_qm_vop_chown(struct xfs_trans *, struct xfs_inode *, struct xfs_dquot **, struct xfs_dquot *); extern int xfs_qm_vop_chown_reserve(struct xfs_trans *, struct xfs_inode *, - struct xfs_dquot *, struct xfs_dquot *, uint); + struct xfs_dquot *, struct xfs_dquot *, + struct xfs_dquot *, uint); extern int xfs_qm_dqattach(struct xfs_inode *, uint); extern int xfs_qm_dqattach_locked(struct xfs_inode *, uint); extern void xfs_qm_dqdetach(struct xfs_inode *); @@ -353,10 +363,12 @@ extern void xfs_qm_unmount_quotas(struct xfs_mount *); #else static inline int xfs_qm_vop_dqalloc(struct xfs_inode *ip, uid_t uid, gid_t gid, prid_t prid, - uint flags, struct xfs_dquot **udqp, struct xfs_dquot **gdqp) + uint flags, struct xfs_dquot **udqp, struct xfs_dquot **gdqp, + struct xfs_dquot **pdqp) { *udqp = NULL; *gdqp = NULL; + *pdqp = NULL; return 0; } #define xfs_trans_dup_dqinfo(tp, tp2) @@ -371,14 +383,15 @@ static inline int xfs_trans_reserve_quota_nblks(struct xfs_trans *tp, } static inline int xfs_trans_reserve_quota_bydquots(struct xfs_trans *tp, struct xfs_mount *mp, struct xfs_dquot *udqp, - struct xfs_dquot *gdqp, long nblks, long nions, uint flags) + struct xfs_dquot *gdqp, struct xfs_dquot *pdqp, + long nblks, long nions, uint flags) { return 0; } -#define xfs_qm_vop_create_dqattach(tp, ip, u, g) +#define xfs_qm_vop_create_dqattach(tp, ip, u, g, p) #define xfs_qm_vop_rename_dqattach(it) (0) #define xfs_qm_vop_chown(tp, ip, old, new) (NULL) -#define xfs_qm_vop_chown_reserve(tp, ip, u, g, fl) (0) +#define xfs_qm_vop_chown_reserve(tp, ip, u, g, p, fl) (0) #define xfs_qm_dqattach(ip, fl) (0) #define xfs_qm_dqattach_locked(ip, fl) (0) #define xfs_qm_dqdetach(ip) @@ -392,8 +405,8 @@ static inline int xfs_trans_reserve_quota_bydquots(struct xfs_trans *tp, #define xfs_trans_unreserve_quota_nblks(tp, ip, nblks, ninos, flags) \ xfs_trans_reserve_quota_nblks(tp, ip, -(nblks), -(ninos), flags) -#define xfs_trans_reserve_quota(tp, mp, ud, gd, nb, ni, f) \ - xfs_trans_reserve_quota_bydquots(tp, mp, ud, gd, nb, ni, \ +#define xfs_trans_reserve_quota(tp, mp, ud, gd, pd, nb, ni, f) \ + xfs_trans_reserve_quota_bydquots(tp, mp, ud, gd, pd, nb, ni, \ f | XFS_QMOPT_RES_REGBLKS) extern int xfs_qm_dqcheck(struct xfs_mount *, xfs_disk_dquot_t *, diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c index e830fb56e27f..f4895b662fcb 100644 --- a/fs/xfs/xfs_symlink.c +++ b/fs/xfs/xfs_symlink.c @@ -360,6 +360,7 @@ xfs_symlink( prid_t prid; struct xfs_dquot *udqp = NULL; struct xfs_dquot *gdqp = NULL; + struct xfs_dquot *pdqp = NULL; uint resblks; *ipp = NULL; @@ -386,7 +387,7 @@ xfs_symlink( * Make sure that we have allocated dquot(s) on disk. */ error = xfs_qm_vop_dqalloc(dp, current_fsuid(), current_fsgid(), prid, - XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT, &udqp, &gdqp); + XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT, &udqp, &gdqp, &pdqp); if (error) goto std_return; @@ -427,7 +428,8 @@ xfs_symlink( /* * Reserve disk quota : blocks and inode. */ - error = xfs_trans_reserve_quota(tp, mp, udqp, gdqp, resblks, 1, 0); + error = xfs_trans_reserve_quota(tp, mp, udqp, gdqp, + pdqp, resblks, 1, 0); if (error) goto error_return; @@ -465,7 +467,7 @@ xfs_symlink( /* * Also attach the dquot(s) to it, if applicable. */ - xfs_qm_vop_create_dqattach(tp, ip, udqp, gdqp); + xfs_qm_vop_create_dqattach(tp, ip, udqp, gdqp, pdqp); if (resblks) resblks -= XFS_IALLOC_SPACE_RES(mp); @@ -563,6 +565,7 @@ xfs_symlink( error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES); xfs_qm_dqrele(udqp); xfs_qm_dqrele(gdqp); + xfs_qm_dqrele(pdqp); *ipp = ip; return 0; @@ -576,6 +579,7 @@ xfs_symlink( xfs_trans_cancel(tp, cancel_flags); xfs_qm_dqrele(udqp); xfs_qm_dqrele(gdqp); + xfs_qm_dqrele(pdqp); if (unlock_dp_on_error) xfs_iunlock(dp, XFS_ILOCK_EXCL); diff --git a/fs/xfs/xfs_trans_dquot.c b/fs/xfs/xfs_trans_dquot.c index 3ba64d540168..61407a847b86 100644 --- a/fs/xfs/xfs_trans_dquot.c +++ b/fs/xfs/xfs_trans_dquot.c @@ -163,8 +163,10 @@ xfs_trans_mod_dquot_byino( if (XFS_IS_UQUOTA_ON(mp) && ip->i_udquot) (void) xfs_trans_mod_dquot(tp, ip->i_udquot, field, delta); - if (XFS_IS_OQUOTA_ON(mp) && ip->i_gdquot) + if (XFS_IS_GQUOTA_ON(mp) && ip->i_gdquot) (void) xfs_trans_mod_dquot(tp, ip->i_gdquot, field, delta); + if (XFS_IS_PQUOTA_ON(mp) && ip->i_pdquot) + (void) xfs_trans_mod_dquot(tp, ip->i_pdquot, field, delta); } STATIC struct xfs_dqtrx * @@ -177,8 +179,12 @@ xfs_trans_get_dqtrx( if (XFS_QM_ISUDQ(dqp)) qa = tp->t_dqinfo->dqs[XFS_QM_TRANS_USR]; - else + else if (XFS_QM_ISGDQ(dqp)) qa = tp->t_dqinfo->dqs[XFS_QM_TRANS_GRP]; + else if (XFS_QM_ISPDQ(dqp)) + qa = tp->t_dqinfo->dqs[XFS_QM_TRANS_PRJ]; + else + return NULL; for (i = 0; i < XFS_QM_TRANS_MAXDQS; i++) { if (qa[i].qt_dquot == NULL || @@ -291,11 +297,10 @@ xfs_trans_mod_dquot( /* - * Given an array of dqtrx structures, lock all the dquots associated - * and join them to the transaction, provided they have been modified. - * We know that the highest number of dquots (of one type - usr OR grp), - * involved in a transaction is 2 and that both usr and grp combined - 3. - * So, we don't attempt to make this very generic. + * Given an array of dqtrx structures, lock all the dquots associated and join + * them to the transaction, provided they have been modified. We know that the + * highest number of dquots of one type - usr, grp OR prj - involved in a + * transaction is 2 so we don't need to make this very generic. */ STATIC void xfs_trans_dqlockedjoin( @@ -728,8 +733,8 @@ error_return: /* * Given dquot(s), make disk block and/or inode reservations against them. - * The fact that this does the reservation against both the usr and - * grp/prj quotas