diff options
Diffstat (limited to 'fs')
137 files changed, 3981 insertions, 2867 deletions
diff --git a/fs/block_dev.c b/fs/block_dev.c index 50e8c8582faa..b737451e2e9d 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -370,7 +370,7 @@ int blkdev_fsync(struct file *filp, int datasync) */ mutex_unlock(&bd_inode->i_mutex); - error = blkdev_issue_flush(bdev, GFP_KERNEL, NULL, BLKDEV_IFL_WAIT); + error = blkdev_issue_flush(bdev, GFP_KERNEL, NULL); if (error == -EOPNOTSUPP) error = 0; diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 64f10082f048..5e789f4a3ed0 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2063,7 +2063,7 @@ static void btrfs_end_buffer_write_sync(struct buffer_head *bh, int uptodate) if (uptodate) { set_buffer_uptodate(bh); } else { - if (!buffer_eopnotsupp(bh) && printk_ratelimit()) { + if (printk_ratelimit()) { printk(KERN_WARNING "lost page write due to " "I/O error on %s\n", bdevname(bh->b_bdev, b)); @@ -2200,21 +2200,10 @@ static int write_dev_supers(struct btrfs_device *device, bh->b_end_io = btrfs_end_buffer_write_sync; } - if (i == last_barrier && do_barriers && device->barriers) { - ret = submit_bh(WRITE_BARRIER, bh); - if (ret == -EOPNOTSUPP) { - printk("btrfs: disabling barriers on dev %s\n", - device->name); - set_buffer_uptodate(bh); - device->barriers = 0; - /* one reference for submit_bh */ - get_bh(bh); - lock_buffer(bh); - ret = submit_bh(WRITE_SYNC, bh); - } - } else { + if (i == last_barrier && do_barriers) + ret = submit_bh(WRITE_FLUSH_FUA, bh); + else ret = submit_bh(WRITE_SYNC, bh); - } if (ret) errors++; diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 32d094002a57..0b81ecdb101c 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -1695,8 +1695,7 @@ static int remove_extent_backref(struct btrfs_trans_handle *trans, static void btrfs_issue_discard(struct block_device *bdev, u64 start, u64 len) { - blkdev_issue_discard(bdev, start >> 9, len >> 9, GFP_KERNEL, - BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER); + blkdev_issue_discard(bdev, start >> 9, len >> 9, GFP_KERNEL, 0); } static int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr, diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index dd318ff280b2..e25e46a8b4e2 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -398,7 +398,6 @@ static noinline int device_list_add(const char *path, device->work.func = pending_bios_fn; memcpy(device->uuid, disk_super->dev_item.uuid, BTRFS_UUID_SIZE); - device->barriers = 1; spin_lock_init(&device->io_lock); device->name = kstrdup(path, GFP_NOFS); if (!device->name) { @@ -462,7 +461,6 @@ static struct btrfs_fs_devices *clone_fs_devices(struct btrfs_fs_devices *orig) device->devid = orig_dev->devid; device->work.func = pending_bios_fn; memcpy(device->uuid, orig_dev->uuid, sizeof(device->uuid)); - device->barriers = 1; spin_lock_init(&device->io_lock); INIT_LIST_HEAD(&device->dev_list); INIT_LIST_HEAD(&device->dev_alloc_list); @@ -1489,7 +1487,6 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path) trans = btrfs_start_transaction(root, 0); lock_chunks(root); - device->barriers = 1; device->writeable = 1; device->work.func = pending_bios_fn; generate_random_uuid(device->uuid); @@ -3084,7 +3081,6 @@ static struct btrfs_device *add_missing_dev(struct btrfs_root *root, return NULL; list_add(&device->dev_list, &fs_devices->devices); - device->barriers = 1; device->dev_root = root->fs_info->dev_root; device->devid = devid; device->work.func = pending_bios_fn; diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 31b0fabdd2ea..2b638b6e4eea 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -42,7 +42,6 @@ struct btrfs_device { int running_pending; u64 generation; - int barriers; int writeable; int in_fs_metadata; diff --git a/fs/buffer.c b/fs/buffer.c index 3e7dca279d1c..7f0b9b083f77 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -156,7 +156,7 @@ void end_buffer_write_sync(struct buffer_head *bh, int uptodate) if (uptodate) { set_buffer_uptodate(bh); } else { - if (!buffer_eopnotsupp(bh) && !quiet_error(bh)) { + if (!quiet_error(bh)) { buffer_io_error(bh); printk(KERN_WARNING "lost page write due to " "I/O error on %s\n", @@ -2891,7 +2891,6 @@ static void end_bio_bh_io_sync(struct bio *bio, int err) if (err == -EOPNOTSUPP) { set_bit(BIO_EOPNOTSUPP, &bio->bi_flags); - set_bit(BH_Eopnotsupp, &bh->b_state); } if (unlikely (test_bit(BIO_QUIET,&bio->bi_flags))) @@ -3031,10 +3030,6 @@ int __sync_dirty_buffer(struct buffer_head *bh, int rw) bh->b_end_io = end_buffer_write_sync; ret = submit_bh(rw, bh); wait_on_buffer(bh); - if (buffer_eopnotsupp(bh)) { - clear_buffer_eopnotsupp(bh); - ret = -EOPNOTSUPP; - } if (!ret && !buffer_uptodate(bh)) ret = -EIO; } else { diff --git a/fs/cifs/README b/fs/cifs/README index 7099a526f775..ee68d1036544 100644 --- a/fs/cifs/README +++ b/fs/cifs/README @@ -527,6 +527,11 @@ A partial list of the supported mount options follows: SFU does). In the future the bottom 9 bits of the mode also will be emulated using queries of the security descriptor (ACL). + mfsymlinks Enable support for Minshall+French symlinks + (see http://wiki.samba.org/index.php/UNIX_Extensions#Minshall.2BFrench_symlinks) + This option is ignored when specified together with the + 'sfu' option. Minshall+French symlinks are used even if + the server supports the CIFS Unix Extensions. sign Must use packet signing (helps avoid unwanted data modification by intermediate systems in the route). Note that signing does not work with lanman or plaintext authentication. diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c index eb1ba493489f..103ab8b605b0 100644 --- a/fs/cifs/cifs_debug.c +++ b/fs/cifs/cifs_debug.c @@ -148,7 +148,7 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v) seq_printf(m, "Servers:"); i = 0; - read_lock(&cifs_tcp_ses_lock); + spin_lock(&cifs_tcp_ses_lock); list_for_each(tmp1, &cifs_tcp_ses_list) { server = list_entry(tmp1, struct TCP_Server_Info, tcp_ses_list); @@ -230,7 +230,7 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v) spin_unlock(&GlobalMid_Lock); } } - read_unlock(&cifs_tcp_ses_lock); + spin_unlock(&cifs_tcp_ses_lock); seq_putc(m, '\n'); /* BB add code to dump additional info such as TCP session info now */ @@ -270,7 +270,7 @@ static ssize_t cifs_stats_proc_write(struct file *file, atomic_set(&totBufAllocCount, 0); atomic_set(&totSmBufAllocCount, 0); #endif /* CONFIG_CIFS_STATS2 */ - read_lock(&cifs_tcp_ses_lock); + spin_lock(&cifs_tcp_ses_lock); list_for_each(tmp1, &cifs_tcp_ses_list) { server = list_entry(tmp1, struct TCP_Server_Info, tcp_ses_list); @@ -303,7 +303,7 @@ static ssize_t cifs_stats_proc_write(struct file *file, } } } - read_unlock(&cifs_tcp_ses_lock); + spin_unlock(&cifs_tcp_ses_lock); } return count; @@ -343,7 +343,7 @@ static int cifs_stats_proc_show(struct seq_file *m, void *v) GlobalCurrentXid, GlobalMaxActiveXid); i = 0; - read_lock(&cifs_tcp_ses_lock); + spin_lock(&cifs_tcp_ses_lock); list_for_each(tmp1, &cifs_tcp_ses_list) { server = list_entry(tmp1, struct TCP_Server_Info, tcp_ses_list); @@ -397,7 +397,7 @@ static int cifs_stats_proc_show(struct seq_file *m, void *v) } } } - read_unlock(&cifs_tcp_ses_lock); + spin_unlock(&cifs_tcp_ses_lock); seq_putc(m, '\n'); return 0; diff --git a/fs/cifs/cifs_debug.h b/fs/cifs/cifs_debug.h index aa316891ac0c..8942b28cf807 100644 --- a/fs/cifs/cifs_debug.h +++ b/fs/cifs/cifs_debug.h @@ -34,7 +34,7 @@ void cifs_dump_mids(struct TCP_Server_Info *); extern int traceSMB; /* flag which enables the function below */ void dump_smb(struct smb_hdr *, int); #define CIFS_INFO 0x01 -#define CIFS_RC 0x02 +#define CIFS_RC 0x02 #define CIFS_TIMER 0x04 /* diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c index d6ced7aa23cf..c68a056f27fd 100644 --- a/fs/cifs/cifs_dfs_ref.c +++ b/fs/cifs/cifs_dfs_ref.c @@ -44,8 +44,7 @@ static void cifs_dfs_expire_automounts(struct work_struct *work) void cifs_dfs_release_automount_timer(void) { BUG_ON(!list_empty(&cifs_dfs_automount_list)); - cancel_delayed_work(&cifs_dfs_automount_task); - flush_scheduled_work(); + cancel_delayed_work_sync(&cifs_dfs_automount_task); } /** @@ -306,6 +305,7 @@ cifs_dfs_follow_mountpoint(struct dentry *dentry, struct nameidata *nd) int xid, i; int rc = 0; struct vfsmount *mnt = ERR_PTR(-ENOENT); + struct tcon_link *tlink; cFYI(1, "in %s", __func__); BUG_ON(IS_ROOT(dentry)); @@ -315,14 +315,6 @@ cifs_dfs_follow_mountpoint(struct dentry *dentry, struct nameidata *nd) dput(nd->path.dentry); nd->path.dentry = dget(dentry); - cifs_sb = CIFS_SB(dentry->d_inode->i_sb); - ses = cifs_sb->tcon->ses; - - if (!ses) { - rc = -EINVAL; - goto out_err; - } - /* * The MSDFS spec states that paths in DFS referral requests and * responses must be prefixed by a single '\' character instead of @@ -335,10 +327,20 @@ cifs_dfs_follow_mountpoint(struct dentry *dentry, struct nameidata *nd) goto out_err; } - rc = get_dfs_path(xid, ses , full_path + 1, cifs_sb->local_nls, + cifs_sb = CIFS_SB(dentry->d_inode->i_sb); + tlink = cifs_sb_tlink(cifs_sb); + if (IS_ERR(tlink)) { + rc = PTR_ERR(tlink); + goto out_err; + } + ses = tlink_tcon(tlink)->ses; + + rc = get_dfs_path(xid, ses, full_path + 1, cifs_sb->local_nls, &num_referrals, &referrals, cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR); + cifs_put_tlink(tlink); + for (i = 0; i < num_referrals; i++) { int len; dump_referral(referrals+i); diff --git a/fs/cifs/cifs_fs_sb.h b/fs/cifs/cifs_fs_sb.h index 9e771450c3b8..525ba59a4105 100644 --- a/fs/cifs/cifs_fs_sb.h +++ b/fs/cifs/cifs_fs_sb.h @@ -15,6 +15,8 @@ * the GNU Lesser General Public License for more details. * */ +#include <linux/radix-tree.h> + #ifndef _CIFS_FS_SB_H #define _CIFS_FS_SB_H @@ -36,23 +38,28 @@ #define CIFS_MOUNT_NOPOSIXBRL 0x2000 /* mandatory not posix byte range lock */ #define CIFS_MOUNT_NOSSYNC 0x4000 /* don't do slow SMBflush on every sync*/ #define CIFS_MOUNT_FSCACHE 0x8000 /* local caching enabled */ +#define CIFS_MOUNT_MF_SYMLINKS 0x10000 /* Minshall+French Symlinks enabled */ +#define CIFS_MOUNT_MULTIUSER 0x20000 /* multiuser mount */ struct cifs_sb_info { - struct cifsTconInfo *tcon; /* primary mount */ - struct list_head nested_tcon_q; + struct radix_tree_root tlink_tree; +#define CIFS_TLINK_MASTER_TAG 0 /* is "master" (mount) tcon */ + spinlock_t tlink_tree_lock; struct nls_table *local_nls; unsigned int rsize; unsigned int wsize; + atomic_t active; uid_t mnt_uid; gid_t mnt_gid; mode_t mnt_file_mode; mode_t mnt_dir_mode; - int mnt_cifs_flags; + unsigned int mnt_cifs_flags; int prepathlen; char *prepath; /* relative path under the share to mount to */ #ifdef CONFIG_CIFS_DFS_UPCALL char *mountdata; /* mount options received at mount time */ #endif struct backing_dev_info bdi; + struct delayed_work prune_tlinks; }; #endif /* _CIFS_FS_SB_H */ diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c index 85d7cf7ff2c8..c9b4792ae825 100644 --- a/fs/cifs/cifsacl.c +++ b/fs/cifs/cifsacl.c @@ -557,11 +557,16 @@ static struct cifs_ntsd *get_cifs_acl_by_fid(struct cifs_sb_info *cifs_sb, { struct cifs_ntsd *pntsd = NULL; int xid, rc; + struct tcon_link *tlink = cifs_sb_tlink(cifs_sb); + + if (IS_ERR(tlink)) + return NULL; xid = GetXid(); - rc = CIFSSMBGetCIFSACL(xid, cifs_sb->tcon, fid, &pntsd, pacllen); + rc = CIFSSMBGetCIFSACL(xid, tlink_tcon(tlink), fid, &pntsd, pacllen); FreeXid(xid); + cifs_put_tlink(tlink); cFYI(1, "GetCIFSACL rc = %d ACL len %d", rc, *pacllen); return pntsd; @@ -574,10 +579,16 @@ static struct cifs_ntsd *get_cifs_acl_by_path(struct cifs_sb_info *cifs_sb, int oplock = 0; int xid, rc; __u16 fid; + struct cifsTconInfo *tcon; + struct tcon_link *tlink = cifs_sb_tlink(cifs_sb); + + if (IS_ERR(tlink)) + return NULL; + tcon = tlink_tcon(tlink); xid = GetXid(); - rc = CIFSSMBOpen(xid, cifs_sb->tcon, path, FILE_OPEN, READ_CONTROL, 0, + rc = CIFSSMBOpen(xid, tcon, path, FILE_OPEN, READ_CONTROL, 0, &fid, &oplock, NULL, cifs_sb->local_nls, cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR); if (rc) { @@ -585,11 +596,12 @@ static struct cifs_ntsd *get_cifs_acl_by_path(struct cifs_sb_info *cifs_sb, goto out; } - rc = CIFSSMBGetCIFSACL(xid, cifs_sb->tcon, fid, &pntsd, pacllen); + rc = CIFSSMBGetCIFSACL(xid, tcon, fid, &pntsd, pacllen); cFYI(1, "GetCIFSACL rc = %d ACL len %d", rc, *pacllen); - CIFSSMBClose(xid, cifs_sb->tcon, fid); + CIFSSMBClose(xid, tcon, fid); out: + cifs_put_tlink(tlink); FreeXid(xid); return pntsd; } @@ -603,7 +615,7 @@ static struct cifs_ntsd *get_cifs_acl(struct cifs_sb_info *cifs_sb, struct cifsFileInfo *open_file = NULL; if (inode) - open_file = find_readable_file(CIFS_I(inode)); + open_file = find_readable_file(CIFS_I(inode), true); if (!open_file) return get_cifs_acl_by_path(cifs_sb, path, pacllen); @@ -616,10 +628,15 @@ static int set_cifs_acl_by_fid(struct cifs_sb_info *cifs_sb, __u16 fid, struct cifs_ntsd *pnntsd, u32 acllen) { int xid, rc; + struct tcon_link *tlink = cifs_sb_tlink(cifs_sb); + + if (IS_ERR(tlink)) + return PTR_ERR(tlink); xid = GetXid(); - rc = CIFSSMBSetCIFSACL(xid, cifs_sb->tcon, fid, pnntsd, acllen); + rc = CIFSSMBSetCIFSACL(xid, tlink_tcon(tlink), fid, pnntsd, acllen); FreeXid(xid); + cifs_put_tlink(tlink); cFYI(DBG2, "SetCIFSACL rc = %d", rc); return rc; @@ -631,10 +648,16 @@ static int set_cifs_acl_by_path(struct cifs_sb_info *cifs_sb, const char *path, int oplock = 0; int xid, rc; __u16 fid; + struct cifsTconInfo *tcon; + struct tcon_link *tlink = cifs_sb_tlink(cifs_sb); + if (IS_ERR(tlink)) + return PTR_ERR(tlink); + + tcon = tlink_tcon(tlink); xid = GetXid(); - rc = CIFSSMBOpen(xid, cifs_sb->tcon, path, FILE_OPEN, WRITE_DAC, 0, + rc = CIFSSMBOpen(xid, tcon, path, FILE_OPEN, WRITE_DAC, 0, &fid, &oplock, NULL, cifs_sb->local_nls, cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR); if (rc) { @@ -642,12 +665,13 @@ static int set_cifs_acl_by_path(struct cifs_sb_info *cifs_sb, const char *path, goto out; } - rc = CIFSSMBSetCIFSACL(xid, cifs_sb->tcon, fid, pnntsd, acllen); + rc = CIFSSMBSetCIFSACL(xid, tcon, fid, pnntsd, acllen); cFYI(DBG2, "SetCIFSACL rc = %d", rc); - CIFSSMBClose(xid, cifs_sb->tcon, fid); - out: + CIFSSMBClose(xid, tcon, fid); +out: FreeXid(xid); + cifs_put_tlink(tlink); return rc; } @@ -661,7 +685,7 @@ static int set_cifs_acl(struct cifs_ntsd *pnntsd, __u32 acllen, cFYI(DBG2, "set ACL for %s from mode 0x%x", path, inode->i_mode); - open_file = find_readable_file(CIFS_I(inode)); + open_file = find_readable_file(CIFS_I(inode), true); if (!open_file) return set_cifs_acl_by_path(cifs_sb, path, pnntsd, acllen); diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c index 35042d8f7338..7ac0056294cf 100644 --- a/fs/cifs/cifsencrypt.c +++ b/fs/cifs/cifsencrypt.c @@ -27,6 +27,7 @@ #include "md5.h" #include "cifs_unicode.h" #include "cifsproto.h" +#include "ntlmssp.h" #include <linux/ctype.h> #include <linux/random.h> @@ -42,7 +43,7 @@ extern void SMBencrypt(unsigned char *passwd, const unsigned char *c8, unsigned char *p24); static int cifs_calculate_signature(const struct smb_hdr *cifs_pdu, - const struct mac_key *key, char *signature) + const struct session_key *key, char *signature) { struct MD5Context context; @@ -78,7 +79,7 @@ int cifs_sign_smb(struct smb_hdr *cifs_pdu, struct TCP_Server_Info *server, server->sequence_number++; spin_unlock(&GlobalMid_Lock); - rc = cifs_calculate_signature(cifs_pdu, &server->mac_signing_key, + rc = cifs_calculate_signature(cifs_pdu, &server->session_key, smb_signature); if (rc) memset(cifs_pdu->Signature.SecuritySignature, 0, 8); @@ -89,7 +90,7 @@ int cifs_sign_smb(struct smb_hdr *cifs_pdu, struct TCP_Server_Info *server, } static int cifs_calc_signature2(const struct kvec *iov, int n_vec, - const struct mac_key *key, char *signature) + const struct session_key *key, char *signature) { struct MD5Context context; int i; @@ -145,7 +146,7 @@ int cifs_sign_smb2(struct kvec *iov, int n_vec, struct TCP_Server_Info *server, server->sequence_number++; spin_unlock(&GlobalMid_Lock); - rc = cifs_calc_signature2(iov, n_vec, &server->mac_signing_key, + rc = cifs_calc_signature2(iov, n_vec, &server->session_key, smb_signature); if (rc) memset(cifs_pdu->Signature.SecuritySignature, 0, 8); @@ -156,14 +157,14 @@ int cifs_sign_smb2(struct kvec *iov, int n_vec, struct TCP_Server_Info *server, } int cifs_verify_signature(struct smb_hdr *cifs_pdu, - const struct mac_key *mac_key, + const struct session_key *session_key, __u32 expected_sequence_number) { unsigned int rc; char server_response_sig[8]; char what_we_think_sig_should_be[20]; - if ((cifs_pdu == NULL) || (mac_key == NULL)) + if (cifs_pdu == NULL || session_key == NULL) return -EINVAL; if (cifs_pdu->Command == SMB_COM_NEGOTIATE) @@ -192,7 +193,7 @@ int cifs_verify_signature(struct smb_hdr *cifs_pdu, cpu_to_le32(expected_sequence_number); cifs_pdu->Signature.Sequence.Reserved = 0; - rc = cifs_calculate_signature(cifs_pdu, mac_key, + rc = cifs_calculate_signature(cifs_pdu, session_key, what_we_think_sig_should_be); if (rc) @@ -209,7 +210,7 @@ int cifs_verify_signature(struct smb_hdr *cifs_pdu, } /* We fill in key by putting in 40 byte array which was allocated by caller */ -int cifs_calculate_mac_key(struct mac_key *key, const char *rn, +int cifs_calculate_session_key(struct session_key *key, const char *rn, const char *password) { char temp_key[16]; @@ -262,6 +263,148 @@ void calc_lanman_hash(const char *password, const char *cryptkey, bool encrypt, } #endif /* CIFS_WEAK_PW_HASH */ +/* Build a proper attribute value/target info pairs blob. + * Fill in netbios and dns domain name and workstation name + * and client time (total five av pairs and + one end of fields indicator. + * Allocate domain name which gets freed when session struct is deallocated. + */ +static int +build_avpair_blob(struct cifsSesInfo *ses, const struct nls_table *nls_cp) +{ + unsigned int dlen; + unsigned int wlen; + unsigned int size = 6 * sizeof(struct ntlmssp2_name); + __le64 curtime; + char *defdmname = "WORKGROUP"; + unsigned char *blobptr; + struct ntlmssp2_name *attrptr; + + if (!ses->domainName) { + ses->domainName = kstrdup(defdmname, GFP_KERNEL); + if (!ses->domainName) + return -ENOMEM; + } + + dlen = strlen(ses->domainName); + wlen = strlen(ses->server->hostname); + + /* The length of this blob is a size which is + * six times the size of a structure which holds name/size + + * two times the unicode length of a domain name + + * two times the unicode length of a server name + + * size of a timestamp (which is 8 bytes). + */ + ses->tilen = size + 2 * (2 * dlen) + 2 * (2 * wlen) + 8; + ses->tiblob = kzalloc(ses->tilen, GFP_KERNEL); + if (!ses->tiblob) { + ses->tilen = 0; + cERROR(1, "Challenge target info allocation failure"); + return -ENOMEM; + } + + blobptr = ses->tiblob; + attrptr = (struct ntlmssp2_name *) blobptr; + + attrptr->type = cpu_to_le16(NTLMSSP_AV_NB_DOMAIN_NAME); + attrptr->length = cpu_to_le16(2 * dlen); + blobptr = (unsigned char *)attrptr + sizeof(struct ntlmssp2_name); + cifs_strtoUCS((__le16 *)blobptr, ses->domainName, dlen, nls_cp); + + blobptr += 2 * dlen; + attrptr = (struct ntlmssp2_name *) blobptr; + + attrptr->type = cpu_to_le16(NTLMSSP_AV_NB_COMPUTER_NAME); + attrptr->length = cpu_to_le16(2 * wlen); + blobptr = (unsigned char *)attrptr + sizeof(struct ntlmssp2_name); + cifs_strtoUCS((__le16 *)blobptr, ses->server->hostname, wlen, nls_cp); + + blobptr += 2 * wlen; + attrptr = (struct ntlmssp2_name *) blobptr; + + attrptr->type = cpu_to_le16(NTLMSSP_AV_DNS_DOMAIN_NAME); + attrptr->length = cpu_to_le16(2 * dlen); + blobptr = (unsigned char *)attrptr + sizeof(struct ntlmssp2_name); + cifs_strtoUCS((__le16 *)blobptr, ses->domainName, dlen, nls_cp); + + blobptr += 2 * dlen; + attrptr = (struct ntlmssp2_name *) blobptr; + + attrptr->type = cpu_to_le16(NTLMSSP_AV_DNS_COMPUTER_NAME); + attrptr->length = cpu_to_le16(2 * wlen); + blobptr = (unsigned char *)attrptr + sizeof(struct ntlmssp2_name); + cifs_strtoUCS((__le16 *)blobptr, ses->server->hostname, wlen, nls_cp); + + blobptr += 2 * wlen; + attrptr = (struct ntlmssp2_name *) blobptr; + + attrptr->type = cpu_to_le16(NTLMSSP_AV_TIMESTAMP); + attrptr->length = cpu_to_le16(sizeof(__le64)); + blobptr = (unsigned char *)attrptr + sizeof(struct ntlmssp2_name); + curtime = cpu_to_le64(cifs_UnixTimeToNT(CURRENT_TIME)); + memcpy(blobptr, &curtime, sizeof(__le64)); + + return 0; +} + +/* Server has provided av pairs/target info in the type 2 challenge + * packet and we have plucked it and stored within smb session. + * We parse that blob here to find netbios domain name to be used + * as part of ntlmv2 authentication (in Target String), if not already + * specified on the command line. + * If this function returns without any error but without fetching + * domain name, authentication may fail against some server but + * may not fail against other (those who are not very particular + * about target string i.e. for some, just user name might suffice. + */ +static int +find_domain_name(struct cifsSesInfo *ses) +{ + unsigned int attrsize; + unsigned int type; + unsigned int onesize = sizeof(struct ntlmssp2_name); + unsigned char *blobptr; + unsigned char *blobend; + struct ntlmssp2_name *attrptr; + + if (!ses->tilen || !ses->tiblob) + return 0; + + blobptr = ses->tiblob; + blobend = ses->tiblob + ses->tilen; + + while (blobptr + onesize < blobend) { + attrptr = (struct ntlmssp2_name *) blobptr; + type = le16_to_cpu(attrptr->type); + if (type == NTLMSSP_AV_EOL) + break; + blobptr += 2; /* advance attr type */ + attrsize = le16_to_cpu(attrptr->length); + blobptr += 2; /* advance attr size */ + if (blobptr + attrsize > blobend) + break; + if (type == NTLMSSP_AV_NB_DOMAIN_NAME) { + if (!attrsize) + break; + if (!ses->domainName) { + struct nls_table *default_nls; + ses->domainName = + kmalloc(attrsize + 1, GFP_KERNEL); + if (!ses->domainName) + return -ENOMEM; + default_nls = load_nls_default(); + cifs_from_ucs2(ses->domainName, + (__le16 *)blobptr, attrsize, attrsize, + default_nls, false); + unload_nls(default_nls); + break; + } + } + blobptr += attrsize; /* advance attr value */ + } + + return 0; +} + static int calc_ntlmv2_hash(struct cifsSesInfo *ses, const struct nls_table *nls_cp) { @@ -315,13 +458,14 @@ calc_exit_1: calc_exit_2: /* BB FIXME what about bytes 24 through 40 of the signing key? compare with the NTLM example */ - hmac_md5_final(ses->server->ntlmv2_hash, pctxt); + hmac_md5_final(ses->ntlmv2_hash, pctxt); kfree(pctxt); return rc; } -void setup_ntlmv2_rsp(struct cifsSesInfo *ses, char *resp_buf, +int +setup_ntlmv2_rsp(struct cifsSesInfo *ses, char *resp_buf, const struct nls_table *nls_cp) { int rc; @@ -333,25 +477,48 @@ void setup_ntlmv2_rsp(struct cifsSesInfo *ses, char *resp_buf, buf->time = cpu_to_le64(cifs_UnixTimeToNT(CURRENT_TIME)); get_random_bytes(&buf->client_chal, sizeof(buf->client_chal)); buf->reserved2 = 0; - buf->names[0].type = cpu_to_le16(NTLMSSP_DOMAIN_TYPE); - buf->names[0].length = 0; - buf->names[1].type = 0; - buf->names[1].length = 0; + + if (ses->server->secType == RawNTLMSSP) { + if (!ses->domainName) { + rc = find_domain_name(ses); + if (rc) { + cERROR(1, "error %d finding domain name", rc); + goto setup_ntlmv2_rsp_ret; + } + } + } else { + rc = build_avpair_blob(ses, nls_cp); + if (rc) { + cERROR(1, "error %d building av pair blob", rc); + return rc; + } + } /* calculate buf->ntlmv2_hash */ rc = calc_ntlmv2_hash(ses, nls_cp); - if (rc) + if (rc) { cERROR(1, "could not get v2 hash rc %d", rc); + goto setup_ntlmv2_rsp_ret; + } CalcNTLMv2_response(ses, resp_buf); - /* now calculate the MAC key for NTLMv2 */ - hmac_md5_init_limK_to_64(ses->server->ntlmv2_hash, 16, &context); + /* now calculate the session key for NTLMv2 */ + hmac_md5_init_limK_to_64(ses->ntlmv2_hash, 16, &context); hmac_md5_update(resp_buf, 16, &context); - hmac_md5_final(ses->server->mac_signing_key.data.ntlmv2.key, &context); + hmac_md5_final(ses->auth_key.data.ntlmv2.key, &context); - memcpy(&ses->server->mac_signing_key.data.ntlmv2.resp, resp_buf, + memcpy(&ses->auth_key.data.ntlmv2.resp, resp_buf, sizeof(struct ntlmv2_resp)); - ses->server->mac_signing_key.len = 16 + sizeof(struct ntlmv2_resp); + ses->auth_key.len = 16 + sizeof(struct ntlmv2_resp); + + return 0; + +setup_ntlmv2_rsp_ret: + kfree(ses->tiblob); + ses->tiblob = NULL; + ses->tilen = 0; + + return rc; } void CalcNTLMv2_response(const struct cifsSesInfo *ses, @@ -359,12 +526,15 @@ void CalcNTLMv2_response(const struct cifsSesInfo *ses, { struct HMACMD5Context context; /* rest of v2 struct already generated */ - memcpy(v2_session_response + 8, ses->server->cryptKey, 8); - hmac_md5_init_limK_to_64(ses->server->ntlmv2_hash, 16, &context); + memcpy(v2_session_response + 8, ses->cryptKey, 8); + hmac_md5_init_limK_to_64(ses->ntlmv2_hash, 16, &context); hmac_md5_update(v2_session_response+8, sizeof(struct ntlmv2_resp) - 8, &context); + if (ses->tilen) + hmac_md5_update(ses->tiblob, ses->tilen, &context); + hmac_md5_final(v2_session_response, &context); /* cifs_dump_mem("v2_sess_rsp: ", v2_session_response, 32); */ } diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 50208c15309a..34371637f210 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -35,6 +35,7 @@ #include <linux/delay.h> #include <linux/kthread.h> #include <linux/freezer.h> +#include <net/ipv6.h> #include "cifsfs.h" #include "cifspdu.h" #define DECLARE_GLOBALS_HERE @@ -81,6 +82,24 @@ extern mempool_t *cifs_sm_req_poolp; extern mempool_t *cifs_req_poolp; extern mempool_t *cifs_mid_poolp; +void +cifs_sb_active(struct super_block *sb) +{ + struct cifs_sb_info *server = CIFS_SB(sb); + + if (atomic_inc_return(&server->active) == 1) + atomic_inc(&sb->s_active); +} + +void +cifs_sb_deactive(struct super_block *sb) +{ + struct cifs_sb_info *server = CIFS_SB(sb); + + if (atomic_dec_and_test(&server->active)) + deactivate_super(sb); +} + static int cifs_read_super(struct super_block *sb, void *data, const char *devname, int silent) @@ -96,6 +115,9 @@ cifs_read_super(struct super_block *sb, void *data, if (cifs_sb == NULL) return -ENOMEM; + spin_lock_init(&cifs_sb->tlink_tree_lock); + INIT_RADIX_TREE(&cifs_sb->tlink_tree, GFP_KERNEL); + rc = bdi_setup_and_register(&cifs_sb->bdi, "cifs", BDI_CAP_MAP_COPY); if (rc) { kfree(cifs_sb); @@ -135,9 +157,6 @@ cifs_read_super(struct super_block *sb, void *data, sb->s_magic = CIFS_MAGIC_NUMBER; sb->s_op = &cifs_super_ops; sb->s_bdi = &cifs_sb->bdi; -/* if (cifs_sb->tcon->ses->server->maxBuf > MAX_CIFS_HDR_SIZE + 512) - sb->s_blocksize = - cifs_sb->tcon->ses->server->maxBuf - MAX_CIFS_HDR_SIZE; */ sb->s_blocksize = CIFS_MAX_MSGSIZE; sb->s_blocksize_bits = 14; /* default 2**14 = CIFS_MAX_MSGSIZE */ inode = cifs_root_iget(sb, ROOT_I); @@ -219,7 +238,7 @@ cifs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; struct cifs_sb_info *cifs_sb = CIFS_SB(sb); - struct cifsTconInfo *tcon = cifs_sb->tcon; + struct cifsTconInfo *tcon = cifs_sb_master_tcon(cifs_sb); int rc = -EOPNOTSUPP; int xid; @@ -361,14 +380,36 @@ static int cifs_show_options(struct seq_file *s, struct vfsmount *m) { struct cifs_sb_info *cifs_sb = CIFS_SB(m->mnt_sb); - struct cifsTconInfo *tcon = cifs_sb->tcon; + struct cifsTconInfo *tcon = cifs_sb_master_tcon(cifs_sb); + struct sockaddr *srcaddr; + srcaddr = (struct sockaddr *)&tcon->ses->server->srcaddr; seq_printf(s, ",unc=%s", tcon->treeName); - if (tcon->ses->userName) + + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER) + seq_printf(s, ",multiuser"); + else if (tcon->ses->userName) seq_printf(s, ",username=%s", tcon->ses->userName); + if (tcon->ses->domainName) seq_printf(s, ",domain=%s", tcon->ses->domainName); + if (srcaddr->sa_family != AF_UNSPEC) { + struct sockaddr_in *saddr4; + struct sockaddr_in6 *saddr6; + saddr4 = (struct sockaddr_in *)srcaddr; + saddr6 = (struct sockaddr_in6 *)srcaddr; + if (srcaddr->sa_family == AF_INET6) + seq_printf(s, ",srcaddr=%pI6c", + &saddr6->sin6_addr); + else if (srcaddr->sa_family == AF_INET) + seq_printf(s, ",srcaddr=%pI4", + &saddr4->sin_addr.s_addr); + else + seq_printf(s, ",srcaddr=BAD-AF:%i", + (int)(srcaddr->sa_family)); + } + seq_printf(s, ",uid=%d", cifs_sb->mnt_uid); if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_UID) seq_printf(s, ",forceuid"); @@ -417,6 +458,8 @@ cifs_show_options(struct seq_file *s, struct vfsmount *m) seq_printf(s, ",dynperm"); if (m->mnt_sb->s_flags & MS_POSIXACL) seq_printf(s, ",acl"); + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) + seq_printf(s, ",mfsymlinks"); seq_printf(s, ",rsize=%d", cifs_sb->rsize); seq_printf(s, ",wsize=%d", cifs_sb->wsize); @@ -432,20 +475,18 @@ static void cifs_umount_begin(struct super_block *sb) if (cifs_sb == NULL) return; - tcon = cifs_sb->tcon; - if (tcon == NULL) - return; + tcon = cifs_sb_master_tcon(cifs_sb); - read_lock(&cifs_tcp_ses_lock); + spin_lock(&cifs_tcp_ses_lock); if ((tcon->tc_count > 1) || (tcon->tidStatus == CifsExiting)) { /* we have other mounts to same share or we have already tried to force umount this and woken up all waiting network requests, nothing to do */ - read_unlock(&cifs_tcp_ses_lock); + spin_unlock(&cifs_tcp_ses_lock); return; } else if (tcon->tc_count == 1) tcon->tidStatus = CifsExiting; - read_unlock(&cifs_tcp_ses_lock); + spin_unlock(&cifs_tcp_ses_lock); /* cancel_brl_requests(tcon); */ /* BB mark all brl mids as exiting */ /* cancel_notify_requests(tcon); */ @@ -565,6 +606,7 @@ static int cifs_setlease(struct file *file, long arg, struct file_lock **lease) /* note that this is called by vfs setlease with lock_flocks held to protect *lease from going away */ struct inode *inode = file->f_path.dentry->d_inode; + struct cifsFileInfo *cfile = file->private_data; if (!(S_ISREG(inode->i_mode))) return -EINVAL; @@ -575,8 +617,8 @@ static int cifs_setlease(struct file *file, long arg, struct file_lock **lease) ((arg == F_WRLCK) && (CIFS_I(inode)->clientCanCacheAll))) return generic_setlease(file, arg, lease); - else if (CIFS_SB(inode->i_sb)->tcon->local_lease && - !CIFS_I(inode)->clientCanCacheRead) + else if (tlink_tcon(cfile->tlink)->local_lease && + !CIFS_I(inode)->clientCanCacheRead) /* If the server claims to support oplock on this file, then we still need to check oplock even if the local_lease mount option is set, but there @@ -895,8 +937,8 @@ init_cifs(void) GlobalTotalActiveXid = 0; GlobalMaxActiveXid = 0; memset(Local_System_Name, 0, 15); - rwlock_init(&GlobalSMBSeslock); - rwlock_init(&cifs_tcp_ses_lock); + spin_lock_init(&cifs_tcp_ses_lock); + spin_lock_init(&cifs_file_list_lock); spin_lock_init(&GlobalMid_Lock); if (cifs_max_pending < 2) { @@ -909,11 +951,11 @@ init_cifs(void) rc = cifs_fscache_register(); if (rc) - goto out; + goto out_clean_proc; rc = cifs_init_inodecache(); if (rc) - goto out_clean_proc; + goto out_unreg_fscache; rc = cifs_init_mids(); if (rc) @@ -935,19 +977,19 @@ init_cifs(void) return 0; #ifdef CONFIG_CIFS_UPCALL - out_unregister_filesystem: +out_unregister_filesystem: unregister_filesystem(&cifs_fs_type); #endif - out_destroy_request_bufs: +out_destroy_request_bufs: cifs_destroy_request_bufs(); - out_destroy_mids: +out_destroy_mids: cifs_destroy_mids(); - out_destroy_inodecache: +out_destroy_inodecache: cifs_destroy_inodecache(); - out_clean_proc: - cifs_proc_clean(); +out_unreg_fscache: cifs_fscache_unregister(); - out: +out_clean_proc: + cifs_proc_clean(); return rc; } diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index d82f5fb4761e..f35795a16b42 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -42,10 +42,8 @@ extern const struct address_space_operations cifs_addr_ops; extern const struct address_space_operations cifs_addr_ops_smallbuf; /* Functions related to super block operations */ -/* extern const struct super_operations cifs_super_ops;*/ -extern void cifs_read_inode(struct inode *); -/*extern void cifs_delete_inode(struct inode *);*/ /* BB not needed yet */ -/* extern void cifs_write_inode(struct inode *); */ /* BB not needed yet */ +extern void cifs_sb_active(struct super_block *sb); +extern void cifs_sb_deactive(struct super_block *sb); /* Functions related to inodes */ extern const struct inode_operations cifs_dir_inode_ops; @@ -104,7 +102,7 @@ extern int cifs_readlink(struct dentry *direntry, char __user *buffer, extern int cifs_symlink(struct inode *inode, struct dentry *direntry, const char *symname); extern int cifs_removexattr(struct dentry *, const char *); -extern int cifs_setxattr(struct dentry *, const char *, const void *, +extern int cifs_setxattr(struct dentry *, const char *, const void *, size_t, int); extern ssize_t cifs_getxattr(struct dentry *, const char *, void *, size_t); extern ssize_t cifs_listxattr(struct dentry *, char *, size_t); @@ -114,5 +112,5 @@ extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg); extern const struct export_operations cifs_export_ops; #endif /* EXPERIMENTAL */ -#define CIFS_VERSION "1.65" +#define CIFS_VERSION "1.67" #endif /* _CIFSFS_H */ diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 0cdfb8c32ac6..3365e77f6f24 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -97,7 +97,7 @@ enum protocolEnum { /* Netbios frames protocol not supported at this time */ }; -struct mac_key { +struct session_key { unsigned int len; union { char ntlm[CIFS_SESS_KEY_SIZE + 16]; @@ -139,6 +139,7 @@ struct TCP_Server_Info { struct sockaddr_in sockAddr; struct sockaddr_in6 sockAddr6; } addr; + struct sockaddr_storage srcaddr; /* locally bind to this IP */ wait_queue_head_t response_q; wait_queue_head_t request_q; /* if more than maxmpx to srvr must block*/ struct list_head pending_mid_q; @@ -178,12 +179,10 @@ struct TCP_Server_Info { int capabilities; /* allow selective disabling of caps by smb sess */ int timeAdj; /* Adjust for difference in server time zone in sec */ __u16 CurrentMid; /* multiplex id - rotating counter */ - char cryptKey[CIFS_CRYPTO_KEY_SIZE]; /* 16th byte of RFC1001 workstation name is always null */ char workstation_RFC1001_name[RFC1001_NAME_LEN_WITH_NULL]; __u32 sequence_number; /* needed for CIFS PDU signature */ - struct mac_key mac_signing_key; - char ntlmv2_hash[16]; + struct session_key session_key; unsigned long lstrp; /* when we got last response from this server */ u16 dialect; /* dialect index that server chose */ /* extended security flavors that server supports */ @@ -191,6 +190,7 @@ struct TCP_Server_Info { bool sec_mskerberos; /* supports legacy MS Kerberos */ bool sec_kerberosu2u; /* supports U2U Kerberos */ bool sec_ntlmssp; /* supports NTLMSSP */ + bool session_estab; /* mark when very first sess is established */ #ifdef CONFIG_CIFS_FSCACHE struct fscache_cookie *fscache; /* client index cache cookie */ #endif @@ -222,6 +222,11 @@ struct cifsSesInfo { char userName[MAX_USERNAME_SIZE + 1]; char *domainName; char *password; + char cryptKey[CIFS_CRYPTO_KEY_SIZE]; + struct session_key auth_key; + char ntlmv2_hash[16]; + unsigned int tilen; /* length of the target info blob */ + unsigned char *tiblob; /* target info blob in challenge response */ bool need_reconnect:1; /* connection reset, uid now invalid */ }; /* no more than one of the following three session flags may be set */ @@ -308,6 +313,44 @@ struct cifsTconInfo { }; /* + * This is a refcounted and timestamped container for a tcon pointer. The + * container holds a tcon reference. It is considered safe to free one of + * these when the tl_count goes to 0. The tl_time is the time of the last + * "get" on the container. + */ +struct tcon_link { + unsigned long tl_index; + unsigned long tl_flags; +#define TCON_LINK_MASTER 0 +#define TCON_LINK_PENDING 1 +#define TCON_LINK_IN_TREE 2 + unsigned long tl_time; + atomic_t tl_count; + struct cifsTconInfo *tl_tcon; +}; + +extern struct tcon_link *cifs_sb_tlink(struct cifs_sb_info *cifs_sb); + +static inline struct cifsTconInfo * +tlink_tcon(struct tcon_link *tlink) +{ + return tlink->tl_tcon; +} + +extern void cifs_put_tlink(struct tcon_link *tlink); + +static inline struct tcon_link * +cifs_get_tlink(struct tcon_link *tlink) +{ + if (tlink && !IS_ERR(tlink)) + atomic_inc(&tlink->tl_count); + return tlink; +} + +/* This function is always expected to succeed */ +extern struct cifsTconInfo *cifs_sb_master_tcon(struct cifs_sb_info *cifs_sb); + +/* * This info hangs off the cifsFileInfo structure, pointed to by llist. * This is used to track byte stream locks on the file */ @@ -345,12 +388,11 @@ struct cifsFileInfo { __u16 netfid; /* file id from remote */ /* BB add lock scope info here if needed */ ; /* lock scope id (0 if none) */ - struct file *pfile; /* needed for writepage */ - struct inode *pInode; /* needed for oplock break */ - struct vfsmount *mnt; + struct dentry *dentry; + unsigned int f_flags; + struct tcon_link *tlink; struct mutex lock_mutex; struct list_head llist; /* list of byte range locks we have. */ - bool closePend:1; /* file is marked to close */ bool invalidHandle:1; /* file closed via session abend */ bool oplock_break_cancelled:1; atomic_t count; /* reference count */ @@ -365,14 +407,7 @@ static inline void cifsFileInfo_get(struct cifsFileInfo *cifs_file) atomic_inc(&cifs_file->count); } -/* Release a reference on the file private data */ -static inline void cifsFileInfo_put(struct cifsFileInfo *cifs_file) -{ - if (atomic_dec_and_test(&cifs_file->count)) { - iput(cifs_file->pInode); - kfree(cifs_file); - } -} +void cifsFileInfo_put(struct cifsFileInfo *cifs_file); /* * One of these for each file inode @@ -474,16 +509,16 @@ struct oplock_q_entry { /* for pending dnotify requests */ struct dir_notify_req { - struct list_head lhead; - __le16 Pid; - __le16 PidHigh; - __u16 Mid; - __u16 Tid; - __u16 Uid; - __u16 netfid; - __u32 filter; /* CompletionFilter (for multishot) */ - int multishot; - struct file *pfile; + struct list_head lhead; + __le16 Pid; + __le16 PidHigh; + __u16 Mid; + __u16 Tid; + __u16 Uid; + __u16 netfid; + __u32 filter; /* CompletionFilter (for multishot) */ + int multishot; + struct file *pfile; }; struct dfs_info3_param { @@ -667,7 +702,7 @@ GLOBAL_EXTERN struct list_head cifs_tcp_ses_list; * the reference counters for the server, smb session, and tcon. Finally, * changes to the tcon->tidStatus should be done while holding this lock. */ -GLOBAL_EXTERN rwlock_t cifs_tcp_ses_lock; +GLOBAL_EXTERN spinlock_t cifs_tcp_ses_lock; /* * This lock protects the cifs_file->llist and cifs_file->flist @@ -676,7 +711,7 @@ GLOBAL_EXTERN rwlock_t cifs_tcp_ses_lock; * If cifs_tcp_ses_lock and the lock below are both needed to be held, then * the cifs_tcp_ses_lock must be grabbed first and released last. */ -GLOBAL_EXTERN rwlock_t GlobalSMBSeslock; +GLOBAL_EXTERN spinlock_t cifs_file_list_lock; /* Outstanding dir notify requests */ GLOBAL_EXTERN struct list_head GlobalDnotifyReqList; diff --git a/fs/cifs/cifspdu.h b/fs/cifs/cifspdu.h index 14d036d8db11..b0f4b5656d4c 100644 --- a/fs/cifs/cifspdu.h +++ b/fs/cifs/cifspdu.h @@ -663,7 +663,6 @@ struct ntlmv2_resp { __le64 time; __u64 client_chal; /* random */ __u32 reserved2; - struct ntlmssp2_name names[2]; /* array of name entries could follow ending in minimum 4 byte struct */ } __attribute__((packed)); diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index 1d60c655e3e0..e593c40ba7ba 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -78,9 +78,9 @@ extern int checkSMB(struct smb_hdr *smb, __u16 mid, unsigned int length); extern bool is_valid_oplock_break(struct smb_hdr *smb, struct TCP_Server_Info *); extern bool is_size_safe_to_change(struct cifsInodeInfo *, __u64 eof); -extern struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *); +extern struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *, bool); #ifdef CONFIG_CIFS_EXPERIMENTAL -extern struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *); +extern struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *, bool); #endif extern unsigned int smbCalcSize(struct smb_hdr *ptr); extern unsigned int smbCalcSize_LE(struct smb_hdr *ptr); @@ -105,12 +105,12 @@ extern u64 cifs_UnixTimeToNT(struct timespec); extern struct timespec cnvrtDosUnixTm(__le16 le_date, __le16 le_time, int offset); -extern struct cifsFileInfo *cifs_new_fileinfo(struct inode *newinode, - __u16 fileHandle, struct file *file, - struct vfsmount *mnt, unsigned int oflags); +extern struct cifsFileInfo *cifs_new_fileinfo(__u16 fileHandle, + struct file *file, struct tcon_link *tlink, + __u32 oplock); extern int cifs_posix_open(char *full_path, struct inode **pinode, struct super_block *sb, - int mode, int oflags, + int mode, unsigned int f_flags, __u32 *poplock, __u16 *pnetfid, int xid); void cifs_fill_uniqueid(struct super_block *sb, struct cifs_fattr *fattr); extern void cifs_unix_basic_to_fattr(struct cifs_fattr *fattr, @@ -362,12 +362,12 @@ extern int cifs_sign_smb(struct smb_hdr *, struct TCP_Server_Info *, __u32 *); extern int cifs_sign_smb2(struct kvec *iov, int n_vec, struct TCP_Server_Info *, __u32 *); extern int cifs_verify_signature(struct smb_hdr *, - const struct mac_key *mac_key, + const struct session_key *session_key, __u32 expected_sequence_number); -extern int cifs_calculate_mac_key(struct mac_key *key, const char *rn, +extern int cifs_calculate_session_key(struct session_key *key, const char *rn, const char *pass); extern void CalcNTLMv2_response(const struct cifsSesInfo *, char *); -extern void setup_ntlmv2_rsp(struct cifsSesInfo *, char *, +extern int setup_ntlmv2_rsp(struct cifsSesInfo *, char *, const struct nls_table *); #ifdef CONFIG_CIFS_WEAK_PW_HASH extern void calc_lanman_hash(const char *password, const char *cryptkey, @@ -408,4 +408,8 @@ extern int CIFSSMBSetPosixACL(const int xid, struct cifsTconInfo *tcon, extern int CIFSGetExtAttr(const int xid, struct cifsTconInfo *tcon, const int netfid, __u64 *pExtAttrBits, __u64 *pMask); extern void cifs_autodisable_serverino(struct cifs_sb_info *cifs_sb); +extern bool CIFSCouldBeMFSymlink(const struct cifs_fattr *fattr); +extern int CIFSCheckMFSymlink(struct cifs_fattr *fattr, + const unsigned char *path, + struct cifs_sb_info *cifs_sb, int xid); #endif /* _CIFSPROTO_H */ diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 7e83b356cc9e..e98f1f317b15 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -91,13 +91,13 @@ static void mark_open_files_invalid(struct cifsTconInfo *pTcon) struct list_head *tmp1; /* list all files open on tree connection and mark them invalid */ - write_lock(&GlobalSMBSeslock); + spin_lock(&cifs_file_list_lock); list_for_each_safe(tmp, tmp1, &pTcon->openFileList) { open_file = list_entry(tmp, struct cifsFileInfo, tlist); open_file->invalidHandle = true; open_file->oplock_break_cancelled = true; } - write_unlock(&GlobalSMBSeslock); + spin_unlock(&cifs_file_list_lock); /* BB Add call to invalidate_inodes(sb) for all superblocks mounted to this tcon */ } @@ -503,7 +503,7 @@ CIFSSMBNegotiate(unsigned int xid, struct cifsSesInfo *ses) if (rsp->EncryptionKeyLength == cpu_to_le16(CIFS_CRYPTO_KEY_SIZE)) { - memcpy(server->cryptKey, rsp->EncryptionKey, + memcpy(ses->cryptKey, rsp->EncryptionKey, CIFS_CRYPTO_KEY_SIZE); } else if (server->secMode & SECMODE_PW_ENCRYPT) { rc = -EIO; /* need cryptkey unless plain text */ @@ -574,7 +574,7 @@ CIFSSMBNegotiate(unsigned int xid, struct cifsSesInfo *ses) server->timeAdj = (int)(__s16)le16_to_cpu(pSMBr->ServerTimeZone); server->timeAdj *= 60; if (pSMBr->EncryptionKeyLength == CIFS_CRYPTO_KEY_SIZE) { - memcpy(server->cryptKey, pSMBr->u.EncryptionKey, + memcpy(ses->cryptKey, pSMBr->u.EncryptionKey, CIFS_CRYPTO_KEY_SIZE); } else if ((pSMBr->hdr.Flags2 & SMBFLG2_EXT_SEC) && (pSMBr->EncryptionKeyLength == 0)) { @@ -593,9 +593,9 @@ CIFSSMBNegotiate(unsigned int xid, struct cifsSesInfo *ses) rc = -EIO; goto neg_err_exit; } - read_lock(&cifs_tcp_ses_lock); + spin_lock(&cifs_tcp_ses_lock); if (server->srv_count > 1) { - read_unlock(&cifs_tcp_ses_lock); + spin_unlock(&cifs_tcp_ses_lock); if (memcmp(server->server_GUID, pSMBr->u.extended_response. GUID, 16) != 0) { @@ -605,7 +605,7 @@ CIFSSMBNegotiate(unsigned int xid, struct cifsSesInfo *ses) 16); } } else { - read_unlock(&cifs_tcp_ses_lock); + spin_unlock(&cifs_tcp_ses_lock); memcpy(server->server_GUID, pSMBr->u.extended_response.GUID, 16); } @@ -620,13 +620,15 @@ CIFSSMBNegotiate(unsigned int xid, struct cifsSesInfo *ses) rc = 0; else rc = -EINVAL; - - if (server->sec_kerberos || server->sec_mskerberos) - server->secType = Kerberos; - else if (server->sec_ntlmssp) - server->secType = RawNTLMSSP; - else - rc = -EOPNOTSUPP; + if (server->secType == Kerberos) { + if (!server->sec_kerberos && + !server->sec_mskerberos) + rc = -EOPNOTSUPP; + } else if (server->secType == RawNTLMSSP) { + if (!server->sec_ntlmssp) + rc = -EOPNOTSUPP; + } else + rc = -EOPNOTSUPP; } } else server->capabilities &= ~CAP_EXTENDED_SECURITY; diff --git a/fs/cifs/cn_cifs.h b/fs/cifs/cn_cifs.h deleted file mode 100644 index ea59ccac2eb1..000000000000 --- a/fs/cifs/cn_cifs.h +++ /dev/null @@ -1,37 +0,0 @@ -/* - * fs/cifs/cn_cifs.h - * - * Copyright (c) International Business Machines Corp., 2002 - * Author(s): Steve French (sfrench@us.ibm.com) - * - * This library is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as published - * by the Free Software Foundation; either version 2.1 of the License, or - * (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ - -#ifndef _CN_CIFS_H -#define _CN_CIFS_H -#ifdef CONFIG_CIFS_UPCALL -#include <linux/types.h> -#include <linux/connector.h> - -struct cifs_upcall { - char signature[4]; /* CIFS */ - enum command { - CIFS_GET_IP = 0x00000001, /* get ip address for hostname */ - CIFS_GET_SECBLOB = 0x00000002, /* get SPNEGO wrapped blob */ - } command; - /* union cifs upcall data follows */ -}; -#endif /* CIFS_UPCALL */ -#endif /* _CN_CIFS_H */ diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 88c84a38bccb..7e73176acb58 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -47,7 +47,6 @@ #include "ntlmssp.h" #include "nterr.h" #include "rfc1002pdu.h" -#include "cn_cifs.h" #include "fscache.h" #define CIFS_PORT 445 @@ -100,16 +99,24 @@ struct smb_vol { bool noautotune:1; bool nostrictsync:1; /* do not force expensive SMBflush on every sync */ bool fsc:1; /* enable fscache */ + bool mfsymlinks:1; /* use Minshall+French Symlinks */ + bool multiuser:1; unsigned int rsize; unsigned int wsize; bool sockopt_tcp_nodelay:1; unsigned short int port; char *prepath; + struct sockaddr_storage srcaddr; /* allow binding to a local IP */ struct nls_table *local_nls; }; +/* FIXME: should these be tunable? */ +#define TLINK_ERROR_EXPIRE (1 * HZ) +#define TLINK_IDLE_EXPIRE (600 * HZ) + static int ipv4_connect(struct TCP_Server_Info *server); static int ipv6_connect(struct TCP_Server_Info *server); +static void cifs_prune_tlinks(struct work_struct *work); /* * cifs tcp session reconnection @@ -143,7 +150,7 @@ cifs_reconnect(struct TCP_Server_Info *server) /* before reconnecting the tcp session, mark the smb session (uid) and the tid bad so they are not used until reconnected */ - read_lock(&cifs_tcp_ses_lock); + spin_lock(&cifs_tcp_ses_lock); list_for_each(tmp, &server->smb_ses_list) { ses = list_entry(tmp, struct cifsSesInfo, smb_ses_list); ses->need_reconnect = true; @@ -153,7 +160,7 @@ cifs_reconnect(struct TCP_Server_Info *server) tcon->need_reconnect = true; } } - read_unlock(&cifs_tcp_ses_lock); + spin_unlock(&cifs_tcp_ses_lock); /* do not want to be sending data on a socket we are freeing */ mutex_lock(&server->srv_mutex); if (server->ssocket) { @@ -166,6 +173,8 @@ cifs_reconnect(struct TCP_Server_Info *server) sock_release(server->ssocket); server->ssocket = NULL; } + server->sequence_number = 0; + server->session_estab = false; spin_lock(&GlobalMid_Lock); list_for_each(tmp, &server->pending_mid_q) { @@ -198,7 +207,6 @@ cifs_reconnect(struct TCP_Server_Info *server) spin_lock(&GlobalMid_Lock); if (server->tcpStatus != CifsExiting) server->tcpStatus = CifsGood; - server->sequence_number = 0; spin_unlock(&GlobalMid_Lock); /* atomic_set(&server->inFlight,0);*/ wake_up(&server->response_q); @@ -629,9 +637,9 @@ multi_t2_fnd: } /* end while !EXITING */ /* take it off the list, if it's not already */ - write_lock(&cifs_tcp_ses_lock); + spin_lock(&cifs_tcp_ses_lock); list_del_init(&server->tcp_ses_list); - write_unlock(&cifs_tcp_ses_lock); + spin_unlock(&cifs_tcp_ses_lock); spin_lock(&GlobalMid_Lock); server->tcpStatus = CifsExiting; @@ -669,7 +677,7 @@ multi_t2_fnd: * BB: we shouldn't have to do any of this. It shouldn't be * possible to exit from the thread with active SMB sessions */ - read_lock(&cifs_tcp_ses_lock); + spin_lock(&cifs_tcp_ses_lock); if (list_empty(&server->pending_mid_q)) { /* loop through server session structures attached to this and mark them dead */ @@ -679,7 +687,7 @@ multi_t2_fnd: ses->status = CifsExiting; ses->server = NULL; } - read_unlock(&cifs_tcp_ses_lock); + spin_unlock(&cifs_tcp_ses_lock); } else { /* although we can not zero the server struct pointer yet, since there are active requests which may depnd on them, @@ -702,7 +710,7 @@ multi_t2_fnd: } } spin_unlock(&GlobalMid_Lock); - read_unlock(&cifs_tcp_ses_lock); + spin_unlock(&cifs_tcp_ses_lock); /* 1/8th of sec is more than enough time for them to exit */ msleep(125); } @@ -725,12 +733,12 @@ multi_t2_fnd: if a crazy root user tried to kill cifsd kernel thread explicitly this might happen) */ /* BB: This shouldn't be necessary, see above */ - read_lock(&cifs_tcp_ses_lock); + spin_lock(&cifs_tcp_ses_lock); list_for_each(tmp, &server->smb_ses_list) { ses = list_entry(tmp, struct cifsSesInfo, smb_ses_list); ses->server = NULL; } - read_unlock(&cifs_tcp_ses_lock); + spin_unlock(&cifs_tcp_ses_lock); kfree(server->hostname); task_to_wake = xchg(&server->tsk, NULL); @@ -1046,6 +1054,22 @@ cifs_parse_mount_options(char *options, const char *devname, "long\n"); return 1; } + } else if (strnicmp(data, "srcaddr", 7) == 0) { + vol->srcaddr.ss_family = AF_UNSPEC; + + if (!value || !