diff options
Diffstat (limited to 'fs')
234 files changed, 4781 insertions, 3332 deletions
diff --git a/fs/9p/acl.c b/fs/9p/acl.c index b3c2cc79c20d..082d227fa56b 100644 --- a/fs/9p/acl.c +++ b/fs/9p/acl.c @@ -277,6 +277,7 @@ static int v9fs_xattr_set_acl(const struct xattr_handler *handler, case ACL_TYPE_ACCESS: if (acl) { struct iattr iattr; + struct posix_acl *old_acl = acl; retval = posix_acl_update_mode(inode, &iattr.ia_mode, &acl); if (retval) @@ -287,6 +288,7 @@ static int v9fs_xattr_set_acl(const struct xattr_handler *handler, * by the mode bits. So don't * update ACL. */ + posix_acl_release(old_acl); value = NULL; size = 0; } diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index 6a0f3fa85ef7..3de3b4a89d89 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -534,11 +534,11 @@ v9fs_mmap_file_mmap(struct file *filp, struct vm_area_struct *vma) } static int -v9fs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) +v9fs_vm_page_mkwrite(struct vm_fault *vmf) { struct v9fs_inode *v9inode; struct page *page = vmf->page; - struct file *filp = vma->vm_file; + struct file *filp = vmf->vma->vm_file; struct inode *inode = file_inode(filp); diff --git a/fs/affs/affs.h b/fs/affs/affs.h index 2f088773f1c0..2f8bab390d13 100644 --- a/fs/affs/affs.h +++ b/fs/affs/affs.h @@ -138,9 +138,9 @@ extern int affs_remove_hash(struct inode *dir, struct buffer_head *rem_bh); extern int affs_remove_header(struct dentry *dentry); extern u32 affs_checksum_block(struct super_block *sb, struct buffer_head *bh); extern void affs_fix_checksum(struct super_block *sb, struct buffer_head *bh); -extern void secs_to_datestamp(time64_t secs, struct affs_date *ds); -extern umode_t prot_to_mode(u32 prot); -extern void mode_to_prot(struct inode *inode); +extern void affs_secs_to_datestamp(time64_t secs, struct affs_date *ds); +extern umode_t affs_prot_to_mode(u32 prot); +extern void affs_mode_to_prot(struct inode *inode); __printf(3, 4) extern void affs_error(struct super_block *sb, const char *function, const char *fmt, ...); @@ -162,6 +162,7 @@ extern void affs_free_bitmap(struct super_block *sb); /* namei.c */ +extern const struct export_operations affs_export_ops; extern int affs_hash_name(struct super_block *sb, const u8 *name, unsigned int len); extern struct dentry *affs_lookup(struct inode *dir, struct dentry *dentry, unsigned int); extern int affs_unlink(struct inode *dir, struct dentry *dentry); @@ -178,7 +179,6 @@ extern int affs_rename(struct inode *old_dir, struct dentry *old_dentry, /* inode.c */ -extern unsigned long affs_parent_ino(struct inode *dir); extern struct inode *affs_new_inode(struct inode *dir); extern int affs_notify_change(struct dentry *dentry, struct iattr *attr); extern void affs_evict_inode(struct inode *inode); @@ -213,6 +213,12 @@ extern const struct address_space_operations affs_aops_ofs; extern const struct dentry_operations affs_dentry_operations; extern const struct dentry_operations affs_intl_dentry_operations; +static inline bool affs_validblock(struct super_block *sb, int block) +{ + return(block >= AFFS_SB(sb)->s_reserved && + block < AFFS_SB(sb)->s_partition_size); +} + static inline void affs_set_blocksize(struct super_block *sb, int size) { @@ -222,7 +228,7 @@ static inline struct buffer_head * affs_bread(struct super_block *sb, int block) { pr_debug("%s: %d\n", __func__, block); - if (block >= AFFS_SB(sb)->s_reserved && block < AFFS_SB(sb)->s_partition_size) + if (affs_validblock(sb, block)) return sb_bread(sb, block); return NULL; } @@ -230,7 +236,7 @@ static inline struct buffer_head * affs_getblk(struct super_block *sb, int block) { pr_debug("%s: %d\n", __func__, block); - if (block >= AFFS_SB(sb)->s_reserved && block < AFFS_SB(sb)->s_partition_size) + if (affs_validblock(sb, block)) return sb_getblk(sb, block); return NULL; } @@ -239,7 +245,7 @@ affs_getzeroblk(struct super_block *sb, int block) { struct buffer_head *bh; pr_debug("%s: %d\n", __func__, block); - if (block >= AFFS_SB(sb)->s_reserved && block < AFFS_SB(sb)->s_partition_size) { + if (affs_validblock(sb, block)) { bh = sb_getblk(sb, block); lock_buffer(bh); memset(bh->b_data, 0 , sb->s_blocksize); @@ -254,7 +260,7 @@ affs_getemptyblk(struct super_block *sb, int block) { struct buffer_head *bh; pr_debug("%s: %d\n", __func__, block); - if (block >= AFFS_SB(sb)->s_reserved && block < AFFS_SB(sb)->s_partition_size) { + if (affs_validblock(sb, block)) { bh = sb_getblk(sb, block); wait_on_buffer(bh); set_buffer_uptodate(bh); diff --git a/fs/affs/amigaffs.c b/fs/affs/amigaffs.c index 0ec65c133b93..b573c3b9a328 100644 --- a/fs/affs/amigaffs.c +++ b/fs/affs/amigaffs.c @@ -367,7 +367,7 @@ affs_fix_checksum(struct super_block *sb, struct buffer_head *bh) } void -secs_to_datestamp(time64_t secs, struct affs_date *ds) +affs_secs_to_datestamp(time64_t secs, struct affs_date *ds) { u32 days; u32 minute; @@ -386,55 +386,55 @@ secs_to_datestamp(time64_t secs, struct affs_date *ds) } umode_t -prot_to_mode(u32 prot) +affs_prot_to_mode(u32 prot) { umode_t mode = 0; if (!(prot & FIBF_NOWRITE)) - mode |= S_IWUSR; + mode |= 0200; if (!(prot & FIBF_NOREAD)) - mode |= S_IRUSR; + mode |= 0400; if (!(prot & FIBF_NOEXECUTE)) - mode |= S_IXUSR; + mode |= 0100; if (prot & FIBF_GRP_WRITE) - mode |= S_IWGRP; + mode |= 0020; if (prot & FIBF_GRP_READ) - mode |= S_IRGRP; + mode |= 0040; if (prot & FIBF_GRP_EXECUTE) - mode |= S_IXGRP; + mode |= 0010; if (prot & FIBF_OTR_WRITE) - mode |= S_IWOTH; + mode |= 0002; if (prot & FIBF_OTR_READ) - mode |= S_IROTH; + mode |= 0004; if (prot & FIBF_OTR_EXECUTE) - mode |= S_IXOTH; + mode |= 0001; return mode; } void -mode_to_prot(struct inode *inode) +affs_mode_to_prot(struct inode *inode) { u32 prot = AFFS_I(inode)->i_protect; umode_t mode = inode->i_mode; - if (!(mode & S_IXUSR)) + if (!(mode & 0100)) prot |= FIBF_NOEXECUTE; - if (!(mode & S_IRUSR)) + if (!(mode & 0400)) prot |= FIBF_NOREAD; - if (!(mode & S_IWUSR)) + if (!(mode & 0200)) prot |= FIBF_NOWRITE; - if (mode & S_IXGRP) + if (mode & 0010) prot |= FIBF_GRP_EXECUTE; - if (mode & S_IRGRP) + if (mode & 0040) prot |= FIBF_GRP_READ; - if (mode & S_IWGRP) + if (mode & 0020) prot |= FIBF_GRP_WRITE; - if (mode & S_IXOTH) + if (mode & 0001) prot |= FIBF_OTR_EXECUTE; - if (mode & S_IROTH) + if (mode & 0004) prot |= FIBF_OTR_READ; - if (mode & S_IWOTH) + if (mode & 0002) prot |= FIBF_OTR_WRITE; AFFS_I(inode)->i_protect = prot; diff --git a/fs/affs/inode.c b/fs/affs/inode.c index fe4e1290dbb5..a5e6097eb5a9 100644 --- a/fs/affs/inode.c +++ b/fs/affs/inode.c @@ -69,7 +69,7 @@ struct inode *affs_iget(struct super_block *sb, unsigned long ino) if (affs_test_opt(sbi->s_flags, SF_SETMODE)) inode->i_mode = sbi->s_mode; else - inode->i_mode = prot_to_mode(prot); + inode->i_mode = affs_prot_to_mode(prot); id = be16_to_cpu(tail->uid); if (id == 0 || affs_test_opt(sbi->s_flags, SF_SETUID)) @@ -184,11 +184,12 @@ affs_write_inode(struct inode *inode, struct writeback_control *wbc) } tail = AFFS_TAIL(sb, bh); if (tail->stype == cpu_to_be32(ST_ROOT)) { - secs_to_datestamp(inode->i_mtime.tv_sec,&AFFS_ROOT_TAIL(sb, bh)->root_change); + affs_secs_to_datestamp(inode->i_mtime.tv_sec, + &AFFS_ROOT_TAIL(sb, bh)->root_change); } else { tail->protect = cpu_to_be32(AFFS_I(inode)->i_protect); tail->size = cpu_to_be32(inode->i_size); - secs_to_datestamp(inode->i_mtime.tv_sec,&tail->change); + affs_secs_to_datestamp(inode->i_mtime.tv_sec, &tail->change); if (!(inode->i_ino == AFFS_SB(sb)->s_root_block)) { uid = i_uid_read(inode); gid = i_gid_read(inode); @@ -249,7 +250,7 @@ affs_notify_change(struct dentry *dentry, struct iattr *attr) mark_inode_dirty(inode); if (attr->ia_valid & ATTR_MODE) - mode_to_prot(inode); + affs_mode_to_prot(inode); out: return error; } diff --git a/fs/affs/namei.c b/fs/affs/namei.c index 29186d29a3b6..96dd1d09a273 100644 --- a/fs/affs/namei.c +++ b/fs/affs/namei.c @@ -9,29 +9,10 @@ */ #include "affs.h" +#include <linux/exportfs.h> typedef int (*toupper_t)(int); -static int affs_toupper(int ch); -static int affs_hash_dentry(const struct dentry *, struct qstr *); -static int affs_compare_dentry(const struct dentry *dentry, - unsigned int len, const char *str, const struct qstr *name); -static int affs_intl_toupper(int ch); -static int affs_intl_hash_dentry(const struct dentry *, struct qstr *); -static int affs_intl_compare_dentry(const struct dentry *dentry, - unsigned int len, const char *str, const struct qstr *name); - -const struct dentry_operations affs_dentry_operations = { - .d_hash = affs_hash_dentry, - .d_compare = affs_compare_dentry, -}; - -const struct dentry_operations affs_intl_dentry_operations = { - .d_hash = affs_intl_hash_dentry, - .d_compare = affs_intl_compare_dentry, -}; - - /* Simple toupper() for DOS\1 */ static int @@ -271,7 +252,7 @@ affs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) return -ENOSPC; inode->i_mode = mode; - mode_to_prot(inode); + affs_mode_to_prot(inode); mark_inode_dirty(inode); inode->i_op = &affs_file_inode_operations; @@ -301,7 +282,7 @@ affs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) return -ENOSPC; inode->i_mode = S_IFDIR | mode; - mode_to_prot(inode); + affs_mode_to_prot(inode); inode->i_op = &affs_dir_inode_operations; inode->i_fop = &affs_dir_operations; @@ -347,7 +328,7 @@ affs_symlink(struct inode *dir, struct dentry *dentry, const char *symname) inode_nohighmem(inode); inode->i_data.a_ops = &affs_symlink_aops; inode->i_mode = S_IFLNK | 0777; - mode_to_prot(inode); + affs_mode_to_prot(inode); error = -EIO; bh = affs_bread(sb, inode->i_ino); @@ -465,3 +446,71 @@ done: affs_brelse(bh); return retval; } + +static struct dentry *affs_get_parent(struct dentry *child) +{ + struct inode *parent; + struct buffer_head *bh; + + bh = affs_bread(child->d_sb, d_inode(child)->i_ino); + if (!bh) + return ERR_PTR(-EIO); + + parent = affs_iget(child->d_sb, + be32_to_cpu(AFFS_TAIL(child->d_sb, bh)->parent)); + brelse(bh); + if (IS_ERR(parent)) + return ERR_CAST(parent); + + return d_obtain_alias(parent); +} + +static struct inode *affs_nfs_get_inode(struct super_block *sb, u64 ino, + u32 generation) +{ + struct inode *inode; + + if (!affs_validblock(sb, ino)) + return ERR_PTR(-ESTALE); + + inode = affs_iget(sb, ino); + if (IS_ERR(inode)) + return ERR_CAST(inode); + + if (generation && inode->i_generation != generation) { + iput(inode); + return ERR_PTR(-ESTALE); + } + + return inode; +} + +static struct dentry *affs_fh_to_dentry(struct super_block *sb, struct fid *fid, + int fh_len, int fh_type) +{ + return generic_fh_to_dentry(sb, fid, fh_len, fh_type, + affs_nfs_get_inode); +} + +static struct dentry *affs_fh_to_parent(struct super_block *sb, struct fid *fid, + int fh_len, int fh_type) +{ + return generic_fh_to_parent(sb, fid, fh_len, fh_type, + affs_nfs_get_inode); +} + +const struct export_operations affs_export_ops = { + .fh_to_dentry = affs_fh_to_dentry, + .fh_to_parent = affs_fh_to_parent, + .get_parent = affs_get_parent, +}; + +const struct dentry_operations affs_dentry_operations = { + .d_hash = affs_hash_dentry, + .d_compare = affs_compare_dentry, +}; + +const struct dentry_operations affs_intl_dentry_operations = { + .d_hash = affs_intl_hash_dentry, + .d_compare = affs_intl_compare_dentry, +}; diff --git a/fs/affs/super.c b/fs/affs/super.c index d6384863192c..37532538e8ab 100644 --- a/fs/affs/super.c +++ b/fs/affs/super.c @@ -32,7 +32,7 @@ affs_commit_super(struct super_block *sb, int wait) struct affs_root_tail *tail = AFFS_ROOT_TAIL(sb, bh); lock_buffer(bh); - secs_to_datestamp(ktime_get_real_seconds(), &tail->disk_change); + affs_secs_to_datestamp(ktime_get_real_seconds(), &tail->disk_change); affs_fix_checksum(sb, bh); unlock_buffer(bh); @@ -507,6 +507,7 @@ got_root: return -ENOMEM; } + sb->s_export_op = &affs_export_ops; pr_debug("s_flags=%lX\n", sb->s_flags); return 0; } diff --git a/fs/afs/callback.c b/fs/afs/callback.c index 1e9d2f84e5b5..b29447e03ede 100644 --- a/fs/afs/callback.c +++ b/fs/afs/callback.c @@ -343,7 +343,7 @@ void afs_dispatch_give_up_callbacks(struct work_struct *work) * had callbacks entirely, and the server will call us later to break * them */ - afs_fs_give_up_callbacks(server, &afs_async_call); + afs_fs_give_up_callbacks(server, true); } /* diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c index d764236072b1..2edbdcbf6432 100644 --- a/fs/afs/cmservice.c +++ b/fs/afs/cmservice.c @@ -24,65 +24,86 @@ static int afs_deliver_cb_callback(struct afs_call *); static int afs_deliver_cb_probe_uuid(struct afs_call *); static int afs_deliver_cb_tell_me_about_yourself(struct afs_call *); static void afs_cm_destructor(struct afs_call *); +static void SRXAFSCB_CallBack(struct work_struct *); +static void SRXAFSCB_InitCallBackState(struct work_struct *); +static void SRXAFSCB_Probe(struct work_struct *); +static void SRXAFSCB_ProbeUuid(struct work_struct *); +static void SRXAFSCB_TellMeAboutYourself(struct work_struct *); + +#define CM_NAME(name) \ + const char afs_SRXCB##name##_name[] __tracepoint_string = \ + "CB." #name /* * CB.CallBack operation type */ +static CM_NAME(CallBack); static const struct afs_call_type afs_SRXCBCallBack = { - .name = "CB.CallBack", + .name = afs_SRXCBCallBack_name, .deliver = afs_deliver_cb_callback, .abort_to_error = afs_abort_to_error, .destructor = afs_cm_destructor, + .work = SRXAFSCB_CallBack, }; /* * CB.InitCallBackState operation type */ +static CM_NAME(InitCallBackState); static const struct afs_call_type afs_SRXCBInitCallBackState = { - .name = "CB.InitCallBackState", + .name = afs_SRXCBInitCallBackState_name, .deliver = afs_deliver_cb_init_call_back_state, .abort_to_error = afs_abort_to_error, .destructor = afs_cm_destructor, + .work = SRXAFSCB_InitCallBackState, }; /* * CB.InitCallBackState3 operation type */ +static CM_NAME(InitCallBackState3); static const struct afs_call_type afs_SRXCBInitCallBackState3 = { - .name = "CB.InitCallBackState3", + .name = afs_SRXCBInitCallBackState3_name, .deliver = afs_deliver_cb_init_call_back_state3, .abort_to_error = afs_abort_to_error, .destructor = afs_cm_destructor, + .work = SRXAFSCB_InitCallBackState, }; /* * CB.Probe operation type */ +static CM_NAME(Probe); static const struct afs_call_type afs_SRXCBProbe = { - .name = "CB.Probe", + .name = afs_SRXCBProbe_name, .deliver = afs_deliver_cb_probe, .abort_to_error = afs_abort_to_error, .destructor = afs_cm_destructor, + .work = SRXAFSCB_Probe, }; /* * CB.ProbeUuid operation type */ +static CM_NAME(ProbeUuid); static const struct afs_call_type afs_SRXCBProbeUuid = { - .name = "CB.ProbeUuid", + .name = afs_SRXCBProbeUuid_name, .deliver = afs_deliver_cb_probe_uuid, .abort_to_error = afs_abort_to_error, .destructor = afs_cm_destructor, + .work = SRXAFSCB_ProbeUuid, }; /* * CB.TellMeAboutYourself operation type */ +static CM_NAME(TellMeAboutYourself); static const struct afs_call_type afs_SRXCBTellMeAboutYourself = { - .name = "CB.TellMeAboutYourself", + .name = afs_SRXCBTellMeAboutYourself_name, .deliver = afs_deliver_cb_tell_me_about_yourself, .abort_to_error = afs_abort_to_error, .destructor = afs_cm_destructor, + .work = SRXAFSCB_TellMeAboutYourself, }; /* @@ -153,6 +174,7 @@ static void SRXAFSCB_CallBack(struct work_struct *work) afs_send_empty_reply(call); afs_break_callbacks(call->server, call->count, call->request); + afs_put_call(call); _leave(""); } @@ -274,9 +296,7 @@ static int afs_deliver_cb_callback(struct afs_call *call) return -ENOTCONN; call->server = server; - INIT_WORK(&call->work, SRXAFSCB_CallBack); - queue_work(afs_wq, &call->work); - return 0; + return afs_queue_call_work(call); } /* @@ -290,6 +310,7 @@ static void SRXAFSCB_InitCallBackState(struct work_struct *work) afs_init_callback_state(call->server); afs_send_empty_reply(call); + afs_put_call(call); _leave(""); } @@ -320,9 +341,7 @@ static int afs_deliver_cb_init_call_back_state(struct afs_call *call) return -ENOTCONN; call->server = server; - INIT_WORK(&call->work, SRXAFSCB_InitCallBackState); - queue_work(afs_wq, &call->work); - return 0; + return afs_queue_call_work(call); } /* @@ -332,7 +351,7 @@ static int afs_deliver_cb_init_call_back_state3(struct afs_call *call) { struct sockaddr_rxrpc srx; struct afs_server *server; - struct afs_uuid *r; + struct uuid_v1 *r; unsigned loop; __be32 *b; int ret; @@ -362,15 +381,15 @@ static int afs_deliver_cb_init_call_back_state3(struct afs_call *call) } _debug("unmarshall UUID"); - call->request = kmalloc(sizeof(struct afs_uuid), GFP_KERNEL); + call->request = kmalloc(sizeof(struct uuid_v1), GFP_KERNEL); if (!call->request) return -ENOMEM; b = call->buffer; r = call->request; - r->time_low = ntohl(b[0]); - r->time_mid = ntohl(b[1]); - r->time_hi_and_version = ntohl(b[2]); + r->time_low = b[0]; + r->time_mid = htons(ntohl(b[1])); + r->time_hi_and_version = htons(ntohl(b[2])); r->clock_seq_hi_and_reserved = ntohl(b[3]); r->clock_seq_low = ntohl(b[4]); @@ -394,9 +413,7 @@ static int afs_deliver_cb_init_call_back_state3(struct afs_call *call) return -ENOTCONN; call->server = server; - INIT_WORK(&call->work, SRXAFSCB_InitCallBackState); - queue_work(afs_wq, &call->work); - return 0; + return afs_queue_call_work(call); } /* @@ -408,6 +425,7 @@ static void SRXAFSCB_Probe(struct work_struct *work) _enter(""); afs_send_empty_reply(call); + afs_put_call(call); _leave(""); } @@ -427,9 +445,7 @@ static int afs_deliver_cb_probe(struct afs_call *call) /* no unmarshalling required */ call->state = AFS_CALL_REPLYING; - INIT_WORK(&call->work, SRXAFSCB_Probe); - queue_work(afs_wq, &call->work); - return 0; + return afs_queue_call_work(call); } /* @@ -438,7 +454,7 @@ static int afs_deliver_cb_probe(struct afs_call *call) static void SRXAFSCB_ProbeUuid(struct work_struct *work) { struct afs_call *call = container_of(work, struct afs_call, work); - struct afs_uuid *r = call->request; + struct uuid_v1 *r = call->request; struct { __be32 match; @@ -452,6 +468,7 @@ static void SRXAFSCB_ProbeUuid(struct work_struct *work) reply.match = htonl(1); afs_send_simple_reply(call, &reply, sizeof(reply)); + afs_put_call(call); _leave(""); } @@ -460,7 +477,7 @@ static void SRXAFSCB_ProbeUuid(struct work_struct *work) */ static int afs_deliver_cb_probe_uuid(struct afs_call *call) { - struct afs_uuid *r; + struct uuid_v1 *r; unsigned loop; __be32 *b; int ret; @@ -486,15 +503,15 @@ static int afs_deliver_cb_probe_uuid(struct afs_call *call) } _debug("unmarshall UUID"); - call->request = kmalloc(sizeof(struct afs_uuid), GFP_KERNEL); + call->request = kmalloc(sizeof(struct uuid_v1), GFP_KERNEL); if (!call->request) return -ENOMEM; b = call->buffer; r = call->request; - r->time_low = ntohl(b[0]); - r->time_mid = ntohl(b[1]); - r->time_hi_and_version = ntohl(b[2]); + r->time_low = b[0]; + r->time_mid = htons(ntohl(b[1])); + r->time_hi_and_version = htons(ntohl(b[2])); r->clock_seq_hi_and_reserved = ntohl(b[3]); r->clock_seq_low = ntohl(b[4]); @@ -510,9 +527,7 @@ static int afs_deliver_cb_probe_uuid(struct afs_call *call) call->state = AFS_CALL_REPLYING; - INIT_WORK(&call->work, SRXAFSCB_ProbeUuid); - queue_work(afs_wq, &call->work); - return 0; + return afs_queue_call_work(call); } /* @@ -554,9 +569,9 @@ static void SRXAFSCB_TellMeAboutYourself(struct work_struct *work) memset(&reply, 0, sizeof(reply)); reply.ia.nifs = htonl(nifs); - reply.ia.uuid[0] = htonl(afs_uuid.time_low); - reply.ia.uuid[1] = htonl(afs_uuid.time_mid); - reply.ia.uuid[2] = htonl(afs_uuid.time_hi_and_version); + reply.ia.uuid[0] = afs_uuid.time_low; + reply.ia.uuid[1] = htonl(ntohs(afs_uuid.time_mid)); + reply.ia.uuid[2] = htonl(ntohs(afs_uuid.time_hi_and_version)); reply.ia.uuid[3] = htonl((s8) afs_uuid.clock_seq_hi_and_reserved); reply.ia.uuid[4] = htonl((s8) afs_uuid.clock_seq_low); for (loop = 0; loop < 6; loop++) @@ -574,7 +589,7 @@ static void SRXAFSCB_TellMeAboutYourself(struct work_struct *work) reply.cap.capcount = htonl(1); reply.cap.caps[0] = htonl(AFS_CAP_ERROR_TRANSLATION); afs_send_simple_reply(call, &reply, sizeof(reply)); - + afs_put_call(call); _leave(""); } @@ -594,7 +609,5 @@ static int afs_deliver_cb_tell_me_about_yourself(struct afs_call *call) /* no unmarshalling required */ call->state = AFS_CALL_REPLYING; - INIT_WORK(&call->work, SRXAFSCB_TellMeAboutYourself); - queue_work(afs_wq, &call->work); - return 0; + return afs_queue_call_work(call); } diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 51a241e09fbb..949f960337f5 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -252,7 +252,7 @@ static int afs_dir_iterate_block(struct dir_context *ctx, /* skip entries marked unused in the bitmap */ if (!(block->pagehdr.bitmap[offset / 8] & (1 << (offset % 8)))) { - _debug("ENT[%Zu.%u]: unused", + _debug("ENT[%zu.%u]: unused", blkoff / sizeof(union afs_dir_block), offset); if (offset >= curr) ctx->pos = blkoff + @@ -266,7 +266,7 @@ static int afs_dir_iterate_block(struct dir_context *ctx, sizeof(*block) - offset * sizeof(union afs_dirent)); - _debug("ENT[%Zu.%u]: %s %Zu \"%s\"", + _debug("ENT[%zu.%u]: %s %zu \"%s\"", blkoff / sizeof(union afs_dir_block), offset, (offset < curr ? "skip" : "fill"), nlen, dire->u.name); @@ -274,23 +274,23 @@ static int afs_dir_iterate_block(struct dir_context *ctx, /* work out where the next possible entry is */ for (tmp = nlen; tmp > 15; tmp -= sizeof(union afs_dirent)) { if (next >= AFS_DIRENT_PER_BLOCK) { - _debug("ENT[%Zu.%u]:" + _debug("ENT[%zu.%u]:" " %u travelled beyond end dir block" - " (len %u/%Zu)", + " (len %u/%zu)", blkoff / sizeof(union afs_dir_block), offset, next, tmp, nlen); return -EIO; } if (!(block->pagehdr.bitmap[next / 8] & (1 << (next % 8)))) { - _debug("ENT[%Zu.%u]:" - " %u unmarked extension (len %u/%Zu)", + _debug("ENT[%zu.%u]:" + " %u unmarked extension (len %u/%zu)", blkoff / sizeof(union afs_dir_block), offset, next, tmp, nlen); return -EIO; } - _debug("ENT[%Zu.%u]: ext %u/%Zu", + _debug("ENT[%zu.%u]: ext %u/%zu", blkoff / sizeof(union afs_dir_block), next, tmp, nlen); next++; diff --git a/fs/afs/file.c b/fs/afs/file.c index 6344aee4ac4b..ba7b71fba34b 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -16,6 +16,7 @@ #include <linux/pagemap.h> #include <linux/writeback.h> #include <linux/gfp.h> +#include <linux/task_io_accounting_ops.h> #include "internal.h" static int afs_readpage(struct file *file, struct page *page); @@ -101,6 +102,21 @@ int afs_release(struct inode *inode, struct file *file) return 0; } +/* + * Dispose of a ref to a read record. + */ +void afs_put_read(struct afs_read *req) +{ + int i; + + if (atomic_dec_and_test(&req->usage)) { + for (i = 0; i < req->nr_pages; i++) + if (req->pages[i]) + put_page(req->pages[i]); + kfree(req); + } +} + #ifdef CONFIG_AFS_FSCACHE /* * deal with notification that a page was read from the cache @@ -126,9 +142,8 @@ int afs_page_filler(void *data, struct page *page) { struct inode *inode = page->mapping->host; struct afs_vnode *vnode = AFS_FS_I(inode); + struct afs_read *req; struct key *key = data; - size_t len; - off_t offset; int ret; _enter("{%x},{%lu},{%lu}", key_serial(key), inode->i_ino, page->index); @@ -164,12 +179,23 @@ int afs_page_filler(void *data, struct page *page) _debug("cache said ENOBUFS"); default: go_on: - offset = page->index << PAGE_SHIFT; - len = min_t(size_t, i_size_read(inode) - offset, PAGE_SIZE); + req = kzalloc(sizeof(struct afs_read) + sizeof(struct page *), + GFP_KERNEL); + if (!req) + goto enomem; + + atomic_set(&req->usage, 1); + req->pos = (loff_t)page->index << PAGE_SHIFT; + req->len = min_t(size_t, i_size_read(inode) - req->pos, + PAGE_SIZE); + req->nr_pages = 1; + req->pages[0] = page; + get_page(page); /* read the contents of the file from the server into the * page */ - ret = afs_vnode_fetch_data(vnode, key, offset, len, page); + ret = afs_vnode_fetch_data(vnode, key, req); + afs_put_read(req); if (ret < 0) { if (ret == -ENOENT) { _debug("got NOENT from server" @@ -201,6 +227,8 @@ int afs_page_filler(void *data, struct page *page) _leave(" = 0"); return 0; +enomem: + ret = -ENOMEM; error: SetPageError(page); unlock_page(page); @@ -235,6 +263,131 @@ static int afs_readpage(struct file *file, struct page *page) } /* + * Make pages available as they're filled. + */ +static void afs_readpages_page_done(struct afs_call *call, struct afs_read *req) +{ +#ifdef CONFIG_AFS_FSCACHE + struct afs_vnode *vnode = call->reply; +#endif + struct page *page = req->pages[req->index]; + + req->pages[req->index] = NULL; + SetPageUptodate(page); + + /* send the page to the cache */ +#ifdef CONFIG_AFS_FSCACHE + if (PageFsCache(page) && + fscache_write_page(vnode->cache, page, GFP_KERNEL) != 0) { + fscache_uncache_page(vnode->cache, page); + BUG_ON(PageFsCache(page)); + } +#endif + unlock_page(page); + put_page(page); +} + +/* + * Read a contiguous set of pages. + */ +static int afs_readpages_one(struct file *file, struct address_space *mapping, + struct list_head *pages) +{ + struct afs_vnode *vnode = AFS_FS_I(mapping->host); + struct afs_read *req; + struct list_head *p; + struct page *first, *page; + struct key *key = file->private_data; + pgoff_t index; + int ret, n, i; + + /* Count the number of contiguous pages at the front of the list. Note + * that the list goes prev-wards rather than next-wards. + */ + first = list_entry(pages->prev, struct page, lru); + index = first->index + 1; + n = 1; + for (p = first->lru.prev; p != pages; p = p->prev) { + page = list_entry(p, struct page, lru); + if (page->index != index) + break; + index++; + n++; + } + + req = kzalloc(sizeof(struct afs_read) + sizeof(struct page *) * n, + GFP_NOFS); + if (!req) + return -ENOMEM; + + atomic_set(&req->usage, 1); + req->page_done = afs_readpages_page_done; + req->pos = first->index; + req->pos <<= PAGE_SHIFT; + + /* Transfer the pages to the request. We add them in until one fails + * to add to the LRU and then we stop (as that'll make a hole in the + * contiguous run. + * + * Note that it's possible for the file size to change whilst we're + * doing this, but we rely on the server returning less than we asked + * for if the file shrank. We also rely on this to deal with a partial + * page at the end of the file. + */ + do { + page = list_entry(pages->prev, struct page, lru); + list_del(&page->lru); + index = page->index; + if (add_to_page_cache_lru(page, mapping, index, + readahead_gfp_mask(mapping))) { +#ifdef CONFIG_AFS_FSCACHE + fscache_uncache_page(vnode->cache, page); +#endif + put_page(page); + break; + } + + req->pages[req->nr_pages++] = page; + req->len += PAGE_SIZE; + } while (req->nr_pages < n); + + if (req->nr_pages == 0) { + kfree(req); + return 0; + } + + ret = afs_vnode_fetch_data(vnode, key, req); + if (ret < 0) + goto error; + + task_io_account_read(PAGE_SIZE * req->nr_pages); + afs_put_read(req); + return 0; + +error: + if (ret == -ENOENT) { + _debug("got NOENT from server" + " - marking file deleted and stale"); + set_bit(AFS_VNODE_DELETED, &vnode->flags); + ret = -ESTALE; + } + + for (i = 0; i < req->nr_pages; i++) { + page = req->pages[i]; + if (page) { +#ifdef CONFIG_AFS_FSCACHE + fscache_uncache_page(vnode->cache, page); +#endif + SetPageError(page); + unlock_page(page); + } + } + + afs_put_read(req); + return ret; +} + +/* * read a set of pages */ static int afs_readpages(struct file *file, struct address_space *mapping, @@ -287,8 +440,11 @@ static int afs_readpages(struct file *file, struct address_space *mapping, return ret; } - /* load the missing pages from the network */ - ret = read_cache_pages(mapping, pages, afs_page_filler, key); + while (!list_empty(pages)) { + ret = afs_readpages_one(file, mapping, pages); + if (ret < 0) + break; + } _leave(" = %d [netting]", ret); return ret; diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c index 31c616ab9b40..ac8e766978dc 100644 --- a/fs/afs/fsclient.c +++ b/fs/afs/fsclient.c @@ -275,7 +275,7 @@ int afs_fs_fetch_file_status(struct afs_server *server, struct key *key, struct afs_vnode *vnode, struct afs_volsync *volsync, - const struct afs_wait_mode *wait_mode) + bool async) { struct afs_call *call; __be32 *bp; @@ -300,7 +300,7 @@ int afs_fs_fetch_file_status(struct afs_server *server, bp[2] = htonl(vnode->fid.vnode); bp[3] = htonl(vnode->fid.unique); - return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode); + return afs_make_call(&server->addr, call, GFP_NOFS, async); } /* @@ -309,15 +309,19 @@ int afs_fs_fetch_file_status(struct afs_server *server, static int afs_deliver_fs_fetch_data(struct afs_call *call) { struct afs_vnode *vnode = call->reply; + struct afs_read *req = call->reply3; const __be32 *bp; - struct page *page; + unsigned int size; void *buffer; int ret; - _enter("{%u}", call->unmarshall); + _enter("{%u,%zu/%u;%u/%llu}", + call->unmarshall, call->offset, call->count, + req->remain, req->actual_len); switch (call->unmarshall) { case 0: + req->actual_len = 0; call->offset = 0; call->unmarshall++; if (call->operation_ID != FSFETCHDATA64) { @@ -334,10 +338,8 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) if (ret < 0) return ret; - call->count = ntohl(call->tmp); - _debug("DATA length MSW: %u", call->count); - if (call->count > 0) - return -EBADMSG; + req->actual_len = ntohl(call->tmp); + req->actual_len <<= 32; call->offset = 0; call->unmarshall++; @@ -349,26 +351,52 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) if (ret < 0) return ret; - call->count = ntohl(call->tmp); - _debug("DATA length: %u", call->count); - if (call->count > PAGE_SIZE) + req->actual_len |= ntohl(call->tmp); + _debug("DATA length: %llu", req->actual_len); + /* Check that the server didn't want to send us extra. We + * might want to just discard instead, but that requires + * cooperation from AF_RXRPC. + */ + if (req->actual_len > req->len) return -EBADMSG; - call->offset = 0; + + req->remain = req->actual_len; + call->offset = req->pos & (PAGE_SIZE - 1); + req->index = 0; + if (req->actual_len == 0) + goto no_more_data; call->unmarshall++; + begin_page: + if (req->remain > PAGE_SIZE - call->offset) + size = PAGE_SIZE - call->offset; + else + size = req->remain; + call->count = call->offset + size; + ASSERTCMP(call->count, <=, PAGE_SIZE); + req->remain -= size; + /* extract the returned data */ case 3: - _debug("extract data"); - if (call->count > 0) { - page = call->reply3; - buffer = kmap(page); - ret = afs_extract_data(call, buffer, - call->count, true); - kunmap(page); - if (ret < 0) - return ret; + _debug("extract data %u/%llu %zu/%u", + req->remain, req->actual_len, call->offset, call->count); + + buffer = kmap(req->pages[req->index]); + ret = afs_extract_data(call, buffer, call->count, true); + kunmap(req->pages[req->index]); + if (ret < 0) + return ret; + if (call->offset == PAGE_SIZE) { + if (req->page_done) + req->page_done(call, req); + if (req->remain > 0) { + req->index++; + call->offset = 0; + goto begin_page; + } } + no_more_data: call->offset = 0; call->unmarshall++; @@ -393,17 +421,25 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) } if (call->count < PAGE_SIZE) { - _debug("clear"); - page = call->reply3; - buffer = kmap(page); + buffer = kmap(req->pages[req->index]); memset(buffer + call->count, 0, PAGE_SIZE - call->count); - kunmap(page); + kunmap(req->pages[req->index]); + if (req->page_done) + req->page_done(call, req); } _leave(" = 0 [done]"); return 0; } +static void afs_fetch_data_destructor(struct afs_call *call) +{ + struct afs_read *req = call->reply3; + + afs_put_read(req); + afs_flat_call_destructor(call); +} + /* * FS.FetchData operation type */ @@ -411,14 +447,14 @@ static const struct afs_call_type afs_RXFSFetchData = { .name = "FS.FetchData", .deliver = afs_deliver_fs_fetch_data, .abort_to_error = afs_abort_to_error, - .destructor = afs_flat_call_destructor, + .destructor = afs_fetch_data_destructor, }; static const struct afs_call_type afs_RXFSFetchData64 = { .name = "FS.FetchData64", .deliver = afs_deliver_fs_fetch_data, .abort_to_error = afs_abort_to_error, - .destructor = afs_flat_call_destructor, + .destructor = afs_fetch_data_destructor, }; /* @@ -427,17 +463,14 @@ static const struct afs_call_type afs_RXFSFetchData64 = { static int afs_fs_fetch_data64(struct afs_server *server, struct key *key, struct afs_vnode *vnode, - off_t offset, size_t length, - struct page *buffer, - const struct afs_wait_mode *wait_mode) + struct afs_read *req, + bool async) { struct afs_call *call; __be32 *bp; _enter(""); - ASSERTCMP(length, <, ULONG_MAX); - call = afs_alloc_flat_call(&afs_RXFSFetchData64, 32, (21 + 3 + 6) * 4); if (!call) return -ENOMEM; @@ -445,7 +478,7 @@ static int afs_fs_fetch_data64(struct afs_server *server, call->key = key; call->reply = vnode; call->reply2 = NULL; /* volsync */ - call->reply3 = buffer; + call->reply3 = req; call->service_id = FS_SERVICE; call->port = htons(AFS_FS_PORT); call->operation_ID = FSFETCHDATA64; @@ -456,12 +489,13 @@ static int afs_fs_fetch_data64(struct afs_server *server, bp[1] = htonl(vnode->fid.vid); bp[2] = htonl(vnode->fid.vnode); bp[3] = htonl(vnode->fid.unique); - bp[4] = htonl(upper_32_bits(offset)); - bp[5] = htonl((u32) offset); + bp[4] = htonl(upper_32_bits(req->pos)); + bp[5] = htonl(lower_32_bits(req->pos)); bp[6] = 0; - bp[7] = htonl((u32) length); + bp[7] = htonl(lower_32_bits(req->len)); - return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode); + atomic_inc(&req->usage); + return afs_make_call(&server->addr, call, GFP_NOFS, async); } /* @@ -470,16 +504,16 @@ static int afs_fs_fetch_data64(struct afs_server *server, int afs_fs_fetch_data(struct afs_server *server, struct key *key, struct afs_vnode *vnode, - off_t offset, size_t length, - struct page *buffer, - const struct afs_wait_mode *wait_mode) + struct afs_read *req, + bool async) { struct afs_call *call; __be32 *bp; - if (upper_32_bits(offset) || upper_32_bits(offset + length)) - return afs_fs_fetch_data64(server, key, vnode, offset, length, - buffer, wait_mode); + if (upper_32_bits(req->pos) || + upper_32_bits(req->len) || + upper_32_bits(req->pos + req->len)) + return afs_fs_fetch_data64(server, key, vnode, req, async); _enter(""); @@ -490,7 +524,7 @@ int afs_fs_fetch_data(struct afs_server *server, call->key = key; call->reply = vnode; call->reply2 = NULL; /* volsync */ - call->reply3 = buffer; + call->reply3 = req; call->service_id = FS_SERVICE; call->port = htons(AFS_FS_PORT); call->operation_ID = FSFETCHDATA; @@ -501,10 +535,11 @@ int afs_fs_fetch_data(struct afs_server *server, bp[1] = htonl(vnode->fid.vid); bp[2] = htonl(vnode->fid.vnode); bp[3] = htonl(vnode->fid.unique); - bp[4] = htonl(offset); - bp[5] = htonl(length); + bp[4] = htonl(lower_32_bits(req->pos)); + bp[5] = htonl(lower_32_bits(req->len)); - return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode); + atomic_inc(&req->usage); + return afs_make_call(&server->addr, call, GFP_NOFS, async); } /* @@ -533,7 +568,7 @@ static const struct afs_call_type afs_RXFSGiveUpCallBacks = { * - the callbacks are held in the server->cb_break ring */ int afs_fs_give_up_callbacks(struct afs_server *server, - const struct afs_wait_mode *wait_mode) + bool async) { struct afs_call *call; size_t ncallbacks; @@ -587,7 +622,7 @@ int afs_fs_give_up_callbacks(struct afs_server *server, ASSERT(ncallbacks > 0); wake_up_nr(&server->cb_break_waitq, ncallbacks); - return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode); + return afs_make_call(&server->addr, call, GFP_NOFS, async); } /* @@ -638,7 +673,7 @@ int afs_fs_create(struct afs_server *server, struct afs_fid *newfid, struct afs_file_status *newstatus, struct afs_callback *newcb, - const struct afs_wait_mode *wait_mode) + bool async) { struct afs_call *call; size_t namesz, reqsz, padsz; @@ -683,7 +718,7 @@ int afs_fs_create(struct afs_server *server, *bp++ = htonl(mode & S_IALLUGO); /* unix mode */ *bp++ = 0; /* segment size */ - return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode); + return afs_make_call(&server->addr, call, GFP_NOFS, async); } /* @@ -728,7 +763,7 @@ int afs_fs_remove(struct afs_server *server, struct afs_vnode *vnode, const char *name, bool isdir, - const struct afs_wait_mode *wait_mode) + bool async) { struct afs_call *call; size_t namesz, reqsz, padsz; @@ -763,7 +798,7 @@ int afs_fs_remove(struct afs_server *server, bp = (void *) bp + padsz; } - return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode); + return afs_make_call(&server->addr, call, GFP_NOFS, async); } /* @@ -809,7 +844,7 @@ int afs_fs_link(struct afs_server *server, struct afs_vnode *dvnode, struct afs_vnode *vnode, const char *name, - const struct afs_wait_mode *wait_mode) + bool async) { struct afs_call *call; size_t namesz, reqsz, padsz; @@ -848,7 +883,7 @@ int afs_fs_link(struct afs_server *server, *bp++ = htonl(vnode->fid.vnode); *bp++ = htonl(vnode->fid.unique); - return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode); + return afs_make_call(&server->addr, call, GFP_NOFS, async); } /* @@ -897,7 +932,7 @@ int afs_fs_symlink(struct afs_server *server, const char *contents, struct afs_fid *newfid, struct afs_file_status *newstatus, - const struct afs_wait_mode *wait_mode) + bool async) { struct afs_call *call; size_t namesz, reqsz, padsz, c_namesz, c_padsz; @@ -952,7 +987,7 @@ int afs_fs_symlink(struct afs_server *server, *bp++ = htonl(S_IRWXUGO); /* unix mode */ *bp++ = 0; /* segment size */ - return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode); + return afs_make_call(&server->addr, call, GFP_NOFS, async); } /* @@ -1001,7 +1036,7 @@ int afs_fs_rename(struct afs_server *server, const char *orig_name, struct afs_vnode *new_dvnode, const char *new_name, - const struct afs_wait_mode *wait_mode) + bool async) { struct afs_call *call; size_t reqsz, o_namesz, o_padsz, n_namesz, n_padsz; @@ -1055,7 +1090,7 @@ int afs_fs_rename(struct afs_server *server, bp = (void *) bp + n_padsz; } - return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode); + return afs_make_call(&server->addr, call, GFP_NOFS, async); } /* @@ -1110,7 +1145,7 @@ static int afs_fs_store_data64(struct afs_server *server, pgoff_t first, pgoff_t last, unsigned offset, unsigned to, loff_t size, loff_t pos, loff_t i_size, - const struct afs_wait_mode *wait_mode) + bool async) { struct afs_vnode *vnode = wb->vnode; struct afs_call *call; @@ -1159,7 +1194,7 @@ static int afs_fs_store_data64(struct afs_server *server, *bp++ = htonl(i_size >> 32); *bp++ = htonl((u32) i_size); - return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode); + return