is important, because this follows a both-or-nothing + * The fact that this does the reservation against user, group and + * project quotas is important, because this follows a all-or-nothing * approach. * * flags = XFS_QMOPT_FORCE_RES evades limit enforcement. Used by chown. @@ -744,6 +749,7 @@ xfs_trans_reserve_quota_bydquots( struct xfs_mount *mp, struct xfs_dquot *udqp, struct xfs_dquot *gdqp, + struct xfs_dquot *pdqp, long nblks, long ninos, uint flags) @@ -771,11 +777,21 @@ xfs_trans_reserve_quota_bydquots( goto unwind_usr; } + if (pdqp) { + error = xfs_trans_dqresv(tp, mp, pdqp, nblks, ninos, flags); + if (error) + goto unwind_grp; + } + /* * Didn't change anything critical, so, no need to log */ return 0; +unwind_grp: + flags |= XFS_QMOPT_FORCE_RES; + if (gdqp) + xfs_trans_dqresv(tp, mp, gdqp, -nblks, -ninos, flags); unwind_usr: flags |= XFS_QMOPT_FORCE_RES; if (udqp) @@ -817,6 +833,7 @@ xfs_trans_reserve_quota_nblks( */ return xfs_trans_reserve_quota_bydquots(tp, mp, ip->i_udquot, ip->i_gdquot, + ip->i_pdquot, nblks, ninos, flags); } diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c index 42c0ef288aeb..dc730ac272be 100644 --- a/fs/xfs/xfs_vnodeops.c +++ b/fs/xfs/xfs_vnodeops.c @@ -489,6 +489,7 @@ xfs_create( prid_t prid; struct xfs_dquot *udqp = NULL; struct xfs_dquot *gdqp = NULL; + struct xfs_dquot *pdqp = NULL; uint resblks; uint log_res; uint log_count; @@ -507,7 +508,8 @@ xfs_create( * Make sure that we have allocated dquot(s) on disk. */ error = xfs_qm_vop_dqalloc(dp, current_fsuid(), current_fsgid(), prid, - XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT, &udqp, &gdqp); + XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT, + &udqp, &gdqp, &pdqp); if (error) return error; @@ -559,7 +561,8 @@ xfs_create( /* * Reserve disk quota and the inode. */ - error = xfs_trans_reserve_quota(tp, mp, udqp, gdqp, resblks, 1, 0); + error = xfs_trans_reserve_quota(tp, mp, udqp, gdqp, + pdqp, resblks, 1, 0); if (error) goto out_trans_cancel; @@ -623,7 +626,7 @@ xfs_create( * These ids of the inode couldn't have changed since the new * inode has been locked ever since it was created. */ - xfs_qm_vop_create_dqattach(tp, ip, udqp, gdqp); + xfs_qm_vop_create_dqattach(tp, ip, udqp, gdqp, pdqp); error = xfs_bmap_finish(&tp, &free_list, &committed); if (error) @@ -635,6 +638,7 @@ xfs_create( xfs_qm_dqrele(udqp); xfs_qm_dqrele(gdqp); + xfs_qm_dqrele(pdqp); *ipp = ip; return 0; @@ -656,6 +660,7 @@ xfs_create( xfs_qm_dqrele(udqp); xfs_qm_dqrele(gdqp); + xfs_qm_dqrele(pdqp); if (unlock_dp_on_error) xfs_iunlock(dp, XFS_ILOCK_EXCL); @@ -1568,7 +1573,7 @@ xfs_free_file_space( } xfs_ilock(ip, XFS_ILOCK_EXCL); error = xfs_trans_reserve_quota(tp, mp, - ip->i_udquot, ip->i_gdquot, + ip->i_udquot, ip->i_gdquot, ip->i_pdquot, resblks, 0, XFS_QMOPT_RES_REGBLKS); if (error) goto error1; |