*value) { + printk(KERN_WARNING "CIFS: srcaddr value" + " not specified.\n"); + return 1; /* needs_arg; */ + } + i = cifs_convert_address((struct sockaddr *)&vol->srcaddr, + value, strlen(value)); + if (i < 0) { + printk(KERN_WARNING "CIFS: Could not parse" + " srcaddr: %s\n", + value); + return 1; + } } else if (strnicmp(data, "prefixpath", 10) == 0) { if (!value || !*value) { printk(KERN_WARNING @@ -1325,6 +1349,10 @@ cifs_parse_mount_options(char *options, const char *devname, "/proc/fs/cifs/LookupCacheEnabled to 0\n"); } else if (strnicmp(data, "fsc", 3) == 0) { vol->fsc = true; + } else if (strnicmp(data, "mfsymlinks", 10) == 0) { + vol->mfsymlinks = true; + } else if (strnicmp(data, "multiuser", 8) == 0) { + vol->multiuser = true; } else printk(KERN_WARNING "CIFS: Unknown mount option %s\n", data); @@ -1356,6 +1384,13 @@ cifs_parse_mount_options(char *options, const char *devname, return 1; } } + + if (vol->multiuser && !(vol->secFlg & CIFSSEC_MAY_KRB5)) { + cERROR(1, "Multiuser mounts currently require krb5 " + "authentication!"); + return 1; + } + if (vol->UNCip == NULL) vol->UNCip = &vol->UNC[2]; @@ -1374,8 +1409,36 @@ cifs_parse_mount_options(char *options, const char *devname, return 0; } +/** Returns true if srcaddr isn't specified and rhs isn't + * specified, or if srcaddr is specified and + * matches the IP address of the rhs argument. + */ +static bool +srcip_matches(struct sockaddr *srcaddr, struct sockaddr *rhs) +{ + switch (srcaddr->sa_family) { + case AF_UNSPEC: + return (rhs->sa_family == AF_UNSPEC); + case AF_INET: { + struct sockaddr_in *saddr4 = (struct sockaddr_in *)srcaddr; + struct sockaddr_in *vaddr4 = (struct sockaddr_in *)rhs; + return (saddr4->sin_addr.s_addr == vaddr4->sin_addr.s_addr); + } + case AF_INET6: { + struct sockaddr_in6 *saddr6 = (struct sockaddr_in6 *)srcaddr; + struct sockaddr_in6 *vaddr6 = (struct sockaddr_in6 *)&rhs; + return ipv6_addr_equal(&saddr6->sin6_addr, &vaddr6->sin6_addr); + } + default: + WARN_ON(1); + return false; /* don't expect to be here */ + } +} + + static bool -match_address(struct TCP_Server_Info *server, struct sockaddr *addr) +match_address(struct TCP_Server_Info *server, struct sockaddr *addr, + struct sockaddr *srcaddr) { struct sockaddr_in *addr4 = (struct sockaddr_in *)addr; struct sockaddr_in6 *addr6 = (struct sockaddr_in6 *)addr; @@ -1402,6 +1465,9 @@ match_address(struct TCP_Server_Info *server, struct sockaddr *addr) break; } + if (!srcip_matches(srcaddr, (struct sockaddr *)&server->srcaddr)) + return false; + return true; } @@ -1458,29 +1524,21 @@ cifs_find_tcp_session(struct sockaddr *addr, struct smb_vol *vol) { struct TCP_Server_Info *server; - write_lock(&cifs_tcp_ses_lock); + spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(server, &cifs_tcp_ses_list, tcp_ses_list) { - /* - * the demux thread can exit on its own while still in CifsNew - * so don't accept any sockets in that state. Since the - * tcpStatus never changes back to CifsNew it's safe to check - * for this without a lock. - */ - if (server->tcpStatus == CifsNew) - continue; - - if (!match_address(server, addr)) + if (!match_address(server, addr, + (struct sockaddr *)&vol->srcaddr)) continue; if (!match_security(server, vol)) continue; ++server->srv_count; - write_unlock(&cifs_tcp_ses_lock); + spin_unlock(&cifs_tcp_ses_lock); cFYI(1, "Existing tcp session with server found"); return server; } - write_unlock(&cifs_tcp_ses_lock); + spin_unlock(&cifs_tcp_ses_lock); return NULL; } @@ -1489,14 +1547,14 @@ cifs_put_tcp_session(struct TCP_Server_Info *server) { struct task_struct *task; - write_lock(&cifs_tcp_ses_lock); + spin_lock(&cifs_tcp_ses_lock); if (--server->srv_count > 0) { - write_unlock(&cifs_tcp_ses_lock); + spin_unlock(&cifs_tcp_ses_lock); return; } list_del_init(&server->tcp_ses_list); - write_unlock(&cifs_tcp_ses_lock); + spin_unlock(&cifs_tcp_ses_lock); spin_lock(&GlobalMid_Lock); server->tcpStatus = CifsExiting; @@ -1574,6 +1632,7 @@ cifs_get_tcp_session(struct smb_vol *volume_info) volume_info->source_rfc1001_name, RFC1001_NAME_LEN_WITH_NULL); memcpy(tcp_ses->server_RFC1001_name, volume_info->target_rfc1001_name, RFC1001_NAME_LEN_WITH_NULL); + tcp_ses->session_estab = false; tcp_ses->sequence_number = 0; INIT_LIST_HEAD(&tcp_ses->tcp_ses_list); INIT_LIST_HEAD(&tcp_ses->smb_ses_list); @@ -1584,6 +1643,8 @@ cifs_get_tcp_session(struct smb_vol *volume_info) * no need to spinlock this init of tcpStatus or srv_count */ tcp_ses->tcpStatus = CifsNew; + memcpy(&tcp_ses->srcaddr, &volume_info->srcaddr, + sizeof(tcp_ses->srcaddr)); ++tcp_ses->srv_count; if (addr.ss_family == AF_INET6) { @@ -1618,9 +1679,9 @@ cifs_get_tcp_session(struct smb_vol *volume_info) } /* thread spawned, put it on the list */ - write_lock(&cifs_tcp_ses_lock); + spin_lock(&cifs_tcp_ses_lock); list_add(&tcp_ses->tcp_ses_list, &cifs_tcp_ses_list); - write_unlock(&cifs_tcp_ses_lock); + spin_unlock(&cifs_tcp_ses_lock); cifs_fscache_get_client_cookie(tcp_ses); @@ -1642,7 +1703,7 @@ cifs_find_smb_ses(struct TCP_Server_Info *server, struct smb_vol *vol) { struct cifsSesInfo *ses; - write_lock(&cifs_tcp_ses_lock); + spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { switch (server->secType) { case Kerberos: @@ -1662,10 +1723,10 @@ cifs_find_smb_ses(struct TCP_Server_Info *server, struct smb_vol *vol) continue; } ++ses->ses_count; - write_unlock(&cifs_tcp_ses_lock); + spin_unlock(&cifs_tcp_ses_lock); return ses; } - write_unlock(&cifs_tcp_ses_lock); + spin_unlock(&cifs_tcp_ses_lock); return NULL; } @@ -1676,14 +1737,14 @@ cifs_put_smb_ses(struct cifsSesInfo *ses) struct TCP_Server_Info *server = ses->server; cFYI(1, "%s: ses_count=%d\n", __func__, ses->ses_count); - write_lock(&cifs_tcp_ses_lock); + spin_lock(&cifs_tcp_ses_lock); if (--ses->ses_count > 0) { - write_unlock(&cifs_tcp_ses_lock); + spin_unlock(&cifs_tcp_ses_lock); return; } list_del_init(&ses->smb_ses_list); - write_unlock(&cifs_tcp_ses_lock); + spin_unlock(&cifs_tcp_ses_lock); if (ses->status == CifsGood) { xid = GetXid(); @@ -1740,6 +1801,8 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb_vol *volume_info) if (ses == NULL) goto get_ses_fail; + ses->tilen = 0; + ses->tiblob = NULL; /* new SMB session uses our server ref */ ses->server = server; if (server->addr.sockAddr6.sin6_family == AF_INET6) @@ -1778,9 +1841,9 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb_vol *volume_info) goto get_ses_fail; /* success, put it on the list */ - write_lock(&cifs_tcp_ses_lock); + spin_lock(&cifs_tcp_ses_lock); list_add(&ses->smb_ses_list, &server->smb_ses_list); - write_unlock(&cifs_tcp_ses_lock); + spin_unlock(&cifs_tcp_ses_lock); FreeXid(xid); return ses; @@ -1797,7 +1860,7 @@ cifs_find_tcon(struct cifsSesInfo *ses, const char *unc) struct list_head *tmp; struct cifsTconInfo *tcon; - write_lock(&cifs_tcp_ses_lock); + spin_lock(&cifs_tcp_ses_lock); list_for_each(tmp, &ses->tcon_list) { tcon = list_entry(tmp, struct cifsTconInfo, tcon_list); if (tcon->tidStatus == CifsExiting) @@ -1806,10 +1869,10 @@ cifs_find_tcon(struct cifsSesInfo *ses, const char *unc) continue; ++tcon->tc_count; - write_unlock(&cifs_tcp_ses_lock); + spin_unlock(&cifs_tcp_ses_lock); return tcon; } - write_unlock(&cifs_tcp_ses_lock); + spin_unlock(&cifs_tcp_ses_lock); return NULL; } @@ -1820,14 +1883,14 @@ cifs_put_tcon(struct cifsTconInfo *tcon) struct cifsSesInfo *ses = tcon->ses; cFYI(1, "%s: tc_count=%d\n", __func__, tcon->tc_count); - write_lock(&cifs_tcp_ses_lock); + spin_lock(&cifs_tcp_ses_lock); if (--tcon->tc_count > 0) { - write_unlock(&cifs_tcp_ses_lock); + spin_unlock(&cifs_tcp_ses_lock); return; } list_del_init(&tcon->tcon_list); - write_unlock(&cifs_tcp_ses_lock); + spin_unlock(&cifs_tcp_ses_lock); xid = GetXid(); CIFSSMBTDis(xid, tcon); @@ -1900,9 +1963,9 @@ cifs_get_tcon(struct cifsSesInfo *ses, struct smb_vol *volume_info) tcon->nocase = volume_info->nocase; tcon->local_lease = volume_info->local_lease; - write_lock(&cifs_tcp_ses_lock); + spin_lock(&cifs_tcp_ses_lock); list_add(&tcon->tcon_list, &ses->tcon_list); - write_unlock(&cifs_tcp_ses_lock); + spin_unlock(&cifs_tcp_ses_lock); cifs_fscache_get_super_cookie(tcon); @@ -1913,6 +1976,23 @@ out_fail: return ERR_PTR(rc); } +void +cifs_put_tlink(struct tcon_link *tlink) +{ + if (!tlink || IS_ERR(tlink)) + return; + + if (!atomic_dec_and_test(&tlink->tl_count) || + test_bit(TCON_LINK_IN_TREE, &tlink->tl_flags)) { + tlink->tl_time = jiffies; + return; + } + + if (!IS_ERR(tlink_tcon(tlink))) + cifs_put_tcon(tlink_tcon(tlink)); + kfree(tlink); + return; +} int get_dfs_path(int xid, struct cifsSesInfo *pSesInfo, const char *old_path, @@ -1997,6 +2077,33 @@ static void rfc1002mangle(char *target, char *source, unsigned int length) } +static int +bind_socket(struct TCP_Server_Info *server) +{ + int rc = 0; + if (server->srcaddr.ss_family != AF_UNSPEC) { + /* Bind to the specified local IP address */ + struct socket *socket = server->ssocket; + rc = socket->ops->bind(socket, + (struct sockaddr *) &server->srcaddr, + sizeof(server->srcaddr)); + if (rc < 0) { + struct sockaddr_in *saddr4; + struct sockaddr_in6 *saddr6; + saddr4 = (struct sockaddr_in *)&server->srcaddr; + saddr6 = (struct sockaddr_in6 *)&server->srcaddr; + if (saddr6->sin6_family == AF_INET6) + cERROR(1, "cifs: " + "Failed to bind to: %pI6c, error: %d\n", + &saddr6->sin6_addr, rc); + else + cERROR(1, "cifs: " + "Failed to bind to: %pI4, error: %d\n", + &saddr4->sin_addr.s_addr, rc); + } + } + return rc; +} static int ipv4_connect(struct TCP_Server_Info *server) @@ -2022,6 +2129,10 @@ ipv4_connect(struct TCP_Server_Info *server) cifs_reclassify_socket4(socket); } + rc = bind_socket(server); + if (rc < 0) + return rc; + /* user overrode default port */ if (server->addr.sockAddr.sin_port) { rc = socket->ops->connect(socket, (struct sockaddr *) @@ -2184,6 +2295,10 @@ ipv6_connect(struct TCP_Server_Info *server) cifs_reclassify_socket6(socket); } + rc = bind_socket(server); + if (rc < 0) + return rc; + /* user overrode default port */ if (server->addr.sockAddr6.sin6_port) { rc = socket->ops->connect(socket, @@ -2383,6 +2498,8 @@ convert_delimiter(char *path, char delim) static void setup_cifs_sb(struct smb_vol *pvolume_info, struct cifs_sb_info *cifs_sb) { + INIT_DELAYED_WORK(&cifs_sb->prune_tlinks, cifs_prune_tlinks); + if (pvolume_info->rsize > CIFSMaxBufSize) { cERROR(1, "rsize %d too large, using MaxBufSize", pvolume_info->rsize); @@ -2462,10 +2579,21 @@ static void setup_cifs_sb(struct smb_vol *pvolume_info, cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_DYNPERM; if (pvolume_info->fsc) cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_FSCACHE; + if (pvolume_info->multiuser) + cifs_sb->mnt_cifs_flags |= (CIFS_MOUNT_MULTIUSER | + CIFS_MOUNT_NO_PERM); if (pvolume_info->direct_io) { cFYI(1, "mounting share using direct i/o"); cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_DIRECT_IO; } + if (pvolume_info->mfsymlinks) { + if (pvolume_info->sfu_emul) { + cERROR(1, "mount option mfsymlinks ignored if sfu " + "mount option is used"); + } else { + cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_MF_SYMLINKS; + } + } if ((pvolume_info->cifs_acl) && (pvolume_info->dynperm)) cERROR(1, "mount option dynperm ignored if cifsacl " @@ -2552,6 +2680,7 @@ cifs_mount(struct super_block *sb, struct cifs_sb_info *cifs_sb, struct TCP_Server_Info *srvTcp; char *full_path; char *mount_data = mount_data_global; + struct tcon_link *tlink; #ifdef CONFIG_CIFS_DFS_UPCALL struct dfs_info3_param *referrals = NULL; unsigned int num_referrals = 0; @@ -2563,6 +2692,7 @@ try_mount_again: pSesInfo = NULL; srvTcp = NULL; full_path = NULL; + tlink = NULL; xid = GetXid(); @@ -2638,8 +2768,6 @@ try_mount_again: goto remote_path_check; } - cifs_sb->tcon = tcon; - /* do not care if following two calls succeed - informational */ if (!tcon->ipc) { CIFSSMBQFSDeviceInfo(xid, tcon); @@ -2748,6 +2876,38 @@ remote_path_check: #endif } + if (rc) + goto mount_fail_check; + + /* now, hang the tcon off of the superblock */ + tlink = kzalloc(sizeof *tlink, GFP_KERNEL); + if (tlink == NULL) { + rc = -ENOMEM; + goto mount_fail_check; + } + + tlink->tl_index = pSesInfo->linux_uid; + tlink->tl_tcon = tcon; + tlink->tl_time = jiffies; + set_bit(TCON_LINK_MASTER, &tlink->tl_flags); + set_bit(TCON_LINK_IN_TREE, &tlink->tl_flags); + + rc = radix_tree_preload(GFP_KERNEL); + if (rc == -ENOMEM) { + kfree(tlink); + goto mount_fail_check; + } + + spin_lock(&cifs_sb->tlink_tree_lock); + radix_tree_insert(&cifs_sb->tlink_tree, pSesInfo->linux_uid, tlink); + radix_tree_tag_set(&cifs_sb->tlink_tree, pSesInfo->linux_uid, + CIFS_TLINK_MASTER_TAG); + spin_unlock(&cifs_sb->tlink_tree_lock); + radix_tree_preload_end(); + + queue_delayed_work(system_nrt_wq, &cifs_sb->prune_tlinks, + TLINK_IDLE_EXPIRE); + mount_fail_check: /* on error free sesinfo and tcon struct if needed */ if (rc) { @@ -2825,14 +2985,13 @@ CIFSTCon(unsigned int xid, struct cifsSesInfo *ses, #ifdef CONFIG_CIFS_WEAK_PW_HASH if ((global_secflags & CIFSSEC_MAY_LANMAN) && (ses->server->secType == LANMAN)) - calc_lanman_hash(tcon->password, ses->server->cryptKey, + calc_lanman_hash(tcon->password, ses->cryptKey, ses->server->secMode & SECMODE_PW_ENCRYPT ? true : false, bcc_ptr); else #endif /* CIFS_WEAK_PW_HASH */ - SMBNTencrypt(tcon->password, ses->server->cryptKey, - bcc_ptr); + SMBNTencrypt(tcon->password, ses->cryptKey, bcc_ptr); bcc_ptr += CIFS_SESS_KEY_SIZE; if (ses->capabilities & CAP_UNICODE) { @@ -2934,19 +3093,39 @@ CIFSTCon(unsigned int xid, struct cifsSesInfo *ses, int cifs_umount(struct super_block *sb, struct cifs_sb_info *cifs_sb) { - int rc = 0; + int i, ret; char *tmp; + struct tcon_link *tlink[8]; + unsigned long index = 0; + + cancel_delayed_work_sync(&cifs_sb->prune_tlinks); + + do { + spin_lock(&cifs_sb->tlink_tree_lock); + ret = radix_tree_gang_lookup(&cifs_sb->tlink_tree, + (void **)tlink, index, + ARRAY_SIZE(tlink)); + /* increment index for next pass */ + if (ret > 0) + index = tlink[ret - 1]->tl_index + 1; + for (i = 0; i < ret; i++) { + cifs_get_tlink(tlink[i]); + clear_bit(TCON_LINK_IN_TREE, &tlink[i]->tl_flags); + radix_tree_delete(&cifs_sb->tlink_tree, + tlink[i]->tl_index); + } + spin_unlock(&cifs_sb->tlink_tree_lock); - if (cifs_sb->tcon) - cifs_put_tcon(cifs_sb->tcon); + for (i = 0; i < ret; i++) + cifs_put_tlink(tlink[i]); + } while (ret != 0); - cifs_sb->tcon = NULL; tmp = cifs_sb->prepath; cifs_sb->prepathlen = 0; cifs_sb->prepath = NULL; kfree(tmp); - return rc; + return 0; } int cifs_negotiate_protocol(unsigned int xid, struct cifsSesInfo *ses) @@ -2997,6 +3176,15 @@ int cifs_setup_session(unsigned int xid, struct cifsSesInfo *ses, if (rc) { cERROR(1, "Send error in SessSetup = %d", rc); } else { + mutex_lock(&ses->server->srv_mutex); + if (!server->session_estab) { + memcpy(&server->session_key.data, + &ses->auth_key.data, ses->auth_key.len); + server->session_key.len = ses->auth_key.len; + ses->server->session_estab = true; + } + mutex_unlock(&server->srv_mutex); + cFYI(1, "CIFS Session Established successfully"); spin_lock(&GlobalMid_Lock); ses->status = CifsGood; @@ -3007,3 +3195,237 @@ int cifs_setup_session(unsigned int xid, struct cifsSesInfo *ses, return rc; } +static struct cifsTconInfo * +cifs_construct_tcon(struct cifs_sb_info *cifs_sb, uid_t fsuid) +{ + struct cifsTconInfo *master_tcon = cifs_sb_master_tcon(cifs_sb); + struct cifsSesInfo *ses; + struct cifsTconInfo *tcon = NULL; + struct smb_vol *vol_info; + char username[MAX_USERNAME_SIZE + 1]; + + vol_info = kzalloc(sizeof(*vol_info), GFP_KERNEL); + if (vol_info == NULL) { + tcon = ERR_PTR(-ENOMEM); + goto out; + } + + snprintf(username, MAX_USERNAME_SIZE, "krb50x%x", fsuid); + vol_info->username = username; + vol_info->local_nls = cifs_sb->local_nls; + vol_info->linux_uid = fsuid; + vol_info->cred_uid = fsuid; + vol_info->UNC = master_tcon->treeName; + vol_info->retry = master_tcon->retry; + vol_info->nocase = master_tcon->nocase; + vol_info->local_lease = master_tcon->local_lease; + vol_info->no_linux_ext = !master_tcon->unix_ext; + + /* FIXME: allow for other secFlg settings */ + vol_info->secFlg = CIFSSEC_MUST_KRB5; + + /* get a reference for the same TCP session */ + spin_lock(&cifs_tcp_ses_lock); + ++master_tcon->ses->server->srv_count; + spin_unlock(&cifs_tcp_ses_lock); + + ses = cifs_get_smb_ses(master_tcon->ses->server, vol_info); + if (IS_ERR(ses)) { + tcon = (struct cifsTconInfo *)ses; + cifs_put_tcp_session(master_tcon->ses->server); + goto out; + } + + tcon = cifs_get_tcon(ses, vol_info); + if (IS_ERR(tcon)) { + cifs_put_smb_ses(ses); + goto out; + } + + if (ses->capabilities & CAP_UNIX) + reset_cifs_unix_caps(0, tcon, NULL, vol_info); +out: + kfree(vol_info); + + return tcon; +} + +static struct tcon_link * +cifs_sb_master_tlink(struct cifs_sb_info *cifs_sb) +{ + struct tcon_link *tlink; + unsigned int ret; + + spin_lock(&cifs_sb->tlink_tree_lock); + ret = radix_tree_gang_lookup_tag(&cifs_sb->tlink_tree, (void **)&tlink, + 0, 1, CIFS_TLINK_MASTER_TAG); + spin_unlock(&cifs_sb->tlink_tree_lock); + + /* the master tcon should always be present */ + if (ret == 0) + BUG(); + + return tlink; +} + +struct cifsTconInfo * +cifs_sb_master_tcon(struct cifs_sb_info *cifs_sb) +{ + return tlink_tcon(cifs_sb_master_tlink(cifs_sb)); +} + +static int +cifs_sb_tcon_pending_wait(void *unused) +{ + schedule(); + return signal_pending(current) ? -ERESTARTSYS : 0; +} + +/* + * Find or construct an appropriate tcon given a cifs_sb and the fsuid of the + * current task. + * + * If the superblock doesn't refer to a multiuser mount, then just return + * the master tcon for the mount. + * + * First, search the radix tree for an existing tcon for this fsuid. If one + * exists, then check to see if it's pending construction. If it is then wait + * for construction to complete. Once it's no longer pending, check to see if + * it failed and either return an error or retry construction, depending on + * the timeout. + * + * If one doesn't exist then insert a new tcon_link struct into the tree and + * try to construct a new one. + */ +struct tcon_link * +cifs_sb_tlink(struct cifs_sb_info *cifs_sb) +{ + int ret; + unsigned long fsuid = (unsigned long) current_fsuid(); + struct tcon_link *tlink, *newtlink; + + if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER)) + return cifs_get_tlink(cifs_sb_master_tlink(cifs_sb)); + + spin_lock(&cifs_sb->tlink_tree_lock); + tlink = radix_tree_lookup(&cifs_sb->tlink_tree, fsuid); + if (tlink) + cifs_get_tlink(tlink); + spin_unlock(&cifs_sb->tlink_tree_lock); + + if (tlink == NULL) { + newtlink = kzalloc(sizeof(*tlink), GFP_KERNEL); + if (newtlink == NULL) + return ERR_PTR(-ENOMEM); + newtlink->tl_index = fsuid; + newtlink->tl_tcon = ERR_PTR(-EACCES); + set_bit(TCON_LINK_PENDING, &newtlink->tl_flags); + set_bit(TCON_LINK_IN_TREE, &newtlink->tl_flags); + cifs_get_tlink(newtlink); + + ret = radix_tree_preload(GFP_KERNEL); + if (ret != 0) { + kfree(newtlink); + return ERR_PTR(ret); + } + + spin_lock(&cifs_sb->tlink_tree_lock); + /* was one inserted after previous search? */ + tlink = radix_tree_lookup(&cifs_sb->tlink_tree, fsuid); + if (tlink) { + cifs_get_tlink(tlink); + spin_unlock(&cifs_sb->tlink_tree_lock); + radix_tree_preload_end(); + kfree(newtlink); + goto wait_for_construction; + } + ret = radix_tree_insert(&cifs_sb->tlink_tree, fsuid, newtlink); + spin_unlock(&cifs_sb->tlink_tree_lock); + radix_tree_preload_end(); + if (ret) { + kfree(newtlink); + return ERR_PTR(ret); + } + tlink = newtlink; + } else { +wait_for_construction: + ret = wait_on_bit(&tlink->tl_flags, TCON_LINK_PENDING, + cifs_sb_tcon_pending_wait, + TASK_INTERRUPTIBLE); + if (ret) { + cifs_put_tlink(tlink); + return ERR_PTR(ret); + } + + /* if it's good, return it */ + if (!IS_ERR(tlink->tl_tcon)) + return tlink; + + /* return error if we tried this already recently */ + if (time_before(jiffies, tlink->tl_time + TLINK_ERROR_EXPIRE)) { + cifs_put_tlink(tlink); + return ERR_PTR(-EACCES); + } + + if (test_and_set_bit(TCON_LINK_PENDING, &tlink->tl_flags)) + goto wait_for_construction; + } + + tlink->tl_tcon = cifs_construct_tcon(cifs_sb, fsuid); + clear_bit(TCON_LINK_PENDING, &tlink->tl_flags); + wake_up_bit(&tlink->tl_flags, TCON_LINK_PENDING); + + if (IS_ERR(tlink->tl_tcon)) { + cifs_put_tlink(tlink); + return ERR_PTR(-EACCES); + } + + return tlink; +} + +/* + * periodic workqueue job that scans tcon_tree for a superblock and closes + * out tcons. + */ +static void +cifs_prune_tlinks(struct work_struct *work) +{ + struct cifs_sb_info *cifs_sb = container_of(work, struct cifs_sb_info, + prune_tlinks.work); + struct tcon_link *tlink[8]; + unsigned long now = jiffies; + unsigned long index = 0; + int i, ret; + + do { + spin_lock(&cifs_sb->tlink_tree_lock); + ret = radix_tree_gang_lookup(&cifs_sb->tlink_tree, + (void **)tlink, index, + ARRAY_SIZE(tlink)); + /* increment index for next pass */ + if (ret > 0) + index = tlink[ret - 1]->tl_index + 1; + for (i = 0; i < ret; i++) { + if (test_bit(TCON_LINK_MASTER, &tlink[i]->tl_flags) || + atomic_read(&tlink[i]->tl_count) != 0 || + time_after(tlink[i]->tl_time + TLINK_IDLE_EXPIRE, + now)) { + tlink[i] = NULL; + continue; + } + cifs_get_tlink(tlink[i]); + clear_bit(TCON_LINK_IN_TREE, &tlink[i]->tl_flags); + radix_tree_delete(&cifs_sb->tlink_tree, + tlink[i]->tl_index); + } + spin_unlock(&cifs_sb->tlink_tree_lock); + + for (i = 0; i < ret; i++) { + if (tlink[i] != NULL) + cifs_put_tlink(tlink[i]); + } + } while (ret != 0); + + queue_delayed_work(system_nrt_wq, &cifs_sb->prune_tlinks, + TLINK_IDLE_EXPIRE); +} diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index f9ed0751cc12..3840eddbfb7a 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -54,18 +54,18 @@ build_path_from_dentry(struct dentry *direntry) int dfsplen; char *full_path; char dirsep; - struct cifs_sb_info *cifs_sb; + struct cifs_sb_info *cifs_sb = CIFS_SB(direntry->d_sb); + struct cifsTconInfo *tcon = cifs_sb_master_tcon(cifs_sb); if (direntry == NULL) return NULL; /* not much we can do if dentry is freed and we need to reopen the file after it was closed implicitly when the server crashed */ - cifs_sb = CIFS_SB(direntry->d_sb); dirsep = CIFS_DIR_SEP(cifs_sb); pplen = cifs_sb->prepathlen; - if (cifs_sb->tcon && (cifs_sb->tcon->Flags & SMB_SHARE_IS_IN_DFS)) - dfsplen = strnlen(cifs_sb->tcon->treeName, MAX_TREE_SIZE + 1); + if (tcon->Flags & SMB_SHARE_IS_IN_DFS) + dfsplen = strnlen(tcon->treeName, MAX_TREE_SIZE + 1); else dfsplen = 0; cifs_bp_rename_retry: @@ -117,7 +117,7 @@ cifs_bp_rename_retry: /* BB test paths to Windows with '/' in the midst of prepath */ if (dfsplen) { - strncpy(full_path, cifs_sb->tcon->treeName, dfsplen); + strncpy(full_path, tcon->treeName, dfsplen); if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) { int i; for (i = 0; i < dfsplen; i++) { @@ -130,135 +130,6 @@ cifs_bp_rename_retry: return full_path; } -struct cifsFileInfo * -cifs_new_fileinfo(struct inode *newinode, __u16 fileHandle, - struct file *file, struct vfsmount *mnt, unsigned int oflags) -{ - int oplock = 0; - struct cifsFileInfo *pCifsFile; - struct cifsInodeInfo *pCifsInode; - struct cifs_sb_info *cifs_sb = CIFS_SB(mnt->mnt_sb); - - pCifsFile = kzalloc(sizeof(struct cifsFileInfo), GFP_KERNEL); - if (pCifsFile == NULL) - return pCifsFile; - - if (oplockEnabled) - oplock = REQ_OPLOCK; - - pCifsFile->netfid = fileHandle; - pCifsFile->pid = current->tgid; - pCifsFile->pInode = igrab(newinode); - pCifsFile->mnt = mnt; - pCifsFile->pfile = file; - pCifsFile->invalidHandle = false; - pCifsFile->closePend = false; - mutex_init(&pCifsFile->fh_mutex); - mutex_init(&pCifsFile->lock_mutex); - INIT_LIST_HEAD(&pCifsFile->llist); - atomic_set(&pCifsFile->count, 1); - INIT_WORK(&pCifsFile->oplock_break, cifs_oplock_break); - - write_lock(&GlobalSMBSeslock); - list_add(&pCifsFile->tlist, &cifs_sb->tcon->openFileList); - pCifsInode = CIFS_I(newinode); - if (pCifsInode) { - /* if readable file instance put first in list*/ - if (oflags & FMODE_READ) - list_add(&pCifsFile->flist, &pCifsInode->openFileList); - else - list_add_tail(&pCifsFile->flist, - &pCifsInode->openFileList); - - if ((oplock & 0xF) == OPLOCK_EXCLUSIVE) { - pCifsInode->clientCanCacheAll = true; - pCifsInode->clientCanCacheRead = true; - cFYI(1, "Exclusive Oplock inode %p", newinode); - } else if ((oplock & 0xF) == OPLOCK_READ) - pCifsInode->clientCanCacheRead = true; - } - write_unlock(&GlobalSMBSeslock); - - file->private_data = pCifsFile; - - return pCifsFile; -} - -int cifs_posix_open(char *full_path, struct inode **pinode, - struct super_block *sb, int mode, int oflags, - __u32 *poplock, __u16 *pnetfid, int xid) -{ - int rc; - FILE_UNIX_BASIC_INFO *presp_data; - __u32 posix_flags = 0; - struct cifs_sb_info *cifs_sb = CIFS_SB(sb); - struct cifs_fattr fattr; - - cFYI(1, "posix open %s", full_path); - - presp_data = kzalloc(sizeof(FILE_UNIX_BASIC_INFO), GFP_KERNEL); - if (presp_data == NULL) - return -ENOMEM; - -/* So far cifs posix extensions can only map the following flags. - There are other valid fmode oflags such as FMODE_LSEEK, FMODE_PREAD, but - so far we do not seem to need them, and we can treat them as local only */ - if ((oflags & (FMODE_READ | FMODE_WRITE)) == - (FMODE_READ | FMODE_WRITE)) - posix_flags = SMB_O_RDWR; - else if (oflags & FMODE_READ) - posix_flags = SMB_O_RDONLY; - else if (oflags & FMODE_WRITE) - posix_flags = SMB_O_WRONLY; - if (oflags & O_CREAT) - posix_flags |= SMB_O_CREAT; - if (oflags & O_EXCL) - posix_flags |= SMB_O_EXCL; - if (oflags & O_TRUNC) - posix_flags |= SMB_O_TRUNC; - /* be safe and imply O_SYNC for O_DSYNC */ - if (oflags & O_DSYNC) - posix_flags |= SMB_O_SYNC; - if (oflags & O_DIRECTORY) - posix_flags |= SMB_O_DIRECTORY; - if (oflags & O_NOFOLLOW) - posix_flags |= SMB_O_NOFOLLOW; - if (oflags & O_DIRECT) - posix_flags |= SMB_O_DIRECT; - - mode &= ~current_umask(); - rc = CIFSPOSIXCreate(xid, cifs_sb->tcon, posix_flags, mode, - pnetfid, presp_data, poplock, full_path, - cifs_sb->local_nls, cifs_sb->mnt_cifs_flags & - CIFS_MOUNT_MAP_SPECIAL_CHR); - if (rc) - goto posix_open_ret; - - if (presp_data->Type == cpu_to_le32(-1)) - goto posix_open_ret; /* open ok, caller does qpathinfo */ - - if (!pinode) - goto posix_open_ret; /* caller does not need info */ - - cifs_unix_basic_to_fattr(&fattr, presp_data, cifs_sb); - - /* get new inode and set it up */ - if (*pinode == NULL) { - cifs_fill_uniqueid(sb, &fattr); - *pinode = cifs_iget(sb, &fattr); - if (!*pinode) { - rc = -ENOMEM; - goto posix_open_ret; - } - } else { - cifs_fattr_to_inode(*pinode, &fattr); - } - -posix_open_ret: - kfree(presp_data); - return rc; -} - static void setup_cifs_dentry(struct cifsTconInfo *tcon, struct dentry *direntry, struct inode *newinode) @@ -291,6 +162,7 @@ cifs_create(struct inode *inode, struct dentry *direntry, int mode, int desiredAccess = GENERIC_READ | GENERIC_WRITE; __u16 fileHandle; struct cifs_sb_info *cifs_sb; + struct tcon_link *tlink; struct cifsTconInfo *tcon; char *full_path = NULL; FILE_ALL_INFO *buf = NULL; @@ -300,21 +172,26 @@ cifs_create(struct inode *inode, struct dentry *direntry, int mode, xid = GetXid(); cifs_sb = CIFS_SB(inode->i_sb); - tcon = cifs_sb->tcon; - - full_path = build_path_from_dentry(direntry); - if (full_path == NULL) { - rc = -ENOMEM; - goto cifs_create_out; + tlink = cifs_sb_tlink(cifs_sb); + if (IS_ERR(tlink)) { + FreeXid(xid); + return PTR_ERR(tlink); } + tcon = tlink_tcon(tlink); if (oplockEnabled) oplock = REQ_OPLOCK; if (nd && (nd->flags & LOOKUP_OPEN)) - oflags = nd->intent.open.flags; + oflags = nd->intent.open.file->f_flags; else - oflags = FMODE_READ | SMB_O_CREAT; + oflags = O_RDONLY | O_CREAT; + + full_path = build_path_from_dentry(direntry); + if (full_path == NULL) { + rc = -ENOMEM; + goto cifs_create_out; + } if (tcon->unix_ext && (tcon->ses->capabilities & CAP_UNIX) && (CIFS_UNIX_POSIX_PATH_OPS_CAP & @@ -344,9 +221,9 @@ cifs_create(struct inode *inode, struct dentry *direntry, int mode, /* if the file is going to stay open, then we need to set the desired access properly */ desiredAccess = 0; - if (oflags & FMODE_READ) + if (OPEN_FMODE(oflags) & FMODE_READ) desiredAccess |= GENERIC_READ; /* is this too little? */ - if (oflags & FMODE_WRITE) + if (OPEN_FMODE(oflags) & FMODE_WRITE) desiredAccess |= GENERIC_WRITE; if ((oflags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL)) @@ -375,7 +252,7 @@ cifs_create(struct inode *inode, struct dentry *direntry, int mode, if (!tcon->unix_ext && (mode & S_IWUGO) == 0) create_options |= CREATE_OPTION_READONLY; - if (cifs_sb->tcon->ses->capabilities & CAP_NT_SMBS) + if (tcon->ses->capabilities & CAP_NT_SMBS) rc = CIFSSMBOpen(xid, tcon, full_path, disposition, desiredAccess, create_options, &fileHandle, &oplock, buf, cifs_sb->local_nls, @@ -467,8 +344,7 @@ cifs_create_set_dentry: goto cifs_create_out; } - pfile_info = cifs_new_fileinfo(newinode, fileHandle, filp, - nd->path.mnt, oflags); + pfile_info = cifs_new_fileinfo(fileHandle, filp, tlink, oplock); if (pfile_info == NULL) { fput(filp); CIFSSMBClose(xid, tcon, fileHandle); @@ -481,6 +357,7 @@ cifs_create_set_dentry: cifs_create_out: kfree(buf); kfree(full_path); + cifs_put_tlink(tlink); FreeXid(xid); return rc; } @@ -491,6 +368,7 @@ int cifs_mknod(struct inode *inode, struct dentry *direntry, int mode, int rc = -EPERM; int xid; struct cifs_sb_info *cifs_sb; + struct tcon_link *tlink; struct cifsTconInfo *pTcon; char *full_path = NULL; struct inode *newinode = NULL; @@ -503,10 +381,14 @@ int cifs_mknod(struct inode *inode, struct dentry *direntry, int mode, if (!old_valid_dev(device_number)) return -EINVAL; - xid = GetXid(); - cifs_sb = CIFS_SB(inode->i_sb); - pTcon = cifs_sb->tcon; + tlink = cifs_sb_tlink(cifs_sb); + if (IS_ERR(tlink)) + return PTR_ERR(tlink); + + pTcon = tlink_tcon(tlink); + + xid = GetXid(); full_path = build_path_from_dentry(direntry); if (full_path == NULL) { @@ -606,6 +488,7 @@ mknod_out: kfree(full_path); kfree(buf); FreeXid(xid); + cifs_put_tlink(tlink); return rc; } @@ -619,6 +502,7 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry, __u16 fileHandle = 0; bool posix_open = false; struct cifs_sb_info *cifs_sb; + struct tcon_link *tlink; struct cifsTconInfo *pTcon; struct cifsFileInfo *cfile; struct inode *newInode = NULL; @@ -633,7 +517,12 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry, /* check whether path exists */ cifs_sb = CIFS_SB(parent_dir_inode->i_sb); - pTcon = cifs_sb->tcon; + tlink = cifs_sb_tlink(cifs_sb); + if (IS_ERR(tlink)) { + FreeXid(xid); + return (struct dentry *)tlink; + } + pTcon = tlink_tcon(tlink); /* * Don't allow the separator character in a path component. @@ -644,8 +533,8 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry, for (i = 0; i < direntry->d_name.len; i++) if (direntry->d_name.name[i] == '\\') { cFYI(1, "Invalid file name"); - FreeXid(xid); - return ERR_PTR(-EINVAL); + rc = -EINVAL; + goto lookup_out; } } @@ -655,7 +544,8 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry, */ if (nd && (nd->flags & LOOKUP_EXCL)) { d_instantiate(direntry, NULL); - return NULL; + rc = 0; + goto lookup_out; } /* can not grab the rename sem here since it would @@ -663,8 +553,8 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry, in which we already have the sb rename sem */ full_path = build_path_from_dentry(direntry); if (full_path == NULL) { - FreeXid(xid); - return ERR_PTR(-ENOMEM); + rc = -ENOMEM; + goto lookup_out; } if (direntry->d_inode != NULL) { @@ -687,11 +577,11 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry, if (pTcon->unix_ext) { if (nd && !(nd->flags & (LOOKUP_PARENT | LOOKUP_DIRECTORY)) && (nd->flags & LOOKUP_OPEN) && !pTcon->broken_posix_open && - (nd->intent.open.flags & O_CREAT)) { + (nd->intent.open.file->f_flags & O_CREAT)) { rc = cifs_posix_open(full_path, &newInode, parent_dir_inode->i_sb, nd->intent.open.create_mode, - nd->intent.open.flags, &oplock, + nd->intent.open.file->f_flags, &oplock, &fileHandle, xid); /* * The check below works around a bug in POSIX @@ -727,9 +617,8 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry, goto lookup_out; } - cfile = cifs_new_fileinfo(newInode, fileHandle, filp, - nd->path.mnt, - nd->intent.open.flags); + cfile = cifs_new_fileinfo(fileHandle, filp, tlink, + oplock); if (cfile == NULL) { fput(filp); CIFSSMBClose(xid, pTcon, fileHandle); @@ -759,6 +648,7 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry, lookup_out: kfree(full_path); + cifs_put_tlink(tlink); FreeXid(xid); return ERR_PTR(rc); } diff --git a/fs/cifs/file.c b/fs/cifs/file.c index de748c652d11..8c81e7b14d53 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -60,34 +60,32 @@ static inline int cifs_convert_flags(unsigned int flags) FILE_READ_DATA); } -static inline fmode_t cifs_posix_convert_flags(unsigned int flags) +static u32 cifs_posix_convert_flags(unsigned int flags) { - fmode_t posix_flags = 0; + u32 posix_flags = 0; if ((flags & O_ACCMODE) == O_RDONLY) - posix_flags = FMODE_READ; + posix_flags = SMB_O_RDONLY; else if ((flags & O_ACCMODE) == O_WRONLY) - posix_flags = FMODE_WRITE; - else if ((flags & O_ACCMODE) == O_RDWR) { - /* GENERIC_ALL is too much permission to request - can cause unnecessary access denied on create */ - /* return GENERIC_ALL; */ - posix_flags = FMODE_READ | FMODE_WRITE; - } - /* can not map O_CREAT or O_EXCL or O_TRUNC flags when - reopening a file. They had their effect on the original open */ - if (flags & O_APPEND) - posix_flags |= (fmode_t)O_APPEND; + posix_flags = SMB_O_WRONLY; + else if ((flags & O_ACCMODE) == O_RDWR) + posix_flags = SMB_O_RDWR; + + if (flags & O_CREAT) + posix_flags |= SMB_O_CREAT; + if (flags & O_EXCL) + posix_flags |= SMB_O_EXCL; + if (flags & O_TRUNC) + posix_flags |= SMB_O_TRUNC; + /* be safe and imply O_SYNC for O_DSYNC */ if (flags & O_DSYNC) - posix_flags |= (fmode_t)O_DSYNC; - if (flags & __O_SYNC) - posix_flags |= (fmode_t)__O_SYNC; + posix_flags |= SMB_O_SYNC; if (flags & O_DIRECTORY) - posix_flags |= (fmode_t)O_DIRECTORY; + posix_flags |= SMB_O_DIRECTORY; if (flags & O_NOFOLLOW) - posix_flags |= (fmode_t)O_NOFOLLOW; + posix_flags |= SMB_O_NOFOLLOW; if (flags & O_DIRECT) - posix_flags |= (fmode_t)O_DIRECT; + posix_flags |= SMB_O_DIRECT; return posix_flags; } @@ -106,66 +104,8 @@ static inline int cifs_get_disposition(unsigned int flags) return FILE_OPEN; } -/* all arguments to this function must be checked for validity in caller */ -static inline int -cifs_posix_open_inode_helper(struct inode *inode, struct file *file, - struct cifsInodeInfo *pCifsInode, __u32 oplock, - u16 netfid) -{ - - write_lock(&GlobalSMBSeslock); - - pCifsInode = CIFS_I(file->f_path.dentry->d_inode); - if (pCifsInode == NULL) { - write_unlock(&GlobalSMBSeslock); - return -EINVAL; - } - - if (pCifsInode->clientCanCacheRead) { - /* we have the inode open somewhere else - no need to discard cache data */ - goto psx_client_can_cache; - } - - /* BB FIXME need to fix this check to move it earlier into posix_open - BB fIX following section BB FIXME */ - - /* if not oplocked, invalidate inode pages if mtime or file - size changed */ -/* temp = cifs_NTtimeToUnix(le64_to_cpu(buf->LastWriteTime)); - if (timespec_equal(&file->f_path.dentry->d_inode->i_mtime, &temp) && - (file->f_path.dentry->d_inode->i_size == - (loff_t)le64_to_cpu(buf->EndOfFile))) { - cFYI(1, "inode unchanged on server"); - } else { - if (file->f_path.dentry->d_inode->i_mapping) { - rc = filemap_write_and_wait(file->f_path.dentry->d_inode->i_mapping); - if (rc != 0) - CIFS_I(file->f_path.dentry->d_inode)->write_behind_rc = rc; - } - cFYI(1, "invalidating remote inode since open detected it " - "changed"); - invalidate_remote_inode(file->f_path.dentry->d_inode); - } */ - -psx_client_can_cache: - if ((oplock & 0xF) == OPLOCK_EXCLUSIVE) { - pCifsInode->clientCanCacheAll = true; - pCifsInode->clientCanCacheRead = true; - cFYI(1, "Exclusive Oplock granted on inode %p", - file->f_path.dentry->d_inode); - } else if ((oplock & 0xF) == OPLOCK_READ) - pCifsInode->clientCanCacheRead = true; - - /* will have to change the unlock if we reenable the - filemap_fdatawrite (which does not seem necessary */ - write_unlock(&GlobalSMBSeslock); - return 0; -} - -/* all arguments to this function must be checked for validity in caller */ static inline int cifs_open_inode_helper(struct inode *inode, - struct cifsTconInfo *pTcon, int *oplock, FILE_ALL_INFO *buf, + struct cifsTconInfo *pTcon, __u32 oplock, FILE_ALL_INFO *buf, char *full_path, int xid) { struct cifsInodeInfo *pCifsInode = CIFS_I(inode); @@ -207,16 +147,175 @@ client_can_cache: rc = cifs_get_inode_info(&inode, full_path, buf, inode->i_sb, xid, NULL); - if ((*oplock & 0xF) == OPLOCK_EXCLUSIVE) { + if ((oplock & 0xF) == OPLOCK_EXCLUSIVE) { pCifsInode->clientCanCacheAll = true; pCifsInode->clientCanCacheRead = true; cFYI(1, "Exclusive Oplock granted on inode %p", inode); - } else if ((*oplock & 0xF) == OPLOCK_READ) + } else if ((oplock & 0xF) == OPLOCK_READ) pCifsInode->clientCanCacheRead = true; return rc; } +int cifs_posix_open(char *full_path, struct inode **pinode, + struct super_block *sb, int mode, unsigned int f_flags, + __u32 *poplock, __u16 *pnetfid, int xid) +{ + int rc; + FILE_UNIX_BASIC_INFO *presp_data; + __u32 posix_flags = 0; + struct cifs_sb_info *cifs_sb = CIFS_SB(sb); + struct cifs_fattr fattr; + struct tcon_link *tlink; + struct cifsTconInfo *tcon; + + cFYI(1, "posix open %s", full_path); + + presp_data = kzalloc(sizeof(FILE_UNIX_BASIC_INFO), GFP_KERNEL); + if (presp_data == NULL) + return -ENOMEM; + + tlink = cifs_sb_tlink(cifs_sb); + if (IS_ERR(tlink)) { + rc = PTR_ERR(tlink); + goto posix_open_ret; + } + + tcon = tlink_tcon(tlink); + mode &= ~current_umask(); + + posix_flags = cifs_posix_convert_flags(f_flags); + rc = CIFSPOSIXCreate(xid, tcon, posix_flags, mode, pnetfid, presp_data, + poplock, full_path, cifs_sb->local_nls, + cifs_sb->mnt_cifs_flags & + CIFS_MOUNT_MAP_SPECIAL_CHR); + cifs_put_tlink(tlink); + + if (rc) + goto posix_open_ret; + + if (presp_data->Type == cpu_to_le32(-1)) + goto posix_open_ret; /* open ok, caller does qpathinfo */ + + if (!pinode) + goto posix_open_ret; /* caller does not need info */ + + cifs_unix_basic_to_fattr(&fattr, presp_data, cifs_sb); + + /* get new inode and set it up */ + if (*pinode == NULL) { + cifs_fill_uniqueid(sb, &fattr); + *pinode = cifs_iget(sb, &fattr); + if (!*pinode) { + rc = -ENOMEM; + goto posix_open_ret; + } + } else { + cifs_fattr_to_inode(*pinode, &fattr); + } + +posix_open_ret: + kfree(presp_data); + return rc; +} + +struct cifsFileInfo * +cifs_new_fileinfo(__u16 fileHandle, struct file *file, + struct tcon_link *tlink, __u32 oplock) +{ + struct dentry *dentry = file->f_path.dentry; + struct inode *inode = dentry->d_inode; + struct cifsInodeInfo *pCifsInode = CIFS_I(inode); + struct cifsFileInfo *pCifsFile; + + pCifsFile = kzalloc(sizeof(struct cifsFileInfo), GFP_KERNEL); + if (pCifsFile == NULL) + return pCifsFile; + + pCifsFile->netfid = fileHandle; + pCifsFile->pid = current->tgid; + pCifsFile->uid = current_fsuid(); + pCifsFile->dentry = dget(dentry); + pCifsFile->f_flags = file->f_flags; + pCifsFile->invalidHandle = false; + pCifsFile->tlink = cifs_get_tlink(tlink); + mutex_init(&pCifsFile->fh_mutex); + mutex_init(&pCifsFile->lock_mutex); + INIT_LIST_HEAD(&pCifsFile->llist); + atomic_set(&pCifsFile->count, 1); + INIT_WORK(&pCifsFile->oplock_break, cifs_oplock_break); + + spin_lock(&cifs_file_list_lock); + list_add(&pCifsFile->tlist, &(tlink_tcon(tlink)->openFileList)); + /* if readable file instance put first in list*/ + if (file->f_mode & FMODE_READ) + list_add(&pCifsFile->flist, &pCifsInode->openFileList); + else + list_add_tail(&pCifsFile->flist, &pCifsInode->openFileList); + spin_unlock(&cifs_file_list_lock); + + if ((oplock & 0xF) == OPLOCK_EXCLUSIVE) { + pCifsInode->clientCanCacheAll = true; + pCifsInode->clientCanCacheRead = true; + cFYI(1, "Exclusive Oplock inode %p", inode); + } else if ((oplock & 0xF) == OPLOCK_READ) + pCifsInode->clientCanCacheRead = true; + + file->private_data = pCifsFile; + return pCifsFile; +} + +/* + * Release a reference on the file private data. This may involve closing + * the filehandle out on the server. + */ +void cifsFileInfo_put(struct cifsFileInfo *cifs_file) +{ + struct cifsTconInfo *tcon = tlink_tcon(cifs_file->tlink); + struct cifsInodeInfo *cifsi = CIFS_I(cifs_file->dentry->d_inode); + struct cifsLockInfo *li, *tmp; + + spin_lock(&cifs_file_list_lock); + if (!atomic_dec_and_test(&cifs_file->count)) { + spin_unlock(&cifs_file_list_lock); + return; + } + + /* remove it from the lists */ + list_del(&cifs_file->flist); + list_del(&cifs_file->tlist); + + if (list_empty(&cifsi->openFileList)) { + cFYI(1, "closing last open instance for inode %p", + cifs_file->dentry->d_inode); + cifsi->clientCanCacheRead = false; + cifsi->clientCanCacheAll = false; + } + spin_unlock(&cifs_file_list_lock); + + if (!tcon->need_reconnect && !cifs_file->invalidHandle) { + int xid, rc; + + xid = GetXid(); + rc = CIFSSMBClose(xid, tcon, cifs_file->netfid); + FreeXid(xid); + } + + /* Delete any outstanding lock records. We'll lose them when the file + * is closed anyway. + */ + mutex_lock(&cifs_file->lock_mutex); + list_for_each_entry_safe(li, tmp, &cifs_file->llist, llist) { + list_del(&li->llist); + kfree(li); + } + mutex_unlock(&cifs_file->lock_mutex); + + cifs_put_tlink(cifs_file->tlink); + dput(cifs_file->dentry); + kfree(cifs_file); +} + int cifs_open(struct inode *inode, struct file *file) { int rc = -EACCES; @@ -224,6 +323,7 @@ int cifs_open(struct inode *inode, struct file *file) __u32 oplock; struct cifs_sb_info *cifs_sb; struct cifsTconInfo *tcon; + struct tcon_link *tlink; struct cifsFileInfo *pCifsFile = NULL; struct cifsInodeInfo *pCifsInode; char *full_path = NULL; @@ -235,7 +335,12 @@ int cifs_open(struct inode *inode, struct file *file) xid = GetXid(); cifs_sb = CIFS_SB(inode->i_sb); - tcon = cifs_sb->tcon; + tlink = cifs_sb_tlink(cifs_sb); + if (IS_ERR(tlink)) { + FreeXid(xid); + return PTR_ERR(tlink); + } + tcon = tlink_tcon(tlink); pCifsInode = CIFS_I(file->f_path.dentry->d_inode); @@ -257,27 +362,15 @@ int cifs_open(struct inode *inode, struct file *file) (tcon->ses->capabilities & CAP_UNIX) && (CIFS_UNIX_POSIX_PATH_OPS_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability))) { - int oflags = (int) cifs_posix_convert_flags(file->f_flags); - oflags |= SMB_O_CREAT; /* can not refresh inode info since size could be stale */ rc = cifs_posix_open(full_path, &inode, inode->i_sb, cifs_sb->mnt_file_mode /* ignored */, - oflags, &oplock, &netfid, xid); + file->f_flags, &oplock, &netfid, xid); if (rc == 0) { cFYI(1, "posix open succeeded"); - /* no need for special case handling of setting mode - on read only files needed here */ - rc = cifs_posix_open_inode_helper(inode, file, - pCifsInode, oplock, netfid); - if (rc != 0) { - CIFSSMBClose(xid, tcon, netfid); - goto out; - } - - pCifsFile = cifs_new_fileinfo(inode, netfid, file, - file->f_path.mnt, - oflags); + pCifsFile = cifs_new_fileinfo(netfid, file, tlink, + oplock); if (pCifsFile == NULL) { CIFSSMBClose(xid, tcon, netfid); rc = -ENOMEM; @@ -345,7 +438,7 @@ int cifs_open(struct inode *inode, struct file *file) goto out; } - if (cifs_sb->tcon->ses->capabilities & CAP_NT_SMBS) + if (tcon->ses->capabilities & CAP_NT_SMBS) rc = CIFSSMBOpen(xid, tcon, full_path, disposition, desiredAccess, CREATE_NOT_DIR, &netfid, &oplock, buf, cifs_sb->local_nls, cifs_sb->mnt_cifs_flags @@ -365,12 +458,11 @@ int cifs_open(struct inode *inode, struct file *file) goto out; } - rc = cifs_open_inode_helper(inode, tcon, &oplock, buf, full_path, xid); + rc = cifs_open_inode_helper(inode, tcon, oplock, buf, full_path, xid); if (rc != 0) goto out; - pCifsFile = cifs_new_fileinfo(inode, netfid, file, file->f_path.mnt, - file->f_flags); + pCifsFile = cifs_new_fileinfo(netfid, file, tlink, oplock); if (pCifsFile == NULL) { rc = -ENOMEM; goto out; @@ -402,6 +494,7 @@ out: kfree(buf); kfree(full_path); FreeXid(xid); + cifs_put_tlink(tlink); return rc; } @@ -416,14 +509,13 @@ static int cifs_relock_file(struct cifsFileInfo *cifsFile) return rc; } -static int cifs_reopen_file(struct file *file, bool can_flush) +static int cifs_reopen_file(struct cifsFileInfo *pCifsFile, bool can_flush) { int rc = -EACCES; int xid; __u32 oplock; struct cifs_sb_info *cifs_sb; struct cifsTconInfo *tcon; - struct cifsFileInfo *pCifsFile; struct cifsInodeInfo *pCifsInode; struct inode *inode; char *full_path = NULL; @@ -431,11 +523,6 @@ static int cifs_reopen_file(struct file *file, bool can_flush) int disposition = FILE_OPEN; __u16 netfid; - if (file->private_data) - pCifsFile = file->private_data; - else - return -EBADF; - xid = GetXid(); mutex_lock(&pCifsFile->fh_mutex); if (!pCifsFile->invalidHandle) { @@ -445,39 +532,24 @@ static int cifs_reopen_file(struct file *file, bool can_flush) return rc; } - if (file->f_path.dentry == NULL) { - cERROR(1, "no valid name if dentry freed"); - dump_stack(); - rc = -EBADF; - goto reopen_error_exit; - } - - inode = file->f_path.dentry->d_inode; - if (inode == NULL) { - cERROR(1, "inode not valid"); - dump_stack(); - rc = -EBADF; - goto reopen_error_exit; - } - + inode = pCifsFile->dentry->d_inode; cifs_sb = CIFS_SB(inode->i_sb); - tcon = cifs_sb->tcon; + tcon = tlink_tcon(pCifsFile->tlink); /* can not grab rename sem here because various ops, including those that already have the rename sem can end up causing writepage to get called and if the server was down that means we end up here, and we can never tell if the caller already has the rename_sem */ - full_path = build_path_from_dentry(file->f_path.dentry); + full_path = build_path_from_dentry(pCifsFile->dentry); if (full_path == NULL) { rc = -ENOMEM; -reopen_error_exit: mutex_unlock(&pCifsFile->fh_mutex); FreeXid(xid); return rc; } cFYI(1, "inode = 0x%p file flags 0x%x for %s", - inode, file->f_flags, full_path); + inode, pCifsFile->f_flags, full_path); if (oplockEnabled) oplock = REQ_OPLOCK; @@ -487,8 +559,14 @@ reopen_error_exit: if (tcon->unix_ext && (tcon->ses->capabilities & CAP_UNIX) && (CIFS_UNIX_POSIX_PATH_OPS_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability))) { - int oflags = (int) cifs_posix_convert_flags(file->f_flags); - /* can not refresh inode info since size could be stale */ + + /* + * O_CREAT, O_EXCL and O_TRUNC already had their effect on the + * original open. Must mask them off for a reopen. + */ + unsigned int oflags = pCifsFile->f_flags & + ~(O_CREAT | O_EXCL | O_TRUNC); + rc = cifs_posix_open(full_path, NULL, inode->i_sb, cifs_sb->mnt_file_mode /* ignored */, oflags, &oplock, &netfid, xid); @@ -500,7 +578,7 @@ reopen_error_exit: in the reconnect path it is important to retry hard */ } - desiredAccess = cifs_convert_flags(file->f_flags); + desiredAccess = cifs_convert_flags(pCifsFile->f_flags); /* Can not refresh inode by passing in file_info buf to be returned by SMBOpen and then calling get_inode_info with returned buf @@ -516,49 +594,50 @@ reopen_error_exit: mutex_unlock(&pCifsFile->fh_mutex); cFYI(1, "cifs_open returned 0x%x", rc); cFYI(1, "oplock: %d", oplock); - } else { + goto reopen_error_exit; + } + reopen_success: - pCifsFile->netfid = netfid; - pCifsFile->invalidHandle = false; - mutex_unlock(&pCifsFile->fh_mutex); - pCifsInode = CIFS_I(inode); - if (pCifsInode) { - if (can_flush) { - rc = filemap_write_and_wait(inode->i_mapping); - if (rc != 0) - CIFS_I(inode)->write_behind_rc = rc; - /* temporarily disable caching while we - go to server to get inode info */ - pCifsInode->clientCanCacheAll = false; - pCifsInode->clientCanCacheRead = false; - if (tcon->unix_ext) - rc = cifs_get_inode_info_unix(&inode, - full_path, inode->i_sb, xid); - else - rc = cifs_get_inode_info(&inode, - full_path, NULL, inode->i_sb, - xid, NULL); - } /* else we are writing out data to server already - and could deadlock if we tried to flush data, and - since we do not know if we have data that would - invalidate the current end of file on the server - we can not go to the server to get the new inod - info */ - if ((oplock & 0xF) == OPLOCK_EXCLUSIVE) { - pCifsInode->clientCanCacheAll = true; - pCifsInode->clientCanCacheRead = true; - cFYI(1, "Exclusive Oplock granted on inode %p", - file->f_path.dentry->d_inode); - } else if ((oplock & 0xF) == OPLOCK_READ) { - pCifsInode->clientCanCacheRead = true; - pCifsInode->clientCanCacheAll = false; - } else { - pCifsInode->clientCanCacheRead = false; - pCifsInode->clientCanCacheAll = false; - } - cifs_relock_file(pCifsFile); - } + pCifsFile->netfid = netfid; + pCifsFile->invalidHandle = false; + mutex_unlock(&pCifsFile->fh_mutex); + pCifsInode = CIFS_I(inode); + + if (can_flush) { + rc = filemap_write_and_wait(inode->i_mapping); + if (rc != 0) + CIFS_I(inode)->write_behind_rc = rc; + + pCifsInode->clientCanCacheAll = false; + pCifsInode->clientCanCacheRead = false; + if (tcon->unix_ext) + rc = cifs_get_inode_info_unix(&inode, + full_path, inode->i_sb, xid); + else + rc = cifs_get_inode_info(&inode, + full_path, NULL, inode->i_sb, + xid, NULL); + } /* else we are writing out data to server already + and could deadlock if we tried to flush data, and + since we do not know if we have data that would + invalidate the current end of file on the server + we can not go to the server to get the new inod + info */ + if ((oplock & 0xF) == OPLOCK_EXCLUSIVE) { + pCifsInode->clientCanCacheAll = true; + pCifsInode->clientCanCacheRead = true; + cFYI(1, "Exclusive Oplock granted on inode %p", + pCifsFile->dentry->d_inode); + } else if ((oplock & 0xF) == OPLOCK_READ) { + pCifsInode->clientCanCacheRead = true; + pCifsInode->clientCanCacheAll = false; + } else { + pCifsInode->clientCanCacheRead = false; + pCifsInode->clientCanCacheAll = false; } + cifs_relock_file(pCifsFile); + +reopen_error_exit: kfree(full_path); FreeXid(xid); return rc; @@ -566,79 +645,11 @@ reopen_success: int cifs_close(struct inode *inode, struct file *file) { - int rc = 0; - int xid, timeout; - struct cifs_sb_info *cifs_sb; - struct cifsTconInfo *pTcon; - struct cifsFileInfo *pSMBFile = file->private_data; + cifsFileInfo_put(file->private_data); + file->private_data = NULL; - xid = GetXid(); - - cifs_sb = CIFS_SB(inode->i_sb); - pTcon = cifs_sb->tcon; - if (pSMBFile) { - struct cifsLockInfo *li, *tmp; - write_lock(&GlobalSMBSeslock); - pSMBFile->closePend = true; - if (pTcon) { - /* no sense reconnecting to close a file that is - already closed */ - if (!pTcon->need_reconnect) { - write_unlock(&GlobalSMBSeslock); - timeout = 2; - while ((atomic_read(&pSMBFile->count) != 1) - && (timeout <= 2048)) { - /* Give write a better chance to get to - server ahead of the close. We do not - want to add a wait_q here as it would - increase the memory utilization as - the struct would be in each open file, - but this should give enough time to - clear the socket */ - cFYI(DBG2, "close delay, write pending"); - msleep(timeout); - timeout *= 4; - } - if (!pTcon->need_reconnect && - !pSMBFile->invalidHandle) - rc = CIFSSMBClose(xid, pTcon, - pSMBFile->netfid); - } else - write_unlock(&GlobalSMBSeslock); - } else - write_unlock(&GlobalSMBSeslock); - - /* Delete any outstanding lock records. - We'll lose them when the file is closed anyway. */ - mutex_lock(&pSMBFile->lock_mutex); - list_for_each_entry_safe(li, tmp, &pSMBFile->llist, llist) { - list_del(&li->llist); - kfree(li); - } - mutex_unlock(&pSMBFile->lock_mutex); - - write_lock(&GlobalSMBSeslock); - list_del(&pSMBFile->flist); - list_del(&pSMBFile->tlist); - write_unlock(&GlobalSMBSeslock); - cifsFileInfo_put(file->private_data); - file->private_data = NULL; - } else - rc = -EBADF; - - read_lock(&GlobalSMBSeslock); - if (list_empty(&(CIFS_I(inode)->openFileList))) { - cFYI(1, "closing last open instance for inode %p", inode); - /* if the file is not open we do not know if we can cache info - on this inode, much less write behind and read ahead */ - CIFS_I(inode)->clientCanCacheRead = false; - CIFS_I(inode)->clientCanCacheAll = false; - } - read_unlock(&GlobalSMBSeslock); - if ((rc == 0) && CIFS_I(inode)->write_behind_rc) - rc = CIFS_I(inode)->write_behind_rc; - FreeXid(xid); - return rc; + /* return code from the ->release op is always ignored */ + return 0; } int cifs_closedir(struct inode *inode, struct file *file) @@ -653,25 +664,21 @@ int cifs_closedir(struct inode *inode, struct file *file) xid = GetXid(); if (pCFileStruct) { - struct cifsTconInfo *pTcon; - struct cifs_sb_info *cifs_sb = - CIFS_SB(file->f_path.dentry->d_sb); - - pTcon = cifs_sb->tcon; + struct cifsTconInfo *pTcon = tlink_tcon(pCFileStruct->tlink); cFYI(1, "Freeing private data in close dir"); - write_lock(&GlobalSMBSeslock); + spin_lock(&cifs_file_list_lock); if (!pCFileStruct->srch_inf.endOfSearch && !pCFileStruct->invalidHandle) { pCFileStruct->invalidHandle = true; - write_unlock(&GlobalSMBSeslock); + spin_unlock(&cifs_file_list_lock); rc = CIFSFindClose(xid, pTcon, pCFileStruct->netfid); cFYI(1, "Closing uncompleted readdir with rc %d", rc); /* not much we can do if it fails anyway, ignore rc */ rc = 0; } else - write_unlock(&GlobalSMBSeslock); + spin_unlock(&cifs_file_list_lock); ptmp = pCFileStruct->srch_inf.ntwrk_buf_start; if (ptmp) { cFYI(1, "closedir free smb buf in srch struct"); @@ -681,6 +688,7 @@ int cifs_closedir(struct inode *inode, struct file *file) else cifs_buf_release(ptmp); } + cifs_put_tlink(pCFileStruct->tlink); kfree(file->private_data); file->private_data = NULL; } @@ -767,7 +775,7 @@ int cifs_lock(struct file *file, int cmd, struct file_lock *pfLock) cFYI(1, "Unknown type of lock"); cifs_sb = CIFS_SB(file->f_path.dentry->d_sb); - tcon = cifs_sb->tcon; + tcon = tlink_tcon(((struct cifsFileInfo *)file->private_data)->tlink); if (file->private_data == NULL) { rc = -EBADF; @@ -960,14 +968,14 @@ ssize_t cifs_user_write(struct file *file, const char __user *write_data, cifs_sb = CIFS_SB(file->f_path.dentry->d_sb); - pTcon = cifs_sb->tcon; - /* cFYI(1, " write %d bytes to offset %lld of %s", write_size, *poffset, file->f_path.dentry->d_name.name); */ if (file->private_data == NULL) return -EBADF; + open_file = file->private_data; + pTcon = tlink_tcon(open_file->tlink); rc = generic_write_checks(file, poffset, &write_size, 0); if (rc) @@ -988,19 +996,12 @@ ssize_t cifs_user_write(struct file *file, const char __user *write_data, we blocked so return what we managed to write */ return total_written; } - if (open_file->closePend) { - FreeXid(xid); - if (total_written) - return total_written; - else - return -EBADF; - } if (open_file->invalidHandle) { /* we could deadlock if we called filemap_fdatawait from here so tell reopen_file not to flush data to server now */ - rc = cifs_reopen_file(file, false); + rc = cifs_reopen_file(open_file, false); if (rc != 0) break; } @@ -1048,8 +1049,9 @@ ssize_t cifs_user_write(struct file *file, const char __user *write_data, return total_written; } -static ssize_t cifs_write(struct file *file, const char *write_data, - size_t write_size, loff_t *poffset) +static ssize_t cifs_write(struct cifsFileInfo *open_file, + const char *write_data, size_t write_size, + loff_t *poffset) { int rc = 0; unsigned int bytes_written = 0; @@ -1057,19 +1059,15 @@ static ssize_t cifs_write(struct file *file, const char *write_data, struct cifs_sb_info *cifs_sb; struct cifsTconInfo *pTcon; int xid, long_op; - struct cifsFileInfo *open_file; - struct cifsInodeInfo *cifsi = CIFS_I(file->f_path.dentry->d_inode); + struct dentry *dentry = open_file->dentry; + struct cifsInodeInfo *cifsi = CIFS_I(dentry->d_inode); - cifs_sb = CIFS_SB(file->f_path.dentry->d_sb); - - pTcon = cifs_sb->tcon; + cifs_sb = CIFS_SB(dentry->d_sb); cFYI(1, "write %zd bytes to offset %lld of %s", write_size, - *poffset, file->f_path.dentry->d_name.name); + *poffset, dentry->d_name.name); - if (file->private_data == NULL) - return -EBADF; - open_file = file->private_data; + pTcon = tlink_tcon(open_file->tlink); xid = GetXid(); @@ -1078,28 +1076,12 @@ static ssize_t cifs_write(struct file *file, const char *write_data, total_written += bytes_written) { rc = -EAGAIN; while (rc == -EAGAIN) { - if (file->private_data == NULL) { - /* file has been closed on us */ - FreeXid(xid); - /* if we have gotten here we have written some data - and blocked, and the file has been freed on us - while we blocked so return what we managed to - write */ - return total_written; - } - if (open_file->closePend) { - FreeXid(xid); - if (total_written) - return total_written; - else - return -EBADF; - } if (open_file->invalidHandle) { /* we could deadlock if we called filemap_fdatawait from here so tell reopen_file not to flush data to server now */ - rc = cifs_reopen_file(file, false); + rc = cifs_reopen_file(open_file, false); if (rc != 0) break; } @@ -1146,43 +1128,41 @@ static ssize_t cifs_write(struct file *file, const char *write_data, cifs_stats_bytes_written(pTcon, total_written); - /* since the write may have blocked check these pointers again */ - if ((file->f_path.dentry) && (file->f_path.dentry->d_inode)) { -/*BB We could make this contingent on superblock ATIME flag too */ -/* file->f_path.dentry->d_inode->i_ctime = - file->f_path.dentry->d_inode->i_mtime = CURRENT_TIME;*/ - if (total_written > 0) { - spin_lock(&file->f_path.dentry->d_inode->i_lock); - if (*poffset > file->f_path.dentry->d_inode->i_size) - i_size_write(file->f_path.dentry->d_inode, - *poffset); - spin_unlock(&file->f_path.dentry->d_inode->i_lock); - } - mark_inode_dirty_sync(file->f_path.dentry->d_inode); + if (total_written > 0) { + spin_lock(&dentry->d_inode->i_lock); + if (*poffset > dentry->d_inode->i_size) + i_size_write(dentry->d_inode, *poffset); + spin_unlock(&dentry->d_inode->i_lock); } + mark_inode_dirty_sync(dentry->d_inode); FreeXid(xid); return total_written; } #ifdef CONFIG_CIFS_EXPERIMENTAL -struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode) +struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode, + bool fsuid_only) { struct cifsFileInfo *open_file = NULL; + struct cifs_sb_info *cifs_sb = CIFS_SB(cifs_inode->vfs_inode.i_sb); + + /* only filter by fsuid on multiuser mounts */ + if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER)) + fsuid_only = false; - read_lock(&GlobalSMBSeslock); + spin_lock(&cifs_file_list_lock); /* we could simply get the first_list_entry since write-only entries are always at the end of the list but since the first entry might have a close pending, we go through the whole list */ list_for_each_entry(open_file, &cifs_inode->openFileList, flist) { - if (open_file->closePend) + if (fsuid_only && open_file->uid != current_fsuid()) continue; - if (open_file->pfile && ((open_file->pfile->f_flags & O_RDWR) || - (open_file->pfile->f_flags & O_RDONLY))) { + if (OPEN_FMODE(open_file->f_flags) & FMODE_READ) { if (!open_file->invalidHandle) { /* found a good file */ /* lock it so it will not be closed on us */ cifsFileInfo_get(open_file); - read_unlock(&GlobalSMBSeslock); + spin_unlock(&cifs_file_list_lock); return open_file; } /* else might as well continue, and look for another, or simply have the caller reopen it @@ -1190,14 +1170,16 @@ struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode) } else /* write only file */ break; /* write only files are last so must be done */ } - read_unlock(&GlobalSMBSeslock); + spin_unlock(&cifs_file_list_lock); return NULL; } #endif -struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *cifs_inode) +struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *cifs_inode, + bool fsuid_only) { struct cifsFileInfo *open_file; + struct cifs_sb_info *cifs_sb = CIFS_SB(cifs_inode->vfs_inode.i_sb); bool any_available = false; int rc; @@ -1211,53 +1193,39 @@ struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *cifs_inode) return NULL; } - read_lock(&GlobalSMBSeslock); + /* only filter by fsuid on multiuser mounts */ + if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER)) + fsuid_only = false; + + spin_lock(&cifs_file_list_lock); refind_writable: list_for_each_entry(open_file, &cifs_inode->openFileList, flist) { - if (open_file->closePend || - (!any_available && open_file->pid != current->tgid)) + if (!any_available && open_file->pid != current->tgid) continue; - - if (open_file->pfile && - ((open_file->pfile->f_flags & O_RDWR) || - (open_file->pfile->f_flags & O_WRONLY))) { + if (fsuid_only && open_file->uid != current_fsuid()) + continue; + if (OPEN_FMODE(open_file->f_flags) & FMODE_WRITE) { cifsFileInfo_get(open_file); if (!open_file->invalidHandle) { /* found a good writable file */ - read_unlock(&GlobalSMBSeslock); + spin_unlock(&cifs_file_list_lock); return open_file; } - read_unlock(&GlobalSMBSeslock); + spin_unlock(&cifs_file_list_lock); + /* Had to unlock since following call can block */ - rc = cifs_reopen_file(open_file->pfile, false); - if (!rc) { - if (!open_file->closePend) - return open_file; - else { /* start over in case this was deleted */ - /* since the list could be modified */ - read_lock(&GlobalSMBSeslock); - cifsFileInfo_put(open_file); - goto refind_writable; - } - } + rc = cifs_reopen_file(open_file, false); + if (!rc) + return open_file; - /* if it fails, try another handle if possible - - (we can not do this if closePending since - loop could be modified - in which case we - have to start at the beginning of the list - again. Note that it would be bad - to hold up writepages here (rather than - in caller) with continuous retries */ + /* if it fails, try another handle if possible */ cFYI(1, "wp failed on reopen file"); - read_lock(&GlobalSMBSeslock); - /* can not use this handle, no write - pending on this one after all */ cifsFileInfo_put(open_file); - if (open_file->closePend) /* list could have changed */ - goto refind_writable; + spin_lock(&cifs_file_list_lock); + /* else we simply continue to the next entry. Thus we do not loop on reopen errors. If we can not reopen the file, for example if we @@ -1272,7 +1240,7 @@ refind_writable: any_available = true; goto refind_writable; } - read_unlock(&GlobalSMBSeslock); + spin_unlock(&cifs_file_list_lock); return NULL; } @@ -1284,7 +1252,6 @@ static int cifs_partialpagewrite(struct page *page, unsigned from, unsigned to) int rc = -EFAULT; int bytes_written = 0; struct cifs_sb_info *cifs_sb; - struct cifsTconInfo *pTcon; struct inode *inode; struct cifsFileInfo *open_file; @@ -1293,7 +1260,6 @@ static int cifs_partialpagewrite(struct page *page, unsigned from, unsigned to) inode = page->mapping->host; cifs_sb = CIFS_SB(inode->i_sb); - pTcon = cifs_sb->tcon; offset += (loff_t)from; write_data = kmap(page); @@ -1314,10 +1280,10 @@ static int cifs_partialpagewrite(struct page *page, unsigned from, unsigned to) if (mapping->host->i_size - offset < (loff_t)to) to = (unsigned)(mapping->host->i_size - offset); - open_file = find_writable_file(CIFS_I(mapping->host)); + open_file = find_writable_file(CIFS_I(mapping->host), false); if (open_file) { - bytes_written = cifs_write(open_file->pfile, write_data, - to-from, &offset); + bytes_written = cifs_write(open_file, write_data, + to - from, &offset); cifsFileInfo_put(open_file); /* Does mm or vfs already set times? */ inode->i_atime = inode->i_mtime = current_fs_time(inode->i_sb); @@ -1352,6 +1318,7 @@ static int cifs_writepages(struct address_space *mapping, int nr_pages; __u64 offset = 0; struct cifsFileInfo *open_file; + struct cifsTconInfo *tcon; struct cifsInodeInfo *cifsi = CIFS_I(mapping->host); struct page *page; struct pagevec pvec; @@ -1359,6 +1326,15 @@ static int cifs_writepages(struct address_space *mapping, int scanned = 0; int xid, long_op; + /* + * BB: Is this meaningful for a non-block-device file system? + * If it is, we should test it again after we do I/O + */ + if (wbc->nonblocking && bdi_write_congested(bdi)) { + wbc->encountered_congestion = 1; + return 0; + } + cifs_sb = CIFS_SB(mapping->host->i_sb); /* @@ -1368,27 +1344,29 @@ static int cifs_writepages(struct address_space *mapping, if (cifs_sb->wsize < PAGE_CACHE_SIZE) return generic_writepages(mapping, wbc); - if ((cifs_sb->tcon->ses) && (cifs_sb->tcon->ses->server)) - if (cifs_sb->tcon->ses->server->secMode & - (SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED)) - if (!experimEnabled) - return generic_writepages(mapping, wbc); - iov = kmalloc(32 * sizeof(struct kvec), GFP_KERNEL); if (iov == NULL) return generic_writepages(mapping, wbc); - /* - * BB: Is this meaningful for a non-block-device file system? - * If it is, we should test it again after we do I/O + * if there's no open file, then this is likely to fail too, + * but it'll at least handle the return. Maybe it should be + * a BUG() instead? */ - if (wbc->nonblocking && bdi_write_congested(bdi)) { - wbc->encountered_congestion = 1; + open_file = find_writable_file(CIFS_I(mapping->host), false); + if (!open_file) { kfree(iov); - return 0; + return generic_writepages(mapping, wbc); } + tcon = tlink_tcon(open_file->tlink); + if (!experimEnabled && tcon->ses->server->secMode & + (SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED)) { + cifsFileInfo_put(open_file); + return generic_writepages(mapping, wbc); + } + cifsFileInfo_put(open_file); + xid = GetXid(); pagevec_init(&pvec, 0); @@ -1492,38 +1470,34 @@ retry: break; } if (n_iov) { - /* Search for a writable handle every time we call - * CIFSSMBWrite2. We can't rely on the last handle - * we used to still be valid - */ - open_file = find_writable_file(CIFS_I(mapping->host)); + open_file = find_writable_file(CIFS_I(mapping->host), + false); if (!open_file) { cERROR(1, "No writable handles for inode"); rc = -EBADF; } else { long_op = cifs_write_timeout(cifsi, offset); - rc = CIFSSMBWrite2(xid, cifs_sb->tcon, - open_file->netfid, + rc = CIFSSMBWrite2(xid, tcon, open_file->netfid, bytes_to_write, offset, &bytes_written, iov, n_iov, long_op); cifsFileInfo_put(open_file); cifs_update_eof(cifsi, offset, bytes_written); + } - if (rc || bytes_written < bytes_to_write) { - cERROR(1, "Write2 ret %d, wrote %d", - rc, bytes_written); - /* BB what if continued retry is - requested via mount flags? */ - if (rc == -ENOSPC) - set_bit(AS_ENOSPC, &mapping->flags); - else - set_bit(AS_EIO, &mapping->flags); - } else { - cifs_stats_bytes_written(cifs_sb->tcon, - bytes_written); - } + if (rc || bytes_written < bytes_to_write) { + cERROR(1, "Write2 ret %d, wrote %d", + rc, bytes_written); + /* BB what if continued retry is + requested via mount flags? */ + if (rc == -ENOSPC) + set_bit(AS_ENOSPC, &mapping->flags); + else + set_bit(AS_EIO, &mapping->flags); + } else { + cifs_stats_bytes_written(tcon, bytes_written); } + for (i = 0; i < n_iov; i++) { page = pvec.pages[first + i]; /* Should we also set page error on @@ -1624,7 +1598,8 @@ static int cifs_write_end(struct file *file, struct address_space *mapping, /* BB check if anything else missing out of ppw such as updating last write time */ page_data = kmap(page); - rc = cifs_write(file, page_data + offset, copied, &pos); + rc = cifs_write(file->private_data, page_data + offset, + copied, &pos); /* if (rc < 0) should we set writebehind rc? */ kunmap(page); @@ -1665,7 +1640,7 @@ int cifs_fsync(struct file *file, int datasync) if (rc == 0) { rc = CIFS_I(inode)->write_behind_rc; CIFS_I(inode)->write_behind_rc = 0; - tcon = CIFS_SB(inode->i_sb)->tcon; + tcon = tlink_tcon(smbfile->tlink); if (!rc && tcon && smbfile && !(CIFS_SB(inode->i_sb)->mnt_cifs_flags & CIFS_MOUNT_NOSSYNC)) rc = CIFSSMBFlush(xid, tcon, smbfile->netfid); @@ -1750,7 +1725,6 @@ ssize_t cifs_user_read(struct file *file, char __user *read_data, xid = GetXid(); cifs_sb = CIFS_SB(file->f_path.dentry->d_sb); - pTcon = cifs_sb->tcon; if (file->private_data == NULL) { rc = -EBADF; @@ -1758,6 +1732,7 @@ ssize_t cifs_user_read(struct file *file, char __user *read_data, return rc; } open_file = file->private_data; + pTcon = tlink_tcon(open_file->tlink); if ((file->f_flags & O_ACCMODE) == O_WRONLY) cFYI(1, "attempting read on write only file instance"); @@ -1771,9 +1746,8 @@ ssize_t cifs_user_read(struct file *file, char __user *read_data, smb_read_data = NULL; while (rc == -EAGAIN) { int buf_type = CIFS_NO_BUFFER; - if ((open_file->invalidHandle) && - (!open_file->closePend)) { - rc = cifs_reopen_file(file, true); + if (open_file->invalidHandle) { + rc = cifs_reopen_file(open_file, true); if (rc != 0) break; } @@ -1831,7 +1805,6 @@ static ssize_t cifs_read(struct file *file, char *read_data, size_t read_size, xid = GetXid(); cifs_sb = CIFS_SB(file->f_path.dentry->d_sb); - pTcon = cifs_sb->tcon; if (file->private_data == NULL) { rc = -EBADF; @@ -1839,6 +1812,7 @@ static ssize_t cifs_read(struct file *file, char *read_data, size_t read_size, return rc; } open_file = file->private_data; + pTcon = tlink_tcon(open_file->tlink); if ((file->f_flags & O_ACCMODE) == O_WRONLY) cFYI(1, "attempting read on write only file instance"); @@ -1857,9 +1831,8 @@ static ssize_t cifs_read(struct file *file, char *read_data, size_t read_size, } rc = -EAGAIN; while (rc == -EAGAIN) { - if ((open_file->invalidHandle) && - (!open_file->closePend)) { - rc = cifs_reopen_file(file, true); + if (open_file->invalidHandle) { + rc = cifs_reopen_file(open_file, true); if (rc != 0) break; } @@ -1974,7 +1947,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping, } open_file = file->private_data; cifs_sb = CIFS_SB(file->f_path.dentry->d_sb); - pTcon = cifs_sb->tcon; + pTcon = tlink_tcon(open_file->tlink); /* * Reads as many pages as possible from fscache. Returns -ENOBUFS @@ -2022,9 +1995,8 @@ static int cifs_readpages(struct file *file, struct address_space *mapping, read_size, contig_pages); rc = -EAGAIN; while (rc == -EAGAIN) { - if ((open_file->invalidHandle) && - (!open_file->closePend)) { - rc = cifs_reopen_file(file, true); + if (open_file->invalidHandle) { + rc = cifs_reopen_file(open_file, true); if (rc != 0) break; } @@ -2173,18 +2145,14 @@ static int is_inode_writable(struct cifsInodeInfo *cifs_inode) { struct cifsFileInfo *open_file; - read_lock(&GlobalSMBSeslock); + spin_lock(&cifs_file_list_lock); list_for_each_entry(open_file, &cifs_inode->openFileList, flist) { - if (open_file->closePend) - continue; - if (open_file->pfile && - ((open_file->pfile->f_flags & O_RDWR) || - (open_file->pfile->f_flags & O_WRONLY))) { - read_unlock(&GlobalSMBSeslock); + if (OPEN_FMODE(open_file->f_flags) & FMODE_WRITE) { + spin_unlock(&cifs_file_list_lock); return 1; } } - read_unlock(&GlobalSMBSeslock); + spin_unlock(&cifs_file_list_lock); return 0; } @@ -2310,9 +2278,8 @@ void cifs_oplock_break(struct work_struct *work) { struct cifsFileInfo *cfile = container_of(work, struct cifsFileInfo, oplock_break); - struct inode *inode = cfile->pInode; + struct inode *inode = cfile->dentry->d_inode; struct cifsInodeInfo *cinode = CIFS_I(inode); - struct cifs_sb_info *cifs_sb = CIFS_SB(cfile->mnt->mnt_sb); int rc, waitrc = 0; if (inode && S_ISREG(inode->i_mode)) { @@ -2338,9 +2305,9 @@ void cifs_oplock_break(struct work_struct *work) * not bother sending an oplock release if session to server still is * disconnected since oplock already released by the server */ - if (!cfile->closePend && !cfile->oplock_break_cancelled) { - rc = CIFSSMBLock(0, cifs_sb->tcon, cfile->netfid, 0, 0, 0, 0, - LOCKING_ANDX_OPLOCK_RELEASE, false); + if (!cfile->oplock_break_cancelled) { + rc = CIFSSMBLock(0, tlink_tcon(cfile->tlink), cfile->netfid, 0, + 0, 0, 0, LOCKING_ANDX_OPLOCK_RELEASE, false); cFYI(1, "Oplock release rc = %d", rc); } @@ -2349,22 +2316,22 @@ void cifs_oplock_break(struct work_struct *work) * finished grabbing reference for us. Make sure it's done by * waiting for GlobalSMSSeslock. */ - write_lock(&GlobalSMBSeslock); - write_unlock(&GlobalSMBSeslock); + spin_lock(&cifs_file_list_lock); + spin_unlock(&cifs_file_list_lock); cifs_oplock_break_put(cfile); } void cifs_oplock_break_get(struct cifsFileInfo *cfile) { - mntget(cfile->mnt); + cifs_sb_active(cfile->dentry->d_sb); cifsFileInfo_get(cfile); } void cifs_oplock_break_put(struct cifsFileInfo *cfile) { - mntput(cfile->mnt); cifsFileInfo_put(cfile); + cifs_sb_deactive(cfile->dentry->d_sb); } const struct address_space_operations cifs_addr_ops = { diff --git a/fs/cifs/fscache.c b/fs/cifs/fscache.c index 9f3f5c4be161..a2ad94efcfe6 100644 --- a/fs/cifs/fscache.c +++ b/fs/cifs/fscache.c @@ -62,15 +62,15 @@ static void cifs_fscache_enable_inode_cookie(struct inode *inode) { struct cifsInodeInfo *cifsi = CIFS_I(inode); struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); + struct cifsTconInfo *tcon = cifs_sb_master_tcon(cifs_sb); if (cifsi->fscache) return; - cifsi->fscache = fscache_acquire_cookie(cifs_sb->tcon->fscache, - &cifs_fscache_inode_object_def, - cifsi); - cFYI(1, "CIFS: got FH cookie (0x%p/0x%p)", - cifs_sb->tcon->fscache, cifsi->fscache); + cifsi->fscache = fscache_acquire_cookie(tcon->fscache, + &cifs_fscache_inode_object_def, cifsi); + cFYI(1, "CIFS: got FH cookie (0x%p/0x%p)", tcon->fscache, + cifsi->fscache); } void cifs_fscache_release_inode_cookie(struct inode *inode) @@ -117,7 +117,8 @@ void cifs_fscache_reset_inode_cookie(struct inode *inode) /* retire the current fscache cache and get a new one */ fscache_relinquish_cookie(cifsi->fscache, 1); - cifsi->fscache = fscache_acquire_cookie(cifs_sb->tcon->fscache, + cifsi->fscache = fscache_acquire_cookie( + cifs_sb_master_tcon(cifs_sb)->fscache, &cifs_fscache_inode_object_def, cifsi); cFYI(1, "CIFS: new cookie 0x%p oldcookie 0x%p", diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 53cce8cc2224..94979309698a 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -52,7 +52,7 @@ static void cifs_set_ops(struct inode *inode, const bool is_dfs_referral) /* check if server can support readpages */ - if (cifs_sb->tcon->ses->server->maxBuf < + if (cifs_sb_master_tcon(cifs_sb)->ses->server->maxBuf < PAGE_CACHE_SIZE + MAX_CIFS_HDR_SIZE) inode->i_data.a_ops = &cifs_addr_ops_smallbuf; else @@ -288,8 +288,8 @@ int cifs_get_file_info_unix(struct file *filp) struct cifs_fattr fattr; struct inode *inode = filp->f_path.dentry->d_inode; struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); - struct cifsTconInfo *tcon = cifs_sb->tcon; struct cifsFileInfo *cfile = filp->private_data; + struct cifsTconInfo *tcon = tlink_tcon(cfile->tlink); xid = GetXid(); rc = CIFSSMBUnixQFileInfo(xid, tcon, cfile->netfid, &find_data); @@ -313,15 +313,21 @@ int cifs_get_inode_info_unix(struct inode **pinode, FILE_UNIX_BASIC_INFO find_data; struct cifs_fattr fattr; struct cifsTconInfo *tcon; + struct tcon_link *tlink; struct cifs_sb_info *cifs_sb = CIFS_SB(sb); - tcon = cifs_sb->tcon; cFYI(1, "Getting info on %s", full_path); + tlink = cifs_sb_tlink(cifs_sb); + if (IS_ERR(tlink)) + return PTR_ERR(tlink); + tcon = tlink_tcon(tlink); + /* could have done a find first instead but this returns more info */ rc = CIFSSMBUnixQPathInfo(xid, tcon, full_path, &find_data, cifs_sb->local_nls, cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR); + cifs_put_tlink(tlink); if (!rc) { cifs_unix_basic_to_fattr(&fattr, &find_data, cifs_sb); @@ -332,6 +338,13 @@ int cifs_get_inode_info_unix(struct inode **pinode, return rc; } + /* check for Minshall+French symlinks */ + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) { + int tmprc = CIFSCheckMFSymlink(&fattr, full_path, cifs_sb, xid); + if (tmprc) + cFYI(1, "CIFSCheckMFSymlink: %d", tmprc); + } + if (*pinode == NULL) { /* get new inode */ cifs_fill_uniqueid(sb, &fattr); @@ -353,7 +366,8 @@ cifs_sfu_type(struct cifs_fattr *fattr, const unsigned char *path, int rc; int oplock = 0; __u16 netfid; - struct cifsTconInfo *pTcon = cifs_sb->tcon; + struct tcon_link *tlink; + struct cifsTconInfo *tcon; char buf[24]; unsigned int bytes_read; char *pbuf; @@ -372,7 +386,12 @@ cifs_sfu_type(struct cifs_fattr *fattr, const unsigned char *path, return -EINVAL; /* EOPNOTSUPP? */ } - rc = CIFSSMBOpen(xid, pTcon, path, FILE_OPEN, GENERIC_READ, + tlink = cifs_sb_tlink(cifs_sb); + if (IS_ERR(tlink)) + return PTR_ERR(tlink); + tcon = tlink_tcon(tlink); + + rc = CIFSSMBOpen(xid, tcon, path, FILE_OPEN, GENERIC_READ, CREATE_NOT_DIR, &netfid, &oplock, NULL, cifs_sb->local_nls, cifs_sb->mnt_cifs_flags & @@ -380,7 +399,7 @@ cifs_sfu_type(struct cifs_fattr *fattr, const unsigned char *path, if (rc == 0) { int buf_type = CIFS_NO_BUFFER; /* Read header */ - rc = CIFSSMBRead(xid, pTcon, netfid, + rc = CIFSSMBRead(xid, tcon, netfid, 24 /* length */, 0 /* offset */, &bytes_read, &pbuf, &buf_type); if ((rc == 0) && (bytes_read >= 8)) { @@ -422,8 +441,9 @@ cifs_sfu_type(struct cifs_fattr *fattr, const unsigned char *path, fattr->cf_dtype = DT_REG; rc = -EOPNOTSUPP; /* or some unknown SFU type */ } - CIFSSMBClose(xid, pTcon, netfid); + CIFSSMBClose(xid, tcon, netfid); } + cifs_put_tlink(tlink); return rc; } @@ -441,11 +461,19 @@ static int cifs_sfu_mode(struct cifs_fattr *fattr, const unsigned char *path, ssize_t rc; char ea_value[4]; __u32 mode; + struct tcon_link *tlink; + struct cifsTconInfo *tcon; - rc = CIFSSMBQAllEAs(xid, cifs_sb->tcon, path, "SETFILEBITS", + tlink = cifs_sb_tlink(cifs_sb); + if (IS_ERR(tlink)) + return PTR_ERR(tlink); + tcon = tlink_tcon(tlink); + + rc = CIFSSMBQAllEAs(xid, tcon, path, "SETFILEBITS", ea_value, 4 /* size of buf */, cifs_sb->local_nls, cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR); + cifs_put_tlink(tlink); if (rc < 0) return (int)rc; else if (rc > 3) { @@ -468,6 +496,8 @@ static void cifs_all_info_to_fattr(struct cifs_fattr *fattr, FILE_ALL_INFO *info, struct cifs_sb_info *cifs_sb, bool adjust_tz) { + struct cifsTconInfo *tcon = cifs_sb_master_tcon(cifs_sb); + memset(fattr, 0, sizeof(*fattr)); fattr->cf_cifsattrs = le32_to_cpu(info->Attributes); if (info->DeletePending) @@ -482,8 +512,8 @@ cifs_all_info_to_fattr(struct cifs_fattr *fattr, FILE_ALL_INFO *info, fattr->cf_mtime = cifs_NTtimeToUnix(info->LastWriteTime); if (adjust_tz) { - fattr->cf_ctime.tv_sec += cifs_sb->tcon->ses->server->timeAdj; - fattr->cf_mtime.tv_sec += cifs_sb->tcon->ses->server->timeAdj; + fattr->cf_ctime.tv_sec += tcon->ses->server->timeAdj; + fattr->cf_mtime.tv_sec += tcon->ses->server->timeAdj; } fattr->cf_eof = le64_to_cpu(info->EndOfFile); @@ -515,8 +545,8 @@ int cifs_get_file_info(struct file *filp) struct cifs_fattr fattr; struct inode *inode = filp->f_path.dentry->d_inode; struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); - struct cifsTconInfo *tcon = cifs_sb->tcon; struct cifsFileInfo *cfile = filp->private_data; + struct cifsTconInfo *tcon = tlink_tcon(cfile->tlink); xid = GetXid(); rc = CIFSSMBQFileInfo(xid, tcon, cfile->netfid, &find_data); @@ -554,26 +584,33 @@ int cifs_get_inode_info(struct inode **pinode, { int rc = 0, tmprc; struct cifsTconInfo *pTcon; + struct tcon_link *tlink; struct cifs_sb_info *cifs_sb = CIFS_SB(sb); char *buf = NULL; bool adjustTZ = false; struct cifs_fattr fattr; - pTcon = cifs_sb->tcon; + tlink = cifs_sb_tlink(cifs_sb); + if (IS_ERR(tlink)) + return PTR_ERR(tlink); + pTcon = tlink_tcon(tlink); + cFYI(1, "Getting info on %s", full_path); if ((pfindData == NULL) && (*pinode != NULL)) { if (CIFS_I(*pinode)->clientCanCacheRead) { cFYI(1, "No need to revalidate cached inode sizes"); - return rc; + goto cgii_exit; } } /* if file info not passed in then get it from server */ if (pfindData == NULL) { buf = kmalloc(sizeof(FILE_ALL_INFO), GFP_KERNEL); - if (buf == NULL) - return -ENOMEM; + if (buf == NULL) { + rc = -ENOMEM; + goto cgii_exit; + } pfindData = (FILE_ALL_INFO *)buf; /* could do find first instead but this returns more info */ @@ -661,6 +698,13 @@ int cifs_get_inode_info(struct inode **pinode, if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL) cifs_sfu_mode(&fattr, full_path, cifs_sb, xid); + /* check for Minshall+French symlinks */ + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) { + tmprc = CIFSCheckMFSymlink(&fattr, full_path, cifs_sb, xid); + if (tmprc) + cFYI(1, "CIFSCheckMFSymlink: %d", tmprc); + } + if (!*pinode) { *pinode = cifs_iget(sb, &fattr); if (!*pinode) @@ -671,6 +715,7 @@ int cifs_get_inode_info(struct inode **pinode, cgii_exit: kfree(buf); + cifs_put_tlink(tlink); return rc; } @@ -683,6 +728,7 @@ char *cifs_build_path_to_root(struct cifs_sb_info *cifs_sb) int pplen = cifs_sb->prepathlen; int dfsplen; char *full_path = NULL; + struct cifsTconInfo *tcon = cifs_sb_master_tcon(cifs_sb); /* if no prefix path, simply set path to the root of share to "" */ if (pplen == 0) { @@ -692,8 +738,8 @@ char *cifs_build_path_to_root(struct cifs_sb_info *cifs_sb) return full_path; } - if (cifs_sb->tcon && (cifs_sb->tcon->Flags & SMB_SHARE_IS_IN_DFS)) - dfsplen = strnlen(cifs_sb->tcon->treeName, MAX_TREE_SIZE + 1); + if (tcon->Flags & SMB_SHARE_IS_IN_DFS) + dfsplen = strnlen(tcon->treeName, MAX_TREE_SIZE + 1); else dfsplen = 0; @@ -702,7 +748,7 @@ char *cifs_build_path_to_root(struct cifs_sb_info *cifs_sb) return full_path; if (dfsplen) { - strncpy(full_path, cifs_sb->tcon->treeName, dfsplen); + strncpy(full_path, tcon->treeName, dfsplen); /* switch slash direction in prepath depending on whether * windows or posix style path names */ @@ -818,18 +864,18 @@ retry_iget5_locked: struct inode *cifs_root_iget(struct super_block *sb, unsigned long ino) { int xid; - struct cifs_sb_info *cifs_sb; + struct cifs_sb_info *cifs_sb = CIFS_SB(sb); struct inode *inode = NULL; long rc; char *full_path; + struct cifsTconInfo *tcon = cifs_sb_master_tcon(cifs_sb); - cifs_sb = CIFS_SB(sb); full_path = cifs_build_path_to_root(cifs_sb); if (full_path == NULL) return ERR_PTR(-ENOMEM); xid = GetXid(); - if (cifs_sb->tcon->unix_ext) + if (tcon->unix_ext) rc = cifs_get_inode_info_unix(&inode, full_path, sb, xid); else rc = cifs_get_inode_info(&inode, full_path, NULL, sb, @@ -840,10 +886,10 @@ struct inode *cifs_root_iget(struct super_block *sb, unsigned long ino) #ifdef CONFIG_CIFS_FSCACHE /* populate tcon->resource_id */ - cifs_sb->tcon->resource_id = CIFS_I(inode)->uniqueid; + tcon->resource_id = CIFS_I(inode)->uniqueid; #endif - if (rc && cifs_sb->tcon->ipc) { + if (rc && tcon->ipc) { cFYI(1, "ipc connection - fake read inode"); inode->i_mode |= S_IFDIR; inode->i_nlink = 2; @@ -879,7 +925,8 @@ cifs_set_file_info(struct inode *inode, struct iattr *attrs, int xid, struct cifsFileInfo *open_file; struct cifsInodeInfo *cifsInode = CIFS_I(inode); struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); - struct cifsTconInfo *pTcon = cifs_sb->tcon; + struct tcon_link *tlink = NULL; + struct cifsTconInfo *pTcon; FILE_BASIC_INFO info_buf; if (attrs == NULL) @@ -918,13 +965,22 @@ cifs_set_file_info(struct inode *inode, struct iattr *attrs, int xid, /* * If the file is already open for write, just use that fileid */ - open_file = find_writable_file(cifsInode); + open_file = find_writable_file(cifsInode, true); if (open_file) { netfid = open_file->netfid; netpid = open_file->pid; + pTcon = tlink_tcon(open_file->tlink); goto set_via_filehandle; } + tlink = cifs_sb_tlink(cifs_sb); + if (IS_ERR(tlink)) { + rc = PTR_ERR(tlink); + tlink = NULL; + goto out; + } + pTcon = tlink_tcon(tlink); + /* * NT4 apparently returns success on this call, but it doesn't * really work. @@ -968,6 +1024,8 @@ set_via_filehandle: else cifsFileInfo_put(open_file); out: + if (tlink != NULL) + cifs_put_tlink(tlink); return rc; } @@ -985,10 +1043,16 @@ cifs_rename_pending_delete(char *full_path, struct dentry *dentry, int xid) struct inode *inode = dentry->d_inode; struct cifsInodeInfo *cifsInode = CIFS_I(inode); struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); - struct cifsTconInfo *tcon = cifs_sb->tcon; + struct tcon_link *tlink; + struct cifsTconInfo *tcon; __u32 dosattr, origattr; FILE_BASIC_INFO *info_buf = NULL; + tlink = cifs_sb_tlink(cifs_sb); + if (IS_ERR(tlink)) + return PTR_ERR(tlink); + tcon = tlink_tcon(tlink); + rc = CIFSSMBOpen(xid, tcon, full_path, FILE_OPEN, DELETE|FILE_WRITE_ATTRIBUTES, CREATE_NOT_DIR, &netfid, &oplock, NULL, cifs_sb->local_nls, @@ -1057,6 +1121,7 @@ out_close: CIFSSMBClose(xid, tcon, netfid); out: kfree(info_buf); + cifs_put_tlink(tlink); return rc; /* @@ -1096,12 +1161,18 @@ int cifs_unlink(struct inode *dir, struct dentry *dentry) struct cifsInodeInfo *cifs_inode; struct super_block *sb = dir->i_sb; struct cifs_sb_info *cifs_sb = CIFS_SB(sb); - struct cifsTconInfo *tcon = cifs_sb->tcon; + struct tcon_link *tlink; + struct cifsTconInfo *tcon; struct iattr *attrs = NULL; __u32 dosattr = 0, origattr = 0; cFYI(1, "cifs_unlink, dir=0x%p, dentry=0x%p", dir, dentry); + tlink = cifs_sb_tlink(cifs_sb); + if (IS_ERR(tlink)) + return PTR_ERR(tlink); + tcon = tlink_tcon(tlink); + xid = GetXid(); /* Unlink can be called from rename so we can not take the @@ -1109,8 +1180,7 @@ int cifs_unlink(struct inode *dir, struct dentry *dentry) full_path = build_path_from_dentry(dentry); if (full_path == NULL) { rc = -ENOMEM; - FreeXid(xid); - return rc; + goto unlink_out; } if ((tcon->ses->capabilities & CAP_UNIX) && @@ -1176,10 +1246,11 @@ out_reval: dir->i_ctime = dir->i_mtime = current_fs_time(sb); cifs_inode = CIFS_I(dir); CIFS_I(dir)->time = 0; /* force revalidate of dir as well */ - +unlink_out: kfree(full_path); kfree(attrs); FreeXid(xid); + cifs_put_tlink(tlink); return rc; } @@ -1188,6 +1259,7 @@ int cifs_mkdir(struct inode *inode, struct dentry *direntry, int mode) int rc = 0, tmprc; int xid; struct cifs_sb_info *cifs_sb; + struct tcon_link *tlink; struct cifsTconInfo *pTcon; char *full_path = NULL; struct inode *newinode = NULL; @@ -1195,16 +1267,18 @@ int cifs_mkdir(struct inode *inode, struct dentry *direntry, int mode) cFYI(1, "In cifs_mkdir, mode = 0x%x inode = 0x%p", mode, inode); - xid = GetXid(); - cifs_sb = CIFS_SB(inode->i_sb); - pTcon = cifs_sb->tcon; + tlink = cifs_sb_tlink(cifs_sb); + if (IS_ERR(tlink)) + return PTR_ERR(tlink); + pTcon = tlink_tcon(tlink); + + xid = GetXid(); full_path = build_path_from_dentry(direntry); if (full_path == NULL) { rc = -ENOMEM; - FreeXid(xid); - return rc; + goto mkdir_out; } if ((pTcon->ses->capabilities & CAP_UNIX) && @@ -1362,6 +1436,7 @@ mkdir_get_info: mkdir_out: kfree(full_path); FreeXid(xid); + cifs_put_tlink(tlink); return rc; } @@ -1370,6 +1445,7 @@ int cifs_rmdir(struct inode *inode, struct dentry *direntry) int rc = 0; int xid; struct cifs_sb_info *cifs_sb; + struct tcon_link *tlink; struct cifsTconInfo *pTcon; char *full_path = NULL; struct cifsInodeInfo *cifsInode; @@ -1378,18 +1454,23 @@ int cifs_rmdir(struct inode *inode, struct dentry *direntry) xid = GetXid(); - cifs_sb = CIFS_SB(inode->i_sb); - pTcon = cifs_sb->tcon; - full_path = build_path_from_dentry(direntry); if (full_path == NULL) { rc = -ENOMEM; - FreeXid(xid); - return rc; + goto rmdir_exit; } + cifs_sb = CIFS_SB(inode->i_sb); + tlink = cifs_sb_tlink(cifs_sb); + if (IS_ERR(tlink)) { + rc = PTR_ERR(tlink); + goto rmdir_exit; + } + pTcon = tlink_tcon(tlink); + rc = CIFSSMBRmDir(xid, pTcon, full_path, cifs_sb->local_nls, cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR); + cifs_put_tlink(tlink); if (!rc) { drop_nlink(inode); @@ -1410,6 +1491,7 @@ int cifs_rmdir(struct inode *inode, struct dentry *direntry) direntry->d_inode->i_ctime = inode->i_ctime = inode->i_mtime = current_fs_time(inode->i_sb); +rmdir_exit: kfree(full_path); FreeXid(xid); return rc; @@ -1420,10 +1502,16 @@ cifs_do_rename(int xid, struct dentry *from_dentry, const char *fromPath, struct dentry *to_dentry, const char *toPath) { struct cifs_sb_info *cifs_sb = CIFS_SB(from_dentry->d_sb); - struct cifsTconInfo *pTcon = cifs_sb->tcon; + struct tcon_link *tlink; + struct cifsTconInfo *pTcon; __u16 srcfid; int oplock, rc; + tlink = cifs_sb_tlink(cifs_sb); + if (IS_ERR(tlink)) + return PTR_ERR(tlink); + pTcon = tlink_tcon(tlink); + /* try path-based rename first */ rc = CIFSSMBRename(xid, pTcon, fromPath, toPath, cifs_sb->local_nls, cifs_sb->mnt_cifs_flags & @@ -1435,11 +1523,11 @@ cifs_do_rename(int xid, struct dentry *from_dentry, const char *fromPath, * rename by filehandle to various Windows servers. */ if (rc == 0 || rc != -ETXTBSY) - return rc; + goto do_rename_exit; /* open-file renames don't work across directories */ if (to_dentry->d_parent != from_dentry->d_parent) - return rc; + goto do_rename_exit; /* open the file to be renamed -- we need DELETE perms */ rc = CIFSSMBOpen(xid, pTcon, fromPath, FILE_OPEN, DELETE, @@ -1455,7 +1543,8 @@ cifs_do_rename(int xid, struct dentry *from_dentry, const char *fromPath, CIFSSMBClose(xid, pTcon, srcfid); } - +do_rename_exit: + cifs_put_tlink(tlink); return rc; } @@ -1465,13 +1554,17 @@ int cifs_rename(struct inode *source_dir, struct dentry *source_dentry, char *fromName = NULL; char *toName = NULL; struct cifs_sb_info *cifs_sb; + struct tcon_link *tlink; struct cifsTconInfo *tcon; FILE_UNIX_BASIC_INFO *info_buf_source = NULL; FILE_UNIX_BASIC_INFO *info_buf_target; int xid, rc, tmprc; cifs_sb = CIFS_SB(source_dir->i_sb); - tcon = cifs_sb->tcon; + tlink = cifs_sb_tlink(cifs_sb); + if (IS_ERR(tlink)) + return PTR_ERR(tlink); + tcon = tlink_tcon(tlink); xid = GetXid(); @@ -1547,6 +1640,7 @@ cifs_rename_exit: kfree(fromName); kfree(toName); FreeXid(xid); + cifs_put_tlink(tlink); return rc; } @@ -1599,11 +1693,12 @@ int cifs_revalidate_file(struct file *filp) { int rc = 0; struct inode *inode = filp->f_path.dentry->d_inode; + struct cifsFileInfo *cfile = (struct cifsFileInfo *) filp->private_data; if (!cifs_inode_needs_reval(inode)) goto check_inval; - if (CIFS_SB(inode->i_sb)->tcon->unix_ext) + if (tlink_tcon(cfile->tlink)->unix_ext) rc = cifs_get_file_info_unix(filp); else rc = cifs_get_file_info(filp); @@ -1644,7 +1739,7 @@ int cifs_revalidate_dentry(struct dentry *dentry) "jiffies %ld", full_path, inode, inode->i_count.counter, dentry, dentry->d_time, jiffies); - if (CIFS_SB(sb)->tcon->unix_ext) + if (cifs_sb_master_tcon(CIFS_SB(sb))->unix_ext) rc = cifs_get_inode_info_unix(&inode, full_path, sb, xid); else rc = cifs_get_inode_info(&inode, full_path, NULL, sb, @@ -1660,13 +1755,29 @@ check_inval: } int cifs_getattr(struct vfsmount *mnt, struct dentry *dentry, - struct kstat *stat) + struct kstat *stat) { + struct cifs_sb_info *cifs_sb = CIFS_SB(dentry->d_sb); + struct cifsTconInfo *tcon = cifs_sb_master_tcon(cifs_sb); int err = cifs_revalidate_dentry(dentry); + if (!err) { generic_fillattr(dentry->d_inode, stat); stat->blksize = CIFS_MAX_MSGSIZE; stat->ino = CIFS_I(dentry->d_inode)->uniqueid; + + /* + * If on a multiuser mount without unix extensions, and the + * admin hasn't overridden them, set the ownership to the + * fsuid/fsgid of the current process. + */ + if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER) && + !tcon->unix_ext) { + if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_UID)) + stat->uid = current_fsuid(); + if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_GID)) + stat->gid = current_fsgid(); + } } return err; } @@ -1708,7 +1819,8 @@ cifs_set_file_size(struct inode *inode, struct iattr *attrs, struct cifsFileInfo *open_file; struct cifsInodeInfo *cifsInode = CIFS_I(inode); struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); - struct cifsTconInfo *pTcon = cifs_sb->tcon; + struct tcon_link *tlink = NULL; + struct cifsTconInfo *pTcon = NULL; /* * To avoid spurious oplock breaks from server, in the case of @@ -1719,10 +1831,11 @@ cifs_set_file_size(struct inode *inode, struct iattr *attrs, * writebehind data than the SMB timeout for the SetPathInfo * request would allow */ - open_file = find_writable_file(cifsInode); + open_file = find_writable_file(cifsInode, true); if (open_file) { __u16 nfid = open_file->netfid; __u32 npid = open_file->pid; + pTcon = tlink_tcon(open_file->tlink); rc = CIFSSMBSetFileSize(xid, pTcon, attrs->ia_size, nfid, npid, false); cifsFileInfo_put(open_file); @@ -1737,6 +1850,13 @@ cifs_set_file_size(struct inode *inode, struct iattr *attrs, rc = -EINVAL; if (rc != 0) { + if (pTcon == NULL) { + tlink = cifs_sb_tlink(cifs_sb); + if (IS_ERR(tlink)) + return PTR_ERR(tlink); + pTcon = tlink_tcon(tlink); + } + /* Set file size by pathname rather than by handle either because no valid, writeable file handle for it was found or because there was an error setting @@ -1766,6 +1886,8 @@ cifs_set_file_size(struct inode *inode, struct iattr *attrs, CIFSSMBClose(xid, pTcon, netfid); } } + if (tlink) + cifs_put_tlink(tlink); } if (rc == 0) { @@ -1786,7 +1908,8 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs) struct inode *inode = direntry->d_inode; struct cifsInodeInfo *cifsInode = CIFS_I(inode); struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); - struct cifsTconInfo *pTcon = cifs_sb->tcon; + struct tcon_link *tlink; + struct cifsTconInfo *pTcon; struct cifs_unix_set_info_args *args = NULL; struct cifsFileInfo *open_file; @@ -1873,17 +1996,25 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs) args->ctime = NO_CHANGE_64; args->device = 0; - open_file = find_writable_file(cifsInode); + open_file = find_writable_file(cifsInode, true); if (open_file) { u16 nfid = open_file->netfid; u32 npid = open_file->pid; + pTcon = tlink_tcon(open_file->tlink); rc = CIFSSMBUnixSetFileInfo(xid, pTcon, args, nfid, npid); cifsFileInfo_put(open_file); } else { + tlink = cifs_sb_tlink(cifs_sb); + if (IS_ERR(tlink)) { + rc = PTR_ERR(tlink); + goto out; + } + pTcon = tlink_tcon(tlink); rc = CIFSSMBUnixSetPathInfo(xid, pTcon, full_path, args, cifs_sb->local_nls, cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR); + cifs_put_tlink(tlink); } if (rc) @@ -2064,7 +2195,7 @@ cifs_setattr(struct dentry *direntry, struct iattr *attrs) { struct inode *inode = direntry->d_inode; struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); - struct cifsTconInfo *pTcon = cifs_sb->tcon; + struct cifsTconInfo *pTcon = cifs_sb_master_tcon(cifs_sb); if (pTcon->unix_ext) return cifs_setattr_unix(direntry, attrs); diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c index 9d38a71c8e14..077bf756f342 100644 --- a/fs/cifs/ioctl.c +++ b/fs/cifs/ioctl.c @@ -37,11 +37,11 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg) int xid; struct cifs_sb_info *cifs_sb; #ifdef CONFIG_CIFS_POSIX + struct cifsFileInfo *pSMBFile = filep->private_data; + struct cifsTconInfo *tcon = tlink_tcon(pSMBFile->tlink); __u64 ExtAttrBits = 0; __u64 ExtAttrMask = 0; - __u64 caps; - struct cifsTconInfo *tcon; - struct cifsFileInfo *pSMBFile = filep->private_data; + __u64 caps = le64_to_cpu(tcon->fsUnixInfo.Capability); #endif /* CONFIG_CIFS_POSIX */ xid = GetXid(); @@ -50,17 +50,6 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg) cifs_sb = CIFS_SB(inode->i_sb); -#ifdef CONFIG_CIFS_POSIX - tcon = cifs_sb->tcon; - if (tcon) - caps = le64_to_cpu(tcon->fsUnixInfo.Capability); - else { - rc = -EIO; - FreeXid(xid); - return -EIO; - } -#endif /* CONFIG_CIFS_POSIX */ - switch (command) { case CIFS_IOC_CHECKUMOUNT: cFYI(1, "User unmount attempted"); diff --git a/fs/cifs/link.c b/fs/cifs/link.c index 473ca8033656..85cdbf831e7b 100644 --- a/fs/cifs/link.c +++ b/fs/cifs/link.c @@ -28,6 +28,296 @@ #include "cifsproto.h" #include "cifs_debug.h" #include "cifs_fs_sb.h" +#include "md5.h" + +#define CIFS_MF_SYMLINK_LEN_OFFSET (4+1) +#define CIFS_MF_SYMLINK_MD5_OFFSET (CIFS_MF_SYMLINK_LEN_OFFSET+(4+1)) +#define CIFS_MF_SYMLINK_LINK_OFFSET (CIFS_MF_SYMLINK_MD5_OFFSET+(32+1)) +#define CIFS_MF_SYMLINK_LINK_MAXLEN (1024) +#define CIFS_MF_SYMLINK_FILE_SIZE \ + (CIFS_MF_SYMLINK_LINK_OFFSET + CIFS_MF_SYMLINK_LINK_MAXLEN) + +#define CIFS_MF_SYMLINK_LEN_FORMAT "XSym\n%04u\n" +#define CIFS_MF_SYMLINK_MD5_FORMAT \ + "%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x\n" +#define CIFS_MF_SYMLINK_MD5_ARGS(md5_hash) \ + md5_hash[0], md5_hash[1], md5_hash[2], md5_hash[3], \ + md5_hash[4], md5_hash[5], md5_hash[6], md5_hash[7], \ + md5_hash[8], md5_hash[9], md5_hash[10], md5_hash[11],\ + md5_hash[12], md5_hash[13], md5_hash[14], md5_hash[15] + +static int +CIFSParseMFSymlink(const u8 *buf, + unsigned int buf_len, + unsigned int *_link_len, + char **_link_str) +{ + int rc; + unsigned int link_len; + const char *md5_str1; + const char *link_str; + struct MD5Context md5_ctx; + u8 md5_hash[16]; + char md5_str2[34]; + + if (buf_len != CIFS_MF_SYMLINK_FILE_SIZE) + return -EINVAL; + + md5_str1 = (const char *)&buf[CIFS_MF_SYMLINK_MD5_OFFSET]; + link_str = (const char *)&buf[CIFS_MF_SYMLINK_LINK_OFFSET]; + + rc = sscanf(buf, CIFS_MF_SYMLINK_LEN_FORMAT, &link_len); + if (rc != 1) + return -EINVAL; + + cifs_MD5_init(&md5_ctx); + cifs_MD5_update(&md5_ctx, (const u8 *)link_str, link_len); + cifs_MD5_final(md5_hash, &md5_ctx); + + snprintf(md5_str2, sizeof(md5_str2), + CIFS_MF_SYMLINK_MD5_FORMAT, + CIFS_MF_SYMLINK_MD5_ARGS(md5_hash)); + + if (strncmp(md5_str1, md5_str2, 17) != 0) + return -EINVAL; + + if (_link_str) { + *_link_str = kstrndup(link_str, link_len, GFP_KERNEL); + if (!