afs_make_call(&server->addr, call, GFP_NOFS, async); } /* @@ -1168,7 +1203,7 @@ static int afs_fs_store_data64(struct afs_server *server, int afs_fs_store_data(struct afs_server *server, struct afs_writeback *wb, pgoff_t first, pgoff_t last, unsigned offset, unsigned to, - const struct afs_wait_mode *wait_mode) + bool async) { struct afs_vnode *vnode = wb->vnode; struct afs_call *call; @@ -1194,7 +1229,7 @@ int afs_fs_store_data(struct afs_server *server, struct afs_writeback *wb, if (pos >> 32 || i_size >> 32 || size >> 32 || (pos + size) >> 32) return afs_fs_store_data64(server, wb, first, last, offset, to, - size, pos, i_size, wait_mode); + size, pos, i_size, async); call = afs_alloc_flat_call(&afs_RXFSStoreData, (4 + 6 + 3) * 4, @@ -1233,7 +1268,7 @@ int afs_fs_store_data(struct afs_server *server, struct afs_writeback *wb, *bp++ = htonl(size); *bp++ = htonl(i_size); - return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode); + return afs_make_call(&server->addr, call, GFP_NOFS, async); } /* @@ -1295,7 +1330,7 @@ static const struct afs_call_type afs_RXFSStoreData64_as_Status = { */ static int afs_fs_setattr_size64(struct afs_server *server, struct key *key, struct afs_vnode *vnode, struct iattr *attr, - const struct afs_wait_mode *wait_mode) + bool async) { struct afs_call *call; __be32 *bp; @@ -1334,7 +1369,7 @@ static int afs_fs_setattr_size64(struct afs_server *server, struct key *key, *bp++ = htonl(attr->ia_size >> 32); /* new file length */ *bp++ = htonl((u32) attr->ia_size); - return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode); + return afs_make_call(&server->addr, call, GFP_NOFS, async); } /* @@ -1343,7 +1378,7 @@ static int afs_fs_setattr_size64(struct afs_server *server, struct key *key, */ static int afs_fs_setattr_size(struct afs_server *server, struct key *key, struct afs_vnode *vnode, struct iattr *attr, - const struct afs_wait_mode *wait_mode) + bool async) { struct afs_call *call; __be32 *bp; @@ -1354,7 +1389,7 @@ static int afs_fs_setattr_size(struct afs_server *server, struct key *key, ASSERT(attr->ia_valid & ATTR_SIZE); if (attr->ia_size >> 32) return afs_fs_setattr_size64(server, key, vnode, attr, - wait_mode); + async); call = afs_alloc_flat_call(&afs_RXFSStoreData_as_Status, (4 + 6 + 3) * 4, @@ -1382,7 +1417,7 @@ static int afs_fs_setattr_size(struct afs_server *server, struct key *key, *bp++ = 0; /* size of write */ *bp++ = htonl(attr->ia_size); /* new file length */ - return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode); + return afs_make_call(&server->addr, call, GFP_NOFS, async); } /* @@ -1391,14 +1426,14 @@ static int afs_fs_setattr_size(struct afs_server *server, struct key *key, */ int afs_fs_setattr(struct afs_server *server, struct key *key, struct afs_vnode *vnode, struct iattr *attr, - const struct afs_wait_mode *wait_mode) + bool async) { struct afs_call *call; __be32 *bp; if (attr->ia_valid & ATTR_SIZE) return afs_fs_setattr_size(server, key, vnode, attr, - wait_mode); + async); _enter(",%x,{%x:%u},,", key_serial(key), vnode->fid.vid, vnode->fid.vnode); @@ -1424,7 +1459,7 @@ int afs_fs_setattr(struct afs_server *server, struct key *key, xdr_encode_AFS_StoreStatus(&bp, attr); - return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode); + return afs_make_call(&server->addr, call, GFP_NOFS, async); } /* @@ -1626,7 +1661,7 @@ int afs_fs_get_volume_status(struct afs_server *server, struct key *key, struct afs_vnode *vnode, struct afs_volume_status *vs, - const struct afs_wait_mode *wait_mode) + bool async) { struct afs_call *call; __be32 *bp; @@ -1656,7 +1691,7 @@ int afs_fs_get_volume_status(struct afs_server *server, bp[0] = htonl(FSGETVOLUMESTATUS); bp[1] = htonl(vnode->fid.vid); - return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode); + return afs_make_call(&server->addr, call, GFP_NOFS, async); } /* @@ -1718,7 +1753,7 @@ int afs_fs_set_lock(struct afs_server *server, struct key *key, struct afs_vnode *vnode, afs_lock_type_t type, - const struct afs_wait_mode *wait_mode) + bool async) { struct afs_call *call; __be32 *bp; @@ -1742,7 +1777,7 @@ int afs_fs_set_lock(struct afs_server *server, *bp++ = htonl(vnode->fid.unique); *bp++ = htonl(type); - return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode); + return afs_make_call(&server->addr, call, GFP_NOFS, async); } /* @@ -1751,7 +1786,7 @@ int afs_fs_set_lock(struct afs_server *server, int afs_fs_extend_lock(struct afs_server *server, struct key *key, struct afs_vnode *vnode, - const struct afs_wait_mode *wait_mode) + bool async) { struct afs_call *call; __be32 *bp; @@ -1774,7 +1809,7 @@ int afs_fs_extend_lock(struct afs_server *server, *bp++ = htonl(vnode->fid.vnode); *bp++ = htonl(vnode->fid.unique); - return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode); + return afs_make_call(&server->addr, call, GFP_NOFS, async); } /* @@ -1783,7 +1818,7 @@ int afs_fs_extend_lock(struct afs_server *server, int afs_fs_release_lock(struct afs_server *server, struct key *key, struct afs_vnode *vnode, - const struct afs_wait_mode *wait_mode) + bool async) { struct afs_call *call; __be32 *bp; @@ -1806,5 +1841,5 @@ int afs_fs_release_lock(struct afs_server *server, *bp++ = htonl(vnode->fid.vnode); *bp++ = htonl(vnode->fid.unique); - return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode); + return afs_make_call(&server->addr, call, GFP_NOFS, async); } diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 535a38d2c1d0..8acf3670e756 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -19,6 +19,7 @@ #include <linux/sched.h> #include <linux/fscache.h> #include <linux/backing-dev.h> +#include <linux/uuid.h> #include <net/af_rxrpc.h> #include "afs.h" @@ -51,31 +52,22 @@ struct afs_mount_params { struct key *key; /* key to use for secure mounting */ }; -/* - * definition of how to wait for the completion of an operation - */ -struct afs_wait_mode { - /* RxRPC received message notification */ - rxrpc_notify_rx_t notify_rx; - - /* synchronous call waiter and call dispatched notification */ - int (*wait)(struct afs_call *call); - - /* asynchronous call completion */ - void (*async_complete)(void *reply, int error); +enum afs_call_state { + AFS_CALL_REQUESTING, /* request is being sent for outgoing call */ + AFS_CALL_AWAIT_REPLY, /* awaiting reply to outgoing call */ + AFS_CALL_AWAIT_OP_ID, /* awaiting op ID on incoming call */ + AFS_CALL_AWAIT_REQUEST, /* awaiting request data on incoming call */ + AFS_CALL_REPLYING, /* replying to incoming call */ + AFS_CALL_AWAIT_ACK, /* awaiting final ACK of incoming call */ + AFS_CALL_COMPLETE, /* Completed or failed */ }; - -extern const struct afs_wait_mode afs_sync_call; -extern const struct afs_wait_mode afs_async_call; - /* * a record of an in-progress RxRPC call */ struct afs_call { const struct afs_call_type *type; /* type of call */ - const struct afs_wait_mode *wait_mode; /* completion wait mode */ wait_queue_head_t waitq; /* processes awaiting completion */ - struct work_struct async_work; /* asynchronous work processor */ + struct work_struct async_work; /* async I/O processor */ struct work_struct work; /* actual work processor */ struct rxrpc_call *rxcall; /* RxRPC call handle */ struct key *key; /* security for this call */ @@ -91,15 +83,8 @@ struct afs_call { pgoff_t first; /* first page in mapping to deal with */ pgoff_t last; /* last page in mapping to deal with */ size_t offset; /* offset into received data store */ - enum { /* call state */ - AFS_CALL_REQUESTING, /* request is being sent for outgoing call */ - AFS_CALL_AWAIT_REPLY, /* awaiting reply to outgoing call */ - AFS_CALL_AWAIT_OP_ID, /* awaiting op ID on incoming call */ - AFS_CALL_AWAIT_REQUEST, /* awaiting request data on incoming call */ - AFS_CALL_REPLYING, /* replying to incoming call */ - AFS_CALL_AWAIT_ACK, /* awaiting final ACK of incoming call */ - AFS_CALL_COMPLETE, /* Completed or failed */ - } state; + atomic_t usage; + enum afs_call_state state; int error; /* error code */ u32 abort_code; /* Remote abort ID or 0 */ unsigned request_size; /* size of request data */ @@ -110,6 +95,7 @@ struct afs_call { bool incoming; /* T if incoming call */ bool send_pages; /* T if data from mapping should be sent */ bool need_attention; /* T if RxRPC poked us */ + bool async; /* T if asynchronous */ u16 service_id; /* RxRPC service ID to call */ __be16 port; /* target UDP port */ u32 operation_ID; /* operation ID for an incoming call */ @@ -131,6 +117,25 @@ struct afs_call_type { /* clean up a call */ void (*destructor)(struct afs_call *call); + + /* Work function */ + void (*work)(struct work_struct *work); +}; + +/* + * Record of an outstanding read operation on a vnode. + */ +struct afs_read { + loff_t pos; /* Where to start reading */ + loff_t len; /* How much to read */ + loff_t actual_len; /* How much we're actually getting */ + atomic_t usage; + unsigned int remain; /* Amount remaining */ + unsigned int index; /* Which page we're reading into */ + unsigned int pg_offset; /* Offset in page we're at */ + unsigned int nr_pages; + void (*page_done)(struct afs_call *, struct afs_read *); + struct page *pages[]; }; /* @@ -403,30 +408,6 @@ struct afs_interface { unsigned mtu; /* MTU of interface */ }; -/* - * UUID definition [internet draft] - * - the timestamp is a 60-bit value, split 32/16/12, and goes in 100ns - * increments since midnight 15th October 1582 - * - add AFS_UUID_TO_UNIX_TIME to convert unix time in 100ns units to UUID - * time - * - the clock sequence is a 14-bit counter to avoid duplicate times - */ -struct afs_uuid { - u32 time_low; /* low part of timestamp */ - u16 time_mid; /* mid part of timestamp */ - u16 time_hi_and_version; /* high part of timestamp and version */ -#define AFS_UUID_TO_UNIX_TIME 0x01b21dd213814000ULL -#define AFS_UUID_TIMEHI_MASK 0x0fff -#define AFS_UUID_VERSION_TIME 0x1000 /* time-based UUID */ -#define AFS_UUID_VERSION_NAME 0x3000 /* name-based UUID */ -#define AFS_UUID_VERSION_RANDOM 0x4000 /* (pseudo-)random generated UUID */ - u8 clock_seq_hi_and_reserved; /* clock seq hi and variant */ -#define AFS_UUID_CLOCKHI_MASK 0x3f -#define AFS_UUID_VARIANT_STD 0x80 - u8 clock_seq_low; /* clock seq low */ - u8 node[6]; /* spatially unique node ID (MAC addr) */ -}; - /*****************************************************************************/ /* * cache.c @@ -494,6 +475,7 @@ extern const struct file_operations afs_file_operations; extern int afs_open(struct inode *, struct file *); extern int afs_release(struct inode *, struct file *); extern int afs_page_filler(void *, struct page *); +extern void afs_put_read(struct afs_read *); /* * flock.c @@ -509,50 +491,37 @@ extern int afs_flock(struct file *, int, struct file_lock *); */ extern int afs_fs_fetch_file_status(struct afs_server *, struct key *, struct afs_vnode *, struct afs_volsync *, - const struct afs_wait_mode *); -extern int afs_fs_give_up_callbacks(struct afs_server *, - const struct afs_wait_mode *); + bool); +extern int afs_fs_give_up_callbacks(struct afs_server *, bool); extern int afs_fs_fetch_data(struct afs_server *, struct key *, - struct afs_vnode *, off_t, size_t, struct page *, - const struct afs_wait_mode *); + struct afs_vnode *, struct afs_read *, bool); extern int afs_fs_create(struct afs_server *, struct key *, struct afs_vnode *, const char *, umode_t, struct afs_fid *, struct afs_file_status *, - struct afs_callback *, - const struct afs_wait_mode *); + struct afs_callback *, bool); extern int afs_fs_remove(struct afs_server *, struct key *, - struct afs_vnode *, const char *, bool, - const struct afs_wait_mode *); + struct afs_vnode *, const char *, bool, bool); extern int afs_fs_link(struct afs_server *, struct key *, struct afs_vnode *, - struct afs_vnode *, const char *, - const struct afs_wait_mode *); + struct afs_vnode *, const char *, bool); extern int afs_fs_symlink(struct afs_server *, struct key *, struct afs_vnode *, const char *, const char *, - struct afs_fid *, struct afs_file_status *, - const struct afs_wait_mode *); + struct afs_fid *, struct afs_file_status *, bool); extern int afs_fs_rename(struct afs_server *, struct key *, struct afs_vnode *, const char *, - struct afs_vnode *, const char *, - const struct afs_wait_mode *); + struct afs_vnode *, const char *, bool); extern int afs_fs_store_data(struct afs_server *, struct afs_writeback *, - pgoff_t, pgoff_t, unsigned, unsigned, - const struct afs_wait_mode *); + pgoff_t, pgoff_t, unsigned, unsigned, bool); extern int afs_fs_setattr(struct afs_server *, struct key *, - struct afs_vnode *, struct iattr *, - const struct afs_wait_mode *); + struct afs_vnode *, struct iattr *, bool); extern int afs_fs_get_volume_status(struct afs_server *, struct key *, struct afs_vnode *, - struct afs_volume_status *, - const struct afs_wait_mode *); + struct afs_volume_status *, bool); extern int afs_fs_set_lock(struct afs_server *, struct key *, - struct afs_vnode *, afs_lock_type_t, - const struct afs_wait_mode *); + struct afs_vnode *, afs_lock_type_t, bool); extern int afs_fs_extend_lock(struct afs_server *, struct key *, - struct afs_vnode *, - const struct afs_wait_mode *); + struct afs_vnode *, bool); extern int afs_fs_release_lock(struct afs_server *, struct key *, - struct afs_vnode *, - const struct afs_wait_mode *); + struct afs_vnode *, bool); /* * inode.c @@ -573,7 +542,7 @@ extern int afs_drop_inode(struct inode *); * main.c */ extern struct workqueue_struct *afs_wq; -extern struct afs_uuid afs_uuid; +extern struct uuid_v1 afs_uuid; /* * misc.c @@ -592,6 +561,11 @@ extern int afs_mntpt_check_symlink(struct afs_vnode *, struct key *); extern void afs_mntpt_kill_timer(void); /* + * netdevices.c + */ +extern int afs_get_ipv4_interfaces(struct afs_interface *, size_t, bool); + +/* * proc.c */ extern int afs_proc_init(void); @@ -603,11 +577,13 @@ extern void afs_proc_cell_remove(struct afs_cell *); * rxrpc.c */ extern struct socket *afs_socket; +extern atomic_t afs_outstanding_calls; extern int afs_open_socket(void); extern void afs_close_socket(void); -extern int afs_make_call(struct in_addr *, struct afs_call *, gfp_t, - const struct afs_wait_mode *); +extern void afs_put_call(struct afs_call *); +extern int afs_queue_call_work(struct afs_call *); +extern int afs_make_call(struct in_addr *, struct afs_call *, gfp_t, bool); extern struct afs_call *afs_alloc_flat_call(const struct afs_call_type *, size_t, size_t); extern void afs_flat_call_destructor(struct afs_call *); @@ -653,21 +629,14 @@ extern int afs_fs_init(void); extern void afs_fs_exit(void); /* - * use-rtnetlink.c - */ -extern int afs_get_ipv4_interfaces(struct afs_interface *, size_t, bool); -extern int afs_get_MAC_address(u8 *, size_t); - -/* * vlclient.c */ extern int afs_vl_get_entry_by_name(struct in_addr *, struct key *, const char *, struct afs_cache_vlocation *, - const struct afs_wait_mode *); + bool); extern int afs_vl_get_entry_by_id(struct in_addr *, struct key *, afs_volid_t, afs_voltype_t, - struct afs_cache_vlocation *, - const struct afs_wait_mode *); + struct afs_cache_vlocation *, bool); /* * vlocation.c @@ -699,7 +668,7 @@ extern void afs_vnode_finalise_status_update(struct afs_vnode *, extern int afs_vnode_fetch_status(struct afs_vnode *, struct afs_vnode *, struct key *); extern int afs_vnode_fetch_data(struct afs_vnode *, struct key *, - off_t, size_t, struct page *); + struct afs_read *); extern int afs_vnode_create(struct afs_vnode *, struct key *, const char *, umode_t, struct afs_fid *, struct afs_file_status *, struct afs_callback *, struct afs_server **); @@ -756,6 +725,8 @@ extern int afs_fsync(struct file *, loff_t, loff_t, int); /* * debug tracing */ +#include <trace/events/afs.h> + extern unsigned afs_debug; #define dbgprintk(FMT,...) \ diff --git a/fs/afs/main.c b/fs/afs/main.c index 0b187ef3b5b7..51d7d17bca57 100644 --- a/fs/afs/main.c +++ b/fs/afs/main.c @@ -15,6 +15,7 @@ #include <linux/completion.h> #include <linux/sched.h> #include <linux/random.h> +#define CREATE_TRACE_POINTS #include "internal.h" MODULE_DESCRIPTION("AFS Client File System"); @@ -30,53 +31,10 @@ static char *rootcell; module_param(rootcell, charp, 0); MODULE_PARM_DESC(rootcell, "root AFS cell name and VL server IP addr list"); -struct afs_uuid afs_uuid; +struct uuid_v1 afs_uuid; struct workqueue_struct *afs_wq; /* - * get a client UUID - */ -static int __init afs_get_client_UUID(void) -{ - struct timespec ts; - u64 uuidtime; - u16 clockseq; - int ret; - - /* read the MAC address of one of the external interfaces and construct - * a UUID from it */ - ret = afs_get_MAC_address(afs_uuid.node, sizeof(afs_uuid.node)); - if (ret < 0) - return ret; - - getnstimeofday(&ts); - uuidtime = (u64) ts.tv_sec * 1000 * 1000 * 10; - uuidtime += ts.tv_nsec / 100; - uuidtime += AFS_UUID_TO_UNIX_TIME; - afs_uuid.time_low = uuidtime; - afs_uuid.time_mid = uuidtime >> 32; - afs_uuid.time_hi_and_version = (uuidtime >> 48) & AFS_UUID_TIMEHI_MASK; - afs_uuid.time_hi_and_version |= AFS_UUID_VERSION_TIME; - - get_random_bytes(&clockseq, 2); - afs_uuid.clock_seq_low = clockseq; - afs_uuid.clock_seq_hi_and_reserved = - (clockseq >> 8) & AFS_UUID_CLOCKHI_MASK; - afs_uuid.clock_seq_hi_and_reserved |= AFS_UUID_VARIANT_STD; - - _debug("AFS UUID: %08x-%04x-%04x-%02x%02x-%02x%02x%02x%02x%02x%02x", - afs_uuid.time_low, - afs_uuid.time_mid, - afs_uuid.time_hi_and_version, - afs_uuid.clock_seq_hi_and_reserved, - afs_uuid.clock_seq_low, - afs_uuid.node[0], afs_uuid.node[1], afs_uuid.node[2], - afs_uuid.node[3], afs_uuid.node[4], afs_uuid.node[5]); - - return 0; -} - -/* * initialise the AFS client FS module */ static int __init afs_init(void) @@ -85,9 +43,7 @@ static int __init afs_init(void) printk(KERN_INFO "kAFS: Red Hat AFS client v0.1 registering.\n"); - ret = afs_get_client_UUID(); - if (ret < 0) - return ret; + generate_random_uuid((unsigned char *)&afs_uuid); /* create workqueue */ ret = -ENOMEM; diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c index 81dd075356b9..d4fb0afc0097 100644 --- a/fs/afs/mntpt.c +++ b/fs/afs/mntpt.c @@ -202,7 +202,7 @@ static struct vfsmount *afs_mntpt_do_automount(struct dentry *mntpt) /* try and do the mount */ _debug("--- attempting mount %s -o %s ---", devname, options); - mnt = vfs_kern_mount(&afs_fs_type, 0, devname, options); + mnt = vfs_submount(mntpt, &afs_fs_type, devname, options); _debug("--- mount result %p ---", mnt); free_page((unsigned long) devname); diff --git a/fs/afs/netdevices.c b/fs/afs/netdevices.c index 7ad36506c256..40b2bab3e401 100644 --- a/fs/afs/netdevices.c +++ b/fs/afs/netdevices.c @@ -12,27 +12,6 @@ #include "internal.h" /* - * get a MAC address from a random ethernet interface that has a real one - * - the buffer will normally be 6 bytes in size - */ -int afs_get_MAC_address(u8 *mac, size_t maclen) -{ - struct net_device *dev; - int ret = -ENODEV; - - BUG_ON(maclen != ETH_ALEN); - - rtnl_lock(); - dev = __dev_getfirstbyhwtype(&init_net, ARPHRD_ETHER); - if (dev) { - memcpy(mac, dev->dev_addr, maclen); - ret = 0; - } - rtnl_unlock(); - return ret; -} - -/* * get a list of this system's interface IPv4 addresses, netmasks and MTUs * - maxbufs must be at least 1 * - returns the number of interface records in the buffer diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index 25f05a8d21b1..95f42872b787 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -19,35 +19,16 @@ struct socket *afs_socket; /* my RxRPC socket */ static struct workqueue_struct *afs_async_calls; static struct afs_call *afs_spare_incoming_call; -static atomic_t afs_outstanding_calls; +atomic_t afs_outstanding_calls; -static void afs_free_call(struct afs_call *); static void afs_wake_up_call_waiter(struct sock *, struct rxrpc_call *, unsigned long); static int afs_wait_for_call_to_complete(struct afs_call *); static void afs_wake_up_async_call(struct sock *, struct rxrpc_call *, unsigned long); -static int afs_dont_wait_for_call_to_complete(struct afs_call *); static void afs_process_async_call(struct work_struct *); static void afs_rx_new_call(struct sock *, struct rxrpc_call *, unsigned long); static void afs_rx_discard_new_call(struct rxrpc_call *, unsigned long); static int afs_deliver_cm_op_id(struct afs_call *); -/* synchronous call management */ -const struct afs_wait_mode afs_sync_call = { - .notify_rx = afs_wake_up_call_waiter, - .wait = afs_wait_for_call_to_complete, -}; - -/* asynchronous call management */ -const struct afs_wait_mode afs_async_call = { - .notify_rx = afs_wake_up_async_call, - .wait = afs_dont_wait_for_call_to_complete, -}; - -/* asynchronous incoming call management */ -static const struct afs_wait_mode afs_async_incoming_call = { - .notify_rx = afs_wake_up_async_call, -}; - /* asynchronous incoming call initial processing */ static const struct afs_call_type afs_RXCMxxxx = { .name = "CB.xxxx", @@ -130,9 +111,11 @@ void afs_close_socket(void) { _enter(""); + kernel_listen(afs_socket, 0); + flush_workqueue(afs_async_calls); + if (afs_spare_incoming_call) { - atomic_inc(&afs_outstanding_calls); - afs_free_call(afs_spare_incoming_call); + afs_put_call(afs_spare_incoming_call); afs_spare_incoming_call = NULL; } @@ -141,7 +124,6 @@ void afs_close_socket(void) TASK_UNINTERRUPTIBLE); _debug("no outstanding calls"); - flush_workqueue(afs_async_calls); kernel_sock_shutdown(afs_socket, SHUT_RDWR); flush_workqueue(afs_async_calls); sock_release(afs_socket); @@ -152,44 +134,79 @@ void afs_close_socket(void) } /* - * free a call + * Allocate a call. */ -static void afs_free_call(struct afs_call *call) +static struct afs_call *afs_alloc_call(const struct afs_call_type *type, + gfp_t gfp) { - _debug("DONE %p{%s} [%d]", - call, call->type->name, atomic_read(&afs_outstanding_calls)); + struct afs_call *call; + int o; - ASSERTCMP(call->rxcall, ==, NULL); - ASSERT(!work_pending(&call->async_work)); - ASSERT(call->type->name != NULL); + call = kzalloc(sizeof(*call), gfp); + if (!call) + return NULL; - kfree(call->request); - kfree(call); + call->type = type; + atomic_set(&call->usage, 1); + INIT_WORK(&call->async_work, afs_process_async_call); + init_waitqueue_head(&call->waitq); - if (atomic_dec_and_test(&afs_outstanding_calls)) - wake_up_atomic_t(&afs_outstanding_calls); + o = atomic_inc_return(&afs_outstanding_calls); + trace_afs_call(call, afs_call_trace_alloc, 1, o, + __builtin_return_address(0)); + return call; } /* - * End a call but do not free it + * Dispose of a reference on a call. */ -static void afs_end_call_nofree(struct afs_call *call) +void afs_put_call(struct afs_call *call) { - if (call->rxcall) { - rxrpc_kernel_end_call(afs_socket, call->rxcall); - call->rxcall = NULL; + int n = atomic_dec_return(&call->usage); + int o = atomic_read(&afs_outstanding_calls); + + trace_afs_call(call, afs_call_trace_put, n + 1, o, + __builtin_return_address(0)); + + ASSERTCMP(n, >=, 0); + if (n == 0) { + ASSERT(!work_pending(&call->async_work)); + ASSERT(call->type->name != NULL); + + if (call->rxcall) { + rxrpc_kernel_end_call(afs_socket, call->rxcall); + call->rxcall = NULL; + } + if (call->type->destructor) + call->type->destructor(call); + + kfree(call->request); + kfree(call); + + o = atomic_dec_return(&afs_outstanding_calls); + trace_afs_call(call, afs_call_trace_free, 0, o, + __builtin_return_address(0)); + if (o == 0) + wake_up_atomic_t(&afs_outstanding_calls); } - if (call->type->destructor) - call->type->destructor(call); } /* - * End a call and free it + * Queue the call for actual work. Returns 0 unconditionally for convenience. */ -static void afs_end_call(struct afs_call *call) +int afs_queue_call_work(struct afs_call *call) { - afs_end_call_nofree(call); - afs_free_call(call); + int u = atomic_inc_return(&call->usage); + + trace_afs_call(call, afs_call_trace_work, u, + atomic_read(&afs_outstanding_calls), + __builtin_return_address(0)); + + INIT_WORK(&call->work, call->type->work); + + if (!queue_work(afs_wq, &call->work)) + afs_put_call(call); + return 0; } /* @@ -200,25 +217,19 @@ struct afs_call *afs_alloc_flat_call(const struct afs_call_type *type, { struct afs_call *call; - call = kzalloc(sizeof(*call), GFP_NOFS); + call = afs_alloc_call(type, GFP_NOFS); if (!call) goto nomem_call; - _debug("CALL %p{%s} [%d]", - call, type->name, atomic_read(&afs_outstanding_calls)); - atomic_inc(&afs_outstanding_calls); - - call->type = type; - call->request_size = request_size; - call->reply_max = reply_max; - if (request_size) { + call->request_size = request_size; call->request = kmalloc(request_size, GFP_NOFS); if (!call->request) goto nomem_free; } if (reply_max) { + call->reply_max = reply_max; call->buffer = kmalloc(reply_max, GFP_NOFS); if (!call->buffer) goto nomem_free; @@ -228,7 +239,7 @@ struct afs_call *afs_alloc_flat_call(const struct afs_call_type *type, return call; nomem_free: - afs_free_call(call); + afs_put_call(call); nomem_call: return NULL; } @@ -315,7 +326,7 @@ static int afs_send_pages(struct afs_call *call, struct msghdr *msg, * initiate a call */ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp, - const struct afs_wait_mode *wait_mode) + bool async) { struct sockaddr_rxrpc srx; struct rxrpc_call *rxcall; @@ -332,8 +343,7 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp, call, call->type->name, key_serial(call->key), atomic_read(&afs_outstanding_calls)); - call->wait_mode = wait_mode; - INIT_WORK(&call->async_work, afs_process_async_call); + call->async = async; memset(&srx, 0, sizeof(srx)); srx.srx_family = AF_RXRPC; @@ -347,7 +357,9 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp, /* create a call */ rxcall = rxrpc_kernel_begin_call(afs_socket, &srx, call->key, (unsigned long) call, gfp, - wait_mode->notify_rx); + (async ? + afs_wake_up_async_call : + afs_wake_up_call_waiter)); call->key = NULL; if (IS_ERR(rxcall)) { ret = PTR_ERR(rxcall); @@ -386,12 +398,15 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp, /* at this point, an async call may no longer exist as it may have * already completed */ - return wait_mode->wait(call); + if (call->async) + return -EINPROGRESS; + + return afs_wait_for_call_to_complete(call); error_do_abort: rxrpc_kernel_abort_call(afs_socket, rxcall, RX_USER_ABORT, -ret, "KSD"); error_kill_call: - afs_end_call(call); + afs_put_call(call); _leave(" = %d", ret); return ret; } @@ -416,6 +431,8 @@ static void afs_deliver_to_call(struct afs_call *call) ret = rxrpc_kernel_recv_data(afs_socket, call->rxcall, NULL, 0, &offset, false, &call->abort_code); + trace_afs_recv_data(call, 0, offset, false, ret); + if (ret == -EINPROGRESS || ret == -EAGAIN) return; if (ret == 1 || ret < 0) { @@ -459,7 +476,7 @@ static void afs_deliver_to_call(struct afs_call *call) done: if (call->state == AFS_CALL_COMPLETE && call->incoming) - afs_end_call(call); + afs_put_call(call); out: _leave(""); return; @@ -516,7 +533,7 @@ static int afs_wait_for_call_to_complete(struct afs_call *call) } _debug("call complete"); - afs_end_call(call); + afs_put_call(call); _leave(" = %d", ret); return ret; } @@ -540,24 +557,25 @@ static void afs_wake_up_async_call(struct sock *sk, struct rxrpc_call *rxcall, unsigned long call_user_ID) { struct afs_call *call = (struct afs_call *)call_user_ID; + int u; + trace_afs_notify_call(rxcall, call); call->need_attention = true; - queue_work(afs_async_calls, &call->async_work); -} -/* - * put a call into asynchronous mode - * - mustn't touch the call descriptor as the call my have completed by the - * time we get here - */ -static int afs_dont_wait_for_call_to_complete(struct afs_call *call) -{ - _enter(""); - return -EINPROGRESS; + u = __atomic_add_unless(&call->usage, 1, 0); + if (u != 0) { + trace_afs_call(call, afs_call_trace_wake, u, + atomic_read(&afs_outstanding_calls), + __builtin_return_address(0)); + + if (!queue_work(afs_async_calls, &call->async_work)) + afs_put_call(call); + } } /* - * delete an asynchronous call + * Delete an asynchronous call. The work item carries a ref to the call struct + * that we need to release. */ static void afs_delete_async_call(struct work_struct *work) { @@ -565,13 +583,14 @@ static void afs_delete_async_call(struct work_struct *work) _enter(""); - afs_free_call(call); + afs_put_call(call); _leave(""); } /* - * perform processing on an asynchronous call + * Perform I/O processing on an asynchronous call. The work item carries a ref + * to the call struct that we either need to release or to pass on. */ static void afs_process_async_call(struct work_struct *work) { @@ -584,21 +603,19 @@ static void afs_process_async_call(struct work_struct *work) afs_deliver_to_call(call); } - if (call->state == AFS_CALL_COMPLETE && call->wait_mode) { - if (call->wait_mode->async_complete) - call->wait_mode->async_complete(call->reply, - call->error); + if (call->state == AFS_CALL_COMPLETE) { call->reply = NULL; - /* kill the call */ - afs_end_call_nofree(call); - - /* we can't just delete the call because the work item may be - * queued */ + /* We have two refs to release - one from the alloc and one + * queued with the work item - and we can't just deallocate the + * call because the work item may be queued again. + */ call->async_work.func = afs_delete_async_call; - queue_work(afs_async_calls, &call->async_work); + if (!queue_work(afs_async_calls, &call->async_work)) + afs_put_call(call); } + afs_put_call(call); _leave(""); } @@ -618,15 +635,13 @@ static void afs_charge_preallocation(struct work_struct *work) for (;;) { if (!call) { - call = kzalloc(sizeof(struct afs_call), GFP_KERNEL); + call = afs_alloc_call(&afs_RXCMxxxx, GFP_KERNEL); if (!call) break; - INIT_WORK(&call->async_work, afs_process_async_call); - call->wait_mode = &afs_async_incoming_call; - call->type = &afs_RXCMxxxx; - init_waitqueue_head(&call->waitq); + call->async = true; call->state = AFS_CALL_AWAIT_OP_ID; + init_waitqueue_head(&call->waitq); } if (rxrpc_kernel_charge_accept(afs_socket, @@ -648,9 +663,8 @@ static void afs_rx_discard_new_call(struct rxrpc_call *rxcall, { struct afs_call *call = (struct afs_call *)user_call_ID; - atomic_inc(&afs_outstanding_calls); call->rxcall = NULL; - afs_free_call(call); + afs_put_call(call); } /* @@ -659,7 +673,6 @@ static void afs_rx_discard_new_call(struct rxrpc_call *rxcall, static void afs_rx_new_call(struct sock *sk, struct rxrpc_call *rxcall, unsigned long user_call_ID) { - atomic_inc(&afs_outstanding_calls); queue_work(afs_wq, &afs_charge_preallocation_work); } @@ -689,6 +702,8 @@ static int afs_deliver_cm_op_id(struct afs_call *call) if (!afs_cm_incoming_call(call)) return -ENOTSUPP; + trace_afs_cb_call(call); + /* pass responsibility for the remainer of this message off to the * cache manager op */ return call->type->deliver(call); @@ -721,7 +736,6 @@ void afs_send_empty_reply(struct afs_call *call) rxrpc_kernel_abort_call(afs_socket, call->rxcall, RX_USER_ABORT, ENOMEM, "KOO"); default: - afs_end_call(call); _leave(" [error]"); return; } @@ -760,7 +774,6 @@ void afs_send_simple_reply(struct afs_call *call, const void *buf, size_t len) rxrpc_kernel_abort_call(afs_socket, call->rxcall, RX_USER_ABORT, ENOMEM, "KOO"); } - afs_end_call(call); _leave(" [error]"); } @@ -780,6 +793,7 @@ int afs_extract_data(struct afs_call *call, void *buf, size_t count, ret = rxrpc_kernel_recv_data(afs_socket, call->rxcall, buf, count, &call->offset, want_more, &call->abort_code); + trace_afs_recv_data(call, count, call->offset, want_more, ret); if (ret == 0 || ret == -EAGAIN) return ret; diff --git a/fs/afs/vlclient.c b/fs/afs/vlclient.c index 94bcd97d22b8..a5e4cc561b6c 100644 --- a/fs/afs/vlclient.c +++ b/fs/afs/vlclient.c @@ -147,7 +147,7 @@ int afs_vl_get_entry_by_name(struct in_addr *addr, struct key *key, const char *volname, struct afs_cache_vlocation *entry, - const struct afs_wait_mode *wait_mode) + bool async) { struct afs_call *call; size_t volnamesz, reqsz, padsz; @@ -177,7 +177,7 @@ int afs_vl_get_entry_by_name(struct in_addr *addr, memset((void *) bp + volnamesz, 0, padsz); /* initiate the call */ - return afs_make_call(addr, call, GFP_KERNEL, wait_mode); + return afs_make_call(addr, call, GFP_KERNEL, async); } /* @@ -188,7 +188,7 @@ int afs_vl_get_entry_by_id(struct in_addr *addr, afs_volid_t volid, afs_voltype_t voltype, struct afs_cache_vlocation *entry, - const struct afs_wait_mode *wait_mode) + bool async) { struct afs_call *call; __be32 *bp; @@ -211,5 +211,5 @@ int afs_vl_get_entry_by_id(struct in_addr *addr, *bp = htonl(voltype); /* initiate the call */ - return afs_make_call(addr, call, GFP_KERNEL, wait_mode); + return afs_make_call(addr, call, GFP_KERNEL, async); } diff --git a/fs/afs/vlocation.c b/fs/afs/vlocation.c index 45a86396fd2d..d7d8dd8c0b31 100644 --- a/fs/afs/vlocation.c +++ b/fs/afs/vlocation.c @@ -53,7 +53,7 @@ static int afs_vlocation_access_vl_by_name(struct afs_vlocation *vl, /* attempt to access the VL server */ ret = afs_vl_get_entry_by_name(&addr, key, vl->vldb.name, vldb, - &afs_sync_call); + false); switch (ret) { case 0: goto out; @@ -111,7 +111,7 @@ static int afs_vlocation_access_vl_by_id(struct afs_vlocation *vl, /* attempt to access the VL server */ ret = afs_vl_get_entry_by_id(&addr, key, volid, voltype, vldb, - &afs_sync_call); + false); switch (ret) { case 0: goto out; diff --git a/fs/afs/vnode.c b/fs/afs/vnode.c index 25cf4c3f4ff7..dcb956143c86 100644 --- a/fs/afs/vnode.c +++ b/fs/afs/vnode.c @@ -358,7 +358,7 @@ get_anyway: server, ntohl(server->addr.s_addr)); ret = afs_fs_fetch_file_status(server, key, vnode, NULL, - &afs_sync_call); + false); } while (!afs_volume_release_fileserver(vnode, server, ret)); @@ -393,7 +393,7 @@ no_server: * - TODO implement caching */ int afs_vnode_fetch_data(struct afs_vnode *vnode, struct key *key, - off_t offset, size_t length, struct page *page) + struct afs_read *desc) { struct afs_server *server; int ret; @@ -420,8 +420,8 @@ int afs_vnode_fetch_data(struct afs_vnode *vnode, struct key *key, _debug("USING SERVER: %08x\n", ntohl(server->addr.s_addr)); - ret = afs_fs_fetch_data(server, key, vnode, offset, length, - page, &afs_sync_call); + ret = afs_fs_fetch_data(server, key, vnode, desc, + false); } while (!afs_volume_release_fileserver(vnode, server, ret)); @@ -477,7 +477,7 @@ int afs_vnode_create(struct afs_vnode *vnode, struct key *key, _debug("USING SERVER: %08x\n", ntohl(server->addr.s_addr)); ret = afs_fs_create(server, key, vnode, name, mode, newfid, - newstatus, newcb, &afs_sync_call); + newstatus, newcb, false); } while (!afs_volume_release_fileserver(vnode, server, ret)); @@ -533,7 +533,7 @@ int afs_vnode_remove(struct afs_vnode *vnode, struct key *key, const char *name, _debug("USING SERVER: %08x\n", ntohl(server->addr.s_addr)); ret = afs_fs_remove(server, key, vnode, name, isdir, - &afs_sync_call); + false); } while (!afs_volume_release_fileserver(vnode, server, ret)); @@ -595,7 +595,7 @@ int afs_vnode_link(struct afs_vnode *dvnode, struct afs_vnode *vnode, _debug("USING SERVER: %08x\n", ntohl(server->addr.s_addr)); ret = afs_fs_link(server, key, dvnode, vnode, name, - &afs_sync_call); + false); } while (!afs_volume_release_fileserver(dvnode, server, ret)); @@ -659,7 +659,7 @@ int afs_vnode_symlink(struct afs_vnode *vnode, struct key *key, _debug("USING SERVER: %08x\n", ntohl(server->addr.s_addr)); ret = afs_fs_symlink(server, key, vnode, name, content, - newfid, newstatus, &afs_sync_call); + newfid, newstatus, false); } while (!afs_volume_release_fileserver(vnode, server, ret)); @@ -729,7 +729,7 @@ int afs_vnode_rename(struct afs_vnode *orig_dvnode, _debug("USING SERVER: %08x\n", ntohl(server->addr.s_addr)); ret = afs_fs_rename(server, key, orig_dvnode, orig_name, - new_dvnode, new_name, &afs_sync_call); + new_dvnode, new_name, false); } while (!afs_volume_release_fileserver(orig_dvnode, server, ret)); @@ -795,7 +795,7 @@ int afs_vnode_store_data(struct afs_writeback *wb, pgoff_t first, pgoff_t last, _debug("USING SERVER: %08x\n", ntohl(server->addr.s_addr)); ret = afs_fs_store_data(server, wb, first, last, offset, to, - &afs_sync_call); + false); } while (!afs_volume_release_fileserver(vnode, server, ret)); @@ -847,7 +847,7 @@ int afs_vnode_setattr(struct afs_vnode *vnode, struct key *key, _debug("USING SERVER: %08x\n", ntohl(server->addr.s_addr)); - ret = afs_fs_setattr(server, key, vnode, attr, &afs_sync_call); + ret = afs_fs_setattr(server, key, vnode, attr, false); } while (!afs_volume_release_fileserver(vnode, server, ret)); @@ -894,7 +894,7 @@ int afs_vnode_get_volume_status(struct afs_vnode *vnode, struct key *key, _debug("USING SERVER: %08x\n", ntohl(server->addr.s_addr)); - ret = afs_fs_get_volume_status(server, key, vnode, vs, &afs_sync_call); + ret = afs_fs_get_volume_status(server, key, vnode, vs, false); } while (!afs_volume_release_fileserver(vnode, server, ret)); @@ -933,7 +933,7 @@ int afs_vnode_set_lock(struct afs_vnode *vnode, struct key *key, _debug("USING SERVER: %08x\n", ntohl(server->addr.s_addr)); - ret = afs_fs_set_lock(server, key, vnode, type, &afs_sync_call); + ret = afs_fs_set_lock(server, key, vnode, type, false); } while (!afs_volume_release_fileserver(vnode, server, ret)); @@ -971,7 +971,7 @@ int afs_vnode_extend_lock(struct afs_vnode *vnode, struct key *key) _debug("USING SERVER: %08x\n", ntohl(server->addr.s_addr)); - ret = afs_fs_extend_lock(server, key, vnode, &afs_sync_call); + ret = afs_fs_extend_lock(server, key, vnode, false); } while (!afs_volume_release_fileserver(vnode, server, ret)); @@ -1009,7 +1009,7 @@ int afs_vnode_release_lock(struct afs_vnode *vnode, struct key *key) _debug("USING SERVER: %08x\n", ntohl(server->addr.s_addr)); - ret = afs_fs_release_lock(server, key, vnode, &afs_sync_call); + ret = afs_fs_release_lock(server, key, vnode, false); } while (!afs_volume_release_fileserver(vnode, server, ret)); diff --git a/fs/afs/volume.c b/fs/afs/volume.c index d142a2449e65..546f9d01710b 100644 --- a/fs/afs/volume.c +++ b/fs/afs/volume.c @@ -106,6 +106,7 @@ struct afs_volume *afs_volume_lookup(struct afs_mount_params *params) volume->cell = params->cell; volume->vid = vlocation->vldb.vid[params->type]; + volume->bdi.ra_pages = VM_MAX_READAHEAD*1024/PAGE_SIZE; ret = bdi_setup_and_register(&volume->bdi, "afs"); if (ret) goto error_bdi; diff --git a/fs/afs/write.c b/fs/afs/write.c index f865c3f05bea..c83c1a0e851f 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -86,19 +86,30 @@ void afs_put_writeback(struct afs_writeback *wb) static int afs_fill_page(struct afs_vnode *vnode, struct key *key, loff_t pos, struct page *page) { + struct afs_read *req; loff_t i_size; int ret; - int len; _enter(",,%llu", (unsigned long long)pos); + req = kzalloc(sizeof(struct afs_read) + sizeof(struct page *), + GFP_KERNEL); + if (!req) + return -ENOMEM; + + atomic_set(&req->usage, 1); + req->pos = pos; + req->nr_pages = 1; + req->pages[0] = page; + i_size = i_size_read(&vnode->vfs_inode); if (pos + PAGE_SIZE > i_size) - len = i_size - pos; + req->len = i_size - pos; else - len = PAGE_SIZE; + req->len = PAGE_SIZE; - ret = afs_vnode_fetch_data(vnode, key, pos, len, page); + ret = afs_vnode_fetch_data(vnode, key, req); + afs_put_read(req); if (ret < 0) { if (ret == -ENOENT) { _debug("got NOENT from server" @@ -512,7 +512,7 @@ static int aio_setup_ring(struct kioctx *ctx) ctx->mmap_base = do_mmap_pgoff(ctx->aio_ring_file, 0, ctx->mmap_size, PROT_READ | PROT_WRITE, - MAP_SHARED, 0, &unused); + MAP_SHARED, 0, &unused, NULL); up_write(&mm->mmap_sem); if (IS_ERR((void *)ctx->mmap_base)) { ctx->mmap_size = 0; diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c index 6f48d670c941..806df746f1a9 100644 --- a/fs/autofs4/dev-ioctl.c +++ b/fs/autofs4/dev-ioctl.c @@ -38,8 +38,6 @@ * which have been left busy at at service shutdown. */ -#define AUTOFS_DEV_IOCTL_SIZE sizeof(struct autofs_dev_ioctl) - typedef int (*ioctl_fn)(struct file *, struct autofs_sb_info *, struct autofs_dev_ioctl *); diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c index 82e8f6edfb48..d79ced925861 100644 --- a/fs/autofs4/root.c +++ b/fs/autofs4/root.c @@ -281,8 +281,8 @@ static int autofs4_mount_wait(const struct path *path, bool rcu_walk) pr_debug("waiting for mount name=%pd\n", path->dentry); status = autofs4_wait(sbi, path, NFY_MOUNT); pr_debug("mount wait done status=%d\n", status); + ino->last_used = jiffies; } - ino->last_used = jiffies; return status; } @@ -321,16 +321,21 @@ static struct dentry *autofs4_mountpoint_changed(struct path *path) */ if (autofs_type_indirect(sbi->type) && d_unhashed(dentry)) { struct dentry *parent = dentry->d_parent; - struct autofs_info *ino; struct dentry *new; new = d_lookup(parent, &dentry->d_name); if (!new) return NULL; - ino = autofs4_dentry_ino(new); - ino->last_used = jiffies; - dput(path->dentry); - path->dentry = new; + if (new == dentry) + dput(new); + else { + struct autofs_info *ino; + + ino = autofs4_dentry_ino(new); + ino->last_used = jiffies; + dput(path->dentry); + path->dentry = new; + } } return path->dentry; } diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c index 1278335ce366..79fbd85db4ba 100644 --- a/fs/autofs4/waitq.c +++ b/fs/autofs4/waitq.c @@ -436,8 +436,8 @@ int autofs4_wait(struct autofs_sb_info *sbi, memcpy(&wq->name, &qstr, sizeof(struct qstr)); wq->dev = autofs4_get_dev(sbi); wq->ino = autofs4_get_ino(sbi); - wq->uid = current_real_cred()->uid; - wq->gid = current_real_cred()->gid; + wq->uid = current_cred()->uid; + wq->gid = current_cred()->gid; wq->pid = pid; wq->tgid = tgid; wq->status = -EINTR; /* Status return if interrupted */ diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index e7bf01373bc4..443a6f537d56 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -91,12 +91,18 @@ static struct linux_binfmt elf_format = { #define BAD_ADDR(x) ((unsigned long)(x) >= TASK_SIZE) -static int set_brk(unsigned long start, unsigned long end) +static int set_brk(unsigned long start, unsigned long end, int prot) { start = ELF_PAGEALIGN(start); end = ELF_PAGEALIGN(end); if (end > start) { - int error = vm_brk(start, end - start); + /* + * Map the last of the bss segment. + * If the header is requesting these pages to be + * executable, honour that (ppc32 needs this). + */ + int error = vm_brk_flags(start, end - start, + prot & PROT_EXEC ? VM_EXEC : 0); if (error) return error; } @@ -524,6 +530,7 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex, unsigned long load_addr = 0; int load_addr_set = 0; unsigned long last_bss = 0, elf_bss = 0; + int bss_prot = 0; unsigned long error = ~0UL; unsigned long total_size; int i; @@ -606,8 +613,10 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex, * elf_bss and last_bss is the bss section. */ k = load_addr + eppnt->p_vaddr + eppnt->p_memsz; - if (k > last_bss) + if (k > last_bss) { last_bss = k; + bss_prot = elf_prot; + } } } @@ -623,13 +632,14 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex, /* * Next, align both the file and mem bss up to the page size, * since this is where elf_bss was just zeroed up to, and where - * last_bss will end after the vm_brk() below. + * last_bss will end after the vm_brk_flags() below. */ elf_bss = ELF_PAGEALIGN(elf_bss); last_bss = ELF_PAGEALIGN(last_bss); /* Finally, if there is still more bss to allocate, do it. */ if (last_bss > elf_bss) { - error = vm_brk(elf_bss, last_bss - elf_bss); + error = vm_brk_flags(elf_bss, last_bss - elf_bss, + bss_prot & PROT_EXEC ? VM_EXEC : 0); if (error) goto out; } @@ -674,6 +684,7 @@ static int load_elf_binary(struct linux_binprm *bprm) unsigned long error; struct elf_phdr *elf_ppnt, *elf_phdata, *interp_elf_phdata = NULL; unsigned long elf_bss, elf_brk; + int bss_prot = 0; int retval, i; unsigned long elf_entry; unsigned long interp_load_addr = 0; @@ -882,7 +893,8 @@ static int load_elf_binary(struct linux_binprm *bprm) before this one. Map anonymous pages, if needed, and clear the area. */ retval = set_brk(elf_bss + load_bias, - elf_brk + load_bias); + elf_brk + load_bias, + bss_prot); if (retval) goto out_free_dentry; nbyte = ELF_PAGEOFFSET(elf_bss); @@ -976,8 +988,10 @@ static int load_elf_binary(struct linux_binprm *bprm) if (end_data < k) end_data = k; k = elf_ppnt->p_vaddr + elf_ppnt->p_memsz; - if (k > elf_brk) + if (k > elf_brk) { + bss_prot = elf_prot; elf_brk = k; + } } loc->elf_ex.e_entry += load_bias; @@ -993,7 +1007,7 @@ static int load_elf_binary(struct linux_binprm *bprm) * mapping in the interpreter, to make sure it doesn't wind * up getting placed where the bss needs to go. */ - retval = set_brk(elf_bss, elf_brk); + retval = set_brk(elf_bss, elf_brk, bss_prot); if (retval) goto out_free_dentry; if (likely(elf_bss != elf_brk) && unlikely(padzero(elf_bss))) { diff --git a/fs/block_dev.c b/fs/block_dev.c index 3c47614a4b32..77c30f15a02c 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -884,6 +884,8 @@ static void bdev_evict_inode(struct inode *inode) spin_lock(&bdev_lock); list_del_init(&bdev->bd_list); spin_unlock(&bdev_lock); + if (bdev->bd_bdi != &noop_backing_dev_info) + bdi_put(bdev->bd_bdi); } static const struct super_operations bdev_sops = { @@ -954,6 +956,21 @@ static int bdev_set(struct inode *inode, void *data) static LIST_HEAD(all_bdevs); +/* + * If there is a bdev inode for this device, unhash it so that it gets evicted + * as soon as last inode reference is dropped. + */ +void bdev_unhash_inode(dev_t dev) +{ + struct inode *inode; + + inode = ilookup5(blockdev_superblock, hash(dev), bdev_test, &dev); + if (inode) { + remove_inode_hash(inode); + iput(inode); + } +} + struct block_device *bdget(dev_t dev) { struct block_device *bdev; @@ -971,7 +988,8 @@ struct block_device *bdget(dev_t dev) bdev->bd_contains = NULL; bdev->bd_super = NULL; bdev->bd_inode = inode; - bdev->bd_block_size = (1 << inode->i_blkbits); + bdev->bd_bdi = &noop_backing_dev_info; + bdev->bd_block_size = i_blocksize(inode); bdev->bd_part_count = 0; bdev->bd_invalidated = 0; inode->i_mode = S_IFBLK; @@ -1025,13 +1043,22 @@ static struct block_device *bd_acquire(struct inode *inode) spin_lock(&bdev_lock); bdev = inode->i_bdev; - if (bdev) { + if (bdev && !inode_unhashed(bdev->bd_inode)) { bdgrab(bdev); spin_unlock(&bdev_lock); return bdev; } spin_unlock(&bdev_lock); + /* + * i_bdev references block device inode that was already shut down + * (corresponding device got removed). Remove the reference and look + * up block device inode again just in case new device got + * reestablished under the same device number. + */ + if (bdev) + bd_forget(inode); + bdev = bdget(inode->i_rdev); if (bdev) { spin_lock(&bdev_lock); @@ -1527,6 +1554,8 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) bdev->bd_disk = disk; bdev->bd_queue = disk->queue; bdev->bd_contains = bdev; + if (bdev->bd_bdi == &noop_backing_dev_info) + bdev->bd_bdi = bdi_get(disk->queue->backing_dev_info); if (!partno) { ret = -ENXIO; @@ -1622,6 +1651,8 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) bdev->bd_disk = NULL; bdev->bd_part = NULL; bdev->bd_queue = NULL; + bdi_put(bdev->bd_bdi); + bdev->bd_bdi = &noop_backing_dev_info; if (bdev != bdev->bd_contains) __blkdev_put(bdev->bd_contains, mode, 1); bdev->bd_contains = NULL; diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 8299601a3549..7699e16784d3 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -956,8 +956,7 @@ static int __add_delayed_refs(struct btrfs_delayed_ref_head *head, u64 seq, /* * add all inline backrefs for bytenr to the list */ -static int __add_inline_refs(struct btrfs_fs_info *fs_info, - struct btrfs_path *path, u64 bytenr, +static int __add_inline_refs(struct btrfs_path *path, u64 bytenr, int *info_level, struct list_head *prefs, struct ref_root *ref_tree, u64 *total_refs, u64 inum) @@ -1284,7 +1283,7 @@ again: */ delayed_refs = &trans->transaction->delayed_refs; spin_lock(&delayed_refs->lock); - head = btrfs_find_delayed_ref_head(trans, bytenr); + head = btrfs_find_delayed_ref_head(delayed_refs, bytenr); if (head) { if (!mutex_trylock(&head->mutex)) { atomic_inc(&head->node.refs); @@ -1354,7 +1353,7 @@ again: if (key.objectid == bytenr && (key.type == BTRFS_EXTENT_ITEM_KEY || key.type == BTRFS_METADATA_ITEM_KEY)) { - ret = __add_inline_refs(fs_info, path, bytenr, + ret = __add_inline_refs(path, bytenr, &info_level, &prefs, ref_tree, &total_refs, inum); diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h index 1a8fa46ff87e..819a6d27218a 100644 --- a/fs/btrfs/btrfs_inode.h +++ b/fs/btrfs/btrfs_inode.h @@ -224,16 +224,16 @@ static inline void btrfs_insert_inode_hash(struct inode *inode) __insert_inode_hash(inode, h); } -static inline u64 btrfs_ino(struct inode *inode) +static inline u64 btrfs_ino(struct btrfs_inode *inode) { - u64 ino = BTRFS_I(inode)->location.objectid; + u64 ino = inode->location.objectid; /* * !ino: btree_inode * type == BTRFS_ROOT_ITEM_KEY: subvol dir */ - if (!ino || BTRFS_I(inode)->location.type == BTRFS_ROOT_ITEM_KEY) - ino = inode->i_ino; + if (!ino || inode->location.type == BTRFS_ROOT_ITEM_KEY) + ino = inode->vfs_inode.i_ino; return ino; } @@ -248,23 +248,21 @@ static inline bool btrfs_is_free_space_inode(struct inode *inode) struct btrfs_root *root = BTRFS_I(inode)->root; if (root == root->fs_info->tree_root && - btrfs_ino(inode) != BTRFS_BTREE_INODE_OBJECTID) + btrfs_ino(BTRFS_I(inode)) != BTRFS_BTREE_INODE_OBJECTID) return true; if (BTRFS_I(inode)->location.objectid == BTRFS_FREE_INO_OBJECTID) return true; return false; } -static inline int btrfs_inode_in_log(struct inode *inode, u64 generation) +static inline int btrfs_inode_in_log(struct btrfs_inode *inode, u64 generation) { int ret = 0; - spin_lock(&BTRFS_I(inode)->lock); - if (BTRFS_I(inode)->logged_trans == generation && - BTRFS_I(inode)->last_sub_trans <= - BTRFS_I(inode)->last_log_commit && - BTRFS_I(inode)->last_sub_trans <= - BTRFS_I(inode)->root->last_log_commit) { + spin_lock(&inode->lock); + if (inode->logged_trans == generation && + inode->last_sub_trans <= inode->last_log_commit && + inode->last_sub_trans <= inode->root->last_log_commit) { /* * After a ranged fsync we might have left some extent maps * (that fall outside the fsync's range). So return false @@ -272,10 +270,10 @@ static inline int btrfs_inode_in_log(struct inode *inode, u64 generation) * will be called and process those extent maps. */ smp_mb(); - if (list_empty(&BTRFS_I(inode)->extent_tree.modified_extents)) + if (list_empty(&inode->extent_tree.modified_extents)) ret = 1; } - spin_unlock(&BTRFS_I(inode)->lock); + spin_unlock(&inode->lock); return ret; } @@ -326,6 +324,24 @@ static inline void btrfs_inode_resume_unlocked_dio(struct inode *inode) &BTRFS_I(inode)->runtime_flags); } +static inline void btrfs_print_data_csum_error(struct inode *inode, + u64 logical_start, u32 csum, u32 csum_expected, int mirror_num) +{ + struct btrfs_root *root = BTRFS_I(inode)->root; + + /* Output minus objectid, which is more meaningful */ + if (root->objectid >= BTRFS_LAST_FREE_OBJECTID) + btrfs_warn_rl(root->fs_info, + "csum failed root %lld ino %lld off %llu csum 0x%08x expected csum 0x%08x mirror %d", + root->objectid, btrfs_ino(BTRFS_I(inode)), + logical_start, csum, csum_expected, mirror_num); + else + btrfs_warn_rl(root->fs_info, + "csum failed root %llu ino %llu off %llu csum 0x%08x expected csum 0x%08x mirror %d", + root->objectid, btrfs_ino(BTRFS_I(inode)), + logical_start, csum, csum_expected, mirror_num); +} + bool btrfs_page_exists_in_range(struct inode *inode, loff_t start, loff_t end); #endif diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index c4444d6f439f..903c32c9eb22 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -124,10 +124,8 @@ static int check_compressed_csum(struct inode *inode, kunmap_atomic(kaddr); if (csum != *cb_sum) { - btrfs_info(BTRFS_I(inode)->root->fs_info, - "csum failed ino %llu extent %llu csum %u wanted %u mirror %d", - btrfs_ino(inode), disk_start, csum, *cb_sum, - cb->mirror_num); + btrfs_print_data_csum_error(inode, disk_start, csum, + *cb_sum, cb->mirror_num); ret = -EIO; goto fail; } diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index a426dc822d4d..1192bc7d2ee7 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -28,9 +28,9 @@ static int split_node(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, int level); -static int split_leaf(struct btrfs_trans_handle *trans, struct btrfs_root - *root, struct btrfs_key *ins_key, - struct btrfs_path *path, int data_size, int extend); +static int split_leaf(struct btrfs_trans_handle *trans, struct btrfs_root *root, + const struct btrfs_key *ins_key, struct btrfs_path *path, + int data_size, int extend); static int push_node_left(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, struct extent_buffer *dst, @@ -426,7 +426,7 @@ void btrfs_put_tree_mod_seq(struct btrfs_fs_info *fs_info, tm_root = &fs_info->tree_mod_log; for (node = rb_first(tm_root); node; node = next) { next = rb_next(node); - tm = container_of(node, struct tree_mod_elem, node); + tm = rb_entry(node, struct tree_mod_elem, node); if (tm->seq > min_seq) continue; rb_erase(node, tm_root); @@ -460,7 +460,7 @@ __tree_mod_log_insert(struct btrfs_fs_info *fs_info, struct tree_mod_elem *tm) tm_root = &fs_info->tree_mod_log; new = &tm_root->rb_node; while (*new) { - cur = container_of(*new, struct tree_mod_elem, node); + cur = rb_entry(*new, struct tree_mod_elem, node); parent = *new; if (cur->logical < tm->logical) new = &((*new)->rb_left); @@ -746,7 +746,7 @@ __tree_mod_log_search(struct btrfs_fs_info *fs_info, u64 start, u64 min_seq, tm_root = &fs_info->tree_mod_log; node = tm_root->rb_node; while (node) { - cur = container_of(node, struct tree_mod_elem, node); + cur = rb_entry(node, struct tree_mod_elem, node); if (cur->logical < start) { node = node->rb_left; } else if (cur->logical > start) { @@ -1074,7 +1074,7 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans, ret = btrfs_dec_ref(trans, root, buf, 1); BUG_ON(ret); /* -ENOMEM */ } - clean_tree_block(trans, fs_info, buf); + clean_tree_block(fs_info, buf); *last_ref = 1; } return 0; @@ -1326,7 +1326,7 @@ __tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct extent_buffer *eb, next = rb_next(&tm->node); if (!next) break; - tm = container_of(next, struct tree_mod_elem, node); + tm = rb_entry(next, struct tree_mod_elem, node); if (tm->logical != first_tm->logical) break; } @@ -1580,7 +1580,8 @@ static int close_blocks(u64 blocknr, u64 other, u32 blocksize) /* * compare two keys in a memcmp fashion */ -static int comp_keys(struct btrfs_disk_key *disk, struct btrfs_key *k2) +static int comp_keys(const struct btrfs_disk_key *disk, + const struct btrfs_key *k2) { struct btrfs_key k1; @@ -1592,7 +1593,7 @@ static int comp_keys(struct btrfs_disk_key *disk, struct btrfs_key *k2) /* * same as comp_keys only with two btrfs_key's */ -int btrfs_comp_cpu_keys(struct btrfs_key *k1, struct btrfs_key *k2) +int btrfs_comp_cpu_keys(const struct btrfs_key *k1, const struct btrfs_key *k2) { if (k1->objectid > k2->objectid) return 1; @@ -1732,8 +1733,8 @@ int btrfs_realloc_node(struct btrfs_trans_handle *trans, * slot may point to max if the key is bigger than all of the keys */ static noinline int generic_bin_search(struct extent_buffer *eb, - unsigned long p, - int item_size, struct btrfs_key *key, + unsigned long p, int item_size, + const struct btrfs_key *key, int max, int *slot) { int low = 0; @@ -1802,7 +1803,7 @@ static noinline int generic_bin_search(struct extent_buffer *eb, * simple bin_search frontend that does the right thing for * leaves vs nodes */ -static int bin_search(struct extent_buffer *eb, struct btrfs_key *key, +static int bin_search(struct extent_buffer *eb, const struct btrfs_key *key, int level, int *slot) { if (level == 0) @@ -1819,7 +1820,7 @@ static int bin_search(struct extent_buffer *eb, struct btrfs_key *key, slot); } -int btrfs_bin_search(struct extent_buffer *eb, struct btrfs_key *key, +int btrfs_bin_search(struct extent_buffer *eb, const struct btrfs_key *key, int level, int *slot) { return bin_search(eb, key, level, slot); @@ -1937,7 +1938,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, path->locks[level] = 0; path->nodes[level] = NULL; - clean_tree_block(trans, fs_info, mid); + clean_tree_block(fs_info, mid); btrfs_tree_unlock(mid); /* once for the path */ free_extent_buffer(mid); @@ -1998,7 +1999,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, if (wret < 0 && wret != -ENOSPC) ret = wret; if (btrfs_header_nritems(right) == 0) { - clean_tree_block(trans, fs_info, right); + clean_tree_block(fs_info, right); btrfs_tree_unlock(right); del_ptr(root, path, level + 1, pslot + 1); root_sub_used(root, right->len); @@ -2042,7 +2043,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, BUG_ON(wret == 1); } if (btrfs_header_nritems(mid) == 0) { - clean_tree_block(trans, fs_info, mid); + clean_tree_block(fs_info, mid); btrfs_tree_unlock(mid); del_ptr(root, path, level + 1, pslot); root_sub_used(root, mid->len); @@ -2437,10 +2438,9 @@ noinline void btrfs_unlock_up_safe(struct btrfs_path *path, int level) * reada. -EAGAIN is returned and the search must be repeated. */ static int -read_block_for_search(struct btrfs_trans_handle *trans, - struct btrfs_root *root, struct btrfs_path *p, - struct extent_buffer **eb_ret, int level, int slot, - struct btrfs_key *key, u64 time_seq) +read_block_for_search(struct btrfs_root *root, struct btrfs_path *p, + struct extent_buffer **eb_ret, int level, int slot, + const struct btrfs_key *key) { struct btrfs_fs_info *fs_info = root->fs_info; u64 blocknr; @@ -2587,7 +2587,7 @@ done: } static void key_search_validate(struct extent_buffer *b, - struct btrfs_key *key, + const struct btrfs_key *key, int level) { #ifdef CONFIG_BTRFS_ASSERT @@ -2606,7 +2606,7 @@ static void key_search_validate(struct extent_buffer *b, #endif } -static int key_search(struct extent_buffer *b, struct btrfs_key *key, +static int key_search(struct extent_buffer *b, const struct btrfs_key *key, int level, int *prev_cmp, int *slot) { if (*prev_cmp != 0) { @@ -2668,9 +2668,9 @@ int btrfs_find_item(struct btrfs_root *fs_root, struct btrfs_path *path, * tree. if ins_len < 0, nodes will be merged as we walk down the tree (if * possible) */ -int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root - *root, struct btrfs_key *key, struct btrfs_path *p, int - ins_len, int cow) +int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root *root, + const struct btrfs_key *key, struct btrfs_path *p, + int ins_len, int cow) { struct btrfs_fs_info *fs_info = root->fs_info; struct extent_buffer *b; @@ -2870,8 +2870,8 @@ cow_done: goto done; } - err = read_block_for_search(trans, root, p, - &b, level, slot, key, 0); + err = read_block_for_search(root, p, &b, level, + slot, key); if (err == -EAGAIN) goto again; if (err) { @@ -2953,7 +2953,7 @@ done: * The resulting path and return value will be set up as if we called * btrfs_search_slot at that point in time with ins_len and cow both set to 0. */ -int btrfs_search_old_slot(struct btrfs_root *root, struct btrfs_key *key, +int btrfs_search_old_slot(struct btrfs_root *root, const struct btrfs_key *key, struct btrfs_path *p, u64 time_seq) { struct btrfs_fs_info *fs_info = root->fs_info; @@ -3014,8 +3014,8 @@ again: goto done; } - err = read_block_for_search(NULL, root, p, &b, level, - slot, key, time_seq); + err = read_block_for_search(root, p, &b, level, + slot, key); if (err == -EAGAIN) goto again; if (err) { @@ -3067,8 +3067,9 @@ done: * < 0 on error */ int btrfs_search_slot_for_read(struct btrfs_root *root, - struct btrfs_key *key, struct btrfs_path *p, - int find_higher, int return_any) + const struct btrfs_key *key, + struct btrfs_path *p, int find_higher, + int return_any) { int ret; struct extent_buffer *leaf; @@ -3166,7 +3167,7 @@ static void fixup_low_keys(struct btrfs_fs_info *fs_info, */ void btrfs_set_item_key_safe(struct btrfs_fs_info *fs_info, struct btrfs_path *path, - struct btrfs_key *new_key) + const struct btrfs_key *new_key) { struct btrfs_disk_key disk_key; struct extent_buffer *eb; @@ -3594,8 +3595,7 @@ noinline int btrfs_leaf_free_space(struct btrfs_fs_info *fs_info, * min slot controls the lowest index we're willing to push to the * right. We'll push up to and including min_slot, but no lower */ -static noinline int __push_leaf_right(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, +static noinline int __push_leaf_right(struct btrfs_fs_info *fs_info, struct btrfs_path *path, int data_size, int empty, struct extent_buffer *right, @@ -3704,7 +3704,7 @@ static noinline int __push_leaf_right(struct btrfs_trans_handle *trans, if (left_nritems) btrfs_mark_buffer_dirty(left); else - clean_tree_block(trans, fs_info, left); + clean_tree_block(fs_info, left); btrfs_mark_buffer_dirty(right); @@ -3716,7 +3716,7 @@ static noinline int __push_leaf_right(struct btrfs_trans_handle *trans, if (path->slots[0] >= left_nritems) { path->slots[0] -= left_nritems; if (btrfs_header_nritems(path->nodes[0]) == 0) - clean_tree_block(trans, fs_info, path->nodes[0]); + clean_tree_block(fs_info, path->nodes[0]); btrfs_tree_unlock(path->nodes[0]); free_extent_buffer(path->nodes[0]); path->nodes[0] = right; @@ -3809,7 +3809,7 @@ static int push_leaf_right(struct btrfs_trans_handle *trans, struct btrfs_root return 0; } - return __push_leaf_right(trans, fs_info, path, min_data_size, empty, + return __push_leaf_right(fs_info, path, min_data_size, empty, right, free_space, left_nritems, min_slot); out_unlock: btrfs_tree_unlock(right); @@ -3825,8 +3825,7 @@ out_unlock: * item at 'max_slot' won't be touched. Use (u32)-1 to make us do all the * items */ -static noinline int __push_leaf_left(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, +static noinline int __push_leaf_left(struct btrfs_fs_info *fs_info, struct btrfs_path *path, int data_size, int empty, struct extent_buffer *left, int free_space, u32 right_nritems, @@ -3945,7 +3944,7 @@ static noinline int __push_leaf_left(struct btrfs_trans_handle *trans, if (right_nritems) btrfs_mark_buffer_dirty(right); else - clean_tree_block(trans, fs_info, right); + clean_tree_block(fs_info, right); btrfs_item_key(right, &disk_key, 0); fixup_low_keys(fs_info, path, &disk_key, 1); @@ -4035,7 +4034,7 @@ static int push_leaf_left(struct btrfs_trans_handle *trans, struct btrfs_root goto out; } - return __push_leaf_left(trans, fs_info, path, min_data_size, + return __push_leaf_left(fs_info, path, min_data_size, empty, left, free_space, right_nritems, max_slot); out: @@ -4180,7 +4179,7 @@ static noinline int push_for_double_split(struct btrfs_trans_handle *trans, */ static noinline int split_leaf(struct btrfs_trans_handle *trans, struct btrfs_root *root, - struct btrfs_key *ins_key, + const struct btrfs_key *ins_key, struct btrfs_path *path, int data_size, int extend) { @@ -4412,10 +4411,9 @@ err: return ret; } -static noinline int split_item(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, +static noinline int split_item(struct btrfs_fs_info *fs_info, struct btrfs_path *path, - struct btrfs_key *new_key, + const struct btrfs_key *new_key, unsigned long split_offset) { struct extent_buffer *leaf; @@ -4501,7 +4499,7 @@ static noinline int split_item(struct btrfs_trans_handle *trans, int btrfs_split_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, - struct btrfs_key *new_key, + const struct btrfs_key *new_key, unsigned long split_offset) { int ret; @@ -4510,7 +4508,7 @@ int btrfs_split_item(struct btrfs_trans_handle *trans, if (ret) return ret; - ret = split_item(trans, root->fs_info, path, new_key, split_offset); + ret = split_item(root->fs_info, path, new_key, split_offset); return ret; } @@ -4525,7 +4523,7 @@ int btrfs_split_item(struct btrfs_trans_handle *trans, int btrfs_duplicate_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, - struct btrfs_key *new_key) + const struct btrfs_key *new_key) { struct extent_buffer *leaf; int ret; @@ -4726,7 +4724,7 @@ void btrfs_extend_item(struct btrfs_fs_info *fs_info, struct btrfs_path *path, * that doesn't call btrfs_search_slot */ void setup_items_for_insert(struct btrfs_root *root, struct btrfs_path *path, - struct btrfs_key *cpu_key, u32 *data_size, + const struct btrfs_key *cpu_key, u32 *data_size, u32 total_data, u32 total_size, int nr) { struct btrfs_fs_info *fs_info = root->fs_info; @@ -4820,7 +4818,7 @@ void setup_items_for_insert(struct btrfs_root *root, struct btrfs_path *path, int btrfs_insert_empty_items(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, - struct btrfs_key *cpu_key, u32 *data_size, + const struct btrfs_key *cpu_key, u32 *data_size, int nr) { int ret = 0; @@ -4851,9 +4849,9 @@ int btrfs_insert_empty_items(struct btrfs_trans_handle *trans, * Given a key and some data, insert an item into the tree. * This does all the path init required, making room in the tree if needed. */ -int btrfs_insert_item(struct btrfs_trans_handle *trans, struct btrfs_root - *root, struct btrfs_key *cpu_key, void *data, u32 - data_size) +int btrfs_insert_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, + const struct btrfs_key *cpu_key, void *data, + u32 data_size) { int ret = 0; struct btrfs_path *path; @@ -5008,7 +5006,7 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root, btrfs_set_header_level(leaf, 0); } else { btrfs_set_path_blocking(path); - clean_tree_block(trans, fs_info, leaf); + clean_tree_block(fs_info, leaf); btrfs_del_leaf(trans, root, path, leaf); } } else { @@ -5243,7 +5241,7 @@ out: static int tree_move_down(struct btrfs_fs_info *fs_info, struct btrfs_path *path, - int *level, int root_level) + int *level) { struct extent_buffer *eb; @@ -5258,8 +5256,7 @@ static int tree_move_down(struct btrfs_fs_info *fs_info, return 0; } -static int tree_move_next_or_upnext(struct btrfs_fs_info *fs_info, - struct btrfs_path *path, +static int tree_move_next_or_upnext(struct btrfs_path *path, int *level, int root_level) { int ret = 0; @@ -5298,10 +5295,9 @@ static int tree_advance(struct btrfs_fs_info *fs_info, int ret; if (*level == 0 || !allow_down) { - ret = tree_move_next_or_upnext(fs_info, path, level, - root_level); + ret = tree_move_next_or_upnext(path, level, root_level); } else { - ret = tree_move_down(fs_info, path, level, root_level); + ret = tree_move_down(fs_info, path, level); } if (ret >= 0) { if (*level == 0) @@ -5784,8 +5780,8 @@ again: next = c; next_rw_lock = path->locks[level]; - ret = read_block_for_search(NULL, root, path, &next, level, - slot, &key, 0); + ret = read_block_for_search(root, path, &next, level, + slot, &key); if (ret == -EAGAIN) goto again; @@ -5834,8 +5830,8 @@ again: if (!level) break; - ret = read_block_for_search(NULL, root, path, &next, level, - 0, &key, 0); + ret = read_block_for_search(root, path, &next, level, + 0, &key); if (ret == -EAGAIN) goto again; diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 6a823719b6c5..105d4d43993e 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -97,6 +97,14 @@ static const int btrfs_csum_sizes[] = { 4 }; #define BTRFS_MAX_EXTENT_SIZE SZ_128M +/* + * Count how many BTRFS_MAX_EXTENT_SIZE cover the @size + */ +static inline u32 count_max_extents(u64 size) +{ + return div_u64(size + BTRFS_MAX_EXTENT_SIZE - 1, BTRFS_MAX_EXTENT_SIZE); +} + struct btrfs_mapping_tree { struct extent_map_tree map_tree; }; @@ -1953,7 +1961,7 @@ BTRFS_SETGET_STACK_FUNCS(disk_key_offset, struct btrfs_disk_key, offset, 64); BTRFS_SETGET_STACK_FUNCS(disk_key_type, struct btrfs_disk_key, type, 8); static inline void btrfs_disk_key_to_cpu(struct btrfs_key *cpu, - struct btrfs_disk_key *disk) + const struct btrfs_disk_key *disk) { cpu->offset = le64_to_cpu(disk->offset); cpu->type = disk->type; @@ -1961,7 +1969,7 @@ static inline void btrfs_disk_key_to_cpu(struct btrfs_key *cpu, } static inline void btrfs_cpu_key_to_disk(struct btrfs_disk_key *disk, - struct btrfs_key *cpu) + const struct btrfs_key *cpu) { disk->offset = cpu_to_le64(cpu->offset); disk->type = cpu->type; @@ -1993,8 +2001,7 @@ static inline void btrfs_dir_item_key_to_cpu(struct extent_buffer *eb, btrfs_disk_key_to_cpu(key, &disk_key); } - -static inline u8 btrfs_key_type(struct btrfs_key *key) +static inline u8 btrfs_key_type(const struct btrfs_key *key) { return key->type; } @@ -2577,8 +2584,7 @@ int btrfs_pin_extent_for_log_replay(struct btrfs_fs_info *fs_info, u64 bytenr, u64 num_bytes); int btrfs_exclude_logged_extents(struct btrfs_fs_info *fs_info, struct extent_buffer *eb); -int btrfs_cross_ref_exist(struct btrfs_trans_handle *trans, - struct btrfs_root *root, +int btrfs_cross_ref_exist(struct btrfs_root *root, u64 objectid, u64 offset, u64 bytenr); struct btrfs_block_group_cache *btrfs_lookup_block_group( struct btrfs_fs_info *info, @@ -2587,10 +2593,11 @@ void btrfs_get_block_group(struct btrfs_block_group_cache *cache); void btrfs_put_block_group(struct btrfs_block_group_cache *cache); int get_block_group_index(struct btrfs_block_group_cache *cache); struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans, - struct btrfs_root *root, u64 parent, - u64 root_objectid, - struct btrfs_disk_key *key, int level, - u64 hint, u64 empty_size); + struct btrfs_root *root, + u64 parent, u64 root_objectid, + const struct btrfs_disk_key *key, + int level, u64 hint, + u64 empty_size); void btrfs_free_tree_block(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *buf, @@ -2623,8 +2630,7 @@ int btrfs_free_reserved_extent(struct btrfs_fs_info *fs_info, u64 start, u64 len, int delalloc); int btrfs_free_and_pin_reserved_extent(struct btrfs_fs_info *fs_info, u64 start, u64 len); -void btrfs_prepare_extent_commit(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info); +void btrfs_prepare_extent_commit(struct btrfs_fs_info *fs_info); int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info); int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, @@ -2696,8 +2702,7 @@ int btrfs_subvolume_reserve_metadata(struct btrfs_root *root, int nitems, u64 *qgroup_reserved, bool use_global_rsv); void btrfs_subvolume_release_metadata(struct btrfs_fs_info *fs_info, - struct btrfs_block_rsv *rsv, - u64 qgroup_reserved); + struct btrfs_block_rsv *rsv); int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes); void btrfs_delalloc_release_metadata(struct inode *inode, u64 num_bytes); int btrfs_delalloc_reserve_space(struct inode *inode, u64 start, u64 len); @@ -2724,7 +2729,7 @@ int btrfs_cond_migrate_bytes(struct btrfs_fs_info *fs_info, void btrfs_block_rsv_release(struct btrfs_fs_info *fs_info, struct btrfs_block_rsv *block_rsv, u64 num_bytes); -int btrfs_inc_block_group_ro(struct btrfs_root *root, +int btrfs_inc_block_group_ro(struct btrfs_fs_info *fs_info, struct btrfs_block_group_cache *cache); void btrfs_dec_block_group_ro(struct btrfs_block_group_cache *cache); void btrfs_put_block_group_cache(struct btrfs_fs_info *info); @@ -2750,9 +2755,9 @@ u64 add_new_free_space(struct btrfs_block_group_cache *block_group, struct btrfs_fs_info *info, u64 start, u64 end); /* ctree.c */ -int btrfs_bin_search(struct extent_buffer *eb, struct btrfs_key *key, +int btrfs_bin_search(struct extent_buffer *eb, const struct btrfs_key *key, int level, int *slot); -int btrfs_comp_cpu_keys(struct btrfs_key *k1, struct btrfs_key *k2); +int btrfs_comp_cpu_keys(const struct btrfs_key *k1, const struct btrfs_key *k2); int btrfs_previous_item(struct btrfs_root *root, struct btrfs_path *path, u64 min_objectid, int type); @@ -2760,7 +2765,7 @@ int btrfs_previous_extent_item(struct btrfs_root *root, struct btrfs_path *path, u64 min_objectid); void btrfs_set_item_key_safe(struct btrfs_fs_info *fs_info, struct btrfs_path *path, - struct btrfs_key *new_key); + const struct btrfs_key *new_key); struct extent_buffer *btrfs_root_node(struct btrfs_root *root); struct extent_buffer *btrfs_lock_root_node(struct btrfs_root *root); int btrfs_find_next_key(struct btrfs_root *root, struct btrfs_path *path, @@ -2802,22 +2807,23 @@ void btrfs_truncate_item(struct btrfs_fs_info *fs_info, int btrfs_split_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, - struct btrfs_key *new_key, + const struct btrfs_key *new_key, unsigned long split_offset); int btrfs_duplicate_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, - struct btrfs_key *new_key); + const struct btrfs_key *new_key); int btrfs_find_item(struct btrfs_root *fs_root, struct btrfs_path *path, u64 inum, u64 ioff, u8 key_type, struct btrfs_key *found_key); -int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root - *root, struct btrfs_key *key, struct btrfs_path *p, int - ins_len, int cow); -int btrfs_search_old_slot(struct btrfs_root *root, struct btrfs_key *key, +int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root *root, + const struct btrfs_key *key, struct btrfs_path *p, + int ins_len, int cow); +int btrfs_search_old_slot(struct btrfs_root *root, const struct btrfs_key *key, struct btrfs_path *p, u64 time_seq); int btrfs_search_slot_for_read(struct btrfs_root *root, - struct btrfs_key *key, struct btrfs_path *p, - int find_higher, int return_any); + const struct btrfs_key *key, + struct btrfs_path *p, int find_higher, + int return_any); int btrfs_realloc_node(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *parent, int start_slot, u64 *last_ret, @@ -2840,19 +2846,20 @@ static inline int btrfs_del_item(struct btrfs_trans_handle *trans, } void setup_items_for_insert(struct btrfs_root *root, struct btrfs_path *path, - struct btrfs_key *cpu_key, u32 *data_size, + const struct btrfs_key *cpu_key, u32 *data_size, u32 total_data, u32 total_size, int nr); -int btrfs_insert_item(struct btrfs_trans_handle *trans, struct btrfs_root - *root, struct btrfs_key *key, void *data, u32 data_size); +int btrfs_insert_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, + const struct btrfs_key *key, void *data, u32 data_size); int btrfs_insert_empty_items(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, - struct btrfs_key *cpu_key, u32 *data_size, int nr); + const struct btrfs_key *cpu_key, u32 *data_size, + int nr); static inline int btrfs_insert_empty_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, - struct btrfs_key *key, + const struct btrfs_key *key, u32 data_size) { return btrfs_insert_empty_items(trans, root, path, key, &data_size, 1); @@ -2941,15 +2948,15 @@ int btrfs_del_root_ref(struct btrfs_trans_handle *trans, u64 root_id, u64 ref_id, u64 dirid, u64 *sequence, const char *name, int name_len); int btrfs_del_root(struct btrfs_trans_handle *trans, struct btrfs_root *root, - struct btrfs_key *key); -int btrfs_insert_root(struct btrfs_trans_handle *trans, struct btrfs_root - *root, struct btrfs_key *key, struct btrfs_root_item - *item); + const struct btrfs_key *key); +int btrfs_insert_root(struct btrfs_trans_handle *trans, struct btrfs_root *root, + const struct btrfs_key *key, + struct btrfs_root_item *item); int __must_check btrfs_update_root(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_key *key, struct btrfs_root_item *item); -int btrfs_find_root(struct btrfs_root *root, struct btrfs_key *search_key, +int btrfs_find_root(struct btrfs_root *root, const struct btrfs_key *search_key, struct btrfs_path *path, struct btrfs_root_item *root_item, struct btrfs_key *root_key); int btrfs_find_orphan_roots(struct btrfs_fs_info *fs_info); @@ -3119,7 +3126,7 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry); int btrfs_set_inode_index(struct inode *dir, u64 *index); int btrfs_unlink_inode(struct btrfs_trans_handle *trans, struct btrfs_root *root, - struct inode *dir, struct inode *inode, + struct btrfs_inode *dir, struct btrfs_inode *inode, const char *name, int name_len); int btrfs_add_link(struct btrfs_trans_handle *trans, struct inode *parent_inode, struct inode *inode, @@ -3147,7 +3154,7 @@ int btrfs_create_subvol_root(struct btrfs_trans_handle *trans, int btrfs_merge_bio_hook(struct page *page, unsigned long offset, size_t size, struct bio *bio, unsigned long bio_flags); -int btrfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf); +int btrfs_page_mkwrite(struct vm_fault *vmf); int btrfs_readpage(struct file *file, struct page *page); void btrfs_evict_inode(struct inode *inode); int btrfs_write_inode(struct inode *inode, struct writeback_control *wbc); @@ -3447,7 +3454,8 @@ do { \ "BTRFS: Transaction aborted (error %d)\n", \ (errno)); \ } else { \ - pr_debug("BTRFS: Transaction aborted (error %d)\n", \ + btrfs_debug((trans)->fs_info, \ + "Transaction aborted (error %d)", \ (errno)); \ } \ } \ diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index 80982a83c9fd..f7a6ee5ccc80 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -72,14 +72,14 @@ static inline int btrfs_is_continuous_delayed_item( return 0; } -static struct btrfs_delayed_node *btrfs_get_delayed_node(struct inode *inode) +static struct btrfs_delayed_node *btrfs_get_delayed_node( + struct btrfs_inode *btrfs_inode) { - struct btrfs_inode *btrfs_inode = BTRFS_I(inode); struct btrfs_root *root = btrfs_inode->root; - u64 ino = btrfs_ino(inode); + u64 ino = btrfs_ino(btrfs_inode); struct btrfs_delayed_node *node; - node = ACCESS_ONCE(btrfs_inode->delayed_node); + node = READ_ONCE(btrfs_inode->delayed_node); if (node) { atomic_inc(&node->refs); return node; @@ -107,16 +107,15 @@ static struct btrfs_delayed_node *btrfs_get_delayed_node(struct inode *inode) /* Will return either the node or PTR_ERR(-ENOMEM) */ static struct btrfs_delayed_node *btrfs_get_or_create_delayed_node( - struct inode *inode) + struct btrfs_inode *btrfs_inode) { struct btrfs_delayed_node *node; - struct btrfs_inode *btrfs_inode = BTRFS_I(inode); struct btrfs_root *root = btrfs_inode->root; - u64 ino = btrfs_ino(inode); + u64 ino = btrfs_ino(btrfs_inode); int ret; again: - node = btrfs_get_delayed_node(inode); + node = btrfs_get_delayed_node(btrfs_inode); if (node) return node; @@ -574,7 +573,7 @@ static void btrfs_delayed_item_release_metadata(struct btrfs_fs_info *fs_info, static int btrfs_delayed_inode_reserve_metadata( struct btrfs_trans_handle *trans, struct btrfs_root *root, - struct inode *inode, + struct btrfs_inode *inode, struct btrfs_delayed_node *node) { struct btrfs_fs_info *fs_info = root->fs_info; @@ -603,13 +602,13 @@ static int btrfs_delayed_inode_reserve_metadata( * worth which is less likely to hurt us. */ if (src_rsv && src_rsv->type == BTRFS_BLOCK_RSV_DELALLOC) { - spin_lock(&BTRFS_I(inode)->lock); + spin_lock(&inode->lock); if (test_and_clear_bit(BTRFS_INODE_DELALLOC_META_RESERVED, - &BTRFS_I(inode)->runtime_flags)) + &inode->runtime_flags)) release = true; else src_rsv = NULL; - spin_unlock(&BTRFS_I(inode)->lock); + spin_unlock(&inode->lock); } /* @@ -1196,7 +1195,7 @@ int btrfs_run_delayed_items_nr(struct btrfs_trans_handle *trans, } int btrfs_commit_inode_delayed_items(struct btrfs_trans_handle *trans, - struct inode *inode) + struct btrfs_inode *inode) { struct btrfs_delayed_node *delayed_node = btrfs_get_delayed_node(inode); struct btrfs_path *path; @@ -1233,9 +1232,9 @@ int btrfs_commit_inode_delayed_items(struct btrfs_trans_handle *trans, return ret; } -int btrfs_commit_inode_delayed_inode(struct inode *inode) +int btrfs_commit_inode_delayed_inode(struct btrfs_inode *inode) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb); struct btrfs_trans_handle *trans; struct btrfs_delayed_node *delayed_node = btrfs_get_delayed_node(inode); struct btrfs_path *path; @@ -1288,15 +1287,15 @@ out: return ret; } -void btrfs_remove_delayed_node(struct inode *inode) +void btrfs_remove_delayed_node(struct btrfs_inode *inode) { struct btrfs_delayed_node *delayed_node; - delayed_node = ACCESS_ONCE(BTRFS_I(inode)->delayed_node); + delayed_node = READ_ONCE(inode->delayed_node); if (!delayed_node) return; - BTRFS_I(inode)->delayed_node = NULL; + inode->delayed_node = NULL; btrfs_release_delayed_node(delayed_node); } @@ -1434,7 +1433,7 @@ void btrfs_balance_delayed_items(struct btrfs_fs_info *fs_info) int btrfs_insert_delayed_dir_index(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, const char *name, int name_len, - struct inode *dir, + struct btrfs_inode *dir, struct btrfs_disk_key *disk_key, u8 type, u64 index) { @@ -1510,7 +1509,7 @@ static int btrfs_delete_delayed_insertion_item(struct btrfs_fs_info *fs_info, int btrfs_delete_delayed_dir_index(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, - struct inode *dir, u64 index) + struct btrfs_inode *dir, u64 index) { struct btrfs_delayed_node *node; struct btrfs_delayed_item *item; @@ -1558,7 +1557,7 @@ end: return ret; } -int btrfs_inode_delayed_dir_index_count(struct inode *inode) +int btrfs_inode_delayed_dir_index_count(struct btrfs_inode *inode) { struct btrfs_delayed_node *delayed_node = btrfs_get_delayed_node(inode); @@ -1575,7 +1574,7 @@ int btrfs_inode_delayed_dir_index_count(struct inode *inode) return -EINVAL; } - BTRFS_I(inode)->index_cnt = delayed_node->index_cnt; + inode->index_cnt = delayed_node->index_cnt; btrfs_release_delayed_node(delayed_node); return 0; } @@ -1587,7 +1586,7 @@ bool btrfs_readdir_get_delayed_items(struct inode *inode, struct btrfs_delayed_node *delayed_node; struct btrfs_delayed_item *item; - delayed_node = btrfs_get_delayed_node(inode); + delayed_node = btrfs_get_delayed_node(BTRFS_I(inode)); if (!delayed_node) return false; @@ -1776,7 +1775,7 @@ int btrfs_fill_inode(struct inode *inode, u32 *rdev) struct btrfs_delayed_node *delayed_node; struct btrfs_inode_item *inode_item; - delayed_node = btrfs_get_delayed_node(inode); + delayed_node = btrfs_get_delayed_node(BTRFS_I(inode)); if (!delayed_node) return -ENOENT; @@ -1831,7 +1830,7 @@ int btrfs_delayed_update_inode(struct btrfs_trans_handle *trans, struct btrfs_delayed_node *delayed_node; int ret = 0; - delayed_node = btrfs_get_or_create_delayed_node(inode); + delayed_node = btrfs_get_or_create_delayed_node(BTRFS_I(inode)); if (IS_ERR(delayed_node)) return PTR_ERR(delayed_node); @@ -1841,7 +1840,7 @@ int btrfs_delayed_update_inode(struct btrfs_trans_handle *trans, goto release_node; } - ret = btrfs_delayed_inode_reserve_metadata(trans, root, inode, + ret = btrfs_delayed_inode_reserve_metadata(trans, root, BTRFS_I(inode), delayed_node); if (ret) goto release_node; @@ -1856,9 +1855,9 @@ release_node: return ret; } -int btrfs_delayed_delete_inode_ref(struct inode *inode) +int btrfs_delayed_delete_inode_ref(struct btrfs_inode *inode) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb); struct btrfs_delayed_node *delayed_node; /* @@ -1933,7 +1932,7 @@ static void __btrfs_kill_delayed_node(struct btrfs_delayed_node *delayed_node) mutex_unlock(&delayed_node->mutex); } -void btrfs_kill_delayed_inode_items(struct inode *inode) +void btrfs_kill_delayed_inode_items(struct btrfs_inode *inode) { struct btrfs_delayed_node *delayed_node; diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h index 8a2bf5e3e4cf..40327cc3b99a 100644 --- a/fs/btrfs/delayed-inode.h +++ b/fs/btrfs/delayed-inode.h @@ -101,15 +101,15 @@ static inline void btrfs_init_delayed_root( int btrfs_insert_delayed_dir_index(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, const char *name, int name_len, - struct inode *dir, + struct btrfs_inode *dir, struct btrfs_disk_key *disk_key, u8 type, u64 index); int btrfs_delete_delayed_dir_index(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, - struct inode *dir, u64 index); + struct btrfs_inode *dir, u64 index); -int btrfs_inode_delayed_dir_index_count(struct inode *inode); +int btrfs_inode_delayed_dir_index_count(struct btrfs_inode *inode); int btrfs_run_delayed_items(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info); @@ -119,17 +119,17 @@ int btrfs_run_delayed_items_nr(struct btrfs_trans_handle *trans, void btrfs_balance_delayed_items(struct btrfs_fs_info *fs_info); int btrfs_commit_inode_delayed_items(struct btrfs_trans_handle *trans, - struct inode *inode); + struct btrfs_inode *inode); /* Used for evicting the inode. */ -void btrfs_remove_delayed_node(struct inode *inode); -void btrfs_kill_delayed_inode_items(struct inode *inode); -int btrfs_commit_inode_delayed_inode(struct inode *inode); +void btrfs_remove_delayed_node(struct btrfs_inode *inode); +void btrfs_kill_delayed_inode_items(struct btrfs_inode *inode); +int btrfs_commit_inode_delayed_inode(struct btrfs_inode *inode); int btrfs_delayed_update_inode(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct inode *inode); int btrfs_fill_inode(struct inode *inode, u32 *rdev); -int btrfs_delayed_delete_inode_ref(struct inode *inode); +int btrfs_delayed_delete_inode_ref(struct btrfs_inode *inode); /* Used for drop dead root */ void btrfs_kill_all_delayed_nodes(struct btrfs_root *root); diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c index ef724a5fc30e..6eb80952efb3 100644 --- a/fs/btrfs/delayed-ref.c +++ b/fs/btrfs/delayed-ref.c @@ -550,13 +550,14 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info, struct btrfs_delayed_ref_node *ref, struct btrfs_qgroup_extent_record *qrecord, u64 bytenr, u64 num_bytes, u64 ref_root, u64 reserved, - int action, int is_data) + int action, int is_data, int *qrecord_inserted_ret) { struct btrfs_delayed_ref_head *existing; struct btrfs_delayed_ref_head *head_ref = NULL; struct btrfs_delayed_ref_root *delayed_refs; int count_mod = 1; int must_insert_reserved = 0; + int qrecord_inserted = 0; /* If reserved is provided, it must be a data extent. */ BUG_ON(!is_data && reserved); @@ -623,6 +624,8 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info, if(btrfs_qgroup_trace_extent_nolock(fs_info, delayed_refs, qrecord)) kfree(qrecord); + else + qrecord_inserted = 1; } spin_lock_init(&head_ref->lock); @@ -650,6 +653,8 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info, atomic_inc(&delayed_refs->num_entries); trans->delayed_ref_updates++; } + if (qrecord_inserted_ret) + *qrecord_inserted_ret = qrecord_inserted; return head_ref; } @@ -779,6 +784,7 @@ int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info, struct btrfs_delayed_ref_head *head_ref; struct btrfs_delayed_ref_root *delayed_refs; struct btrfs_qgroup_extent_record *record = NULL; + int qrecord_inserted; BUG_ON(extent_op && extent_op->is_data); ref = kmem_cache_alloc(btrfs_delayed_tree_ref_cachep, GFP_NOFS); @@ -806,12 +812,15 @@ int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info, * the spin lock */ head_ref = add_delayed_ref_head(fs_info, trans, &head_ref->node, record, - bytenr, num_bytes, 0, 0, action, 0); + bytenr, num_bytes, 0, 0, action, 0, + &qrecord_inserted); add_delayed_tree_ref(fs_info, trans, head_ref, &ref->node, bytenr, num_bytes, parent, ref_root, level, action); spin_unlock(&delayed_refs->lock); + if (qrecord_inserted) + return btrfs_qgroup_trace_extent_post(fs_info, record); return 0; free_head_ref: @@ -829,15 +838,14 @@ int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info, struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, u64 parent, u64 ref_root, - u64 owner, u64 offset, u64 reserved, int action, - struct btrfs_delayed_extent_op *extent_op) + u64 owner, u64 offset, u64 reserved, int action) { struct btrfs_delayed_data_ref *ref; struct btrfs_delayed_ref_head *head_ref; struct btrfs_delayed_ref_root *delayed_refs; struct btrfs_qgroup_extent_record *record = NULL; + int qrecord_inserted; - BUG_ON(extent_op && !extent_op->is_data); ref = kmem_cache_alloc(btrfs_delayed_data_ref_cachep, GFP_NOFS); if (!ref) return -ENOMEM; @@ -859,7 +867,7 @@ int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info, } } - head_ref->extent_op = extent_op; + head_ref->extent_op = NULL; delayed_refs = &trans->transaction->delayed_refs; spin_lock(&delayed_refs->lock); @@ -870,13 +878,15 @@ int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info, */ head_ref = add_delayed_ref_head(fs_info, trans, &head_ref->node, record, bytenr, num_bytes, ref_root, reserved, - action, 1); + action, 1, &qrecord_inserted); add_delayed_data_ref(fs_info, trans, head_ref, &ref->node, bytenr, num_bytes, parent, ref_root, owner, offset, action); spin_unlock(&delayed_refs->lock); + if (qrecord_inserted) + return btrfs_qgroup_trace_extent_post(fs_info, record); return 0; } @@ -899,7 +909,7 @@ int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info, add_delayed_ref_head(fs_info, trans, &head_ref->node, NULL, bytenr, num_bytes, 0, 0, BTRFS_UPDATE_DELAYED_HEAD, - extent_op->is_data); + extent_op->is_data, NULL); spin_unlock(&delayed_refs->lock); return 0; @@ -911,11 +921,8 @@ int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info, * the head node if any where found, or NULL if not. */ struct btrfs_delayed_ref_head * -btrfs_find_delayed_ref_head(struct btrfs_trans_handle *trans, u64 bytenr) +btrfs_find_delayed_ref_head(struct btrfs_delayed_ref_root *delayed_refs, u64 bytenr) { - struct btrfs_delayed_ref_root *delayed_refs; - - delayed_refs = &trans->transaction->delayed_refs; return find_ref_head(&delayed_refs->href_root, bytenr, 0); } diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h index 50947b5a9152..0e537f98f1a1 100644 --- a/fs/btrfs/delayed-ref.h +++ b/fs/btrfs/delayed-ref.h @@ -250,8 +250,7 @@ int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info, struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, u64 parent, u64 ref_root, - u64 owner, u64 offset, u64 reserved, int action, - struct btrfs_delayed_extent_op *extent_op); + u64 owner, u64 offset, u64 reserved, int action); int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info, struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, @@ -262,7 +261,8 @@ void btrfs_merge_delayed_refs(struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_head *head); struct btrfs_delayed_ref_head * -btrfs_find_delayed_ref_head(struct btrfs_trans_handle *trans, u64 bytenr); +btrfs_find_delayed_ref_head(struct btrfs_delayed_ref_root *delayed_refs, + u64 bytenr); int btrfs_delayed_ref_lock(struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_head *head); static inline void btrfs_delayed_ref_unlock(struct btrfs_delayed_ref_head *head) diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c index b039fe0c751a..724504a2d7ac 100644 --- a/fs/btrfs/dir-item.c +++ b/fs/btrfs/dir-item.c @@ -133,7 +133,7 @@ int btrfs_insert_dir_item(struct btrfs_trans_handle *trans, struct btrfs_root struct btrfs_disk_key disk_key; u32 data_size; - key.objectid = btrfs_ino(dir); + key.objectid = btrfs_ino(BTRFS_I(dir)); key.type = BTRFS_DIR_ITEM_KEY; key.offset = btrfs_name_hash(name, name_len); @@ -174,8 +174,7 @@ second_insert: btrfs_release_path(path); ret2 = btrfs_insert_delayed_dir_index(trans, root->fs_info, name, - name_len, dir, &disk_key, type, - index); + name_len, BTRFS_I(dir), &disk_key, type, index); out_free: btrfs_free_path(path); if (ret) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 18004169552c..207db0270b15 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -64,8 +64,7 @@ static const struct extent_io_ops btree_extent_io_ops; static void end_workqueue_fn(struct btrfs_work *work); static void free_fs_root(struct btrfs_root *root); -static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info, - int read_only); +static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info); static void btrfs_destroy_ordered_extents(struct btrfs_root *root); static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, struct btrfs_fs_info *fs_info); @@ -1005,7 +1004,7 @@ static int __btree_submit_bio_done(struct inode *inode, struct bio *bio, return ret; } -static int check_async_write(struct inode *inode, unsigned long bio_flags) +static int check_async_write(unsigned long bio_flags) { if (bio_flags & EXTENT_BIO_TREE_LOG) return 0; @@ -1021,7 +1020,7 @@ static int btree_submit_bio_hook(struct inode *inode, struct bio *bio, u64 bio_offset) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - int async = check_async_write(inode, bio_flags); + int async = check_async_write(bio_flags); int ret; if (bio_op(bio) != REQ_OP_WRITE) { @@ -1248,8 +1247,7 @@ struct extent_buffer *read_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr, } -void clean_tree_block(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, +void clean_tree_block(struct btrfs_fs_info *fs_info, struct extent_buffer *buf) { if (btrfs_header_generation(buf) == @@ -1800,7 +1798,7 @@ static int btrfs_congested_fn(void *congested_data, int bdi_bits) list_for_each_entry_rcu(device, &info->fs_devices->devices, dev_list) { if (!device->bdev) continue; - bdi = blk_get_backing_dev_info(device->bdev); + bdi = device->bdev->bd_bdi; if (bdi_congested(bdi, bdi_bits)) { ret = 1; break; @@ -2802,7 +2800,7 @@ int open_ctree(struct super_block *sb, memcpy(fs_info->fsid, fs_info->super_copy->fsid, BTRFS_FSID_SIZE); - ret = btrfs_check_super_valid(fs_info, sb->s_flags & MS_RDONLY); + ret = btrfs_check_super_valid(fs_info); if (ret) { btrfs_err(fs_info, "superblock contains fatal errors"); err = -EINVAL; @@ -3411,7 +3409,7 @@ struct buffer_head *btrfs_read_dev_super(struct block_device *bdev) */ static int write_dev_supers(struct btrfs_device *device, struct btrfs_super_block *sb, - int do_barriers, int wait, int max_mirrors) + int wait, int max_mirrors) { struct buffer_head *bh; int i; @@ -3696,7 +3694,7 @@ int btrfs_calc_num_tolerated_disk_barrier_failures( return num_tolerated_disk_barrier_failures; } -static int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors) +int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors) { struct list_head *head; struct btrfs_device *dev; @@ -3753,7 +3751,7 @@ static int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors) flags = btrfs_super_flags(sb); btrfs_set_super_flags(sb, flags | BTRFS_HEADER_FLAG_WRITTEN); - ret = write_dev_supers(dev, sb, do_barriers, 0, max_mirrors); + ret = write_dev_supers(dev, sb, 0, max_mirrors); if (ret) total_errors++; } @@ -3776,7 +3774,7 @@ static int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors) if (!dev->in_fs_metadata || !dev->writeable) continue; - ret = write_dev_supers(dev, sb, do_barriers, 1, max_mirrors); + ret = write_dev_supers(dev, sb, 1, max_mirrors); if (ret) total_errors++; } @@ -3790,12 +3788,6 @@ static int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors) return 0; } -int write_ctree_super(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, int max_mirrors) -{ - return write_all_supers(fs_info, max_mirrors); -} - /* Drop a fs root from the radix tree and free it. */ void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info, struct btrfs_root *root) @@ -4122,8 +4114,7 @@ int btrfs_read_buffer(struct extent_buffer *buf, u64 parent_transid) return btree_read_extent_buffer_pages(fs_info, buf, parent_transid); } -static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info, - int read_only) +static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info) { struct btrfs_super_block *sb = fs_info->super_copy; u64 nodesize = btrfs_super_nodesize(sb); diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index 44dcd9af6b7c..0be2d4fe705b 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -52,14 +52,12 @@ int reada_tree_block_flagged(struct btrfs_fs_info *fs_info, u64 bytenr, struct extent_buffer *btrfs_find_create_tree_block( struct btrfs_fs_info *fs_info, u64 bytenr); -void clean_tree_block(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, struct extent_buffer *buf); +void clean_tree_block(struct btrfs_fs_info *fs_info, struct extent_buffer *buf); int open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_devices, char *options); void close_ctree(struct btrfs_fs_info *fs_info); -int write_ctree_super(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, int max_mirrors); +int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors); struct buffer_head *btrfs_read_dev_super(struct block_device *bdev); int btrfs_read_dev_one_super(struct block_device *bdev, int copy_num, struct buffer_head **bh_ret); diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c index 340d90751263..87144c9f9593 100644 --- a/fs/btrfs/export.c +++ b/fs/btrfs/export.c @@ -30,7 +30,7 @@ static int btrfs_encode_fh(struct inode *inode, u32 *fh, int *max_len, len = BTRFS_FID_SIZE_NON_CONNECTABLE; type = FILEID_BTRFS_WITHOUT_PARENT; - fid->objectid = btrfs_ino(inode); + fid->objectid = btrfs_ino(BTRFS_I(inode)); fid->root_objectid = BTRFS_I(inode)->root->objectid; fid->gen = inode->i_generation; @@ -166,13 +166,13 @@ static struct dentry *btrfs_get_parent(struct dentry *child) if (!path) return ERR_PTR(-ENOMEM); - if (btrfs_ino(dir) == BTRFS_FIRST_FREE_OBJECTID) { + if (btrfs_ino(BTRFS_I(dir)) == BTRFS_FIRST_FREE_OBJECTID) { key.objectid = root->root_key.objectid; key.type = BTRFS_ROOT_BACKREF_KEY; key.offset = (u64)-1; root = fs_info->tree_root; } else { - key.objectid = btrfs_ino(dir); + key.objectid = btrfs_ino(BTRFS_I(dir)); key.type = BTRFS_INODE_REF_KEY; key.offset = (u64)-1; } @@ -235,13 +235,10 @@ static int btrfs_get_name(struct dentry *parent, char *name, int ret; u64 ino; - if (!dir || !inode) - return -EINVAL; - if (!S_ISDIR(dir->i_mode)) return -EINVAL; - ino = btrfs_ino(inode); + ino = btrfs_ino(BTRFS_I(inode)); path = btrfs_alloc_path(); if (!path) @@ -255,7 +252,7 @@ static int btrfs_get_name(struct dentry *parent, char *name, root = fs_info->tree_root; } else { key.objectid = ino; - key.offset = btrfs_ino(dir); + key.offset = btrfs_ino(BTRFS_I(dir)); key.type = BTRFS_INODE_REF_KEY; } diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index dcd2e798767e..c35b96633554 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -888,7 +888,7 @@ search_again: delayed_refs = &trans->transaction->delayed_refs; spin_lock(&delayed_refs->lock); - head = btrfs_find_delayed_ref_head(trans, bytenr); + head = btrfs_find_delayed_ref_head(delayed_refs, bytenr); if (head) { if (!mutex_trylock(&head->mutex)) { atomic_inc(&head->node.refs); @@ -1035,10 +1035,11 @@ out_free: #ifdef BTRFS_COMPAT_EXTENT_TREE_V0 static int convert_extent_item_v0(struct btrfs_trans_handle *trans, - struct btrfs_root *root, + struct btrfs_fs_info *fs_info, struct btrfs_path *path, u64 owner, u32 extra_size) { + struct btrfs_root *root = fs_info->extent_root; struct btrfs_extent_item *item; struct btrfs_extent_item_v0 *ei0; struct btrfs_extent_ref_v0 *ref0; @@ -1092,7 +1093,7 @@ static int convert_extent_item_v0(struct btrfs_trans_handle *trans, return ret; BUG_ON(ret); /* Corruption */ - btrfs_extend_item(root->fs_info, path, new_size); + btrfs_extend_item(fs_info, path, new_size); leaf = path->nodes[0]; item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item); @@ -1151,12 +1152,13 @@ static int match_extent_data_ref(struct extent_buffer *leaf, } static noinline int lookup_extent_data_ref(struct btrfs_trans_handle *trans, - struct btrfs_root *root, + struct btrfs_fs_info *fs_info, struct btrfs_path *path, u64 bytenr, u64 parent, u64 root_objectid, u64 owner, u64 offset) { + struct btrfs_root *root = fs_info->extent_root; struct btrfs_key key; struct btrfs_extent_data_ref *ref; struct extent_buffer *leaf; @@ -1238,12 +1240,13 @@ fail: } static noinline int insert_extent_data_ref(struct btrfs_trans_handle *trans, - struct btrfs_root *root, + struct btrfs_fs_info *fs_info, struct btrfs_path *path, u64 bytenr, u64 parent, u64 root_objectid, u64 owner, u64 offset, int refs_to_add) { + struct btrfs_root *root = fs_info->extent_root; struct btrfs_key key; struct extent_buffer *leaf; u32 size; @@ -1317,7 +1320,7 @@ fail: } static noinline int remove_extent_data_ref(struct btrfs_trans_handle *trans, - struct btrfs_root *root, + struct btrfs_fs_info *fs_info, struct btrfs_path *path, int refs_to_drop, int *last_ref) { @@ -1354,7 +1357,7 @@ static noinline int remove_extent_data_ref(struct btrfs_trans_handle *trans, num_refs -= refs_to_drop; if (num_refs == 0) { - ret = btrfs_del_item(trans, root, path); + ret = btrfs_del_item(trans, fs_info->extent_root, path); *last_ref = 1; } else { if (key.type == BTRFS_EXTENT_DATA_REF_KEY) @@ -1416,11 +1419,12 @@ static noinline u32 extent_data_ref_count(struct btrfs_path *path, } static noinline int lookup_tree_block_ref(struct btrfs_trans_handle *trans, - struct btrfs_root *root, + struct btrfs_fs_info *fs_info, struct btrfs_path *path, u64 bytenr, u64 parent, u64 root_objectid) { + struct btrfs_root *root = fs_info->extent_root; struct btrfs_key key; int ret; @@ -1449,7 +1453,7 @@ static noinline int lookup_tree_block_ref(struct btrfs_trans_handle *trans, } static noinline int insert_tree_block_ref(struct btrfs_trans_handle *trans, - struct btrfs_root *root, + struct btrfs_fs_info *fs_info, struct btrfs_path *path, u64 bytenr, u64 parent, u64 root_objectid) @@ -1466,7 +1470,8 @@ static noinline int insert_tree_block_ref(struct btrfs_trans_handle *trans, key.offset = root_objectid; } - ret = btrfs_insert_empty_item(trans, root, path, &key, 0); + ret = btrfs_insert_empty_item(trans, fs_info->extent_root, + path, &key, 0); btrfs_release_path(path); return ret; } @@ -1524,14 +1529,14 @@ static int find_next_key(struct btrfs_path *path, int level, */ static noinline_for_stack int lookup_inline_extent_backref(struct btrfs_trans_handle *trans, - struct btrfs_root *root, + struct btrfs_fs_info *fs_info, struct btrfs_path *path, struct btrfs_extent_inline_ref **ref_ret, u64 bytenr, u64 num_bytes, u64 parent, u64 root_objectid, u64 owner, u64 offset, int insert) { - struct btrfs_fs_info *fs_info = root->fs_info; + struct btrfs_root *root = fs_info->extent_root; struct btrfs_key key; struct extent_buffer *leaf; struct btrfs_extent_item *ei; @@ -1614,7 +1619,7 @@ again: err = -ENOENT; goto out; } - ret = convert_extent_item_v0(trans, root, path, owner, + ret = convert_extent_item_v0(trans, fs_info, path, owner, extra_size); if (ret < 0) { err = ret; @@ -1716,7 +1721,7 @@ out: * helper to add new inline back ref */ static noinline_for_stack -void setup_inline_extent_backref(struct btrfs_root *root, +void setup_inline_extent_backref(struct btrfs_fs_info *fs_info, struct btrfs_path *path, struct btrfs_extent_inline_ref *iref, u64 parent, u64 root_objectid, @@ -1739,7 +1744,7 @@ void setup_inline_extent_backref(struct btrfs_root *root, type = extent_ref_type(parent, owner); size = btrfs_extent_inline_ref_size(type); - btrfs_extend_item(root->fs_info, path, size); + btrfs_extend_item(fs_info, path, size); ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item); refs = btrfs_extent_refs(leaf, ei); @@ -1777,7 +1782,7 @@ void setup_inline_extent_backref(struct btrfs_root *root, } static int lookup_extent_backref(struct btrfs_trans_handle *trans, - struct btrfs_root *root, + struct btrfs_fs_info *fs_info, struct btrfs_path *path, struct btrfs_extent_inline_ref **ref_ret, u64 bytenr, u64 num_bytes, u64 parent, @@ -1785,7 +1790,7 @@ static int lookup_extent_backref(struct btrfs_trans_handle *trans, { int ret; - ret = lookup_inline_extent_backref(trans, root, path, ref_ret, + ret = lookup_inline_extent_backref(trans, fs_info, path, ref_ret, bytenr, num_bytes, parent, root_objectid, owner, offset, 0); if (ret != -ENOENT) @@ -1795,11 +1800,12 @@ static int lookup_extent_backref(struct btrfs_trans_handle *trans, *ref_ret = NULL; if (owner < BTRFS_FIRST_FREE_OBJECTID) { - ret = lookup_tree_block_ref(trans, root, path, bytenr, parent, - root_objectid); + ret = lookup_tree_block_ref(trans, fs_info, path, bytenr, + parent, root_objectid); } else { - ret = lookup_extent_data_ref(trans, root, path, bytenr, parent, - root_objectid, owner, offset); + ret = lookup_extent_data_ref(trans, fs_info, path, bytenr, + parent, root_objectid, owner, + offset); } return ret; } @@ -1808,7 +1814,7 @@ static int lookup_extent_backref(struct btrfs_trans_handle *trans, * helper to update/remove inline back ref */ static noinline_for_stack -void update_inline_extent_backref(struct btrfs_root *root, +void update_inline_extent_backref(struct btrfs_fs_info *fs_info, struct btrfs_path *path, struct btrfs_extent_inline_ref *iref, int refs_to_mod, @@ -1866,14 +1872,14 @@ void update_inline_extent_backref(struct btrfs_root *root, memmove_extent_buffer(leaf, ptr, ptr + size, end - ptr - size); item_size -= size; - btrfs_truncate_item(root->fs_info, path, item_size, 1); + btrfs_truncate_item(fs_info, path, item_size, 1); } btrfs_mark_buffer_dirty(leaf); } static noinline_for_stack int insert_inline_extent_backref(struct btrfs_trans_handle *trans, - struct btrfs_root *root, + struct btrfs_fs_info *fs_info, struct btrfs_path *path, u64 bytenr, u64 num_bytes, u64 parent, u64 root_objectid, u64 owner, @@ -1883,15 +1889,15 @@ int insert_inline_extent_backref(struct btrfs_trans_handle *trans, struct btrfs_extent_inline_ref *iref; int ret; - ret = lookup_inline_extent_backref(trans, root, path, &iref, + ret = lookup_inline_extent_backref(trans, fs_info, path, &iref, bytenr, num_bytes, parent, root_objectid, owner, offset, 1); if (ret == 0) { BUG_ON(owner < BTRFS_FIRST_FREE_OBJECTID); - update_inline_extent_backref(root, path, iref, + update_inline_extent_backref(fs_info, path, iref, refs_to_add, extent_op, NULL); } else if (ret == -ENOENT) { - setup_inline_extent_backref(root, path, iref, parent, + setup_inline_extent_backref(fs_info, path, iref, parent, root_objectid, owner, offset, refs_to_add, extent_op); ret = 0; @@ -1900,7 +1906,7 @@ int insert_inline_extent_backref(struct btrfs_trans_handle *trans, } static int insert_extent_backref(struct btrfs_trans_handle *trans, - struct btrfs_root *root, + struct btrfs_fs_info *fs_info, struct btrfs_path *path, u64 bytenr, u64 parent, u64 root_objectid, u64 owner, u64 offset, int refs_to_add) @@ -1908,10 +1914,10 @@ static int insert_extent_backref(struct btrfs_trans_handle *trans, int ret; if (owner < BTRFS_FIRST_FREE_OBJECTID) { BUG_ON(refs_to_add != 1); - ret = insert_tree_block_ref(trans, root, path, bytenr, + ret = insert_tree_block_ref(trans, fs_info, path, bytenr, parent, root_objectid); } else { - ret = insert_extent_data_ref(trans, root, path, bytenr, + ret = insert_extent_data_ref(trans, fs_info, path, bytenr, parent, root_objectid, owner, offset, refs_to_add); } @@ -1919,7 +1925,7 @@ static int insert_extent_backref(struct btrfs_trans_handle *trans, } static int remove_extent_backref(struct btrfs_trans_handle *trans, - struct btrfs_root *root, + struct btrfs_fs_info *fs_info, struct btrfs_path *path, struct btrfs_extent_inline_ref *iref, int refs_to_drop, int is_data, int *last_ref) @@ -1928,14 +1934,14 @@ static int remove_extent_backref(struct btrfs_trans_handle *trans, BUG_ON(!is_data && refs_to_drop != 1); if (iref) { - update_inline_extent_backref(root, path, iref, + update_inline_extent_backref(fs_info, path, iref, -refs_to_drop, NULL, last_ref); } else if (is_data) { - ret = remove_extent_data_ref(trans, root, path, refs_to_drop, + ret = remove_extent_data_ref(trans, fs_info, path, refs_to_drop, last_ref); } else { *last_ref = 1; - ret = btrfs_del_item(trans, root, path); + ret = btrfs_del_item(trans, fs_info->extent_root, path); } return ret; } @@ -2089,7 +2095,7 @@ int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, ret = btrfs_add_delayed_data_ref(fs_info, trans, bytenr, num_bytes, parent, root_objectid, owner, offset, 0, - BTRFS_ADD_DELAYED_REF, NULL); + BTRFS_ADD_DELAYED_REF); } return ret; } @@ -2117,9 +2123,9 @@ static int __btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, path->reada = READA_FORWARD; path->leave_spinning = 1; /* this will setup the path even if it fails to insert the back ref */ - ret = insert_inline_extent_backref(trans, fs_info->extent_root, path, - bytenr, num_bytes, parent, - root_objectid, owner, offset, + ret = insert_inline_extent_backref(trans, fs_info, path, bytenr, + num_bytes, parent, root_objectid, + owner, offset, refs_to_add, extent_op); if ((ret < 0 && ret != -EAGAIN) || !ret) goto out; @@ -2143,9 +2149,8 @@ static int __btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, path->reada = READA_FORWARD; path->leave_spinning = 1; /* now insert the actual backref */ - ret = insert_extent_backref(trans, fs_info->extent_root, - path, bytenr, parent, root_objectid, - owner, offset, refs_to_add); + ret = insert_extent_backref(trans, fs_info, path, bytenr, parent, + root_objectid, owner, offset, refs_to_add); if (ret) btrfs_abort_transaction(trans, ret); out: @@ -2290,8 +2295,7 @@ again: item_size = btrfs_item_size_nr(leaf, path->slots[0]); #ifdef BTRFS_COMPAT_EXTENT_TREE_V0 if (item_size < sizeof(*ei)) { - ret = convert_extent_item_v0(trans, fs_info->extent_root, - path, (u64)-1, 0); + ret = convert_extent_item_v0(trans, fs_info, path, (u64)-1, 0); if (ret < 0) { err = ret; goto out; @@ -3028,8 +3032,7 @@ int btrfs_set_disk_extent_flags(struct btrfs_trans_handle *trans, return ret; } -static noinline int check_delayed_ref(struct btrfs_trans_handle *trans, - struct btrfs_root *root, +static noinline int check_delayed_ref(struct btrfs_root *root, struct btrfs_path *path, u64 objectid, u64 offset, u64 bytenr) { @@ -3037,11 +3040,16 @@ static noinline int check_delayed_ref(struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_node *ref; struct btrfs_delayed_data_ref *data_ref; struct btrfs_delayed_ref_root *delayed_refs; + struct btrfs_transaction *cur_trans; int ret = 0; - delayed_refs = &trans->transaction->delayed_refs; + cur_trans = root->fs_info->running_transaction; + if (!cur_trans) + return 0; + + delayed_refs = &cur_trans->delayed_refs; spin_lock(&delayed_refs->lock); - head = btrfs_find_delayed_ref_head(trans, bytenr); + head = btrfs_find_delayed_ref_head(delayed_refs, bytenr); if (!head) { spin_unlock(&delayed_refs->lock); return 0; @@ -3090,8 +3098,7 @@ static noinline int check_delayed_ref(struct btrfs_trans_handle *trans, return ret; } -static noinline int check_committed_ref(struct btrfs_trans_handle *trans, - struct btrfs_root *root, +static noinline int check_committed_ref(struct btrfs_root *root, struct btrfs_path *path, u64 objectid, u64 offset, u64 bytenr) { @@ -3162,9 +3169,8 @@ out: return ret; } -int btrfs_cross_ref_exist(struct btrfs_trans_handle *trans, - struct btrfs_root *root, - u64 objectid, u64 offset, u64 bytenr) +int btrfs_cross_ref_exist(struct btrfs_root *root, u64 objectid, u64 offset, + u64 bytenr) { struct btrfs_path *path; int ret; @@ -3175,12 +3181,12 @@ int btrfs_cross_ref_exist(struct btrfs_trans_handle *trans, return -ENOENT; do { - ret = check_committed_ref(trans, root, path, objectid, + ret = check_committed_ref(root, path, objectid, offset, bytenr); if (ret && ret != -ENOENT) goto out; - ret2 = check_delayed_ref(trans, root, path, objectid, + ret2 = check_delayed_ref(root, path, objectid, offset, bytenr); } while (ret2 == -EAGAIN); @@ -3368,7 +3374,7 @@ static int cache_save_setup(struct btrfs_block_group_cache *block_group, if (trans->aborted) return 0; again: - inode = lookup_free_space_inode(root, block_group, path); + inode = lookup_free_space_inode(fs_info, block_group, path); if (IS_ERR(inode) && PTR_ERR(inode) != -ENOENT) { ret = PTR_ERR(inode); btrfs_release_path(path); @@ -3382,7 +3388,8 @@ again: if (block_group->ro) goto out_free; - ret = create_free_space_inode(root, trans, block_group, path); + ret = create_free_space_inode(fs_info, trans, block_group, + path); if (ret) goto out_free; goto again; @@ -3424,7 +3431,7 @@ again: if (ret) goto out_put; - ret = btrfs_truncate_free_space_cache(root, trans, NULL, inode); + ret = btrfs_truncate_free_space_cache(trans, NULL, inode); if (ret) goto out_put; } @@ -4119,6 +4126,15 @@ u64 btrfs_get_alloc_profile(struct btrfs_root *root, int data) return ret; } +static u64 btrfs_space_info_used(struct btrfs_space_info *s_info, + bool may_use_included) +{ + ASSERT(s_info); + return s_info->bytes_used + s_info->bytes_reserved + + s_info->bytes_pinned + s_info->bytes_readonly + + (may_use_included ? s_info->bytes_may_use : 0); +} + int btrfs_alloc_data_chunk_ondemand(struct inode *inode, u64 bytes) { struct btrfs_space_info *data_sinfo; @@ -4144,9 +4160,7 @@ int btrfs_alloc_data_chunk_ondemand(struct inode *inode, u64 bytes) again: /* make sure we have enough space to handle the data first */ spin_lock(&data_sinfo->lock); - used = data_sinfo->bytes_used + data_sinfo->bytes_reserved + - data_sinfo->bytes_pinned + data_sinfo->bytes_readonly + - data_sinfo->bytes_may_use; + used = btrfs_space_info_used(data_sinfo, true); if (used + bytes > data_sinfo->total_bytes) { struct btrfs_trans_handle *trans; @@ -4421,9 +4435,7 @@ void check_system_chunk(struct btrfs_trans_handle *trans, info = __find_space_info(fs_info, BTRFS_BLOCK_GROUP_SYSTEM); spin_lock(&info->lock); - left = info->total_bytes - info->bytes_used - info->bytes_pinned - - info->bytes_reserved - info->bytes_readonly - - info->bytes_may_use; + left = info->total_bytes - btrfs_space_info_used(info, true); spin_unlock(&info->lock); num_devs = get_profile_num_devs(fs_info, type); @@ -4606,8 +4618,7 @@ static int can_overcommit(struct btrfs_root *root, return 0; profile = btrfs_get_alloc_profile(root, 0); - used = space_info->bytes_used + space_info->bytes_reserved + - space_info->bytes_pinned + space_info->bytes_readonly; + used = btrfs_space_info_used(space_info, false); /* * We only want to allow over committing if we have lots of actual space @@ -4787,11 +4798,10 @@ skip_async: * get us somewhere and then commit the transaction if it does. Otherwise it * will return -ENOSPC. */ -static int may_commit_transaction(struct btrfs_root *root, +static int may_commit_transaction(struct btrfs_fs_info *fs_info, struct btrfs_space_info *space_info, u64 bytes, int force) { - struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_block_rsv *delayed_rsv = &fs_info->delayed_block_rsv; struct btrfs_trans_handle *trans; @@ -4823,7 +4833,7 @@ static int may_commit_transaction(struct btrfs_root *root, spin_unlock(&delayed_rsv->lock); commit: - trans = btrfs_join_transaction(root); + trans = btrfs_join_transaction(fs_info->fs_root); if (IS_ERR(trans)) return -ENOSPC; @@ -4837,11 +4847,11 @@ struct reserve_ticket { wait_queue_head_t wait; }; -static int flush_space(struct btrfs_root *root, +static int flush_space(struct btrfs_fs_info *fs_info, struct btrfs_space_info *space_info, u64 num_bytes, u64 orig_bytes, int state) { - struct btrfs_fs_info *fs_info = root->fs_info; + struct btrfs_root *root = fs_info->fs_root; struct btrfs_trans_handle *trans; int nr; int ret = 0; @@ -4881,7 +4891,8 @@ static int flush_space(struct btrfs_root *root, ret = 0; break; case COMMIT_TRANS: - ret = may_commit_transaction(root, space_info, orig_bytes, 0); + ret = may_commit_transaction(fs_info, space_info, + orig_bytes, 0); break; default: ret = -ENOSPC; @@ -4993,8 +5004,8 @@ static void btrfs_async_reclaim_metadata_space(struct work_struct *work) struct reserve_ticket *ticket; int ret; - ret = flush_space(fs_info->fs_root, space_info, to_reclaim, - to_reclaim, flush_state); + ret = flush_space(fs_info, space_info, to_reclaim, to_reclaim, + flush_state); spin_lock(&space_info->lock); if (list_empty(&space_info->tickets)) { space_info->flush = 0; @@ -5049,8 +5060,8 @@ static void priority_reclaim_metadata_space(struct btrfs_fs_info *fs_info, spin_unlock(&space_info->lock); do { - flush_space(fs_info->fs_root, space_info, to_reclaim, - to_reclaim, flush_state); + flush_space(fs_info, space_info, to_reclaim, to_reclaim, + flush_state); flush_state++; spin_lock(&space_info->lock); if (ticket->bytes == 0) { @@ -5135,9 +5146,7 @@ static int __reserve_metadata_bytes(struct