*_link_str) + return -ENOMEM; + } + + *_link_len = link_len; + return 0; +} + +static int +CIFSFormatMFSymlink(u8 *buf, unsigned int buf_len, const char *link_str) +{ + unsigned int link_len; + unsigned int ofs; + struct MD5Context md5_ctx; + u8 md5_hash[16]; + + if (buf_len != CIFS_MF_SYMLINK_FILE_SIZE) + return -EINVAL; + + link_len = strlen(link_str); + + if (link_len > CIFS_MF_SYMLINK_LINK_MAXLEN) + return -ENAMETOOLONG; + + cifs_MD5_init(&md5_ctx); + cifs_MD5_update(&md5_ctx, (const u8 *)link_str, link_len); + cifs_MD5_final(md5_hash, &md5_ctx); + + snprintf(buf, buf_len, + CIFS_MF_SYMLINK_LEN_FORMAT CIFS_MF_SYMLINK_MD5_FORMAT, + link_len, + CIFS_MF_SYMLINK_MD5_ARGS(md5_hash)); + + ofs = CIFS_MF_SYMLINK_LINK_OFFSET; + memcpy(buf + ofs, link_str, link_len); + + ofs += link_len; + if (ofs < CIFS_MF_SYMLINK_FILE_SIZE) { + buf[ofs] = '\n'; + ofs++; + } + + while (ofs < CIFS_MF_SYMLINK_FILE_SIZE) { + buf[ofs] = ' '; + ofs++; + } + + return 0; +} + +static int +CIFSCreateMFSymLink(const int xid, struct cifsTconInfo *tcon, + const char *fromName, const char *toName, + const struct nls_table *nls_codepage, int remap) +{ + int rc; + int oplock = 0; + __u16 netfid = 0; + u8 *buf; + unsigned int bytes_written = 0; + + buf = kmalloc(CIFS_MF_SYMLINK_FILE_SIZE, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + rc = CIFSFormatMFSymlink(buf, CIFS_MF_SYMLINK_FILE_SIZE, toName); + if (rc != 0) { + kfree(buf); + return rc; + } + + rc = CIFSSMBOpen(xid, tcon, fromName, FILE_CREATE, GENERIC_WRITE, + CREATE_NOT_DIR, &netfid, &oplock, NULL, + nls_codepage, remap); + if (rc != 0) { + kfree(buf); + return rc; + } + + rc = CIFSSMBWrite(xid, tcon, netfid, + CIFS_MF_SYMLINK_FILE_SIZE /* length */, + 0 /* offset */, + &bytes_written, buf, NULL, 0); + CIFSSMBClose(xid, tcon, netfid); + kfree(buf); + if (rc != 0) + return rc; + + if (bytes_written != CIFS_MF_SYMLINK_FILE_SIZE) + return -EIO; + + return 0; +} + +static int +CIFSQueryMFSymLink(const int xid, struct cifsTconInfo *tcon, + const unsigned char *searchName, char **symlinkinfo, + const struct nls_table *nls_codepage, int remap) +{ + int rc; + int oplock = 0; + __u16 netfid = 0; + u8 *buf; + char *pbuf; + unsigned int bytes_read = 0; + int buf_type = CIFS_NO_BUFFER; + unsigned int link_len = 0; + FILE_ALL_INFO file_info; + + rc = CIFSSMBOpen(xid, tcon, searchName, FILE_OPEN, GENERIC_READ, + CREATE_NOT_DIR, &netfid, &oplock, &file_info, + nls_codepage, remap); + if (rc != 0) + return rc; + + if (file_info.EndOfFile != CIFS_MF_SYMLINK_FILE_SIZE) { + CIFSSMBClose(xid, tcon, netfid); + /* it's not a symlink */ + return -EINVAL; + } + + buf = kmalloc(CIFS_MF_SYMLINK_FILE_SIZE, GFP_KERNEL); + if (!buf) + return -ENOMEM; + pbuf = buf; + + rc = CIFSSMBRead(xid, tcon, netfid, + CIFS_MF_SYMLINK_FILE_SIZE /* length */, + 0 /* offset */, + &bytes_read, &pbuf, &buf_type); + CIFSSMBClose(xid, tcon, netfid); + if (rc != 0) { + kfree(buf); + return rc; + } + + rc = CIFSParseMFSymlink(buf, bytes_read, &link_len, symlinkinfo); + kfree(buf); + if (rc != 0) + return rc; + + return 0; +} + +bool +CIFSCouldBeMFSymlink(const struct cifs_fattr *fattr) +{ + if (!(fattr->cf_mode & S_IFREG)) + /* it's not a symlink */ + return false; + + if (fattr->cf_eof != CIFS_MF_SYMLINK_FILE_SIZE) + /* it's not a symlink */ + return false; + + return true; +} + +int +CIFSCheckMFSymlink(struct cifs_fattr *fattr, + const unsigned char *path, + struct cifs_sb_info *cifs_sb, int xid) +{ + int rc; + int oplock = 0; + __u16 netfid = 0; + struct tcon_link *tlink; + struct cifsTconInfo *pTcon; + u8 *buf; + char *pbuf; + unsigned int bytes_read = 0; + int buf_type = CIFS_NO_BUFFER; + unsigned int link_len = 0; + FILE_ALL_INFO file_info; + + if (!CIFSCouldBeMFSymlink(fattr)) + /* it's not a symlink */ + return 0; + + tlink = cifs_sb_tlink(cifs_sb); + if (IS_ERR(tlink)) + return PTR_ERR(tlink); + pTcon = tlink_tcon(tlink); + + rc = CIFSSMBOpen(xid, pTcon, path, FILE_OPEN, GENERIC_READ, + CREATE_NOT_DIR, &netfid, &oplock, &file_info, + cifs_sb->local_nls, + cifs_sb->mnt_cifs_flags & + CIFS_MOUNT_MAP_SPECIAL_CHR); + if (rc != 0) + goto out; + + if (file_info.EndOfFile != CIFS_MF_SYMLINK_FILE_SIZE) { + CIFSSMBClose(xid, pTcon, netfid); + /* it's not a symlink */ + goto out; + } + + buf = kmalloc(CIFS_MF_SYMLINK_FILE_SIZE, GFP_KERNEL); + if (!buf) { + rc = -ENOMEM; + goto out; + } + pbuf = buf; + + rc = CIFSSMBRead(xid, pTcon, netfid, + CIFS_MF_SYMLINK_FILE_SIZE /* length */, + 0 /* offset */, + &bytes_read, &pbuf, &buf_type); + CIFSSMBClose(xid, pTcon, netfid); + if (rc != 0) { + kfree(buf); + goto out; + } + + rc = CIFSParseMFSymlink(buf, bytes_read, &link_len, NULL); + kfree(buf); + if (rc == -EINVAL) { + /* it's not a symlink */ + rc = 0; + goto out; + } + + if (rc != 0) + goto out; + + /* it is a symlink */ + fattr->cf_eof = link_len; + fattr->cf_mode &= ~S_IFMT; + fattr->cf_mode |= S_IFLNK | S_IRWXU | S_IRWXG | S_IRWXO; + fattr->cf_dtype = DT_LNK; +out: + cifs_put_tlink(tlink); + return rc; +} int cifs_hardlink(struct dentry *old_file, struct inode *inode, @@ -37,17 +327,17 @@ cifs_hardlink(struct dentry *old_file, struct inode *inode, int xid; char *fromName = NULL; char *toName = NULL; - struct cifs_sb_info *cifs_sb_target; + struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); + struct tcon_link *tlink; struct cifsTconInfo *pTcon; struct cifsInodeInfo *cifsInode; - xid = GetXid(); - - cifs_sb_target = CIFS_SB(inode->i_sb); - pTcon = cifs_sb_target->tcon; + tlink = cifs_sb_tlink(cifs_sb); + if (IS_ERR(tlink)) + return PTR_ERR(tlink); + pTcon = tlink_tcon(tlink); -/* No need to check for cross device links since server will do that - BB note DFS case in future though (when we may have to check) */ + xid = GetXid(); fromName = build_path_from_dentry(old_file); toName = build_path_from_dentry(direntry); @@ -56,16 +346,15 @@ cifs_hardlink(struct dentry *old_file, struct inode *inode, goto cifs_hl_exit; } -/* if (cifs_sb_target->tcon->ses->capabilities & CAP_UNIX)*/ if (pTcon->unix_ext) rc = CIFSUnixCreateHardLink(xid, pTcon, fromName, toName, - cifs_sb_target->local_nls, - cifs_sb_target->mnt_cifs_flags & + cifs_sb->local_nls, + cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR); else { rc = CIFSCreateHardLink(xid, pTcon, fromName, toName, - cifs_sb_target->local_nls, - cifs_sb_target->mnt_cifs_flags & + cifs_sb->local_nls, + cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR); if ((rc == -EIO) || (rc == -EINVAL)) rc = -EOPNOTSUPP; @@ -101,6 +390,7 @@ cifs_hl_exit: kfree(fromName); kfree(toName); FreeXid(xid); + cifs_put_tlink(tlink); return rc; } @@ -113,10 +403,19 @@ cifs_follow_link(struct dentry *direntry, struct nameidata *nd) char *full_path = NULL; char *target_path = NULL; struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); - struct cifsTconInfo *tcon = cifs_sb->tcon; + struct tcon_link *tlink = NULL; + struct cifsTconInfo *tcon; xid = GetXid(); + tlink = cifs_sb_tlink(cifs_sb); + if (IS_ERR(tlink)) { + rc = PTR_ERR(tlink); + tlink = NULL; + goto out; + } + tcon = tlink_tcon(tlink); + /* * For now, we just handle symlinks with unix extensions enabled. * Eventually we should handle NTFS reparse points, and MacOS @@ -130,7 +429,8 @@ cifs_follow_link(struct dentry *direntry, struct nameidata *nd) * but there doesn't seem to be any harm in allowing the client to * read them. */ - if (!(tcon->ses->capabilities & CAP_UNIX)) { + if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) + && !(tcon->ses->capabilities & CAP_UNIX)) { rc = -EACCES; goto out; } @@ -141,8 +441,21 @@ cifs_follow_link(struct dentry *direntry, struct nameidata *nd) cFYI(1, "Full path: %s inode = 0x%p", full_path, inode); - rc = CIFSSMBUnixQuerySymLink(xid, tcon, full_path, &target_path, - cifs_sb->local_nls); + rc = -EACCES; + /* + * First try Minshall+French Symlinks, if configured + * and fallback to UNIX Extensions Symlinks. + */ + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) + rc = CIFSQueryMFSymLink(xid, tcon, full_path, &target_path, + cifs_sb->local_nls, + cifs_sb->mnt_cifs_flags & + CIFS_MOUNT_MAP_SPECIAL_CHR); + + if ((rc != 0) && (tcon->ses->capabilities & CAP_UNIX)) + rc = CIFSSMBUnixQuerySymLink(xid, tcon, full_path, &target_path, + cifs_sb->local_nls); + kfree(full_path); out: if (rc != 0) { @@ -151,6 +464,8 @@ out: } FreeXid(xid); + if (tlink) + cifs_put_tlink(tlink); nd_set_link(nd, target_path); return NULL; } @@ -160,29 +475,37 @@ cifs_symlink(struct inode *inode, struct dentry *direntry, const char *symname) { int rc = -EOPNOTSUPP; int xid; - struct cifs_sb_info *cifs_sb; + struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); + struct tcon_link *tlink; struct cifsTconInfo *pTcon; char *full_path = NULL; struct inode *newinode = NULL; xid = GetXid(); - cifs_sb = CIFS_SB(inode->i_sb); - pTcon = cifs_sb->tcon; + tlink = cifs_sb_tlink(cifs_sb); + if (IS_ERR(tlink)) { + rc = PTR_ERR(tlink); + goto symlink_exit; + } + pTcon = tlink_tcon(tlink); full_path = build_path_from_dentry(direntry); - if (full_path == NULL) { rc = -ENOMEM; - FreeXid(xid); - return rc; + goto symlink_exit; } cFYI(1, "Full path: %s", full_path); cFYI(1, "symname is %s", symname); /* BB what if DFS and this volume is on different share? BB */ - if (pTcon->unix_ext) + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) + rc = CIFSCreateMFSymLink(xid, pTcon, full_path, symname, + cifs_sb->local_nls, + cifs_sb->mnt_cifs_flags & + CIFS_MOUNT_MAP_SPECIAL_CHR); + else if (pTcon->unix_ext) rc = CIFSUnixCreateSymLink(xid, pTcon, full_path, symname, cifs_sb->local_nls); /* else @@ -208,8 +531,9 @@ cifs_symlink(struct inode *inode, struct dentry *direntry, const char *symname) d_instantiate(direntry, newinode); } } - +symlink_exit: kfree(full_path); + cifs_put_tlink(tlink); FreeXid(xid); return rc; } diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index 3ccadc1326d6..1c681f6a6803 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -347,7 +347,7 @@ header_assemble(struct smb_hdr *buffer, char smb_command /* command */ , if (current_fsuid() != treeCon->ses->linux_uid) { cFYI(1, "Multiuser mode and UID " "did not match tcon uid"); - read_lock(&cifs_tcp_ses_lock); + spin_lock(&cifs_tcp_ses_lock); list_for_each(temp_item, &treeCon->ses->server->smb_ses_list) { ses = list_entry(temp_item, struct cifsSesInfo, smb_ses_list); if (ses->linux_uid == current_fsuid()) { @@ -361,7 +361,7 @@ header_assemble(struct smb_hdr *buffer, char smb_command /* command */ , } } } - read_unlock(&cifs_tcp_ses_lock); + spin_unlock(&cifs_tcp_ses_lock); } } } @@ -551,7 +551,7 @@ is_valid_oplock_break(struct smb_hdr *buf, struct TCP_Server_Info *srv) return false; /* look up tcon based on tid & uid */ - read_lock(&cifs_tcp_ses_lock); + spin_lock(&cifs_tcp_ses_lock); list_for_each(tmp, &srv->smb_ses_list) { ses = list_entry(tmp, struct cifsSesInfo, smb_ses_list); list_for_each(tmp1, &ses->tcon_list) { @@ -560,25 +560,15 @@ is_valid_oplock_break(struct smb_hdr *buf, struct TCP_Server_Info *srv) continue; cifs_stats_inc(&tcon->num_oplock_brks); - read_lock(&GlobalSMBSeslock); + spin_lock(&cifs_file_list_lock); list_for_each(tmp2, &tcon->openFileList) { netfile = list_entry(tmp2, struct cifsFileInfo, tlist); if (pSMB->Fid != netfile->netfid) continue; - /* - * don't do anything if file is about to be - * closed anyway. - */ - if (netfile->closePend) { - read_unlock(&GlobalSMBSeslock); - read_unlock(&cifs_tcp_ses_lock); - return true; - } - cFYI(1, "file id match, oplock break"); - pCifsInode = CIFS_I(netfile->pInode); + pCifsInode = CIFS_I(netfile->dentry->d_inode); pCifsInode->clientCanCacheAll = false; if (pSMB->OplockLevel == 0) pCifsInode->clientCanCacheRead = false; @@ -594,17 +584,17 @@ is_valid_oplock_break(struct smb_hdr *buf, struct TCP_Server_Info *srv) cifs_oplock_break_get(netfile); netfile->oplock_break_cancelled = false; - read_unlock(&GlobalSMBSeslock); - read_unlock(&cifs_tcp_ses_lock); + spin_unlock(&cifs_file_list_lock); + spin_unlock(&cifs_tcp_ses_lock); return true; } - read_unlock(&GlobalSMBSeslock); - read_unlock(&cifs_tcp_ses_lock); + spin_unlock(&cifs_file_list_lock); + spin_unlock(&cifs_tcp_ses_lock); cFYI(1, "No matching file for oplock break"); return true; } } - read_unlock(&cifs_tcp_ses_lock); + spin_unlock(&cifs_tcp_ses_lock); cFYI(1, "Can not process oplock break for non-existent connection"); return true; } @@ -729,6 +719,6 @@ cifs_autodisable_serverino(struct cifs_sb_info *cifs_sb) "properly. Hardlinks will not be recognized on this " "mount. Consider mounting with the \"noserverino\" " "option to silence this message.", - cifs_sb->tcon->treeName); + cifs_sb_master_tcon(cifs_sb)->treeName); } } diff --git a/fs/cifs/ntlmssp.h b/fs/cifs/ntlmssp.h index 49c9a4e75319..5d52e4a3b1ed 100644 --- a/fs/cifs/ntlmssp.h +++ b/fs/cifs/ntlmssp.h @@ -61,6 +61,21 @@ #define NTLMSSP_NEGOTIATE_KEY_XCH 0x40000000 #define NTLMSSP_NEGOTIATE_56 0x80000000 +/* Define AV Pair Field IDs */ +enum av_field_type { + NTLMSSP_AV_EOL = 0, + NTLMSSP_AV_NB_COMPUTER_NAME, + NTLMSSP_AV_NB_DOMAIN_NAME, + NTLMSSP_AV_DNS_COMPUTER_NAME, + NTLMSSP_AV_DNS_DOMAIN_NAME, + NTLMSSP_AV_DNS_TREE_NAME, + NTLMSSP_AV_FLAGS, + NTLMSSP_AV_TIMESTAMP, + NTLMSSP_AV_RESTRICTION, + NTLMSSP_AV_TARGET_NAME, + NTLMSSP_AV_CHANNEL_BINDINGS +}; + /* Although typedefs are not commonly used for structure definitions */ /* in the Linux kernel, in this particular case they are useful */ /* to more closely match the standards document for NTLMSSP from */ diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index d5e591fab475..ef7bb7b50f58 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -102,7 +102,7 @@ cifs_readdir_lookup(struct dentry *parent, struct qstr *name, return NULL; } - if (CIFS_SB(sb)->tcon->nocase) + if (cifs_sb_master_tcon(CIFS_SB(sb))->nocase) dentry->d_op = &cifs_ci_dentry_ops; else dentry->d_op = &cifs_dentry_ops; @@ -171,7 +171,7 @@ static void cifs_std_info_to_fattr(struct cifs_fattr *fattr, FIND_FILE_STANDARD_INFO *info, struct cifs_sb_info *cifs_sb) { - int offset = cifs_sb->tcon->ses->server->timeAdj; + int offset = cifs_sb_master_tcon(cifs_sb)->ses->server->timeAdj; memset(fattr, 0, sizeof(*fattr)); fattr->cf_atime = cnvrtDosUnixTm(info->LastAccessDate, @@ -199,7 +199,7 @@ int get_symlink_reparse_path(char *full_path, struct cifs_sb_info *cifs_sb, int len; int oplock = 0; int rc; - struct cifsTconInfo *ptcon = cifs_sb->tcon; + struct cifsTconInfo *ptcon = cifs_sb_tcon(cifs_sb); char *tmpbuffer; rc = CIFSSMBOpen(xid, ptcon, full_path, FILE_OPEN, GENERIC_READ, @@ -223,34 +223,35 @@ int get_symlink_reparse_path(char *full_path, struct cifs_sb_info *cifs_sb, static int initiate_cifs_search(const int xid, struct file *file) { int rc = 0; - char *full_path; + char *full_path = NULL; struct cifsFileInfo *cifsFile; - struct cifs_sb_info *cifs_sb; + struct cifs_sb_info *cifs_sb = CIFS_SB(file->f_path.dentry->d_sb); + struct tcon_link *tlink; struct cifsTconInfo *pTcon; - if (file->private_data == NULL) { + tlink = cifs_sb_tlink(cifs_sb); + if (IS_ERR(tlink)) + return PTR_ERR(tlink); + pTcon = tlink_tcon(tlink); + + if (file->private_data == NULL) file->private_data = kzalloc(sizeof(struct cifsFileInfo), GFP_KERNEL); + if (file->private_data == NULL) { + rc = -ENOMEM; + goto error_exit; } - if (file->private_data == NULL) - return -ENOMEM; cifsFile = file->private_data; cifsFile->invalidHandle = true; cifsFile->srch_inf.endOfSearch = false; - - cifs_sb = CIFS_SB(file->f_path.dentry->d_sb); - if (cifs_sb == NULL) - return -EINVAL; - - pTcon = cifs_sb->tcon; - if (pTcon == NULL) - return -EINVAL; + cifsFile->tlink = cifs_get_tlink(tlink); full_path = build_path_from_dentry(file->f_path.dentry); - - if (full_path == NULL) - return -ENOMEM; + if (full_path == NULL) { + rc = -ENOMEM; + goto error_exit; + } cFYI(1, "Full path: %s start at: %lld", full_path, file->f_pos); @@ -283,7 +284,9 @@ ffirst_retry: cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_SERVER_INUM; goto ffirst_retry; } +error_exit: kfree(full_path); + cifs_put_tlink(tlink); return rc; } @@ -525,14 +528,14 @@ static int find_cifs_entry(const int xid, struct cifsTconInfo *pTcon, (index_to_find < first_entry_in_buffer)) { /* close and restart search */ cFYI(1, "search backing up - close and restart search"); - write_lock(&GlobalSMBSeslock); + spin_lock(&cifs_file_list_lock); if (!cifsFile->srch_inf.endOfSearch && !cifsFile->invalidHandle) { cifsFile->invalidHandle = true; - write_unlock(&GlobalSMBSeslock); + spin_unlock(&cifs_file_list_lock); CIFSFindClose(xid, pTcon, cifsFile->netfid); } else - write_unlock(&GlobalSMBSeslock); + spin_unlock(&cifs_file_list_lock); if (cifsFile->srch_inf.ntwrk_buf_start) { cFYI(1, "freeing SMB ff cache buf on search rewind"); if (cifsFile->srch_inf.smallBuf) @@ -738,6 +741,15 @@ static int cifs_filldir(char *pfindEntry, struct file *file, filldir_t filldir, cifs_autodisable_serverino(cifs_sb); } + if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) && + CIFSCouldBeMFSymlink(&fattr)) + /* + * trying to get the type and mode can be slow, + * so just call those regular files for now, and mark + * for reval + */ + fattr.cf_flags |= CIFS_FATTR_NEED_REVAL; + ino = cifs_uniqueid_to_ino_t(fattr.cf_uniqueid); tmp_dentry = cifs_readdir_lookup(file->f_dentry, &qstring, &fattr); @@ -777,9 +789,17 @@ int cifs_readdir(struct file *file, void *direntry, filldir_t filldir) xid = GetXid(); cifs_sb = CIFS_SB(file->f_path.dentry->d_sb); - pTcon = cifs_sb->tcon; - if (pTcon == NULL) - return -EINVAL; + + /* + * Ensure FindFirst doesn't fail before doing filldir() for '.' and + * '..'. Otherwise we won't be able to notify VFS in case of failure. + */ + if (file->private_data == NULL) { + rc = initiate_cifs_search(xid, file); + cFYI(1, "initiate cifs search rc %d", rc); + if (rc) + goto rddir2_exit; + } switch ((int) file->f_pos) { case 0: @@ -805,14 +825,6 @@ int cifs_readdir(struct file *file, void *direntry, filldir_t filldir) if after then keep searching till find it */ if (file->private_data == NULL) { - rc = initiate_cifs_search(xid, file); - cFYI(1, "initiate cifs search rc %d", rc); - if (rc) { - FreeXid(xid); - return rc; - } - } - if (file->private_data == NULL) { rc = -EINVAL; FreeXid(xid); return rc; @@ -829,6 +841,7 @@ int cifs_readdir(struct file *file, void *direntry, filldir_t filldir) CIFSFindClose(xid, pTcon, cifsFile->netfid); } */ + pTcon = tlink_tcon(cifsFile->tlink); rc = find_cifs_entry(xid, pTcon, file, ¤t_entry, &num_to_fill); if (rc) { diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c index 0a57cb7db5dd..2a11efd96592 100644 --- a/fs/cifs/sess.c +++ b/fs/cifs/sess.c @@ -80,7 +80,7 @@ static __le16 get_next_vcnum(struct cifsSesInfo *ses) if (max_vcs < 2) max_vcs = 0xFFFF; - write_lock(&cifs_tcp_ses_lock); + spin_lock(&cifs_tcp_ses_lock); if ((ses->need_reconnect) && is_first_ses_reconnect(ses)) goto get_vc_num_exit; /* vcnum will be zero */ for (i = ses->server->srv_count - 1; i < max_vcs; i++) { @@ -112,7 +112,7 @@ static __le16 get_next_vcnum(struct cifsSesInfo *ses) vcnum = i; ses->vcnum = vcnum; get_vc_num_exit: - write_unlock(&cifs_tcp_ses_lock); + spin_unlock(&cifs_tcp_ses_lock); return cpu_to_le16(vcnum); } @@ -383,6 +383,9 @@ static int decode_ascii_ssetup(char **pbcc_area, int bleft, static int decode_ntlmssp_challenge(char *bcc_ptr, int blob_len, struct cifsSesInfo *ses) { + unsigned int tioffset; /* challenge message target info area */ + unsigned int tilen; /* challenge message target info area length */ + CHALLENGE_MESSAGE *pblob = (CHALLENGE_MESSAGE *)bcc_ptr; if (blob_len < sizeof(CHALLENGE_MESSAGE)) { @@ -399,12 +402,25 @@ static int decode_ntlmssp_challenge(char *bcc_ptr, int blob_len, return -EINVAL; } - memcpy(ses->server->cryptKey, pblob->Challenge, CIFS_CRYPTO_KEY_SIZE); + memcpy(ses->cryptKey, pblob->Challenge, CIFS_CRYPTO_KEY_SIZE); /* BB we could decode pblob->NegotiateFlags; some may be useful */ /* In particular we can examine sign flags */ /* BB spec says that if AvId field of MsvAvTimestamp is populated then we must set the MIC field of the AUTHENTICATE_MESSAGE */ + tioffset = cpu_to_le16(pblob->TargetInfoArray.BufferOffset); + tilen = cpu_to_le16(pblob->TargetInfoArray.Length); + ses->tilen = tilen; + if (ses->tilen) { + ses->tiblob = kmalloc(tilen, GFP_KERNEL); + if (!ses->tiblob) { + cERROR(1, "Challenge target info allocation failure"); + ses->tilen = 0; + return -ENOMEM; + } + memcpy(ses->tiblob, bcc_ptr + tioffset, ses->tilen); + } + return 0; } @@ -425,7 +441,7 @@ static void build_ntlmssp_negotiate_blob(unsigned char *pbuffer, /* BB is NTLMV2 session security format easier to use here? */ flags = NTLMSSP_NEGOTIATE_56 | NTLMSSP_REQUEST_TARGET | NTLMSSP_NEGOTIATE_128 | NTLMSSP_NEGOTIATE_UNICODE | - NTLMSSP_NEGOTIATE_NT_ONLY | NTLMSSP_NEGOTIATE_NTLM; + NTLMSSP_NEGOTIATE_NTLM; if (ses->server->secMode & (SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED)) flags |= NTLMSSP_NEGOTIATE_SIGN; @@ -448,13 +464,16 @@ static void build_ntlmssp_negotiate_blob(unsigned char *pbuffer, maximum possible size is fixed and small, making this approach cleaner. This function returns the length of the data in the blob */ static int build_ntlmssp_auth_blob(unsigned char *pbuffer, + u16 *buflen, struct cifsSesInfo *ses, - const struct nls_table *nls_cp, bool first) + const struct nls_table *nls_cp) { + int rc; + unsigned int size; AUTHENTICATE_MESSAGE *sec_blob = (AUTHENTICATE_MESSAGE *)pbuffer; __u32 flags; unsigned char *tmp; - char ntlm_session_key[CIFS_SESS_KEY_SIZE]; + struct ntlmv2_resp ntlmv2_response = {}; memcpy(sec_blob->Signature, NTLMSSP_SIGNATURE, 8); sec_blob->MessageType = NtLmAuthenticate; @@ -462,7 +481,7 @@ static int build_ntlmssp_auth_blob(unsigned char *pbuffer, flags = NTLMSSP_NEGOTIATE_56 | NTLMSSP_REQUEST_TARGET | NTLMSSP_NEGOTIATE_TARGET_INFO | NTLMSSP_NEGOTIATE_128 | NTLMSSP_NEGOTIATE_UNICODE | - NTLMSSP_NEGOTIATE_NT_ONLY | NTLMSSP_NEGOTIATE_NTLM; + NTLMSSP_NEGOTIATE_NTLM; if (ses->server->secMode & (SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED)) flags |= NTLMSSP_NEGOTIATE_SIGN; @@ -477,19 +496,26 @@ static int build_ntlmssp_auth_blob(unsigned char *pbuffer, sec_blob->LmChallengeResponse.Length = 0; sec_blob->LmChallengeResponse.MaximumLength = 0; - /* calculate session key, BB what about adding similar ntlmv2 path? */ - SMBNTencrypt(ses->password, ses->server->cryptKey, ntlm_session_key); - if (first) - cifs_calculate_mac_key(&ses->server->mac_signing_key, - ntlm_session_key, ses->password); - - memcpy(tmp, ntlm_session_key, CIFS_SESS_KEY_SIZE); sec_blob->NtChallengeResponse.BufferOffset = cpu_to_le32(tmp - pbuffer); - sec_blob->NtChallengeResponse.Length = cpu_to_le16(CIFS_SESS_KEY_SIZE); - sec_blob->NtChallengeResponse.MaximumLength = - cpu_to_le16(CIFS_SESS_KEY_SIZE); + rc = setup_ntlmv2_rsp(ses, (char *)&ntlmv2_response, nls_cp); + if (rc) { + cERROR(1, "Error %d during NTLMSSP authentication", rc); + goto setup_ntlmv2_ret; + } + size = sizeof(struct ntlmv2_resp); + memcpy(tmp, (char *)&ntlmv2_response, size); + tmp += size; + if (ses->tilen > 0) { + memcpy(tmp, ses->tiblob, ses->tilen); + tmp += ses->tilen; + } - tmp += CIFS_SESS_KEY_SIZE; + sec_blob->NtChallengeResponse.Length = cpu_to_le16(size + ses->tilen); + sec_blob->NtChallengeResponse.MaximumLength = + cpu_to_le16(size + ses->tilen); + kfree(ses->tiblob); + ses->tiblob = NULL; + ses->tilen = 0; if (ses->domainName == NULL) { sec_blob->DomainName.BufferOffset = cpu_to_le32(tmp - pbuffer); @@ -501,7 +527,6 @@ static int build_ntlmssp_auth_blob(unsigned char *pbuffer, len = cifs_strtoUCS((__le16 *)tmp, ses->domainName, MAX_USERNAME_SIZE, nls_cp); len *= 2; /* unicode is 2 bytes each */ - len += 2; /* trailing null */ sec_blob->DomainName.BufferOffset = cpu_to_le32(tmp - pbuffer); sec_blob->DomainName.Length = cpu_to_le16(len); sec_blob->DomainName.MaximumLength = cpu_to_le16(len); @@ -518,7 +543,6 @@ static int build_ntlmssp_auth_blob(unsigned char *pbuffer, len = cifs_strtoUCS((__le16 *)tmp, ses->userName, MAX_USERNAME_SIZE, nls_cp); len *= 2; /* unicode is 2 bytes each */ - len += 2; /* trailing null */ sec_blob->UserName.BufferOffset = cpu_to_le32(tmp - pbuffer); sec_blob->UserName.Length = cpu_to_le16(len); sec_blob->UserName.MaximumLength = cpu_to_le16(len); @@ -533,7 +557,10 @@ static int build_ntlmssp_auth_blob(unsigned char *pbuffer, sec_blob->SessionKey.BufferOffset = cpu_to_le32(tmp - pbuffer); sec_blob->SessionKey.Length = 0; sec_blob->SessionKey.MaximumLength = 0; - return tmp - pbuffer; + +setup_ntlmv2_ret: + *buflen = tmp - pbuffer; + return rc; } @@ -545,19 +572,6 @@ static void setup_ntlmssp_neg_req(SESSION_SETUP_ANDX *pSMB, return; } - -static int setup_ntlmssp_auth_req(SESSION_SETUP_ANDX *pSMB, - struct cifsSesInfo *ses, - const struct nls_table *nls, bool first_time) -{ - int bloblen; - - bloblen = build_ntlmssp_auth_blob(&pSMB->req.SecurityBlob[0], ses, nls, - first_time); - pSMB->req.SecurityBlobLength = cpu_to_le16(bloblen); - - return bloblen; -} #endif int @@ -579,15 +593,12 @@ CIFS_SessSetup(unsigned int xid, struct cifsSesInfo *ses, int bytes_remaining; struct key *spnego_key = NULL; __le32 phase = NtLmNegotiate; /* NTLMSSP, if needed, is multistage */ - bool first_time; + u16 blob_len; + char *ntlmsspblob = NULL; if (ses == NULL) return -EINVAL; - read_lock(&cifs_tcp_ses_lock); - first_time = is_first_ses_reconnect(ses); - read_unlock(&cifs_tcp_ses_lock); - type = ses->server->secType; cFYI(1, "sess setup type %d", type); @@ -658,7 +669,7 @@ ssetup_ntlmssp_authenticate: /* BB calculate hash with password */ /* and copy into bcc */ - calc_lanman_hash(ses->password, ses->server->cryptKey, + calc_lanman_hash(ses->password, ses->cryptKey, ses->server->secMode & SECMODE_PW_ENCRYPT ? true : false, lnm_session_key); @@ -685,15 +696,11 @@ ssetup_ntlmssp_authenticate: cpu_to_le16(CIFS_SESS_KEY_SIZE); /* calculate session key */ - SMBNTencrypt(ses->password, ses->server->cryptKey, - ntlm_session_key); + SMBNTencrypt(ses->password, ses->cryptKey, ntlm_session_key); - if (first_time) /* should this be moved into common code - with similar ntlmv2 path? */ - cifs_calculate_mac_key(&ses->server->mac_signing_key, - ntlm_session_key, ses->password); + cifs_calculate_session_key(&ses->auth_key, + ntlm_session_key, ses->password); /* copy session key */ - memcpy(bcc_ptr, (char *)ntlm_session_key, CIFS_SESS_KEY_SIZE); bcc_ptr += CIFS_SESS_KEY_SIZE; memcpy(bcc_ptr, (char *)ntlm_session_key, CIFS_SESS_KEY_SIZE); @@ -725,16 +732,31 @@ ssetup_ntlmssp_authenticate: pSMB->req_no_secext.CaseInsensitivePasswordLength = 0; /* cpu_to_le16(LM2_SESS_KEY_SIZE); */ - pSMB->req_no_secext.CaseSensitivePasswordLength = - cpu_to_le16(sizeof(struct ntlmv2_resp)); - /* calculate session key */ - setup_ntlmv2_rsp(ses, v2_sess_key, nls_cp); - /* FIXME: calculate MAC key */ + rc = setup_ntlmv2_rsp(ses, v2_sess_key, nls_cp); + if (rc) { + cERROR(1, "Error %d during NTLMv2 authentication", rc); + kfree(v2_sess_key); + goto ssetup_exit; + } memcpy(bcc_ptr, (char *)v2_sess_key, - sizeof(struct ntlmv2_resp)); + sizeof(struct ntlmv2_resp)); bcc_ptr += sizeof(struct ntlmv2_resp); kfree(v2_sess_key); + /* set case sensitive password length after tilen may get + * assigned, tilen is 0 otherwise. + */ + pSMB->req_no_secext.CaseSensitivePasswordLength = + cpu_to_le16(sizeof(struct ntlmv2_resp) + ses->tilen); + if (ses->tilen > 0) { + memcpy(bcc_ptr, ses->tiblob, ses->tilen); + bcc_ptr += ses->tilen; + /* we never did allocate ses->domainName to free */ + kfree(ses->tiblob); + ses->tiblob = NULL; + ses->tilen = 0; + } + if (ses->capabilities & CAP_UNICODE) { if (iov[0].iov_len % 2) { *bcc_ptr = 0; @@ -765,17 +787,14 @@ ssetup_ntlmssp_authenticate: } /* bail out if key is too long */ if (msg->sesskey_len > - sizeof(ses->server->mac_signing_key.data.krb5)) { + sizeof(ses->auth_key.data.krb5)) { cERROR(1, "Kerberos signing key too long (%u bytes)", msg->sesskey_len); rc = -EOVERFLOW; goto ssetup_exit; } - if (first_time) { - ses->server->mac_signing_key.len = msg->sesskey_len; - memcpy(ses->server->mac_signing_key.data.krb5, - msg->data, msg->sesskey_len); - } + ses->auth_key.len = msg->sesskey_len; + memcpy(ses->auth_key.data.krb5, msg->data, msg->sesskey_len); pSMB->req.hdr.Flags2 |= SMBFLG2_EXT_SEC; capabilities |= CAP_EXTENDED_SECURITY; pSMB->req.Capabilities = cpu_to_le32(capabilities); @@ -815,12 +834,30 @@ ssetup_ntlmssp_authenticate: if (phase == NtLmNegotiate) { setup_ntlmssp_neg_req(pSMB, ses); iov[1].iov_len = sizeof(NEGOTIATE_MESSAGE); + iov[1].iov_base = &pSMB->req.SecurityBlob[0]; } else if (phase == NtLmAuthenticate) { - int blob_len; - blob_len = setup_ntlmssp_auth_req(pSMB, ses, - nls_cp, - first_time); + /* 5 is an empirical value, large enought to + * hold authenticate message, max 10 of + * av paris, doamin,user,workstation mames, + * flags etc.. + */ + ntlmsspblob = kmalloc( + 5*sizeof(struct _AUTHENTICATE_MESSAGE), + GFP_KERNEL); + if (!ntlmsspblob) { + cERROR(1, "Can't allocate NTLMSSP"); + rc = -ENOMEM; + goto ssetup_exit; + } + + rc = build_ntlmssp_auth_blob(ntlmsspblob, + &blob_len, ses, nls_cp); + if (rc) + goto ssetup_exit; iov[1].iov_len = blob_len; + iov[1].iov_base = ntlmsspblob; + pSMB->req.SecurityBlobLength = + cpu_to_le16(blob_len); /* Make sure that we tell the server that we are using the uid that it just gave us back on the response (challenge) */ @@ -830,7 +867,6 @@ ssetup_ntlmssp_authenticate: rc = -ENOSYS; goto ssetup_exit; } - iov[1].iov_base = &pSMB->req.SecurityBlob[0]; /* unicode strings must be word aligned */ if ((iov[0].iov_len + iov[1].iov_len) % 2) { *bcc_ptr = 0; @@ -895,7 +931,6 @@ ssetup_ntlmssp_authenticate: bcc_ptr = pByteArea(smb_buf); if (smb_buf->WordCount == 4) { - __u16 blob_len; blob_len = le16_to_cpu(pSMB->resp.SecurityBlobLength); if (blob_len > bytes_remaining) { cERROR(1, "bad security blob length %d", blob_len); @@ -931,6 +966,8 @@ ssetup_exit: key_put(spnego_key); } kfree(str_area); + kfree(ntlmsspblob); + ntlmsspblob = NULL; if (resp_buf_type == CIFS_SMALL_BUFFER) { cFYI(1, "ssetup freeing small buf %p", iov[0].iov_base); cifs_small_buf_release(iov[0].iov_base); diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index 82f78c4d6978..a66c91eb6eb4 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -543,7 +543,7 @@ SendReceive2(const unsigned int xid, struct cifsSesInfo *ses, (ses->server->secMode & (SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED))) { rc = cifs_verify_signature(midQ->resp_buf, - &ses->server->mac_signing_key, + &ses->server->session_key, midQ->sequence_number+1); if (rc) { cERROR(1, "Unexpected SMB signature"); @@ -731,7 +731,7 @@ SendReceive(const unsigned int xid, struct cifsSesInfo *ses, (ses->server->secMode & (SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED))) { rc = cifs_verify_signature(out_buf, - &ses->server->mac_signing_key, + &ses->server->session_key, midQ->sequence_number+1); if (rc) { cERROR(1, "Unexpected SMB signature"); @@ -981,7 +981,7 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifsTconInfo *tcon, (ses->server->secMode & (SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED))) { rc = cifs_verify_signature(out_buf, - &ses->server->mac_signing_key, + &ses->server->session_key, midQ->sequence_number+1); if (rc) { cERROR(1, "Unexpected SMB signature"); diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c index a1509207bfa6..a264b744bb41 100644 --- a/fs/cifs/xattr.c +++ b/fs/cifs/xattr.c @@ -47,9 +47,10 @@ int cifs_removexattr(struct dentry *direntry, const char *ea_name) #ifdef CONFIG_CIFS_XATTR int xid; struct cifs_sb_info *cifs_sb; + struct tcon_link *tlink; struct cifsTconInfo *pTcon; struct super_block *sb; - char *full_path; + char *full_path = NULL; if (direntry == NULL) return -EIO; @@ -58,16 +59,19 @@ int cifs_removexattr(struct dentry *direntry, const char *ea_name) sb = direntry->d_inode->i_sb; if (sb == NULL) return -EIO; - xid = GetXid(); cifs_sb = CIFS_SB(sb); - pTcon = cifs_sb->tcon; + tlink = cifs_sb_tlink(cifs_sb); + if (IS_ERR(tlink)) + return PTR_ERR(tlink); + pTcon = tlink_tcon(tlink); + + xid = GetXid(); full_path = build_path_from_dentry(direntry); if (full_path == NULL) { rc = -ENOMEM; - FreeXid(xid); - return rc; + goto remove_ea_exit; } if (ea_name == NULL) { cFYI(1, "Null xattr names not supported"); @@ -91,6 +95,7 @@ int cifs_removexattr(struct dentry *direntry, const char *ea_name) remove_ea_exit: kfree(full_path); FreeXid(xid); + cifs_put_tlink(tlink); #endif return rc; } @@ -102,6 +107,7 @@ int cifs_setxattr(struct dentry *direntry, const char *ea_name, #ifdef CONFIG_CIFS_XATTR int xid; struct cifs_sb_info *cifs_sb; + struct tcon_link *tlink; struct cifsTconInfo *pTcon; struct super_block *sb; char *full_path; @@ -113,16 +119,19 @@ int cifs_setxattr(struct dentry *direntry, const char *ea_name, sb = direntry->d_inode->i_sb; if (sb == NULL) return -EIO; - xid = GetXid(); cifs_sb = CIFS_SB(sb); - pTcon = cifs_sb->tcon; + tlink = cifs_sb_tlink(cifs_sb); + if (IS_ERR(tlink)) + return PTR_ERR(tlink); + pTcon = tlink_tcon(tlink); + + xid = GetXid(); full_path = build_path_from_dentry(direntry); if (full_path == NULL) { rc = -ENOMEM; - FreeXid(xid); - return rc; + goto set_ea_exit; } /* return dos attributes as pseudo xattr */ /* return alt name if available as pseudo attr */ @@ -132,9 +141,8 @@ int cifs_setxattr(struct dentry *direntry, const char *ea_name, returns as xattrs */ if (value_size > MAX_EA_VALUE_SIZE) { cFYI(1, "size of EA value too large"); - kfree(full_path); - FreeXid(xid); - return -EOPNOTSUPP; + rc = -EOPNOTSUPP; + goto set_ea_exit; } if (ea_name == NULL) { @@ -198,6 +206,7 @@ int cifs_setxattr(struct dentry *direntry, const char *ea_name, set_ea_exit: kfree(full_path); FreeXid(xid); + cifs_put_tlink(tlink); #endif return rc; } @@ -209,6 +218,7 @@ ssize_t cifs_getxattr(struct dentry *direntry, const char *ea_name, #ifdef CONFIG_CIFS_XATTR int xid; struct cifs_sb_info *cifs_sb; + struct tcon_link *tlink; struct cifsTconInfo *pTcon; struct super_block *sb; char *full_path; @@ -221,16 +231,18 @@ ssize_t cifs_getxattr(struct dentry *direntry, const char *ea_name, if (sb == NULL) return -EIO; - xid = GetXid(); - cifs_sb = CIFS_SB(sb); - pTcon = cifs_sb->tcon; + tlink = cifs_sb_tlink(cifs_sb); + if (IS_ERR(tlink)) + return PTR_ERR(tlink); + pTcon = tlink_tcon(tlink); + + xid = GetXid(); full_path = build_path_from_dentry(direntry); if (full_path == NULL) { rc = -ENOMEM; - FreeXid(xid); - return rc; + goto get_ea_exit; } /* return dos attributes as pseudo xattr */ /* return alt name if available as pseudo attr */ @@ -323,6 +335,7 @@ ssize_t cifs_getxattr(struct dentry *direntry, const char *ea_name, get_ea_exit: kfree(full_path); FreeXid(xid); + cifs_put_tlink(tlink); #endif return rc; } @@ -333,6 +346,7 @@ ssize_t cifs_listxattr(struct dentry *direntry, char *data, size_t buf_size) #ifdef CONFIG_CIFS_XATTR int xid; struct cifs_sb_info *cifs_sb; + struct tcon_link *tlink; struct cifsTconInfo *pTcon; struct super_block *sb; char *full_path; @@ -346,18 +360,20 @@ ssize_t cifs_listxattr(struct dentry *direntry, char *data, size_t buf_size) return -EIO; cifs_sb = CIFS_SB(sb); - pTcon = cifs_sb->tcon; - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR) return -EOPNOTSUPP; + tlink = cifs_sb_tlink(cifs_sb); + if (IS_ERR(tlink)) + return PTR_ERR(tlink); + pTcon = tlink_tcon(tlink); + xid = GetXid(); full_path = build_path_from_dentry(direntry); if (full_path == NULL) { rc = -ENOMEM; - FreeXid(xid); - return rc; + goto list_ea_exit; } /* return dos attributes as pseudo xattr */ /* return alt name if available as pseudo attr */ @@ -370,8 +386,10 @@ ssize_t cifs_listxattr(struct dentry *direntry, char *data, size_t buf_size) cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR); +list_ea_exit: kfree(full_path); FreeXid(xid); + cifs_put_tlink(tlink); #endif return rc; } diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c index 031dbe3a15ca..64e5f3efdd81 100644 --- a/fs/dlm/lock.c +++ b/fs/dlm/lock.c @@ -1846,6 +1846,9 @@ static void send_bast_queue(struct dlm_rsb *r, struct list_head *head, struct dlm_lkb *gr; list_for_each_entry(gr, head, lkb_statequeue) { + /* skip self when sending basts to convertqueue */ + if (gr == lkb) + continue; if (gr->lkb_bastfn && modes_require_bast(gr, lkb)) { queue_bast(r, gr, lkb->lkb_rqmode); gr->lkb_highbast = lkb->lkb_rqmode; diff --git a/fs/ext3/fsync.c b/fs/ext3/fsync.c index d7e9f74dc3a6..09b13bb34c94 100644 --- a/fs/ext3/fsync.c +++ b/fs/ext3/fsync.c @@ -90,7 +90,6 @@ int ext3_sync_file(struct file *file, int datasync) * storage */ if (needs_barrier) - blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL, - BLKDEV_IFL_WAIT); + blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL); return ret; } diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index 592adf2e546e..3f3ff5ee8f9d 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -128,10 +128,9 @@ int ext4_sync_file(struct file *file, int datasync) (journal->j_fs_dev != journal->j_dev) && (journal->j_flags & JBD2_BARRIER)) blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, - NULL, BLKDEV_IFL_WAIT); + NULL); ret = jbd2_log_wait_commit(journal, commit_tid); } else if (journal->j_flags & JBD2_BARRIER) - blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL, - BLKDEV_IFL_WAIT); + blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL); return ret; } diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 4b4ad4b7ce57..19aa0d44d822 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2566,7 +2566,7 @@ static inline void ext4_issue_discard(struct super_block *sb, discard_block = block + ext4_group_first_block_no(sb, block_group); trace_ext4_discard_blocks(sb, (unsigned long long) discard_block, count); - ret = sb_issue_discard(sb, discard_block, count); + ret = sb_issue_discard(sb, discard_block, count, GFP_NOFS, 0); if (ret == EOPNOTSUPP) { ext4_warning(sb, "discard not supported, disabling"); clear_opt(EXT4_SB(sb)->s_mount_opt, DISCARD); diff --git a/fs/fat/fatent.c b/fs/fat/fatent.c index 81184d3b75a3..b47d2c9f4fa1 100644 --- a/fs/fat/fatent.c +++ b/fs/fat/fatent.c @@ -577,7 +577,8 @@ int fat_free_clusters(struct inode *inode, int cluster) sb_issue_discard(sb, fat_clus_to_blknr(sbi, first_cl), - nr_clus * sbi->sec_per_clus); + nr_clus * sbi->sec_per_clus, + GFP_NOFS, 0); first_cl = cluster; } diff --git a/fs/fat/misc.c b/fs/fat/misc.c index 1736f2356388..970e682ea754 100644 --- a/fs/fat/misc.c +++ b/fs/fat/misc.c @@ -255,10 +255,7 @@ int fat_sync_bhs(struct buffer_head **bhs, int nr_bhs) for (i = 0; i < nr_bhs; i++) { wait_on_buffer(bhs[i]); - if (buffer_eopnotsupp(bhs[i])) { - clear_buffer_eopnotsupp(bhs[i]); - err = -EOPNOTSUPP; - } else if (!err && !buffer_uptodate(bhs[i])) + if (!err && !buffer_uptodate(bhs[i])) err = -EIO; } return err; diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index ac750bd31a6f..eb01f3575e10 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -592,22 +592,13 @@ static void log_write_header(struct gfs2_sbd *sdp, u32 flags, int pull) lh->lh_hash = cpu_to_be32(hash); bh->b_end_io = end_buffer_write_sync; - if (test_bit(SDF_NOBARRIERS, &sdp->sd_flags)) - goto skip_barrier; get_bh(bh); - submit_bh(WRITE_BARRIER | REQ_META, bh); - wait_on_buffer(bh); - if (buffer_eopnotsupp(bh)) { - clear_buffer_eopnotsupp(bh); - set_buffer_uptodate(bh); - fs_info(sdp, "barrier sync failed - disabling barriers\n"); - set_bit(SDF_NOBARRIERS, &sdp->sd_flags); - lock_buffer(bh); -skip_barrier: - get_bh(bh); + if (test_bit(SDF_NOBARRIERS, &sdp->sd_flags)) submit_bh(WRITE_SYNC | REQ_META, bh); - wait_on_buffer(bh); - } + else + submit_bh(WRITE_FLUSH_FUA | REQ_META, bh); + wait_on_buffer(bh); + if (!buffer_uptodate(bh)) gfs2_io_error_bh(sdp, bh); brelse(bh); diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c index d7eb1e209aa8..ebef7ab6e17e 100644 --- a/fs/gfs2/main.c +++ b/fs/gfs2/main.c @@ -144,7 +144,7 @@ static int __init init_gfs2_fs(void) error = -ENOMEM; gfs_recovery_wq = alloc_workqueue("gfs_recovery", - WQ_RESCUER | WQ_FREEZEABLE, 0); + WQ_MEM_RECLAIM | WQ_FREEZEABLE, 0); if (!gfs_recovery_wq) goto fail_wq; diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index fb67f593f408..bef3ab6cf5c1 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -866,8 +866,7 @@ static void gfs2_rgrp_send_discards(struct gfs2_sbd *sdp, u64 offset, if ((start + nr_sects) != blk) { rv = blkdev_issue_discard(bdev, start, nr_sects, GFP_NOFS, - BLKDEV_IFL_WAIT | - BLKDEV_IFL_BARRIER); + 0); if (rv) goto fail; nr_sects = 0; @@ -881,8 +880,7 @@ start_new_extent: } } if (nr_sects) { - rv = blkdev_issue_discard(bdev, start, nr_sects, GFP_NOFS, - BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER); + rv = blkdev_issue_discard(bdev, start, nr_sects, GFP_NOFS, 0); if (rv) goto fail; } diff --git a/fs/jbd/commit.c b/fs/jbd/commit.c index 95d8c11c929e..85a6883c0aca 100644 --- a/fs/jbd/commit.c +++ b/fs/jbd/commit.c @@ -137,34 +137,10 @@ static int journal_write_commit_record(journal_t *journal, JBUFFER_TRACE(descriptor, "write commit block"); set_buffer_dirty(bh); - if (journal->j_flags & JFS_BARRIER) { - ret = __sync_dirty_buffer(bh, WRITE_SYNC | WRITE_BARRIER); - - /* - * Is it possible for another commit to fail at roughly - * the same time as this one? If so, we don't want to - * trust the barrier flag in the super, but instead want - * to remember if we sent a barrier request - */ - if (ret == -EOPNOTSUPP) { - char b[BDEVNAME_SIZE]; - - printk(KERN_WARNING - "JBD: barrier-based sync failed on %s - " - "disabling barriers\n", - bdevname(journal->j_dev, b)); - spin_lock(&journal->j_state_lock); - journal->j_flags &= ~JFS_BARRIER; - spin_unlock(&journal->j_state_lock); - - /* And try again, without the barrier */ - set_buffer_uptodate(bh); - set_buffer_dirty(bh); - ret = sync_dirty_buffer(bh); - } - } else { + if (journal->j_flags & JFS_BARRIER) + ret = __sync_dirty_buffer(bh, WRITE_SYNC | WRITE_FLUSH_FUA); + else ret = sync_dirty_buffer(bh); - } put_bh(bh); /* One for getblk() */ journal_put_journal_head(descriptor); @@ -318,7 +294,7 @@ void journal_commit_transaction(journal_t *journal) int first_tag = 0; int tag_flag; int i; - int write_op = WRITE; + int write_op = WRITE_SYNC; /* * First job: lock down the current transaction and wait for diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index 5247e7ffdcb4..6571a056e55d 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -532,8 +532,7 @@ int jbd2_cleanup_journal_tail(journal_t *journal) */ if ((journal->j_fs_dev != journal->j_dev) && (journal->j_flags & JBD2_BARRIER)) - blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL, NULL, - BLKDEV_IFL_WAIT); + blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL, NULL); if (!(journal->j_flags & JBD2_ABORT)) jbd2_journal_update_superblock(journal, 1); return 0; diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 7c068c189d80..bc6be8bda1cc 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -134,25 +134,11 @@ static int journal_submit_commit_record(journal_t *journal, if (journal->j_flags & JBD2_BARRIER && !JBD2_HAS_INCOMPAT_FEATURE(journal, - JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) { - ret = submit_bh(WRITE_SYNC_PLUG | WRITE_BARRIER, bh); - if (ret == -EOPNOTSUPP) { - printk(KERN_WARNING - "JBD2: Disabling barriers on %s, " - "not supported by device\n", journal->j_devname); - write_lock(&journal->j_state_lock); - journal->j_flags &= ~JBD2_BARRIER; - write_unlock(&journal->j_state_lock); - - /* And try again, without the barrier */ - lock_buffer(bh); - set_buffer_uptodate(bh); - clear_buffer_dirty(bh); - ret = submit_bh(WRITE_SYNC_PLUG, bh); - } - } else { + JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) + ret = submit_bh(WRITE_SYNC_PLUG | WRITE_FLUSH_FUA, bh); + else ret = submit_bh(WRITE_SYNC_PLUG, bh); - } + *cbh = bh; return ret; } @@ -166,29 +152,8 @@ static int journal_wait_on_commit_record(journal_t *journal, { int ret = 0; -retry: clear_buffer_dirty(bh); wait_on_buffer(bh); - if (buffer_eopnotsupp(bh) && (journal->j_flags & JBD2_BARRIER)) { - printk(KERN_WARNING - "JBD2: %s: disabling barries on %s - not supported " - "by device\n", __func__, journal->j_devname); - write_lock(&journal->j_state_lock); - journal->j_flags &= ~JBD2_BARRIER; - write_unlock(&journal->j_state_lock); - - lock_buffer(bh); - clear_buffer_dirty(bh); - set_buffer_uptodate(bh); - bh->b_end_io = journal_end_buffer_io_sync; - - ret = submit_bh(WRITE_SYNC_PLUG, bh); - if (ret) { - unlock_buffer(bh); - return ret; - } - goto retry; - } if (unlikely(!buffer_uptodate(bh))) ret = -EIO; @@ -360,7 +325,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) int tag_bytes = journal_tag_bytes(journal); struct buffer_head *cbh = NULL; /* For transactional checksums */ __u32 crc32_sum = ~0; - int write_op = WRITE; + int write_op = WRITE_SYNC; /* * First job: lock down the current transaction and wait for @@ -701,6 +666,16 @@ start_journal_io: } } + err = journal_finish_inode_data_buffers(journal, commit_transaction); + if (err) { + printk(KERN_WARNING + "JBD2: Detected IO errors while flushing file data " + "on %s\n", journal->j_devname); + if (journal->j_flags & JBD2_ABORT_ON_SYNCDATA_ERR) + jbd2_journal_abort(journal, err); + err = 0; + } + /* * If the journal is not located on the file system device, * then we must flush the file system device before we issue @@ -709,8 +684,7 @@ start_journal_io: if (commit_transaction->t_flushed_data_blocks && (journal->j_fs_dev != journal->j_dev) && (journal->j_flags & JBD2_BARRIER)) - blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL, NULL, - BLKDEV_IFL_WAIT); + blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL, NULL); /* Done it all: now write the commit record asynchronously. */ if (JBD2_HAS_INCOMPAT_FEATURE(journal, @@ -719,19 +693,6 @@ start_journal_io: &cbh, crc32_sum); if (err) __jbd2_journal_abort_hard(journal); - if (journal->j_flags & JBD2_BARRIER) - blkdev_issue_flush(journal->j_dev, GFP_KERNEL, NULL, - BLKDEV_IFL_WAIT); - } - - err = journal_finish_inode_data_buffers(journal, commit_transaction); - if (err) { - printk(KERN_WARNING - "JBD2: Detected IO errors while flushing file data " - "on %s\n", journal->j_devname); - if (journal->j_flags & JBD2_ABORT_ON_SYNCDATA_ERR) - jbd2_journal_abort(journal, err); - err = 0; } /* Lo and behold: we have just managed to send a transaction to @@ -845,6 +806,11 @@ wait_for_iobuf: } if (!err && !is_journal_aborted(journal)) err = journal_wait_on_commit_record(journal, cbh); + if (JBD2_HAS_INCOMPAT_FEATURE(journal, + JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT) && + journal->j_flags & JBD2_BARRIER) { + blkdev_issue_flush(journal->j_dev, GFP_KERNEL, NULL); + } if (err) jbd2_journal_abort(journal, err); diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index ab629078f4e2..35ae03c0db86 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -180,17 +180,9 @@ static int nilfs_sync_super(struct nilfs_sb_info *sbi, int flag) retry: set_buffer_dirty(nilfs->ns_sbh[0]); - if (nilfs_test_opt(sbi, BARRIER)) { err = __sync_dirty_buffer(nilfs->ns_sbh[0], - WRITE_SYNC | WRITE_BARRIER); - if (err == -EOPNOTSUPP) { - nilfs_warning(sbi->s_super, __func__, - "barrier-based sync failed. " - "disabling barriers\n"); - nilfs_clear_opt(sbi, BARRIER); - goto retry; - } + WRITE_SYNC | WRITE_FLUSH_FUA); } else { err = sync_dirty_buffer(nilfs->ns_sbh[0]); } diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c index bd02b6127d35..0254be2d73c6 100644 --- a/fs/nilfs2/the_nilfs.c +++ b/fs/nilfs2/the_nilfs.c @@ -635,9 +635,7 @@ int nilfs_discard_segments(struct the_nilfs *nilfs, __u64 *segnump, ret = blkdev_issue_discard(nilfs->ns_bdev, start * sects_per_block, nblocks * sects_per_block, - GFP_NOFS, - BLKDEV_IFL_WAIT | - BLKDEV_IFL_BARRIER); + GFP_NOFS, 0); if (ret < 0) return ret; nblocks = 0; @@ -647,8 +645,7 @@ int nilfs_discard_segments(struct the_nilfs *nilfs, __u64 *segnump, ret = blkdev_issue_discard(nilfs->ns_bdev, start * sects_per_block, nblocks * sects_per_block, - GFP_NOFS, - BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER); + GFP_NOFS, 0); return ret; } diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 9e8cc4346b76..1ca6867935bb 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -187,8 +187,7 @@ static int ocfs2_sync_file(struct file *file, int datasync) * platter */ if (osb->s_mount_opt & OCFS2_MOUNT_BARRIER) - blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, - NULL, BLKDEV_IFL_WAIT); + blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL); goto bail; } diff --git a/fs/partitions/check.c b/fs/partitions/check.c index 79fbf3f390f0..b81bfc016a05 100644 --- a/fs/partitions/check.c +++ b/fs/partitions/check.c @@ -352,6 +352,7 @@ static void part_release(struct device *dev) { struct hd_struct *p = dev_to_part(dev); free_part_stats(p); + free_part_info(p); kfree(p); } @@ -364,17 +365,25 @@ struct device_type part_type = { static void delete_partition_rcu_cb(struct rcu_head *head) { struct hd_struct *part = container_of(head, struct hd_struct, rcu_head); + struct gendisk *disk = part_to_disk(part); + struct request_queue *q = disk->queue; + unsigned long flags; part->start_sect = 0; part->nr_sects = 0; part_stat_set_all(part, 0); put_device(part_to_dev(part)); + + spin_lock_irqsave(q->queue_lock, flags); + elv_quiesce_end(q); + spin_unlock_irqrestore(q->queue_lock, flags); } void delete_partition(struct gendisk *disk, int partno) { struct disk_part_tbl *ptbl = disk->part_tbl; struct hd_struct *part; + struct request_queue *q = disk->queue; if (partno >= ptbl->len) return; @@ -389,6 +398,10 @@ void delete_partition(struct gendisk *disk, int partno) kobject_put(part->holder_dir); device_del(part_to_dev(part)); + spin_lock_irq(q->queue_lock); + elv_quiesce_start(q); + spin_unlock_irq(q->queue_lock); + call_rcu(&part->rcu_head, delete_partition_rcu_cb); } @@ -401,7 +414,8 @@ static DEVICE_ATTR(whole_disk, S_IRUSR | S_IRGRP | S_IROTH, whole_disk_show, NULL); struct hd_struct *add_partition(struct gendisk *disk, int partno, - sector_t start, sector_t len, int flags) + sector_t start, sector_t len, int flags, + struct partition_meta_info *info) { struct hd_struct *p; dev_t devt = MKDEV(0, 0); @@ -438,6 +452,14 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno, p->partno = partno; p->policy = get_disk_ro(disk); + if (info) { + struct partition_meta_info *pinfo = alloc_part_info(disk); + if (!pinfo) + goto out_free_stats; + memcpy(pinfo, info, sizeof(*info)); + p->info = pinfo; + } + dname = dev_name(ddev); if (isdigit(dname[strlen(dname) - 1])) dev_set_name(pdev, "%sp%d", dname, partno); @@ -451,7 +473,7 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno, err = blk_alloc_devt(p, &devt); if (err) - goto out_free_stats; + goto out_free_info; pdev->devt = devt; /* delay uevent until 'holders' subdir is created */ @@ -481,6 +503,8 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno, return p; +out_free_info: + free_part_info(p); out_free_stats: free_part_stats(p); out_free: @@ -513,14 +537,14 @@ void register_disk(struct gendisk *disk) if (device_add(ddev)) return; -#ifndef CONFIG_SYSFS_DEPRECATED - err = sysfs_create_link(block_depr, &ddev->kobj, - kobject_name(&ddev->kobj)); - if (err) { - device_del(ddev); - return; + if (!sysfs_deprecated) { + err = sysfs_create_link(block_depr, &ddev->kobj, + kobject_name(&ddev->kobj)); + if (err) { + device_del(ddev); + return; + } } -#endif disk->part0.holder_dir = kobject_create_and_add("holders", &ddev->kobj); disk->slave_dir = kobject_create_and_add("slaves", &ddev->kobj); @@ -642,6 +666,7 @@ rescan: /* add partitions */ for (p = 1; p < state->limit; p++) { sector_t size, from; + struct partition_meta_info *info = NULL; size = state->parts[p].size; if (!size) @@ -675,8 +700,12 @@ rescan: size = get_capacity(disk) - from; } } + + if (state->parts[p].has_info) + info = &state->parts[p].info; part = add_partition(disk, p, from, size, - state->parts[p].flags); + state->parts[p].flags, + &state->parts[p].info); if (IS_ERR(part)) { printk(KERN_ERR " %s: p%d could not be added: %ld\n", disk->disk_name, p, -PTR_ERR(part)); @@ -737,8 +766,7 @@ void del_gendisk(struct gendisk *disk) kobject_put(disk->part0.holder_dir); kobject_put(disk->slave_dir); disk->driverfs_dev = NULL; -#ifndef CONFIG_SYSFS_DEPRECATED - sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk))); -#endif + if (!sysfs_deprecated) + sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk))); device_del(disk_to_dev(disk)); } diff --git a/fs/partitions/check.h b/fs/partitions/check.h index 8e4e103ba216..d68bf4dc3bc2 100644 --- a/fs/partitions/check.h +++ b/fs/partitions/check.h @@ -1,5 +1,6 @@ #include <linux/pagemap.h> #include <linux/blkdev.h> +#include <linux/genhd.h> /* * add_gd_partition adds a partitions details to the devices partition @@ -12,6 +13,8 @@ struct parsed_partitions { sector_t from; sector_t size; int flags; + bool has_info; + struct partition_meta_info info; } parts[DISK_MAX_PARTS]; int next; int limit; diff --git a/fs/partitions/efi.c b/fs/partitions/efi.c index dbb44d4bb8a7..ac0ccb5026a2 100644 --- a/fs/partitions/efi.c +++ b/fs/partitions/efi.c @@ -94,6 +94,7 @@ * ************************************************************/ #include <linux/crc32.h> +#include <linux/ctype.h> #include <linux/math64.h> #include <linux/slab.h> #include "check.h" @@ -604,6 +605,7 @@ int efi_partition(struct parsed_partitions *state) gpt_entry *ptes = NULL; u32 i; unsigned ssz = bdev_logical_block_size(state->bdev) / 512; + u8 unparsed_guid[37]; if (!find_valid_gpt(state, &gpt, &ptes) || !gpt || !ptes) { kfree(gpt); @@ -614,6 +616,9 @@ int efi_partition(struct parsed_partitions *state) pr_debug("GUID Partition Table is valid! Yea!\n"); for (i = 0; i < le32_to_cpu(gpt->num_partition_entries) && i < state->limit-1; i++) { + struct partition_meta_info *info; + unsigned label_count = 0; + unsigned label_max; u64 start = le64_to_cpu(ptes[i].starting_lba); u64 size = le64_to_cpu(ptes[i].ending_lba) - le64_to_cpu(ptes[i].starting_lba) + 1ULL; @@ -627,6 +632,26 @@ int efi_partition(struct parsed_partitions *state) if (!efi_guidcmp(ptes[i].partition_type_guid, PARTITION_LINUX_RAID_GUID)) state->parts[i + 1].flags = ADDPART_FLAG_RAID; + + info = &state->parts[i + 1].info; + /* Instead of doing a manual swap to big endian, reuse the + * common ASCII hex format as the interim. + */ + efi_guid_unparse(&ptes[i].unique_partition_guid, unparsed_guid); + part_pack_uuid(unparsed_guid, info->uuid); + + /* Naively convert UTF16-LE to 7 bits. */ + label_max = min(sizeof(info->volname) - 1, + sizeof(ptes[i].partition_name)); + info->volname[label_max] = 0; + while (label_count < label_max) { + u8 c = ptes[i].partition_name[label_count] & 0xff; + if (c && !isprint(c)) + c = '!'; + info->volname[label_count] = c; + label_count++; + } + state->parts[i + 1].has_info = true; } kfree(ptes); kfree(gpt); diff --git a/fs/pipe.c b/fs/pipe.c index 279eef96c51c..37eb1ebeaa90 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -382,7 +382,7 @@ pipe_read(struct kiocb *iocb, const struct iovec *_iov, error = ops->confirm(pipe, buf); if (error) { if (!ret) - error = ret; + ret = error; break; } diff --git a/fs/proc/proc_tty.c b/fs/proc/proc_tty.c index 83adcc869437..dc44f94022f1 100644 --- a/fs/proc/proc_tty.c +++ b/fs/proc/proc_tty.c @@ -12,7 +12,10 @@ #include <linux/proc_fs.h> #include <linux/stat.h> #include <linux/tty.h> +#include <linux/tty_driver.h> +#include <linux/console.h> #include <linux/seq_file.h> +#include <linux/fdtable.h> #include <linux/bitops.h> /* @@ -137,6 +140,160 @@ static const struct file_operations proc_tty_drivers_operations = { }; /* + * The device ID of file descriptor 0 of the current reading + * task if a character device... + */ +static dev_t current_dev; + +/* + * This is the handler for /proc/tty/consoles + */ +static int show_console_dev(struct seq_file *m, void *v) +{ + const struct tty_driver *driver; + struct console *con; + int index, len; + char flags[10]; + dev_t dev; + + if (v == SEQ_START_TOKEN) + return 0; + con = (struct console *)v; + if (!con) + return 0; + driver = con->device(con, &index); + if (!driver) + return 0; + dev = MKDEV(driver->major, driver->minor_start) + index; + + index = 0; + if (con->flags & CON_ENABLED) + flags[index++] = 'E'; + if (con->flags & CON_CONSDEV) + flags[index++] = 'C'; + if (con->flags & CON_BOOT) + flags[index++] = 'B'; + if (con->flags & CON_PRINTBUFFER) + flags[index++] = 'p'; + if (con->flags & CON_BRL) + flags[index++] = 'b'; + if (con->flags & CON_ANYTIME) + flags[index++] = 'a'; + if (current_dev == dev) + flags[index++] = '*'; + flags[index] = 0; + + seq_printf(m, "%s%d%n", con->name, con->index, &len); + len = 21 - len; + if (len < 1) + len = 1; + seq_printf(m, "%*c", len, ' '); + seq_printf(m, "%c%c%c (%s)%n", con->read ? 'R' : '-', + con->write ? 'W' : '-', con->unblank ? 'U' : '-', + flags, &len); + len = 13 - len; + if (len < 1) + len = 1; + seq_printf(m, "%*c%4d:%d\n", len, ' ', MAJOR(dev), MINOR(dev)); + + return 0; +} + +/* iterator for consoles */ +static void *c_start(struct seq_file *m, loff_t *pos) +{ + struct console *con; + loff_t off = 0; + + if (*pos == 0) + return SEQ_START_TOKEN; + + acquire_console_sem(); + for (con = console_drivers; con; con = con->next) { + if (!con->device) + continue; + if (++off == *pos) + break; + } + release_console_sem(); + + return con; +} + +static void *c_next(struct seq_file *m, void *v, loff_t *pos) +{ + struct console *con; + + acquire_console_sem(); + if (v == SEQ_START_TOKEN) + con = console_drivers; + else + con = ((struct console *)v)->next; + for (; con; con = con->next) { + if (!con->device) + continue; + ++*pos; + break; + } + release_console_sem(); + + return con; +} + +static void c_stop(struct seq_file *m, void *v) +{ +} + +static const struct seq_operations tty_consoles_op = { + .start = c_start, + .next = c_next, + .stop = c_stop, + .show = show_console_dev +}; + +/* + * Used for open /proc/tty/consoles. Before this detect + * the device ID of file descriptor 0 of the current + * reading task if a character device... + */ +static int tty_consoles_open(struct inode *inode, struct file *file) +{ + struct files_struct *curfiles; + + current_dev = 0; + curfiles = get_files_struct(current); + if (curfiles) { + const struct file *curfp; + spin_lock(&curfiles->file_lock); + curfp = fcheck_files(curfiles, 0); + if (curfp && curfp->private_data) { + const struct inode *inode; + dget(curfp->f_dentry); + inode = curfp->f_dentry->d_inode; + if (S_ISCHR(inode->i_mode)) { + struct tty_struct *tty; + tty = (struct tty_struct *)curfp->private_data; + if (tty && tty->magic == TTY_MAGIC) { + tty = tty_pair_get_tty(tty); + current_dev = tty_devnum(tty); + } + } + dput(curfp->f_dentry); + } + spin_unlock(&curfiles->file_lock); + put_files_struct(curfiles); + } + return seq_open(file, &tty_consoles_op); +} + +static const struct file_operations proc_tty_consoles_operations = { + .open = tty_consoles_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +/* * This function is called by tty_register_driver() to handle * registering the driver's /proc handler into /proc/tty/driver/<foo> */ @@ -186,4 +343,5 @@ void __init proc_tty_init(void) proc_tty_driver = proc_mkdir_mode("tty/driver", S_IRUSR|S_IXUSR, NULL); proc_create("tty/ldiscs", 0, NULL, &tty_ldiscs_proc_fops); proc_create("tty/drivers", 0, NULL, &proc_tty_drivers_operations); + proc_create("tty/consoles", 0, NULL, &proc_tty_consoles_operations); } diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c index 6846371498b6..91f080cc76c8 100644 --- a/fs/reiserfs/file.c +++ b/fs/reiserfs/file.c @@ -152,8 +152,7 @@ static int reiserfs_sync_file(struct file *filp, int datasync) barrier_done = reiserfs_commit_for_inode(inode); reiserfs_write_unlock(inode->i_sb); if (barrier_done != 1 && reiserfs_barrier_flush(inode->i_sb)) - blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL, - BLKDEV_IFL_WAIT); + blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL); if (barrier_done < 0) return barrier_done; return (err < 0) ? -EIO : 0; diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c index 812e2c05aa29..076c8b194682 100644 --- a/fs/reiserfs/journal.c +++ b/fs/reiserfs/journal.c @@ -138,13 +138,6 @@ static int reiserfs_clean_and_file_buffer(struct buffer_head *bh) return 0; } -static void disable_barrier(struct super_block *s) -{ - REISERFS_SB(s)->s_mount_opt &= ~(1 << REISERFS_BARRIER_FLUSH); - printk("reiserfs: disabling flush barriers on %s\n", - reiserfs_bdevname(s)); -} - static struct reiserfs_bitmap_node *allocate_bitmap_node(struct super_block *sb) { @@ -677,30 +670,6 @@ static void submit_ordered_buffer(struct buffer_head *bh) submit_bh(WRITE, bh); } -static int submit_barrier_buffer(struct buffer_head *bh) -{ - get_bh(bh); - bh->b_end_io = reiserfs_end_ordered_io; - clear_buffer_dirty(bh); - if (!buffer_uptodate(bh)) - BUG(); - return submit_bh(WRITE_BARRIER, bh); -} - -static void check_barrier_completion(struct super_block *s, - struct buffer_head *bh) -{ - if (buffer_eopnotsupp(bh)) { - clear_buffer_eopnotsupp(bh); - disable_barrier(s); - set_buffer_uptodate(bh); - set_buffer_dirty(bh); - reiserfs_write_unlock(s); - sync_dirty_buffer(bh); - reiserfs_write_lock(s); - } -} - #define CHUNK_SIZE 32 struct buffer_chunk { struct buffer_head *bh[CHUNK_SIZE]; @@ -1009,7 +978,6 @@ static int flush_commit_list(struct super_block *s, struct buffer_head *tbh = NULL; unsigned int trans_id = jl->j_trans_id; struct reiserfs_journal *journal = SB_JOURNAL(s); - int barrier = 0; int retval = 0; int write_len; @@ -1094,24 +1062,6 @@ static int flush_commit_list(struct super_block *s, } atomic_dec(&journal->j_async_throttle); - /* We're skipping the commit if there's an error */ - if (retval || reiserfs_is_journal_aborted(journal)) - barrier = 0; - - /* wait on everything written so far before writing the commit - * if we are in barrier mode, send the commit down now - */ - barrier = reiserfs_barrier_flush(s); - if (barrier) { - int ret; - lock_buffer(jl->j_commit_bh); - ret = submit_barrier_buffer(jl->j_commit_bh); - if (ret == -EOPNOTSUPP) { - set_buffer_uptodate(jl->j_commit_bh); - disable_barrier(s); - barrier = 0; - } - } for (i = 0; i < (jl->j_len + 1); i++) { bn = SB_ONDISK_JOURNAL_1st_BLOCK(s) + (jl->j_start + i) % SB_ONDISK_JOURNAL_SIZE(s); @@ -1143,27 +1093,22 @@ static int flush_commit_list(struct super_block *s, BUG_ON(atomic_read(&(jl->j_commit_left)) != 1); - if (!barrier) { - /* If there was a write error in the journal - we can't commit - * this transaction - it will be invalid and, if successful, - * will just end up propagating the write error out to - * the file system. */ - if (likely(!retval && !reiserfs_is_journal_aborted (journal))) { - if (buffer_dirty(jl->j_commit_bh)) - BUG(); - mark_buffer_dirty(jl->j_commit_bh) ; - reiserfs_write_unlock(s); - sync_dirty_buffer(jl->j_commit_bh) ; - reiserfs_write_lock(s); - } - } else { + /* If there was a write error in the journal - we can't commit + * this transaction - it will be invalid and, if successful, + * will just end up propagating the write error out to + * the file system. */ + if (likely(!retval && !reiserfs_is_journal_aborted (journal))) { + if (buffer_dirty(jl->j_commit_bh)) + BUG(); + mark_buffer_dirty(jl->j_commit_bh) ; reiserfs_write_unlock(s); - wait_on_buffer(jl->j_commit_bh); + if (reiserfs_barrier_flush(s)) + __sync_dirty_buffer(jl->j_commit_bh, WRITE_FLUSH_FUA); + else + sync_dirty_buffer(jl->j_commit_bh); reiserfs_write_lock(s); } - check_barrier_completion(s, jl->j_commit_bh); - /* If there was a write error in the journal - we can't commit this * transaction - it will be invalid and, if successful, will just end * up propagating the write error out to the filesystem. */ @@ -1319,26 +1264,15 @@ static int _update_journal_header_block(struct super_block *sb, jh->j_first_unflushed_offset = cpu_to_le32(offset); jh->j_mount_id = cpu_to_le32(journal->j_mount_id); - if (reiserfs_barrier_flush(sb)) { - int ret; - lock_buffer(journal->j_header_bh); - ret = submit_barrier_buffer(journal->j_header_bh); - if (ret == -EOPNOTSUPP) { - set_buffer_uptodate(journal->j_header_bh); - disable_barrier(sb); - goto sync; - } - reiserfs_write_unlock(sb); - wait_on_buffer(journal->j_header_bh); - reiserfs_write_lock(sb); - check_barrier_completion(sb, journal->j_header_bh); - } else { - sync: - set_buffer_dirty(journal->j_header_bh); - reiserfs_write_unlock(sb); + set_buffer_dirty(journal->j_header_bh); + reiserfs_write_unlock(sb); + + if (reiserfs_barrier_flush(sb)) + __sync_dirty_buffer(journal->j_header_bh, WRITE_FLUSH_FUA); + else sync_dirty_buffer(journal->j_header_bh); - reiserfs_write_lock(sb); - } + + reiserfs_write_lock(sb); if (!buffer_uptodate(journal->j_header_bh)) { reiserfs_warning(sb, "journal-837", "IO error during journal replay"); diff --git a/fs/sysfs/bin.c b/fs/sysfs/bin.c index 4e321f7353fa..a4759833d62d 100644 --- a/fs/sysfs/bin.c +++ b/fs/sysfs/bin.c @@ -179,30 +179,14 @@ static void bin_vma_open(struct vm_area_struct *vma) struct bin_buffer *bb = file->private_data; struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata; - if (!bb->vm_ops || !bb->vm_ops->open) - return; - - if (!sysfs_get_active(attr_sd)) - return; - - bb->vm_ops->open(vma); - - sysfs_put_active(attr_sd); -} - -static void bin_vma_close(struct vm_area_struct *vma) -{ - struct file *file = vma->vm_file; - struct bin_buffer *bb = file->private_data; - struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata; - - if (!bb->vm_ops || !bb->vm_ops->close) + if (!bb->vm_ops) return; if (!sysfs_get_active(attr_sd)) return; - bb->vm_ops->close(vma); + if (bb->vm_ops->open) + bb->vm_ops->open(vma); sysfs_put_active(attr_sd); } @@ -214,13 +198,15 @@ static int bin_fault(struct vm_area_struct *vma, struct vm_fault *vmf) struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata; int ret; - if (!bb->vm_ops || !bb->vm_ops->fault) + if (!bb->vm_ops) return VM_FAULT_SIGBUS; if (!sysfs_get_active(attr_sd)) return VM_FAULT_SIGBUS; - ret = bb->vm_ops->fault(vma, vmf); + ret = VM_FAULT_SIGBUS; + if (bb->vm_ops->fault) + ret = bb->vm_ops->fault(vma, vmf); sysfs_put_active(attr_sd); return ret; @@ -236,13 +222,12 @@ static int bin_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) if (!bb->vm_ops) return VM_FAULT_SIGBUS; - if (!bb->vm_ops->page_mkwrite) - return 0; - if (!sysfs_get_active(attr_sd)) return VM_FAULT_SIGBUS; - ret = bb->vm_ops->page_mkwrite(vma, vmf); + ret = 0; + if (bb->vm_ops->page_mkwrite) + ret = bb->vm_ops->page_mkwrite(vma, vmf); sysfs_put_active(attr_sd); return ret; @@ -256,13 +241,15 @@ static int bin_access(struct vm_area_struct *vma, unsigned long addr, struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata; int ret; - if (!bb->vm_ops || !bb->vm_ops->access) + if (!bb->vm_ops) return -EINVAL; if (!sysfs_get_active(attr_sd)) return -EINVAL; - ret = bb->vm_ops->access(vma, addr, buf, len, write); + ret = -EINVAL; + if (bb->vm_ops->access) + ret = bb->vm_ops->access(vma, addr, buf, len, write); sysfs_put_active(attr_sd); return ret; @@ -276,13 +263,15 @@ static int bin_set_policy(struct vm_area_struct *vma, struct mempolicy *new) struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata; int ret; - if (!bb->vm_ops || !bb->vm_ops->set_policy) + if (!bb->vm_ops) return 0; if (!sysfs_get_active(attr_sd)) return -EINVAL; - ret = bb->vm_ops->set_policy(vma, new); + ret = 0; + if (bb->vm_ops->set_policy) + ret = bb->vm_ops->set_policy(vma, new); sysfs_put_active(attr_sd); return ret; @@ -296,13 +285,15 @@ static struct mempolicy *bin_get_policy(struct vm_area_struct *vma, struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata; struct mempolicy *pol; - if (!bb->vm_ops || !bb->vm_ops->get_policy) + if (!bb->vm_ops) return vma->vm_policy; if (!sysfs_get_active(attr_sd)) return vma->vm_policy; - pol = bb->vm_ops->get_policy(vma, addr); + pol = vma->vm_policy; + if (bb->vm_ops->get_policy) + pol = bb->vm_ops->get_policy(vma, addr); sysfs_put_active(attr_sd); return pol; @@ -316,13 +307,15 @@ static int bin_migrate(struct vm_area_struct *vma, const nodemask_t *from, struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata; int ret; - if (!bb->vm_ops || !bb->vm_ops->migrate) + if (!bb->vm_ops) return 0; if (!sysfs_get_active(attr_sd)) return 0; - ret = bb->vm_ops->migrate(vma, from, to, flags); + ret = 0; + if (bb->vm_ops->migrate) + ret = bb->vm_ops->migrate(vma, from, to, flags); sysfs_put_active(attr_sd); return ret; @@ -331,7 +324,6 @@ static int bin_migrate(struct vm_area_struct *vma, const nodemask_t *from, static const struct vm_operations_struct bin_vm_ops = { .open = bin_vma_open, - .close = bin_vma_close, .fault = bin_fault, .page_mkwrite = bin_page_mkwrite, .access = bin_access, @@ -377,6 +369,14 @@ static int mmap(struct file *file, struct vm_area_struct *vma) if (bb->mmapped && bb->vm_ops != vma->vm_ops) goto out_put; + /* + * It is not possible to successfully wrap close. + * So error if someone is trying to use close. + */ + rc = -EINVAL; + if (vma->vm_ops && vma->vm_ops->close) + goto out_put; + rc = 0; bb->mmapped = 1; bb->vm_ops = vma->vm_ops; diff --git a/fs/ubifs/commit.c b/fs/ubifs/commit.c index 37fa7ed062d8..02429d81ca33 100644 --- a/fs/ubifs/commit.c +++ b/fs/ubifs/commit.c @@ -63,7 +63,9 @@ static int do_commit(struct ubifs_info *c) struct ubifs_lp_stats lst; dbg_cmt("start"); - if (c->ro_media) { + ubifs_assert(!c->ro_media && !c->ro_mount); + + if (c->ro_error) { err = -EROFS; goto out_up; } diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c index c6c553fd0b3d..0bee4dbffc31 100644 --- a/fs/ubifs/debug.c +++ b/fs/ubifs/debug.c @@ -2239,6 +2239,162 @@ out_free: return err; } +/** + * dbg_check_data_nodes_order - check that list of data nodes is sorted. + * @c: UBIFS file-system description object + * @head: the list of nodes ('struct ubifs_scan_node' objects) + * + * This function returns zero if the list of data nodes is sorted correctly, + * and %-EINVAL if not. + */ +int dbg_check_data_nodes_order(struct ubifs_info *c, struct list_head *head) +{ + struct list_head *cur; + struct ubifs_scan_node *sa, *sb; + + if (!(ubifs_chk_flags & UBIFS_CHK_GEN)) + return 0; + + for (cur = head->next; cur->next != head; cur = cur->next) { + ino_t inuma, inumb; + uint32_t blka, blkb; + + cond_resched(); + sa = container_of(cur, struct ubifs_scan_node, list); + sb = container_of(cur->next, struct ubifs_scan_node, list); + + if (sa->type != UBIFS_DATA_NODE) { + ubifs_err("bad node type %d", sa->type); + dbg_dump_node(c, sa->node); + return -EINVAL; + } + if (sb->type != UBIFS_DATA_NODE) { + ubifs_err("bad node type %d", sb->type); + dbg_dump_node(c, sb->node); + return -EINVAL; + } + + inuma = key_inum(c, &sa->key); + inumb = key_inum(c, &sb->key); + + if (inuma < inumb) + continue; + if (inuma > inumb) { + ubifs_err("larger inum %lu goes before inum %lu", + (unsigned long)inuma, (unsigned long)inumb); + goto error_dump; + } + + blka = key_block(c, &sa->key); + blkb = key_block(c, &sb->key); + + if (blka > blkb) { + ubifs_err("larger block %u goes before %u", blka, blkb); + goto error_dump; + } + if (blka == blkb) { + ubifs_err("two data nodes for the same block"); + goto error_dump; + } + } + + return 0; + +error_dump: + dbg_dump_node(c, sa->node); + dbg_dump_node(c, sb->node); + return -EINVAL; +} + +/** + * dbg_check_nondata_nodes_order - check that list of data nodes is sorted. + * @c: UBIFS file-system description object + * @head: the list of nodes ('struct ubifs_scan_node' objects) + * + * This function returns zero if the list of non-data nodes is sorted correctly, + * and %-EINVAL if not. + */ +int dbg_check_nondata_nodes_order(struct ubifs_info *c, struct list_head *head) +{ + struct list_head *cur; + struct ubifs_scan_node *sa, *sb; + + if (!(ubifs_chk_flags & UBIFS_CHK_GEN)) + return 0; + + for (cur = head->next; cur->next != head; cur = cur->next) { + ino_t inuma, inumb; + uint32_t hasha, hashb; + + cond_resched(); + sa = container_of(cur, struct ubifs_scan_node, list); + sb = container_of(cur->next, struct ubifs_scan_node, list); + + if (sa->type != UBIFS_INO_NODE && sa->type != UBIFS_DENT_NODE && + sa->type != UBIFS_XENT_NODE) { + ubifs_err("bad node type %d", sa->type); + dbg_dump_node(c, sa->node); + return -EINVAL; + } + if (sa->type != UBIFS_INO_NODE && sa->type != UBIFS_DENT_NODE && + sa->type != UBIFS_XENT_NODE) { + ubifs_err("bad node type %d", sb->type); + dbg_dump_node(c, sb->node); + return -EINVAL; + } + + if (sa->type != UBIFS_INO_NODE && sb->type == UBIFS_INO_NODE) { + ubifs_err("non-inode node goes before inode node"); + goto error_dump; + } + + if (sa->type == UBIFS_INO_NODE && sb->type != UBIFS_INO_NODE) + continue; + + if (sa->type == UBIFS_INO_NODE && sb->type == UBIFS_INO_NODE) { + /* Inode nodes are sorted in descending size order */ + if (sa->len < sb->len) { + ubifs_err("smaller inode node goes first"); + goto error_dump; + } + continue; + } + + /* + * This is either a dentry or xentry, which should be sorted in + * ascending (parent ino, hash) order. + */ + inuma = key_inum(c, &sa->key); + inumb = key_inum(c, &sb->key); + + if (inuma < inumb) + continue; + if (inuma > inumb) { + ubifs_err("larger inum %lu goes before inum %lu", + (unsigned long)inuma, (unsigned long)inumb); + goto error_dump; + } + + hasha = key_block(c, &sa->key); + hashb = key_block(c, &sb->key); + + if (hasha > hashb) { + ubifs_err("larger hash %u goes before %u", hasha, hashb); + goto error_dump; + } + } + + return 0; + +error_dump: + ubifs_msg("dumping first node"); + dbg_dump_node(c, sa->node); + ubifs_msg("dumping second node"); + dbg_dump_node(c, sb->node); + return -EINVAL; + return 0; +} + static int invocation_cnt; int dbg_force_in_the_gaps(void) diff --git a/fs/ubifs/debug.h b/fs/ubifs/debug.h index 29d960101ea6..69ebe4729151 100644 --- a/fs/ubifs/debug.h +++ b/fs/ubifs/debug.h @@ -324,6 +324,8 @@ int dbg_check_lpt_nodes(struct ubifs_info *c, struct ubifs_cnode *cnode, int row, int col); int dbg_check_inode_size(struct ubifs_info *c, const struct inode *inode, loff_t size); +int dbg_check_data_nodes_order(struct ubifs_info *c, struct list_head *head); +int dbg_check_nondata_nodes_order(struct ubifs_info *c, struct list_head *head); /* Force the use of in-the-gaps method for testing */ @@ -465,6 +467,8 @@ void dbg_debugfs_exit_fs(struct ubifs_info *c); #define dbg_check_lprops(c) 0 #define dbg_check_lpt_nodes(c, cnode, row, col) 0 #define dbg_check_inode_size(c, inode, size) 0 +#define dbg_check_data_nodes_order(c, head) 0 +#define dbg_check_nondata_nodes_order(c, head) 0 #define dbg_force_in_the_gaps_enabled 0 #define dbg_force_in_the_gaps() 0 #define dbg_failure_mode 0 diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 03ae894c45de..d77db7e36484 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -433,8 +433,9 @@ static int ubifs_write_begin(struct file *file, struct address_space *mapping, struct page *page; ubifs_assert(ubifs_inode(inode)->ui_size == inode->i_size); + ubifs_assert(!c->ro_media && !c->ro_mount); - if (unlikely(c->ro_media)) + if (unlikely(c->ro_error)) return -EROFS; /* Try out the fast-path part first */ @@ -1439,9 +1440,9 @@ static int ubifs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vm dbg_gen("ino %lu, pg %lu, i_size %lld", inode->i_ino, page->index, i_size_read(inode)); - ubifs_assert(!(inode->i_sb->s_flags & MS_RDONLY)); + ubifs_assert(!c->ro_media && !c->ro_mount); - if (unlikely(c->ro_media)) + if (unlikely(c->ro_error)) return VM_FAULT_SIGBUS; /* -EROFS */ /* diff --git a/fs/ubifs/gc.c b/fs/ubifs/gc.c index 918d1582ca05..151f10882820 100644 --- a/fs/ubifs/gc.c +++ b/fs/ubifs/gc.c @@ -125,10 +125,16 @@ int data_nodes_cmp(void *priv, struct list_head *a, struct list_head *b) struct ubifs_scan_node *sa, *sb; cond_resched(); + if (a == b) + return 0; + sa = list_entry(a, struct ubifs_scan_node, list); sb = list_entry(b, struct ubifs_scan_node, list); + ubifs_assert(key_type(c, &sa->key) == UBIFS_DATA_KEY); ubifs_assert(key_type(c, &sb->key) == UBIFS_DATA_KEY); + ubifs_assert(sa->type == UBIFS_DATA_NODE); + ubifs_assert(sb->type == UBIFS_DATA_NODE); inuma = key_inum(c, &sa->key); inumb = key_inum(c, &sb->key); @@ -157,28 +163,40 @@ int data_nodes_cmp(void *priv, struct list_head *a, struct list_head *b) */ int nondata_nodes_cmp(void *priv, struct list_head *a, struct list_head *b) { - int typea, typeb; ino_t inuma, inumb; struct ubifs_info *c = priv; struct ubifs_scan_node *sa, *sb; cond_resched(); + if (a == b) + return 0; + sa = list_entry(a, struct ubifs_scan_node, list); sb = list_entry(b, struct ubifs_scan_node, list); - typea = key_type(c, &sa->key); - typeb = key_type(c, &sb->key); - ubifs_assert(typea != UBIFS_DATA_KEY && typeb != UBIFS_DATA_KEY); + + ubifs_assert(key_type(c, &sa->key) != UBIFS_DATA_KEY && + key_type(c, &sb->key) != UBIFS_DATA_KEY); + ubifs_assert(sa->type != UBIFS_DATA_NODE && + sb->type != UBIFS_DATA_NODE); /* Inodes go before directory entries */ - if (typea == UBIFS_INO_KEY) { - if (typeb == UBIFS_INO_KEY) + if (sa->type == UBIFS_INO_NODE) { + if (sb->type == UBIFS_INO_NODE) return sb->len - sa->len; return -1; } - if (typeb == UBIFS_INO_KEY) + if (sb->type == UBIFS_INO_NODE) return 1; - ubifs_assert(typea == UBIFS_DENT_KEY && typeb == UBIFS_DENT_KEY); + ubifs_assert(key_type(c, &sa->key) == UBIFS_DENT_KEY || + key_type(c, &sa->key) == UBIFS_XENT_KEY); + ubifs_assert(key_type(c, &sb->key) == UBIFS_DENT_KEY || + key_type(c, &sb->key) == UBIFS_XENT_KEY); + ubifs_assert(sa->type == UBIFS_DENT_NODE || + sa->type == UBIFS_XENT_NODE); + ubifs_assert(sb->type == UBIFS_DENT_NODE || + sb->type == UBIFS_XENT_NODE); + inuma = key_inum(c, &sa->key); inumb = key_inum(c, &sb->key); @@ -224,17 +242,33 @@ int nondata_nodes_cmp(void *priv, struct list_head *a, struct list_head *b) static int sort_nodes(struct ubifs_info *c, struct ubifs_scan_leb *sleb, struct list_head *nondata, int *min) { + int err; struct ubifs_scan_node *snod, *tmp; *min = INT_MAX; /* Separate data nodes and non-data nodes */ list_for_each_entry_safe(snod, tmp, &sleb->nodes, list) { - int err; + ubifs_assert(snod->type == UBIFS_INO_NODE || + snod->type == UBIFS_DATA_NODE || + snod->type == UBIFS_DENT_NODE || + snod->type == UBIFS_XENT_NODE || + snod->type == UBIFS_TRUN_NODE); + + if (snod->type != UBIFS_INO_NODE && + snod->type != UBIFS_DATA_NODE && + snod->type != UBIFS_DENT_NODE && + snod->type != UBIFS_XENT_NODE) { + /* Probably truncation node, zap it */ + list_del(&snod->list); + kfree(snod); + continue; + } - ubifs_assert(snod->type != UBIFS_IDX_NODE); - ubifs_assert(snod->type != UBIFS_REF_NODE); - ubifs_assert(snod->type != UBIFS_CS_NODE); + ubifs_assert(key_type(c, &snod->key) == UBIFS_DATA_KEY || + key_type(c, &snod->key) == UBIFS_INO_KEY || + key_type(c, &snod->key) == UBIFS_DENT_KEY || + key_type(c, &snod->key) == UBIFS_XENT_KEY); err = ubifs_tnc_has_node(c, &snod->key, 0, sleb->lnum, snod->offs, 0); @@ -258,6 +292,13 @@ static int sort_nodes(struct ubifs_info *c, struct ubifs_scan_leb *sleb, /* Sort data and non-data nodes */ list_sort(c, &sleb->nodes, &data_nodes_cmp); list_sort(c, nondata, &nondata_nodes_cmp); + + err = dbg_check_data_nodes_order(c, &sleb->nodes); + if (err) + return err; + err = dbg_check_nondata_nodes_order(c, nondata); + if (err) + return err; return 0; } @@ -575,13 +616,14 @@ int ubifs_garbage_collect(struct ubifs_info *c, int anyway) struct ubifs_wbuf *wbuf = &c->jheads[GCHD].wbuf; ubifs_assert_cmt_locked(c); + ubifs_assert(!c->ro_media && !c->ro_mount); if (ubifs_gc_should_commit(c)) return -EAGAIN; mutex_lock_nested(&wbuf->io_mutex, wbuf->jhead); - if (c->ro_media) { + if (c->ro_error) { ret = -EROFS; goto out_unlock; } @@ -677,14 +719,12 @@ int ubifs_garbage_collect(struct ubifs_info *c, int anyway) ret = ubifs_garbage_collect_leb(c, &lp); if (ret < 0) { - if (ret == -EAGAIN || ret == -ENOSPC) { + if (ret == -EAGAIN) { /* - * These codes are not errors, so we have to - * return the LEB to lprops. But if the - * 'ubifs_return_leb()' function fails, its - * failure code is propagated to the caller - * instead of the original '-EAGAIN' or - * '-ENOSPC'. + * This is not error, so we have to return the + * LEB to lprops. But if 'ubifs_return_leb()' + * fails, its failure code is propagated to the + * caller instead of the original '-EAGAIN'. */ err = ubifs_return_leb(c, lp.lnum); if (err) @@ -774,8 +814,8 @@ out_unlock: out: ubifs_assert(ret < 0); ubifs_assert(ret != -ENOSPC && ret != -EAGAIN); - ubifs_ro_mode(c, ret); ubifs_wbuf_sync_nolock(wbuf); + ubifs_ro_mode(c, ret); mutex_unlock(&wbuf->io_mutex); ubifs_return_leb(c, lp.lnum); return ret; diff --git a/fs/ubifs/io.c b/fs/ubifs/io.c index bcf5a16f30bb..d82173182eeb 100644 --- a/fs/ubifs/io.c +++ b/fs/ubifs/io.c @@ -61,8 +61,8 @@ */ void ubifs_ro_mode(struct ubifs_info *c, int err) { - if (!c->ro_media) { - c->ro_media = 1; + if (!c->ro_error) { + c->ro_error = 1; c->no_chk_data_crc = 0; c->vfs_sb->s_flags |= MS_RDONLY; ubifs_warn("switched to read-only mode, error %d", err); @@ -356,11 +356,11 @@ int ubifs_wbuf_sync_nolock(struct ubifs_wbuf *wbuf) dbg_io("LEB %d:%d, %d bytes, jhead %s", wbuf->lnum, wbuf->offs, wbuf->used, dbg_jhead(wbuf->jhead)); - ubifs_assert(!(c->vfs_sb->s_flags & MS_RDONLY)); ubifs_assert(!(wbuf->avail & 7)); ubifs_assert(wbuf->offs + c->min_io_size <= c->leb_size); + ubifs_assert(!c->ro_media && !c->ro_mount); - if (c->ro_media) + if (c->ro_error) return -EROFS; ubifs_pad(c, wbuf->buf + wbuf->used, wbuf->avail); @@ -440,11 +440,12 @@ int ubifs_bg_wbufs_sync(struct ubifs_info *c) { int err, i; + ubifs_assert(!c->ro_media && !c->ro_mount); if (!c->need_wbuf_sync) return 0; c->need_wbuf_sync = 0; - if (c->ro_media) { + if (c->ro_error) { err = -EROFS; goto out_timers; } @@ -519,6 +520,7 @@ int ubifs_wbuf_write_nolock(struct ubifs_wbuf *wbuf, void *buf, int len) ubifs_assert(!(wbuf->offs & 7) && wbuf->offs <= c->leb_size); ubifs_assert(wbuf->avail > 0 && wbuf->avail <= c->min_io_size); ubifs_assert(mutex_is_locked(&wbuf->io_mutex)); + ubifs_assert(!c->ro_media && !c->ro_mount); if (c->leb_size - wbuf->offs - wbuf->used < aligned_len) { err = -ENOSPC; @@ -527,7 +529,7 @@ int ubifs_wbuf_write_nolock(struct ubifs_wbuf *wbuf, void *buf, int len) cancel_wbuf_timer_nolock(wbuf); - if (c->ro_media) + if (c->ro_error) return -EROFS; if (aligned_len <= wbuf->avail) { @@ -663,8 +665,9 @@ int ubifs_write_node(struct ubifs_info *c, void *buf, int len, int lnum, buf_len); ubifs_assert(lnum >= 0 && lnum < c->leb_cnt && offs >= 0); ubifs_assert(offs % c->min_io_size == 0 && offs < c->leb_size); + ubifs_assert(!c->ro_media && !c->ro_mount); - if (c->ro_media) + if (c->ro_error) return -EROFS; ubifs_prepare_node(c, buf, len, 1); @@ -815,7 +818,8 @@ int ubifs_read_node(const struct ubifs_info *c, void *buf, int type, int len, return 0; out: - ubifs_err("bad node at LEB %d:%d", lnum, offs); + ubifs_err("bad node at LEB %d:%d, LEB mapping status %d", lnum, offs, + ubi_is_mapped(c->ubi, lnum)); dbg_dump_node(c, buf); dbg_dump_stack(); return -EINVAL; diff --git a/fs/ubifs/journal.c b/fs/ubifs/journal.c index d321baeca68d..914f1bd89e57 100644 --- a/fs/ubifs/journal.c +++ b/fs/ubifs/journal.c @@ -122,11 +122,12 @@ static int reserve_space(struct ubifs_info *c, int jhead, int len) * better to try to allocate space at the ends of eraseblocks. This is * what the squeeze parameter does. */ + ubifs_assert(!c->ro_media && !c->ro_mount); squeeze = (jhead == BASEHD); again: mutex_lock_nested(&wbuf->io_mutex, wbuf->jhead); - if (c->ro_media) { + if (c->ro_error) { err = -EROFS; goto out_unlock; } diff --git a/fs/ubifs/key.h b/fs/ubifs/key.h index 0f530c684f0b..92a8491a8f8c 100644 --- a/fs/ubifs/key.h +++ b/fs/ubifs/key.h @@ -306,6 +306,20 @@ static inline void trun_key_init(const struct ubifs_info *c, } /** + * invalid_key_init - initialize invalid node key. + * @c: UBIFS file-system description object + * @key: key to initialize + * + * This is a helper function which marks a @key object as invalid. + */ +static inline void invalid_key_init(const struct ubifs_info *c, + union ubifs_key *key) +{ + key->u32[0] = 0xDEADBEAF; + key->u32[1] = UBIFS_INVALID_KEY; +} + +/** * key_type - get key type. * @c: UBIFS file-system description object * @key: key to get type of diff --git a/fs/ubifs/log.c b/fs/ubifs/log.c index c345e125f42c..4d0cb1241460 100644 --- a/fs/ubifs/log.c +++ b/fs/ubifs/log.c @@ -159,7 +159,7 @@ void ubifs_add_bud(struct ubifs_info *c, struct ubifs_bud *bud) jhead = &c->jheads[bud->jhead]; list_add_tail(&bud->list, &jhead->buds_list); } else - ubifs_assert(c->replaying && (c->vfs_sb->s_flags & MS_RDONLY)); + ubifs_assert(c->replaying && c->ro_mount); /* * Note, although this is a new bud, we anyway account this space now, @@ -223,8 +223,8 @@ int ubifs_add_bud_to_log(struct ubifs_info *c, int jhead, int lnum, int offs) } mutex_lock(&c->log_mutex); - - if (c->ro_media) { + ubifs_assert(!c->ro_media && !c->ro_mount); + if (c->ro_error) { err = -EROFS; goto out_unlock; } diff --git a/fs/ubifs/lpt.c b/fs/ubifs/lpt.c index 0084a33c4c69..72775d35b99e 100644 --- a/fs/ubifs/lpt.c +++ b/fs/ubifs/lpt.c @@ -1363,6 +1363,7 @@ static int read_lsave(struct ubifs_info *c) goto out; for (i = 0; i < c->lsave_cnt; i++) { int lnum = c->lsave[i]; + struct ubifs_lprops *lprops; /* * Due to automatic resizing, the values in the lsave table @@ -1370,7 +1371,11 @@ static int read_lsave(struct ubifs_info *c) */ if (lnum >= c->leb_cnt) continue; - ubifs_lpt_lookup(c, lnum); + lprops = ubifs_lpt_lookup(c, lnum); + if (IS_ERR(lprops)) { + err = PTR_ERR(lprops); + goto out; + } } out: vfree(buf); diff --git a/fs/ubifs/lpt_commit.c b/fs/ubifs/lpt_commit.c index d12535b7fc78..5c90dec5db0b 100644 --- a/fs/ubifs/lpt_commit.c +++ b/fs/ubifs/lpt_commit.c @@ -705,6 +705,9 @@ static int make_tree_dirty(struct ubifs_info *c) struct ubifs_pnode *pnode; pnode = pnode_lookup(c, 0); + if (IS_ERR(pnode)) + return PTR_ERR(pnode); + while (pnode) { do_make_pnode_dirty(c, pnode); pnode = next_pnode_to_dirty(c, pnode); diff --git a/fs/ubifs/master.c b/fs/ubifs/master.c index 28beaeedadc0..21f47afdacff 100644 --- a/fs/ubifs/master.c +++ b/fs/ubifs/master.c @@ -361,7 +361,8 @@ int ubifs_write_master(struct ubifs_info *c) { int err, lnum, offs, len; - if (c->ro_media) + ubifs_assert(!c->ro_media && !c->ro_mount); + if (c->ro_error) return -EROFS; lnum = UBIFS_MST_LNUM; diff --git a/fs/ubifs/misc.h b/fs/ubifs/misc.h index 4fa81d867e41..c3de04dc952a 100644 --- a/fs/ubifs/misc.h +++ b/fs/ubifs/misc.h @@ -132,7 +132,8 @@ static inline int ubifs_leb_unmap(const struct ubifs_info *c, int lnum) { int err; - if (c->ro_media) + ubifs_assert(!c->ro_media && !c->ro_mount); + if (c->ro_error) return -EROFS; err = ubi_leb_unmap(c->ubi, lnum); if (err) { @@ -159,7 +160,8 @@ static inline int ubifs_leb_write(const struct ubifs_info *c, int lnum, { int err; - if (c->ro_media) + ubifs_assert(!c->ro_media && !c->ro_mount); + if (c->ro_error) return -EROFS; err = ubi_leb_write(c->ubi, lnum, buf, offs, len, dtype); if (err) { @@ -186,7 +188,8 @@ static inline int ubifs_leb_change(const struct ubifs_info *c, int lnum, { int err; - if (c->ro_media) + ubifs_assert(!c->ro_media && !c->ro_mount); + if (c->ro_error) return -EROFS; err = ubi_leb_change(c->ubi, lnum, buf, len, dtype); if (err) { diff --git a/fs/ubifs/recovery.c b/fs/ubifs/recovery.c index daae9e1f5382..77e9b874b6c2 100644 --- a/fs/ubifs/recovery.c +++ b/fs/ubifs/recovery.c @@ -292,7 +292,7 @@ int ubifs_recover_master_node(struct ubifs_info *c) memcpy(c->mst_node, mst, UBIFS_MST_NODE_SZ); - if ((c->vfs_sb->s_flags & MS_RDONLY)) { + if (c->ro_mount) { /* Read-only mode. Keep a copy for switching to rw mode */ c->rcvrd_mst_node = kmalloc(sz, GFP_KERNEL); if (!c->rcvrd_mst_node) { @@ -469,7 +469,7 @@ static int fix_unclean_leb(struct ubifs_info *c, struct ubifs_scan_leb *sleb, endpt = snod->offs + snod->len; } - if ((c->vfs_sb->s_flags & MS_RDONLY) && !c->remounting_rw) { + if (c->ro_mount && !c->remounting_rw) { /* Add to recovery list */ struct ubifs_unclean_leb *ucleb; @@ -772,7 +772,8 @@ out_free: * @sbuf: LEB-sized buffer to use * * This function does a scan of a LEB, but caters for errors that might have - * been caused by the unclean unmount from which we are attempting to recover. + * been caused by unclean reboots from which we are attempting to recover + * (assume that only the last log LEB can be corrupted by an unclean reboot). * * This function returns %0 on success and a negative error code on failure. */ @@ -883,7 +884,7 @@ int ubifs_recover_inl_heads(const struct ubifs_info *c, void *sbuf) { int err; - ubifs_assert(!(c->vfs_sb->s_flags & MS_RDONLY) || c->remounting_rw); + ubifs_assert(!c->ro_mount || c->remounting_rw); dbg_rcvry("checking index head at %d:%d", c->ihead_lnum, c->ihead_offs); err = recover_head(c, c->ihead_lnum, c->ihead_offs, sbuf); @@ -1461,7 +1462,7 @@ int ubifs_recover_size(struct ubifs_info *c) } } if (e->exists && e->i_size < e->d_size) { - if (!e->inode && (c->vfs_sb->s_flags & MS_RDONLY)) { + if (!e->inode && c->ro_mount) { /* Fix the inode size and pin it in memory */ struct inode *inode; diff --git a/fs/ubifs/replay.c b/fs/ubifs/replay.c index 5c2d6d759a3e..eed0fcff8d73 100644 --- a/fs/ubifs/replay.c +++ b/fs/ubifs/replay.c @@ -627,8 +627,7 @@ static int replay_bud(struct ubifs_info *c, int lnum, int offs, int jhead, ubifs_assert(sleb->endpt - offs >= used); ubifs_assert(sleb->endpt % c->min_io_size == 0); - if (sleb->endpt + c->min_io_size <= c->leb_size && - !(c->vfs_sb->s_flags & MS_RDONLY)) + if (sleb->endpt + c->min_io_size <= c->leb_size && !c->ro_mount) err = ubifs_wbuf_seek_nolock(&c->jheads[jhead].wbuf, lnum, sleb->endpt, UBI_SHORTTERM); @@ -840,6 +839,11 @@ static int replay_log_leb(struct ubifs_info *c, int lnum, int offs, void *sbuf) if (IS_ERR(sleb)) { if (PTR_ERR(sleb) != -EUCLEAN || !c->need_recovery) return PTR_ERR(sleb); + /* + * Note, the below function will recover this log LEB only if + * it is the last, because unclean reboots can possibly corrupt + * only the tail of the log. + */ sleb = ubifs_recover_log_leb(c, lnum, offs, sbuf); if (IS_ERR(sleb)) return PTR_ERR(sleb); @@ -851,7 +855,6 @@ static int replay_log_leb(struct ubifs_info *c, int lnum, int offs, void *sbuf) } node = sleb->buf; - snod = list_entry(sleb->nodes.next, struct ubifs_scan_node, list); if (c->cs_sqnum == 0) { /* @@ -898,7 +901,6 @@ static int replay_log_leb(struct ubifs_info *c, int lnum, int offs, void *sbuf) } list_for_each_entry(snod, &sleb->nodes, list) { - cond_resched(); if (snod->sqnum >= SQNUM_WATERMARK) { @@ -1011,7 +1013,6 @@ out: int ubifs_replay_journal(struct ubifs_info *c) { int err, i, lnum, offs, free; - void *sbuf = NULL; BUILD_BUG_ON(UBIFS_TRUN_KEY > 5); @@ -1026,14 +1027,8 @@ int ubifs_replay_journal(struct ubifs_info *c) return -EINVAL; } - sbuf = vmalloc(c->leb_size); - if (!sbuf) - return -ENOMEM; - dbg_mnt("start replaying the journal"); - c->replaying = 1; - lnum = c->ltail_lnum = c->lhead_lnum; offs = c->lhead_offs; @@ -1046,7 +1041,7 @@ int ubifs_replay_journal(struct ubifs_info *c) lnum = UBIFS_LOG_LNUM; offs = 0; } - err = replay_log_leb(c, lnum, offs, sbuf); + err = replay_log_leb(c, lnum, offs, c->sbuf); if (err == 1) /* We hit the end of the log */ break; @@ -1079,7 +1074,6 @@ int ubifs_replay_journal(struct ubifs_info *c) out: destroy_replay_tree(c); destroy_bud_list(c); - vfree(sbuf); c->replaying = 0; return err; } diff --git a/fs/ubifs/sb.c b/fs/ubifs/sb.c index 96cb62c8a9dd..bf31b4729e51 100644 --- a/fs/ubifs/sb.c +++ b/fs/ubifs/sb.c @@ -542,11 +542,8 @@ int ubifs_read_superblock(struct ubifs_info *c) * due to the unavailability of time-travelling equipment. */ if (c->fmt_version > UBIFS_FORMAT_VERSION) { - struct super_block *sb = c->vfs_sb; - int mounting_ro = sb->s_flags & MS_RDONLY; - - ubifs_assert(!c->ro_media || mounting_ro); - if (!mounting_ro || + ubifs_assert(!c->ro_media || c->ro_mount); + if (!c->ro_mount || c->ro_compat_version > UBIFS_RO_COMPAT_VERSION) { ubifs_err("on-flash format version is w%d/r%d, but " "software only supports up to version " @@ -624,7 +621,7 @@ int ubifs_read_superblock(struct ubifs_info *c) c->old_leb_cnt = c->leb_cnt; if (c->leb_cnt < c->vi.size && c->leb_cnt < c->max_leb_cnt) { c->leb_cnt = min_t(int, c->max_leb_cnt, c->vi.size); - if (c->vfs_sb->s_flags & MS_RDONLY) + if (c->ro_mount) dbg_mnt("Auto resizing (ro) from %d LEBs to %d LEBs", c->old_leb_cnt, c->leb_cnt); else { diff --git a/fs/ubifs/scan.c b/fs/ubifs/scan.c index 96c525384191..3e1ee57dbeaa 100644 --- a/fs/ubifs/scan.c +++ b/fs/ubifs/scan.c @@ -197,7 +197,7 @@ int ubifs_add_snod(const struct ubifs_info *c, struct ubifs_scan_leb *sleb, struct ubifs_ino_node *ino = buf; struct ubifs_scan_node *snod; - snod = kzalloc(sizeof(struct ubifs_scan_node), GFP_NOFS); + snod = kmalloc(sizeof(struct ubifs_scan_node), GFP_NOFS); if (!snod) return -ENOMEM; @@ -212,13 +212,15 @@ int ubifs_add_snod(const struct ubifs_info *c, struct ubifs_scan_leb *sleb, case UBIFS_DENT_NODE: case UBIFS_XENT_NODE: case UBIFS_DATA_NODE: - case UBIFS_TRUN_NODE: /* * The key is in the same place in all keyed * nodes. */ key_read(c, &ino->key, &snod->key); break; + default: + invalid_key_init(c, &snod->key); + break; } list_add_tail(&snod->list, &sleb->nodes); sleb->nodes_cnt += 1; diff --git a/fs/ubifs/shrinker.c b/fs/ubifs/shrinker.c index 0b201114a5ad..46961c003236 100644 --- a/fs/ubifs/shrinker.c +++ b/fs/ubifs/shrinker.c @@ -250,7 +250,7 @@ static int kick_a_thread(void) dirty_zn_cnt = atomic_long_read(&c->dirty_zn_cnt); if (!dirty_zn_cnt || c->cmt_state == COMMIT_BROKEN || - c->ro_media) { + c->ro_mount || c->ro_error) { mutex_unlock(&c->umount_mutex); continue; } diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index cd5900b85d38..9a47c9f0ad07 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -1137,11 +1137,11 @@ static int check_free_space(struct ubifs_info *c) */ static int mount_ubifs(struct ubifs_info *c) { - struct super_block *sb = c->vfs_sb; - int err, mounted_read_only = (sb->s_flags & MS_RDONLY); + int err; long long x; size_t sz; + c->ro_mount = !!(c->vfs_sb->s_flags & MS_RDONLY); err = init_constants_early(c); if (err) return err; @@ -1154,7 +1154,7 @@ static int mount_ubifs(struct ubifs_info *c) if (err) goto out_free; - if (c->empty && (mounted_read_only || c->ro_media)) { + if (c->empty && (c->ro_mount || c->ro_media)) { /* * This UBI volume is empty, and read-only, or the file system * is mounted read-only - we cannot format it. @@ -1165,7 +1165,7 @@ static int mount_ubifs(struct ubifs_info *c) goto out_free; } - if (c->ro_media && !mounted_read_only) { + if (c->ro_media && !c->ro_mount) { ubifs_err("cannot mount read-write - read-only media"); err = -EROFS; goto out_free; @@ -1185,7 +1185,7 @@ static int mount_ubifs(struct ubifs_info *c) if (!c->sbuf) goto out_free; - if (!mounted_read_only) { + if (!c->ro_mount) { c->ileb_buf = vmalloc(c->leb_size); if (!c->ileb_buf) goto out_free; @@ -1228,7 +1228,7 @@ static int mount_ubifs(struct ubifs_info *c) } sprintf(c->bgt_name, BGT_NAME_PATTERN, c->vi.ubi_num, c->vi.vol_id); - if (!mounted_read_only) { + if (!c->ro_mount) { err = alloc_wbufs(c); if (err) goto out_cbuf; @@ -1254,12 +1254,12 @@ static int mount_ubifs(struct ubifs_info *c) if ((c->mst_node->flags & cpu_to_le32(UBIFS_MST_DIRTY)) != 0) { ubifs_msg("recovery needed"); c->need_recovery = 1; - if (!mounted_read_only) { + if (!c->ro_mount) { err = ubifs_recover_inl_heads(c, c->sbuf); if (err) goto out_master; } - } else if (!mounted_read_only) { + } else if (!c->ro_mount) { /* * Set the "dirty" flag so that if we reboot uncleanly we * will notice this immediately on the next mount. @@ -1270,7 +1270,7 @@ static int mount_ubifs(struct ubifs_info *c) goto out_master; } - err = ubifs_lpt_init(c, 1, !mounted_read_only); + err = ubifs_lpt_init(c, 1, !c->ro_mount); if (err) goto out_lpt; @@ -1285,11 +1285,11 @@ static int mount_ubifs(struct ubifs_info *c) /* Calculate 'min_idx_lebs' after journal replay */ c->min_idx_lebs = ubifs_calc_min_idx_lebs(c); - err = ubifs_mount_orphans(c, c->need_recovery, mounted_read_only); + err = ubifs_mount_orphans(c, c->need_recovery, c->ro_mount); if (err) goto out_orphans; - if (!mounted_read_only) { + if (!c->ro_mount) { int lnum; err = check_free_space(c); @@ -1351,7 +1351,7 @@ static int mount_ubifs(struct ubifs_info *c) spin_unlock(&ubifs_infos_lock); if (c->need_recovery) { - if (mounted_read_only) + if (c->ro_mount) ubifs_msg("recovery deferred"); else { c->need_recovery = 0; @@ -1378,7 +1378,7 @@ static int mount_ubifs(struct ubifs_info *c) ubifs_msg("mounted UBI device %d, volume %d, name \"%s\"", c->vi.ubi_num, c->vi.vol_id, c->vi.name); - if (mounted_read_only) + if (c->ro_mount) ubifs_msg("mounted read-only"); x = (long long)c->main_lebs * c->leb_size; ubifs_msg("file system size: %lld bytes (%lld KiB, %lld MiB, %d " @@ -1640,7 +1640,7 @@ static int ubifs_remount_rw(struct ubifs_info *c) } dbg_gen("re-mounted read-write"); - c->vfs_sb->s_flags &= ~MS_RDONLY; + c->ro_mount = 0; c->remounting_rw = 0; c->always_chk_crc = 0; err = dbg_check_space_info(c); @@ -1676,7 +1676,7 @@ static void ubifs_remount_ro(struct ubifs_info *c) int i, err; ubifs_assert(!c->need_recovery); - ubifs_assert(!(c->vfs_sb->s_flags & MS_RDONLY)); + ubifs_assert(!c->ro_mount); mutex_lock(&c->umount_mutex); if (c->bgt) { @@ -1686,10 +1686,8 @@ static void ubifs_remount_ro(struct ubifs_info *c) dbg_save_space_info(c); - for (i = 0; i < c->jhead_cnt; i++) { + for (i = 0; i < c->jhead_cnt; i++) ubifs_wbuf_sync(&c->jheads[i].wbuf); - hrtimer_cancel(&c->jheads[i].wbuf.timer); - } c->mst_node->flags &= ~cpu_to_le32(UBIFS_MST_DIRTY); c->mst_node->flags |= cpu_to_le32(UBIFS_MST_NO_ORPHS); @@ -1704,6 +1702,7 @@ static void ubifs_remount_ro(struct ubifs_info *c) vfree(c->ileb_buf); c->ileb_buf = NULL; ubifs_lpt_free(c, 1); + c->ro_mount = 1; err = dbg_check_space_info(c); if (err) ubifs_ro_mode(c, err); @@ -1735,7 +1734,7 @@ static void ubifs_put_super(struct super_block *sb) * the mutex is locked. */ mutex_lock(&c->umount_mutex); - if (!(c->vfs_sb->s_flags & MS_RDONLY)) { + if (!c->ro_mount) { /* * First of all kill the background thread to make sure it does * not interfere with un-mounting and freeing resources. @@ -1745,23 +1744,22 @@ static void ubifs_put_super(struct super_block *sb) c->bgt = NULL; } - /* Synchronize write-buffers */ - if (c->jheads) - for (i = 0; i < c->jhead_cnt; i++) - ubifs_wbuf_sync(&c->jheads[i].wbuf); - /* - * On fatal errors c->ro_media is set to 1, in which case we do + * On fatal errors c->ro_error is set to 1, in which case we do * not write the master node. */ - if (!c->ro_media) { + if (!c->ro_error) { + int err; + + /* Synchronize write-buffers */ + for (i = 0; i < c->jhead_cnt; i++) + ubifs_wbuf_sync(&c->jheads[i].wbuf); + /* * We are being cleanly unmounted which means the * orphans were killed - indicate this in the master * node. Also save the reserved GC LEB number. */ - int err; - c->mst_node->flags &= ~cpu_to_le32(UBIFS_MST_DIRTY); c->mst_node->flags |= cpu_to_le32(UBIFS_MST_NO_ORPHS); c->mst_node->gc_lnum = cpu_to_le32(c->gc_lnum); @@ -1774,6 +1772,10 @@ static void ubifs_put_super(struct super_block *sb) */ ubifs_err("failed to write master node, " "error %d", err); + } else { + for (i = 0; i < c->jhead_cnt; i++) + /* Make sure write-buffer timers are canceled */ + hrtimer_cancel(&c->jheads[i].wbuf.timer); } } @@ -1797,17 +1799,21 @@ static int ubifs_remount_fs(struct super_block *sb, int *flags, char *data) return err; } - if ((sb->s_flags & MS_RDONLY) && !