btrfs_root *root, spin_lock(&space_info->lock); ret = -ENOSPC; - used = space_info->bytes_used + space_info->bytes_reserved + - space_info->bytes_pinned + space_info->bytes_readonly + - space_info->bytes_may_use; + used = btrfs_space_info_used(space_info, true); /* * If we have enough space then hooray, make our reservation and carry @@ -5630,9 +5639,7 @@ static void update_global_block_rsv(struct btrfs_fs_info *fs_info) block_rsv->size = min_t(u64, num_bytes, SZ_512M); if (block_rsv->reserved < block_rsv->size) { - num_bytes = sinfo->bytes_used + sinfo->bytes_pinned + - sinfo->bytes_reserved + sinfo->bytes_readonly + - sinfo->bytes_may_use; + num_bytes = btrfs_space_info_used(sinfo, true); if (sinfo->total_bytes > num_bytes) { num_bytes = sinfo->total_bytes - num_bytes; num_bytes = min(num_bytes, @@ -5756,7 +5763,7 @@ int btrfs_orphan_reserve_metadata(struct btrfs_trans_handle *trans, u64 num_bytes = btrfs_calc_trans_metadata_size(fs_info, 1); trace_btrfs_space_reservation(fs_info, "orphan", - btrfs_ino(inode), num_bytes, 1); + btrfs_ino(BTRFS_I(inode)), num_bytes, 1); return btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes, 1); } @@ -5767,7 +5774,7 @@ void btrfs_orphan_release_metadata(struct inode *inode) u64 num_bytes = btrfs_calc_trans_metadata_size(fs_info, 1); trace_btrfs_space_reservation(fs_info, "orphan", - btrfs_ino(inode), num_bytes, 0); + btrfs_ino(BTRFS_I(inode)), num_bytes, 0); btrfs_block_rsv_release(fs_info, root->orphan_block_rsv, num_bytes); } @@ -5799,7 +5806,7 @@ int btrfs_subvolume_reserve_metadata(struct btrfs_root *root, if (test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) { /* One for parent inode, two for dir entries */ num_bytes = 3 * fs_info->nodesize; - ret = btrfs_qgroup_reserve_meta(root, num_bytes); + ret = btrfs_qgroup_reserve_meta(root, num_bytes, true); if (ret) return ret; } else { @@ -5824,8 +5831,7 @@ int btrfs_subvolume_reserve_metadata(struct btrfs_root *root, } void btrfs_subvolume_release_metadata(struct btrfs_fs_info *fs_info, - struct btrfs_block_rsv *rsv, - u64 qgroup_reserved) + struct btrfs_block_rsv *rsv) { btrfs_block_rsv_release(fs_info, rsv, (u64)-1); } @@ -5844,11 +5850,9 @@ static unsigned drop_outstanding_extent(struct inode *inode, u64 num_bytes) { unsigned drop_inode_space = 0; unsigned dropped_extents = 0; - unsigned num_extents = 0; + unsigned num_extents; - num_extents = (unsigned)div64_u64(num_bytes + - BTRFS_MAX_EXTENT_SIZE - 1, - BTRFS_MAX_EXTENT_SIZE); + num_extents = count_max_extents(num_bytes); ASSERT(num_extents); ASSERT(BTRFS_I(inode)->outstanding_extents >= num_extents); BTRFS_I(inode)->outstanding_extents -= num_extents; @@ -5927,7 +5931,7 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes) struct btrfs_block_rsv *block_rsv = &fs_info->delalloc_block_rsv; u64 to_reserve = 0; u64 csum_bytes; - unsigned nr_extents = 0; + unsigned nr_extents; enum btrfs_reserve_flush_enum flush = BTRFS_RESERVE_FLUSH_ALL; int ret = 0; bool delalloc_lock = true; @@ -5960,9 +5964,7 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes) num_bytes = ALIGN(num_bytes, fs_info->sectorsize); spin_lock(&BTRFS_I(inode)->lock); - nr_extents = (unsigned)div64_u64(num_bytes + - BTRFS_MAX_EXTENT_SIZE - 1, - BTRFS_MAX_EXTENT_SIZE); + nr_extents = count_max_extents(num_bytes); BTRFS_I(inode)->outstanding_extents += nr_extents; nr_extents = 0; @@ -5979,7 +5981,7 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes) if (test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) { ret = btrfs_qgroup_reserve_meta(root, - nr_extents * fs_info->nodesize); + nr_extents * fs_info->nodesize, true); if (ret) goto out_fail; } @@ -6005,7 +6007,7 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes) if (to_reserve) trace_btrfs_space_reservation(fs_info, "delalloc", - btrfs_ino(inode), to_reserve, 1); + btrfs_ino(BTRFS_I(inode)), to_reserve, 1); if (release_extra) btrfs_block_rsv_release(fs_info, block_rsv, btrfs_calc_trans_metadata_size(fs_info, 1)); @@ -6068,7 +6070,7 @@ out_fail: if (to_free) { btrfs_block_rsv_release(fs_info, block_rsv, to_free); trace_btrfs_space_reservation(fs_info, "delalloc", - btrfs_ino(inode), to_free, 0); + btrfs_ino(BTRFS_I(inode)), to_free, 0); } if (delalloc_lock) mutex_unlock(&BTRFS_I(inode)->delalloc_mutex); @@ -6104,7 +6106,7 @@ void btrfs_delalloc_release_metadata(struct inode *inode, u64 num_bytes) return; trace_btrfs_space_reservation(fs_info, "delalloc", - btrfs_ino(inode), to_free, 0); + btrfs_ino(BTRFS_I(inode)), to_free, 0); btrfs_block_rsv_release(fs_info, &fs_info->delalloc_block_rsv, to_free); } @@ -6561,8 +6563,7 @@ static int btrfs_free_reserved_bytes(struct btrfs_block_group_cache *cache, spin_unlock(&space_info->lock); return ret; } -void btrfs_prepare_extent_commit(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info) +void btrfs_prepare_extent_commit(struct btrfs_fs_info *fs_info) { struct btrfs_caching_control *next; struct btrfs_caching_control *caching_ctl; @@ -6845,7 +6846,7 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, if (is_data) skinny_metadata = 0; - ret = lookup_extent_backref(trans, extent_root, path, &iref, + ret = lookup_extent_backref(trans, info, path, &iref, bytenr, num_bytes, parent, root_objectid, owner_objectid, owner_offset); @@ -6877,8 +6878,8 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, #endif if (!found_extent) { BUG_ON(iref); - ret = remove_extent_backref(trans, extent_root, path, - NULL, refs_to_drop, + ret = remove_extent_backref(trans, info, path, NULL, + refs_to_drop, is_data, &last_ref); if (ret) { btrfs_abort_transaction(trans, ret); @@ -6953,8 +6954,8 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, #ifdef BTRFS_COMPAT_EXTENT_TREE_V0 if (item_size < sizeof(*ei)) { BUG_ON(found_extent || extent_slot != path->slots[0]); - ret = convert_extent_item_v0(trans, extent_root, path, - owner_objectid, 0); + ret = convert_extent_item_v0(trans, info, path, owner_objectid, + 0); if (ret < 0) { btrfs_abort_transaction(trans, ret); goto out; @@ -7021,7 +7022,7 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, btrfs_mark_buffer_dirty(leaf); } if (found_extent) { - ret = remove_extent_backref(trans, extent_root, path, + ret = remove_extent_backref(trans, info, path, iref, refs_to_drop, is_data, &last_ref); if (ret) { @@ -7095,7 +7096,7 @@ static noinline int check_ref_cleanup(struct btrfs_trans_handle *trans, delayed_refs = &trans->transaction->delayed_refs; spin_lock(&delayed_refs->lock); - head = btrfs_find_delayed_ref_head(trans, bytenr); + head = btrfs_find_delayed_ref_head(delayed_refs, bytenr); if (!head) goto out_delayed_unlock; @@ -7244,7 +7245,7 @@ int btrfs_free_extent(struct btrfs_trans_handle *trans, num_bytes, parent, root_objectid, owner, offset, 0, - BTRFS_DROP_DELAYED_REF, NULL); + BTRFS_DROP_DELAYED_REF); } return ret; } @@ -7419,12 +7420,11 @@ btrfs_release_block_group(struct btrfs_block_group_cache *cache, * If there is no suitable free space, we will record the max size of * the free space extent currently. */ -static noinline int find_free_extent(struct btrfs_root *orig_root, +static noinline int find_free_extent(struct btrfs_fs_info *fs_info, u64 ram_bytes, u64 num_bytes, u64 empty_size, u64 hint_byte, struct btrfs_key *ins, u64 flags, int delalloc) { - struct btrfs_fs_info *fs_info = orig_root->fs_info; int ret = 0; struct btrfs_root *root = fs_info->extent_root; struct btrfs_free_cluster *last_ptr = NULL; @@ -7716,18 +7716,20 @@ unclustered_alloc: last_ptr->fragmented = 1; spin_unlock(&last_ptr->lock); } - spin_lock(&block_group->free_space_ctl->tree_lock); - if (cached && - block_group->free_space_ctl->free_space < - num_bytes + empty_cluster + empty_size) { - if (block_group->free_space_ctl->free_space > - max_extent_size) - max_extent_size = - block_group->free_space_ctl->free_space; - spin_unlock(&block_group->free_space_ctl->tree_lock); - goto loop; + if (cached) { + struct btrfs_free_space_ctl *ctl = + block_group->free_space_ctl; + + spin_lock(&ctl->tree_lock); + if (ctl->free_space < + num_bytes + empty_cluster + empty_size) { + if (ctl->free_space > max_extent_size) + max_extent_size = ctl->free_space; + spin_unlock(&ctl->tree_lock); + goto loop; + } + spin_unlock(&ctl->tree_lock); } - spin_unlock(&block_group->free_space_ctl->tree_lock); offset = btrfs_find_space_for_alloc(block_group, search_start, num_bytes, empty_size, @@ -7908,9 +7910,8 @@ static void dump_space_info(struct btrfs_fs_info *fs_info, spin_lock(&info->lock); btrfs_info(fs_info, "space_info %llu has %llu free, is %sfull", info->flags, - info->total_bytes - info->bytes_used - info->bytes_pinned - - info->bytes_reserved - info->bytes_readonly - - info->bytes_may_use, (info->full) ? "" : "not "); + info->total_bytes - btrfs_space_info_used(info, true), + info->full ? "" : "not "); btrfs_info(fs_info, "space_info total=%llu, used=%llu, pinned=%llu, reserved=%llu, may_use=%llu, readonly=%llu", info->total_bytes, info->bytes_used, info->bytes_pinned, @@ -7951,7 +7952,7 @@ int btrfs_reserve_extent(struct btrfs_root *root, u64 ram_bytes, flags = btrfs_get_alloc_profile(root, is_data); again: WARN_ON(num_bytes < fs_info->sectorsize); - ret = find_free_extent(root, ram_bytes, num_bytes, empty_size, + ret = find_free_extent(fs_info, ram_bytes, num_bytes, empty_size, hint_byte, ins, flags, delalloc); if (!ret && !is_data) { btrfs_dec_block_group_reservations(fs_info, ins->objectid); @@ -8194,8 +8195,7 @@ int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans, ret = btrfs_add_delayed_data_ref(fs_info, trans, ins->objectid, ins->offset, 0, root_objectid, owner, offset, - ram_bytes, BTRFS_ADD_DELAYED_EXTENT, - NULL); + ram_bytes, BTRFS_ADD_DELAYED_EXTENT); return ret; } @@ -8256,7 +8256,7 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root, btrfs_set_header_generation(buf, trans->transid); btrfs_set_buffer_lockdep_class(root->root_key.objectid, buf, level); btrfs_tree_lock(buf); - clean_tree_block(trans, fs_info, buf); + clean_tree_block(fs_info, buf); clear_bit(EXTENT_BUFFER_STALE, &buf->bflags); btrfs_set_lock_blocking(buf); @@ -8351,10 +8351,11 @@ static void unuse_block_rsv(struct btrfs_fs_info *fs_info, * returns the tree buffer or an ERR_PTR on error. */ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans, - struct btrfs_root *root, - u64 parent, u64 root_objectid, - struct btrfs_disk_key *key, int level, - u64 hint, u64 empty_size) + struct btrfs_root *root, + u64 parent, u64 root_objectid, + const struct btrfs_disk_key *key, + int level, u64 hint, + u64 empty_size) { struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_key ins; @@ -8876,7 +8877,7 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans, btrfs_set_lock_blocking(eb); path->locks[level] = BTRFS_WRITE_LOCK_BLOCKING; } - clean_tree_block(trans, fs_info, eb); + clean_tree_block(fs_info, eb); } if (eb == root->node) { @@ -9346,8 +9347,7 @@ static int inc_block_group_ro(struct btrfs_block_group_cache *cache, int force) num_bytes = cache->key.offset - cache->reserved - cache->pinned - cache->bytes_super - btrfs_block_group_used(&cache->item); - if (sinfo->bytes_used + sinfo->bytes_reserved + sinfo->bytes_pinned + - sinfo->bytes_may_use + sinfo->bytes_readonly + num_bytes + + if (btrfs_space_info_used(sinfo, true) + num_bytes + min_allocable_bytes <= sinfo->total_bytes) { sinfo->bytes_readonly += num_bytes; cache->ro++; @@ -9360,17 +9360,16 @@ out: return ret; } -int btrfs_inc_block_group_ro(struct btrfs_root *root, +int btrfs_inc_block_group_ro(struct btrfs_fs_info *fs_info, struct btrfs_block_group_cache *cache) { - struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_trans_handle *trans; u64 alloc_flags; int ret; again: - trans = btrfs_join_transaction(root); + trans = btrfs_join_transaction(fs_info->extent_root); if (IS_ERR(trans)) return PTR_ERR(trans); @@ -9557,9 +9556,8 @@ int btrfs_can_relocate(struct btrfs_fs_info *fs_info, u64 bytenr) * all of the extents from this block group. If we can, we're good */ if ((space_info->total_bytes != block_group->key.offset) && - (space_info->bytes_used + space_info->bytes_reserved + - space_info->bytes_pinned + space_info->bytes_readonly + - min_free < space_info->total_bytes)) { + (btrfs_space_info_used(space_info, false) + min_free < + space_info->total_bytes)) { spin_unlock(&space_info->lock); goto out; } @@ -10317,7 +10315,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, * get the inode first so any iput calls done for the io_list * aren't the final iput (no unlinks allowed now) */ - inode = lookup_free_space_inode(tree_root, block_group, path); + inode = lookup_free_space_inode(fs_info, block_group, path); mutex_lock(&trans->transaction->cache_write_mutex); /* diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 4ac383a3a649..d15b5ddb6732 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -98,7 +98,7 @@ static inline void __btrfs_debug_check_extent_io_range(const char *caller, if (end >= PAGE_SIZE && (end % 2) == 0 && end != isize - 1) { btrfs_debug_rl(BTRFS_I(inode)->root->fs_info, "%s: ino %llu isize %llu odd range [%llu,%llu]", - caller, btrfs_ino(inode), isize, start, end); + caller, btrfs_ino(BTRFS_I(inode)), isize, start, end); } } #else @@ -144,7 +144,7 @@ static void add_extent_changeset(struct extent_state *state, unsigned bits, if (!set && (state->state & bits) == 0) return; changeset->bytes_changed += state->end - state->start + 1; - ret = ulist_add(changeset->range_changed, state->start, state->end, + ret = ulist_add(&changeset->range_changed, state->start, state->end, GFP_ATOMIC); /* ENOMEM */ BUG_ON(ret < 0); @@ -226,6 +226,11 @@ static struct extent_state *alloc_extent_state(gfp_t mask) { struct extent_state *state; + /* + * The given mask might be not appropriate for the slab allocator, + * drop the unsupported bits + */ + mask &= ~(__GFP_DMA32|__GFP_HIGHMEM); state = kmem_cache_alloc(extent_state_cache, mask); if (!state) return state; @@ -1549,33 +1554,24 @@ out: return found; } +static int __process_pages_contig(struct address_space *mapping, + struct page *locked_page, + pgoff_t start_index, pgoff_t end_index, + unsigned long page_ops, pgoff_t *index_ret); + static noinline void __unlock_for_delalloc(struct inode *inode, struct page *locked_page, u64 start, u64 end) { - int ret; - struct page *pages[16]; unsigned long index = start >> PAGE_SHIFT; unsigned long end_index = end >> PAGE_SHIFT; - unsigned long nr_pages = end_index - index + 1; - int i; + ASSERT(locked_page); if (index == locked_page->index && end_index == index) return; - while (nr_pages > 0) { - ret = find_get_pages_contig(inode->i_mapping, index, - min_t(unsigned long, nr_pages, - ARRAY_SIZE(pages)), pages); - for (i = 0; i < ret; i++) { - if (pages[i] != locked_page) - unlock_page(pages[i]); - put_page(pages[i]); - } - nr_pages -= ret; - index += ret; - cond_resched(); - } + __process_pages_contig(inode->i_mapping, locked_page, index, end_index, + PAGE_UNLOCK, NULL); } static noinline int lock_delalloc_pages(struct inode *inode, @@ -1584,59 +1580,19 @@ static noinline int lock_delalloc_pages(struct inode *inode, u64 delalloc_end) { unsigned long index = delalloc_start >> PAGE_SHIFT; - unsigned long start_index = index; + unsigned long index_ret = index; unsigned long end_index = delalloc_end >> PAGE_SHIFT; - unsigned long pages_locked = 0; - struct page *pages[16]; - unsigned long nrpages; int ret; - int i; - /* the caller is responsible for locking the start index */ + ASSERT(locked_page); if (index == locked_page->index && index == end_index) return 0; - /* skip the page at the start index */ - nrpages = end_index - index + 1; - while (nrpages > 0) { - ret = find_get_pages_contig(inode->i_mapping, index, - min_t(unsigned long, - nrpages, ARRAY_SIZE(pages)), pages); - if (ret == 0) { - ret = -EAGAIN; - goto done; - } - /* now we have an array of pages, lock them all */ - for (i = 0; i < ret; i++) { - /* - * the caller is taking responsibility for - * locked_page - */ - if (pages[i] != locked_page) { - lock_page(pages[i]); - if (!PageDirty(pages[i]) || - pages[i]->mapping != inode->i_mapping) { - ret = -EAGAIN; - unlock_page(pages[i]); - put_page(pages[i]); - goto done; - } - } - put_page(pages[i]); - pages_locked++; - } - nrpages -= ret; - index += ret; - cond_resched(); - } - ret = 0; -done: - if (ret && pages_locked) { - __unlock_for_delalloc(inode, locked_page, - delalloc_start, - ((u64)(start_index + pages_locked - 1)) << - PAGE_SHIFT); - } + ret = __process_pages_contig(inode->i_mapping, locked_page, index, + end_index, PAGE_LOCK, &index_ret); + if (ret == -EAGAIN) + __unlock_for_delalloc(inode, locked_page, delalloc_start, + (u64)index_ret << PAGE_SHIFT); return ret; } @@ -1726,37 +1682,47 @@ out_failed: return found; } -void extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end, - u64 delalloc_end, struct page *locked_page, - unsigned clear_bits, - unsigned long page_ops) +static int __process_pages_contig(struct address_space *mapping, + struct page *locked_page, + pgoff_t start_index, pgoff_t end_index, + unsigned long page_ops, pgoff_t *index_ret) { - struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree; - int ret; + unsigned long nr_pages = end_index - start_index + 1; + unsigned long pages_locked = 0; + pgoff_t index = start_index; struct page *pages[16]; - unsigned long index = start >> PAGE_SHIFT; - unsigned long end_index = end >> PAGE_SHIFT; - unsigned long nr_pages = end_index - index + 1; + unsigned ret; + int err = 0; int i; - clear_extent_bit(tree, start, end, clear_bits, 1, 0, NULL, GFP_NOFS); - if (page_ops == 0) - return; + if (page_ops & PAGE_LOCK) { + ASSERT(page_ops == PAGE_LOCK); + ASSERT(index_ret && *index_ret == start_index); + } if ((page_ops & PAGE_SET_ERROR) && nr_pages > 0) - mapping_set_error(inode->i_mapping, -EIO); + mapping_set_error(mapping, -EIO); while (nr_pages > 0) { - ret = find_get_pages_contig(inode->i_mapping, index, + ret = find_get_pages_contig(mapping, index, min_t(unsigned long, nr_pages, ARRAY_SIZE(pages)), pages); - for (i = 0; i < ret; i++) { + if (ret == 0) { + /* + * Only if we're going to lock these pages, + * can we find nothing at @index. + */ + ASSERT(page_ops & PAGE_LOCK); + return ret; + } + for (i = 0; i < ret; i++) { if (page_ops & PAGE_SET_PRIVATE2) SetPagePrivate2(pages[i]); if (pages[i] == locked_page) { put_page(pages[i]); + pages_locked++; continue; } if (page_ops & PAGE_CLEAR_DIRTY) @@ -1769,12 +1735,40 @@ void extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end, end_page_writeback(pages[i]); if (page_ops & PAGE_UNLOCK) unlock_page(pages[i]); + if (page_ops & PAGE_LOCK) { + lock_page(pages[i]); + if (!PageDirty(pages[i]) || + pages[i]->mapping != mapping) { + unlock_page(pages[i]); + put_page(pages[i]); + err = -EAGAIN; + goto out; + } + } put_page(pages[i]); + pages_locked++; } nr_pages -= ret; index += ret; cond_resched(); } +out: + if (err && index_ret) + *index_ret = start_index + pages_locked - 1; + return err; +} + +void extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end, + u64 delalloc_end, struct page *locked_page, + unsigned clear_bits, + unsigned long page_ops) +{ + clear_extent_bit(&BTRFS_I(inode)->io_tree, start, end, clear_bits, 1, 0, + NULL, GFP_NOFS); + + __process_pages_contig(inode->i_mapping, locked_page, + start >> PAGE_SHIFT, end >> PAGE_SHIFT, + page_ops, NULL); } /* @@ -2060,7 +2054,7 @@ int repair_io_failure(struct inode *inode, u64 start, u64 length, u64 logical, btrfs_info_rl_in_rcu(fs_info, "read error corrected: ino %llu off %llu (dev %s sector %llu)", - btrfs_ino(inode), start, + btrfs_ino(BTRFS_I(inode)), start, rcu_str_deref(dev->name), sector); btrfs_bio_counter_dec(fs_info); bio_put(bio); @@ -2765,7 +2759,6 @@ static int submit_extent_page(int op, int op_flags, struct extent_io_tree *tree, size_t size, unsigned long offset, struct block_device *bdev, struct bio **bio_ret, - unsigned long max_pages, bio_end_io_t end_io_func, int mirror_num, unsigned long prev_bio_flags, @@ -2931,7 +2924,6 @@ static int __do_readpage(struct extent_io_tree *tree, } } while (cur <= end) { - unsigned long pnr = (last_byte >> PAGE_SHIFT) + 1; bool force_bio_submit = false; if (cur >= last_byte) { @@ -3066,10 +3058,9 @@ static int __do_readpage(struct extent_io_tree *tree, continue; } - pnr -= page->index; ret = submit_extent_page(REQ_OP_READ, read_flags, tree, NULL, page, sector, disk_io_size, pg_offset, - bdev, bio, pnr, + bdev, bio, end_bio_extent_readpage, mirror_num, *bio_flags, this_bio_flag, @@ -3210,7 +3201,7 @@ int extent_read_full_page(struct extent_io_tree *tree, struct page *page, return ret; } -static void update_nr_written(struct page *page, struct writeback_control *wbc, +static void update_nr_written(struct writeback_control *wbc, unsigned long nr_written) { wbc->nr_to_write -= nr_written; @@ -3330,7 +3321,6 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode, u64 block_start; u64 iosize; sector_t sector; - struct extent_state *cached_state = NULL; struct extent_map *em; struct block_device *bdev; size_t pg_offset = 0; @@ -3349,10 +3339,9 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode, else redirty_page_for_writepage(wbc, page); - update_nr_written(page, wbc, nr_written); + update_nr_written(wbc, nr_written); unlock_page(page); - ret = 1; - goto done_unlocked; + return 1; } } @@ -3360,7 +3349,7 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode, * we don't want to touch the inode after unlocking the page, * so we update the mapping writeback index now */ - update_nr_written(page, wbc, nr_written + 1); + update_nr_written(wbc, nr_written + 1); end = page_end; if (i_size <= start) { @@ -3374,7 +3363,6 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode, while (cur <= end) { u64 em_end; - unsigned long max_nr; if (cur >= i_size) { if (tree->ops && tree->ops->writepage_end_io_hook) @@ -3431,8 +3419,6 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode, continue; } - max_nr = (i_size >> PAGE_SHIFT) + 1; - set_range_writeback(tree, cur, cur + iosize - 1); if (!PageWriteback(page)) { btrfs_err(BTRFS_I(inode)->root->fs_info, @@ -3442,11 +3428,14 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode, ret = submit_extent_page(REQ_OP_WRITE, write_flags, tree, wbc, page, sector, iosize, pg_offset, - bdev, &epd->bio, max_nr, + bdev, &epd->bio, end_bio_extent_writepage, 0, 0, 0, false); - if (ret) + if (ret) { SetPageError(page); + if (PageWriteback(page)) + end_page_writeback(page); + } cur = cur + iosize; pg_offset += iosize; @@ -3454,11 +3443,6 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode, } done: *nr_ret = nr; - -done_unlocked: - - /* drop our reference on any cached states */ - free_extent_state(cached_state); return ret; } @@ -3761,20 +3745,21 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb, set_page_writeback(p); ret = submit_extent_page(REQ_OP_WRITE, write_flags, tree, wbc, p, offset >> 9, PAGE_SIZE, 0, bdev, - &epd->bio, -1, + &epd->bio, end_bio_extent_buffer_writepage, 0, epd->bio_flags, bio_flags, false); epd->bio_flags = bio_flags; if (ret) { set_btree_ioerr(p); - end_page_writeback(p); + if (PageWriteback(p)) + end_page_writeback(p); if (atomic_sub_and_test(num_pages - i, &eb->io_pages)) end_extent_buffer_writeback(eb); ret = -EIO; break; } offset += PAGE_SIZE; - update_nr_written(p, wbc, 1); + update_nr_written(wbc, 1); unlock_page(p); } @@ -3926,8 +3911,7 @@ retry: * WB_SYNC_ALL then we were called for data integrity and we must wait for * existing IO to complete. */ -static int extent_write_cache_pages(struct extent_io_tree *tree, - struct address_space *mapping, +static int extent_write_cache_pages(struct address_space *mapping, struct writeback_control *wbc, writepage_t writepage, void *data, void (*flush_fn)(void *)) @@ -4168,8 +4152,7 @@ int extent_writepages(struct extent_io_tree *tree, .bio_flags = 0, }; - ret = extent_write_cache_pages(tree, mapping, wbc, - __extent_writepage, &epd, + ret = extent_write_cache_pages(mapping, wbc, __extent_writepage, &epd, flush_write_bio); flush_epd_write_bio(&epd); return ret; @@ -4264,8 +4247,6 @@ static int try_release_extent_state(struct extent_map_tree *map, EXTENT_IOBITS, 0, NULL)) ret = 0; else { - if ((mask & GFP_NOFS) == GFP_NOFS) - mask = GFP_NOFS; /* * at this point we can safely clear everything except the * locked bit and the nodatasum bit @@ -4410,8 +4391,8 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, * lookup the last file extent. We're not using i_size here * because there might be preallocation past i_size */ - ret = btrfs_lookup_file_extent(NULL, root, path, btrfs_ino(inode), -1, - 0); + ret = btrfs_lookup_file_extent(NULL, root, path, + btrfs_ino(BTRFS_I(inode)), -1, 0); if (ret < 0) { btrfs_free_path(path); return ret; @@ -4426,7 +4407,7 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, found_type = found_key.type; /* No extents, but there might be delalloc bits */ - if (found_key.objectid != btrfs_ino(inode) || + if (found_key.objectid != btrfs_ino(BTRFS_I(inode)) || found_type != BTRFS_EXTENT_DATA_KEY) { /* have to trust i_size as the end */ last = (u64)-1; @@ -4535,8 +4516,8 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, * lookup stuff. */ ret = btrfs_check_shared(trans, root->fs_info, - root->objectid, - btrfs_ino(inode), bytenr); + root->objectid, + btrfs_ino(BTRFS_I(inode)), bytenr); if (trans) btrfs_end_transaction(trans); if (ret < 0) diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 17f9ce479ed7..270d03be290e 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -45,13 +45,14 @@ #define EXTENT_BUFFER_IN_TREE 10 #define EXTENT_BUFFER_WRITE_ERR 11 /* write IO error */ -/* these are flags for extent_clear_unlock_delalloc */ +/* these are flags for __process_pages_contig */ #define PAGE_UNLOCK (1 << 0) #define PAGE_CLEAR_DIRTY (1 << 1) #define PAGE_SET_WRITEBACK (1 << 2) #define PAGE_END_WRITEBACK (1 << 3) #define PAGE_SET_PRIVATE2 (1 << 4) #define PAGE_SET_ERROR (1 << 5) +#define PAGE_LOCK (1 << 6) /* * page->private values. Every page that is controlled by the extent @@ -192,7 +193,7 @@ struct extent_changeset { u64 bytes_changed; /* Changed ranges */ - struct ulist *range_changed; + struct ulist range_changed; }; static inline void extent_set_compress_type(unsigned long *bio_flags, diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index e97e322c28f0..f7b9a92ad56d 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -255,7 +255,7 @@ static int __btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio, } else { btrfs_info_rl(fs_info, "no csum found for inode %llu start %llu", - btrfs_ino(inode), offset); + btrfs_ino(BTRFS_I(inode)), offset); } item = NULL; btrfs_release_path(path); @@ -856,8 +856,8 @@ insert: tmp = min(tmp, (next_offset - file_key.offset) >> fs_info->sb->s_blocksize_bits); - tmp = max((u64)1, tmp); - tmp = min(tmp, (u64)MAX_CSUM_ITEMS(fs_info, csum_size)); + tmp = max_t(u64, 1, tmp); + tmp = min_t(u64, tmp, MAX_CSUM_ITEMS(fs_info, csum_size)); ins_size = csum_size * tmp; } else { ins_size = csum_size; @@ -977,7 +977,7 @@ void btrfs_extent_item_to_extent_map(struct inode *inode, } else { btrfs_err(fs_info, "unknown file extent item type %d, inode %llu, offset %llu, root %llu", - type, btrfs_ino(inode), extent_start, + type, btrfs_ino(BTRFS_I(inode)), extent_start, root->root_key.objectid); } } diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index b5c5da215d05..c1d2a07205da 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -168,7 +168,7 @@ int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans, if (!defrag) return -ENOMEM; - defrag->ino = btrfs_ino(inode); + defrag->ino = btrfs_ino(BTRFS_I(inode)); defrag->transid = transid; defrag->root = root->root_key.objectid; @@ -702,7 +702,7 @@ int __btrfs_drop_extents(struct btrfs_trans_handle *trans, struct btrfs_file_extent_item *fi; struct btrfs_key key; struct btrfs_key new_key; - u64 ino = btrfs_ino(inode); + u64 ino = btrfs_ino(BTRFS_I(inode)); u64 search_start = start; u64 disk_bytenr = 0; u64 num_bytes = 0; @@ -1102,7 +1102,7 @@ int btrfs_mark_extent_written(struct btrfs_trans_handle *trans, int del_slot = 0; int recow; int ret; - u64 ino = btrfs_ino(inode); + u64 ino = btrfs_ino(BTRFS_I(inode)); path = btrfs_alloc_path(); if (!path) @@ -2062,7 +2062,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) * commit does not start nor waits for ordered extents to complete. */ smp_mb(); - if (btrfs_inode_in_log(inode, fs_info->generation) || + if (btrfs_inode_in_log(BTRFS_I(inode), fs_info->generation) || (full_sync && BTRFS_I(inode)->last_trans <= fs_info->last_trans_committed) || (!btrfs_have_ordered_extents_in_range(inode, start, len) && @@ -2203,7 +2203,7 @@ static int hole_mergeable(struct inode *inode, struct extent_buffer *leaf, return 0; btrfs_item_key_to_cpu(leaf, &key, slot); - if (key.objectid != btrfs_ino(inode) || + if (key.objectid != btrfs_ino(BTRFS_I(inode)) || key.type != BTRFS_EXTENT_DATA_KEY) return 0; @@ -2237,7 +2237,7 @@ static int fill_holes(struct btrfs_trans_handle *trans, struct inode *inode, if (btrfs_fs_incompat(fs_info, NO_HOLES)) goto out; - key.objectid = btrfs_ino(inode); + key.objectid = btrfs_ino(BTRFS_I(inode)); key.type = BTRFS_EXTENT_DATA_KEY; key.offset = offset; @@ -2285,9 +2285,8 @@ static int fill_holes(struct btrfs_trans_handle *trans, struct inode *inode, } btrfs_release_path(path); - ret = btrfs_insert_file_extent(trans, root, btrfs_ino(inode), offset, - 0, 0, end - offset, 0, end - offset, - 0, 0, 0); + ret = btrfs_insert_file_extent(trans, root, btrfs_ino(BTRFS_I(inode)), + offset, 0, 0, end - offset, 0, end - offset, 0, 0, 0); if (ret) return ret; @@ -2876,7 +2875,7 @@ static long btrfs_fallocate(struct file *file, int mode, if (!ret) ret = btrfs_prealloc_file_range(inode, mode, range->start, - range->len, 1 << inode->i_blkbits, + range->len, i_blocksize(inode), offset + len, &alloc_hint); else btrfs_free_reserved_data_space(inode, range->start, diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 7015892c9ee8..1a131f7d6c1b 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -94,12 +94,11 @@ static struct inode *__lookup_free_space_inode(struct btrfs_root *root, return inode; } -struct inode *lookup_free_space_inode(struct btrfs_root *root, +struct inode *lookup_free_space_inode(struct btrfs_fs_info *fs_info, struct btrfs_block_group_cache *block_group, struct btrfs_path *path) { struct inode *inode = NULL; - struct btrfs_fs_info *fs_info = root->fs_info; u32 flags = BTRFS_INODE_NODATASUM | BTRFS_INODE_NODATACOW; spin_lock(&block_group->lock); @@ -109,7 +108,7 @@ struct inode *lookup_free_space_inode(struct btrfs_root *root, if (inode) return inode; - inode = __lookup_free_space_inode(root, path, + inode = __lookup_free_space_inode(fs_info->tree_root, path, block_group->key.objectid); if (IS_ERR(inode)) return inode; @@ -192,7 +191,7 @@ static int __create_free_space_inode(struct btrfs_root *root, return 0; } -int create_free_space_inode(struct btrfs_root *root, +int create_free_space_inode(struct btrfs_fs_info *fs_info, struct btrfs_trans_handle *trans, struct btrfs_block_group_cache *block_group, struct btrfs_path *path) @@ -200,11 +199,11 @@ int create_free_space_inode(struct btrfs_root *root, int ret; u64 ino; - ret = btrfs_find_free_objectid(root, &ino); + ret = btrfs_find_free_objectid(fs_info->tree_root, &ino); if (ret < 0) return ret; - return __create_free_space_inode(root, trans, path, ino, + return __create_free_space_inode(fs_info->tree_root, trans, path, ino, block_group->key.objectid); } @@ -227,21 +226,21 @@ int btrfs_check_trunc_cache_free_space(struct btrfs_fs_info *fs_info, return ret; } -int btrfs_truncate_free_space_cache(struct btrfs_root *root, - struct btrfs_trans_handle *trans, +int btrfs_truncate_free_space_cache(struct btrfs_trans_handle *trans, struct btrfs_block_group_cache *block_group, struct inode *inode) { + struct btrfs_root *root = BTRFS_I(inode)->root; int ret = 0; - struct btrfs_path *path = btrfs_alloc_path(); bool locked = false; - if (!path) { - ret = -ENOMEM; - goto fail; - } - if (block_group) { + struct btrfs_path *path = btrfs_alloc_path(); + + if (!path) { + ret = -ENOMEM; + goto fail; + } locked = true; mutex_lock(&trans->transaction->cache_write_mutex); if (!list_empty(&block_group->io_list)) { @@ -258,8 +257,8 @@ int btrfs_truncate_free_space_cache(struct btrfs_root *root, spin_lock(&block_group->lock); block_group->disk_cache_state = BTRFS_DC_CLEAR; spin_unlock(&block_group->lock); + btrfs_free_path(path); } - btrfs_free_path(path); btrfs_i_size_write(inode, 0); truncate_pagecache(inode, 0); @@ -286,14 +285,14 @@ fail: return ret; } -static int readahead_cache(struct inode *inode) +static void readahead_cache(struct inode *inode) { struct file_ra_state *ra; unsigned long last_index; ra = kzalloc(sizeof(*ra), GFP_NOFS); if (!ra) - return -ENOMEM; + return; file_ra_state_init(ra, inode->i_mapping); last_index = (i_size_read(inode) - 1) >> PAGE_SHIFT; @@ -301,8 +300,6 @@ static int readahead_cache(struct inode *inode) page_cache_sync_readahead(inode->i_mapping, ra, NULL, 0, last_index); kfree(ra); - - return 0; } static int io_ctl_init(struct btrfs_io_ctl *io_ctl, struct inode *inode, @@ -313,7 +310,7 @@ static int io_ctl_init(struct btrfs_io_ctl *io_ctl, struct inode *inode, num_pages = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); - if (btrfs_ino(inode) != BTRFS_FREE_INO_OBJECTID) + if (btrfs_ino(BTRFS_I(inode)) != BTRFS_FREE_INO_OBJECTID) check_crcs = 1; /* Make sure we can fit our crcs into the first page */ @@ -730,9 +727,7 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode, if (ret) return ret; - ret = readahead_cache(inode); - if (ret) - goto out; + readahead_cache(inode); ret = io_ctl_prepare_pages(&io_ctl, inode, 1); if (ret) @@ -828,7 +823,6 @@ int load_free_space_cache(struct btrfs_fs_info *fs_info, struct btrfs_block_group_cache *block_group) { struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; - struct btrfs_root *root = fs_info->tree_root; struct inode *inode; struct btrfs_path *path; int ret = 0; @@ -852,7 +846,7 @@ int load_free_space_cache(struct btrfs_fs_info *fs_info, path->search_commit_root = 1; path->skip_locking = 1; - inode = lookup_free_space_inode(root, block_group, path); + inode = lookup_free_space_inode(fs_info, block_group, path); if (IS_ERR(inode)) { btrfs_free_path(path); return 0; @@ -1128,8 +1122,7 @@ cleanup_bitmap_list(struct list_head *bitmap_list) static void noinline_for_stack cleanup_write_cache_enospc(struct inode *inode, struct btrfs_io_ctl *io_ctl, - struct extent_state **cached_state, - struct list_head *bitmap_list) + struct extent_state **cached_state) { io_ctl_drop_pages(io_ctl); unlock_extent_cached(&BTRFS_I(inode)->io_tree, 0, @@ -1225,8 +1218,6 @@ int btrfs_wait_cache_io(struct btrfs_trans_handle *trans, * @ctl - the free space cache we are going to write out * @block_group - the block_group for this cache if it belongs to a block_group * @trans - the trans handle - * @path - the path to use - * @offset - the offset for the key we'll insert * * This function writes out a free space cache struct to disk for quick recovery * on mount. This will return 0 if it was successful in writing the cache out, @@ -1236,8 +1227,7 @@ static int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode, struct btrfs_free_space_ctl *ctl, struct btrfs_block_group_cache *block_group, struct btrfs_io_ctl *io_ctl, - struct btrfs_trans_handle *trans, - struct btrfs_path *path, u64 offset) + struct btrfs_trans_handle *trans) { struct btrfs_fs_info *fs_info = root->fs_info; struct extent_state *cached_state = NULL; @@ -1365,7 +1355,7 @@ out_nospc_locked: mutex_unlock(&ctl->cache_writeout_mutex); out_nospc: - cleanup_write_cache_enospc(inode, io_ctl, &cached_state, &bitmap_list); + cleanup_write_cache_enospc(inode, io_ctl, &cached_state); if (block_group && (block_group->flags & BTRFS_BLOCK_GROUP_DATA)) up_write(&block_group->data_rwsem); @@ -1378,7 +1368,6 @@ int btrfs_write_out_cache(struct btrfs_fs_info *fs_info, struct btrfs_block_group_cache *block_group, struct btrfs_path *path) { - struct btrfs_root *root = fs_info->tree_root; struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; struct inode *inode; int ret = 0; @@ -1390,13 +1379,12 @@ int btrfs_write_out_cache(struct btrfs_fs_info *fs_info, } spin_unlock(&block_group->lock); - inode = lookup_free_space_inode(root, block_group, path); + inode = lookup_free_space_inode(fs_info, block_group, path); if (IS_ERR(inode)) return 0; - ret = __btrfs_write_out_cache(root, inode, ctl, block_group, - &block_group->io_ctl, trans, - path, block_group->key.objectid); + ret = __btrfs_write_out_cache(fs_info->tree_root, inode, ctl, + block_group, &block_group->io_ctl, trans); if (ret) { #ifdef DEBUG btrfs_err(fs_info, @@ -3543,8 +3531,7 @@ int btrfs_write_out_ino_cache(struct btrfs_root *root, return 0; memset(&io_ctl, 0, sizeof(io_ctl)); - ret = __btrfs_write_out_cache(root, inode, ctl, NULL, &io_ctl, - trans, path, 0); + ret = __btrfs_write_out_cache(root, inode, ctl, NULL, &io_ctl, trans); if (!ret) { /* * At this point writepages() didn't error out, so our metadata diff --git a/fs/btrfs/free-space-cache.h b/fs/btrfs/free-space-cache.h index 6f3c025a2c6c..79eca4cabb1c 100644 --- a/fs/btrfs/free-space-cache.h +++ b/fs/btrfs/free-space-cache.h @@ -51,18 +51,17 @@ struct btrfs_free_space_op { struct btrfs_io_ctl; -struct inode *lookup_free_space_inode(struct btrfs_root *root, +struct inode *lookup_free_space_inode(struct btrfs_fs_info *fs_info, struct btrfs_block_group_cache *block_group, struct btrfs_path *path); -int create_free_space_inode(struct btrfs_root *root, +int create_free_space_inode(struct btrfs_fs_info *fs_info, struct btrfs_trans_handle *trans, struct btrfs_block_group_cache *block_group, struct btrfs_path *path); int btrfs_check_trunc_cache_free_space(struct btrfs_fs_info *fs_info, struct btrfs_block_rsv *rsv); -int btrfs_truncate_free_space_cache(struct btrfs_root *root, - struct btrfs_trans_handle *trans, +int btrfs_truncate_free_space_cache(struct btrfs_trans_handle *trans, struct btrfs_block_group_cache *block_group, struct inode *inode); int load_free_space_cache(struct btrfs_fs_info *fs_info, diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c index ff0c55337c2e..dd7fb22a955a 100644 --- a/fs/btrfs/free-space-tree.c +++ b/fs/btrfs/free-space-tree.c @@ -1269,7 +1269,7 @@ int btrfs_clear_free_space_tree(struct btrfs_fs_info *fs_info) list_del(&free_space_root->dirty_list); btrfs_tree_lock(free_space_root->node); - clean_tree_block(trans, fs_info, free_space_root->node); + clean_tree_block(fs_info, free_space_root->node); btrfs_tree_unlock(free_space_root->node); btrfs_free_tree_block(trans, free_space_root, free_space_root->node, 0, 1); diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c index 144b119ff43f..3bbb8f095953 100644 --- a/fs/btrfs/inode-map.c +++ b/fs/btrfs/inode-map.c @@ -467,7 +467,7 @@ again: } if (i_size_read(inode) > 0) { - ret = btrfs_truncate_free_space_cache(root, trans, NULL, inode); + ret = btrfs_truncate_free_space_cache(trans, NULL, inode); if (ret) { if (ret != -ENOSPC) btrfs_abort_transaction(trans, ret); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 1e861a063721..f02823f088c2 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -71,6 +71,7 @@ struct btrfs_dio_data { u64 reserve; u64 unsubmitted_oe_range_start; u64 unsubmitted_oe_range_end; + int overwrite; }; static const struct inode_operations btrfs_dir_inode_operations; @@ -108,11 +109,11 @@ static noinline int cow_file_range(struct inode *inode, u64 start, u64 end, u64 delalloc_end, int *page_started, unsigned long *nr_written, int unlock, struct btrfs_dedupe_hash *hash); -static struct extent_map *create_pinned_em(struct inode *inode, u64 start, - u64 len, u64 orig_start, - u64 block_start, u64 block_len, - u64 orig_block_len, u64 ram_bytes, - int type); +static struct extent_map *create_io_em(struct inode *inode, u64 start, u64 len, + u64 orig_start, u64 block_start, + u64 block_len, u64 orig_block_len, + u64 ram_bytes, int compress_type, + int type); static int btrfs_dirty_inode(struct inode *inode); @@ -166,7 +167,7 @@ static int insert_inline_extent(struct btrfs_trans_handle *trans, struct btrfs_key key; size_t datasize; - key.objectid = btrfs_ino(inode); + key.objectid = btrfs_ino(BTRFS_I(inode)); key.offset = start; key.type = BTRFS_EXTENT_DATA_KEY; @@ -388,6 +389,15 @@ static inline int inode_need_compress(struct inode *inode) return 0; } +static inline void inode_should_defrag(struct inode *inode, + u64 start, u64 end, u64 num_bytes, u64 small_write) +{ + /* If this is a small write inside eof, kick off a defrag */ + if (num_bytes < small_write && + (start > 0 || end + 1 < BTRFS_I(inode)->disk_i_size)) + btrfs_add_inode_defrag(NULL, inode); +} + /* * we create compressed extents in two phases. The first * phase compresses a range of pages that have already been @@ -430,10 +440,7 @@ static noinline void compress_file_range(struct inode *inode, int compress_type = fs_info->compress_type; int redirty = 0; - /* if this is a small write inside eof, kick off a defrag */ - if ((end - start + 1) < SZ_16K && - (start > 0 || end + 1 < BTRFS_I(inode)->disk_i_size)) - btrfs_add_inode_defrag(NULL, inode); + inode_should_defrag(inode, start, end, end - start + 1, SZ_16K); actual_end = min_t(u64, isize, end + 1); again: @@ -541,7 +548,7 @@ cont: * to make an uncompressed inline extent. */ ret = cow_file_range_inline(root, inode, start, end, - 0, 0, NULL); + 0, BTRFS_COMPRESS_NONE, NULL); } else { /* try making a compressed inline extent */ ret = cow_file_range_inline(root, inode, start, end, @@ -690,7 +697,6 @@ static noinline void submit_compressed_extents(struct inode *inode, struct btrfs_key ins; struct extent_map *em; struct btrfs_root *root = BTRFS_I(inode)->root; - struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree; struct extent_io_tree *io_tree; int ret = 0; @@ -778,46 +784,19 @@ retry: * here we're doing allocation and writeback of the * compressed pages */ - btrfs_drop_extent_cache(inode, async_extent->start, - async_extent->start + - async_extent->ram_size - 1, 0); - - em = alloc_extent_map(); - if (!em) { - ret = -ENOMEM; - goto out_free_reserve; - } - em->start = async_extent->start; - em->len = async_extent->ram_size; - em->orig_start = em->start; - em->mod_start = em->start; - em->mod_len = em->len; - - em->block_start = ins.objectid; - em->block_len = ins.offset; - em->orig_block_len = ins.offset; - em->ram_bytes = async_extent->ram_size; - em->bdev = fs_info->fs_devices->latest_bdev; - em->compress_type = async_extent->compress_type; - set_bit(EXTENT_FLAG_PINNED, &em->flags); - set_bit(EXTENT_FLAG_COMPRESSED, &em->flags); - em->generation = -1; - - while (1) { - write_lock(&em_tree->lock); - ret = add_extent_mapping(em_tree, em, 1); - write_unlock(&em_tree->lock); - if (ret != -EEXIST) { - free_extent_map(em); - break; - } - btrfs_drop_extent_cache(inode, async_extent->start, - async_extent->start + - async_extent->ram_size - 1, 0); - } - - if (ret) + em = create_io_em(inode, async_extent->start, + async_extent->ram_size, /* len */ + async_extent->start, /* orig_start */ + ins.objectid, /* block_start */ + ins.offset, /* block_len */ + ins.offset, /* orig_block_len */ + async_extent->ram_size, /* ram_bytes */ + async_extent->compress_type, + BTRFS_ORDERED_COMPRESSED); + if (IS_ERR(em)) + /* ret value is not necessary due to void function */ goto out_free_reserve; + free_extent_map(em); ret = btrfs_add_ordered_extent_compress(inode, async_extent->start, @@ -952,7 +931,6 @@ static noinline int cow_file_range(struct inode *inode, u64 blocksize = fs_info->sectorsize; struct btrfs_key ins; struct extent_map *em; - struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree; int ret = 0; if (btrfs_is_free_space_inode(inode)) { @@ -965,15 +943,12 @@ static noinline int cow_file_range(struct inode *inode, num_bytes = max(blocksize, num_bytes); disk_num_bytes = num_bytes; - /* if this is a small write inside eof, kick off defrag */ - if (num_bytes < SZ_64K && - (start > 0 || end + 1 < BTRFS_I(inode)->disk_i_size)) - btrfs_add_inode_defrag(NULL, inode); + inode_should_defrag(inode, start, end, num_bytes, SZ_64K); if (start == 0) { /* lets try to make an inline extent */ - ret = cow_file_range_inline(root, inode, start, end, 0, 0, - NULL); + ret = cow_file_range_inline(root, inode, start, end, 0, + BTRFS_COMPRESS_NONE, NULL); if (ret == 0) { extent_clear_unlock_delalloc(inode, start, end, delalloc_end, NULL, @@ -1008,39 +983,18 @@ static noinline int cow_file_range(struct inode *inode, if (ret < 0) goto out_unlock; - em = alloc_extent_map(); - if (!em) { - ret = -ENOMEM; - goto out_reserve; - } - em->start = start; - em->orig_start = em->start; ram_size = ins.offset; - em->len = ins.offset; - em->mod_start = em->start; - em->mod_len = em->len; - - em->block_start = ins.objectid; - em->block_len = ins.offset; - em->orig_block_len = ins.offset; - em->ram_bytes = ram_size; - em->bdev = fs_info->fs_devices->latest_bdev; - set_bit(EXTENT_FLAG_PINNED, &em->flags); - em->generation = -1; - - while (1) { - write_lock(&em_tree->lock); - ret = add_extent_mapping(em_tree, em, 1); - write_unlock(&em_tree->lock); - if (ret != -EEXIST) { - free_extent_map(em); - break; - } - btrfs_drop_extent_cache(inode, start, - start + ram_size - 1, 0); - } - if (ret) + em = create_io_em(inode, start, ins.offset, /* len */ + start, /* orig_start */ + ins.objectid, /* block_start */ + ins.offset, /* block_len */ + ins.offset, /* orig_block_len */ + ram_size, /* ram_bytes */ + BTRFS_COMPRESS_NONE, /* compress_type */ + BTRFS_ORDERED_REGULAR /* type */); + if (IS_ERR(em)) goto out_reserve; + free_extent_map(em); cur_alloc_size = ins.offset; ret = btrfs_add_ordered_extent(inode, start, ins.objectid, @@ -1164,7 +1118,6 @@ static int cow_file_range_async(struct inode *inode, struct page *locked_page, struct btrfs_root *root = BTRFS_I(inode)->root; unsigned long nr_pages; u64 cur_end; - int limit = 10 * SZ_1M; clear_extent_bit(&BTRFS_I(inode)->io_tree, start, end, EXTENT_LOCKED, 1, 0, NULL, GFP_NOFS); @@ -1196,12 +1149,6 @@ static int cow_file_range_async(struct inode *inode, struct page *locked_page, btrfs_queue_work(fs_info->delalloc_workers, &async_cow->work); - if (atomic_read(&fs_info->async_delalloc_pages) > limit) { - wait_event(fs_info->async_submit_wait, - (atomic_read(&fs_info->async_delalloc_pages) < - limit)); - } - while (atomic_read(&fs_info->async_submit_draining) && atomic_read(&fs_info->async_delalloc_pages)) { wait_event(fs_info->async_submit_wait, @@ -1250,11 +1197,11 @@ static noinline int run_delalloc_nocow(struct inode *inode, { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_root *root = BTRFS_I(inode)->root; - struct btrfs_trans_handle *trans; struct extent_buffer *leaf; struct btrfs_path *path; struct btrfs_file_extent_item *fi; struct btrfs_key found_key; + struct extent_map *em; u64 cow_start; u64 cur_offset; u64 extent_end; @@ -1269,7 +1216,7 @@ static noinline int run_delalloc_nocow(struct inode *inode, int nocow; int check_prev = 1; bool nolock; - u64 ino = btrfs_ino(inode); + u64 ino = btrfs_ino(BTRFS_I(inode)); path = btrfs_alloc_path(); if (!path) { @@ -1286,30 +1233,10 @@ static noinline int run_delalloc_nocow(struct inode *inode, nolock = btrfs_is_free_space_inode(inode); - if (nolock) - trans = btrfs_join_transaction_nolock(root); - else - trans = btrfs_join_transaction(root); - - if (IS_ERR(trans)) { - extent_clear_unlock_delalloc(inode, start, end, end, - locked_page, - EXTENT_LOCKED | EXTENT_DELALLOC | - EXTENT_DO_ACCOUNTING | - EXTENT_DEFRAG, PAGE_UNLOCK | - PAGE_CLEAR_DIRTY | - PAGE_SET_WRITEBACK | - PAGE_END_WRITEBACK); - btrfs_free_path(path); - return PTR_ERR(trans); - } - - trans->block_rsv = &fs_info->delalloc_block_rsv; - cow_start = (u64)-1; cur_offset = start; while (1) { - ret = btrfs_lookup_file_extent(trans, root, path, ino, + ret = btrfs_lookup_file_extent(NULL, root, path, ino, cur_offset, 0); if (ret < 0) goto error; @@ -1382,7 +1309,7 @@ next_slot: goto out_check; if (btrfs_extent_readonly(fs_info, disk_bytenr)) goto out_check; - if (btrfs_cross_ref_exist(trans, root, ino, + if (btrfs_cross_ref_exist(root, ino, found_key.offset - extent_offset, disk_bytenr)) goto out_check; @@ -1455,35 +1382,28 @@ out_check: } if (extent_type == BTRFS_FILE_EXTENT_PREALLOC) { - struct extent_map *em; - struct extent_map_tree *em_tree; - em_tree = &BTRFS_I(inode)->extent_tree; - em = alloc_extent_map(); - BUG_ON(!em); /* -ENOMEM */ - em->start = cur_offset; - em->orig_start = found_key.offset - extent_offset; - em->len = num_bytes; - em->block_len = num_bytes; - em->block_start = disk_bytenr; - em->orig_block_len = disk_num_bytes; - em->ram_bytes = ram_bytes; - em->bdev = fs_info->fs_devices->latest_bdev; - em->mod_start = em->start; - em->mod_len = em->len; - set_bit(EXTENT_FLAG_PINNED, &em->flags); - set_bit(EXTENT_FLAG_FILLING, &em->flags); - em->generation = -1; - while (1) { - write_lock(&em_tree->lock); - ret = add_extent_mapping(em_tree, em, 1); - write_unlock(&em_tree->lock); - if (ret != -EEXIST) { - free_extent_map(em); - break; - } - btrfs_drop_extent_cache(inode, em->start, - em->start + em->len - 1, 0); + u64 orig_start = found_key.offset - extent_offset; + + em = create_io_em(inode, cur_offset, num_bytes, + orig_start, + disk_bytenr, /* block_start */ + num_bytes, /* block_len */ + disk_num_bytes, /* orig_block_len */ + ram_bytes, BTRFS_COMPRESS_NONE, + BTRFS_ORDERED_PREALLOC); + if (IS_ERR(em)) { + if (!nolock && nocow) + btrfs_end_write_no_snapshoting(root); + if (nocow) + btrfs_dec_nocow_writers(fs_info, + disk_bytenr); + ret = PTR_ERR(em); + goto error; } + free_extent_map(em); + } + + if (extent_type == BTRFS_FILE_EXTENT_PREALLOC) { type = BTRFS_ORDERED_PREALLOC; } else { type = BTRFS_ORDERED_NOCOW; @@ -1534,10 +1454,6 @@ out_check: } error: - err = btrfs_end_transaction(trans); - if (!ret) - ret = err; - if (ret && cur_offset < end) extent_clear_unlock_delalloc(inode, cur_offset, end, end, locked_page, EXTENT_LOCKED | @@ -1609,7 +1525,7 @@ static void btrfs_split_extent_hook(struct inode *inode, size = orig->end - orig->start + 1; if (size > BTRFS_MAX_EXTENT_SIZE) { - u64 num_extents; + u32 num_extents; u64 new_size; /* @@ -1617,13 +1533,10 @@ static void btrfs_split_extent_hook(struct inode *inode, * applies here, just in reverse. */ new_size = orig->end - split + 1; - num_extents = div64_u64(new_size + BTRFS_MAX_EXTENT_SIZE - 1, - BTRFS_MAX_EXTENT_SIZE); + num_extents = count_max_extents(new_size); new_size = split - orig->start; - num_extents += div64_u64(new_size + BTRFS_MAX_EXTENT_SIZE - 1, - BTRFS_MAX_EXTENT_SIZE); - if (div64_u64(size + BTRFS_MAX_EXTENT_SIZE - 1, - BTRFS_MAX_EXTENT_SIZE) >= num_extents) + num_extents += count_max_extents(new_size); + if (count_max_extents(size) >= num_extents) return; } @@ -1643,7 +1556,7 @@ static void btrfs_merge_extent_hook(struct inode *inode, struct extent_state *other) { u64 new_size, old_size; - u64 num_extents; + u32 num_extents; /* not delalloc, ignore it */ if (!(other->state & EXTENT_DELALLOC)) @@ -1681,14 +1594,10 @@ static void btrfs_merge_extent_hook(struct inode *inode, * this case. */ old_size = other->end - other->start + 1; - num_extents = div64_u64(old_size + BTRFS_MAX_EXTENT_SIZE - 1, - BTRFS_MAX_EXTENT_SIZE); + num_extents = count_max_extents(old_size); old_size = new->end - new->start + 1; - num_extents += div64_u64(old_size + BTRFS_MAX_EXTENT_SIZE - 1, - BTRFS_MAX_EXTENT_SIZE); - - if (div64_u64(new_size + BTRFS_MAX_EXTENT_SIZE - 1, - BTRFS_MAX_EXTENT_SIZE) >= num_extents) + num_extents += count_max_extents(old_size); + if (count_max_extents(new_size) >= num_extents) return; spin_lock(&BTRFS_I(inode)->lock); @@ -1797,8 +1706,7 @@ static void btrfs_clear_bit_hook(struct inode *inode, { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); u64 len = state->end + 1 - state->start; - u64 num_extents = div64_u64(len + BTRFS_MAX_EXTENT_SIZE -1, - BTRFS_MAX_EXTENT_SIZE); + u32 num_extents = count_max_extents(len); spin_lock(&BTRFS_I(inode)->lock); if ((state->state & EXTENT_DEFRAG) && (*bits & EXTENT_DEFRAG)) @@ -1997,8 +1905,7 @@ out: * at IO completion time based on sums calculated at bio submission time. */ static noinline int add_pending_csums(struct btrfs_trans_handle *trans, - struct inode *inode, u64 file_offset, - struct list_head *list) + struct inode *inode, struct list_head *list) { struct btrfs_ordered_sum *sum; @@ -2161,7 +2068,7 @@ static int insert_reserved_file_extent(struct btrfs_trans_handle *trans, goto out; if (!extent_inserted) { - ins.objectid = btrfs_ino(inode); + ins.objectid = btrfs_ino(BTRFS_I(inode)); ins.offset = file_pos; ins.type = BTRFS_EXTENT_DATA_KEY; @@ -2194,8 +2101,7 @@ static int insert_reserved_file_extent(struct btrfs_trans_handle *trans, ins.offset = disk_num_bytes; ins.type = BTRFS_EXTENT_ITEM_KEY; ret = btrfs_alloc_reserved_file_extent(trans, root->root_key.objectid, - btrfs_ino(inode), file_pos, - ram_bytes, &ins); + btrfs_ino(BTRFS_I(inode)), file_pos, ram_bytes, &ins); /* * Release the reserved range from inode dirty range map, as it is * already moved into delayed_ref_head @@ -2320,7 +2226,7 @@ static noinline int record_one_backref(u64 inum, u64 offset, u64 root_id, u64 num_bytes; if (BTRFS_I(inode)->root->root_key.objectid == root_id && - inum == btrfs_ino(inode)) + inum == btrfs_ino(BTRFS_I(inode))) return 0; key.objectid = root_id; @@ -2589,7 +2495,7 @@ static noinline int relink_extent_backref(struct btrfs_path *path, if (ret) goto out_free_path; again: - key.objectid = btrfs_ino(inode); + key.objectid = btrfs_ino(BTRFS_I(inode)); key.type = BTRFS_EXTENT_DATA_KEY; key.offset = start; @@ -2768,7 +2674,7 @@ record_old_file_extents(struct inode *inode, if (!path) goto out_kfree; - key.objectid = btrfs_ino(inode); + key.objectid = btrfs_ino(BTRFS_I(inode)); key.type = BTRFS_EXTENT_DATA_KEY; key.offset = new->file_pos; @@ -2803,7 +2709,7 @@ record_old_file_extents(struct inode *inode, btrfs_item_key_to_cpu(l, &key, slot); - if (key.objectid != btrfs_ino(inode)) + if (key.objectid != btrfs_ino(BTRFS_I(inode))) break; if (key.type != BTRFS_EXTENT_DATA_KEY) break; @@ -2993,8 +2899,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent) goto out_unlock; } - add_pending_csums(trans, inode, ordered_extent->file_offset, - &ordered_extent->list); + add_pending_csums(trans, inode, &ordered_extent->list); btrfs_ordered_update_i_size(inode, 0, ordered_extent); ret = btrfs_update_inode_fallback(trans, root, inode); @@ -3123,9 +3028,8 @@ static int __readpage_endio_check(struct inode *inode, kunmap_atomic(kaddr); return 0; zeroit: - btrfs_warn_rl(BTRFS_I(inode)->root->fs_info, - "csum failed ino %llu off %llu csum %u expected csum %u", - btrfs_ino(inode), start, csum, csum_expected); + btrfs_print_data_csum_error(inode, start, csum, csum_expected, + io_bio->mirror_num); memset(kaddr + pgoff, 1, len); flush_dcache_page(page); kunmap_atomic(kaddr); @@ -3326,7 +3230,8 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode) /* insert an orphan item to track this unlinked/truncated file */ if (insert >= 1) { - ret = btrfs_insert_orphan_item(trans, root, btrfs_ino(inode)); + ret = btrfs_insert_orphan_item(trans, root, + btrfs_ino(BTRFS_I(inode))); if (ret) { atomic_dec(&root->orphan_inodes); if (reserve) { @@ -3382,7 +3287,7 @@ static int btrfs_orphan_del(struct btrfs_trans_handle *trans, atomic_dec(&root->orphan_inodes); if (trans) ret = btrfs_del_orphan_item(trans, root, - btrfs_ino(inode)); + btrfs_ino(BTRFS_I(inode))); } if (release_rsv) @@ -3789,7 +3694,7 @@ cache_index: goto cache_acl; btrfs_item_key_to_cpu(leaf, &location, path->slots[0]); - if (location.objectid != btrfs_ino(inode)) + if (location.objectid != btrfs_ino(BTRFS_I(inode))) goto cache_acl; ptr = btrfs_item_ptr_offset(leaf, path->slots[0]); @@ -3811,14 +3716,14 @@ cache_acl: * any xattrs or acls */ maybe_acls = acls_after_inode_item(leaf, path->slots[0], - btrfs_ino(inode), &first_xattr_slot); + btrfs_ino(BTRFS_I(inode)), &first_xattr_slot); if (first_xattr_slot != -1) { path->slots[0] = first_xattr_slot; ret = btrfs_load_inode_props(inode, path); if (ret) btrfs_err(fs_info, "error loading props for ino %llu (root %llu): %d", - btrfs_ino(inode), + btrfs_ino(BTRFS_I(inode)), root->root_key.objectid, ret); } btrfs_free_path(path); @@ -3993,7 +3898,8 @@ noinline int btrfs_update_inode_fallback(struct btrfs_trans_handle *trans, */ static int __btrfs_unlink_inode(struct btrfs_trans_handle *trans, struct btrfs_root *root, - struct inode *dir, struct inode *inode, + struct btrfs_inode *dir, + struct btrfs_inode *inode, const char *name, int name_len) { struct btrfs_fs_info *fs_info = root->fs_info; @@ -4040,10 +3946,10 @@ static int __btrfs_unlink_inode(struct btrfs_trans_handle *trans, * that we delay to delete it, and just do this deletion when * we update the inode item. */ - if (BTRFS_I(inode)->dir_index) { + if (inode->dir_index) { ret = btrfs_delayed_delete_inode_ref(inode); if (!ret) { - index = BTRFS_I(inode)->dir_index; + index = inode->dir_index; goto skip_backref; } } @@ -4064,15 +3970,15 @@ skip_backref: goto err; } - ret = btrfs_del_inode_ref_in_log(trans, root, name, name_len, - inode, dir_ino); + ret = btrfs_del_inode_ref_in_log(trans, root, name, name_len, inode, + dir_ino); if (ret != 0 && ret != -ENOENT) { btrfs_abort_transaction(trans, ret); goto err; } - ret = btrfs_del_dir_entries_in_log(trans, root, name, name_len, - dir, index); + ret = btrfs_del_dir_entries_in_log(trans, root, name, name_len, dir, + index); if (ret == -ENOENT) ret = 0; else if (ret) @@ -4082,26 +3988,27 @@ err: if (ret) goto out; - btrfs_i_size_write(dir, dir->i_size - name_len * 2); - inode_inc_iversion(inode); - inode_inc_iversion(dir); - inode->i_ctime = dir->i_mtime = - dir->i_ctime = current_time(inode); - ret = btrfs_update_inode(trans, root, dir); + btrfs_i_size_write(&dir->vfs_inode, + dir->vfs_inode.i_size - name_len * 2); + inode_inc_iversion(&inode->vfs_inode); + inode_inc_iversion(&dir->vfs_inode); + inode->vfs_inode.i_ctime = dir->vfs_inode.i_mtime = + dir->vfs_inode.i_ctime = current_time(&inode->vfs_inode); + ret = btrfs_update_inode(trans, root, &dir->vfs_inode); out: return ret; } int btrfs_unlink_inode(struct btrfs_trans_handle *trans, struct btrfs_root *root, - struct inode *dir, struct inode *inode, + struct btrfs_inode *dir, struct btrfs_inode *inode, const char *name, int name_len) { int ret; ret = __btrfs_unlink_inode(trans, root, dir, inode, name, name_len); if (!ret) { - drop_nlink(inode); - ret = btrfs_update_inode(trans, root, inode); + drop_nlink(&inode->vfs_inode); + ret = btrfs_update_inode(trans, root, &inode->vfs_inode); } return ret; } @@ -4139,10 +4046,12 @@ static int btrfs_unlink(struct inode *dir, struct dentry *dentry) if (IS_ERR(trans)) return PTR_ERR(trans); - btrfs_record_unlink_dir(trans, dir, d_inode(dentry), 0); + btrfs_record_unlink_dir(trans, BTRFS_I(dir), BTRFS_I(d_inode(dentry)), + 0); - ret = btrfs_unlink_inode(trans, root, dir, d_inode(dentry), - dentry->d_name.name, dentry->d_name.len); + ret = btrfs_unlink_inode(trans, root, BTRFS_I(dir), + BTRFS_I(d_inode(dentry)), dentry->d_name.name, + dentry->d_name.len); if (ret) goto out; @@ -4170,7 +4079,7 @@ int btrfs_unlink_subvol(struct btrfs_trans_handle *trans, struct btrfs_key key; u64 index; int ret; - u64 dir_ino = btrfs_ino(dir); + u64 dir_ino = btrfs_ino(BTRFS_I(dir)); path = btrfs_alloc_path(); if (!path) @@ -4222,7 +4131,7 @@ int btrfs_unlink_subvol(struct btrfs_trans_handle *trans, } btrfs_release_path(path); - ret = btrfs_delete_delayed_dir_index(trans, fs_info, dir, index); + ret = btrfs_delete_delayed_dir_index(trans, fs_info, BTRFS_I(dir), index); if (ret) { btrfs_abort_transaction(trans, ret); goto out; @@ -4249,14 +4158,14 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry) if (inode->i_size > BTRFS_EMPTY_DIR_SIZE) return -ENOTEMPTY; - if (btrfs_ino(inode) == BTRFS_FIRST_FREE_OBJECTID) + if (btrfs_ino(BTRFS_I(inode)) == BTRFS_FIRST_FREE_OBJECTID) return -EPERM; trans = __unlink_start_trans(dir); if (IS_ERR(trans)) return PTR_ERR(trans); - if (unlikely(btrfs_ino(inode) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)) { + if (unlikely(btrfs_ino(BTRFS_I(inode)) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)) { err = btrfs_unlink_subvol(trans, root, dir, BTRFS_I(inode)->location.objectid, dentry->d_name.name, @@ -4271,8 +4180,9 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry) last_unlink_trans = BTRFS_I(inode)->last_unlink_trans; /* now the directory is empty */ - err = btrfs_unlink_inode(trans, root, dir, d_inode(dentry), - dentry->d_name.name, dentry->d_name.len); + err = btrfs_unlink_inode(trans, root, BTRFS_I(dir), + BTRFS_I(d_inode(dentry)), dentry->d_name.name, + dentry->d_name.len); if (!err) { btrfs_i_size_write(inode, 0); /* @@ -4398,7 +4308,7 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, int extent_type = -1; int ret; int err = 0; - u64 ino = btrfs_ino(inode); + u64 ino = btrfs_ino(BTRFS_I(inode)); u64 bytes_deleted = 0; bool be_nice = 0; bool should_throttle = 0; @@ -4437,7 +4347,7 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, * items. */ if (min_type == 0 && root == BTRFS_I(inode)->root) - btrfs_kill_delayed_inode_items(inode); + btrfs_kill_delayed_inode_items(BTRFS_I(inode)); key.objectid = ino; key.offset = (u64)-1; @@ -4702,6 +4612,13 @@ error: btrfs_free_path(path); + if (err == 0) { + /* only inline file may have last_size != new_size */ + if (new_size >= fs_info->sectorsize || + new_size > fs_info->max_inline) + ASSERT(last_size == new_size); + } + if (be_nice && bytes_deleted > SZ_32M) { unsigned long updates = trans->delayed_ref_updates; if (updates) { @@ -4870,8 +4787,8 @@ static int maybe_insert_hole(struct btrfs_root *root, struct inode *inode, return ret; } - ret = btrfs_insert_file_extent(trans, root, btrfs_ino(inode), offset, - 0, 0, len, 0, len, 0, 0, 0); + ret = btrfs_insert_file_extent(trans, root, btrfs_ino(BTRFS_I(inode)), + offset, 0, 0, len, 0, len, 0, 0, 0); if (ret) btrfs_abort_transaction(trans, ret); else @@ -5087,6 +5004,13 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr) if (ret && inode->i_nlink) { int err; + /* To get a stable disk_i_size */ + err = btrfs_wait_ordered_range(inode, 0, (u64)-1); + if (err) { + btrfs_orphan_del(NULL, inode); + return err; + } + /* * failed to truncate, disk_i_size is only adjusted down * as we remove extents, so it should represent the true @@ -5282,7 +5206,7 @@ void btrfs_evict_inode(struct inode *inode) goto no_delete; } - ret = btrfs_commit_inode_delayed_inode(inode); + ret = btrfs_commit_inode_delayed_inode(BTRFS_I(inode)); if (ret) { btrfs_orphan_del(NULL, inode); goto no_delete; @@ -5402,12 +5326,12 @@ void btrfs_evict_inode(struct inode *inode) trans->block_rsv = &fs_info->trans_block_rsv; if (!(root == fs_info->tree_root || root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID)) - btrfs_return_ino(root, btrfs_ino(inode)); + btrfs_return_ino(root, btrfs_ino(BTRFS_I(inode))); btrfs_end_transaction(trans); btrfs_btree_balance_dirty(fs_info); no_delete: - btrfs_remove_delayed_node(inode); + btrfs_remove_delayed_node(BTRFS_I(inode)); clear_inode(inode); } @@ -5429,8 +5353,8 @@ static int btrfs_inode_by_name(struct inode *dir, struct dentry *dentry, if (!path) return -ENOMEM; - di = btrfs_lookup_dir_item(NULL, root, path, btrfs_ino(dir), name, - namelen, 0); + di = btrfs_lookup_dir_item(NULL, root, path, btrfs_ino(BTRFS_I(dir)), + name, namelen, 0); if (IS_ERR(di)) ret = PTR_ERR(di); @@ -5485,7 +5409,7 @@ static int fixup_tree_root_location(struct btrfs_fs_info *fs_info, leaf = path->nodes[0]; ref = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_root_ref); - if (btrfs_root_ref_dirid(leaf, ref) != btrfs_ino(dir) || + if (btrfs_root_ref_dirid(leaf, ref) != btrfs_ino(BTRFS_I(dir)) || btrfs_root_ref_name_len(leaf, ref) != dentry->d_name.len) goto out; @@ -5520,7 +5444,7 @@ static void inode_tree_add(struct inode *inode) struct rb_node **p; struct rb_node *parent; struct rb_node *new = &BTRFS_I(inode)->rb_node; - u64 ino = btrfs_ino(inode); + u64 ino = btrfs_ino(BTRFS_I(inode)); if (inode_unhashed(inode)) return; @@ -5531,9 +5455,9 @@ static void inode_tree_add(struct inode *inode) parent = *p; entry = rb_entry(parent, struct btrfs_inode, rb_node); - if (ino < btrfs_ino(&entry->vfs_inode)) + if (ino < btrfs_ino(BTRFS_I(&entry->vfs_inode))) p = &parent->rb_left; - else if (ino > btrfs_ino(&entry->vfs_inode)) + else if (ino > btrfs_ino(BTRFS_I(&entry->vfs_inode))) p = &parent->rb_right; else { WARN_ON(!(entry->vfs_inode.i_state & @@ -5593,9 +5517,9 @@ again: prev = node; entry = rb_entry(node, struct btrfs_inode, rb_node); - if (objectid < btrfs_ino(&entry->vfs_inode)) + if (objectid < btrfs_ino(BTRFS_I(&entry->vfs_inode))) node = node->rb_left; - else if (objectid > btrfs_ino(&entry->vfs_inode)) + else if (objectid > btrfs_ino(BTRFS_I(&entry->vfs_inode))) node = node->rb_right; else break; @@ -5603,7 +5527,7 @@ again: if (!node) { while (prev) { entry = rb_entry(prev, struct btrfs_inode, rb_node); - if (objectid <= btrfs_ino(&entry->vfs_inode)) { + if (objectid <= btrfs_ino(BTRFS_I(&entry->vfs_inode))) { node = prev; break; } @@ -5612,7 +5536,7 @@ again: } while (node) { entry = rb_entry(node, struct btrfs_inode, rb_node); - objectid = btrfs_ino(&entry->vfs_inode) + 1; + objectid = btrfs_ino(BTRFS_I(&entry->vfs_inode)) + 1; inode = igrab(&entry->vfs_inode); if (inode) { spin_unlock(&root->inode_lock); @@ -5796,7 +5720,7 @@ static int btrfs_dentry_delete(const struct dentry *dentry) if (btrfs_root_refs(&root->root_item) == 0) return 1; - if (btrfs_ino(inode) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID) + if (btrfs_ino(BTRFS_I(inode)) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID) return 1; } return 0; @@ -5865,7 +5789,7 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx) key.type = BTRFS_DIR_INDEX_KEY; key.offset = ctx->pos; - key.objectid = btrfs_ino(inode); + key.objectid = btrfs_ino(BTRFS_I(inode)); ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) @@ -6062,7 +5986,7 @@ static int btrfs_set_inode_index_count(struct inode *inode) struct extent_buffer *leaf; int ret; - key.objectid = btrfs_ino(inode); + key.objectid = btrfs_ino(BTRFS_I(inode)); key.type = BTRFS_DIR_INDEX_KEY; key.offset = (u64)-1; @@ -6094,7 +6018,7 @@ static int btrfs_set_inode_index_count(struct inode *inode) leaf = path->nodes[0]; btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]); - if (found_key.objectid != btrfs_ino(inode) || + if (found_key.objectid != btrfs_ino(BTRFS_I(inode)) || found_key.type != BTRFS_DIR_INDEX_KEY) { BTRFS_I(inode)->index_cnt = 2; goto out; @@ -6115,7 +6039,7 @@ int btrfs_set_inode_index(struct inode *dir, u64 *index) int ret = 0; if (BTRFS_I(dir)->index_cnt == (u64)-1) { - ret = btrfs_inode_delayed_dir_index_count(dir); + ret = btrfs_inode_delayed_dir_index_count(BTRFS_I(dir)); if (ret) { ret = btrfs_set_inode_index_count(dir); if (ret) @@ -6294,7 +6218,7 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans, if (ret) btrfs_err(fs_info, "error inheriting props for ino %llu (root %llu): %d", - btrfs_ino(inode), root->root_key.objectid, ret); + btrfs_ino(BTRFS_I(inode)), root->root_key.objectid, ret); return inode; @@ -6327,8 +6251,8 @@ int btrfs_add_link(struct btrfs_trans_handle *trans, int ret = 0; struct btrfs_key key; struct btrfs_root *root = BTRFS_I(parent_inode)->root; - u64 ino = btrfs_ino(inode); - u64 parent_ino = btrfs_ino(parent_inode); + u64 ino = btrfs_ino(BTRFS_I(inode)); + u64 parent_ino = btrfs_ino(BTRFS_I(parent_inode)); if (unlikely(ino == BTRFS_FIRST_FREE_OBJECTID)) { memcpy(&key, &BTRFS_I(inode)->root->root_key, sizeof(key)); @@ -6427,8 +6351,8 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry, goto out_unlock; inode = btrfs_new_inode(trans, root, dir, dentry->d_name.name, - dentry->d_name.len, btrfs_ino(dir), objectid, - mode, &index); + dentry->d_name.len, btrfs_ino(BTRFS_I(dir)), objectid, + mode, &index); if (IS_ERR(inode)) { err = PTR_ERR(inode); goto out_unlock; @@ -6499,8 +6423,8 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry, goto out_unlock; inode = btrfs_new_inode(trans, root, dir, dentry->d_name.name, - dentry->d_name.len, btrfs_ino(dir), objectid, - mode, &index); + dentry->d_name.len, btrfs_ino(BTRFS_I(dir)), objectid, + mode, &index); if (IS_ERR(inode)) { err = PTR_ERR(inode); goto out_unlock; @@ -6609,7 +6533,7 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir, goto fail; } d_instantiate(dentry, inode); - btrfs_log_new_name(trans, inode, NULL, parent); + btrfs_log_new_name(trans, BTRFS_I(inode), NULL, parent); } btrfs_balance_delayed_items(fs_info); @@ -6649,8 +6573,8 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) goto out_fail; inode = btrfs_new_inode(trans, root, dir, dentry->d_name.name, - dentry->d_name.len, btrfs_ino(dir), objectid, - S_IFDIR | mode, &index); + dentry->d_name.len, btrfs_ino(BTRFS_I(dir)), objectid, + S_IFDIR | mode, &index); if (IS_ERR(inode)) { err = PTR_ERR(inode); goto out_fail; @@ -6810,7 +6734,7 @@ struct extent_map *btrfs_get_extent(struct inode *inode, struct page *page, int err = 0; u64 extent_start = 0; u64 extent_end = 0; - u64 objectid = btrfs_ino(inode); + u64 objectid = btrfs_ino(BTRFS_I(inode)); u32 found_type; struct btrfs_path *path = NULL; struct btrfs_root *root = BTRFS_I(inode)->root; @@ -7068,7 +6992,7 @@ insert: write_unlock(&em_tree->lock); out: - trace_btrfs_get_extent(root, inode, em); + trace_btrfs_get_extent(root, BTRFS_I(inode), em); btrfs_free_path(path); if (trans) { @@ -7225,9 +7149,11 @@ static struct extent_map *btrfs_create_dio_extent(struct inode *inode, int ret; if (type != BTRFS_ORDERED_NOCOW) { - em = create_pinned_em(inode, start, len, orig_start, - block_start, block_len, orig_block_len, - ram_bytes, type); + em = create_io_em(inode, start, len, orig_start, + block_start, block_len, orig_block_len, + ram_bytes, + BTRFS_COMPRESS_NONE, /* compress_type */ + type); if (IS_ERR(em)) goto out; } @@ -7264,7 +7190,7 @@ static struct extent_map *btrfs_new_extent_direct(struct inode *inode, em = btrfs_create_dio_extent(inode, start, ins.offset, start, ins.objectid, ins.offset, ins.offset, - ins.offset, 0); + ins.offset, BTRFS_ORDERED_REGULAR); btrfs_dec_block_group_reservations(fs_info, ins.objectid); if (IS_ERR(em)) btrfs_free_reserved_extent(fs_info, ins.objectid, @@ -7282,7 +7208,6 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len, u64 *ram_bytes) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - struct btrfs_trans_handle *trans; struct btrfs_path *path; int ret; struct extent_buffer *leaf; @@ -7302,8 +7227,8 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len, if (!path) return -ENOMEM; - ret = btrfs_lookup_file_extent(NULL, root, path, btrfs_ino(inode), - offset, 0); + ret = btrfs_lookup_file_extent(NULL, root, path, + btrfs_ino(BTRFS_I(inode)), offset, 0); if (ret < 0) goto out; @@ -7319,7 +7244,7 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len, ret = 0; leaf = path->nodes[0]; btrfs_item_key_to_cpu(leaf, &key, slot); - if (key.objectid != btrfs_ino(inode) || + if (key.objectid != btrfs_ino(BTRFS_I(inode)) || key.type != BTRFS_EXTENT_DATA_KEY) { /* not our file or wrong item type, must cow */ goto out; @@ -7385,15 +7310,9 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len, * look for other files referencing this extent, if we * find any we must cow */ - trans = btrfs_join_transaction(root); - if (IS_ERR(trans)) { - ret = 0; - goto out; - } - ret = btrfs_cross_ref_exist(trans, root, btrfs_ino(inode), + ret = btrfs_cross_ref_exist(root, btrfs_ino(BTRFS_I(inode)), key.offset - backref_offset, disk_bytenr); - btrfs_end_transaction(trans); if (ret) { ret = 0; goto out; @@ -7570,17 +7489,23 @@ static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend, return ret; } -static struct extent_map *create_pinned_em(struct inode *inode, u64 start, - u64 len, u64 orig_start, - u64 block_start, u64 block_len, - u64 orig_block_len, u64 ram_bytes, - int type) +/* The callers of this must take lock_extent() */ +static struct extent_map *create_io_em(struct inode *inode, u64 start, u64 len, + u64 orig_start, u64 block_start, + u64 block_len, u64 orig_block_len, + u64 ram_bytes, int compress_type, + int type) { struct extent_map_tree *em_tree; struct extent_map *em; struct btrfs_root *root = BTRFS_I(inode)->root; int ret; + ASSERT(type == BTRFS_ORDERED_PREALLOC || + type == BTRFS_ORDERED_COMPRESSED || + type == BTRFS_ORDERED_NOCOW || + type == BTRFS_ORDERED_REGULAR); + em_tree = &BTRFS_I(inode)->extent_tree; em = alloc_extent_map(); if (!em) @@ -7588,8 +7513,6 @@ static struct extent_map *create_pinned_em(struct inode *inode, u64 start, em->start = start; em->orig_start = orig_start; - em->mod_start = start; - em->mod_len = len; em->len = len; em->block_len = block_len; em->block_start = block_start; @@ -7598,8 +7521,12 @@ static struct extent_map *create_pinned_em(struct inode *inode, u64 start, em->ram_bytes = ram_bytes; em->generation = -1; set_bit(EXTENT_FLAG_PINNED, &em->flags); - if (type == BTRFS_ORDERED_PREALLOC) + if (type == BTRFS_ORDERED_PREALLOC) { set_bit(EXTENT_FLAG_FILLING, &em->flags); + } else if (type == BTRFS_ORDERED_COMPRESSED) { + set_bit(EXTENT_FLAG_COMPRESSED, &em->flags); + em->compress_type = compress_type; + } do { btrfs_drop_extent_cache(inode, em->start, @@ -7607,6 +7534,10 @@ static struct extent_map *create_pinned_em(struct inode *inode, u64 start, write_lock(&em_tree->lock); ret = add_extent_mapping(em_tree, em, 1); write_unlock(&em_tree->lock); + /* + * The caller has taken lock_extent(), who could race with us + * to add em? + */ } while (ret == -EEXIST); if (ret) { @@ -7614,6 +7545,7 @@ static struct extent_map *create_pinned_em(struct inode *inode, u64 start, return ERR_PTR(ret); } + /* em got 2 refs now, callers needs to do free_extent_map once. */ return em; } @@ -7621,10 +7553,8 @@ static void adjust_dio_outstanding_extents(struct inode *inode, struct btrfs_dio_data *dio_data, const u64 len) { - unsigned num_extents; + unsigned num_extents = count_max_extents(len); - num_extents = (unsigned) div64_u64(len + BTRFS_MAX_EXTENT_SIZE - 1, - BTRFS_MAX_EXTENT_SIZE); /* * If we have an outstanding_extents count still set then we're * within our reservation, otherwise we need to adjust our inode @@ -7804,7 +7734,7 @@ unlock: * Need to update the i_size under the extent lock so buffered * readers will get the updated i_size when we unlock. */ - if (start + len > i_size_read(inode)) + if (!dio_data->overwrite && start + len > i_size_read(inode)) i_size_write(inode, start + len); adjust_dio_outstanding_extents(inode, dio_data, len); @@ -8254,7 +8184,8 @@ static void btrfs_end_dio_bio(struct bio *bio) if (err) btrfs_warn(BTRFS_I(dip->inode)->root->fs_info, "direct IO failed ino %llu rw %d,%u sector %#Lx len %u err no %d", - btrfs_ino(dip->inode), bio_op(bio), bio->bi_opf, + btrfs_ino(BTRFS_I(dip->inode)), bio_op(bio), + bio->bi_opf, (unsigned long long)bio->bi_iter.bi_sector, bio->bi_iter.bi_size, err); @@ -8679,15 +8610,14 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) * not unlock the i_mutex at this case. */ if (offset + count <= inode->i_size) { + dio_data.overwrite = 1; inode_unlock(inode); relock = true; } ret = btrfs_delalloc_reserve_space(inode, offset, count); if (ret) goto out; - dio_data.outstanding_extents = div64_u64(count + - BTRFS_MAX_EXTENT_SIZE - 1, - BTRFS_MAX_EXTENT_SIZE); + dio_data.outstanding_extents = count_max_extents(count); /* * We need to know how many extents we reserved so that we can @@ -8831,7 +8761,7 @@ static int btrfs_releasepage(struct page *page, gfp_t gfp_flags) { if (PageWriteback(page) || PageDirty(page)) return 0; - return __btrfs_releasepage(page, gfp_flags & GFP_NOFS); + return __btrfs_releasepage(page, gfp_flags); } static void btrfs_invalidatepage(struct page *page, unsigned int offset, @@ -8964,10 +8894,10 @@ again: * beyond EOF, then the page is guaranteed safe against truncation until we * unlock the page. */ -int btrfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) +int btrfs_page_mkwrite(struct vm_fault *vmf) { struct page *page = vmf->page; - struct inode *inode = file_inode(vma->vm_file); + struct inode *inode = file_inode(vmf->vma->vm_file); struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; struct btrfs_ordered_extent *ordered; @@ -9000,7 +8930,7 @@ int btrfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) ret = btrfs_delalloc_reserve_space(inode, page_start, reserved_space); if (!ret) { - ret = file_update_time(vma->vm_file); + ret = file_update_time(vmf->vma->vm_file); reserved = 1; } if (ret) { @@ -9032,7 +8962,7 @@ again: * we can't set the delalloc bits if there are pending ordered * extents. Drop our locks and wait for them to finish */ - ordered = btrfs_lookup_ordered_range(inode, page_start, page_end); + ordered = btrfs_lookup_ordered_range(inode, page_start, PAGE_SIZE); if (ordered) { unlock_extent_cached(io_tree, page_start, page_end, &cached_state, GFP_NOFS); @@ -9056,11 +8986,11 @@ again: } /* - * XXX - page_mkwrite gets called every time the page is dirtied, even - * if it was already dirty, so for space accounting reasons we need to - * clear any delalloc bits for the range we are fixing to save. There - * is probably a better way to do this, but for now keep consistent with - * prepare_pages in the normal write path. + * page_mkwrite gets called when the page is firstly dirtied after it's + * faulted in, but write(2) could also dirty a page and set delalloc + * bits, thus in this case for space account reason, we still need to + * clear any delalloc bits within this page range since we have to + * reserve data&meta space before lock_page() (see above comments). */ clear_extent_bit(&BTRFS_I(inode)->io_tree, page_start, end, EXTENT_DIRTY | EXTENT_DELALLOC | @@ -9384,7 +9314,7 @@ void btrfs_destroy_inode(struct inode *inode) if (test_bit(BTRFS_INODE_HAS_ORPHAN_ITEM, &BTRFS_I(inode)->runtime_flags)) { btrfs_info(fs_info, "inode %llu still on the orphan list", - btrfs_ino(inode)); + btrfs_ino(BTRFS_I(inode))); atomic_dec(&root->orphan_inodes); } @@ -9513,8 +9443,8 @@ static int btrfs_rename_exchange(struct inode *old_dir, struct inode *old_inode = old_dentry->d_inode; struct timespec ctime = current_time(old_inode); struct dentry *parent; - u64 old_ino = btrfs_ino(old_inode); - u64 new_ino = btrfs_ino(new_inode); + u64 old_ino = btrfs_ino(BTRFS_I(old_inode)); + u64 new_ino = btrfs_ino(BTRFS_I(new_inode)); u64 old_idx = 0; u64 new_idx = 0; u64 root_objectid; @@ -9571,7 +9501,8 @@ static int btrfs_rename_exchange(struct inode *old_dir, new_dentry->d_name.name, new_dentry->d_name.len, old_ino, - btrfs_ino(new_dir), old_idx); + btrfs_ino(BTRFS_I(new_dir)), + old_idx); if (ret) goto out_fail; } @@ -9587,7 +9518,8 @@ static int btrfs_rename_exchange(struct inode *old_dir, old_dentry->d_name.name, old_dentry->d_name.len, new_ino, - btrfs_ino(old_dir), new_idx); + btrfs_ino(BTRFS_I(old_dir)), + new_idx); if (ret) goto out_fail; } @@ -9603,8 +9535,10 @@ static int btrfs_rename_exchange(struct inode *old_dir, new_inode->i_ctime = ctime; if (old_dentry->d_parent != new_dentry->d_parent) { - btrfs_record_unlink_dir(trans, old_dir, old_inode, 1); - btrfs_record_unlink_dir(trans, new_dir, new_inode, 1); + btrfs_record_unlink_dir(trans, BTRFS_I(old_dir), + BTRFS_I(old_inode), 1); + btrfs_record_unlink_dir(trans, BTRFS_I(new_dir), + BTRFS_I(new_inode), 1); } /* src is a subvolume */ @@ -9615,8 +9549,8 @@ static int btrfs_rename_exchange(struct inode *old_dir, old_dentry->d_name.name, old_dentry->d_name.len); } else { /* src is an inode */ - ret = __btrfs_unlink_inode(trans, root, old_dir, - old_dentry->d_inode, + ret = __btrfs_unlink_inode(trans, root, BTRFS_I(old_dir), + BTRFS_I(old_dentry->d_inode), old_dentry->d_name.name, old_dentry->d_name.len); if (!ret) @@ -9635,8 +9569,8 @@ static int btrfs_rename_exchange(struct inode *old_dir, new_dentry->d_name.name, new_dentry->d_name.len); } else { /* dest is an inode */ - ret = __btrfs_unlink_inode(trans, dest, new_dir, - new_dentry->d_inode, + ret = __btrfs_unlink_inode(trans, dest, BTRFS_I(new_dir), + BTRFS_I(new_dentry->d_inode), new_dentry->d_name.name, new_dentry->d_name.len); if (!ret) @@ -9670,13 +9604,15 @@ static int btrfs_rename_exchange(struct inode *old_dir, if (root_log_pinned) { parent = new_dentry->d_parent; - btrfs_log_new_name(trans, old_inode, old_dir, parent); + btrfs_log_new_name(trans, BTRFS_I(old_inode), BTRFS_I(old_dir), + parent); btrfs_end_log_trans(root); root_log_pinned = false; } if (dest_log_pinned) { parent = old_dentry->d_parent; - btrfs_log_new_name(trans, new_inode, new_dir, parent); + btrfs_log_new_name(trans, BTRFS_I(new_inode), BTRFS_I(new_dir), + parent); btrfs_end_log_trans(dest); dest_log_pinned = false; } @@ -9693,11 +9629,11 @@ out_fail: * allow the tasks to sync it. */ if (ret && (root_log_pinned || dest_log_pinned)) { - if (btrfs_inode_in_log(old_dir, fs_info->generation) || - btrfs_inode_in_log(new_dir, fs_info->generation) || - btrfs_inode_in_log(old_inode, fs_info->generation) || + if (btrfs_inode_in_log(BTRFS_I(old_dir), fs_info->generation) || + btrfs_inode_in_log(BTRFS_I(new_dir), fs_info->generation) || + btrfs_inode_in_log(BTRFS_I(old_inode), fs_info->generation) || (new_inode && - btrfs_inode_in_log(new_inode, fs_info->generation))) + btrfs_inode_in_log(BTRFS_I(new_inode), fs_info->generation))) btrfs_set_log_full_commit(fs_info, trans); if (root_log_pinned) { @@ -9736,7 +9672,7 @@ static int btrfs_whiteout_for_rename(struct btrfs_trans_handle *trans, inode = btrfs_new_inode(trans, root, dir, dentry->d_name.name, dentry->d_name.len, - btrfs_ino(dir), + btrfs_ino(BTRFS_I(dir)), objectid, S_IFCHR | WHITEOUT_MODE, &index); @@ -9784,10 +9720,10 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, u64 index = 0; u64 root_objectid; int ret; - u64 old_ino = btrfs_ino(old_inode); + u64 old_ino = btrfs_ino(BTRFS_I(old_inode)); bool log_pinned = false; - if (btrfs_ino(new_dir) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID) + if (btrfs_ino(BTRFS_I(new_dir)) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID) return -EPERM; /* we only allow rename subvolume link between subvolumes */ @@ -9795,7 +9731,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, return -EXDEV; if (old_ino == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID || - (new_inode && btrfs_ino(new_inode) == BTRFS_FIRST_FREE_OBJECTID)) + (new_inode && btrfs_ino(BTRFS_I(new_inode)) == BTRFS_FIRST_FREE_OBJECTID)) return -ENOTEMPTY; if (S_ISDIR(old_inode->i_mode) && new_inode && @@ -9870,7 +9806,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, new_dentry->d_name.name, new_dentry->d_name.len, old_ino, - btrfs_ino(new_dir), index); + btrfs_ino(BTRFS_I(new_dir)), index); if (ret) goto out_fail; } @@ -9883,7 +9819,8 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, old_inode->i_ctime = current_time(old_dir); if (old_dentry->d_parent != new_dentry->d_parent) - btrfs_record_unlink_dir(trans, old_dir, old_inode, 1); + btrfs_record_unlink_dir(trans, BTRFS_I(old_dir), + BTRFS_I(old_inode), 1); if (unlikely(old_ino == BTRFS_FIRST_FREE_OBJECTID)) { root_objectid = BTRFS_I(old_inode)->root->root_key.objectid; @@ -9891,8 +9828,8 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, old_dentry->d_name.name, old_dentry->d_name.len); } else { - ret = __btrfs_unlink_inode(trans, root, old_dir, - d_inode(old_dentry), + ret = __btrfs_unlink_inode(trans, root, BTRFS_I(old_dir), + BTRFS_I(d_inode(old_dentry)), old_dentry->d_name.name, old_dentry->d_name.len); if (!ret) @@ -9906,7 +9843,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, if (new_inode) { inode_inc_iversion(new_inode); new_inode->i_ctime = current_time(new_inode); - if (unlikely(btrfs_ino(new_inode) == + if (unlikely(btrfs_ino(BTRFS_I(new_inode)) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)) { root_objectid = BTRFS_I(new_inode)->location.objectid; ret = btrfs_unlink_subvol(trans, dest, new_dir, @@ -9915,8 +9852,8 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, new_dentry->d_name.len); BUG_ON(new_inode->i_nlink == 0); } else { - ret = btrfs_unlink_inode(trans, dest, new_dir, - d_inode(new_dentry), + ret = btrfs_unlink_inode(trans, dest, BTRFS_I(new_dir), + BTRFS_I(d_inode(new_dentry)), new_dentry->d_name.name, new_dentry->d_name.len); } @@ -9942,7 +9879,8 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, if (log_pinned) { struct dentry *parent = new_dentry->d_parent; - btrfs_log_new_name(trans, old_inode, old_dir, parent); + btrfs_log_new_name(trans, BTRFS_I(old_inode), BTRFS_I(old_dir), + parent); btrfs_end_log_trans(root); log_pinned = false; } @@ -9969,11 +9907,11 @@ out_fail: * allow the tasks to sync it. */ if (ret && log_pinned) { - if (btrfs_inode_in_log(old_dir, fs_info->generation) || - btrfs_inode_in_log(new_dir, fs_info->generation) || - btrfs_inode_in_log(old_inode, fs_info->generation) || + if (btrfs_inode_in_log(BTRFS_I(old_dir), fs_info->generation) || + btrfs_inode_in_log(BTRFS_I(new_dir), fs_info->generation) || + btrfs_inode_in_log(BTRFS_I(old_inode), fs_info->generation) || (new_inode && - btrfs_inode_in_log(new_inode, fs_info->generation))) + btrfs_inode_in_log(BTRFS_I(new_inode), fs_info->generation))) btrfs_set_log_full_commit(fs_info, trans); btrfs_end_log_trans(root); @@ -10237,8 +10175,8 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry, goto out_unlock; inode = btrfs_new_inode(trans, root, dir, dentry->d_name.name, - dentry->d_name.len, btrfs_ino(dir), objectid, - S_IFLNK|S_IRWXUGO, &index); + dentry->d_name.len, btrfs_ino(BTRFS_I(dir)), + objectid, S_IFLNK|S_IRWXUGO, &index); if (IS_ERR(inode)) { err = PTR_ERR(inode); goto out_unlock; @@ -10264,7 +10202,7 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry, err = -ENOMEM; goto out_unlock_inode; } - key.objectid = btrfs_ino(inode); + key.objectid = btrfs_ino(BTRFS_I(inode)); key.offset = 0; key.type = BTRFS_EXTENT_DATA_KEY; datasize = btrfs_file_extent_calc_inline_size(name_len); @@ -10517,7 +10455,7 @@ static int btrfs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) goto out; inode = btrfs_new_inode(trans, root, dir, NULL, 0, - btrfs_ino(dir), objectid, mode, &index); + btrfs_ino(BTRFS_I(dir)), objectid, mode, &index); if (IS_ERR(inode)) { ret = PTR_ERR(inode); inode = NULL; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 21e51b0ba188..d8539979b44f 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -395,7 +395,7 @@ static noinline int btrfs_ioctl_fitrim(struct file *file, void __user *arg) q = bdev_get_queue(device->bdev); if (blk_queue_discard(q)) { num_devices++; - minlen = min((u64)q->limits.discard_granularity, + minlen = min_t(u64, q->limits.discard_granularity, minlen); } } @@ -487,8 +487,7 @@ static noinline int create_subvol(struct inode *dir, trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) { ret = PTR_ERR(trans); - btrfs_subvolume_release_metadata(fs_info, &block_rsv, - qgroup_reserved); + btrfs_subvolume_release_metadata(fs_info, &block_rsv); goto fail_free; } trans->block_rsv = &block_rsv; @@ -601,7 +600,7 @@ static noinline int create_subvol(struct inode *dir, ret = btrfs_add_root_ref(trans, fs_info, objectid, root->root_key.objectid, - btrfs_ino(dir), index, name, namelen); + btrfs_ino(BTRFS_I(dir)), index, name, namelen); BUG_ON(ret); ret = btrfs_uuid_tree_add(trans, fs_info, root_item->uuid, @@ -613,7 +612,7 @@ fail: kfree(root_item); trans->block_rsv = NULL; trans->bytes_reserved = 0; - btrfs_subvolume_release_metadata(fs_info, &block_rsv, qgroup_reserved); + btrfs_subvolume_release_metadata(fs_info, &block_rsv); if (async_transid) { *async_transid = trans->transid; @@ -657,7 +656,7 @@ static void btrfs_wait_for_no_snapshoting_writes(struct btrfs_root *root) } static int create_snapshot(struct btrfs_root *root, struct inode *dir, - struct dentry *dentry, char *name, int namelen, + struct dentry *dentry, u64 *async_transid, bool readonly, struct btrfs_qgroup_inherit *inherit) { @@ -670,12 +669,12 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, if (!test_bit(BTRFS_ROOT_REF_COWS, &root->state)) return -EINVAL; - pending_snapshot = kzalloc(sizeof(*pending_snapshot), GFP_NOFS); + pending_snapshot = kzalloc(sizeof(*pending_snapshot), GFP_KERNEL); if (!pending_snapshot) return -ENOMEM; pending_snapshot->root_item = kzalloc(sizeof(struct btrfs_root_item), - GFP_NOFS); + GFP_KERNEL); pending_snapshot->path = btrfs_alloc_path(); if (!pending_snapshot->root_item || !pending_snapshot->path) { ret = -ENOMEM; @@ -753,9 +752,7 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, d_instantiate(dentry, inode); ret = 0; fail: - btrfs_subvolume_release_metadata(fs_info, - &pending_snapshot->block_rsv, - pending_snapshot->qgroup_reserved); + btrfs_subvolume_release_metadata(fs_info, &pending_snapshot->block_rsv); dec_and_free: if (atomic_dec_and_test(&root->will_be_snapshoted)) wake_up_atomic_t(&root->will_be_snapshoted); @@ -874,7 +871,7 @@ static noinline int btrfs_mksubvol(const struct path *parent, goto out_up_read; if (snap_src) { - error = create_snapshot(snap_src, dir, dentry, name, namelen, + error = create_snapshot(snap_src, dir, dentry, async_transid, readonly, inherit); } else { error = create_subvol(dir, dentry, name, namelen, @@ -941,7 +938,7 @@ static int find_new_extents(struct btrfs_root *root, struct btrfs_file_extent_item *extent; int type; int ret; - u64 ino = btrfs_ino(inode); + u64 ino = btrfs_ino(BTRFS_I(inode)); path = btrfs_alloc_path(); if (!path) @@ -1780,7 +1777,7 @@ static noinline int btrfs_ioctl_subvol_getflags(struct file *file, int ret = 0; u64 flags = 0; - if (btrfs_ino(inode) != BTRFS_FIRST_FREE_OBJECTID) + if (btrfs_ino(BTRFS_I(inode)) != BTRFS_FIRST_FREE_OBJECTID) return -EINVAL; down_read(&fs_info->subvol_sem); @@ -1812,7 +1809,7 @@ static noinline int btrfs_ioctl_subvol_setflags(struct file *file, if (ret) goto out; - if (btrfs_ino(inode) != BTRFS_FIRST_FREE_OBJECTID) { + if (btrfs_ino(BTRFS_I(inode)) != BTRFS_FIRST_FREE_OBJECTID) { ret = -EINVAL; goto out_drop_write; } @@ -2446,7 +2443,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file, if (err) goto out_dput; - if (btrfs_ino(inode) != BTRFS_FIRST_FREE_OBJECTID) { + if (btrfs_ino(BTRFS_I(inode)) != BTRFS_FIRST_FREE_OBJECTID) { err = -EINVAL; goto out_dput; } @@ -2497,7 +2494,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file, trans->block_rsv = &block_rsv; trans->bytes_reserved = block_rsv.size; - btrfs_record_snapshot_destroy(trans, dir); + btrfs_record_snapshot_destroy(trans, BTRFS_I(dir)); ret = btrfs_unlink_subvol(trans, root, dir, dest->root_key.objectid, @@ -2555,7 +2552,7 @@ out_end_trans: err = ret; inode->i_flags |= S_DEAD; out_release: - btrfs_subvolume_release_metadata(fs_info, &block_rsv, qgroup_reserved); + btrfs_subvolume_release_metadata(fs_info, &block_rsv); out_up_write: up_write(&fs_info->subvol_sem); if (err) { @@ -2613,9 +2610,6 @@ static int btrfs_ioctl_defrag(struct file *file, void __user *argp) goto out; } ret = btrfs_defrag_root(root); - if (ret) - goto out; - ret = btrfs_defrag_root(root->fs_info->extent_root); break; case S_IFREG: if (!(file->f_mode & FMODE_WRITE)) { @@ -3047,11 +3041,21 @@ static int btrfs_cmp_data_prepare(struct inode *src, u64 loff, cmp->src_pages = src_pgarr; cmp->dst_pages = dst_pgarr; - ret = gather_extent_pages(src, cmp->src_pages, cmp->num_pages, loff); + /* + * If deduping ranges in the same inode, locking rules make it mandatory + * to always lock pages in ascending order to avoid deadlocks with + * concurrent tasks (such as starting writeback/delalloc). + */ + if (src == dst && dst_loff < loff) { + swap(src_pgarr, dst_pgarr); + swap(loff, dst_loff); + } + + ret = gather_extent_pages(src, src_pgarr, cmp->num_pages, loff); if (ret) goto out; - ret = gather_extent_pages(dst, cmp->dst_pages, cmp->num_pages, dst_loff); + ret = gather_extent_pages(dst, dst_pgarr, cmp->num_pages, dst_loff); out: if (ret) @@ -3059,8 +3063,7 @@ out: return 0; } -static int btrfs_cmp_data(struct inode *src, u64 loff, struct inode *dst, - u64 dst_loff, u64 len, struct cmp_pages *cmp) +static int btrfs_cmp_data(u64 len, struct cmp_pages *cmp) { int ret = 0; int i; @@ -3128,26 +3131,27 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen, int ret; u64 len = olen; struct cmp_pages cmp; - int same_inode = 0; + bool same_inode = (src == dst); u64 same_lock_start = 0; u64 same_lock_len = 0; - if (src == dst) - same_inode = 1; - if (len == 0) return 0; - if (same_inode) { + if (same_inode) inode_lock(src); + else + btrfs_double_inode_lock(src, dst); - ret = extent_same_check_offsets(src, loff, &len, olen); - if (ret) - goto out_unlock; - ret = extent_same_check_offsets(src, dst_loff, &len, olen); - if (ret) - goto out_unlock; + ret = extent_same_check_offsets(src, loff, &len, olen); + if (ret) + goto out_unlock; + + ret = extent_same_check_offsets(dst, dst_loff, &len, olen); + if (ret) + goto out_unlock; + if (same_inode) { /* * Single inode case wants the same checks, except we * don't want our length pushed out past i_size as @@ -3175,16 +3179,6 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen, same_lock_start = min_t(u64, loff, dst_loff); same_lock_len = max_t(u64, loff, dst_loff) + len - same_lock_start; - } else { - btrfs_double_inode_lock(src, dst); - - ret = extent_same_check_offsets(src, loff, &len, olen); - if (ret) - goto out_unlock; - - ret = extent_same_check_offsets(dst, dst_loff, &len, olen); - if (ret) - goto out_unlock; } /* don't make the dst file partly checksummed */ @@ -3236,7 +3230,7 @@ again: } /* pass original length for comparison so we stay within i_size */ - ret = btrfs_cmp_data(src, loff, dst, dst_loff, olen, &cmp); + ret = btrfs_cmp_data(olen, &cmp); if (ret == 0) ret = btrfs_clone(src, dst, loff, olen, len, dst_loff, 1); @@ -3399,8 +3393,7 @@ static void clone_update_extent_map(struct inode *inode, * data into the destination inode's inline extent if the later is greater then * the former. */ -static int clone_copy_inline_extent(struct inode *src, - struct inode *dst, +static int clone_copy_inline_extent(struct inode *dst, struct btrfs_trans_handle *trans, struct btrfs_path *path, struct btrfs_key *new_key, @@ -3420,7 +3413,7 @@ static int clone_copy_inline_extent(struct inode *src, if (new_key->offset > 0) return -EOPNOTSUPP; - key.objectid = btrfs_ino(dst); + key.objectid = btrfs_ino(BTRFS_I(dst)); key.type = BTRFS_EXTENT_DATA_KEY; key.offset = 0; ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); @@ -3435,7 +3428,7 @@ static int clone_copy_inline_extent(struct inode *src, goto copy_inline_extent; } btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); - if (key.objectid == btrfs_ino(dst) && + if (key.objectid == btrfs_ino(BTRFS_I(dst)) && key.type == BTRFS_EXTENT_DATA_KEY) { ASSERT(key.offset > 0); return -EOPNOTSUPP; @@ -3469,7 +3462,7 @@ static int clone_copy_inline_extent(struct inode *src, } else if (ret == 0) { btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); - if (key.objectid == btrfs_ino(dst) && + if (key.objectid == btrfs_ino(BTRFS_I(dst)) && key.type == BTRFS_EXTENT_DATA_KEY) return -EOPNOTSUPP; } @@ -3563,7 +3556,7 @@ static int btrfs_clone(struct inode *src, struct inode *inode, path->reada = READA_FORWARD; /* clone data */ - key.objectid = btrfs_ino(src); + key.objectid = btrfs_ino(BTRFS_I(src)); key.type = BTRFS_EXTENT_DATA_KEY; key.offset = off; @@ -3606,7 +3599,7 @@ process_slot: btrfs_item_key_to_cpu(leaf, &key, slot); if (key.type > BTRFS_EXTENT_DATA_KEY || - key.objectid != btrfs_ino(src)) + key.objectid != btrfs_ino(BTRFS_I(src))) break; if (key.type == BTRFS_EXTENT_DATA_KEY) { @@ -3659,7 +3652,7 @@ process_slot: path->leave_spinning = 0; memcpy(&new_key, &key, sizeof(new_key)); - new_key.objectid = btrfs_ino(inode); + new_key.objectid = btrfs_ino(BTRFS_I(inode)); if (off <= key.offset) new_key.offset = key.offset + destoff - off; else @@ -3749,7 +3742,7 @@ process_slot: fs_info, disko, diskl, 0, root->root_key.objectid, - btrfs_ino(inode), + btrfs_ino(BTRFS_I(inode)), new_key.offset - datao); if (ret) { btrfs_abort_transaction(trans, @@ -3779,7 +3772,7 @@ process_slot: size -= skip + trim; datal -= skip + trim; - ret = clone_copy_inline_extent(src, inode, + ret = clone_copy_inline_extent(inode, trans, path, &new_key, drop_start, @@ -5129,7 +5122,7 @@ static long _btrfs_ioctl_set_received_subvol(struct file *file, down_write(&fs_info->subvol_sem); - if (btrfs_ino(inode) != BTRFS_FIRST_FREE_OBJECTID) { + if (btrfs_ino(BTRFS_I(inode)) != BTRFS_FIRST_FREE_OBJECTID) { ret = -EINVAL; goto out; } diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index 041c3326d109..bc2aba810629 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -432,7 +432,7 @@ out: } /* Needs to either be called under a log transaction or the log_mutex */ -void btrfs_get_logged_extents(struct inode *inode, +void btrfs_get_logged_extents(struct btrfs_inode *inode, struct list_head *logged_list, const loff_t start, const loff_t end) @@ -442,7 +442,7 @@ void btrfs_get_logged_extents(struct inode *inode, struct rb_node *n; struct rb_node *prev; - tree = &BTRFS_I(inode)->ordered_tree; + tree = &inode->ordered_tree; spin_lock_irq(&tree->lock); n = __tree_search(&tree->tree, end, &prev); if (!n) @@ -984,8 +984,18 @@ int btrfs_ordered_update_i_size(struct inode *inode, u64 offset, } disk_i_size = BTRFS_I(inode)->disk_i_size; - /* truncate file */ - if (disk_i_size > i_size) { + /* + * truncate file. + * If ordered is not NULL, then this is called from endio and + * disk_i_size will be updated by either truncate itself or any + * in-flight IOs which are inside the disk_i_size. + * + * Because btrfs_setsize() may set i_size with disk_i_size if truncate + * fails somehow, we need to make sure we have a precise disk_i_size by + * updating it as usual. + * + */ + if (!ordered && disk_i_size > i_size) { BTRFS_I(inode)->disk_i_size = orig_offset; ret = 0; goto out; @@ -1032,25 +1042,22 @@ int btrfs_ordered_update_i_size(struct inode *inode, u64 offset, /* We treat this entry as if it doesn't exist */ if (test_bit(BTRFS_ORDERED_UPDATED_ISIZE, &test->flags)) continue; - if (test->file_offset + test->len <= disk_i_size) + + if (entry_end(test) <= disk_i_size) break; if (test->file_offset >= i_size) break; - if (entry_end(test) > disk_i_size) { - /* - * we don't update disk_i_size now, so record this - * undealt i_size. Or we will not know the real - * i_size. - */ - if (test->outstanding_isize < offset) - test->outstanding_isize = offset; - if (ordered && - ordered->outstanding_isize > - test->outstanding_isize) - test->outstanding_isize = - ordered->outstanding_isize; - goto out; - } + + /* + * We don't update disk_i_size now, so record this undealt + * i_size. Or we will not know the real i_size. + */ + if (test->outstanding_isize < offset) + test->outstanding_isize = offset; + if (ordered && + ordered->outstanding_isize > test->outstanding_isize) + test->outstanding_isize = ordered->outstanding_isize; + goto out; } new_i_size = min_t(u64, offset, i_size); diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h index 5f2b0ca28705..a8cb8efe6fae 100644 --- a/fs/btrfs/ordered-data.h +++ b/fs/btrfs/ordered-data.h @@ -75,6 +75,8 @@ struct btrfs_ordered_sum { * in the logging code. */ #define BTRFS_ORDERED_PENDING 11 /* We are waiting for this ordered extent to * complete in the current transaction. */ +#define BTRFS_ORDERED_REGULAR 12 /* Regular IO for COW */ + struct btrfs_ordered_extent { /* logical offset in the file */ u64 file_offset; @@ -201,7 +203,7 @@ int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr, const u64 range_start, const u64 range_len); int btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr, const u64 range_start, const u64 range_len); -void btrfs_get_logged_extents(struct inode *inode, +void btrfs_get_logged_extents(struct btrfs_inode *inode, struct list_head *logged_list, const loff_t start, const loff_t end); diff --git a/fs/btrfs/props.c b/fs/btrfs/props.c index f2621e330954..d6cb155ef7a1 100644 --- a/fs/btrfs/props.c +++ b/fs/btrfs/props.c @@ -279,7 +279,7 @@ static void inode_prop_iterator(void *ctx, if (unlikely(ret)) btrfs_warn(root->fs_info, "error applying prop %s to ino %llu (root %llu): %d", - handler->xattr_name, btrfs_ino(inode), + handler->xattr_name, btrfs_ino(BTRFS_I(inode)), root->root_key.objectid, ret); else set_bit(BTRFS_INODE_HAS_PROPS, &BTRFS_I(inode)->runtime_flags); @@ -288,7 +288,7 @@ static void inode_prop_iterator(void *ctx, int btrfs_load_inode_props(struct inode *inode, struct btrfs_path *path) { struct btrfs_root *root = BTRFS_I(inode)->root; - u64 ino = btrfs_ino(inode); + u64 ino = btrfs_ino(BTRFS_I(inode)); int ret; ret = iterate_object_props(root, path, ino, inode_prop_iterator, inode); diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 662821f1252c..a5da750c1087 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -319,7 +319,7 @@ int btrfs_read_qgroup_config(struct btrfs_fs_info *fs_info) if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) return 0; - fs_info->qgroup_ulist = ulist_alloc(GFP_NOFS); + fs_info->qgroup_ulist = ulist_alloc(GFP_KERNEL); if (!fs_info->qgroup_ulist) { ret = -ENOMEM; goto out; @@ -876,7 +876,7 @@ int btrfs_quota_enable(struct btrfs_trans_handle *trans, goto out; } - fs_info->qgroup_ulist = ulist_alloc(GFP_NOFS); + fs_info->qgroup_ulist = ulist_alloc(GFP_KERNEL); if (!fs_info->qgroup_ulist) { ret = -ENOMEM; goto out; @@ -1019,7 +1019,7 @@ int btrfs_quota_disable(struct btrfs_trans_handle *trans, list_del("a_root->dirty_list); btrfs_tree_lock(quota_root->node); - clean_tree_block(trans, fs_info, quota_root->node); + clean_tree_block(fs_info, quota_root->node); btrfs_tree_unlock(quota_root->node); btrfs_free_tree_block(trans, quota_root, quota_root->node, 0, 1); @@ -1038,6 +1038,15 @@ static void qgroup_dirty(struct btrfs_fs_info *fs_info, list_add(&qgroup->dirty, &fs_info->dirty_qgroups); } +static void report_reserved_underflow(struct btrfs_fs_info *fs_info, + struct btrfs_qgroup *qgroup, + u64 num_bytes) +{ + btrfs_warn(fs_info, + "qgroup %llu reserved space underflow, have: %llu, to free: %llu", + qgroup->qgroupid, qgroup->reserved, num_bytes); + qgroup->reserved = 0; +} /* * The easy accounting, if we are adding/removing the only ref for an extent * then this qgroup and all of the parent qgroups get their reference and @@ -1065,8 +1074,12 @@ static int __qgroup_excl_accounting(struct btrfs_fs_info *fs_info, WARN_ON(sign < 0 && qgroup->excl < num_bytes); qgroup->excl += sign * num_bytes; qgroup->excl_cmpr += sign * num_bytes; - if (sign > 0) - qgroup->reserved -= num_bytes; + if (sign > 0) { + if (WARN_ON(qgroup->reserved < num_bytes)) + report_reserved_underflow(fs_info, qgroup, num_bytes); + else + qgroup->reserved -= num_bytes; + } qgroup_dirty(fs_info, qgroup); @@ -1086,8 +1099,13 @@ static int __qgroup_excl_accounting(struct btrfs_fs_info *fs_info, qgroup->rfer_cmpr += sign * num_bytes; WARN_ON(sign < 0 && qgroup->excl < num_bytes); qgroup->excl += sign * num_bytes; - if (sign > 0) - qgroup->reserved -= num_bytes; + if (sign > 0) { + if (WARN_ON(qgroup->reserved < num_bytes)) + report_reserved_underflow(fs_info, qgroup, + num_bytes); + else + qgroup->reserved -= num_bytes; + } qgroup->excl_cmpr += sign * num_bytes; qgroup_dirty(fs_info, qgroup); @@ -1156,7 +1174,7 @@ int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans, if (btrfs_qgroup_level(src) >= btrfs_qgroup_level(dst)) return -EINVAL; - tmp = ulist_alloc(GFP_NOFS); + tmp = ulist_alloc(GFP_KERNEL); if (!tmp) return -ENOMEM; @@ -1205,7 +1223,7 @@ out: return ret; } -int __del_qgroup_relation(struct btrfs_trans_handle *trans, +static int __del_qgroup_relation(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, u64 src, u64 dst) { struct btrfs_root *quota_root; @@ -1216,7 +1234,7 @@ int __del_qgroup_relation(struct btrfs_trans_handle *trans, int ret = 0; int err; - tmp = ulist_alloc(GFP_NOFS); + tmp = ulist_alloc(GFP_KERNEL); if (!tmp) return -ENOMEM; @@ -1446,8 +1464,9 @@ int btrfs_qgroup_prepare_account_extents(struct btrfs_trans_handle *trans, while (node) { record = rb_entry(node, struct btrfs_qgroup_extent_record, node); - ret = btrfs_find_all_roots(NULL, fs_info, record->bytenr, 0, - &record->old_roots); + if (WARN_ON(!record->old_roots)) + ret = btrfs_find_all_roots(NULL, fs_info, + record->bytenr, 0, &record->old_roots); if (ret < 0) break; if (qgroup_to_skip) @@ -1486,6 +1505,28 @@ int btrfs_qgroup_trace_extent_nolock(struct btrfs_fs_info *fs_info, return 0; } +int btrfs_qgroup_trace_extent_post(struct btrfs_fs_info *fs_info, + struct btrfs_qgroup_extent_record *qrecord) +{ + struct ulist *old_root; + u64 bytenr = qrecord->bytenr; + int ret; + + ret = btrfs_find_all_roots(NULL, fs_info, bytenr, 0, &old_root); + if (ret < 0) + return ret; + + /* + * Here we don't need to get the lock of + * trans->transaction->delayed_refs, since inserted qrecord won't + * be deleted, only qrecord->node may be modified (new qrecord insert) + * + * So modifying qrecord->old_roots is safe here + */ + qrecord->old_roots = old_root; + return 0; +} + int btrfs_qgroup_trace_extent(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, u64 bytenr, u64 num_bytes, gfp_t gfp_flag) @@ -1511,9 +1552,11 @@ int btrfs_qgroup_trace_extent(struct btrfs_trans_handle *trans, spin_lock(&delayed_refs->lock); ret = btrfs_qgroup_trace_extent_nolock(fs_info, delayed_refs, record); spin_unlock(&delayed_refs->lock); - if (ret > 0) + if (ret > 0) { kfree(record); - return 0; + return 0; + } + return btrfs_qgroup_trace_extent_post(fs_info, record); } int btrfs_qgroup_trace_leaf_items(struct btrfs_trans_handle *trans, @@ -1571,8 +1614,7 @@ int btrfs_qgroup_trace_leaf_items(struct btrfs_trans_handle *trans, * If we increment the root nodes slot counter past the number of * elements, 1 is returned to signal completion of the search. */ -static int adjust_slots_upwards(struct btrfs_root *root, - struct btrfs_path *path, int root_level) +static int adjust_slots_upwards(struct btrfs_path *path, int root_level) { int level = 0; int nr, slot; @@ -1713,7 +1755,7 @@ walk_down: goto out; /* Nonzero return here means we completed our search */ - ret = adjust_slots_upwards(root, path, root_level); + ret = adjust_slots_upwards(path, root_level); if (ret) break; @@ -1927,13 +1969,14 @@ btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans, u64 nr_old_roots = 0; int ret = 0; + if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) + return 0; + if (new_roots) nr_new_roots = new_roots->nnodes; if (old_roots) nr_old_roots = old_roots->nnodes; - if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) - goto out_free; BUG_ON(!fs_info->quota_root); trace_btrfs_qgroup_account_extent(fs_info, bytenr, num_bytes, @@ -2170,9 +2213,7 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, goto out; } - rcu_read_lock(); level_size = fs_info->nodesize; - rcu_read_unlock(); } /* @@ -2306,7 +2347,20 @@ out: return ret; } -static int qgroup_reserve(struct btrfs_root *root, u64 num_bytes) +static bool qgroup_check_limits(const struct btrfs_qgroup *qg, u64 num_bytes) +{ + if ((qg->lim_flags & BTRFS_QGROUP_LIMIT_MAX_RFER) && + qg->reserved + (s64)qg->rfer + num_bytes > qg->max_rfer) + return false; + + if ((qg->lim_flags & BTRFS_QGROUP_LIMIT_MAX_EXCL) && + qg->reserved + (s64)qg->excl + num_bytes > qg->max_excl) + return false; + + return true; +} + +static int qgroup_reserve(struct btrfs_root *root, u64 num_bytes, bool enforce) { struct btrfs_root *quota_root; struct btrfs_qgroup *qgroup; @@ -2347,16 +2401,7 @@ static int qgroup_reserve(struct btrfs_root *root, u64 num_bytes) qg = unode_aux_to_qgroup(unode); - if ((qg->lim_flags & BTRFS_QGROUP_LIMIT_MAX_RFER) && - qg->reserved + (s64)qg->rfer + num_bytes > - qg->max_rfer) { - ret = -EDQUOT; - goto out; - } - - if ((qg->lim_flags & BTRFS_QGROUP_LIMIT_MAX_EXCL) && - qg->reserved + (s64)qg->excl + num_bytes > - qg->max_excl) { + if (enforce && !qgroup_check_limits(qg, num_bytes)) { ret = -EDQUOT; goto out; } @@ -2424,7 +2469,10 @@ void btrfs_qgroup_free_refroot(struct btrfs_fs_info *fs_info, qg = unode_aux_to_qgroup(unode); - qg->reserved -= num_bytes; + if (WARN_ON(qg->reserved < num_bytes)) + report_reserved_underflow(fs_info, qg, num_bytes); + else + qg->reserved -= num_bytes; list_for_each_entry(glist, &qg->groups, next_group) { ret = ulist_add(fs_info->qgroup_ulist, @@ -2439,11 +2487,6 @@ out: spin_unlock(&fs_info->qgroup_lock); } -static inline void qgroup_free(struct btrfs_root *root, u64 num_bytes) -{ - return btrfs_qgroup_free_refroot(root->fs_info, root->objectid, - num_bytes); -} void assert_qgroups_uptodate(struct btrfs_trans_handle *trans) { if (list_empty(&trans->qgroup_ref_list) && !trans->delayed_ref_elem.seq) @@ -2803,7 +2846,7 @@ int btrfs_qgroup_reserve_data(struct inode *inode, u64 start, u64 len) return 0; changeset.bytes_changed = 0; - changeset.range_changed = ulist_alloc(GFP_NOFS); + ulist_init(&changeset.range_changed); ret = set_record_extent_bits(&BTRFS_I(inode)->io_tree, start, start + len -1, EXTENT_QGROUP_RESERVED, &changeset); trace_btrfs_qgroup_reserve_data(inode, start, len, @@ -2811,21 +2854,21 @@ int btrfs_qgroup_reserve_data(struct inode *inode, u64 start, u64 len) QGROUP_RESERVE); if (ret < 0) goto cleanup; - ret = qgroup_reserve(root, changeset.bytes_changed); + ret = qgroup_reserve(root, changeset.bytes_changed, true); if (ret < 0) goto cleanup; - ulist_free(changeset.range_changed); + ulist_release(&changeset.range_changed); return ret; cleanup: /* cleanup already reserved ranges */ ULIST_ITER_INIT(&uiter); - while ((unode = ulist_next(changeset.range_changed, &uiter))) + while ((unode = ulist_next(&changeset.range_changed, &uiter))) clear_extent_bit(&BTRFS_I(inode)->io_tree, unode->val, unode->aux, EXTENT_QGROUP_RESERVED, 0, 0, NULL, GFP_NOFS); - ulist_free(changeset.range_changed); + ulist_release(&changeset.range_changed); return ret; } @@ -2837,23 +2880,22 @@ static int __btrfs_qgroup_release_data(struct inode *inode, u64 start, u64 len, int ret; changeset.bytes_changed = 0; - changeset.range_changed = ulist_alloc(GFP_NOFS); - if (!changeset.range_changed) - return -ENOMEM; - + ulist_init(&changeset.range_changed); ret = clear_record_extent_bits(&BTRFS_I(inode)->io_tree, start, start + len -1, EXTENT_QGROUP_RESERVED, &changeset); if (ret < 0) goto out; if (free) { - qgroup_free(BTRFS_I(inode)->root, changeset.bytes_changed); + btrfs_qgroup_free_refroot(BTRFS_I(inode)->root->fs_info, + BTRFS_I(inode)->root->objectid, + changeset.bytes_changed); trace_op = QGROUP_FREE; } trace_btrfs_qgroup_release_data(inode, start, len, changeset.bytes_changed, trace_op); out: - ulist_free(changeset.range_changed); + ulist_release(&changeset.range_changed); return ret; } @@ -2892,7 +2934,8 @@ int btrfs_qgroup_release_data(struct inode *inode, u64 start, u64 len) return __btrfs_qgroup_release_data(inode, start, len, 0); } -int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes) +int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes, + bool enforce) { struct btrfs_fs_info *fs_info = root->fs_info; int ret; @@ -2902,7 +2945,7 @@ int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes) return 0; BUG_ON(num_bytes != round_down(num_bytes, fs_info->nodesize)); - ret = qgroup_reserve(root, num_bytes); + ret = qgroup_reserve(root, num_bytes, enforce); if (ret < 0) return ret; atomic_add(num_bytes, &root->qgroup_meta_rsv); @@ -2921,7 +2964,7 @@ void btrfs_qgroup_free_meta_all(struct btrfs_root *root) reserved = atomic_xchg(&root->qgroup_meta_rsv, 0); if (reserved == 0) return; - qgroup_free(root, reserved); + btrfs_qgroup_free_refroot(fs_info, root->objectid, reserved); } void btrfs_qgroup_free_meta(struct btrfs_root *root, int num_bytes) @@ -2935,7 +2978,7 @@ void btrfs_qgroup_free_meta(struct btrfs_root *root, int num_bytes) BUG_ON(num_bytes != round_down(num_bytes, fs_info->nodesize)); WARN_ON(atomic_read(&root->qgroup_meta_rsv) < num_bytes); atomic_sub(num_bytes, &root->qgroup_meta_rsv); - qgroup_free(root, num_bytes); + btrfs_qgroup_free_refroot(fs_info, root->objectid, num_bytes); } /* @@ -2950,22 +2993,22 @@ void btrfs_qgroup_check_reserved_leak(struct inode *inode) int ret; changeset.bytes_changed = 0; - changeset.range_changed = ulist_alloc(GFP_NOFS); - if (WARN_ON(!changeset.range_changed)) - return; - + ulist_init(&changeset.range_changed); ret = clear_record_extent_bits(&BTRFS_I(inode)->io_tree, 0, (u64)-1, EXTENT_QGROUP_RESERVED, &changeset); WARN_ON(ret < 0); if (WARN_ON(changeset.bytes_changed)) { ULIST_ITER_INIT(&iter); - while ((unode = ulist_next(changeset.range_changed, &iter))) { + while ((unode = ulist_next(&changeset.range_changed, &iter))) { btrfs_warn(BTRFS_I(inode)->root->fs_info, "leaking qgroup reserved space, ino: %lu, start: %llu, end: %llu", inode->i_ino, unode->val, unode->aux); } - qgroup_free(BTRFS_I(inode)->root, changeset.bytes_changed); + btrfs_qgroup_free_refroot(BTRFS_I(inode)->root->fs_info, + BTRFS_I(inode)->root->objectid, + changeset.bytes_changed); + } - ulist_free(changeset.range_changed); + ulist_release(&changeset.range_changed); } diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h index 416ae8e1d23c..26932a8a1993 100644 --- a/fs/btrfs/qgroup.h +++ b/fs/btrfs/qgroup.h @@ -94,9 +94,10 @@ int btrfs_qgroup_prepare_account_extents(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info); /* * Inform qgroup to trace one dirty extent, its info is recorded in @record. - * So qgroup can account it at commit trans time. + * So qgroup can account it at transaction committing time. * - * No lock version, caller must acquire delayed ref lock and allocate memory. + * No lock version, caller must acquire delayed ref lock and allocated memory, + * then call btrfs_qgroup_trace_extent_post() after exiting lock context. * * Return 0 for success insert * Return >0 for existing record, caller can free @record safely. @@ -108,11 +109,37 @@ int btrfs_qgroup_trace_extent_nolock( struct btrfs_qgroup_extent_record *record); /* + * Post handler after qgroup_trace_extent_nolock(). + * + * NOTE: Current qgroup does the expensive backref walk at transaction + * committing time with TRANS_STATE_COMMIT_DOING, this blocks incoming + * new transaction. + * This is designed to allow btrfs_find_all_roots() to get correct new_roots + * result. + * + * However for old_roots there is no need to do backref walk at that time, + * since we search commit roots to walk backref and result will always be + * correct. + * + * Due to the nature of no lock version, we can't do backref there. + * So we must call btrfs_qgroup_trace_extent_post() after exiting + * spinlock context. + * + * TODO: If we can fix and prove btrfs_find_all_roots() can get correct result + * using current root, then we can move all expensive backref walk out of + * transaction committing, but not now as qgroup accounting will be wrong again. + */ +int