(*flags & MS_RDONLY)) { + if (c->ro_mount && !(*flags & MS_RDONLY)) { + if (c->ro_error) { + ubifs_msg("cannot re-mount R/W due to prior errors"); + return -EROFS; + } if (c->ro_media) { - ubifs_msg("cannot re-mount due to prior errors"); + ubifs_msg("cannot re-mount R/W - UBI volume is R/O"); return -EROFS; } err = ubifs_remount_rw(c); if (err) return err; - } else if (!(sb->s_flags & MS_RDONLY) && (*flags & MS_RDONLY)) { - if (c->ro_media) { - ubifs_msg("cannot re-mount due to prior errors"); + } else if (!c->ro_mount && (*flags & MS_RDONLY)) { + if (c->ro_error) { + ubifs_msg("cannot re-mount R/O due to prior errors"); return -EROFS; } ubifs_remount_ro(c); @@ -2049,8 +2055,8 @@ static int ubifs_get_sb(struct file_system_type *fs_type, int flags, */ ubi = open_ubi(name, UBI_READONLY); if (IS_ERR(ubi)) { - ubifs_err("cannot open \"%s\", error %d", - name, (int)PTR_ERR(ubi)); + dbg_err("cannot open \"%s\", error %d", + name, (int)PTR_ERR(ubi)); return PTR_ERR(ubi); } ubi_get_volume_info(ubi, &vi); @@ -2064,9 +2070,11 @@ static int ubifs_get_sb(struct file_system_type *fs_type, int flags, } if (sb->s_root) { + struct ubifs_info *c1 = sb->s_fs_info; + /* A new mount point for already mounted UBIFS */ dbg_gen("this ubi volume is already mounted"); - if ((flags ^ sb->s_flags) & MS_RDONLY) { + if (!!(flags & MS_RDONLY) != c1->ro_mount) { err = -EBUSY; goto out_deact; } diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c index 2194915220e5..ad9cf0133622 100644 --- a/fs/ubifs/tnc.c +++ b/fs/ubifs/tnc.c @@ -1177,6 +1177,7 @@ int ubifs_lookup_level0(struct ubifs_info *c, const union ubifs_key *key, unsigned long time = get_seconds(); dbg_tnc("search key %s", DBGKEY(key)); + ubifs_assert(key_type(c, key) < UBIFS_INVALID_KEY); znode = c->zroot.znode; if (unlikely(!znode)) { @@ -2966,7 +2967,7 @@ static struct ubifs_znode *right_znode(struct ubifs_info *c, * * This function searches an indexing node by its first key @key and its * address @lnum:@offs. It looks up the indexing tree by pulling all indexing - * nodes it traverses to TNC. This function is called fro indexing nodes which + * nodes it traverses to TNC. This function is called for indexing nodes which * were found on the media by scanning, for example when garbage-collecting or * when doing in-the-gaps commit. This means that the indexing node which is * looked for does not have to have exactly the same leftmost key @key, because @@ -2988,6 +2989,8 @@ static struct ubifs_znode *lookup_znode(struct ubifs_info *c, struct ubifs_znode *znode, *zn; int n, nn; + ubifs_assert(key_type(c, key) < UBIFS_INVALID_KEY); + /* * The arguments have probably been read off flash, so don't assume * they are valid. diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index 0c9876b396dd..381d6b207a52 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -119,8 +119,12 @@ * in TNC. However, when replaying, it is handy to introduce fake "truncation" * keys for truncation nodes because the code becomes simpler. So we define * %UBIFS_TRUN_KEY type. + * + * But otherwise, out of the journal reply scope, the truncation keys are + * invalid. */ -#define UBIFS_TRUN_KEY UBIFS_KEY_TYPES_CNT +#define UBIFS_TRUN_KEY UBIFS_KEY_TYPES_CNT +#define UBIFS_INVALID_KEY UBIFS_KEY_TYPES_CNT /* * How much a directory entry/extended attribute entry adds to the parent/host @@ -1028,6 +1032,8 @@ struct ubifs_debug_info; * @max_leb_cnt: maximum count of logical eraseblocks * @old_leb_cnt: count of logical eraseblocks before re-size * @ro_media: the underlying UBI volume is read-only + * @ro_mount: the file-system was mounted as read-only + * @ro_error: UBIFS switched to R/O mode because an error happened * * @dirty_pg_cnt: number of dirty pages (not used) * @dirty_zn_cnt: number of dirty znodes @@ -1168,11 +1174,14 @@ struct ubifs_debug_info; * @replay_sqnum: sequence number of node currently being replayed * @need_recovery: file-system needs recovery * @replaying: set to %1 during journal replay - * @unclean_leb_list: LEBs to recover when mounting ro to rw - * @rcvrd_mst_node: recovered master node to write when mounting ro to rw + * @unclean_leb_list: LEBs to recover when re-mounting R/O mounted FS to R/W + * mode + * @rcvrd_mst_node: recovered master node to write when re-mounting R/O mounted + * FS to R/W mode * @size_tree: inode size information for recovery - * @remounting_rw: set while remounting from ro to rw (sb flags have MS_RDONLY) - * @always_chk_crc: always check CRCs (while mounting and remounting rw) + * @remounting_rw: set while re-mounting from R/O mode to R/W mode + * @always_chk_crc: always check CRCs (while mounting and remounting to R/W + * mode) * @mount_opts: UBIFS-specific mount options * * @dbg: debugging-related information @@ -1268,7 +1277,9 @@ struct ubifs_info { int leb_cnt; int max_leb_cnt; int old_leb_cnt; - int ro_media; + unsigned int ro_media:1; + unsigned int ro_mount:1; + unsigned int ro_error:1; atomic_long_t dirty_pg_cnt; atomic_long_t dirty_zn_cnt; diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c index 286e36e21dae..ba5312802aa9 100644 --- a/fs/xfs/linux-2.6/xfs_buf.c +++ b/fs/xfs/linux-2.6/xfs_buf.c @@ -188,8 +188,8 @@ _xfs_buf_initialize( atomic_set(&bp->b_hold, 1); init_completion(&bp->b_iowait); INIT_LIST_HEAD(&bp->b_list); - INIT_LIST_HEAD(&bp->b_hash_list); - init_MUTEX_LOCKED(&bp->b_sema); /* held, no waiters */ + RB_CLEAR_NODE(&bp->b_rbnode); + sema_init(&bp->b_sema, 0); /* held, no waiters */ XB_SET_OWNER(bp); bp->b_target = target; bp->b_file_offset = range_base; @@ -262,8 +262,6 @@ xfs_buf_free( { trace_xfs_buf_free(bp, _RET_IP_); - ASSERT(list_empty(&bp->b_hash_list)); - if (bp->b_flags & (_XBF_PAGE_CACHE|_XBF_PAGES)) { uint i; @@ -422,8 +420,10 @@ _xfs_buf_find( { xfs_off_t range_base; size_t range_length; - xfs_bufhash_t *hash; - xfs_buf_t *bp, *n; + struct xfs_perag *pag; + struct rb_node **rbp; + struct rb_node *parent; + xfs_buf_t *bp; range_base = (ioff << BBSHIFT); range_length = (isize << BBSHIFT); @@ -432,14 +432,37 @@ _xfs_buf_find( ASSERT(!(range_length < (1 << btp->bt_sshift))); ASSERT(!(range_base & (xfs_off_t)btp->bt_smask)); - hash = &btp->bt_hash[hash_long((unsigned long)ioff, btp->bt_hashshift)]; - - spin_lock(&hash->bh_lock); - - list_for_each_entry_safe(bp, n, &hash->bh_list, b_hash_list) { - ASSERT(btp == bp->b_target); - if (bp->b_file_offset == range_base && - bp->b_buffer_length == range_length) { + /* get tree root */ + pag = xfs_perag_get(btp->bt_mount, + xfs_daddr_to_agno(btp->bt_mount, ioff)); + + /* walk tree */ + spin_lock(&pag->pag_buf_lock); + rbp = &pag->pag_buf_tree.rb_node; + parent = NULL; + bp = NULL; + while (*rbp) { + parent = *rbp; + bp = rb_entry(parent, struct xfs_buf, b_rbnode); + + if (range_base < bp->b_file_offset) + rbp = &(*rbp)->rb_left; + else if (range_base > bp->b_file_offset) + rbp = &(*rbp)->rb_right; + else { + /* + * found a block offset match. If the range doesn't + * match, the only way this is allowed is if the buffer + * in the cache is stale and the transaction that made + * it stale has not yet committed. i.e. we are + * reallocating a busy extent. Skip this buffer and + * continue searching to the right for an exact match. + */ + if (bp->b_buffer_length != range_length) { + ASSERT(bp->b_flags & XBF_STALE); + rbp = &(*rbp)->rb_right; + continue; + } atomic_inc(&bp->b_hold); goto found; } @@ -449,17 +472,21 @@ _xfs_buf_find( if (new_bp) { _xfs_buf_initialize(new_bp, btp, range_base, range_length, flags); - new_bp->b_hash = hash; - list_add(&new_bp->b_hash_list, &hash->bh_list); + rb_link_node(&new_bp->b_rbnode, parent, rbp); + rb_insert_color(&new_bp->b_rbnode, &pag->pag_buf_tree); + /* the buffer keeps the perag reference until it is freed */ + new_bp->b_pag = pag; + spin_unlock(&pag->pag_buf_lock); } else { XFS_STATS_INC(xb_miss_locked); + spin_unlock(&pag->pag_buf_lock); + xfs_perag_put(pag); } - - spin_unlock(&hash->bh_lock); return new_bp; found: - spin_unlock(&hash->bh_lock); + spin_unlock(&pag->pag_buf_lock); + xfs_perag_put(pag); /* Attempt to get the semaphore without sleeping, * if this does not work then we need to drop the @@ -625,8 +652,7 @@ void xfs_buf_readahead( xfs_buftarg_t *target, xfs_off_t ioff, - size_t isize, - xfs_buf_flags_t flags) + size_t isize) { struct backing_dev_info *bdi; @@ -634,8 +660,42 @@ xfs_buf_readahead( if (bdi_read_congested(bdi)) return; - flags |= (XBF_TRYLOCK|XBF_ASYNC|XBF_READ_AHEAD); - xfs_buf_read(target, ioff, isize, flags); + xfs_buf_read(target, ioff, isize, + XBF_TRYLOCK|XBF_ASYNC|XBF_READ_AHEAD|XBF_DONT_BLOCK); +} + +/* + * Read an uncached buffer from disk. Allocates and returns a locked + * buffer containing the disk contents or nothing. + */ +struct xfs_buf * +xfs_buf_read_uncached( + struct xfs_mount *mp, + struct xfs_buftarg *target, + xfs_daddr_t daddr, + size_t length, + int flags) +{ + xfs_buf_t *bp; + int error; + + bp = xfs_buf_get_uncached(target, length, flags); + if (!bp) + return NULL; + + /* set up the buffer for a read IO */ + xfs_buf_lock(bp); + XFS_BUF_SET_ADDR(bp, daddr); + XFS_BUF_READ(bp); + XFS_BUF_BUSY(bp); + + xfsbdstrat(mp, bp); + error = xfs_buf_iowait(bp); + if (error || bp->b_error) { + xfs_buf_relse(bp); + return NULL; + } + return bp; } xfs_buf_t * @@ -707,9 +767,10 @@ xfs_buf_associate_memory( } xfs_buf_t * -xfs_buf_get_noaddr( +xfs_buf_get_uncached( + struct xfs_buftarg *target, size_t len, - xfs_buftarg_t *target) + int flags) { unsigned long page_count = PAGE_ALIGN(len) >> PAGE_SHIFT; int error, i; @@ -725,7 +786,7 @@ xfs_buf_get_noaddr( goto fail_free_buf; for (i = 0; i < page_count; i++) { - bp->b_pages[i] = alloc_page(GFP_KERNEL); + bp->b_pages[i] = alloc_page(xb_to_gfp(flags)); if (!bp->b_pages[i]) goto fail_free_mem; } @@ -740,7 +801,7 @@ xfs_buf_get_noaddr( xfs_buf_unlock(bp); - trace_xfs_buf_get_noaddr(bp, _RET_IP_); + trace_xfs_buf_get_uncached(bp, _RET_IP_); return bp; fail_free_mem: @@ -774,29 +835,30 @@ void xfs_buf_rele( xfs_buf_t *bp) { - xfs_bufhash_t *hash = bp->b_hash; + struct xfs_perag *pag = bp->b_pag; trace_xfs_buf_rele(bp, _RET_IP_); - if (unlikely(!hash)) { + if (!pag) { ASSERT(!bp->b_relse); + ASSERT(RB_EMPTY_NODE(&bp->b_rbnode)); if (atomic_dec_and_test(&bp->b_hold)) xfs_buf_free(bp); return; } + ASSERT(!RB_EMPTY_NODE(&bp->b_rbnode)); ASSERT(atomic_read(&bp->b_hold) > 0); - if (atomic_dec_and_lock(&bp->b_hold, &hash->bh_lock)) { + if (atomic_dec_and_lock(&bp->b_hold, &pag->pag_buf_lock)) { if (bp->b_relse) { atomic_inc(&bp->b_hold); - spin_unlock(&hash->bh_lock); - (*(bp->b_relse)) (bp); - } else if (bp->b_flags & XBF_FS_MANAGED) { - spin_unlock(&hash->bh_lock); + spin_unlock(&pag->pag_buf_lock); + bp->b_relse(bp); } else { ASSERT(!(bp->b_flags & (XBF_DELWRI|_XBF_DELWRI_Q))); - list_del_init(&bp->b_hash_list); - spin_unlock(&hash->bh_lock); + rb_erase(&bp->b_rbnode, &pag->pag_buf_tree); + spin_unlock(&pag->pag_buf_lock); + xfs_perag_put(pag); xfs_buf_free(bp); } } @@ -859,7 +921,7 @@ xfs_buf_lock( trace_xfs_buf_lock(bp, _RET_IP_); if (atomic_read(&bp->b_pin_count) && (bp->b_flags & XBF_STALE)) - xfs_log_force(bp->b_mount, 0); + xfs_log_force(bp->b_target->bt_mount, 0); if (atomic_read(&bp->b_io_remaining)) blk_run_address_space(bp->b_target->bt_mapping); down(&bp->b_sema); @@ -924,19 +986,7 @@ xfs_buf_iodone_work( xfs_buf_t *bp = container_of(work, xfs_buf_t, b_iodone_work); - /* - * We can get an EOPNOTSUPP to ordered writes. Here we clear the - * ordered flag and reissue them. Because we can't tell the higher - * layers directly that they should not issue ordered I/O anymore, they - * need to check if the _XFS_BARRIER_FAILED flag was set during I/O completion. - */ - if ((bp->b_error == EOPNOTSUPP) && - (bp->b_flags & (XBF_ORDERED|XBF_ASYNC)) == (XBF_ORDERED|XBF_ASYNC)) { - trace_xfs_buf_ordered_retry(bp, _RET_IP_); - bp->b_flags &= ~XBF_ORDERED; - bp->b_flags |= _XFS_BARRIER_FAILED; - xfs_buf_iorequest(bp); - } else if (bp->b_iodone) + if (bp->b_iodone) (*(bp->b_iodone))(bp); else if (bp->b_flags & XBF_ASYNC) xfs_buf_relse(bp); @@ -982,7 +1032,6 @@ xfs_bwrite( { int error; - bp->b_mount = mp; bp->b_flags |= XBF_WRITE; bp->b_flags &= ~(XBF_ASYNC | XBF_READ); @@ -1003,8 +1052,6 @@ xfs_bdwrite( { trace_xfs_buf_bdwrite(bp, _RET_IP_); - bp->b_mount = mp; - bp->b_flags &= ~XBF_READ; bp->b_flags |= (XBF_DELWRI | XBF_ASYNC); @@ -1013,7 +1060,7 @@ xfs_bdwrite( /* * Called when we want to stop a buffer from getting written or read. - * We attach the EIO error, muck with its flags, and call biodone + * We attach the EIO error, muck with its flags, and call xfs_buf_ioend * so that the proper iodone callbacks get called. */ STATIC int @@ -1030,21 +1077,21 @@ xfs_bioerror( XFS_BUF_ERROR(bp, EIO); /* - * We're calling biodone, so delete XBF_DONE flag. + * We're calling xfs_buf_ioend, so delete XBF_DONE flag. */ XFS_BUF_UNREAD(bp); XFS_BUF_UNDELAYWRITE(bp); XFS_BUF_UNDONE(bp); XFS_BUF_STALE(bp); - xfs_biodone(bp); + xfs_buf_ioend(bp, 0); return EIO; } /* * Same as xfs_bioerror, except that we are releasing the buffer - * here ourselves, and avoiding the biodone call. + * here ourselves, and avoiding the xfs_buf_ioend call. * This is meant for userdata errors; metadata bufs come with * iodone functions attached, so that we can track down errors. */ @@ -1093,7 +1140,7 @@ int xfs_bdstrat_cb( struct xfs_buf *bp) { - if (XFS_FORCED_SHUTDOWN(bp->b_mount)) { + if (XFS_FORCED_SHUTDOWN(bp->b_target->bt_mount)) { trace_xfs_bdstrat_shut(bp, _RET_IP_); /* * Metadata write that didn't get logged but @@ -1195,7 +1242,7 @@ _xfs_buf_ioapply( if (bp->b_flags & XBF_ORDERED) { ASSERT(!(bp->b_flags & XBF_READ)); - rw = WRITE_BARRIER; + rw = WRITE_FLUSH_FUA; } else if (bp->b_flags & XBF_LOG_BUFFER) { ASSERT(!(bp->b_flags & XBF_READ_AHEAD)); bp->b_flags &= ~_XBF_RUN_QUEUES; @@ -1399,62 +1446,24 @@ xfs_buf_iomove( */ void xfs_wait_buftarg( - xfs_buftarg_t *btp) -{ - xfs_buf_t *bp, *n; - xfs_bufhash_t *hash; - uint i; - - for (i = 0; i < (1 << btp->bt_hashshift); i++) { - hash = &btp->bt_hash[i]; -again: - spin_lock(&hash->bh_lock); - list_for_each_entry_safe(bp, n, &hash->bh_list, b_hash_list) { - ASSERT(btp == bp->b_target); - if (!(bp->b_flags & XBF_FS_MANAGED)) { - spin_unlock(&hash->bh_lock); - /* - * Catch superblock reference count leaks - * immediately - */ - BUG_ON(bp->b_bn == 0); - delay(100); - goto again; - } - } - spin_unlock(&hash->bh_lock); - } -} - -/* - * Allocate buffer hash table for a given target. - * For devices containing metadata (i.e. not the log/realtime devices) - * we need to allocate a much larger hash table. - */ -STATIC void -xfs_alloc_bufhash( - xfs_buftarg_t *btp, - int external) + struct xfs_buftarg *btp) { - unsigned int i; + struct xfs_perag *pag; + uint i; - btp->bt_hashshift = external ? 3 : 12; /* 8 or 4096 buckets */ - btp->bt_hash = kmem_zalloc_large((1 << btp->bt_hashshift) * - sizeof(xfs_bufhash_t)); - for (i = 0; i < (1 << btp->bt_hashshift); i++) { - spin_lock_init(&btp->bt_hash[i].bh_lock); - INIT_LIST_HEAD(&btp->bt_hash[i].bh_list); + for (i = 0; i < btp->bt_mount->m_sb.sb_agcount; i++) { + pag = xfs_perag_get(btp->bt_mount, i); + spin_lock(&pag->pag_buf_lock); + while (rb_first(&pag->pag_buf_tree)) { + spin_unlock(&pag->pag_buf_lock); + delay(100); + spin_lock(&pag->pag_buf_lock); + } + spin_unlock(&pag->pag_buf_lock); + xfs_perag_put(pag); } } -STATIC void -xfs_free_bufhash( - xfs_buftarg_t *btp) -{ - kmem_free_large(btp->bt_hash); - btp->bt_hash = NULL; -} - /* * buftarg list for delwrite queue processing */ @@ -1487,7 +1496,6 @@ xfs_free_buftarg( xfs_flush_buftarg(btp, 1); if (mp->m_flags & XFS_MOUNT_BARRIER) xfs_blkdev_issue_flush(btp); - xfs_free_bufhash(btp); iput(btp->bt_mapping->host); /* Unregister the buftarg first so that we don't get a @@ -1609,6 +1617,7 @@ out_error: xfs_buftarg_t * xfs_alloc_buftarg( + struct xfs_mount *mp, struct block_device *bdev, int external, const char *fsname) @@ -1617,6 +1626,7 @@ xfs_alloc_buftarg( btp = kmem_zalloc(sizeof(*btp), KM_SLEEP); + btp->bt_mount = mp; btp->bt_dev = bdev->bd_dev; btp->bt_bdev = bdev; if (xfs_setsize_buftarg_early(btp, bdev)) @@ -1625,7 +1635,6 @@ xfs_alloc_buftarg( goto error; if (xfs_alloc_delwrite_queue(btp, fsname)) goto error; - xfs_alloc_bufhash(btp, external); return btp; error: @@ -1916,7 +1925,7 @@ xfs_flush_buftarg( bp = list_first_entry(&wait_list, struct xfs_buf, b_list); list_del_init(&bp->b_list); - xfs_iowait(bp); + xfs_buf_iowait(bp); xfs_buf_relse(bp); } } @@ -1933,7 +1942,7 @@ xfs_buf_init(void) goto out; xfslogd_workqueue = alloc_workqueue("xfslogd", - WQ_RESCUER | WQ_HIGHPRI, 1); + WQ_MEM_RECLAIM | WQ_HIGHPRI, 1); if (!xfslogd_workqueue) goto out_free_buf_zone; diff --git a/fs/xfs/linux-2.6/xfs_buf.h b/fs/xfs/linux-2.6/xfs_buf.h index 2a05614f0b92..383a3f37cf98 100644 --- a/fs/xfs/linux-2.6/xfs_buf.h +++ b/fs/xfs/linux-2.6/xfs_buf.h @@ -51,7 +51,6 @@ typedef enum { #define XBF_DONE (1 << 5) /* all pages in the buffer uptodate */ #define XBF_DELWRI (1 << 6) /* buffer has dirty pages */ #define XBF_STALE (1 << 7) /* buffer has been staled, do not find it */ -#define XBF_FS_MANAGED (1 << 8) /* filesystem controls freeing memory */ #define XBF_ORDERED (1 << 11)/* use ordered writes */ #define XBF_READ_AHEAD (1 << 12)/* asynchronous read-ahead */ #define XBF_LOG_BUFFER (1 << 13)/* this is a buffer used for the log */ @@ -86,14 +85,6 @@ typedef enum { */ #define _XBF_PAGE_LOCKED (1 << 22) -/* - * If we try a barrier write, but it fails we have to communicate - * this to the upper layers. Unfortunately b_error gets overwritten - * when the buffer is re-issued so we have to add another flag to - * keep this information. - */ -#define _XFS_BARRIER_FAILED (1 << 23) - typedef unsigned int xfs_buf_flags_t; #define XFS_BUF_FLAGS \ @@ -104,7 +95,6 @@ typedef unsigned int xfs_buf_flags_t; { XBF_DONE, "DONE" }, \ { XBF_DELWRI, "DELWRI" }, \ { XBF_STALE, "STALE" }, \ - { XBF_FS_MANAGED, "FS_MANAGED" }, \ { XBF_ORDERED, "ORDERED" }, \ { XBF_READ_AHEAD, "READ_AHEAD" }, \ { XBF_LOCK, "LOCK" }, /* should never be set */\ @@ -114,8 +104,7 @@ typedef unsigned int xfs_buf_flags_t; { _XBF_PAGES, "PAGES" }, \ { _XBF_RUN_QUEUES, "RUN_QUEUES" }, \ { _XBF_DELWRI_Q, "DELWRI_Q" }, \ - { _XBF_PAGE_LOCKED, "PAGE_LOCKED" }, \ - { _XFS_BARRIER_FAILED, "BARRIER_FAILED" } + { _XBF_PAGE_LOCKED, "PAGE_LOCKED" } typedef enum { @@ -132,14 +121,11 @@ typedef struct xfs_buftarg { dev_t bt_dev; struct block_device *bt_bdev; struct address_space *bt_mapping; + struct xfs_mount *bt_mount; unsigned int bt_bsize; unsigned int bt_sshift; size_t bt_smask; - /* per device buffer hash table */ - uint bt_hashshift; - xfs_bufhash_t *bt_hash; - /* per device delwri queue */ struct task_struct *bt_task; struct list_head bt_list; @@ -167,34 +153,41 @@ typedef int (*xfs_buf_bdstrat_t)(struct xfs_buf *); #define XB_PAGES 2 typedef struct xfs_buf { + /* + * first cacheline holds all the fields needed for an uncontended cache + * hit to be fully processed. The semaphore straddles the cacheline + * boundary, but the counter and lock sits on the first cacheline, + * which is the only bit that is touched if we hit the semaphore + * fast-path on locking. + */ + struct rb_node b_rbnode; /* rbtree node */ + xfs_off_t b_file_offset; /* offset in file */ + size_t b_buffer_length;/* size of buffer in bytes */ + atomic_t b_hold; /* reference count */ + xfs_buf_flags_t b_flags; /* status flags */ struct semaphore b_sema; /* semaphore for lockables */ - unsigned long b_queuetime; /* time buffer was queued */ - atomic_t b_pin_count; /* pin count */ + wait_queue_head_t b_waiters; /* unpin waiters */ struct list_head b_list; - xfs_buf_flags_t b_flags; /* status flags */ - struct list_head b_hash_list; /* hash table list */ - xfs_bufhash_t *b_hash; /* hash table list start */ + struct xfs_perag *b_pag; /* contains rbtree root */ xfs_buftarg_t *b_target; /* buffer target (device) */ - atomic_t b_hold; /* reference count */ xfs_daddr_t b_bn; /* block number for I/O */ - xfs_off_t b_file_offset; /* offset in file */ - size_t b_buffer_length;/* size of buffer in bytes */ size_t b_count_desired;/* desired transfer size */ void *b_addr; /* virtual address of buffer */ struct work_struct b_iodone_work; - atomic_t b_io_remaining; /* #outstanding I/O requests */ xfs_buf_iodone_t b_iodone; /* I/O completion function */ xfs_buf_relse_t b_relse; /* releasing function */ struct completion b_iowait; /* queue for I/O waiters */ void *b_fspriv; void *b_fspriv2; - struct xfs_mount *b_mount; - unsigned short b_error; /* error code on I/O */ - unsigned int b_page_count; /* size of page array */ - unsigned int b_offset; /* page offset in first page */ struct page **b_pages; /* array of page pointers */ struct page *b_page_array[XB_PAGES]; /* inline pages */ + unsigned long b_queuetime; /* time buffer was queued */ + atomic_t b_pin_count; /* pin count */ + atomic_t b_io_remaining; /* #outstanding I/O requests */ + unsigned int b_page_count; /* size of page array */ + unsigned int b_offset; /* page offset in first page */ + unsigned short b_error; /* error code on I/O */ #ifdef XFS_BUF_LOCK_TRACKING int b_last_holder; #endif @@ -213,11 +206,13 @@ extern xfs_buf_t *xfs_buf_read(xfs_buftarg_t *, xfs_off_t, size_t, xfs_buf_flags_t); extern xfs_buf_t *xfs_buf_get_empty(size_t, xfs_buftarg_t *); -extern xfs_buf_t *xfs_buf_get_noaddr(size_t, xfs_buftarg_t *); +extern xfs_buf_t *xfs_buf_get_uncached(struct xfs_buftarg *, size_t, int); extern int xfs_buf_associate_memory(xfs_buf_t *, void *, size_t); extern void xfs_buf_hold(xfs_buf_t *); -extern void xfs_buf_readahead(xfs_buftarg_t *, xfs_off_t, size_t, - xfs_buf_flags_t); +extern void xfs_buf_readahead(xfs_buftarg_t *, xfs_off_t, size_t); +struct xfs_buf *xfs_buf_read_uncached(struct xfs_mount *mp, + struct xfs_buftarg *target, + xfs_daddr_t daddr, size_t length, int flags); /* Releasing Buffers */ extern void xfs_buf_free(xfs_buf_t *); @@ -242,6 +237,8 @@ extern int xfs_buf_iorequest(xfs_buf_t *); extern int xfs_buf_iowait(xfs_buf_t *); extern void xfs_buf_iomove(xfs_buf_t *, size_t, size_t, void *, xfs_buf_rw_t); +#define xfs_buf_zero(bp, off, len) \ + xfs_buf_iomove((bp), (off), (len), NULL, XBRW_ZERO) static inline int xfs_buf_geterror(xfs_buf_t *bp) { @@ -276,8 +273,6 @@ extern void xfs_buf_terminate(void); XFS_BUF_DONE(bp); \ } while (0) -#define XFS_BUF_UNMANAGE(bp) ((bp)->b_flags &= ~XBF_FS_MANAGED) - #define XFS_BUF_DELAYWRITE(bp) ((bp)->b_flags |= XBF_DELWRI) #define XFS_BUF_UNDELAYWRITE(bp) xfs_buf_delwri_dequeue(bp) #define XFS_BUF_ISDELAYWRITE(bp) ((bp)->b_flags & XBF_DELWRI) @@ -356,25 +351,11 @@ static inline void xfs_buf_relse(xfs_buf_t *bp) xfs_buf_rele(bp); } -#define xfs_biodone(bp) xfs_buf_ioend(bp, 0) - -#define xfs_biomove(bp, off, len, data, rw) \ - xfs_buf_iomove((bp), (off), (len), (data), \ - ((rw) == XBF_WRITE) ? XBRW_WRITE : XBRW_READ) - -#define xfs_biozero(bp, off, len) \ - xfs_buf_iomove((bp), (off), (len), NULL, XBRW_ZERO) - -#define xfs_iowait(bp) xfs_buf_iowait(bp) - -#define xfs_baread(target, rablkno, ralen) \ - xfs_buf_readahead((target), (rablkno), (ralen), XBF_DONT_BLOCK) - - /* * Handling of buftargs. */ -extern xfs_buftarg_t *xfs_alloc_buftarg(struct block_device *, int, const char *); +extern xfs_buftarg_t *xfs_alloc_buftarg(struct xfs_mount *, + struct block_device *, int, const char *); extern void xfs_free_buftarg(struct xfs_mount *, struct xfs_buftarg *); extern void xfs_wait_buftarg(xfs_buftarg_t *); extern int xfs_setsize_buftarg(xfs_buftarg_t *, unsigned int, unsigned int); diff --git a/fs/xfs/linux-2.6/xfs_cred.h b/fs/xfs/linux-2.6/xfs_cred.h deleted file mode 100644 index 55bddf3b6091..000000000000 --- a/fs/xfs/linux-2.6/xfs_cred.h +++ /dev/null @@ -1,28 +0,0 @@ -/* - * Copyright (c) 2000-2002,2005 Silicon Graphics, Inc. - * All Rights Reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it would be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write the Free Software Foundation, - * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - */ -#ifndef __XFS_CRED_H__ -#define __XFS_CRED_H__ - -#include <linux/capability.h> - -/* - * Credentials - */ -typedef const struct cred cred_t; - -#endif /* __XFS_CRED_H__ */ diff --git a/fs/xfs/linux-2.6/xfs_fs_subr.c b/fs/xfs/linux-2.6/xfs_fs_subr.c index 1f279b012f94..ed88ed16811c 100644 --- a/fs/xfs/linux-2.6/xfs_fs_subr.c +++ b/fs/xfs/linux-2.6/xfs_fs_subr.c @@ -32,10 +32,9 @@ xfs_tosspages( xfs_off_t last, int fiopt) { - struct address_space *mapping = VFS_I(ip)->i_mapping; - - if (mapping->nrpages) - truncate_inode_pages(mapping, first); + /* can't toss partial tail pages, so mask them out */ + last &= ~(PAGE_SIZE - 1); + truncate_inode_pages_range(VFS_I(ip)->i_mapping, first, last - 1); } int @@ -50,12 +49,11 @@ xfs_flushinval_pages( trace_xfs_pagecache_inval(ip, first, last); - if (mapping->nrpages) { - xfs_iflags_clear(ip, XFS_ITRUNCATED); - ret = filemap_write_and_wait(mapping); - if (!ret) - truncate_inode_pages(mapping, first); - } + xfs_iflags_clear(ip, XFS_ITRUNCATED); + ret = filemap_write_and_wait_range(mapping, first, + last == -1 ? LLONG_MAX : last); + if (!ret) + truncate_inode_pages_range(mapping, first, last); return -ret; } @@ -71,10 +69,9 @@ xfs_flush_pages( int ret = 0; int ret2; - if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) { - xfs_iflags_clear(ip, XFS_ITRUNCATED); - ret = -filemap_fdatawrite(mapping); - } + xfs_iflags_clear(ip, XFS_ITRUNCATED); + ret = -filemap_fdatawrite_range(mapping, first, + last == -1 ? LLONG_MAX : last); if (flags & XBF_ASYNC) return ret; ret2 = xfs_wait_on_pages(ip, first, last); @@ -91,7 +88,9 @@ xfs_wait_on_pages( { struct address_space *mapping = VFS_I(ip)->i_mapping; - if (mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) - return -filemap_fdatawait(mapping); + if (mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) { + return -filemap_fdatawait_range(mapping, first, + last == -1 ? ip->i_size - 1 : last); + } return 0; } diff --git a/fs/xfs/linux-2.6/xfs_globals.c b/fs/xfs/linux-2.6/xfs_globals.c index 2ae8b1ccb02e..76e81cff70b9 100644 --- a/fs/xfs/linux-2.6/xfs_globals.c +++ b/fs/xfs/linux-2.6/xfs_globals.c @@ -16,7 +16,6 @@ * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA */ #include "xfs.h" -#include "xfs_cred.h" #include "xfs_sysctl.h" /* diff --git a/fs/xfs/linux-2.6/xfs_globals.h b/fs/xfs/linux-2.6/xfs_globals.h deleted file mode 100644 index 69f71caf061c..000000000000 --- a/fs/xfs/linux-2.6/xfs_globals.h +++ /dev/null @@ -1,23 +0,0 @@ -/* - * Copyright (c) 2000-2003,2005 Silicon Graphics, Inc. - * All Rights Reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it would be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write the Free Software Foundation, - * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - */ -#ifndef __XFS_GLOBALS_H__ -#define __XFS_GLOBALS_H__ - -extern uint64_t xfs_panic_mask; /* set to cause more panics */ - -#endif /* __XFS_GLOBALS_H__ */ diff --git a/fs/xfs/linux-2.6/xfs_ioctl.c b/fs/xfs/linux-2.6/xfs_ioctl.c index 3b9e626f7cd1..2ea238f6d38e 100644 --- a/fs/xfs/linux-2.6/xfs_ioctl.c +++ b/fs/xfs/linux-2.6/xfs_ioctl.c @@ -790,7 +790,7 @@ xfs_ioc_fsgetxattr( xfs_ilock(ip, XFS_ILOCK_SHARED); fa.fsx_xflags = xfs_ip2xflags(ip); fa.fsx_extsize = ip->i_d.di_extsize << ip->i_mount->m_sb.sb_blocklog; - fa.fsx_projid = ip->i_d.di_projid; + fa.fsx_projid = xfs_get_projid(ip); if (attr) { if (ip->i_afp) { @@ -909,10 +909,10 @@ xfs_ioctl_setattr( return XFS_ERROR(EIO); /* - * Disallow 32bit project ids because on-disk structure - * is 16bit only. + * Disallow 32bit project ids when projid32bit feature is not enabled. */ - if ((mask & FSX_PROJID) && (fa->fsx_projid > (__uint16_t)-1)) + if ((mask & FSX_PROJID) && (fa->fsx_projid > (__uint16_t)-1) && + !xfs_sb_version_hasprojid32bit(&ip->i_mount->m_sb)) return XFS_ERROR(EINVAL); /* @@ -961,7 +961,7 @@ xfs_ioctl_setattr( if (mask & FSX_PROJID) { if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_PQUOTA_ON(mp) && - ip->i_d.di_projid != fa->fsx_projid) { + xfs_get_projid(ip) != fa->fsx_projid) { ASSERT(tp); code = xfs_qm_vop_chown_reserve(tp, ip, udqp, gdqp, capable(CAP_FOWNER) ? @@ -1063,12 +1063,12 @@ xfs_ioctl_setattr( * Change the ownerships and register quota modifications * in the transaction. */ - if (ip->i_d.di_projid != fa->fsx_projid) { + 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_d.di_projid = fa->fsx_projid; + xfs_set_projid(ip, fa->fsx_projid); /* * We may have to rev the inode as well as @@ -1088,8 +1088,8 @@ xfs_ioctl_setattr( xfs_diflags_to_linux(ip); } + xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG); xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); - xfs_ichgtime(ip, XFS_ICHGTIME_CHG); XFS_STATS_INC(xs_ig_attrchg); @@ -1301,7 +1301,8 @@ xfs_file_ioctl( case XFS_IOC_ALLOCSP64: case XFS_IOC_FREESP64: case XFS_IOC_RESVSP64: - case XFS_IOC_UNRESVSP64: { + case XFS_IOC_UNRESVSP64: + case XFS_IOC_ZERO_RANGE: { xfs_flock64_t bf; if (copy_from_user(&bf, arg, sizeof(bf))) diff --git a/fs/xfs/linux-2.6/xfs_ioctl32.c b/fs/xfs/linux-2.6/xfs_ioctl32.c index 6c83f7f62dc9..b3486dfa5520 100644 --- a/fs/xfs/linux-2.6/xfs_ioctl32.c +++ b/fs/xfs/linux-2.6/xfs_ioctl32.c @@ -164,7 +164,8 @@ xfs_ioctl32_bstat_copyin( get_user(bstat->bs_extsize, &bstat32->bs_extsize) || get_user(bstat->bs_extents, &bstat32->bs_extents) || get_user(bstat->bs_gen, &bstat32->bs_gen) || - get_user(bstat->bs_projid, &bstat32->bs_projid) || + get_user(bstat->bs_projid_lo, &bstat32->bs_projid_lo) || + get_user(bstat->bs_projid_hi, &bstat32->bs_projid_hi) || get_user(bstat->bs_dmevmask, &bstat32->bs_dmevmask) || get_user(bstat->bs_dmstate, &bstat32->bs_dmstate) || get_user(bstat->bs_aextents, &bstat32->bs_aextents)) @@ -218,6 +219,7 @@ xfs_bulkstat_one_fmt_compat( put_user(buffer->bs_extents, &p32->bs_extents) || put_user(buffer->bs_gen, &p32->bs_gen) || put_user(buffer->bs_projid, &p32->bs_projid) || + put_user(buffer->bs_projid_hi, &p32->bs_projid_hi) || put_user(buffer->bs_dmevmask, &p32->bs_dmevmask) || put_user(buffer->bs_dmstate, &p32->bs_dmstate) || put_user(buffer->bs_aextents, &p32->bs_aextents)) @@ -574,6 +576,7 @@ xfs_file_compat_ioctl( case XFS_IOC_FSGEOMETRY_V1: case XFS_IOC_FSGROWFSDATA: case XFS_IOC_FSGROWFSRT: + case XFS_IOC_ZERO_RANGE: return xfs_file_ioctl(filp, cmd, p); #else case XFS_IOC_ALLOCSP_32: diff --git a/fs/xfs/linux-2.6/xfs_ioctl32.h b/fs/xfs/linux-2.6/xfs_ioctl32.h index 1024c4f8ba0d..08b605792a99 100644 --- a/fs/xfs/linux-2.6/xfs_ioctl32.h +++ b/fs/xfs/linux-2.6/xfs_ioctl32.h @@ -65,8 +65,10 @@ typedef struct compat_xfs_bstat { __s32 bs_extsize; /* extent size */ __s32 bs_extents; /* number of extents */ __u32 bs_gen; /* generation count */ - __u16 bs_projid; /* project id */ - unsigned char bs_pad[14]; /* pad space, unused */ + __u16 bs_projid_lo; /* lower part of project id */ +#define bs_projid bs_projid_lo /* (previously just bs_projid) */ + __u16 bs_projid_hi; /* high part of project id */ + unsigned char bs_pad[12]; /* pad space, unused */ __u32 bs_dmevmask; /* DMIG event mask */ __u16 bs_dmstate; /* DMIG state info */ __u16 bs_aextents; /* attribute number of extents */ diff --git a/fs/xfs/linux-2.6/xfs_iops.c b/fs/xfs/linux-2.6/xfs_iops.c index b1fc2a6bfe83..ec858e09d546 100644 --- a/fs/xfs/linux-2.6/xfs_iops.c +++ b/fs/xfs/linux-2.6/xfs_iops.c @@ -95,41 +95,6 @@ xfs_mark_inode_dirty( } /* - * Change the requested timestamp in the given inode. - * We don't lock across timestamp updates, and we don't log them but - * we do record the fact that there is dirty information in core. - */ -void -xfs_ichgtime( - xfs_inode_t *ip, - int flags) -{ - struct inode *inode = VFS_I(ip); - timespec_t tv; - int sync_it = 0; - - tv = current_fs_time(inode->i_sb); - - if ((flags & XFS_ICHGTIME_MOD) && - !timespec_equal(&inode->i_mtime, &tv)) { - inode->i_mtime = tv; - sync_it = 1; - } - if ((flags & XFS_ICHGTIME_CHG) && - !timespec_equal(&inode->i_ctime, &tv)) { - inode->i_ctime = tv; - sync_it = 1; - } - - /* - * Update complete - now make sure everyone knows that the inode - * is dirty. - */ - if (sync_it) - xfs_mark_inode_dirty_sync(ip); -} - -/* * Hook in SELinux. This is not quite correct yet, what we really need * here (as we do for default ACLs) is a mechanism by which creation of * these attrs can be journalled at inode creation time (along with the @@ -224,7 +189,7 @@ xfs_vn_mknod( } xfs_dentry_to_name(&name, dentry); - error = xfs_create(XFS_I(dir), &name, mode, rdev, &ip, NULL); + error = xfs_create(XFS_I(dir), &name, mode, rdev, &ip); if (unlikely(error)) goto out_free_acl; @@ -397,7 +362,7 @@ xfs_vn_symlink( (irix_symlink_mode ? 0777 & ~current_umask() : S_IRWXUGO); xfs_dentry_to_name(&name, dentry); - error = xfs_symlink(XFS_I(dir), &name, symname, mode, &cip, NULL); + error = xfs_symlink(XFS_I(dir), &name, symname, mode, &cip); if (unlikely(error)) goto out; diff --git a/fs/xfs/linux-2.6/xfs_linux.h b/fs/xfs/linux-2.6/xfs_linux.h index 2fa0bd9ebc7f..214ddd71ff79 100644 --- a/fs/xfs/linux-2.6/xfs_linux.h +++ b/fs/xfs/linux-2.6/xfs_linux.h @@ -71,6 +71,7 @@ #include <linux/random.h> #include <linux/ctype.h> #include <linux/writeback.h> +#include <linux/capability.h> #include <asm/page.h> #include <asm/div64.h> @@ -79,14 +80,12 @@ #include <asm/byteorder.h> #include <asm/unaligned.h> -#include <xfs_cred.h> #include <xfs_vnode.h> #include <xfs_stats.h> #include <xfs_sysctl.h> #include <xfs_iops.h> #include <xfs_aops.h> #include <xfs_super.h> -#include <xfs_globals.h> #include <xfs_buf.h> /* @@ -144,7 +143,7 @@ #define SYNCHRONIZE() barrier() #define __return_address __builtin_return_address(0) -#define dfltprid 0 +#define XFS_PROJID_DEFAULT 0 #define MAXPATHLEN 1024 #define MIN(a,b) (min(a,b)) diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c index a4e07974955b..ab31ce5aeaf9 100644 --- a/fs/xfs/linux-2.6/xfs_super.c +++ b/fs/xfs/linux-2.6/xfs_super.c @@ -44,7 +44,6 @@ #include "xfs_buf_item.h" #include "xfs_utils.h" #include "xfs_vnodeops.h" -#include "xfs_version.h" #include "xfs_log_priv.h" #include "xfs_trans_priv.h" #include "xfs_filestream.h" @@ -645,7 +644,7 @@ xfs_barrier_test( XFS_BUF_ORDERED(sbp); xfsbdstrat(mp, sbp); - error = xfs_iowait(sbp); + error = xfs_buf_iowait(sbp); /* * Clear all the flags we set and possible error state in the @@ -693,8 +692,7 @@ void xfs_blkdev_issue_flush( xfs_buftarg_t *buftarg) { - blkdev_issue_flush(buftarg->bt_bdev, GFP_KERNEL, NULL, - BLKDEV_IFL_WAIT); + blkdev_issue_flush(buftarg->bt_bdev, GFP_KERNEL, NULL); } STATIC void @@ -758,18 +756,20 @@ xfs_open_devices( * Setup xfs_mount buffer target pointers */ error = ENOMEM; - mp->m_ddev_targp = xfs_alloc_buftarg(ddev, 0, mp->m_fsname); + mp->m_ddev_targp = xfs_alloc_buftarg(mp, ddev, 0, mp->m_fsname); if (!mp->m_ddev_targp) goto out_close_rtdev; if (rtdev) { - mp->m_rtdev_targp = xfs_alloc_buftarg(rtdev, 1, mp->m_fsname); + mp->m_rtdev_targp = xfs_alloc_buftarg(mp, rtdev, 1, + mp->m_fsname); if (!mp->m_rtdev_targp) goto out_free_ddev_targ; } if (logdev && logdev != ddev) { - mp->m_logdev_targp = xfs_alloc_buftarg(logdev, 1, mp->m_fsname); + mp->m_logdev_targp = xfs_alloc_buftarg(mp, logdev, 1, + mp->m_fsname); if (!mp->m_logdev_targp) goto out_free_rtdev_targ; } else { @@ -972,12 +972,7 @@ xfs_fs_inode_init_once( /* * Dirty the XFS inode when mark_inode_dirty_sync() is called so that - * we catch unlogged VFS level updates to the inode. Care must be taken - * here - the transaction code calls mark_inode_dirty_sync() to mark the - * VFS inode dirty in a transaction and clears the i_update_core field; - * it must clear the field after calling mark_inode_dirty_sync() to - * correctly indicate that the dirty state has been propagated into the - * inode log item. + * we catch unlogged VFS level updates to the inode. * * We need the barrier() to maintain correct ordering between unlogged * updates and the transaction commit code that clears the i_update_core @@ -1521,8 +1516,9 @@ xfs_fs_fill_super( if (error) goto out_free_fsname; - if (xfs_icsb_init_counters(mp)) - mp->m_flags |= XFS_MOUNT_NO_PERCPU_SB; + error = xfs_icsb_init_counters(mp); + if (error) + goto out_close_devices; error = xfs_readsb(mp, flags); if (error) @@ -1583,6 +1579,7 @@ xfs_fs_fill_super( xfs_freesb(mp); out_destroy_counters: xfs_icsb_destroy_counters(mp); + out_close_devices: xfs_close_devices(mp); out_free_fsname: xfs_free_fsname(mp); diff --git a/fs/xfs/linux-2.6/xfs_super.h b/fs/xfs/linux-2.6/xfs_super.h index 1ef4a4d2d997..50a3266c999e 100644 --- a/fs/xfs/linux-2.6/xfs_super.h +++ b/fs/xfs/linux-2.6/xfs_super.h @@ -62,6 +62,7 @@ extern void xfs_qm_exit(void); # define XFS_DBG_STRING "no debug" #endif +#define XFS_VERSION_STRING "SGI XFS" #define XFS_BUILD_OPTIONS XFS_ACL_STRING \ XFS_SECURITY_STRING \ XFS_REALTIME_STRING \ diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c index 81976ffed7d6..37d33254981d 100644 --- a/fs/xfs/linux-2.6/xfs_sync.c +++ b/fs/xfs/linux-2.6/xfs_sync.c @@ -39,42 +39,39 @@ #include <linux/kthread.h> #include <linux/freezer.h> +/* + * The inode lookup is done in batches to keep the amount of lock traffic and + * radix tree lookups to a minimum. The batch size is a trade off between + * lookup reduction and stack usage. This is in the reclaim path, so we can't + * be too greedy. + */ +#define XFS_LOOKUP_BATCH 32 -STATIC xfs_inode_t * -xfs_inode_ag_lookup( - struct xfs_mount *mp, - struct xfs_perag *pag, - uint32_t *first_index, - int tag) +STATIC int +xfs_inode_ag_walk_grab( + struct xfs_inode *ip) { - int nr_found; - struct xfs_inode *ip; + struct inode *inode = VFS_I(ip); - /* - * use a gang lookup to find the next inode in the tree - * as the tree is sparse and a gang lookup walks to find - * the number of objects requested. - */ - if (tag == XFS_ICI_NO_TAG) { - nr_found = radix_tree_gang_lookup(&pag->pag_ici_root, - (void **)&ip, *first_index, 1); - } else { - nr_found = radix_tree_gang_lookup_tag(&pag->pag_ici_root, - (void **)&ip, *first_index, 1, tag); + /* nothing to sync during shutdown */ + if (XFS_FORCED_SHUTDOWN(ip->i_mount)) + return EFSCORRUPTED; + + /* avoid new or reclaimable inodes. Leave for reclaim code to flush */ + if (xfs_iflags_test(ip, XFS_INEW | XFS_IRECLAIMABLE | XFS_IRECLAIM)) + return ENOENT; + + /* If we can't grab the inode, it must on it's way to reclaim. */ + if (!igrab(inode)) + return ENOENT; + + if (is_bad_inode(inode)) { + IRELE(ip); + return ENOENT; } - if (!nr_found) - return NULL; - /* - * Update the index for the next lookup. Catch overflows - * into the next AG range which can occur if we have inodes - * in the last block of the AG and we are currently - * pointing to the last inode. - */ - *first_index = XFS_INO_TO_AGINO(mp, ip->i_ino + 1); - if (*first_index < XFS_INO_TO_AGINO(mp, ip->i_ino)) - return NULL; - return ip; + /* inode is valid */ + return 0; } STATIC int @@ -83,49 +80,75 @@ xfs_inode_ag_walk( struct xfs_perag *pag, int (*execute)(struct xfs_inode *ip, struct xfs_perag *pag, int flags), - int flags, - int tag, - int exclusive, - int *nr_to_scan) + int flags) { uint32_t first_index; int last_error = 0; int skipped; + int done; + int nr_found; restart: + done = 0; skipped = 0; first_index = 0; + nr_found = 0; do { + struct xfs_inode *batch[XFS_LOOKUP_BATCH]; int error = 0; - xfs_inode_t *ip; + int i; - if (exclusive) - write_lock(&pag->pag_ici_lock); - else - read_lock(&pag->pag_ici_lock); - ip = xfs_inode_ag_lookup(mp, pag, &first_index, tag); - if (!ip) { - if (exclusive) - write_unlock(&pag->pag_ici_lock); - else - read_unlock(&pag->pag_ici_lock); + read_lock(&pag->pag_ici_lock); + nr_found = radix_tree_gang_lookup(&pag->pag_ici_root, + (void **)batch, first_index, + XFS_LOOKUP_BATCH); + if (!nr_found) { + read_unlock(&pag->pag_ici_lock); break; } - /* execute releases pag->pag_ici_lock */ - error = execute(ip, pag, flags); - if (error == EAGAIN) { - skipped++; - continue; + /* + * Grab the inodes before we drop the lock. if we found + * nothing, nr == 0 and the loop will be skipped. + */ + for (i = 0; i < nr_found; i++) { + struct xfs_inode *ip = batch[i]; + + if (done || xfs_inode_ag_walk_grab(ip)) + batch[i] = NULL; + + /* + * Update the index for the next lookup. Catch overflows + * into the next AG range which can occur if we have inodes + * in the last block of the AG and we are currently + * pointing to the last inode. + */ + first_index = XFS_INO_TO_AGINO(mp, ip->i_ino + 1); + if (first_index < XFS_INO_TO_AGINO(mp, ip->i_ino)) + done = 1; + } + + /* unlock now we've grabbed the inodes. */ + read_unlock(&pag->pag_ici_lock); + + for (i = 0; i < nr_found; i++) { + if (!batch[i]) + continue; + error = execute(batch[i], pag, flags); + IRELE(batch[i]); + if (error == EAGAIN) { + skipped++; + continue; + } + if (error && last_error != EFSCORRUPTED) + last_error = error; } - if (error) - last_error = error; /* bail out if the filesystem is corrupted. */ if (error == EFSCORRUPTED) break; - } while ((*nr_to_scan)--); + } while (nr_found && !done); if (skipped) { delay(1); @@ -134,110 +157,32 @@ restart: return last_error; } -/* - * Select the next per-ag structure to iterate during the walk. The reclaim - * walk is optimised only to walk AGs with reclaimable inodes in them. - */ -static struct xfs_perag * -xfs_inode_ag_iter_next_pag( - struct xfs_mount *mp, - xfs_agnumber_t *first, - int tag) -{ - struct xfs_perag *pag = NULL; - - if (tag == XFS_ICI_RECLAIM_TAG) { - int found; - int ref; - - spin_lock(&mp->m_perag_lock); - found = radix_tree_gang_lookup_tag(&mp->m_perag_tree, - (void **)&pag, *first, 1, tag); - if (found <= 0) { - spin_unlock(&mp->m_perag_lock); - return NULL; - } - *first = pag->pag_agno + 1; - /* open coded pag reference increment */ - ref = atomic_inc_return(&pag->pag_ref); - spin_unlock(&mp->m_perag_lock); - trace_xfs_perag_get_reclaim(mp, pag->pag_agno, ref, _RET_IP_); - } else { - pag = xfs_perag_get(mp, *first); - (*first)++; - } - return pag; -} - int xfs_inode_ag_iterator( struct xfs_mount *mp, int (*execute)(struct xfs_inode *ip, struct xfs_perag *pag, int flags), - int flags, - int tag, - int exclusive, - int *nr_to_scan) + int flags) { struct xfs_perag *pag; int error = 0; int last_error = 0; xfs_agnumber_t ag; - int nr; - nr = nr_to_scan ? *nr_to_scan : INT_MAX; ag = 0; - while ((pag = xfs_inode_ag_iter_next_pag(mp, &ag, tag))) { - error = xfs_inode_ag_walk(mp, pag, execute, flags, tag, - exclusive, &nr); + while ((pag = xfs_perag_get(mp, ag))) { + ag = pag->pag_agno + 1; + error = xfs_inode_ag_walk(mp, pag, execute, flags); xfs_perag_put(pag); if (error) { last_error = error; if (error == EFSCORRUPTED) break; } - if (nr <= 0) - break; } - if (nr_to_scan) - *nr_to_scan = nr; return XFS_ERROR(last_error); } -/* must be called with pag_ici_lock held and releases it */ -int -xfs_sync_inode_valid( - struct xfs_inode *ip, - struct xfs_perag *pag) -{ - struct inode *inode = VFS_I(ip); - int error = EFSCORRUPTED; - - /* nothing to sync during shutdown */ - if (XFS_FORCED_SHUTDOWN(ip->i_mount)) - goto out_unlock; - - /* avoid new or reclaimable inodes. Leave for reclaim code to flush */ - error = ENOENT; - if (xfs_iflags_test(ip, XFS_INEW | XFS_IRECLAIMABLE | XFS_IRECLAIM)) - goto out_unlock; - - /* If we can't grab the inode, it must on it's way to reclaim. */ - if (!igrab(inode)) - goto out_unlock; - - if (is_bad_inode(inode)) { - IRELE(ip); - goto out_unlock; - } - - /* inode is valid */ - error = 0; -out_unlock: - read_unlock(&pag->pag_ici_lock); - return error; -} - STATIC int xfs_sync_inode_data( struct xfs_inode *ip, @@ -248,10 +193,6 @@ xfs_sync_inode_data( struct address_space *mapping = inode->i_mapping; int error = 0; - error = xfs_sync_inode_valid(ip, pag); - if (error) - return error; - if (!mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) goto out_wait; @@ -268,7 +209,6 @@ xfs_sync_inode_data( out_wait: if (flags & SYNC_WAIT) xfs_ioend_wait(ip); - IRELE(ip); return error; } @@ -280,10 +220,6 @@ xfs_sync_inode_attr( { int error = 0; - error = xfs_sync_inode_valid(ip, pag); - if (error) - return error; - xfs_ilock(ip, XFS_ILOCK_SHARED); if (xfs_inode_clean(ip)) goto out_unlock; @@ -302,7 +238,6 @@ xfs_sync_inode_attr( out_unlock: xfs_iunlock(ip, XFS_ILOCK_SHARED); - IRELE(ip); return error; } @@ -318,8 +253,7 @@ xfs_sync_data( ASSERT((flags & ~(SYNC_TRYLOCK|SYNC_WAIT)) == 0); - error = xfs_inode_ag_iterator(mp, xfs_sync_inode_data, flags, - XFS_ICI_NO_TAG, 0, NULL); + error = xfs_inode_ag_iterator(mp, xfs_sync_inode_data, flags); if (error) return XFS_ERROR(error); @@ -337,8 +271,7 @@ xfs_sync_attr( { ASSERT((flags & ~SYNC_WAIT) == 0); - return xfs_inode_ag_iterator(mp, xfs_sync_inode_attr, flags, - XFS_ICI_NO_TAG, 0, NULL); + return xfs_inode_ag_iterator(mp, xfs_sync_inode_attr, flags); } STATIC int @@ -698,6 +631,43 @@ __xfs_inode_clear_reclaim_tag( } /* + * Grab the inode for reclaim exclusively. + * Return 0 if we grabbed it, non-zero otherwise. + */ +STATIC int +xfs_reclaim_inode_grab( + struct xfs_inode *ip, + int flags) +{ + + /* + * do some unlocked checks first to avoid unnecceary lock traffic. + * The first is a flush lock check, the second is a already in reclaim + * check. Only do these checks if we are not going to block on locks. + */ + if ((flags & SYNC_TRYLOCK) && + (!ip->i_flush.done || __xfs_iflags_test(ip, XFS_IRECLAIM))) { + return 1; + } + + /* + * The radix tree lock here protects a thread in xfs_iget from racing + * with us starting reclaim on the inode. Once we have the + * XFS_IRECLAIM flag set it will not touch us. + */ + spin_lock(&ip->i_flags_lock); + ASSERT_ALWAYS(__xfs_iflags_test(ip, XFS_IRECLAIMABLE)); + if (__xfs_iflags_test(ip, XFS_IRECLAIM)) { + /* ignore as it is already under reclaim */ + spin_unlock(&ip->i_flags_lock); + return 1; + } + __xfs_iflags_set(ip, XFS_IRECLAIM); + spin_unlock(&ip->i_flags_lock); + return 0; +} + +/* * Inodes in different states need to be treated differently, and the return * value of xfs_iflush is not sufficient to get this right. The following table * lists the inode states and the reclaim actions necessary for non-blocking @@ -755,23 +725,6 @@ xfs_reclaim_inode( { int error = 0; - /* - * The radix tree lock here protects a thread in xfs_iget from racing - * with us starting reclaim on the inode. Once we have the - * XFS_IRECLAIM flag set it will not touch us. - */ - spin_lock(&ip->i_flags_lock); - ASSERT_ALWAYS(__xfs_iflags_test(ip, XFS_IRECLAIMABLE)); - if (__xfs_iflags_test(ip, XFS_IRECLAIM)) { - /* ignore as it is already under reclaim */ - spin_unlock(&ip->i_flags_lock); - write_unlock(&pag->pag_ici_lock); - return 0; - } - __xfs_iflags_set(ip, XFS_IRECLAIM); - spin_unlock(&ip->i_flags_lock); - write_unlock(&pag->pag_ici_lock); - xfs_ilock(ip, XFS_ILOCK_EXCL); if (!xfs_iflock_nowait(ip)) { if (!(sync_mode & SYNC_WAIT)) @@ -868,13 +821,126 @@ reclaim: } +/* + * Walk the AGs and reclaim the inodes in them. Even if the filesystem is + * corrupted, we still want to try to reclaim all the inodes. If we don't, + * then a shut down during filesystem unmount reclaim walk leak all the + * unreclaimed inodes. + */ +int +xfs_reclaim_inodes_ag( + struct xfs_mount *mp, + int flags, + int *nr_to_scan) +{ + struct xfs_perag *pag; + int error = 0; + int last_error = 0; + xfs_agnumber_t ag; + int trylock = flags & SYNC_TRYLOCK; + int skipped; + +restart: + ag = 0; + skipped = 0; + while ((pag = xfs_perag_get_tag(mp, ag, XFS_ICI_RECLAIM_TAG))) { + unsigned long first_index = 0; + int done = 0; + int nr_found = 0; + + ag = pag->pag_agno + 1; + + if (trylock) { + if (!mutex_trylock(&pag->pag_ici_reclaim_lock)) { + skipped++; + continue; + } + first_index = pag->pag_ici_reclaim_cursor; + } else + mutex_lock(&pag->pag_ici_reclaim_lock); + + do { + struct xfs_inode *batch[XFS_LOOKUP_BATCH]; + int i; + + write_lock(&pag->pag_ici_lock); + nr_found = radix_tree_gang_lookup_tag( + &pag->pag_ici_root, + (void **)batch, first_index, + XFS_LOOKUP_BATCH, + XFS_ICI_RECLAIM_TAG); + if (!nr_found) { + write_unlock(&pag->pag_ici_lock); + break; + } + + /* + * Grab the inodes before we drop the lock. if we found + * nothing, nr == 0 and the loop will be skipped. + */ + for (i = 0; i < nr_found; i++) { + struct xfs_inode *ip = batch[i]; + + if (done || xfs_reclaim_inode_grab(ip, flags)) + batch[i] = NULL; + + /* + * Update the index for the next lookup. Catch + * overflows into the next AG range which can + * occur if we have inodes in the last block of + * the AG and we are currently pointing to the + * last inode. + */ + first_index = XFS_INO_TO_AGINO(mp, ip->i_ino + 1); + if (first_index < XFS_INO_TO_AGINO(mp, ip->i_ino)) + done = 1; + } + + /* unlock now we've grabbed the inodes. */ + write_unlock(&pag->pag_ici_lock); + + for (i = 0; i < nr_found; i++) { + if (!batch[i]) + continue; + error = xfs_reclaim_inode(batch[i], pag, flags); + if (error && last_error != EFSCORRUPTED) + last_error = error; + } + + *nr_to_scan -= XFS_LOOKUP_BATCH; + + } while (nr_found && !done && *nr_to_scan > 0); + + if (trylock && !done) + pag->pag_ici_reclaim_cursor = first_index; + else + pag->pag_ici_reclaim_cursor = 0; + mutex_unlock(&pag->pag_ici_reclaim_lock); + xfs_perag_put(pag); + } + + /* + * if we skipped any AG, and we still have scan count remaining, do + * another pass this time using blocking reclaim semantics (i.e + * waiting on the reclaim locks and ignoring the reclaim cursors). This + * ensure that when we get more reclaimers than AGs we block rather + * than spin trying to execute reclaim. + */ + if (trylock && skipped && *nr_to_scan > 0) { + trylock = 0; + goto restart; + } + return XFS_ERROR(last_error); +} + int xfs_reclaim_inodes( xfs_mount_t *mp, int mode) { - return xfs_inode_ag_iterator(mp, xfs_reclaim_inode, mode, - XFS_ICI_RECLAIM_TAG, 1, NULL); + int nr_to_scan = INT_MAX; + + return xfs_reclaim_inodes_ag(mp, mode, &nr_to_scan); } /* @@ -896,17 +962,16 @@ xfs_reclaim_inode_shrink( if (!(gfp_mask & __GFP_FS)) return -1; - xfs_inode_ag_iterator(mp, xfs_reclaim_inode, 0, - XFS_ICI_RECLAIM_TAG, 1, &nr_to_scan); - /* if we don't exhaust the scan, don't bother coming back */ + xfs_reclaim_inodes_ag(mp, SYNC_TRYLOCK, &nr_to_scan); + /* terminate if we don't exhaust the scan */ if (nr_to_scan > 0) return -1; } reclaimable = 0; ag = 0; - while ((pag = xfs_inode_ag_iter_next_pag(mp, &ag, - XFS_ICI_RECLAIM_TAG))) { + while ((pag = xfs_perag_get_tag(mp, ag, XFS_ICI_RECLAIM_TAG))) { + ag = pag->pag_agno + 1; reclaimable += pag->pag_ici_reclaimable; xfs_perag_put(pag); } diff --git a/fs/xfs/linux-2.6/xfs_sync.h b/fs/xfs/linux-2.6/xfs_sync.h index fe78726196f8..32ba6628290c 100644 --- a/fs/xfs/linux-2.6/xfs_sync.h +++ b/fs/xfs/linux-2.6/xfs_sync.h @@ -47,10 +47,10 @@ void __xfs_inode_set_reclaim_tag(struct xfs_perag *pag, struct xfs_inode *ip); void __xfs_inode_clear_reclaim_tag(struct xfs_mount *mp, struct xfs_perag *pag, struct xfs_inode *ip); -int xfs_sync_inode_valid(struct xfs_inode *ip, struct xfs_perag *pag); +int xfs_sync_inode_grab(struct xfs_inode *ip); int xfs_inode_ag_iterator(struct xfs_mount *mp, int (*execute)(struct xfs_inode *ip, struct xfs_perag *pag, int flags), - int flags, int tag, int write_lock, int *nr_to_scan); + int flags); void xfs_inode_shrinker_register(struct xfs_mount *mp); void xfs_inode_shrinker_unregister(struct xfs_mount *mp); diff --git a/fs/xfs/linux-2.6/xfs_trace.h b/fs/xfs/linux-2.6/xfs_trace.h index be5dffd282a1..acef2e98c594 100644 --- a/fs/xfs/linux-2.6/xfs_trace.h +++ b/fs/xfs/linux-2.6/xfs_trace.h @@ -124,7 +124,7 @@ DEFINE_EVENT(xfs_perag_class, name, \ unsigned long caller_ip), \ TP_ARGS(mp, agno, refcount, caller_ip)) DEFINE_PERAG_REF_EVENT(xfs_perag_get); -DEFINE_PERAG_REF_EVENT(xfs_perag_get_reclaim); +DEFINE_PERAG_REF_EVENT(xfs_perag_get_tag); DEFINE_PERAG_REF_EVENT(xfs_perag_put); DEFINE_PERAG_REF_EVENT(xfs_perag_set_reclaim); DEFINE_PERAG_REF_EVENT(xfs_perag_clear_reclaim); @@ -325,13 +325,12 @@ DEFINE_BUF_EVENT(xfs_buf_lock); DEFINE_BUF_EVENT(xfs_buf_lock_done); DEFINE_BUF_EVENT(xfs_buf_cond_lock); DEFINE_BUF_EVENT(xfs_buf_unlock); -DEFINE_BUF_EVENT(xfs_buf_ordered_retry); DEFINE_BUF_EVENT(xfs_buf_iowait); DEFINE_BUF_EVENT(xfs_buf_iowait_done); DEFINE_BUF_EVENT(xfs_buf_delwri_queue); DEFINE_BUF_EVENT(xfs_buf_delwri_dequeue); DEFINE_BUF_EVENT(xfs_buf_delwri_split); -DEFINE_BUF_EVENT(xfs_buf_get_noaddr); +DEFINE_BUF_EVENT(xfs_buf_get_uncached); DEFINE_BUF_EVENT(xfs_bdstrat_shut); DEFINE_BUF_EVENT(xfs_buf_item_relse); DEFINE_BUF_EVENT(xfs_buf_item_iodone); diff --git a/fs/xfs/linux-2.6/xfs_version.h b/fs/xfs/linux-2.6/xfs_version.h deleted file mode 100644 index f8d279d7563a..000000000000 --- a/fs/xfs/linux-2.6/xfs_version.h +++ /dev/null @@ -1,29 +0,0 @@ -/* - * Copyright (c) 2001-2002,2005 Silicon Graphics, Inc. - * All Rights Reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it would be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write the Free Software Foundation, - * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - */ -#ifndef __XFS_VERSION_H__ -#define __XFS_VERSION_H__ - -/* - * Dummy file that can contain a timestamp to put into the - * XFS init string, to help users keep track of what they're - * running - */ - -#define XFS_VERSION_STRING "SGI XFS" - -#endif /* __XFS_VERSION_H__ */ diff --git a/fs/xfs/quota/xfs_dquot.c b/fs/xfs/quota/xfs_dquot.c index e1a2f6800e01..faf8e1a83a12 100644 --- a/fs/xfs/quota/xfs_dquot.c +++ b/fs/xfs/quota/xfs_dquot.c @@ -463,87 +463,68 @@ xfs_qm_dqtobp( uint flags) { xfs_bmbt_irec_t map; - int nmaps, error; + int nmaps = 1, error; xfs_buf_t *bp; - xfs_inode_t *quotip; - xfs_mount_t *mp; + xfs_inode_t *quotip = XFS_DQ_TO_QIP(dqp); + xfs_mount_t *mp = dqp->q_mount; xfs_disk_dquot_t *ddq; - xfs_dqid_t id; - boolean_t newdquot; + xfs_dqid_t id = be32_to_cpu(dqp->q_core.d_id); xfs_trans_t *tp = (tpp ? *tpp : NULL); - mp = dqp->q_mount; - id = be32_to_cpu(dqp->q_core.d_id); - nmaps = 1; - newdquot = B_FALSE; + dqp->q_fileoffset = (xfs_fileoff_t)id / mp->m_quotainfo->qi_dqperchunk; - /* - * If we don't know where the dquot lives, find out. - */ - if (dqp->q_blkno == (xfs_daddr_t) 0) { - /* We use the id as an index */ - dqp->q_fileoffset = (xfs_fileoff_t)id / - mp->m_quotainfo->qi_dqperchunk; - nmaps = 1; - quotip = XFS_DQ_TO_QIP(dqp); - xfs_ilock(quotip, XFS_ILOCK_SHARED); + xfs_ilock(quotip, XFS_ILOCK_SHARED); + if (XFS_IS_THIS_QUOTA_OFF(dqp)) { /* - * Return if this type of quotas is turned off while we didn't - * have an inode lock + * Return if this type of quotas is turned off while we + * didn't have the quota inode lock. */ - if (XFS_IS_THIS_QUOTA_OFF(dqp)) { - xfs_iunlock(quotip, XFS_ILOCK_SHARED); - return (ESRCH); - } + xfs_iunlock(quotip, XFS_ILOCK_SHARED); + return ESRCH; + } + + /* + * Find the block map; no allocations yet + */ + error = xfs_bmapi(NULL, quotip, dqp->q_fileoffset, + XFS_DQUOT_CLUSTER_SIZE_FSB, XFS_BMAPI_METADATA, + NULL, 0, &map, &nmaps, NULL); + + xfs_iunlock(quotip, XFS_ILOCK_SHARED); + if (error) + return error; + + ASSERT(nmaps == 1); + ASSERT(map.br_blockcount == 1); + + /* + * Offset of dquot in the (fixed sized) dquot chunk. + */ + dqp->q_bufoffset = (id % mp->m_quotainfo->qi_dqperchunk) * + sizeof(xfs_dqblk_t); + + ASSERT(map.br_startblock != DELAYSTARTBLOCK); + if (map.br_startblock == HOLESTARTBLOCK) { /* - * Find the block map; no allocations yet + * We don't allocate unless we're asked to */ - error = xfs_bmapi(NULL, quotip, dqp->q_fileoffset, - XFS_DQUOT_CLUSTER_SIZE_FSB, - XFS_BMAPI_METADATA, - NULL, 0, &map, &nmaps, NULL); + if (!(flags & XFS_QMOPT_DQALLOC)) + return ENOENT; - xfs_iunlock(quotip, XFS_ILOCK_SHARED); + ASSERT(tp); + error = xfs_qm_dqalloc(tpp, mp, dqp, quotip, + dqp->q_fileoffset, &bp); if (error) - return (error); - ASSERT(nmaps == 1); - ASSERT(map.br_blockcount == 1); + return error; + tp = *tpp; + } else { + trace_xfs_dqtobp_read(dqp); /* - * offset of dquot in the (fixed sized) dquot chunk. + * store the blkno etc so that we don't have to do the + * mapping all the time */ - dqp->q_bufoffset = (id % mp->m_quotainfo->qi_dqperchunk) * - sizeof(xfs_dqblk_t); - if (map.br_startblock == HOLESTARTBLOCK) { - /* - * We don't allocate unless we're asked to - */ - if (!(flags & XFS_QMOPT_DQALLOC)) - return (ENOENT); - - ASSERT(tp); - if ((error = xfs_qm_dqalloc(tpp, mp, dqp, quotip, - dqp->q_fileoffset, &bp))) - return (error); - tp = *tpp; - newdquot = B_TRUE; - } else { - /* - * store the blkno etc so that we don't have to do the - * mapping all the time - */ - dqp->q_blkno = XFS_FSB_TO_DADDR(mp, map.br_startblock); - } - } - ASSERT(dqp->q_blkno != DELAYSTARTBLOCK); - ASSERT(dqp->q_blkno != HOLESTARTBLOCK); - - /* - * Read in the buffer, unless we've just done the allocation - * (in which case we already have the buf). - */ - if (!newdquot) { - trace_xfs_dqtobp_read(dqp); + dqp->q_blkno = XFS_FSB_TO_DADDR(mp, map.br_startblock); error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, dqp->q_blkno, @@ -552,13 +533,14 @@ xfs_qm_dqtobp( if (error || !bp) return XFS_ERROR(error); } + ASSERT(XFS_BUF_ISBUSY(bp)); ASSERT(XFS_BUF_VALUSEMA(bp) <= 0); /* * calculate the location of the dquot inside the buffer. */ - ddq = (xfs_disk_dquot_t *)((char *)XFS_BUF_PTR(bp) + dqp->q_bufoffset); + ddq = (struct xfs_disk_dquot *)(XFS_BUF_PTR(bp) + dqp->q_bufoffset); /* * A simple sanity check in case we got a corrupted dquot... @@ -1176,18 +1158,18 @@ xfs_qm_dqflush( xfs_dquot_t *dqp, uint flags) { - xfs_mount_t *mp; - xfs_buf_t *bp; - xfs_disk_dquot_t *ddqp; + struct xfs_mount *mp = dqp->q_mount; + struct xfs_buf *bp; + struct xfs_disk_dquot *ddqp; int error; ASSERT(XFS_DQ_IS_LOCKED(dqp)); ASSERT(!completion_done(&dqp->q_flush)); + trace_xfs_dqflush(dqp); /* - * If not dirty, or it's pinned and we are not supposed to - * block, nada. + * If not dirty, or it's pinned and we are not supposed to block, nada. */ if (!XFS_DQ_IS_DIRTY(dqp) || (!(flags & SYNC_WAIT) && atomic_read(&dqp->q_pincount) > 0)) { @@ -1201,40 +1183,46 @@ xfs_qm_dqflush( * down forcibly. If that's the case we must not write this dquot * to disk, because the log record didn't make it to disk! */ - if (XFS_FORCED_SHUTDOWN(dqp->q_mount)) { - dqp->dq_flags &= ~(XFS_DQ_DIRTY); + if (XFS_FORCED_SHUTDOWN(mp)) { + dqp->dq_flags &= ~XFS_DQ_DIRTY; xfs_dqfunlock(dqp); return XFS_ERROR(EIO); } /* * Get the buffer containing the on-disk dquot - * We don't need a transaction envelope because we know that the - * the ondisk-dquot has already been allocated for. */ - if ((error = xfs_qm_dqtobp(NULL, dqp, &ddqp, &bp, XFS_QMOPT_DOWARN))) { + error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp, dqp->q_blkno, + mp->m_quotainfo->qi_dqchunklen, 0, &bp); + if (error) { ASSERT(error != ENOENT); - /* - * Quotas could have gotten turned off (ESRCH) - */ xfs_dqfunlock(dqp); - return (error); + return error; } - if (xfs_qm_dqcheck(&dqp->q_core, be32_to_cpu(ddqp->d_id), - 0, XFS_QMOPT_DOWARN, "dqflush (incore copy)")) { - xfs_force_shutdown(dqp->q_mount, SHUTDOWN_CORRUPT_INCORE); + /* + * Calculate the location of the dquot inside the buffer. + */ + ddqp = (struct xfs_disk_dquot *)(XFS_BUF_PTR(bp) + dqp->q_bufoffset); + + /* + * A simple sanity check in case we got a corrupted dquot.. + */ + if (xfs_qm_dqcheck(&dqp->q_core, be32_to_cpu(ddqp->d_id), 0, + XFS_QMOPT_DOWARN, "dqflush (incore copy)")) { + xfs_buf_relse(bp); + xfs_dqfunlock(dqp); + xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); return XFS_ERROR(EIO); } /* This is the only portion of data that needs to persist */ - memcpy(ddqp, &(dqp->q_core), sizeof(xfs_disk_dquot_t)); + memcpy(ddqp, &dqp->q_core, sizeof(xfs_disk_dquot_t)); /* * Clear the dirty field and remember the flush lsn for later use. */ - dqp->dq_flags &= ~(XFS_DQ_DIRTY); - mp = dqp->q_mount; + dqp->dq_flags &= ~XFS_DQ_DIRTY; xfs_trans_ail_copy_lsn(mp->m_ail, &dqp->q_logitem.qli_flush_lsn, &dqp->q_logitem.qli_item.li_lsn); diff --git a/fs/xfs/quota/xfs_qm.c b/fs/xfs/quota/xfs_qm.c index 9a92407109a1..f8e854b4fde8 100644 --- a/fs/xfs/quota/xfs_qm.c +++ b/fs/xfs/quota/xfs_qm.c @@ -55,8 +55,6 @@ uint ndquot; kmem_zone_t *qm_dqzone; kmem_zone_t *qm_dqtrxzone; -static cred_t xfs_zerocr; - STATIC void xfs_qm_list_init(xfs_dqlist_t *, char *, int); STATIC void xfs_qm_list_destroy(xfs_dqlist_t *); @@ -837,7 +835,7 @@ xfs_qm_dqattach_locked( 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, ip->i_d.di_projid, XFS_DQ_PROJ, + xfs_qm_dqattach_one(ip, xfs_get_projid(ip), XFS_DQ_PROJ, flags & XFS_QMOPT_DQALLOC, ip->i_udquot, &ip->i_gdquot); /* @@ -1199,87 +1197,6 @@ xfs_qm_list_destroy( mutex_destroy(&(list->qh_lock)); } - -/* - * Stripped down version of dqattach. This doesn't attach, or even look at the - * dquots attached to the inode. The rationale is that there won't be any - * attached at the time this is called from quotacheck. - */ -STATIC int -xfs_qm_dqget_noattach( - xfs_inode_t *ip, - xfs_dquot_t **O_udqpp, - xfs_dquot_t **O_gdqpp) -{ - int error; - xfs_mount_t *mp; - xfs_dquot_t *udqp, *gdqp; - - ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); - mp = ip->i_mount; - udqp = NULL; - gdqp = NULL; - - if (XFS_IS_UQUOTA_ON(mp)) { - ASSERT(ip->i_udquot == NULL); - /* - * We want the dquot allocated if it doesn't exist. - */ - if ((error = xfs_qm_dqget(mp, ip, ip->i_d.di_uid, XFS_DQ_USER, - XFS_QMOPT_DQALLOC | XFS_QMOPT_DOWARN, - &udqp))) { - /* - * Shouldn't be able to turn off quotas here. - */ - ASSERT(error != ESRCH); - ASSERT(error != ENOENT); - return error; - } - ASSERT(udqp); - } - - if (XFS_IS_OQUOTA_ON(mp)) { - ASSERT(ip->i_gdquot == NULL); - if (udqp) - xfs_dqunlock(udqp); - error = XFS_IS_GQUOTA_ON(mp) ? - xfs_qm_dqget(mp, ip, - ip->i_d.di_gid, XFS_DQ_GROUP, - XFS_QMOPT_DQALLOC|XFS_QMOPT_DOWARN, - &gdqp) : - xfs_qm_dqget(mp, ip, - ip->i_d.di_projid, XFS_DQ_PROJ, - XFS_QMOPT_DQALLOC|XFS_QMOPT_DOWARN, - &gdqp); - if (error) { - if (udqp) - xfs_qm_dqrele(udqp); - ASSERT(error != ESRCH); - ASSERT(error != ENOENT); - return error; - } - ASSERT(gdqp); - - /* Reacquire the locks in the right order */ - if (udqp) { - if (! xfs_qm_dqlock_nowait(udqp)) { - xfs_dqunlock(gdqp); - xfs_dqlock(udqp); - xfs_dqlock(gdqp); - } - } - } - - *O_udqpp = udqp; - *O_gdqpp = gdqp; - -#ifdef QUOTADEBUG - if (udqp) ASSERT(XFS_DQ_IS_LOCKED(udqp)); - if (gdqp) ASSERT(XFS_DQ_IS_LOCKED(gdqp)); -#endif - return 0; -} - /* * Create an inode and return with a reference already taken, but unlocked * This is how we create quota inodes @@ -1305,8 +1222,8 @@ xfs_qm_qino_alloc( return error; } - if ((error = xfs_dir_ialloc(&tp, NULL, S_IFREG, 1, 0, - &xfs_zerocr, 0, 1, ip, &committed))) { + error = xfs_dir_ialloc(&tp, NULL, S_IFREG, 1, 0, 0, 1, ip, &committed); + if (error) { xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT); return error; @@ -1516,7 +1433,7 @@ xfs_qm_dqiterate( rablkcnt = map[i+1].br_blockcount; rablkno = map[i+1].br_startblock; while (rablkcnt--) { - xfs_baread(mp->m_ddev_targp, + xfs_buf_readahead(mp->m_ddev_targp, XFS_FSB_TO_DADDR(mp, rablkno), mp->m_quotainfo->qi_dqchunklen); rablkno++; @@ -1546,18 +1463,34 @@ xfs_qm_dqiterate( /* * Called by dqusage_adjust in doing a quotacheck. - * Given the inode, and a dquot (either USR or GRP, doesn't matter), - * this updates its incore copy as well as the buffer copy. This is - * so that once the quotacheck is done, we can just log all the buffers, - * as opposed to logging numerous updates to individual dquots. + * + * Given the inode, and a dquot id this updates both the incore dqout as well + * as the buffer copy. This is so that once the quotacheck is done, we can + * just log all the buffers, as opposed to logging numerous updates to + * individual dquots. */ -STATIC void +STATIC int xfs_qm_quotacheck_dqadjust( - xfs_dquot_t *dqp, + struct xfs_inode *ip, + xfs_dqid_t id, + uint type, xfs_qcnt_t nblks, xfs_qcnt_t rtblks) { - ASSERT(XFS_DQ_IS_LOCKED(dqp)); + struct xfs_mount *mp = ip->i_mount; + struct xfs_dquot *dqp; + int error; + + error = xfs_qm_dqget(mp, ip, id, type, + XFS_QMOPT_DQALLOC | XFS_QMOPT_DOWARN, &dqp); + if (error) { + /* + * Shouldn't be able to turn off quotas here. + */ + ASSERT(error != ESRCH); + ASSERT(error != ENOENT); + return error; + } trace_xfs_dqadjust(dqp); @@ -1582,11 +1515,13 @@ xfs_qm_quotacheck_dqadjust( * There are no timers for the default values set in the root dquot. */ if (dqp->q_core.d_id) { - xfs_qm_adjust_dqlimits(dqp->q_mount, &dqp->q_core); - xfs_qm_adjust_dqtimers(dqp->q_mount, &dqp->q_core); + xfs_qm_adjust_dqlimits(mp, &dqp->q_core); + xfs_qm_adjust_dqtimers(mp, &dqp->q_core); } dqp->dq_flags |= XFS_DQ_DIRTY; + xfs_qm_dqput(dqp); + return 0; } STATIC int @@ -1629,8 +1564,7 @@ xfs_qm_dqusage_adjust( int *res) /* result code value */ { xfs_inode_t *ip; - xfs_dquot_t *udqp, *gdqp; - xfs_qcnt_t nblks, rtblks; + xfs_qcnt_t nblks, rtblks = 0; int error; ASSERT(XFS_IS_QUOTA_RUNNING(mp)); @@ -1650,51 +1584,24 @@ xfs_qm_dqusage_adjust( * the case in all other instances. It's OK that we do this because * quotacheck is done only at mount time. */ - if ((error = xfs_iget(mp, NULL, ino, 0, XFS_ILOCK_EXCL, &ip))) { + error = xfs_iget(mp, NULL, ino, 0, XFS_ILOCK_EXCL, &ip); + if (error) { *res = BULKSTAT_RV_NOTHING; return error; } - /* - * Obtain the locked dquots. In case of an error (eg. allocation - * fails for ENOSPC), we return the negative of the error number - * to bulkstat, so that it can get propagated to quotacheck() and - * making us disable quotas for the file system. - */ - if ((error = xfs_qm_dqget_noattach(ip, &udqp, &gdqp))) { - xfs_iunlock(ip, XFS_ILOCK_EXCL); - IRELE(ip); - *res = BULKSTAT_RV_GIVEUP; - return error; - } + ASSERT(ip->i_delayed_blks == 0); - rtblks = 0; - if (! XFS_IS_REALTIME_INODE(ip)) { - nblks = (xfs_qcnt_t)ip->i_d.di_nblocks; - } else { + if (XFS_IS_REALTIME_INODE(ip)) { /* * Walk thru the extent list and count the realtime blocks. */ - if ((error = xfs_qm_get_rtblks(ip, &rtblks))) { - xfs_iunlock(ip, XFS_ILOCK_EXCL); - IRELE(ip); - if (udqp) - xfs_qm_dqput(udqp); - if (gdqp) - xfs_qm_dqput(gdqp); - *res = BULKSTAT_RV_GIVEUP; - return error; - } - nblks = (xfs_qcnt_t)ip->i_d.di_nblocks - rtblks; + error = xfs_qm_get_rtblks(ip, &rtblks); + if (error) + goto error0; } - ASSERT(ip->i_delayed_blks == 0); - /* - * We can't release the inode while holding its dquot locks. - * The inode can go into inactive and might try to acquire the dquotlocks. - * So, just unlock here and do a vn_rele at the end. - */ - xfs_iunlock(ip, XFS_ILOCK_EXCL); + nblks = (xfs_qcnt_t)ip->i_d.di_nblocks - rtblks; /* * Add the (disk blocks and inode) resources occupied by this @@ -1709,26 +1616,36 @@ xfs_qm_dqusage_adjust( * and quotaoffs don't race. (Quotachecks happen at mount time only). */ if (XFS_IS_UQUOTA_ON(mp)) { - ASSERT(udqp); - xfs_qm_quotacheck_dqadjust(udqp, nblks, rtblks); - xfs_qm_dqput(udqp); + error = xfs_qm_quotacheck_dqadjust(ip, ip->i_d.di_uid, + XFS_DQ_USER, nblks, rtblks); + if (error) + goto error0; } - if (XFS_IS_OQUOTA_ON(mp)) { - ASSERT(gdqp); - xfs_qm_quotacheck_dqadjust(gdqp, nblks, rtblks); - xfs_qm_dqput(gdqp); + + if (XFS_IS_GQUOTA_ON(mp)) { + error = xfs_qm_quotacheck_dqadjust(ip, ip->i_d.di_gid, + XFS_DQ_GROUP, nblks, rtblks); + if (error) + goto error0; } - /* - * Now release the inode. This will send it to 'inactive', and - * possibly even free blocks. - */ - IRELE(ip); - /* - * Goto next inode. - */ + if (XFS_IS_PQUOTA_ON(mp)) { + error = xfs_qm_quotacheck_dqadjust(ip, xfs_get_projid(ip), + XFS_DQ_PROJ, nblks, rtblks); + if (error) + goto error0; + } + + xfs_iunlock(ip, XFS_ILOCK_EXCL); + IRELE(ip); *res = BULKSTAT_RV_DIDONE; return 0; + +error0: + xfs_iunlock(ip, XFS_ILOCK_EXCL); + IRELE(ip); + *res = BULKSTAT_RV_GIVEUP; + return error; } /* @@ -2224,7 +2141,7 @@ xfs_qm_write_sb_changes( /* - * Given an inode, a uid and gid (from cred_t) make sure that we have + * Given an inode, a uid, gid and prid make sure that we have * allocated relevant dquot(s) on disk, and that we won't exceed inode * quotas by creating this file. * This also attaches dquot(s) to the given inode after locking it, @@ -2332,7 +2249,7 @@ xfs_qm_vop_dqalloc( xfs_dqunlock(gq); } } else if ((flags & XFS_QMOPT_PQUOTA) && XFS_IS_PQUOTA_ON(mp)) { - if (ip->i_d.di_projid != prid) { + if (xfs_get_projid(ip) != prid) { xfs_iunlock(ip, lockflags); if ((error = xfs_qm_dqget(mp, NULL, (xfs_dqid_t)prid, XFS_DQ_PROJ, @@ -2454,7 +2371,7 @@ xfs_qm_vop_chown_reserve( } if (XFS_IS_OQUOTA_ON(ip->i_mount) && gdqp) { if (XFS_IS_PQUOTA_ON(ip->i_mount) && - ip->i_d.di_projid != be32_to_cpu(gdqp->q_core.d_id)) + xfs_get_projid(ip) != be32_to_cpu(gdqp->q_core.d_id)) prjflags = XFS_QMOPT_ENOSPC; if (prjflags || @@ -2558,7 +2475,7 @@ xfs_qm_vop_create_dqattach( ip->i_gdquot = gdqp; ASSERT(XFS_IS_OQUOTA_ON(mp)); ASSERT((XFS_IS_GQUOTA_ON(mp) ? - ip->i_d.di_gid : ip->i_d.di_projid) == + ip->i_d.di_gid : xfs_get_projid(ip)) == be32_to_cpu(gdqp->q_core.d_id)); xfs_trans_mod_dquot(tp, gdqp, XFS_TRANS_DQ_ICOUNT, 1); } diff --git a/fs/xfs/quota/xfs_qm_bhv.c b/fs/xfs/quota/xfs_qm_bhv.c index bea02d786c5d..45b5cb1788ab 100644 --- a/fs/xfs/quota/xfs_qm_bhv.c +++ b/fs/xfs/quota/xfs_qm_bhv.c @@ -81,7 +81,7 @@ xfs_qm_statvfs( xfs_mount_t *mp = ip->i_mount; xfs_dquot_t *dqp; - if (!xfs_qm_dqget(mp, NULL, ip->i_d.di_projid, XFS_DQ_PROJ, 0, &dqp)) { + if (!xfs_qm_dqget(mp, NULL, xfs_get_projid(ip), XFS_DQ_PROJ, 0, &dqp)) { xfs_fill_statvfs_from_dquot(statp, &dqp->q_core); xfs_qm_dqput(dqp); } diff --git a/fs/xfs/quota/xfs_qm_syscalls.c b/fs/xfs/quota/xfs_qm_syscalls.c index 45e5849df238..bdebc183223e 100644 --- a/fs/xfs/quota/xfs_qm_syscalls.c +++ b/fs/xfs/quota/xfs_qm_syscalls.c @@ -276,7 +276,7 @@ xfs_qm_scall_trunc_qfile( goto out_unlock; } - xfs_ichgtime(ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); + xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES); out_unlock: @@ -875,21 +875,14 @@ xfs_dqrele_inode( struct xfs_perag *pag, int flags) { - int error; - /* skip quota inodes */ if (ip == ip->i_mount->m_quotainfo->qi_uquotaip || ip == ip->i_mount->m_quotainfo->qi_gquotaip) { ASSERT(ip->i_udquot == NULL); ASSERT(ip->i_gdquot == NULL); - read_unlock(&pag->pag_ici_lock); return 0; } - error = xfs_sync_inode_valid(ip, pag); - if (error) - return error; - xfs_ilock(ip, XFS_ILOCK_EXCL); if ((flags & XFS_UQUOTA_ACCT) && ip->i_udquot) { xfs_qm_dqrele(ip->i_udquot); @@ -900,8 +893,6 @@ xfs_dqrele_inode( ip->i_gdquot = NULL; } xfs_iunlock(ip, XFS_ILOCK_EXCL); - - IRELE(ip); return 0; } @@ -918,8 +909,7 @@ xfs_qm_dqrele_all_inodes( uint flags) { ASSERT(mp->m_quotainfo); - xfs_inode_ag_iterator(mp, xfs_dqrele_inode, flags, - XFS_ICI_NO_TAG, 0, NULL); + xfs_inode_ag_iterator(mp, xfs_dqrele_inode, flags); } /*------------------------------------------------------------------------*/ @@ -1175,7 +1165,7 @@ xfs_qm_internalqcheck_adjust( } xfs_qm_internalqcheck_get_dquots(mp, (xfs_dqid_t) ip->i_d.di_uid, - (xfs_dqid_t) ip->i_d.di_projid, + (xfs_dqid_t) xfs_get_projid(ip), (xfs_dqid_t) ip->i_d.di_gid, &ud, &gd); if (XFS_IS_UQUOTA_ON(mp)) { diff --git a/fs/xfs/xfs_ag.h b/fs/xfs/xfs_ag.h index 4917d4eed4ed..63c7a1a6c022 100644 --- a/fs/xfs/xfs_ag.h +++ b/fs/xfs/xfs_ag.h @@ -230,6 +230,15 @@ typedef struct xfs_perag { rwlock_t pag_ici_lock; /* incore inode lock */ struct radix_tree_root pag_ici_root; /* incore inode cache root */ int pag_ici_reclaimable; /* reclaimable inodes */ + struct mutex pag_ici_reclaim_lock; /* serialisation point */ + unsigned long pag_ici_reclaim_cursor; /* reclaim restart point */ + + /* buffer cache index */ + spinlock_t pag_buf_lock; /* lock for pag_buf_tree */ + struct rb_root pag_buf_tree; /* ordered tree of active buffers */ + + /* for rcu-safe freeing */ + struct rcu_head rcu_head; #endif int pagb_count; /* pagb slots in use */ } xfs_perag_t; diff --git a/fs/xfs/xfs_alloc.c b/fs/xfs/xfs_alloc.c index af168faccc7a..112abc439ca5 100644 --- a/fs/xfs/xfs_alloc.c +++ b/fs/xfs/xfs_alloc.c @@ -675,7 +675,7 @@ xfs_alloc_ag_vextent_near( xfs_agblock_t gtbnoa; /* aligned ... */ xfs_extlen_t gtdiff; /* difference to right side entry */ xfs_extlen_t gtlen; /* length of right side entry */ - xfs_extlen_t gtlena; /* aligned ... */ + xfs_extlen_t gtlena = 0; /* aligned ... */ xfs_agblock_t gtnew; /* useful start bno of right side */ int error; /* error code */ int i; /* result code, temporary */ @@ -684,7 +684,7 @@ xfs_alloc_ag_vextent_near( xfs_agblock_t ltbnoa; /* aligned ... */ xfs_extlen_t ltdiff; /* difference to left side entry */ xfs_extlen_t ltlen; /* length of left side entry */ - xfs_extlen_t ltlena; /* aligned ... */ + xfs_extlen_t ltlena = 0; /* aligned ... */ xfs_agblock_t ltnew; /* useful start bno of left side */ xfs_extlen_t rlen; /* length of returned extent */ #if defined(DEBUG) && defined(__KERNEL__) diff --git a/fs/xfs/xfs_alloc_btree.c b/fs/xfs/xfs_alloc_btree.c index 97f7328967fd..3916925e2584 100644 --- a/fs/xfs/xfs_alloc_btree.c +++ b/fs/xfs/xfs_alloc_btree.c @@ -280,38 +280,6 @@ xfs_allocbt_key_diff( return (__int64_t)be32_to_cpu(kp->ar_startblock) - rec->ar_startblock; } -STATIC int -xfs_allocbt_kill_root( - struct xfs_btree_cur *cur, - struct xfs_buf *bp, - int level, - union xfs_btree_ptr *newroot) -{ - int error; - - XFS_BTREE_TRACE_CURSOR(cur, XBT_ENTRY); - XFS_BTREE_STATS_INC(cur, killroot); - - /* - * Update the root pointer, decreasing the level by 1 and then - * free the old root. - */ - xfs_allocbt_set_root(cur, newroot, -1); - error = xfs_allocbt_free_block(cur, bp); - if (error) { - XFS_BTREE_TRACE_CURSOR(cur, XBT_ERROR); - return error; - } - - XFS_BTREE_STATS_INC(cur, free); - - xfs_btree_setbuf(cur, level, NULL); - cur->bc_nlevels--; - - XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT); - return 0; -} - #ifdef DEBUG STATIC int xfs_allocbt_keys_inorder( @@ -423,7 +391,6 @@ static const struct xfs_btree_ops xfs_allocbt_ops = { .dup_cursor = xfs_allocbt_dup_cursor, .set_root = xfs_allocbt_set_root, - .kill_root = xfs_allocbt_kill_root, .alloc_block = xfs_allocbt_alloc_block, .free_block = xfs_allocbt_free_block, .update_lastrec = xfs_allocbt_update_lastrec, diff --git a/fs/xfs/xfs_attr.c b/fs/xfs/xfs_attr.c index c2568242a901..c86375378810 100644 --- a/fs/xfs/xfs_attr.c +++ b/fs/xfs/xfs_attr.c @@ -355,16 +355,15 @@ xfs_attr_set_int( if (mp->m_flags & XFS_MOUNT_WSYNC) { xfs_trans_set_sync(args.trans); } + + if (!error && (flags & ATTR_KERNOTIME) == 0) { + xfs_trans_ichgtime(args.trans, dp, + XFS_ICHGTIME_CHG); + } err2 = xfs_trans_commit(args.trans, XFS_TRANS_RELEASE_LOG_RES); xfs_iunlock(dp, XFS_ILOCK_EXCL); - /* - * Hit the inode change time. - */ - if (!error && (flags & ATTR_KERNOTIME) == 0) { - xfs_ichgtime(dp, XFS_ICHGTIME_CHG); - } return(error == 0 ? err2 : error); } @@ -420,6 +419,9 @@ xfs_attr_set_int( xfs_trans_set_sync(args.trans); } + if ((flags & ATTR_KERNOTIME) == 0) + xfs_trans_ichgtime(args.trans, dp, XFS_ICHGTIME_CHG); + /* * Commit the last in the sequence of transactions. */ @@ -427,13 +429,6 @@ xfs_attr_set_int( error = xfs_trans_commit(args.trans, XFS_TRANS_RELEASE_LOG_RES); xfs_iunlock(dp, XFS_ILOCK_EXCL); - /* - * Hit the inode change time. - */ - if (!error && (flags & ATTR_KERNOTIME) == 0) { - xfs_ichgtime(dp, XFS_ICHGTIME_CHG); - } - return(error); out: @@ -567,6 +562,9 @@ xfs_attr_remove_int(xfs_inode_t *dp, struct xfs_name *name, int flags) xfs_trans_set_sync(args.trans); } + if ((flags & ATTR_KERNOTIME) == 0) + xfs_trans_ichgtime(args.trans, dp, XFS_ICHGTIME_CHG); + /* * Commit the last in the sequence of transactions. */ @@ -574,13 +572,6 @@ xfs_attr_remove_int(xfs_inode_t *dp, struct xfs_name *name, int flags) error = xfs_trans_commit(args.trans, XFS_TRANS_RELEASE_LOG_RES); xfs_iunlock(dp, XFS_ILOCK_EXCL); - /* - * Hit the inode change time. - */ - if (!error && (flags & ATTR_KERNOTIME) == 0) { - xfs_ichgtime(dp, XFS_ICHGTIME_CHG); - } - return(error); out: @@ -1995,7 +1986,7 @@ xfs_attr_rmtval_get(xfs_da_args_t *args) tmp = (valuelen < XFS_BUF_SIZE(bp)) ? valuelen : XFS_BUF_SIZE(bp); - xfs_biomove(bp, 0, tmp, dst, XBF_READ); + xfs_buf_iomove(bp, 0, tmp, dst, XBRW_READ); xfs_buf_relse(bp); dst += tmp; valuelen -= tmp; @@ -2125,9 +2116,9 @@ xfs_attr_rmtval_set(xfs_da_args_t *args) tmp = (valuelen < XFS_BUF_SIZE(bp)) ? valuelen : XFS_BUF_SIZE(bp); - xfs_biomove(bp, 0, tmp, src, XBF_WRITE); + xfs_buf_iomove(bp, 0, tmp, src, XBRW_WRITE); if (tmp < XFS_BUF_SIZE(bp)) - xfs_biozero(bp, tmp, XFS_BUF_SIZE(bp) - tmp); + xfs_buf_zero(bp, tmp, XFS_BUF_SIZE(bp) - tmp); if ((error = xfs_bwrite(mp, bp))) {/* GROT: NOTE: synchronous write */ return (error); } diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c index f90dadd5a968..8abd12e32e13 100644 --- a/fs/xfs/xfs_bmap.c +++ b/fs/xfs/xfs_bmap.c @@ -614,7 +614,7 @@ xfs_bmap_add_extent( nblks += cur->bc_private.b.allocated; ASSERT(nblks <= da_old); if (nblks < da_old) - xfs_mod_incore_sb(ip->i_mount, XFS_SBS_FDBLOCKS, + xfs_icsb_modify_counters(ip->i_mount, XFS_SBS_FDBLOCKS, (int64_t)(da_old - nblks), rsvd); } /* @@ -1079,7 +1079,8 @@ xfs_bmap_add_extent_delay_real( diff = (int)(temp + temp2 - startblockval(PREV.br_startblock) - (cur ? cur->bc_private.b.allocated : 0)); if (diff > 0 && - xfs_mod_incore_sb(ip->i_mount, XFS_SBS_FDBLOCKS, -((int64_t)diff), rsvd)) { + xfs_icsb_modify_counters(ip->i_mount, XFS_SBS_FDBLOCKS, + -((int64_t)diff), rsvd)) { /* * Ick gross gag me with a spoon. */ @@ -1089,16 +1090,18 @@ xfs_bmap_add_extent_delay_real( temp--; diff--; if (!diff || - !xfs_mod_incore_sb(ip->i_mount, - XFS_SBS_FDBLOCKS, -((int64_t)diff), rsvd)) + !xfs_icsb_modify_counters(ip->i_mount, + XFS_SBS_FDBLOCKS, + -((int64_t)diff), rsvd)) break; } if (temp2) { temp2--; diff--; if (!diff || - !xfs_mod_incore_sb(ip->i_mount, - XFS_SBS_FDBLOCKS, -((int64_t)diff), rsvd)) + !xfs_icsb_modify_counters(ip->i_mount, + XFS_SBS_FDBLOCKS, + -((int64_t)diff), rsvd)) break; } } @@ -1766,7 +1769,7 @@ xfs_bmap_add_extent_hole_delay( } if (oldlen != newlen) { ASSERT(oldlen > newlen); - xfs_mod_incore_sb(ip->i_mount, XFS_SBS_FDBLOCKS, + xfs_icsb_modify_counters(ip->i_mount, XFS_SBS_FDBLOCKS, (int64_t)(oldlen - newlen), rsvd); /* * Nothing to do for disk quota accounting here. @@ -3111,9 +3114,10 @@ xfs_bmap_del_extent( * Nothing to do for disk quota accounting here. */ ASSERT(da_old >= da_new); - if (da_old > da_new) - xfs_mod_incore_sb(mp, XFS_SBS_FDBLOCKS, (int64_t)(da_old - da_new), - rsvd); + if (da_old > da_new) { + xfs_icsb_modify_counters(mp, XFS_SBS_FDBLOCKS, + (int64_t)(da_old - da_new), rsvd); + } done: *logflagsp = flags; return error; @@ -4526,13 +4530,13 @@ xfs_bmapi( -((int64_t)extsz), (flags & XFS_BMAPI_RSVBLOCKS)); } else { - error = xfs_mod_incore_sb(mp, + error = xfs_icsb_modify_counters(mp, XFS_SBS_FDBLOCKS, -((int64_t)alen), (flags & XFS_BMAPI_RSVBLOCKS)); } if (!error) { - error = xfs_mod_incore_sb(mp, + error = xfs_icsb_modify_counters(mp, XFS_SBS_FDBLOCKS, -((int64_t)indlen), (flags & XFS_BMAPI_RSVBLOCKS)); @@ -4542,7 +4546,7 @@ xfs_bmapi( (int64_t)extsz, (flags & XFS_BMAPI_RSVBLOCKS)); else if (error) - xfs_mod_incore_sb(mp, + xfs_icsb_modify_counters(mp, XFS_SBS_FDBLOCKS, (int64_t)alen, (flags & XFS_BMAPI_RSVBLOCKS)); @@ -4744,8 +4748,12 @@ xfs_bmapi( * Check if writing previously allocated but * unwritten extents. */ - if (wr && mval->br_state == XFS_EXT_UNWRITTEN && - ((flags & (XFS_BMAPI_PREALLOC|XFS_BMAPI_DELAY)) == 0)) { + if (wr && + ((mval->br_state == XFS_EXT_UNWRITTEN && + ((flags & (XFS_BMAPI_PREALLOC|XFS_BMAPI_DELAY)) == 0)) || + (mval->br_state == XFS_EXT_NORM && + ((flags & (XFS_BMAPI_PREALLOC|XFS_BMAPI_CONVERT)) == + (XFS_BMAPI_PREALLOC|XFS_BMAPI_CONVERT))))) { /* * Modify (by adding) the state flag, if writing. */ @@ -4757,7 +4765,9 @@ xfs_bmapi( *firstblock; cur->bc_private.b.flist = flist; } - mval->br_state = XFS_EXT_NORM; + mval->br_state = (mval->br_state == XFS_EXT_UNWRITTEN) + ? XFS_EXT_NORM + : XFS_EXT_UNWRITTEN; error = xfs_bmap_add_extent(ip, lastx, &cur, mval, firstblock, flist, &tmp_logflags, whichfork, (flags & XFS_BMAPI_RSVBLOCKS)); @@ -5200,7 +5210,7 @@ xfs_bunmapi( ip, -((long)del.br_blockcount), 0, XFS_QMOPT_RES_RTBLKS); } else { - xfs_mod_incore_sb(mp, XFS_SBS_FDBLOCKS, + xfs_icsb_modify_counters(mp, XFS_SBS_FDBLOCKS, (int64_t)del.br_blockcount, rsvd); (void)xfs_trans_reserve_quota_nblks(NULL, ip, -((long)del.br_blockcount), 0, diff --git a/fs/xfs/xfs_bmap.h b/fs/xfs/xfs_bmap.h index b13569a6179b..71ec9b6ecdfc 100644 --- a/fs/xfs/xfs_bmap.h +++ b/fs/xfs/xfs_bmap.h @@ -74,9 +74,12 @@ typedef struct xfs_bmap_free #define XFS_BMAPI_IGSTATE 0x080 /* Ignore state - */ /* combine contig. space */ #define XFS_BMAPI_CONTIG 0x100 /* must allocate only one extent */ -#define XFS_BMAPI_CONVERT 0x200 /* unwritten extent conversion - */ - /* need write cache flushing and no */ - /* additional allocation alignments */ +/* + * unwritten extent conversion - this needs write cache flushing and no additional + * allocation alignments. When specified with XFS_BMAPI_PREALLOC it converts + * from written to unwritten, otherwise convert from unwritten to written. + */ +#define XFS_BMAPI_CONVERT 0x200 #define XFS_BMAPI_FLAGS \ { XFS_BMAPI_WRITE, "WRITE" }, \ diff --git a/fs/xfs/xfs_btree.c b/fs/xfs/xfs_btree.c index 829af92f0fba..04f9cca8da7e 100644 --- a/fs/xfs/xfs_btree.c +++ b/fs/xfs/xfs_btree.c @@ -217,7 +217,7 @@ xfs_btree_del_cursor( */ for (i = 0; i < cur->bc_nlevels; i++) { if (cur->bc_bufs[i]) - xfs_btree_setbuf(cur, i, NULL); + xfs_trans_brelse(cur->bc_tp, cur->bc_bufs[i]); else if (!error) break; } @@ -656,7 +656,7 @@ xfs_btree_reada_bufl( ASSERT(fsbno != NULLFSBLOCK); d = XFS_FSB_TO_DADDR(mp, fsbno); - xfs_baread(mp->m_ddev_targp, d, mp->m_bsize * count); + xfs_buf_readahead(mp->m_ddev_targp, d, mp->m_bsize * count); } /* @@ -676,7 +676,7 @@ xfs_btree_reada_bufs( ASSERT(agno != NULLAGNUMBER); ASSERT(agbno != NULLAGBLOCK); d = XFS_AGB_TO_DADDR(mp, agno, agbno); - xfs_baread(mp->m_ddev_targp, d, mp->m_bsize * count); + xfs_buf_readahead(mp->m_ddev_targp, d, mp->m_bsize * count); } STATIC int @@ -763,22 +763,19 @@ xfs_btree_readahead( * Set the buffer for level "lev" in the cursor to bp, releasing * any previous buffer. */ -void +STATIC void xfs_btree_setbuf( xfs_btree_cur_t *cur, /* btree cursor */ int lev, /* level in btree */ xfs_buf_t *bp) /* new buffer to set */ { struct xfs_btree_block *b; /* btree block */ - xfs_buf_t *obp; /* old buffer pointer */ - obp = cur->bc_bufs[lev]; - if (obp) - xfs_trans_brelse(cur->bc_tp, obp); + if (cur->bc_bufs[lev]) + xfs_trans_brelse(cur->bc_tp, cur->bc_bufs[lev]); cur->bc_bufs[lev] = bp; cur->bc_ra[lev] = 0; - if (!bp) - return; + b = XFS_BUF_TO_BLOCK(bp); if (cur->bc_flags & XFS_BTREE_LONG_PTRS) { if (be64_to_cpu(b->bb_u.l.bb_leftsib) == NULLDFSBNO) @@ -3011,6 +3008,43 @@ out0: return 0; } +/* + * Kill the current root node, and replace it with it's only child node. + */ +STATIC int +xfs_btree_kill_root( + struct xfs_btree_cur *cur, + struct xfs_buf *bp, + int level, + union xfs_btree_ptr *newroot) +{ + int error; + + XFS_BTREE_TRACE_CURSOR(cur, XBT_ENTRY); + XFS_BTREE_STATS_INC(cur, killroot); + + /* + * Update the root pointer, decreasing the level by 1 and then + * free the old root. + */ + cur->bc_ops->set_root(cur, newroot, -1); + + error = cur->bc_ops->free_block(cur, bp); + if (error) { + XFS_BTREE_TRACE_CURSOR(cur, XBT_ERROR); + return error; + } + + XFS_BTREE_STATS_INC(cur, free); + + cur->bc_bufs[level] = NULL; + cur->bc_ra[level] = 0; + cur->bc_nlevels--; + + XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT); + return 0; +} + STATIC int xfs_btree_dec_cursor( struct xfs_btree_cur *cur, @@ -3195,7 +3229,7 @@ xfs_btree_delrec( * Make it the new root of the btree. */ pp = xfs_btree_ptr_addr(cur, 1, block); - error = cur->bc_ops->kill_root(cur, bp, level, pp); + error = xfs_btree_kill_root(cur, bp, level, pp); if (error) goto error0; } else if (level > 0) { diff --git a/fs/xfs/xfs_btree.h b/fs/xfs/xfs_btree.h index 7fa07062bdda..82fafc66bd1f 100644 --- a/fs/xfs/xfs_btree.h +++ b/fs/xfs/xfs_btree.h @@ -152,9 +152,7 @@ struct xfs_btree_ops { /* update btree root pointer */ void (*set_root)(struct xfs_btree_cur *cur, - union xfs_btree_ptr *nptr, int level_change); - int (*kill_root)(struct xfs_btree_cur *cur, struct xfs_buf *bp, - int level, union xfs_btree_ptr *newroot); + union xfs_btree_ptr *nptr, int level_change); /* block allocation / freeing */ int (*alloc_block)(struct xfs_btree_cur *cur, @@ -399,16 +397,6 @@ xfs_btree_reada_bufs( xfs_agblock_t agbno, /* allocation group block number */ xfs_extlen_t count); /* count of filesystem blocks */ -/* - * Set the buffer for level "lev" in the cursor to bp, releasing - * any previous buffer. - */ -void -xfs_btree_setbuf( - xfs_btree_cur_t *cur, /* btree cursor */ - int lev, /* level in btree */ - struct xfs_buf *bp); /* new buffer to set */ - /* * Common btree core entry points. diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index 1b09d7a280df..2686d0d54c5b 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -692,8 +692,7 @@ xfs_buf_item_init( * the first. If we do already have one, there is * nothing to do here so return. */ - if (bp->b_mount != mp) - bp->b_mount = mp; + ASSERT(bp->b_target->bt_mount == mp); if (XFS_BUF_FSPRIVATE(bp, void *) != NULL) { lip = XFS_BUF_FSPRIVATE(bp, xfs_log_item_t *); if (lip->li_type == XFS_LI_BUF) { @@ -974,7 +973,7 @@ xfs_buf_iodone_callbacks( xfs_buf_do_callbacks(bp, lip); XFS_BUF_SET_FSPRIVATE(bp, NULL); XFS_BUF_CLR_IODONE_FUNC(bp); - xfs_biodone(bp); + xfs_buf_ioend(bp, 0); return; } @@ -1033,7 +1032,7 @@ xfs_buf_iodone_callbacks( xfs_buf_do_callbacks(bp, lip); XFS_BUF_SET_FSPRIVATE(bp, NULL); XFS_BUF_CLR_IODONE_FUNC(bp); - xfs_biodone(bp); + xfs_buf_ioend(bp, 0); } /* diff --git a/fs/xfs/xfs_da_btree.c b/fs/xfs/xfs_da_btree.c index 30fa0e206fba..1c00bedb3175 100644 --- a/fs/xfs/xfs_da_btree.c +++ b/fs/xfs/xfs_da_btree.c @@ -2042,7 +2042,7 @@ xfs_da_do_buf( mappedbno, nmapped, 0, &bp); break; case 3: - xfs_baread(mp->m_ddev_targp, mappedbno, nmapped); + xfs_buf_readahead(mp->m_ddev_targp, mappedbno, nmapped); error = 0; bp = NULL; break; diff --git a/fs/xfs/xfs_dinode.h b/fs/xfs/xfs_dinode.h index e5b153b2e6a3..dffba9ba0db6 100644 --- a/fs/xfs/xfs_dinode.h +++ b/fs/xfs/xfs_dinode.h @@ -49,8 +49,9 @@ typedef struct xfs_dinode { __be32 di_uid; /* owner's user id */ __be32 di_gid; /* owner's group id */ __be32 di_nlink; /* number of links to file */ - __be16 di_projid; /* owner's project id */ - __u8 di_pad[8]; /* unused, zeroed space */ + __be16 di_projid_lo; /* lower part of owner's project id */ + __be16 di_projid_hi; /* higher part owner's project id */ + __u8 di_pad[6]; /* unused, zeroed space */ __be16 di_flushiter; /* incremented on flush */ xfs_timestamp_t di_atime; /* time last accessed */ xfs_timestamp_t di_mtime; /* time last modified */ diff --git a/fs/xfs/xfs_dir2_leaf.c b/fs/xfs/xfs_dir2_leaf.c index 504be8640e91..ae891223be90 100644 --- a/fs/xfs/xfs_dir2_leaf.c +++ b/fs/xfs/xfs_dir2_leaf.c @@ -961,7 +961,7 @@ xfs_dir2_leaf_getdents( if (i > ra_current && map[ra_index].br_blockcount >= mp->m_dirblkfsbs) { - xfs_baread(mp->m_ddev_targp, + xfs_buf_readahead(mp->m_ddev_targp, XFS_FSB_TO_DADDR(mp, map[ra_index].br_startblock + ra_offset), diff --git a/fs/xfs/xfs_fs.h b/fs/xfs/xfs_fs.h index 87c2e9d02288..8f6fc1a96386 100644 --- a/fs/xfs/xfs_fs.h +++ b/fs/xfs/xfs_fs.h @@ -293,9 +293,11 @@ typedef struct xfs_bstat { __s32 bs_extsize; /* extent size */ __s32 bs_extents; /* number of extents */ __u32 bs_gen; /* generation count */ - __u16 bs_projid; /* project id */ + __u16 bs_projid_lo; /* lower part of project id */ +#define bs_projid bs_projid_lo /* (previously just bs_projid) */ __u16 bs_forkoff; /* inode fork offset in bytes */ - unsigned char bs_pad[12]; /* pad space, unused */ + __u16 bs_projid_hi; /* higher part of project id */ + unsigned char bs_pad[10]; /* pad space, unused */ __u32 bs_dmevmask; /* DMIG event mask */ __u16 bs_dmstate; /* DMIG state info */ __u16 bs_aextents; /* attribute number of extents */ @@ -448,6 +450,7 @@ typedef struct xfs_handle { /* XFS_IOC_SETBIOSIZE ---- deprecated 46 */ /* XFS_IOC_GETBIOSIZE ---- deprecated 47 */ #define XFS_IOC_GETBMAPX _IOWR('X', 56, struct getbmap) +#define XFS_IOC_ZERO_RANGE _IOW ('X', 57, struct xfs_flock64) /* * ioctl commands that replace IRIX syssgi()'s diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index 43b1d5699335..a7c116e814af 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -144,12 +144,11 @@ xfs_growfs_data_private( if ((error = xfs_sb_validate_fsb_count(&mp->m_sb, nb))) return error; dpct = pct - mp->m_sb.sb_imax_pct; - error = xfs_read_buf(mp, mp->m_ddev_targp, - XFS_FSB_TO_BB(mp, nb) - XFS_FSS_TO_BB(mp, 1), - XFS_FSS_TO_BB(mp, 1), 0, &bp); - if (error) - return error; - ASSERT(bp); + bp = xfs_buf_read_uncached(mp, mp->m_ddev_targp, + XFS_FSB_TO_BB(mp, nb) - XFS_FSS_TO_BB(mp, 1), + BBTOB(XFS_FSS_TO_BB(mp, 1)), 0); + if (!bp) + return EIO; xfs_buf_relse(bp); new = nb; /* use new as a temporary here */ @@ -597,7 +596,8 @@ out: * the extra reserve blocks from the reserve..... */ int error; - error = xfs_mod_incore_sb(mp, XFS_SBS_FDBLOCKS, fdblks_delta, 0); + error = xfs_icsb_modify_counters(mp, XFS_SBS_FDBLOCKS, + fdblks_delta, 0); if (error == ENOSPC) goto retry; } diff --git a/fs/xfs/xfs_ialloc.c b/fs/xfs/xfs_ialloc.c index 5371d2dc360e..0626a32c3447 100644 --- a/fs/xfs/xfs_ialloc.c +++ b/fs/xfs/xfs_ialloc.c @@ -212,7 +212,7 @@ xfs_ialloc_inode_init( * to log a whole cluster of inodes instead of all the * individual transactions causing a lot of log traffic. */ - xfs_biozero(fbuf, 0, ninodes << mp->m_sb.sb_inodelog); + xfs_buf_zero(fbuf, 0, ninodes << mp->m_sb.sb_inodelog); for (i = 0; i < ninodes; i++) { int ioffset = i << mp->m_sb.sb_inodelog; uint isize = sizeof(struct xfs_dinode); diff --git a/fs/xfs/xfs_ialloc_btree.c b/fs/xfs/xfs_ialloc_btree.c index d352862cefa0..16921f55c542 100644 --- a/fs/xfs/xfs_ialloc_btree.c +++ b/fs/xfs/xfs_ialloc_btree.c @@ -183,38 +183,6 @@ xfs_inobt_key_diff( cur->bc_rec.i.ir_startino; } -STATIC int -xfs_inobt_kill_root( - struct xfs_btree_cur *cur, - struct xfs_buf *bp, - int level, - union xfs_btree_ptr *newroot) -{ - int error; - - XFS_BTREE_TRACE_CURSOR(cur, XBT_ENTRY); - XFS_BTREE_STATS_INC(cur, killroot); - - /* - * Update the root pointer, decreasing the level by 1 and then - * free the old root. - */ - xfs_inobt_set_root(cur, newroot, -1); - error = xfs_inobt_free_block(cur, bp); - if (error) { - XFS_BTREE_TRACE_CURSOR(cur, XBT_ERROR); - return error; - } - - XFS_BTREE_STATS_INC(cur, free); - - cur->bc_bufs[level] = NULL; - cur->bc_nlevels--; - - XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT); - return 0; -} - #ifdef DEBUG STATIC int xfs_inobt_keys_inorder( @@ -309,7 +277,6 @@ static const struct xfs_btree_ops xfs_inobt_ops = { .dup_cursor = xfs_inobt_dup_cursor, .set_root = xfs_inobt_set_root, - .kill_root = xfs_inobt_kill_root, .alloc_block = xfs_inobt_alloc_block, .free_block = xfs_inobt_free_block, .get_minrecs = xfs_inobt_get_minrecs, diff --git a/fs/xfs/xfs_iget.c b/fs/xfs/xfs_iget.c index b1ecc6f97ade..0cdd26932d8e 100644 --- a/fs/xfs/xfs_iget.c +++ b/fs/xfs/xfs_iget.c @@ -365,8 +365,8 @@ xfs_iget( xfs_perag_t *pag; xfs_agino_t agino; - /* the radix tree exists only in inode capable AGs */ - if (XFS_INO_TO_AGNO(mp, ino) >= mp->m_maxagi) + /* reject inode numbers outside existing AGs */ + if (XFS_INO_TO_AGNO(mp, ino) >= mp->m_sb.sb_agcount) return EINVAL; /* get the perag structure and ensure that it's inode capable */ diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 34798f391c49..108c7a085f94 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -660,7 +660,8 @@ xfs_dinode_from_disk( to->di_uid = be32_to_cpu(from->di_uid); to->di_gid = be32_to_cpu(from->di_gid); to->di_nlink = be32_to_cpu(from->di_nlink); - to->di_projid = be16_to_cpu(from->di_projid); + to->di_projid_lo = be16_to_cpu(from->di_projid_lo); + to->di_projid_hi = be16_to_cpu(from->di_projid_hi); memcpy(to->di_pad, from->di_pad, sizeof(to->di_pad)); to->di_flushiter = be16_to_cpu(from->di_flushiter); to->di_atime.t_sec = be32_to_cpu(from->di_atime.t_sec); @@ -695,7 +696,8 @@ xfs_dinode_to_disk( to->di_uid = cpu_to_be32(from->di_uid); to->di_gid = cpu_to_be32(from->di_gid); to->di_nlink = cpu_to_be32(from->di_nlink); - to->di_projid = cpu_to_be16(from->di_projid); + to->di_projid_lo = cpu_to_be16(from->di_projid_lo); + to->di_projid_hi = cpu_to_be16(from->di_projid_hi); memcpy(to->di_pad, from->di_pad, sizeof(to->di_pad)); to->di_flushiter = cpu_to_be16(from->di_flushiter); to->di_atime.t_sec = cpu_to_be32(from->di_atime.t_sec); @@ -874,7 +876,7 @@ xfs_iread( if (ip->i_d.di_version == 1) { ip->i_d.di_nlink = ip->i_d.di_onlink; ip->i_d.di_onlink = 0; - ip->i_d.di_projid = 0; + xfs_set_projid(ip, 0); } ip->i_delayed_blks = 0; @@ -982,8 +984,7 @@ xfs_ialloc( mode_t mode, xfs_nlink_t nlink, xfs_dev_t rdev, - cred_t *cr, - xfs_prid_t prid, + prid_t prid, int okalloc, xfs_buf_t **ialloc_context, boolean_t *call_again, @@ -1027,7 +1028,7 @@ xfs_ialloc( ASSERT(ip->i_d.di_nlink == nlink); ip->i_d.di_uid = current_fsuid(); ip->i_d.di_gid = current_fsgid(); - ip->i_d.di_projid = prid; + xfs_set_projid(ip, prid); memset(&(ip->i_d.di_pad[0]), 0, sizeof(ip->i_d.di_pad)); /* @@ -2725,7 +2726,7 @@ cluster_corrupt_out: XFS_BUF_UNDONE(bp); XFS_BUF_STALE(bp); XFS_BUF_ERROR(bp,EIO); - xfs_biodone(bp); + xfs_buf_ioend(bp, 0); } else { XFS_BUF_STALE(bp); xfs_buf_relse(bp); @@ -3008,7 +3009,7 @@ xfs_iflush_int( memset(&(ip->i_d.di_pad[0]), 0, sizeof(ip->i_d.di_pad)); memset(&(dip->di_pad[0]), 0, sizeof(dip->di_pad)); - ASSERT(ip->i_d.di_projid == 0); + ASSERT(xfs_get_projid(ip) == 0); } } diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index 0898c5417d12..fac52290de90 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -134,8 +134,9 @@ typedef struct xfs_icdinode { __uint32_t di_uid; /* owner's user id */ __uint32_t di_gid; /* owner's group id */ __uint32_t di_nlink; /* number of links to file */ - __uint16_t di_projid; /* owner's project id */ - __uint8_t di_pad[8]; /* unused, zeroed space */ + __uint16_t di_projid_lo; /* lower part of owner's project id */ + __uint16_t di_projid_hi; /* higher part of owner's project id */ + __uint8_t di_pad[6]; /* unused, zeroed space */ __uint16_t di_flushiter; /* incremented on flush */ xfs_ictimestamp_t di_atime; /* time last accessed */ xfs_ictimestamp_t di_mtime; /* time last modified */ @@ -212,7 +213,6 @@ typedef struct xfs_icdinode { #ifdef __KERNEL__ struct bhv_desc; -struct cred; struct xfs_buf; struct xfs_bmap_free; struct xfs_bmbt_irec; @@ -335,6 +335,25 @@ xfs_iflags_test_and_clear(xfs_inode_t *ip, unsigned short flags) } /* + * Project quota id helpers (previously projid was 16bit only + * and using two 16bit values to hold new 32bit projid was choosen + * to retain compatibility with "old" filesystems). + */ +static inline prid_t +xfs_get_projid(struct xfs_inode *ip) +{ + return (prid_t)ip->i_d.di_projid_hi << 16 | ip->i_d.di_projid_lo; +} + +static inline void +xfs_set_projid(struct xfs_inode *ip, + prid_t projid) +{ + ip->i_d.di_projid_hi = (__uint16_t) (projid >> 16); + ip->i_d.di_projid_lo = (__uint16_t) (projid & 0xffff); +} + +/* * Manage the i_flush queue embedded in the inode. This completion * queue synchronizes processes attempting to flush the in-core * inode back to disk. @@ -456,8 +475,8 @@ void xfs_inode_free(struct xfs_inode *ip); * xfs_inode.c prototypes. */ int xfs_ialloc(struct xfs_trans *, xfs_inode_t *, mode_t, - xfs_nlink_t, xfs_dev_t, cred_t *, xfs_prid_t, - int, struct xfs_buf **, boolean_t *, xfs_inode_t **); + xfs_nlink_t, xfs_dev_t, prid_t, int, + struct xfs_buf **, boolean_t *, xfs_inode_t **); uint xfs_ip2xflags(struct xfs_inode *); uint xfs_dic2xflags(struct xfs_dinode *); @@ -471,7 +490,6 @@ int xfs_iunlink(struct xfs_trans *, xfs_inode_t *); void xfs_iext_realloc(xfs_inode_t *, int, int); void xfs_iunpin_wait(xfs_inode_t *); int xfs_iflush(xfs_inode_t *, uint); -void xfs_ichgtime(xfs_inode_t *, int); void xfs_lock_inodes(xfs_inode_t **, int, uint); void xfs_lock_two_inodes(xfs_inode_t *, xfs_inode_t *, uint); diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index fe00777e2796..c7ac020705df 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -223,15 +223,6 @@ xfs_inode_item_format( nvecs = 1; /* - * Make sure the linux inode is dirty. We do this before - * clearing i_update_core as the VFS will call back into - * XFS here and set i_update_core, so we need to dirty the - * inode first so that the ordering of i_update_core and - * unlogged modifications still works as described below. - */ - xfs_mark_inode_dirty_sync(ip); - - /* * Clear i_update_core if the timestamps (or any other * non-transactional modification) need flushing/logging * and we're about to log them with the rest of the core. diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c index 7e3626e5925c..dc1882adaf54 100644 --- a/fs/xfs/xfs_itable.c +++ b/fs/xfs/xfs_itable.c @@ -92,7 +92,8 @@ xfs_bulkstat_one_int( * further change. */ buf->bs_nlink = dic->di_nlink; - buf->bs_projid = dic->di_projid; + buf->bs_projid_lo = dic->di_projid_lo; + buf->bs_projid_hi = dic->di_projid_hi; buf->bs_ino = ino; buf->bs_mode = dic->di_mode; buf->bs_uid = dic->di_uid; diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index 33f718f92a48..cee4ab9f8a9e 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -917,19 +917,6 @@ xlog_iodone(xfs_buf_t *bp) l = iclog->ic_log; /* - * If the _XFS_BARRIER_FAILED flag was set by a lower - * layer, it means the underlying device no longer supports - * barrier I/O. Warn loudly and turn off barriers. - */ - if (bp->b_flags & _XFS_BARRIER_FAILED) { - bp->b_flags &= ~_XFS_BARRIER_FAILED; - l->l_mp->m_flags &= ~XFS_MOUNT_BARRIER; - xfs_fs_cmn_err(CE_WARN, l->l_mp, - "xlog_iodone: Barriers are no longer supported" - " by device. Disabling barriers\n"); - } - - /* * Race to shutdown the filesystem if we see an error. */ if (XFS_TEST_ERROR((XFS_BUF_GETERROR(bp)), l->l_mp, @@ -1131,7 +1118,8 @@ xlog_alloc_log(xfs_mount_t *mp, iclog->ic_prev = prev_iclog; prev_iclog = iclog; - bp = xfs_buf_get_noaddr(log->l_iclog_size, mp->m_logdev_targp); + bp = xfs_buf_get_uncached(mp->m_logdev_targp, + log->l_iclog_size, 0); if (!bp) goto out_free_iclog; if (!XFS_BUF_CPSEMA(bp)) @@ -1309,7 +1297,7 @@ xlog_bdstrat( if (iclog->ic_state & XLOG_STATE_IOERROR) { XFS_BUF_ERROR(bp, EIO); XFS_BUF_STALE(bp); - xfs_biodone(bp); + xfs_buf_ioend(bp, 0); /* * It would seem logical to return EIO here, but we rely on * the log state machine to propagate I/O errors instead of diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c index 7e206fc1fa36..23d6ceb5e97b 100644 --- a/fs/xfs/xfs_log_cil.c +++ b/fs/xfs/xfs_log_cil.c @@ -146,102 +146,6 @@ xlog_cil_init_post_recovery( } /* - * Insert the log item into the CIL and calculate the difference in space - * consumed by the item. Add the space to the checkpoint ticket and calculate - * if the change requires additional log metadata. If it does, take that space - * as well. Remove the amount of space we addded to the checkpoint ticket from - * the current transaction ticket so that the accounting works out correctly. - * - * If this is the first time the item is being placed into the CIL in this - * context, pin it so it can't be written to disk until the CIL is flushed to - * the iclog and the iclog written to disk. - */ -static void -xlog_cil_insert( - struct log *log, - struct xlog_ticket *ticket, - struct xfs_log_item *item, - struct xfs_log_vec *lv) -{ - struct xfs_cil *cil = log->l_cilp; - struct xfs_log_vec *old = lv->lv_item->li_lv; - struct xfs_cil_ctx *ctx = cil->xc_ctx; - int len; - int diff_iovecs; - int iclog_space; - - if (old) { - /* existing lv on log item, space used is a delta */ - ASSERT(!list_empty(&item->li_cil)); - ASSERT(old->lv_buf && old->lv_buf_len && old->lv_niovecs); - - len = lv->lv_buf_len - old->lv_buf_len; - diff_iovecs = lv->lv_niovecs - old->lv_niovecs; - kmem_free(old->lv_buf); - kmem_free(old); - } else { - /* new lv, must pin the log item */ - ASSERT(!lv->lv_item->li_lv); - ASSERT(list_empty(&item->li_cil)); - - len = lv->lv_buf_len; - diff_iovecs = lv->lv_niovecs; - IOP_PIN(lv->lv_item); - - } - len += diff_iovecs * sizeof(xlog_op_header_t); - - /* attach new log vector to log item */ - lv->lv_item->li_lv = lv; - - spin_lock(&cil->xc_cil_lock); - list_move_tail(&item->li_cil, &cil->xc_cil); - ctx->nvecs += diff_iovecs; - - /* - * If this is the first time the item is being committed to the CIL, - * store the sequence number on the log item so we can tell - * in future commits whether this is the first checkpoint the item is - * being committed into. - */ - if (!item->li_seq) - item->li_seq = ctx->sequence; - - /* - * Now transfer enough transaction reservation to the context ticket - * for the checkpoint. The context ticket is special - the unit - * reservation has to grow as well as the current reservation as we - * steal from tickets so we can correctly determine the space used - * during the transaction commit. - */ - if (ctx->ticket->t_curr_res == 0) { - /* first commit in checkpoint, steal the header reservation */ - ASSERT(ticket->t_curr_res >= ctx->ticket->t_unit_res + len); - ctx->ticket->t_curr_res = ctx->ticket->t_unit_res; - ticket->t_curr_res -= ctx->ticket->t_unit_res; - } - - /* do we need space for more log record headers? */ - iclog_space = log->l_iclog_size - log->l_iclog_hsize; - if (len > 0 && (ctx->space_used / iclog_space != - (ctx->space_used + len) / iclog_space)) { - int hdrs; - - hdrs = (len + iclog_space - 1) / iclog_space; - /* need to take into account split region headers, too */ - hdrs *= log->l_iclog_hsize + sizeof(struct xlog_op_header); - ctx->ticket->t_unit_res += hdrs; - ctx->ticket->t_curr_res += hdrs; - ticket->t_curr_res -= hdrs; - ASSERT(ticket->t_curr_res >= len); - } - ticket->t_curr_res -= len; - ctx->space_used += len; - - spin_unlock(&cil->xc_cil_lock); -} - -/* * Format log item into a flat buffers * * For delayed logging, we need to hold a formatted buffer containing all the @@ -286,7 +190,7 @@ xlog_cil_format_items( len += lv->lv_iovecp[index].i_len; lv->lv_buf_len = len; - lv->lv_buf = kmem_zalloc(lv->lv_buf_len, KM_SLEEP|KM_NOFS); + lv->lv_buf = kmem_alloc(lv->lv_buf_len, KM_SLEEP|KM_NOFS); ptr = lv->lv_buf; for (index = 0; index < lv->lv_niovecs; index++) { @@ -300,21 +204,136 @@ xlog_cil_format_items( } } +/* + * Prepare the log item for insertion into the CIL. Calculate the difference in + * log space and vectors it will consume, and if it is a new item pin it as + * well. + */ +STATIC void +xfs_cil_prepare_item( + struct log *log, + struct xfs_log_vec *lv, + int *len, + int *diff_iovecs) +{ + struct xfs_log_vec *old = lv->lv_item->li_lv; + + if (old) { + /* existing lv on log item, space used is a delta */ + ASSERT(!list_empty(&lv->lv_item->li_cil)); + ASSERT(old->lv_buf && old->lv_buf_len && old->lv_niovecs); + + *len += lv->lv_buf_len - old->lv_buf_len; + *diff_iovecs += lv->lv_niovecs - old->lv_niovecs; + kmem_free(old->lv_buf); + kmem_free(old); + } else { + /* new lv, must pin the log item */ + ASSERT(!lv->lv_item->li_lv); + ASSERT(list_empty(&lv->lv_item->li_cil)); + + *len += lv->lv_buf_len; + *diff_iovecs += lv->lv_niovecs; + IOP_PIN(lv->lv_item); + + } + + /* attach new log vector to log item */ + lv->lv_item->li_lv = lv; + + /* + * If this is the first time the item is being committed to the + * CIL, store the sequence number on the log item so we can + * tell in future commits whether this is the first checkpoint + * the item is being committed into. + */ + if (!lv->lv_item->li_seq) + lv->lv_item->li_seq = log->l_cilp->xc_ctx->sequence; +} + +/* + * Insert the log items into the CIL and calculate the difference in space + * consumed by the item. Add the space to the checkpoint ticket and calculate + * if the change requires additional log metadata. If it does, take that space + * as well. Remove the amount of space we addded to the checkpoint ticket from + * the current transaction ticket so that the accounting works out correctly. + */ static void xlog_cil_insert_items( struct log *log, struct xfs_log_vec *log_vector, - struct xlog_ticket *ticket, - xfs_lsn_t *start_lsn) + struct xlog_ticket *ticket) { - struct xfs_log_vec *lv; - - if (start_lsn) - *start_lsn = log->l_cilp->xc_ctx->sequence; + struct xfs_cil *cil = log->l_cilp; + struct xfs_cil_ctx *ctx = cil->xc_ctx; + struct xfs_log_vec *lv; + int len = 0; + int diff_iovecs = 0; + int iclog_space; ASSERT(log_vector); + + /* + * Do all the accounting aggregation and switching of log vectors + * around in a separate loop to the insertion of items into the CIL. + * Then we can do a separate loop to update the CIL within a single + * lock/unlock pair. This reduces the number of round trips on the CIL + * lock from O(nr_logvectors) to O(1) and greatly reduces the overall + * hold time for the transaction commit. + * + * If this is the first time the item is being placed into the CIL in + * this context, pin it so it can't be written to disk until the CIL is + * flushed to the iclog and the iclog written to disk. + * + * We can do this safely because the context can't checkpoint until we + * are done so it doesn't matter exactly how we update the CIL. + */ + for (lv = log_vector; lv; lv = lv->lv_next) + xfs_cil_prepare_item(log, lv, &len, &diff_iovecs); + + /* account for space used by new iovec headers */ + len += diff_iovecs * sizeof(xlog_op_header_t); + + spin_lock(&cil->xc_cil_lock); + + /* move the items to the tail of the CIL */ for (lv = log_vector; lv; lv = lv->lv_next) - xlog_cil_insert(log, ticket, lv->lv_item, lv); + list_move_tail(&lv->lv_item->li_cil, &cil->xc_cil); + + ctx->nvecs += diff_iovecs; + + /* + * Now transfer enough transaction reservation to the context ticket + * for the checkpoint. The context ticket is special - the unit + * reservation has to grow as well as the current reservation as we + * steal from tickets so we can correctly determine the space used + * during the transaction commit. + */ + if (ctx->ticket->t_curr_res == 0) { + /* first commit in checkpoint, steal the header reservation */ + ASSERT(ticket->t_curr_res >= ctx->ticket->t_unit_res + len); + ctx->ticket->t_curr_res = ctx->ticket->t_unit_res; + ticket->t_curr_res -= ctx->ticket->t_unit_res; + } + + /* do we need space for more log record headers? */ + iclog_space = log->l_iclog_size - log->l_iclog_hsize; + if (len > 0 && (ctx->space_used / iclog_space != + (ctx->space_used + len) / iclog_space)) { + int hdrs; + + hdrs = (len + iclog_space - 1) / iclog_space; + /* need to take into account split region headers, too */ + hdrs *= log->l_iclog_hsize + sizeof(struct xlog_op_header); + ctx->ticket->t_unit_res += hdrs; + ctx->ticket->t_curr_res += hdrs; + ticket->t_curr_res -= hdrs; + ASSERT(ticket->t_curr_res >= len); + } + ticket->t_curr_res -= len; + ctx->space_used += len; + + spin_unlock(&cil->xc_cil_lock); } static void @@ -638,7 +657,10 @@ xfs_log_commit_cil( /* lock out background commit */ down_read(&log->l_cilp->xc_ctx_lock); - xlog_cil_insert_items(log, log_vector, tp->t_ticket, commit_lsn); + if (commit_lsn) + *commit_lsn = log->l_cilp->xc_ctx->sequence; + + xlog_cil_insert_items(log, log_vector, tp->t_ticket); /* check we didn't blow the reservation */ if (tp->t_ticket->t_curr_res < 0) diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index 6f3f5fa37acf..966d3f97458c 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -107,7 +107,8 @@ xlog_get_bp( nbblks += log->l_sectBBsize; nbblks = round_up(nbblks, log->l_sectBBsize); - return xfs_buf_get_noaddr(BBTOB(nbblks), log->l_mp->m_logdev_targp); + return xfs_buf_get_uncached(log->l_mp->m_logdev_targp, + BBTOB(nbblks), 0); } STATIC void @@ -167,7 +168,7 @@ xlog_bread_noalign( XFS_BUF_SET_TARGET(bp, log->l_mp->m_logdev_targp); xfsbdstrat(log->l_mp, bp); - error = xfs_iowait(bp); + error = xfs_buf_iowait(bp); if (error) xfs_ioerror_alert("xlog_bread", log->l_mp, bp, XFS_BUF_ADDR(bp)); @@ -321,12 +322,13 @@ xlog_recover_iodone( * this during recovery. One strike! */ xfs_ioerror_alert("xlog_recover_iodone", - bp->b_mount, bp, XFS_BUF_ADDR(bp)); - xfs_force_shutdown(bp->b_mount, SHUTDOWN_META_IO_ERROR); + bp->b_target->bt_mount, bp, + XFS_BUF_ADDR(bp)); + xfs_force_shutdown(bp->b_target->bt_mount, + SHUTDOWN_META_IO_ERROR); } - bp->b_mount = NULL; XFS_BUF_CLR_IODONE_FUNC(bp); - xfs_biodone(bp); + xfs_buf_ioend(bp, 0); } /* @@ -2275,8 +2277,7 @@ xlog_recover_do_buffer_trans( XFS_BUF_STALE(bp); error = xfs_bwrite(mp, bp); } else { - ASSERT(bp->b_mount == NULL || bp->b_mount == mp); - bp->b_mount = mp; + ASSERT(bp->b_target->bt_mount == mp); XFS_BUF_SET_IODONE_FUNC(bp, xlog_recover_iodone); xfs_bdwrite(mp, bp); } @@ -2540,8 +2541,7 @@ xlog_recover_do_inode_trans( } write_inode_buffer: - ASSERT(bp->b_mount == NULL || bp->b_mount == mp); - bp->b_mount = mp; + ASSERT(bp->b_target->bt_mount == mp); XFS_BUF_SET_IODONE_FUNC(bp, xlog_recover_iodone); xfs_bdwrite(mp, bp); error: @@ -2678,8 +2678,7 @@ xlog_recover_do_dquot_trans( memcpy(ddq, recddq, item->ri_buf[1].i_len); ASSERT(dq_f->qlf_size == 2); - ASSERT(bp->b_mount == NULL || bp->b_mount == mp); - bp->b_mount = mp; + ASSERT(bp->b_target->bt_mount == mp); XFS_BUF_SET_IODONE_FUNC(bp, xlog_recover_iodone); xfs_bdwrite(mp, bp); @@ -3817,7 +3816,7 @@ xlog_do_recover( XFS_BUF_READ(bp); XFS_BUF_UNASYNC(bp); xfsbdstrat(log->l_mp, bp); - error = xfs_iowait(bp); + error = xfs_buf_iowait(bp); if (error) { xfs_ioerror_alert("xlog_do_recover", log->l_mp, bp, XFS_BUF_ADDR(bp)); diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index aeb9d72ebf6e..b1498ab5a399 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -52,16 +52,11 @@ STATIC void xfs_icsb_balance_counter(xfs_mount_t *, xfs_sb_field_t, int); STATIC void xfs_icsb_balance_counter_locked(xfs_mount_t *, xfs_sb_field_t, int); -STATIC int xfs_icsb_modify_counters(xfs_mount_t *, xfs_sb_field_t, - int64_t, int); STATIC void xfs_icsb_disable_counter(xfs_mount_t *, xfs_sb_field_t); - #else #define xfs_icsb_balance_counter(mp, a, b) do { } while (0) #define xfs_icsb_balance_counter_locked(mp, a, b) do { } while (0) -#define xfs_icsb_modify_counters(mp, a, b, c) do { } while (0) - #endif static const struct { @@ -199,6 +194,8 @@ xfs_uuid_unmount( /* * Reference counting access wrappers to the perag structures. + * Because we never free per-ag structures, the only thing we + * have to protect against changes is the tree structure itself. */ struct xfs_perag * xfs_perag_get(struct xfs_mount *mp, xfs_agnumber_t agno) @@ -206,19 +203,43 @@ xfs_perag_get(struct xfs_mount *mp, xfs_agnumber_t agno) struct xfs_perag *pag; int ref = 0; - spin_lock(&mp->m_perag_lock); + rcu_read_lock(); pag = radix_tree_lookup(&mp->m_perag_tree, agno); if (pag) { ASSERT(atomic_read(&pag->pag_ref) >= 0); - /* catch leaks in the positive direction during testing */ - ASSERT(atomic_read(&pag->pag_ref) < 1000); ref = atomic_inc_return(&pag->pag_ref); } - spin_unlock(&mp->m_perag_lock); + rcu_read_unlock(); trace_xfs_perag_get(mp, agno, ref, _RET_IP_); return pag; } +/* + * search from @first to find the next perag with the given tag set. + */ +struct xfs_perag * +xfs_perag_get_tag( + struct xfs_mount *mp, + xfs_agnumber_t first, + int tag) +{ + struct xfs_perag *pag; + int found; + int ref; + + rcu_read_lock(); + found = radix_tree_gang_lookup_tag(&mp->m_perag_tree, + (void **)&pag, first, 1, tag); + if (found <= 0) { + rcu_read_unlock(); + return NULL; + } + ref = atomic_inc_return(&pag->pag_ref); + rcu_read_unlock(); + trace_xfs_perag_get_tag(mp, pag->pag_agno, ref, _RET_IP_); + return pag; +} + void xfs_perag_put(struct xfs_perag *pag) { @@ -229,10 +250,18 @@ xfs_perag_put(struct xfs_perag *pag) trace_xfs_perag_put(pag->pag_mount, pag->pag_agno, ref, _RET_IP_); } +STATIC void +__xfs_free_perag( + struct rcu_head *head) +{ + struct xfs_perag *pag = container_of(head, struct xfs_perag, rcu_head); + + ASSERT(atomic_read(&pag->pag_ref) == 0); + kmem_free(pag); +} + /* - * Free up the resources associated with a mount structure. Assume that - * the structure was initially zeroed, so we can tell which fields got - * initialized. + * Free up the per-ag resources associated with the mount structure. */ STATIC void xfs_free_perag( @@ -244,10 +273,9 @@ xfs_free_perag( for (agno = 0; agno < mp->m_sb.sb_agcount; agno++) { spin_lock(&mp->m_perag_lock); pag = radix_tree_delete(&mp->m_perag_tree, agno); - ASSERT(pag); - ASSERT(atomic_read(&pag->pag_ref) == 0); spin_unlock(&mp->m_perag_lock); - kmem_free(pag); + ASSERT(pag); + call_rcu(&pag->rcu_head, __xfs_free_perag); } } @@ -444,7 +472,10 @@ xfs_initialize_perag( pag->pag_agno = index; pag->pag_mount = mp; rwlock_init(&pag->pag_ici_lock); + mutex_init(&pag->pag_ici_reclaim_lock); INIT_RADIX_TREE(&pag->pag_ici_root, GFP_ATOMIC); + spin_lock_init(&pag->pag_buf_lock); + pag->pag_buf_tree = RB_ROOT; if (radix_tree_preload(GFP_NOFS)) goto out_unwind; @@ -639,7 +670,6 @@ int xfs_readsb(xfs_mount_t *mp, int flags) { unsigned int sector_size; - unsigned int extra_flags; xfs_buf_t *bp; int error; @@ -652,28 +682,24 @@ xfs_readsb(xfs_mount_t *mp, int flags) * access to the superblock. */ sector_size = xfs_getsize_buftarg(mp->m_ddev_targp); - extra_flags = XBF_LOCK | XBF_FS_MANAGED | XBF_MAPPED; - bp = xfs_buf_read(mp->m_ddev_targp, XFS_SB_DADDR, BTOBB(sector_size), - extra_flags); - if (!bp || XFS_BUF_ISERROR(bp)) { - xfs_fs_mount_cmn_err(flags, "SB read failed"); - error = bp ? XFS_BUF_GETERROR(bp) : ENOMEM; - goto fail; +reread: + bp = xfs_buf_read_uncached(mp, mp->m_ddev_targp, + XFS_SB_DADDR, sector_size, 0); + if (!bp) { + xfs_fs_mount_cmn_err(flags, "SB buffer read failed"); + return EIO; } - ASSERT(XFS_BUF_ISBUSY(bp)); - ASSERT(XFS_BUF_VALUSEMA(bp) <= 0); /* * Initialize the mount structure from the superblock. * But first do some basic consistency checking. */ xfs_sb_from_disk(&mp->m_sb, XFS_BUF_TO_SBP(bp)); - error = xfs_mount_validate_sb(mp, &(mp->m_sb), flags); if (error) { xfs_fs_mount_cmn_err(flags, "SB validate failed"); - goto fail; + goto release_buf; } /* @@ -684,7 +710,7 @@ xfs_readsb(xfs_mount_t *mp, int flags) "device supports only %u byte sectors (not %u)", sector_size, mp->m_sb.sb_sectsize); error = ENOSYS; - goto fail; + goto release_buf; } /* @@ -692,33 +718,20 @@ xfs_readsb(xfs_mount_t *mp, int flags) * re-read the superblock so the buffer is correctly sized. */ if (sector_size < mp->m_sb.sb_sectsize) { - XFS_BUF_UNMANAGE(bp); xfs_buf_relse(bp); sector_size = mp->m_sb.sb_sectsize; - bp = xfs_buf_read(mp->m_ddev_targp, XFS_SB_DADDR, - BTOBB(sector_size), extra_flags); - if (!bp || XFS_BUF_ISERROR(bp)) { - xfs_fs_mount_cmn_err(flags, "SB re-read failed"); - error = bp ? XFS_BUF_GETERROR(bp) : ENOMEM; - goto fail; - } - ASSERT(XFS_BUF_ISBUSY(bp)); - ASSERT(XFS_BUF_VALUSEMA(bp) <= 0); + goto reread; } /* Initialize per-cpu counters */ xfs_icsb_reinit_counters(mp); mp->m_sb_bp = bp; - xfs_buf_relse(bp); - ASSERT(XFS_BUF_VALUSEMA(bp) > 0); + xfs_buf_unlock(bp); return 0; - fail: - if (bp) { - XFS_BUF_UNMANAGE(bp); - xfs_buf_relse(bp); - } +release_buf: + xfs_buf_relse(bp); return error; } @@ -991,42 +1004,35 @@ xfs_check_sizes(xfs_mount_t *mp) { xfs_buf_t *bp; xfs_daddr_t d; - int error; d = (xfs_daddr_t)XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks); if (XFS_BB_TO_FSB(mp, d) != mp->m_sb.sb_dblocks) { - cmn_err(CE_WARN, "XFS: size check 1 failed"); + cmn_err(CE_WARN, "XFS: filesystem size mismatch detected"); return XFS_ERROR(EFBIG); } - error = xfs_read_buf(mp, mp->m_ddev_targp, - d - XFS_FSS_TO_BB(mp, 1), - XFS_FSS_TO_BB(mp, 1), 0, &bp); - if (!error) { - xfs_buf_relse(bp); - } else { - cmn_err(CE_WARN, "XFS: size check 2 failed"); - if (error == ENOSPC) - error = XFS_ERROR(EFBIG); - return error; + bp = xfs_buf_read_uncached(mp, mp->m_ddev_targp, + d - XFS_FSS_TO_BB(mp, 1), + BBTOB(XFS_FSS_TO_BB(mp, 1)), 0); + if (!bp) { + cmn_err(CE_WARN, "XFS: last sector read failed"); + return EIO; } + xfs_buf_relse(bp); if (mp->m_logdev_targp != mp->m_ddev_targp) { d = (xfs_daddr_t)XFS_FSB_TO_BB(mp, mp->m_sb.sb_logblocks); if (XFS_BB_TO_FSB(mp, d) != mp->m_sb.sb_logblocks) { - cmn_err(CE_WARN, "XFS: size check 3 failed"); + cmn_err(CE_WARN, "XFS: log size mismatch detected"); return XFS_ERROR(EFBIG); } - error = xfs_read_buf(mp, mp->m_logdev_targp, - d - XFS_FSB_TO_BB(mp, 1), - XFS_FSB_TO_BB(mp, 1), 0, &bp); - if (!error) { - xfs_buf_relse(bp); - } else { - cmn_err(CE_WARN, "XFS: size check 3 failed"); - if (error == ENOSPC) - error = XFS_ERROR(EFBIG); - return error; + bp = xfs_buf_read_uncached(mp, mp->m_logdev_targp, + d - XFS_FSB_TO_BB(mp, 1), + XFS_FSB_TO_B(mp, 1), 0); + if (!bp) { + cmn_err(CE_WARN, "XFS: log device read failed"); + return EIO; } + xfs_buf_relse(bp); } return 0; } @@ -1601,7 +1607,7 @@ xfs_unmountfs_writesb(xfs_mount_t *mp) XFS_BUF_UNASYNC(sbp); ASSERT(XFS_BUF_TARGET(sbp) == mp->m_ddev_targp); xfsbdstrat(mp, sbp); - error = xfs_iowait(sbp); + error = xfs_buf_iowait(sbp); if (error) xfs_ioerror_alert("xfs_unmountfs_writesb", mp, sbp, XFS_BUF_ADDR(sbp)); @@ -1832,135 +1838,72 @@ xfs_mod_incore_sb_unlocked( */ int xfs_mod_incore_sb( - xfs_mount_t *mp, - xfs_sb_field_t field, - int64_t delta, - int rsvd) + struct xfs_mount *mp, + xfs_sb_field_t field, + int64_t delta, + int rsvd) { - int status; + int status; - /* check for per-cpu counters */ - switch (field) { #ifdef HAVE_PERCPU_SB - case XFS_SBS_ICOUNT: - case XFS_SBS_IFREE: - case XFS_SBS_FDBLOCKS: - if (!(mp->m_flags & XFS_MOUNT_NO_PERCPU_SB)) { - status = xfs_icsb_modify_counters(mp, field, - delta, rsvd); - break; - } - /* FALLTHROUGH */ + ASSERT(field < XFS_SBS_ICOUNT || field > XFS_SBS_FDBLOCKS); #endif - default: - spin_lock(&mp->m_sb_lock); - status = xfs_mod_incore_sb_unlocked(mp, field, delta, rsvd); - spin_unlock(&mp->m_sb_lock); - break; - } + spin_lock(&mp->m_sb_lock); + status = xfs_mod_incore_sb_unlocked(mp, field, delta, rsvd); + spin_unlock(&mp->m_sb_lock); return status; } /* - * xfs_mod_incore_sb_batch() is used to change more than one field - * in the in-core superblock structure at a time. This modification - * is protected by a lock internal to this module. The fields and - * changes to those fields are specified in the array of xfs_mod_sb - * structures passed in. + * Change more than one field in the in-core superblock structure at a time. * - * Either all of the specified deltas will be applied or none of - * them will. If any modified field dips below 0, then all modifications - * will be backed out and EINVAL will be returned. + * The fields and changes to those fields are specified in the array of + * xfs_mod_sb structures passed in. Either all of the specified deltas + * will be applied or none of them will. If any modified field dips below 0, + * then all modifications will be backed out and EINVAL will be returned. + * + * Note that this function may not be used for the superblock values that + * are tracked with the in-memory per-cpu counters - a direct call to + * xfs_icsb_modify_counters is required for these. */ int -xfs_mod_incore_sb_batch(xfs_mount_t *mp, xfs_mod_sb_t *msb, uint nmsb, int rsvd) +xfs_mod_incore_sb_batch( + struct xfs_mount *mp, + xfs_mod_sb_t *msb, + uint nmsb, + int rsvd) { - int status=0; - xfs_mod_sb_t *msbp; + xfs_mod_sb_t *msbp = &msb[0]; + int error = 0; /* - * Loop through the array of mod structures and apply each - * individually. If any fail, then back out all those - * which have already been applied. Do all of this within - * the scope of the m_sb_lock so that all of the changes will - * be atomic. + * Loop through the array of mod structures and apply each individually. + * If any fail, then back out all those which have already been applied. + * Do all of this within the scope of the m_sb_lock so that all of the + * changes will be atomic. */ spin_lock(&mp->m_sb_lock); - msbp = &msb[0]; for (msbp = &msbp[0]; msbp < (msb + nmsb); msbp++) { - /* - * Apply the delta at index n. If it fails, break - * from the loop so we'll fall into the undo loop - * below. - */ - switch (msbp->msb_field) { -#ifdef HAVE_PERCPU_SB - case XFS_SBS_ICOUNT: - case XFS_SBS_IFREE: - case XFS_SBS_FDBLOCKS: - if (!(mp->m_flags & XFS_MOUNT_NO_PERCPU_SB)) { - spin_unlock(&mp->m_sb_lock); - status = xfs_icsb_modify_counters(mp, - msbp->msb_field, - msbp->msb_delta, rsvd); - spin_lock(&mp->m_sb_lock); - break; - } - /* FALLTHROUGH */ -#endif - default: - status = xfs_mod_incore_sb_unlocked(mp, - msbp->msb_field, - msbp->msb_delta, rsvd); - break; - } + ASSERT(msbp->msb_field < XFS_SBS_ICOUNT || + msbp->msb_field > XFS_SBS_FDBLOCKS); - if (status != 0) { - break; - } + error = xfs_mod_incore_sb_unlocked(mp, msbp->msb_field, + msbp->msb_delta, rsvd); + if (error) + goto unwind; } + spin_unlock(&mp->m_sb_lock); + return 0; - /* - * If we didn't complete the loop above, then back out - * any changes made to the superblock. If you add code - * between the loop above and here, make sure that you - * preserve the value of status. Loop back until - * we step below the beginning of the array. Make sure - * we don't touch anything back there. - */ - if (status != 0) { - msbp--; - while (msbp >= msb) { - switch (msbp->msb_field) { -#ifdef HAVE_PERCPU_SB - case XFS_SBS_ICOUNT: - case XFS_SBS_IFREE: - case XFS_SBS_FDBLOCKS: - if (!(mp->m_flags & XFS_MOUNT_NO_PERCPU_SB)) { - spin_unlock(&mp->m_sb_lock); - status = xfs_icsb_modify_counters(mp, - msbp->msb_field, - -(msbp->msb_delta), - rsvd); - spin_lock(&mp->m_sb_lock); - break; - } - /* FALLTHROUGH */ -#endif - default: - status = xfs_mod_incore_sb_unlocked(mp, - msbp->msb_field, - -(msbp->msb_delta), - rsvd); - break; - } - ASSERT(status == 0); - msbp--; - } +unwind: + while (--msbp >= msb) { + error = xfs_mod_incore_sb_unlocked(mp, msbp->msb_field, + -msbp->msb_delta, rsvd); + ASSERT(error == 0); } spin_unlock(&mp->m_sb_lock); - return status; + return error; } /* @@ -1998,18 +1941,13 @@ xfs_getsb( */ void xfs_freesb( - xfs_mount_t *mp) + struct xfs_mount *mp) { - xfs_buf_t *bp; + struct xfs_buf *bp = mp->m_sb_bp; - /* - * Use xfs_getsb() so that the buffer will be locked - * when we call xfs_buf_relse(). - */ - bp = xfs_getsb(mp, 0); - XFS_BUF_UNMANAGE(bp); - xfs_buf_relse(bp); + xfs_buf_lock(bp); mp->m_sb_bp = NULL; + xfs_buf_relse(bp); } /* @@ -2496,7 +2434,7 @@ xfs_icsb_balance_counter( spin_unlock(&mp->m_sb_lock); } -STATIC int +int xfs_icsb_modify_counters( xfs_mount_t *mp, xfs_sb_field_t field, diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index 622da2179a57..5861b4980740 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -53,7 +53,6 @@ typedef struct xfs_trans_reservations { #include "xfs_sync.h" -struct cred; struct log; struct xfs_mount_args; struct xfs_inode; @@ -91,6 +90,8 @@ extern void xfs_icsb_reinit_counters(struct xfs_mount *); extern void xfs_icsb_destroy_counters(struct xfs_mount *); extern void xfs_icsb_sync_counters(struct xfs_mount *, int); extern void xfs_icsb_sync_counters_locked(struct xfs_mount *, int); +extern int xfs_icsb_modify_counters(struct xfs_mount *, xfs_sb_field_t, + int64_t, int); #else #define xfs_icsb_init_counters(mp) (0) @@ -98,6 +99,8 @@ extern void xfs_icsb_sync_counters_locked(struct xfs_mount *, int); #define xfs_icsb_reinit_counters(mp) do { } while (0) #define xfs_icsb_sync_counters(mp, flags) do { } while (0) #define xfs_icsb_sync_counters_locked(mp, flags) do { } while (0) +#define xfs_icsb_modify_counters(mp, field, delta, rsvd) \ + xfs_mod_incore_sb(mp, field, delta, rsvd) #endif typedef struct xfs_mount { @@ -232,8 +235,6 @@ typedef struct xfs_mount { #define XFS_MOUNT_DIRSYNC (1ULL << 21) /* synchronous directory ops */ #define XFS_MOUNT_COMPAT_IOSIZE (1ULL << 22) /* don't report large preferred * I/O size in stat() */ -#define XFS_MOUNT_NO_PERCPU_SB (1ULL << 23) /* don't use per-cpu superblock - counters */ #define XFS_MOUNT_FILESTREAMS (1ULL << 24) /* enable the filestreams allocator */ #define XFS_MOUNT_NOATTR2 (1ULL << 25) /* disable use of attr2 format */ @@ -327,6 +328,8 @@ xfs_daddr_to_agbno(struct xfs_mount *mp, xfs_daddr_t d) * perag get/put wrappers for ref counting */ struct xfs_perag *xfs_perag_get(struct xfs_mount *mp, xfs_agnumber_t agno); +struct xfs_perag *xfs_perag_get_tag(struct xfs_mount *mp, xfs_agnumber_t agno, + int tag); void xfs_perag_put(struct xfs_perag *pag); /* diff --git a/fs/xfs/xfs_refcache.h b/fs/xfs/xfs_refcache.h deleted file mode 100644 index 2dec79edb510..000000000000 --- a/fs/xfs/xfs_refcache.h +++ /dev/null @@ -1,52 +0,0 @@ -/* - * Copyright (c) 2000-2003,2005 Silicon Graphics, Inc. - * All Rights Reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it would be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write the Free Software Foundation, - * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - */ -#ifndef __XFS_REFCACHE_H__ -#define __XFS_REFCACHE_H__ - -#ifdef HAVE_REFCACHE -/* - * Maximum size (in inodes) for the NFS reference cache - */ -#define XFS_REFCACHE_SIZE_MAX 512 - -struct xfs_inode; -struct xfs_mount; - -extern void xfs_refcache_insert(struct xfs_inode *); -extern void xfs_refcache_purge_ip(struct xfs_inode *); -extern void xfs_refcache_purge_mp(struct xfs_mount *); -extern void xfs_refcache_purge_some(struct xfs_mount *); -extern void xfs_refcache_resize(int); -extern void xfs_refcache_destroy(void); - -extern void xfs_refcache_iunlock(struct xfs_inode *, uint); - -#else - -#define xfs_refcache_insert(ip) do { } while (0) -#define xfs_refcache_purge_ip(ip) do { } while (0) -#define xfs_refcache_purge_mp(mp) do { } while (0) -#define xfs_refcache_purge_some(mp) do { } while (0) -#define xfs_refcache_resize(size) do { } while (0) -#define xfs_refcache_destroy() do { } while (0) - -#define xfs_refcache_iunlock(ip, flags) xfs_iunlock(ip, flags) - -#endif - -#endif /* __XFS_REFCACHE_H__ */ diff --git a/fs/xfs/xfs_rename.c b/fs/xfs/xfs_rename.c index 8fca957200df..d2af0a8381a6 100644 --- a/fs/xfs/xfs_rename.c +++ b/fs/xfs/xfs_rename.c @@ -183,7 +183,7 @@ xfs_rename( * tree quota mechanism would be circumvented. */ if (unlikely((target_dp->i_d.di_flags & XFS_DIFLAG_PROJINHERIT) && - (target_dp->i_d.di_projid != src_ip->i_d.di_projid))) { + (xfs_get_projid(target_dp) != xfs_get_projid(src_ip)))) { error = XFS_ERROR(EXDEV); goto error_return; } @@ -211,7 +211,9 @@ xfs_rename( goto error_return; if (error) goto abort_return; - xfs_ichgtime(target_dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); + + xfs_trans_ichgtime(tp, target_dp, + XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); if (new_parent && src_is_directory) { error = xfs_bumplink(tp, target_dp); @@ -249,7 +251,9 @@ xfs_rename( &first_block, &free_list, spaceres); if (error) goto abort_return; - xfs_ichgtime(target_dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); + + xfs_trans_ichgtime(tp, target_dp, + XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); /* * Decrement the link count on the target since the target @@ -292,7 +296,7 @@ xfs_rename( * inode isn't really being changed, but old unix file systems did * it and some incremental backup programs won't work without it. */ - xfs_ichgtime(src_ip, XFS_ICHGTIME_CHG); + xfs_trans_ichgtime(tp, src_ip, XFS_ICHGTIME_CHG); /* * Adjust the link count on src_dp. This is necessary when @@ -315,7 +319,7 @@ xfs_rename( if (error) goto abort_return; - xfs_ichgtime(src_dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); + xfs_trans_ichgtime(tp, src_dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); xfs_trans_log_inode(tp, src_dp, XFS_ILOG_CORE); if (new_parent) xfs_trans_log_inode(tp, target_dp, XFS_ILOG_CORE); diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c index 891260fea11e..12a191385310 100644 --- a/fs/xfs/xfs_rtalloc.c +++ b/fs/xfs/xfs_rtalloc.c @@ -39,6 +39,7 @@ #include "xfs_trans_space.h" #include "xfs_utils.h" #include "xfs_trace.h" +#include "xfs_buf.h" /* @@ -1883,13 +1884,13 @@ xfs_growfs_rt( /* * Read in the last block of the device, make sure it exists. */ - error = xfs_read_buf(mp, mp->m_rtdev_targp, - XFS_FSB_TO_BB(mp, nrblocks - 1), - XFS_FSB_TO_BB(mp, 1), 0, &bp); - if (error) - return error; - ASSERT(bp); + bp = xfs_buf_read_uncached(mp, mp->m_rtdev_targp, + XFS_FSB_TO_BB(mp, nrblocks - 1), + XFS_FSB_TO_B(mp, 1), 0); + if (!bp) + return EIO; xfs_buf_relse(bp); + /* * Calculate new parameters. These are the final values to be reached. */ @@ -2215,7 +2216,6 @@ xfs_rtmount_init( { xfs_buf_t *bp; /* buffer for last block of subvolume */ xfs_daddr_t d; /* address of last block of subvolume */ - int error; /* error return value */ xfs_sb_t *sbp; /* filesystem superblock copy in mount */ sbp = &mp->m_sb; @@ -2242,15 +2242,12 @@ xfs_rtmount_init( (unsigned long long) mp->m_sb.sb_rblocks); return XFS_ERROR(EFBIG); } - error = xfs_read_buf(mp, mp->m_rtdev_targp, - d - XFS_FSB_TO_BB(mp, 1), - XFS_FSB_TO_BB(mp, 1), 0, &bp); - if (error) { - cmn_err(CE_WARN, - "XFS: realtime mount -- xfs_read_buf failed, returned %d", error); - if (error == ENOSPC) - return XFS_ERROR(EFBIG); - return error; + bp = xfs_buf_read_uncached(mp, mp->m_rtdev_targp, + d - XFS_FSB_TO_BB(mp, 1), + XFS_FSB_TO_B(mp, 1), 0); + if (!bp) { + cmn_err(CE_WARN, "XFS: realtime device size check failed"); + return EIO; } xfs_buf_relse(bp); return 0; diff --git a/fs/xfs/xfs_sb.h b/fs/xfs/xfs_sb.h index 1b017c657494..1eb2ba586814 100644 --- a/fs/xfs/xfs_sb.h +++ b/fs/xfs/xfs_sb.h @@ -80,10 +80,12 @@ struct xfs_mount; #define XFS_SB_VERSION2_RESERVED4BIT 0x00000004 #define XFS_SB_VERSION2_ATTR2BIT 0x00000008 /* Inline attr rework */ #define XFS_SB_VERSION2_PARENTBIT 0x00000010 /* parent pointers */ +#define XFS_SB_VERSION2_PROJID32BIT 0x00000080 /* 32 bit project id */ #define XFS_SB_VERSION2_OKREALFBITS \ (XFS_SB_VERSION2_LAZYSBCOUNTBIT | \ - XFS_SB_VERSION2_ATTR2BIT) + XFS_SB_VERSION2_ATTR2BIT | \ + XFS_SB_VERSION2_PROJID32BIT) #define XFS_SB_VERSION2_OKSASHFBITS \ (0) #define XFS_SB_VERSION2_OKREALBITS \ @@ -495,6 +497,12 @@ static inline void xfs_sb_version_removeattr2(xfs_sb_t *sbp) sbp->sb_versionnum &= ~XFS_SB_VERSION_MOREBITSBIT; } +static inline int xfs_sb_version_hasprojid32bit(xfs_sb_t *sbp) +{ + return xfs_sb_version_hasmorebits(sbp) && + (sbp->sb_features2 & XFS_SB_VERSION2_PROJID32BIT); +} + /* * end of superblock version macros */ diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c index 1c47edaea0d2..f6d956b7711e 100644 --- a/fs/xfs/xfs_trans.c +++ b/fs/xfs/xfs_trans.c @@ -696,7 +696,7 @@ xfs_trans_reserve( * fail if the count would go below zero. */ if (blocks > 0) { - error = xfs_mod_incore_sb(tp->t_mountp, XFS_SBS_FDBLOCKS, + error = xfs_icsb_modify_counters(tp->t_mountp, XFS_SBS_FDBLOCKS, -((int64_t)blocks), rsvd); if (error != 0) { current_restore_flags_nested(&tp->t_pflags, PF_FSTRANS); @@ -767,7 +767,7 @@ undo_log: undo_blocks: if (blocks > 0) { - (void) xfs_mod_incore_sb(tp->t_mountp, XFS_SBS_FDBLOCKS, + xfs_icsb_modify_counters(tp->t_mountp, XFS_SBS_FDBLOCKS, (int64_t)blocks, rsvd); tp->t_blk_res = 0; } @@ -1009,7 +1009,7 @@ void xfs_trans_unreserve_and_mod_sb( xfs_trans_t *tp) { - xfs_mod_sb_t msb[14]; /* If you add cases, add entries */ + xfs_mod_sb_t msb[9]; /* If you add cases, add entries */ xfs_mod_sb_t *msbp; xfs_mount_t *mp = tp->t_mountp; /* REFERENCED */ @@ -1017,55 +1017,61 @@ xfs_trans_unreserve_and_mod_sb( int rsvd; int64_t blkdelta = 0; int64_t rtxdelta = 0; + int64_t idelta = 0; + int64_t ifreedelta = 0; msbp = msb; rsvd = (tp->t_flags & XFS_TRANS_RESERVE) != 0; - /* calculate free blocks delta */ + /* calculate deltas */ if (tp->t_blk_res > 0) blkdelta = tp->t_blk_res; - if ((tp->t_fdblocks_delta != 0) && (xfs_sb_version_haslazysbcount(&mp->m_sb) || (tp->t_flags & XFS_TRANS_SB_DIRTY))) blkdelta += tp->t_fdblocks_delta; - if (blkdelta != 0) { - msbp->msb_field = XFS_SBS_FDBLOCKS; - msbp->msb_delta = blkdelta; - msbp++; - } - - /* calculate free realtime extents delta */ if (tp->t_rtx_res > 0) rtxdelta = tp->t_rtx_res; - if ((tp->t_frextents_delta != 0) && (tp->t_flags & XFS_TRANS_SB_DIRTY)) rtxdelta += tp->t_frextents_delta; + if (xfs_sb_version_haslazysbcount(&mp->m_sb) || + (tp->t_flags & XFS_TRANS_SB_DIRTY)) { + idelta = tp->t_icount_delta; + ifreedelta = tp->t_ifree_delta; + } + + /* apply the per-cpu counters */ + if (blkdelta) { + error = xfs_icsb_modify_counters(mp, XFS_SBS_FDBLOCKS, + blkdelta, rsvd); + if (error) + goto out; + } + + if (idelta) { + error = xfs_icsb_modify_counters(mp, XFS_SBS_ICOUNT, + idelta, rsvd); + if (error) + goto out_undo_fdblocks; + } + + if (ifreedelta) { + error = xfs_icsb_modify_counters(mp, XFS_SBS_IFREE, + ifreedelta, rsvd); + if (error) + goto out_undo_icount; + } + + /* apply remaining deltas */ if (rtxdelta != 0) { msbp->msb_field = XFS_SBS_FREXTENTS; msbp->msb_delta = rtxdelta; msbp++; } - /* apply remaining deltas */ - - if (xfs_sb_version_haslazysbcount(&mp->m_sb) || - (tp->t_flags & XFS_TRANS_SB_DIRTY)) { - if (tp->t_icount_delta != 0) { - msbp->msb_field = XFS_SBS_ICOUNT; - msbp->msb_delta = tp->t_icount_delta; - msbp++; - } - if (tp->t_ifree_delta != 0) { - msbp->msb_field = XFS_SBS_IFREE; - msbp->msb_delta = tp->t_ifree_delta; - msbp++; - } - } - if (tp->t_flags & XFS_TRANS_SB_DIRTY) { if (tp->t_dblocks_delta != 0) { msbp->msb_field = XFS_SBS_DBLOCKS; @@ -1115,8 +1121,24 @@ xfs_trans_unreserve_and_mod_sb( if (msbp > msb) { error = xfs_mod_incore_sb_batch(tp->t_mountp, msb, (uint)(msbp - msb), rsvd); - ASSERT(error == 0); + if (error) + goto out_undo_ifreecount; } + + return; + +out_undo_ifreecount: + if (ifreedelta) + xfs_icsb_modify_counters(mp, XFS_SBS_IFREE, -ifreedelta, rsvd); +out_undo_icount: + if (idelta) + xfs_icsb_modify_counters(mp, XFS_SBS_ICOUNT, -idelta, rsvd); +out_undo_fdblocks: + if (blkdelta) + xfs_icsb_modify_counters(mp, XFS_SBS_FDBLOCKS, -blkdelta, rsvd); +out: + ASSERT(error = 0); + return; } /* @@ -1389,15 +1411,12 @@ xfs_trans_item_committed( */ STATIC void xfs_trans_committed( - struct xfs_trans *tp, + void *arg, int abortflag) { + struct xfs_trans *tp = arg; struct xfs_log_item_desc *lidp, *next; - /* Call the transaction's completion callback if there is one. */ - if (tp->t_callback != NULL) - tp->t_callback(tp, tp->t_callarg); - list_for_each_entry_safe(lidp, next, &tp->t_items, lid_trans) { xfs_trans_item_committed(lidp->lid_item, tp->t_lsn, abortflag); xfs_trans_free_item_desc(lidp); @@ -1525,7 +1544,7 @@ xfs_trans_commit_iclog( * running in simulation mode (the log is explicitly turned * off). */ - tp->t_logcb.cb_func = (void(*)(void*, int))xfs_trans_committed; + tp->t_logcb.cb_func = xfs_trans_committed; tp->t_logcb.cb_arg = tp; /* diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h index c13c0f97b494..246286b77a86 100644 --- a/fs/xfs/xfs_trans.h +++ b/fs/xfs/xfs_trans.h @@ -399,8 +399,6 @@ typedef struct xfs_trans { * transaction. */ struct xfs_mount *t_mountp; /* ptr to fs mount struct */ struct xfs_dquot_acct *t_dqinfo; /* acctg info for dquots */ - xfs_trans_callback_t t_callback; /* transaction callback */ - void *t_callarg; /* callback arg */ unsigned int t_flags; /* misc flags */ int64_t t_icount_delta; /* superblock icount change */ int64_t t_ifree_delta; /* superblock ifree change */ @@ -473,6 +471,7 @@ void xfs_trans_dquot_buf(xfs_trans_t *, struct xfs_buf *, uint); void xfs_trans_inode_alloc_buf(xfs_trans_t *, struct xfs_buf *); int xfs_trans_iget(struct xfs_mount *, xfs_trans_t *, xfs_ino_t , uint, uint, struct xfs_inode **); +void xfs_trans_ichgtime(struct xfs_trans *, struct xfs_inode *, int); void xfs_trans_ijoin_ref(struct xfs_trans *, struct xfs_inode *, uint); void xfs_trans_ijoin(struct xfs_trans *, struct xfs_inode *); void xfs_trans_log_buf(xfs_trans_t *, struct xfs_buf *, uint, uint); diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c index 90af025e6839..c47918c302a5 100644 --- a/fs/xfs/xfs_trans_buf.c +++ b/fs/xfs/xfs_trans_buf.c @@ -336,7 +336,7 @@ xfs_trans_read_buf( ASSERT(!XFS_BUF_ISASYNC(bp)); XFS_BUF_READ(bp); xfsbdstrat(tp->t_mountp, bp); - error = xfs_iowait(bp); + error = xfs_buf_iowait(bp); if (error) { xfs_ioerror_alert("xfs_trans_read_buf", mp, bp, blkno); diff --git a/fs/xfs/xfs_trans_inode.c b/fs/xfs/xfs_trans_inode.c index cdc53a1050c5..ccb34532768b 100644 --- a/fs/xfs/xfs_trans_inode.c +++ b/fs/xfs/xfs_trans_inode.c @@ -118,6 +118,36 @@ xfs_trans_ijoin_ref( } /* + * Transactional inode timestamp update. Requires the inode to be locked and + * joined to the transaction supplied. Relies on the transaction subsystem to + * track dirty state and update/writeback the inode accordingly. + */ +void +xfs_trans_ichgtime( + struct xfs_trans *tp, + struct xfs_inode *ip, + int flags) +{ + struct inode *inode = VFS_I(ip); + timespec_t tv; + + ASSERT(tp); + ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); + ASSERT(ip->i_transp == tp); + + tv = current_fs_time(inode->i_sb); + + if ((flags & XFS_ICHGTIME_MOD) && + !timespec_equal(&inode->i_mtime, &tv)) { + inode->i_mtime = tv; + } + if ((flags & XFS_ICHGTIME_CHG) && + !timespec_equal(&inode->i_ctime, &tv)) { + inode->i_ctime = tv; + } +} + +/* * This is called to mark the fields indicated in fieldmask as needing * to be logged when the transaction is committed. The inode must * already be associated with the given transaction. diff --git a/fs/xfs/xfs_types.h b/fs/xfs/xfs_types.h index 320775295e32..26d1867d8156 100644 --- a/fs/xfs/xfs_types.h +++ b/fs/xfs/xfs_types.h @@ -73,8 +73,6 @@ typedef __int32_t xfs_tid_t; /* transaction identifier */ typedef __uint32_t xfs_dablk_t; /* dir/attr block number (in file) */ typedef __uint32_t xfs_dahash_t; /* dir/attr hash value */ -typedef __uint16_t xfs_prid_t; /* prid_t truncated to 16bits in XFS */ - typedef __uint32_t xlog_tid_t; /* transaction ID type */ /* diff --git a/fs/xfs/xfs_utils.c b/fs/xfs/xfs_utils.c index b7d5769d2df0..8b32d1a4c5a1 100644 --- a/fs/xfs/xfs_utils.c +++ b/fs/xfs/xfs_utils.c @@ -56,7 +56,6 @@ xfs_dir_ialloc( mode_t mode, xfs_nlink_t nlink, xfs_dev_t rdev, - cred_t *credp, prid_t prid, /* project id */ int okalloc, /* ok to allocate new space */ xfs_inode_t **ipp, /* pointer to inode; it will be @@ -93,7 +92,7 @@ xfs_dir_ialloc( * transaction commit so that no other process can steal * the inode(s) that we've just allocated. */ - code = xfs_ialloc(tp, dp, mode, nlink, rdev, credp, prid, okalloc, + code = xfs_ialloc(tp, dp, mode, nlink, rdev, prid, okalloc, &ialloc_context, &call_again, &ip); /* @@ -197,7 +196,7 @@ xfs_dir_ialloc( * other allocations in this allocation group, * this call should always succeed. */ - code = xfs_ialloc(tp, dp, mode, nlink, rdev, credp, prid, + code = xfs_ialloc(tp, dp, mode, nlink, rdev, prid, okalloc, &ialloc_context, &call_again, &ip); /* @@ -235,7 +234,7 @@ xfs_droplink( { int error; - xfs_ichgtime(ip, XFS_ICHGTIME_CHG); + xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG); ASSERT (ip->i_d.di_nlink > 0); ip->i_d.di_nlink--; @@ -299,7 +298,7 @@ xfs_bumplink( { if (ip->i_d.di_nlink >= XFS_MAXLINK) return XFS_ERROR(EMLINK); - xfs_ichgtime(ip, XFS_ICHGTIME_CHG); + xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG); ASSERT(ip->i_d.di_nlink > 0); ip->i_d.di_nlink++; diff --git a/fs/xfs/xfs_utils.h b/fs/xfs/xfs_utils.h index f55b9678264f..456fca314933 100644 --- a/fs/xfs/xfs_utils.h +++ b/fs/xfs/xfs_utils.h @@ -19,8 +19,7 @@ #define __XFS_UTILS_H__ extern int xfs_dir_ialloc(xfs_trans_t **, xfs_inode_t *, mode_t, xfs_nlink_t, - xfs_dev_t, cred_t *, prid_t, int, - xfs_inode_t **, int *); + xfs_dev_t, prid_t, int, xfs_inode_t **, int *); extern int xfs_droplink(xfs_trans_t *, xfs_inode_t *); extern int xfs_bumplink(xfs_trans_t *, xfs_inode_t *); extern void xfs_bump_ino_vers2(xfs_trans_t *, xfs_inode_t *); diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c index 4c7c7bfb2b2f..8e4a63c4151a 100644 --- a/fs/xfs/xfs_vnodeops.c +++ b/fs/xfs/xfs_vnodeops.c @@ -114,7 +114,7 @@ xfs_setattr( */ ASSERT(udqp == NULL); ASSERT(gdqp == NULL); - code = xfs_qm_vop_dqalloc(ip, uid, gid, ip->i_d.di_projid, + code = xfs_qm_vop_dqalloc(ip, uid, gid, xfs_get_projid(ip), qflags, &udqp, &gdqp); if (code) return code; @@ -184,8 +184,11 @@ xfs_setattr( ip->i_size == 0 && ip->i_d.di_nextents == 0) { xfs_iunlock(ip, XFS_ILOCK_EXCL); lock_flags &= ~XFS_ILOCK_EXCL; - if (mask & ATTR_CTIME) - xfs_ichgtime(ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); + if (mask & ATTR_CTIME) { + inode->i_mtime = inode->i_ctime = + current_fs_time(inode->i_sb); + xfs_mark_inode_dirty_sync(ip); + } code = 0; goto error_return; } @@ -1253,8 +1256,7 @@ xfs_create( struct xfs_name *name, mode_t mode, xfs_dev_t rdev, - xfs_inode_t **ipp, - cred_t *credp) + xfs_inode_t **ipp) { int is_dir = S_ISDIR(mode); struct xfs_mount *mp = dp->i_mount; @@ -1266,7 +1268,7 @@ xfs_create( boolean_t unlock_dp_on_error = B_FALSE; uint cancel_flags; int committed; - xfs_prid_t prid; + prid_t prid; struct xfs_dquot *udqp = NULL; struct xfs_dquot *gdqp = NULL; uint resblks; @@ -1279,9 +1281,9 @@ xfs_create( return XFS_ERROR(EIO); if (dp->i_d.di_flags & XFS_DIFLAG_PROJINHERIT) - prid = dp->i_d.di_projid; + prid = xfs_get_projid(dp); else - prid = dfltprid; + prid = XFS_PROJID_DEFAULT; /* * Make sure that we have allocated dquot(s) on disk. @@ -1360,7 +1362,7 @@ xfs_create( * entry pointing to them, but a directory also the "." entry * pointing to itself. */ - error = xfs_dir_ialloc(&tp, dp, mode, is_dir ? 2 : 1, rdev, credp, + error = xfs_dir_ialloc(&tp, dp, mode, is_dir ? 2 : 1, rdev, prid, resblks > 0, &ip, &committed); if (error) { if (error == ENOSPC) @@ -1391,7 +1393,7 @@ xfs_create( ASSERT(error != ENOSPC); goto out_trans_abort; } - xfs_ichgtime(dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); + xfs_trans_ichgtime(tp, dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE); if (is_dir) { @@ -1742,7 +1744,7 @@ xfs_remove( ASSERT(error != ENOENT); goto out_bmap_cancel; } - xfs_ichgtime(dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); + xfs_trans_ichgtime(tp, dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); if (is_dir) { /* @@ -1880,7 +1882,7 @@ xfs_link( * the tree quota mechanism could be circumvented. */ if (unlikely((tdp->i_d.di_flags & XFS_DIFLAG_PROJINHERIT) && - (tdp->i_d.di_projid != sip->i_d.di_projid))) { + (xfs_get_projid(tdp) != xfs_get_projid(sip)))) { error = XFS_ERROR(EXDEV); goto error_return; } @@ -1895,7 +1897,7 @@ xfs_link( &first_block, &free_list, resblks); if (error) goto abort_return; - xfs_ichgtime(tdp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); + xfs_trans_ichgtime(tp, tdp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); xfs_trans_log_inode(tp, tdp, XFS_ILOG_CORE); error = xfs_bumplink(tp, sip); @@ -1933,8 +1935,7 @@ xfs_symlink( struct xfs_name *link_name, const char *target_path, mode_t mode, - xfs_inode_t **ipp, - cred_t *credp) + xfs_inode_t **ipp) { xfs_mount_t *mp = dp->i_mount; xfs_trans_t *tp; @@ -1955,7 +1956,7 @@ xfs_symlink( int byte_cnt; int n; xfs_buf_t *bp; - xfs_prid_t prid; + prid_t prid; struct xfs_dquot *udqp, *gdqp; uint resblks; @@ -1978,9 +1979,9 @@ xfs_symlink( udqp = gdqp = NULL; if (dp->i_d.di_flags & XFS_DIFLAG_PROJINHERIT) - prid = dp->i_d.di_projid; + prid = xfs_get_projid(dp); else - prid = (xfs_prid_t)dfltprid; + prid = XFS_PROJID_DEFAULT; /* * Make sure that we have allocated dquot(s) on disk. @@ -2046,8 +2047,8 @@ xfs_symlink( /* * Allocate an inode for the symlink. */ - error = xfs_dir_ialloc(&tp, dp, S_IFLNK | (mode & ~S_IFMT), - 1, 0, credp, prid, resblks > 0, &ip, NULL); + error = xfs_dir_ialloc(&tp, dp, S_IFLNK | (mode & ~S_IFMT), 1, 0, + prid, resblks > 0, &ip, NULL); if (error) { if (error == ENOSPC) goto error_return; @@ -2129,7 +2130,7 @@ xfs_symlink( &first_block, &free_list, resblks); if (error) goto error1; - xfs_ichgtime(dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); + xfs_trans_ichgtime(tp, dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE); /* @@ -2272,7 +2273,7 @@ xfs_alloc_file_space( count = len; imapp = &imaps[0]; nimaps = 1; - bmapi_flag = XFS_BMAPI_WRITE | (alloc_type ? XFS_BMAPI_PREALLOC : 0); + bmapi_flag = XFS_BMAPI_WRITE | alloc_type; startoffset_fsb = XFS_B_TO_FSBT(mp, offset); allocatesize_fsb = XFS_B_TO_FSB(mp, count); @@ -2431,9 +2432,9 @@ xfs_zero_remaining_bytes( if (endoff > ip->i_size) endoff = ip->i_size; - bp = xfs_buf_get_noaddr(mp->m_sb.sb_blocksize, - XFS_IS_REALTIME_INODE(ip) ? - mp->m_rtdev_targp : mp->m_ddev_targp); + bp = xfs_buf_get_uncached(XFS_IS_REALTIME_INODE(ip) ? + mp->m_rtdev_targp : mp->m_ddev_targp, + mp->m_sb.sb_blocksize, XBF_DONT_BLOCK); if (!bp) return XFS_ERROR(ENOMEM); @@ -2459,7 +2460,7 @@ xfs_zero_remaining_bytes( XFS_BUF_READ(bp); XFS_BUF_SET_ADDR(bp, xfs_fsb_to_db(ip, imap.br_startblock)); xfsbdstrat(mp, bp); - error = xfs_iowait(bp); + error = xfs_buf_iowait(bp); if (error) { xfs_ioerror_alert("xfs_zero_remaining_bytes(read)", mp, bp, XFS_BUF_ADDR(bp)); @@ -2472,7 +2473,7 @@ xfs_zero_remaining_bytes( XFS_BUF_UNREAD(bp); XFS_BUF_WRITE(bp); xfsbdstrat(mp, bp); - error = xfs_iowait(bp); + error = xfs_buf_iowait(bp); if (error) { xfs_ioerror_alert("xfs_zero_remaining_bytes(write)", mp, bp, XFS_BUF_ADDR(bp)); @@ -2711,6 +2712,7 @@ xfs_change_file_space( xfs_off_t llen; xfs_trans_t *tp; struct iattr iattr; + int prealloc_type; if (!S_ISREG(ip->i_d.di_mode)) return XFS_ERROR(EINVAL); @@ -2753,12 +2755,17 @@ xfs_change_file_space( * size to be changed. */ setprealloc = clrprealloc = 0; + prealloc_type = XFS_BMAPI_PREALLOC; switch (cmd) { + case XFS_IOC_ZERO_RANGE: + prealloc_type |= XFS_BMAPI_CONVERT; + xfs_tosspages(ip, startoffset, startoffset + bf->l_len, 0); + /* FALLTHRU */ case XFS_IOC_RESVSP: case XFS_IOC_RESVSP64: error = xfs_alloc_file_space(ip, startoffset, bf->l_len, - 1, attr_flags); + prealloc_type, attr_flags); if (error) return error; setprealloc = 1; @@ -2827,7 +2834,7 @@ xfs_change_file_space( if (ip->i_d.di_mode & S_IXGRP) ip->i_d.di_mode &= ~S_ISGID; - xfs_ichgtime(ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); + xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); } if (setprealloc) ip->i_d.di_flags |= XFS_DIFLAG_PREALLOC; diff --git a/fs/xfs/xfs_vnodeops.h b/fs/xfs/xfs_vnodeops.h index d8dfa8d0dadd..f6702927eee4 100644 --- a/fs/xfs/xfs_vnodeops.h +++ b/fs/xfs/xfs_vnodeops.h @@ -2,7 +2,6 @@ #define _XFS_VNODEOPS_H 1 struct attrlist_cursor_kern; -struct cred; struct file; struct iattr; struct inode; @@ -26,7 +25,7 @@ int xfs_inactive(struct xfs_inode *ip); int xfs_lookup(struct xfs_inode *dp, struct xfs_name *name, struct xfs_inode **ipp, struct xfs_name *ci_name); int xfs_create(struct xfs_inode *dp, struct xfs_name *name, mode_t mode, - xfs_dev_t rdev, struct xfs_inode **ipp, cred_t *credp); + xfs_dev_t rdev, struct xfs_inode **ipp); int xfs_remove(struct xfs_inode *dp, struct xfs_name *name, struct xfs_inode *ip); int xfs_link(struct xfs_inode *tdp, struct xfs_inode *sip, @@ -34,8 +33,7 @@ int xfs_link(struct xfs_inode *tdp, struct xfs_inode *sip, int xfs_readdir(struct xfs_inode *dp, void *dirent, size_t bufsize, xfs_off_t *offset, filldir_t filldir); int xfs_symlink(struct xfs_inode *dp, struct xfs_name *link_name, - const char *target_path, mode_t mode, struct xfs_inode **ipp, - cred_t *credp); + const char *target_path, mode_t mode, struct xfs_inode **ipp); int xfs_set_dmattrs(struct xfs_inode *ip, u_int evmask, u_int16_t state); int xfs_change_file_space(struct xfs_inode *ip, int cmd, xfs_flock64_t *bf, xfs_off_t offset, int attr_flags); |