btrfs_qgroup_trace_extent_post(struct btrfs_fs_info *fs_info, + struct btrfs_qgroup_extent_record *qrecord); + +/* * Inform qgroup to trace one dirty extent, specified by @bytenr and * @num_bytes. * So qgroup can account it at commit trans time. * - * Better encapsulated version. + * Better encapsulated version, with memory allocation and backref walk for + * commit roots. + * So this can sleep. * * Return 0 if the operation is done. * Return <0 for error, like memory allocation failure or invalid parameter @@ -181,7 +208,8 @@ int btrfs_qgroup_reserve_data(struct inode *inode, u64 start, u64 len); int btrfs_qgroup_release_data(struct inode *inode, u64 start, u64 len); int btrfs_qgroup_free_data(struct inode *inode, u64 start, u64 len); -int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes); +int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes, + bool enforce); void btrfs_qgroup_free_meta_all(struct btrfs_root *root); void btrfs_qgroup_free_meta(struct btrfs_root *root, int num_bytes); void btrfs_qgroup_check_reserved_leak(struct inode *inode); diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index d2a9a1ee5361..1571bf26dc07 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -677,11 +677,9 @@ static noinline int lock_stripe_add(struct btrfs_raid_bio *rbio) struct btrfs_raid_bio *freeit = NULL; struct btrfs_raid_bio *cache_drop = NULL; int ret = 0; - int walk = 0; spin_lock_irqsave(&h->lock, flags); list_for_each_entry(cur, &h->hash_list, hash_list) { - walk++; if (cur->bbio->raid_map[0] == rbio->bbio->raid_map[0]) { spin_lock(&cur->bio_list_lock); diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 379711048fb0..ddbde0f08365 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -1548,9 +1548,9 @@ again: prev = node; entry = rb_entry(node, struct btrfs_inode, rb_node); - if (objectid < btrfs_ino(&entry->vfs_inode)) + if (objectid < btrfs_ino(entry)) node = node->rb_left; - else if (objectid > btrfs_ino(&entry->vfs_inode)) + else if (objectid > btrfs_ino(entry)) node = node->rb_right; else break; @@ -1558,7 +1558,7 @@ again: if (!node) { while (prev) { entry = rb_entry(prev, struct btrfs_inode, rb_node); - if (objectid <= btrfs_ino(&entry->vfs_inode)) { + if (objectid <= btrfs_ino(entry)) { node = prev; break; } @@ -1573,7 +1573,7 @@ again: return inode; } - objectid = btrfs_ino(&entry->vfs_inode) + 1; + objectid = btrfs_ino(entry) + 1; if (cond_resched_lock(&root->inode_lock)) goto again; @@ -1609,8 +1609,8 @@ static int get_new_location(struct inode *reloc_inode, u64 *new_bytenr, return -ENOMEM; bytenr -= BTRFS_I(reloc_inode)->index_cnt; - ret = btrfs_lookup_file_extent(NULL, root, path, btrfs_ino(reloc_inode), - bytenr, 0); + ret = btrfs_lookup_file_extent(NULL, root, path, + btrfs_ino(BTRFS_I(reloc_inode)), bytenr, 0); if (ret < 0) goto out; if (ret > 0) { @@ -1698,11 +1698,11 @@ int replace_file_extents(struct btrfs_trans_handle *trans, if (first) { inode = find_next_inode(root, key.objectid); first = 0; - } else if (inode && btrfs_ino(inode) < key.objectid) { + } else if (inode && btrfs_ino(BTRFS_I(inode)) < key.objectid) { btrfs_add_delayed_iput(inode); inode = find_next_inode(root, key.objectid); } - if (inode && btrfs_ino(inode) == key.objectid) { + if (inode && btrfs_ino(BTRFS_I(inode)) == key.objectid) { end = key.offset + btrfs_file_extent_num_bytes(leaf, fi); WARN_ON(!IS_ALIGNED(key.offset, @@ -2088,7 +2088,7 @@ static int invalidate_extent_cache(struct btrfs_root *root, inode = find_next_inode(root, objectid); if (!inode) break; - ino = btrfs_ino(inode); + ino = btrfs_ino(BTRFS_I(inode)); if (ino > max_key->objectid) { iput(inode); @@ -3543,7 +3543,7 @@ truncate: goto out; } - ret = btrfs_truncate_free_space_cache(root, trans, block_group, inode); + ret = btrfs_truncate_free_space_cache(trans, block_group, inode); btrfs_end_transaction(trans); btrfs_btree_balance_dirty(fs_info); @@ -4334,7 +4334,7 @@ int btrfs_relocate_block_group(struct btrfs_fs_info *fs_info, u64 group_start) rc->block_group = btrfs_lookup_block_group(fs_info, group_start); BUG_ON(!rc->block_group); - ret = btrfs_inc_block_group_ro(extent_root, rc->block_group); + ret = btrfs_inc_block_group_ro(fs_info, rc->block_group); if (ret) { err = ret; goto out; @@ -4347,8 +4347,7 @@ int btrfs_relocate_block_group(struct btrfs_fs_info *fs_info, u64 group_start) goto out; } - inode = lookup_free_space_inode(fs_info->tree_root, rc->block_group, - path); + inode = lookup_free_space_inode(fs_info, rc->block_group, path); btrfs_free_path(path); if (!IS_ERR(inode)) diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c index 4c6735491ee0..a08224eab8b4 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -74,7 +74,7 @@ static void btrfs_read_root_item(struct extent_buffer *eb, int slot, * * If we find something return 0, otherwise > 0, < 0 on error. */ -int btrfs_find_root(struct btrfs_root *root, struct btrfs_key *search_key, +int btrfs_find_root(struct btrfs_root *root, const struct btrfs_key *search_key, struct btrfs_path *path, struct btrfs_root_item *root_item, struct btrfs_key *root_key) { @@ -207,7 +207,7 @@ out: } int btrfs_insert_root(struct btrfs_trans_handle *trans, struct btrfs_root *root, - struct btrfs_key *key, struct btrfs_root_item *item) + const struct btrfs_key *key, struct btrfs_root_item *item) { /* * Make sure generation v1 and v2 match. See update_root for details. @@ -337,7 +337,7 @@ int btrfs_find_orphan_roots(struct btrfs_fs_info *fs_info) /* drop the root item for 'key' from 'root' */ int btrfs_del_root(struct btrfs_trans_handle *trans, struct btrfs_root *root, - struct btrfs_key *key) + const struct btrfs_key *key) { struct btrfs_path *path; int ret; diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 9a94670536a6..ff9a11c39f5e 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -282,9 +282,7 @@ static void scrub_remap_extent(struct btrfs_fs_info *fs_info, u64 *extent_physical, struct btrfs_device **extent_dev, int *extent_mirror_num); -static int scrub_setup_wr_ctx(struct scrub_ctx *sctx, - struct scrub_wr_ctx *wr_ctx, - struct btrfs_fs_info *fs_info, +static int scrub_setup_wr_ctx(struct scrub_wr_ctx *wr_ctx, struct btrfs_device *dev, int is_dev_replace); static void scrub_free_wr_ctx(struct scrub_wr_ctx *wr_ctx); @@ -501,7 +499,7 @@ struct scrub_ctx *scrub_setup_ctx(struct btrfs_device *dev, int is_dev_replace) spin_lock_init(&sctx->stat_lock); init_waitqueue_head(&sctx->list_wait); - ret = scrub_setup_wr_ctx(sctx, &sctx->wr_ctx, fs_info, + ret = scrub_setup_wr_ctx(&sctx->wr_ctx, fs_info->dev_replace.tgtdev, is_dev_replace); if (ret) { scrub_free_ctx(sctx); @@ -3584,7 +3582,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, * -> btrfs_scrub_pause() */ scrub_pause_on(fs_info); - ret = btrfs_inc_block_group_ro(root, cache); + ret = btrfs_inc_block_group_ro(fs_info, cache); if (!ret && is_dev_replace) { /* * If we are doing a device replace wait for any tasks @@ -4084,9 +4082,7 @@ static void scrub_remap_extent(struct btrfs_fs_info *fs_info, btrfs_put_bbio(bbio); } -static int scrub_setup_wr_ctx(struct scrub_ctx *sctx, - struct scrub_wr_ctx *wr_ctx, - struct btrfs_fs_info *fs_info, +static int scrub_setup_wr_ctx(struct scrub_wr_ctx *wr_ctx, struct btrfs_device *dev, int is_dev_replace) { diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index b5ae7d3d1896..da687dc79cce 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -265,7 +265,7 @@ void __btrfs_abort_transaction(struct btrfs_trans_handle *trans, function, line, errstr); return; } - ACCESS_ONCE(trans->transaction->aborted) = errno; + WRITE_ONCE(trans->transaction->aborted, errno); /* Wake up anybody who may be waiting on this transaction */ wake_up(&fs_info->transaction_wait); wake_up(&fs_info->transaction_blocked_wait); @@ -1114,7 +1114,7 @@ static int get_default_subvol_objectid(struct btrfs_fs_info *fs_info, u64 *objec static int btrfs_fill_super(struct super_block *sb, struct btrfs_fs_devices *fs_devices, - void *data, int silent) + void *data) { struct inode *inode; struct btrfs_fs_info *fs_info = btrfs_sb(sb); @@ -1611,8 +1611,7 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags, } else { snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev); btrfs_sb(s)->bdev_holder = fs_type; - error = btrfs_fill_super(s, fs_devices, data, - flags & MS_SILENT ? 1 : 0); + error = btrfs_fill_super(s, fs_devices, data); } if (error) { deactivate_locked_super(s); diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 0e0508f488b2..6b3e0fc2fe7a 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -474,7 +474,8 @@ static inline bool need_reserve_reloc_root(struct btrfs_root *root) static struct btrfs_trans_handle * start_transaction(struct btrfs_root *root, unsigned int num_items, - unsigned int type, enum btrfs_reserve_flush_enum flush) + unsigned int type, enum btrfs_reserve_flush_enum flush, + bool enforce_qgroups) { struct btrfs_fs_info *fs_info = root->fs_info; @@ -505,9 +506,10 @@ start_transaction(struct btrfs_root *root, unsigned int num_items, * Do the reservation before we join the transaction so we can do all * the appropriate flushing if need be. */ - if (num_items > 0 && root != fs_info->chunk_root) { + if (num_items && root != fs_info->chunk_root) { qgroup_reserved = num_items * fs_info->nodesize; - ret = btrfs_qgroup_reserve_meta(root, qgroup_reserved); + ret = btrfs_qgroup_reserve_meta(root, qgroup_reserved, + enforce_qgroups); if (ret) return ERR_PTR(ret); @@ -613,8 +615,9 @@ struct btrfs_trans_handle *btrfs_start_transaction(struct btrfs_root *root, unsigned int num_items) { return start_transaction(root, num_items, TRANS_START, - BTRFS_RESERVE_FLUSH_ALL); + BTRFS_RESERVE_FLUSH_ALL, true); } + struct btrfs_trans_handle *btrfs_start_transaction_fallback_global_rsv( struct btrfs_root *root, unsigned int num_items, @@ -625,7 +628,14 @@ struct btrfs_trans_handle *btrfs_start_transaction_fallback_global_rsv( u64 num_bytes; int ret; - trans = btrfs_start_transaction(root, num_items); + /* + * We have two callers: unlink and block group removal. The + * former should succeed even if we will temporarily exceed + * quota and the latter operates on the extent root so + * qgroup enforcement is ignored anyway. + */ + trans = start_transaction(root, num_items, TRANS_START, + BTRFS_RESERVE_FLUSH_ALL, false); if (!IS_ERR(trans) || PTR_ERR(trans) != -ENOSPC) return trans; @@ -654,25 +664,25 @@ struct btrfs_trans_handle *btrfs_start_transaction_lflush( unsigned int num_items) { return start_transaction(root, num_items, TRANS_START, - BTRFS_RESERVE_FLUSH_LIMIT); + BTRFS_RESERVE_FLUSH_LIMIT, true); } struct btrfs_trans_handle *btrfs_join_transaction(struct btrfs_root *root) { - return start_transaction(root, 0, TRANS_JOIN, - BTRFS_RESERVE_NO_FLUSH); + return start_transaction(root, 0, TRANS_JOIN, BTRFS_RESERVE_NO_FLUSH, + true); } struct btrfs_trans_handle *btrfs_join_transaction_nolock(struct btrfs_root *root) { return start_transaction(root, 0, TRANS_JOIN_NOLOCK, - BTRFS_RESERVE_NO_FLUSH); + BTRFS_RESERVE_NO_FLUSH, true); } struct btrfs_trans_handle *btrfs_start_ioctl_transaction(struct btrfs_root *root) { return start_transaction(root, 0, TRANS_USERSPACE, - BTRFS_RESERVE_NO_FLUSH); + BTRFS_RESERVE_NO_FLUSH, true); } /* @@ -691,7 +701,7 @@ struct btrfs_trans_handle *btrfs_start_ioctl_transaction(struct btrfs_root *root struct btrfs_trans_handle *btrfs_attach_transaction(struct btrfs_root *root) { return start_transaction(root, 0, TRANS_ATTACH, - BTRFS_RESERVE_NO_FLUSH); + BTRFS_RESERVE_NO_FLUSH, true); } /* @@ -707,7 +717,7 @@ btrfs_attach_transaction_barrier(struct btrfs_root *root) struct btrfs_trans_handle *trans; trans = start_transaction(root, 0, TRANS_ATTACH, - BTRFS_RESERVE_NO_FLUSH); + BTRFS_RESERVE_NO_FLUSH, true); if (IS_ERR(trans) && PTR_ERR(trans) == -ENOENT) btrfs_wait_for_commit(root->fs_info, 0); @@ -866,14 +876,14 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans, if (lock && !atomic_read(&info->open_ioctl_trans) && should_end_transaction(trans) && - ACCESS_ONCE(cur_trans->state) == TRANS_STATE_RUNNING) { + READ_ONCE(cur_trans->state) == TRANS_STATE_RUNNING) { spin_lock(&info->trans_lock); if (cur_trans->state == TRANS_STATE_RUNNING) cur_trans->state = TRANS_STATE_BLOCKED; spin_unlock(&info->trans_lock); } - if (lock && ACCESS_ONCE(cur_trans->state) == TRANS_STATE_BLOCKED) { + if (lock && READ_ONCE(cur_trans->state) == TRANS_STATE_BLOCKED) { if (throttle) return btrfs_commit_transaction(trans); else @@ -1354,12 +1364,8 @@ static int qgroup_account_snapshot(struct btrfs_trans_handle *trans, * enabled. If this check races with the ioctl, rescan will * kick in anyway. */ - mutex_lock(&fs_info->qgroup_ioctl_lock); - if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) { - mutex_unlock(&fs_info->qgroup_ioctl_lock); + if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) return 0; - } - mutex_unlock(&fs_info->qgroup_ioctl_lock); /* * We are going to commit transaction, see btrfs_commit_transaction() @@ -1504,7 +1510,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, /* check if there is a file/dir which has the same name. */ dir_item = btrfs_lookup_dir_item(NULL, parent_root, path, - btrfs_ino(parent_inode), + btrfs_ino(BTRFS_I(parent_inode)), dentry->d_name.name, dentry->d_name.len, 0); if (dir_item != NULL && !IS_ERR(dir_item)) { @@ -1598,7 +1604,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, */ ret = btrfs_add_root_ref(trans, fs_info, objectid, parent_root->root_key.objectid, - btrfs_ino(parent_inode), index, + btrfs_ino(BTRFS_I(parent_inode)), index, dentry->d_name.name, dentry->d_name.len); if (ret) { btrfs_abort_transaction(trans, ret); @@ -1940,7 +1946,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) int ret; /* Stop the commit early if ->aborted is set */ - if (unlikely(ACCESS_ONCE(cur_trans->aborted))) { + if (unlikely(READ_ONCE(cur_trans->aborted))) { ret = cur_trans->aborted; btrfs_end_transaction(trans); return ret; @@ -2080,7 +2086,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) atomic_read(&cur_trans->num_writers) == 1); /* ->aborted might be set after the previous check, so check it */ - if (unlikely(ACCESS_ONCE(cur_trans->aborted))) { + if (unlikely(READ_ONCE(cur_trans->aborted))) { ret = cur_trans->aborted; goto scrub_continue; } @@ -2194,14 +2200,14 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) * The tasks which save the space cache and inode cache may also * update ->aborted, check it. */ - if (unlikely(ACCESS_ONCE(cur_trans->aborted))) { + if (unlikely(READ_ONCE(cur_trans->aborted))) { ret = cur_trans->aborted; mutex_unlock(&fs_info->tree_log_mutex); mutex_unlock(&fs_info->reloc_mutex); goto scrub_continue; } - btrfs_prepare_extent_commit(trans, fs_info); + btrfs_prepare_extent_commit(fs_info); cur_trans = fs_info->running_transaction; @@ -2251,7 +2257,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) goto scrub_continue; } - ret = write_ctree_super(trans, fs_info, 0); + ret = write_all_supers(fs_info, 0); if (ret) { mutex_unlock(&fs_info->tree_log_mutex); goto scrub_continue; diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index eeffff84f280..3806853cde08 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -97,7 +97,7 @@ #define LOG_WALK_REPLAY_ALL 3 static int btrfs_log_inode(struct btrfs_trans_handle *trans, - struct btrfs_root *root, struct inode *inode, + struct btrfs_root *root, struct btrfs_inode *inode, int inode_only, const loff_t start, const loff_t end, @@ -631,8 +631,8 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans, * file. This must be done before the btrfs_drop_extents run * so we don't try to drop this extent. */ - ret = btrfs_lookup_file_extent(trans, root, path, btrfs_ino(inode), - start, 0); + ret = btrfs_lookup_file_extent(trans, root, path, + btrfs_ino(BTRFS_I(inode)), start, 0); if (ret == 0 && (found_type == BTRFS_FILE_EXTENT_REG || @@ -843,7 +843,7 @@ out: static noinline int drop_one_dir_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, - struct inode *dir, + struct btrfs_inode *dir, struct btrfs_dir_item *di) { struct btrfs_fs_info *fs_info = root->fs_info; @@ -875,7 +875,8 @@ static noinline int drop_one_dir_item(struct btrfs_trans_handle *trans, if (ret) goto out; - ret = btrfs_unlink_inode(trans, root, dir, inode, name, name_len); + ret = btrfs_unlink_inode(trans, root, dir, BTRFS_I(inode), name, + name_len); if (ret) goto out; else @@ -991,8 +992,8 @@ static inline int __add_inode_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, struct btrfs_root *log_root, - struct inode *dir, struct inode *inode, - struct extent_buffer *eb, + struct btrfs_inode *dir, + struct btrfs_inode *inode, u64 inode_objectid, u64 parent_objectid, u64 ref_index, char *name, int namelen, int *search_done) @@ -1047,12 +1048,11 @@ again: parent_objectid, victim_name, victim_name_len)) { - inc_nlink(inode); + inc_nlink(&inode->vfs_inode); btrfs_release_path(path); - ret = btrfs_unlink_inode(trans, root, dir, - inode, victim_name, - victim_name_len); + ret = btrfs_unlink_inode(trans, root, dir, inode, + victim_name, victim_name_len); kfree(victim_name); if (ret) return ret; @@ -1115,16 +1115,16 @@ again: victim_name_len)) { ret = -ENOENT; victim_parent = read_one_inode(root, - parent_objectid); + parent_objectid); if (victim_parent) { - inc_nlink(inode); + inc_nlink(&inode->vfs_inode); btrfs_release_path(path); ret = btrfs_unlink_inode(trans, root, - victim_parent, - inode, - victim_name, - victim_name_len); + BTRFS_I(victim_parent), + inode, + victim_name, + victim_name_len); if (!ret) ret = btrfs_run_delayed_items( trans, @@ -1295,8 +1295,9 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans, goto out; /* if we already have a perfect match, we're done */ - if (!inode_in_dir(root, path, btrfs_ino(dir), btrfs_ino(inode), - ref_index, name, namelen)) { + if (!inode_in_dir(root, path, btrfs_ino(BTRFS_I(dir)), + btrfs_ino(BTRFS_I(inode)), ref_index, + name, namelen)) { /* * look for a conflicting back reference in the * metadata. if we find one we have to unlink that name @@ -1307,7 +1308,8 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans, if (!search_done) { ret = __add_inode_ref(trans, root, path, log, - dir, inode, eb, + BTRFS_I(dir), + BTRFS_I(inode), inode_objectid, parent_objectid, ref_index, name, namelen, @@ -1360,7 +1362,7 @@ static int insert_orphan_item(struct btrfs_trans_handle *trans, } static int count_inode_extrefs(struct btrfs_root *root, - struct inode *inode, struct btrfs_path *path) + struct btrfs_inode *inode, struct btrfs_path *path) { int ret = 0; int name_len; @@ -1404,7 +1406,7 @@ static int count_inode_extrefs(struct btrfs_root *root, } static int count_inode_refs(struct btrfs_root *root, - struct inode *inode, struct btrfs_path *path) + struct btrfs_inode *inode, struct btrfs_path *path) { int ret; struct btrfs_key key; @@ -1477,19 +1479,19 @@ static noinline int fixup_inode_link_count(struct btrfs_trans_handle *trans, struct btrfs_path *path; int ret; u64 nlink = 0; - u64 ino = btrfs_ino(inode); + u64 ino = btrfs_ino(BTRFS_I(inode)); path = btrfs_alloc_path(); if (!path) return -ENOMEM; - ret = count_inode_refs(root, inode, path); + ret = count_inode_refs(root, BTRFS_I(inode), path); if (ret < 0) goto out; nlink = ret; - ret = count_inode_extrefs(root, inode, path); + ret = count_inode_extrefs(root, BTRFS_I(inode), path); if (ret < 0) goto out; @@ -1769,7 +1771,7 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans, if (!exists) goto out; - ret = drop_one_dir_item(trans, root, path, dir, dst_di); + ret = drop_one_dir_item(trans, root, path, BTRFS_I(dir), dst_di); if (ret) goto out; @@ -2052,8 +2054,8 @@ again: } inc_nlink(inode); - ret = btrfs_unlink_inode(trans, root, dir, inode, - name, name_len); + ret = btrfs_unlink_inode(trans, root, BTRFS_I(dir), + BTRFS_I(inode), name, name_len); if (!ret) ret = btrfs_run_delayed_items(trans, fs_info); kfree(name); @@ -2469,7 +2471,7 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans, if (trans) { btrfs_tree_lock(next); btrfs_set_lock_blocking(next); - clean_tree_block(trans, fs_info, next); + clean_tree_block(fs_info, next); btrfs_wait_tree_block_writeback(next); btrfs_tree_unlock(next); } @@ -2549,7 +2551,7 @@ static noinline int walk_up_log_tree(struct btrfs_trans_handle *trans, if (trans) { btrfs_tree_lock(next); btrfs_set_lock_blocking(next); - clean_tree_block(trans, fs_info, next); + clean_tree_block(fs_info, next); btrfs_wait_tree_block_writeback(next); btrfs_tree_unlock(next); } @@ -2627,7 +2629,7 @@ static int walk_log_tree(struct btrfs_trans_handle *trans, if (trans) { btrfs_tree_lock(next); btrfs_set_lock_blocking(next); - clean_tree_block(trans, fs_info, next); + clean_tree_block(fs_info, next); btrfs_wait_tree_block_writeback(next); btrfs_tree_unlock(next); } @@ -2958,7 +2960,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, * the running transaction open, so a full commit can't hop * in and cause problems either. */ - ret = write_ctree_super(trans, fs_info, 1); + ret = write_all_supers(fs_info, 1); if (ret) { btrfs_set_log_full_commit(fs_info, trans); btrfs_abort_transaction(trans, ret); @@ -3084,7 +3086,7 @@ int btrfs_free_log_root_tree(struct btrfs_trans_handle *trans, int btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans, struct btrfs_root *root, const char *name, int name_len, - struct inode *dir, u64 index) + struct btrfs_inode *dir, u64 index) { struct btrfs_root *log; struct btrfs_dir_item *di; @@ -3094,14 +3096,14 @@ int btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans, int bytes_del = 0; u64 dir_ino = btrfs_ino(dir); - if (BTRFS_I(dir)->logged_trans < trans->transid) + if (dir->logged_trans < trans->transid) return 0; ret = join_running_log_trans(root); if (ret) return 0; - mutex_lock(&BTRFS_I(dir)->log_mutex); + mutex_lock(&dir->log_mutex); log = root->log_root; path = btrfs_alloc_path(); @@ -3176,7 +3178,7 @@ int btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans, fail: btrfs_free_path(path); out_unlock: - mutex_unlock(&BTRFS_I(dir)->log_mutex); + mutex_unlock(&dir->log_mutex); if (ret == -ENOSPC) { btrfs_set_log_full_commit(root->fs_info, trans); ret = 0; @@ -3192,25 +3194,25 @@ out_unlock: int btrfs_del_inode_ref_in_log(struct btrfs_trans_handle *trans, struct btrfs_root *root, const char *name, int name_len, - struct inode *inode, u64 dirid) + struct btrfs_inode *inode, u64 dirid) { struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_root *log; u64 index; int ret; - if (BTRFS_I(inode)->logged_trans < trans->transid) + if (inode->logged_trans < trans->transid) return 0; ret = join_running_log_trans(root); if (ret) return 0; log = root->log_root; - mutex_lock(&BTRFS_I(inode)->log_mutex); + mutex_lock(&inode->log_mutex); ret = btrfs_del_inode_ref(trans, log, name, name_len, btrfs_ino(inode), dirid, &index); - mutex_unlock(&BTRFS_I(inode)->log_mutex); + mutex_unlock(&inode->log_mutex); if (ret == -ENOSPC) { btrfs_set_log_full_commit(fs_info, trans); ret = 0; @@ -3260,7 +3262,7 @@ static noinline int insert_dir_log_key(struct btrfs_trans_handle *trans, * to replay anything deleted before the fsync */ static noinline int log_dir_items(struct btrfs_trans_handle *trans, - struct btrfs_root *root, struct inode *inode, + struct btrfs_root *root, struct btrfs_inode *inode, struct btrfs_path *path, struct btrfs_path *dst_path, int key_type, struct btrfs_log_ctx *ctx, @@ -3450,7 +3452,7 @@ done: * key logged by this transaction. */ static noinline int log_directory_changes(struct btrfs_trans_handle *trans, - struct btrfs_root *root, struct inode *inode, + struct btrfs_root *root, struct btrfs_inode *inode, struct btrfs_path *path, struct btrfs_path *dst_path, struct btrfs_log_ctx *ctx) @@ -3464,9 +3466,8 @@ again: min_key = 0; max_key = 0; while (1) { - ret = log_dir_items(trans, root, inode, path, - dst_path, key_type, ctx, min_key, - &max_key); + ret = log_dir_items(trans, root, inode, path, dst_path, key_type, + ctx, min_key, &max_key); if (ret) return ret; if (max_key == (u64)-1) @@ -3595,34 +3596,34 @@ static void fill_inode_item(struct btrfs_trans_handle *trans, static int log_inode_item(struct btrfs_trans_handle *trans, struct btrfs_root *log, struct btrfs_path *path, - struct inode *inode) + struct btrfs_inode *inode) { struct btrfs_inode_item *inode_item; int ret; ret = btrfs_insert_empty_item(trans, log, path, - &BTRFS_I(inode)->location, - sizeof(*inode_item)); + &inode->location, sizeof(*inode_item)); if (ret && ret != -EEXIST) return ret; inode_item = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_inode_item); - fill_inode_item(trans, path->nodes[0], inode_item, inode, 0, 0); + fill_inode_item(trans, path->nodes[0], inode_item, &inode->vfs_inode, + 0, 0); btrfs_release_path(path); return 0; } static noinline int copy_items(struct btrfs_trans_handle *trans, - struct inode *inode, + struct btrfs_inode *inode, struct btrfs_path *dst_path, struct btrfs_path *src_path, u64 *last_extent, int start_slot, int nr, int inode_only, u64 logged_isize) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb); unsigned long src_offset; unsigned long dst_offset; - struct btrfs_root *log = BTRFS_I(inode)->root->log_root; + struct btrfs_root *log = inode->root->log_root; struct btrfs_file_extent_item *extent; struct btrfs_inode_item *inode_item; struct extent_buffer *src = src_path->nodes[0]; @@ -3633,7 +3634,7 @@ static noinline int copy_items(struct btrfs_trans_handle *trans, char *ins_data; int i; struct list_head ordered_sums; - int skip_csum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM; + int skip_csum = inode->flags & BTRFS_INODE_NODATASUM; bool has_extents = false; bool need_find_last_extent = true; bool done = false; @@ -3675,7 +3676,8 @@ static noinline int copy_items(struct btrfs_trans_handle *trans, dst_path->slots[0], struct btrfs_inode_item); fill_inode_item(trans, dst_path->nodes[0], inode_item, - inode, inode_only == LOG_INODE_EXISTS, + &inode->vfs_inode, + inode_only == LOG_INODE_EXISTS, logged_isize); } else { copy_extent_buffer(dst_path->nodes[0], src, dst_offset, @@ -3783,7 +3785,7 @@ static noinline int copy_items(struct btrfs_trans_handle *trans, if (need_find_last_extent) { u64 len; - ret = btrfs_prev_leaf(BTRFS_I(inode)->root, src_path); + ret = btrfs_prev_leaf(inode->root, src_path); if (ret < 0) return ret; if (ret) @@ -3825,8 +3827,8 @@ fill_holes: if (need_find_last_extent) { /* btrfs_prev_leaf could return 1 without releasing the path */ btrfs_release_path(src_path); - ret = btrfs_search_slot(NULL, BTRFS_I(inode)->root, &first_key, - src_path, 0, 0); + ret = btrfs_search_slot(NULL, inode->root, &first_key, + src_path, 0, 0); if (ret < 0) return ret; ASSERT(ret == 0); @@ -3846,7 +3848,7 @@ fill_holes: u64 extent_end; if (i >= btrfs_header_nritems(src_path->nodes[0])) { - ret = btrfs_next_leaf(BTRFS_I(inode)->root, src_path); + ret = btrfs_next_leaf(inode->root, src_path); if (ret < 0) return ret; ASSERT(ret == 0); @@ -3881,8 +3883,7 @@ fill_holes: offset = *last_extent; len = key.offset - *last_extent; ret = btrfs_insert_file_extent(trans, log, btrfs_ino(inode), - offset, 0, 0, len, 0, len, 0, - 0, 0); + offset, 0, 0, len, 0, len, 0, 0, 0); if (ret) break; *last_extent = extent_end; @@ -4055,7 +4056,7 @@ static int wait_ordered_extents(struct btrfs_trans_handle *trans, } static int log_one_extent(struct btrfs_trans_handle *trans, - struct inode *inode, struct btrfs_root *root, + struct btrfs_inode *inode, struct btrfs_root *root, const struct extent_map *em, struct btrfs_path *path, const struct list_head *logged_list, @@ -4072,8 +4073,8 @@ static int log_one_extent(struct btrfs_trans_handle *trans, int extent_inserted = 0; bool ordered_io_err = false; - ret = wait_ordered_extents(trans, inode, root, em, logged_list, - &ordered_io_err); + ret = wait_ordered_extents(trans, &inode->vfs_inode, root, em, + logged_list, &ordered_io_err); if (ret) return ret; @@ -4084,7 +4085,7 @@ static int log_one_extent(struct btrfs_trans_handle *trans, btrfs_init_map_token(&token); - ret = __btrfs_drop_extents(trans, log, inode, path, em->start, + ret = __btrfs_drop_extents(trans, log, &inode->vfs_inode, path, em->start, em->start + em->len, NULL, 0, 1, sizeof(*fi), &extent_inserted); if (ret) @@ -4150,7 +4151,7 @@ static int log_one_extent(struct btrfs_trans_handle *trans, static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans, struct btrfs_root *root, - struct inode *inode, + struct btrfs_inode *inode, struct btrfs_path *path, struct list_head *logged_list, struct btrfs_log_ctx *ctx, @@ -4159,14 +4160,14 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans, { struct extent_map *em, *n; struct list_head extents; - struct extent_map_tree *tree = &BTRFS_I(inode)->extent_tree; + struct extent_map_tree *tree = &inode->extent_tree; u64 test_gen; int ret = 0; int num = 0; INIT_LIST_HEAD(&extents); - down_write(&BTRFS_I(inode)->dio_sem); + down_write(&inode->dio_sem); write_lock(&tree->lock); test_gen = root->fs_info->last_trans_committed; @@ -4206,7 +4207,7 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans, * without writing to the log tree and the fsync must report the * file data write error and not commit the current transaction. */ - ret = filemap_check_errors(inode->i_mapping); + ret = filemap_check_errors(inode->vfs_inode.i_mapping); if (ret) ctx->io_err = ret; process: @@ -4235,13 +4236,13 @@ process: } WARN_ON(!list_empty(&extents)); write_unlock(&tree->lock); - up_write(&BTRFS_I(inode)->dio_sem); + up_write(&inode->dio_sem); btrfs_release_path(path); return ret; } -static int logged_inode_size(struct btrfs_root *log, struct inode *inode, +static int logged_inode_size(struct btrfs_root *log, struct btrfs_inode *inode, struct btrfs_path *path, u64 *size_ret) { struct btrfs_key key; @@ -4279,7 +4280,7 @@ static int logged_inode_size(struct btrfs_root *log, struct inode *inode, */ static int btrfs_log_all_xattrs(struct btrfs_trans_handle *trans, struct btrfs_root *root, - struct inode *inode, + struct btrfs_inode *inode, struct btrfs_path *path, struct btrfs_path *dst_path) { @@ -4374,7 +4375,7 @@ static int btrfs_log_all_xattrs(struct btrfs_trans_handle *trans, */ static int btrfs_log_trailing_hole(struct btrfs_trans_handle *trans, struct btrfs_root *root, - struct inode *inode, + struct btrfs_inode *inode, struct btrfs_path *path) { struct btrfs_fs_info *fs_info = root->fs_info; @@ -4385,7 +4386,7 @@ static int btrfs_log_trailing_hole(struct btrfs_trans_handle *trans, struct extent_buffer *leaf; struct btrfs_root *log = root->log_root; const u64 ino = btrfs_ino(inode); - const u64 i_size = i_size_read(inode); + const u64 i_size = i_size_read(&inode->vfs_inode); if (!btrfs_fs_incompat(fs_info, NO_HOLES)) return 0; @@ -4495,7 +4496,7 @@ static int btrfs_log_trailing_hole(struct btrfs_trans_handle *trans, static int btrfs_check_ref_name_override(struct extent_buffer *eb, const int slot, const struct btrfs_key *key, - struct inode *inode, + struct btrfs_inode *inode, u64 *other_ino) { int ret; @@ -4551,9 +4552,8 @@ static int btrfs_check_ref_name_override(struct extent_buffer *eb, } read_extent_buffer(eb, name, name_ptr, this_name_len); - di = btrfs_lookup_dir_item(NULL, BTRFS_I(inode)->root, - search_path, parent, - name, this_name_len, 0); + di = btrfs_lookup_dir_item(NULL, inode->root, search_path, + parent, name, this_name_len, 0); if (di && !IS_ERR(di)) { struct btrfs_key di_key; @@ -4596,7 +4596,7 @@ out: * This handles both files and directories. */ static int btrfs_log_inode(struct btrfs_trans_handle *trans, - struct btrfs_root *root, struct inode *inode, + struct btrfs_root *root, struct btrfs_inode *inode, int inode_only, const loff_t start, const loff_t end, @@ -4618,7 +4618,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, int ins_nr; bool fast_search = false; u64 ino = btrfs_ino(inode); - struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree; + struct extent_map_tree *em_tree = &inode->extent_tree; u64 logged_isize = 0; bool need_log_inode_item = true; @@ -4639,9 +4639,9 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, /* today the code can only do partial logging of directories */ - if (S_ISDIR(inode->i_mode) || + if (S_ISDIR(inode->vfs_inode.i_mode) || (!test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, - &BTRFS_I(inode)->runtime_flags) && + &inode->runtime_flags) && inode_only >= LOG_INODE_EXISTS)) max_key.type = BTRFS_XATTR_ITEM_KEY; else @@ -4654,8 +4654,8 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, * order for the log replay code to mark inodes for link count * fixup (create temporary BTRFS_TREE_LOG_FIXUP_OBJECTID items). */ - if (S_ISDIR(inode->i_mode) || - BTRFS_I(inode)->generation > fs_info->last_trans_committed) + if (S_ISDIR(inode->vfs_inode.i_mode) || + inode->generation > fs_info->last_trans_committed) ret = btrfs_commit_inode_delayed_items(trans, inode); else ret = btrfs_commit_inode_delayed_inode(inode); @@ -4668,17 +4668,16 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, if (inode_only == LOG_OTHER_INODE) { inode_only = LOG_INODE_EXISTS; - mutex_lock_nested(&BTRFS_I(inode)->log_mutex, - SINGLE_DEPTH_NESTING); + mutex_lock_nested(&inode->log_mutex, SINGLE_DEPTH_NESTING); } else { - mutex_lock(&BTRFS_I(inode)->log_mutex); + mutex_lock(&inode->log_mutex); } /* * a brute force approach to making sure we get the most uptodate * copies of everything. */ - if (S_ISDIR(inode->i_mode)) { + if (S_ISDIR(inode->vfs_inode.i_mode)) { int max_key_type = BTRFS_DIR_LOG_INDEX_KEY; if (inode_only == LOG_INODE_EXISTS) @@ -4699,31 +4698,30 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, * (zeroes), as if an expanding truncate happened, * instead of getting a file of 4Kb only. */ - err = logged_inode_size(log, inode, path, - &logged_isize); + err = logged_inode_size(log, inode, path, &logged_isize); if (err) goto out_unlock; } if (test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, - &BTRFS_I(inode)->runtime_flags)) { + &inode->runtime_flags)) { if (inode_only == LOG_INODE_EXISTS) { max_key.type = BTRFS_XATTR_ITEM_KEY; ret = drop_objectid_items(trans, log, path, ino, max_key.type); } else { clear_bit(BTRFS_INODE_NEEDS_FULL_SYNC, - &BTRFS_I(inode)->runtime_flags); + &inode->runtime_flags); clear_bit(BTRFS_INODE_COPY_EVERYTHING, - &BTRFS_I(inode)->runtime_flags); + &inode->runtime_flags); while(1) { ret = btrfs_truncate_inode_items(trans, - log, inode, 0, 0); + log, &inode->vfs_inode, 0, 0); if (ret != -EAGAIN) break; } } } else if (test_and_clear_bit(BTRFS_INODE_COPY_EVERYTHING, - &BTRFS_I(inode)->runtime_flags) || + &inode->runtime_flags) || inode_only == LOG_INODE_EXISTS) { if (inode_only == LOG_INODE_ALL) fast_search = true; @@ -4764,18 +4762,17 @@ again: if ((min_key.type == BTRFS_INODE_REF_KEY || min_key.type == BTRFS_INODE_EXTREF_KEY) && - BTRFS_I(inode)->generation == trans->transid) { + inode->generation == trans->transid) { u64 other_ino = 0; ret = btrfs_check_ref_name_override(path->nodes[0], - path->slots[0], - &min_key, inode, - &other_ino); + path->slots[0], &min_key, inode, + &other_ino); if (ret < 0) { err = ret; goto out_unlock; } else if (ret > 0 && ctx && - other_ino != btrfs_ino(ctx->inode)) { + other_ino != btrfs_ino(BTRFS_I(ctx->inode))) { struct btrfs_key inode_key; struct inode *other_inode; @@ -4823,9 +4820,10 @@ again: * update the log with the new name before we * unpin it. */ - err = btrfs_log_inode(trans, root, other_inode, - LOG_OTHER_INODE, - 0, LLONG_MAX, ctx); + err = btrfs_log_inode(trans, root, + BTRFS_I(other_inode), + LOG_OTHER_INODE, 0, LLONG_MAX, + ctx); iput(other_inode); if (err) goto out_unlock; @@ -4979,25 +4977,25 @@ log_extents: write_unlock(&em_tree->lock); } - if (inode_only == LOG_INODE_ALL && S_ISDIR(inode->i_mode)) { + if (inode_only == LOG_INODE_ALL && S_ISDIR(inode->vfs_inode.i_mode)) { ret = log_directory_changes(trans, root, inode, path, dst_path, - ctx); + ctx); if (ret) { err = ret; goto out_unlock; } } - spin_lock(&BTRFS_I(inode)->lock); - BTRFS_I(inode)->logged_trans = trans->transid; - BTRFS_I(inode)->last_log_commit = BTRFS_I(inode)->last_sub_trans; - spin_unlock(&BTRFS_I(inode)->lock); + spin_lock(&inode->lock); + inode->logged_trans = trans->transid; + inode->last_log_commit = inode->last_sub_trans; + spin_unlock(&inode->lock); out_unlock: if (unlikely(err)) btrfs_put_logged_extents(&logged_list); else btrfs_submit_logged_extents(&logged_list, log); - mutex_unlock(&BTRFS_I(inode)->log_mutex); + mutex_unlock(&inode->log_mutex); btrfs_free_path(path); btrfs_free_path(dst_path); @@ -5021,13 +5019,13 @@ out_unlock: * we logged the inode or it might have also done the unlink). */ static bool btrfs_must_commit_transaction(struct btrfs_trans_handle *trans, - struct inode *inode) + struct btrfs_inode *inode) { - struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info; + struct btrfs_fs_info *fs_info = inode->root->fs_info; bool ret = false; - mutex_lock(&BTRFS_I(inode)->log_mutex); - if (BTRFS_I(inode)->last_unlink_trans > fs_info->last_trans_committed) { + mutex_lock(&inode->log_mutex); + if (inode->last_unlink_trans > fs_info->last_trans_committed) { /* * Make sure any commits to the log are forced to be full * commits. @@ -5035,7 +5033,7 @@ static bool btrfs_must_commit_transaction(struct btrfs_trans_handle *trans, btrfs_set_log_full_commit(fs_info, trans); ret = true; } - mutex_unlock(&BTRFS_I(inode)->log_mutex); + mutex_unlock(&inode->log_mutex); return ret; } @@ -5084,7 +5082,7 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans, BTRFS_I(inode)->logged_trans = trans->transid; smp_mb(); - if (btrfs_must_commit_transaction(trans, inode)) { + if (btrfs_must_commit_transaction(trans, BTRFS_I(inode))) { ret = 1; break; } @@ -5094,7 +5092,7 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans, if (IS_ROOT(parent)) { inode = d_inode(parent); - if (btrfs_must_commit_transaction(trans, inode)) + if (btrfs_must_commit_transaction(trans, BTRFS_I(inode))) ret = 1; break; } @@ -5159,7 +5157,7 @@ struct btrfs_dir_list { */ static int log_new_dir_dentries(struct btrfs_trans_handle *trans, struct btrfs_root *root, - struct inode *start_inode, + struct btrfs_inode *start_inode, struct btrfs_log_ctx *ctx) { struct btrfs_fs_info *fs_info = root->fs_info; @@ -5237,7 +5235,7 @@ process_leaf: goto next_dir_inode; } - if (btrfs_inode_in_log(di_inode, trans->transid)) { + if (btrfs_inode_in_log(BTRFS_I(di_inode), trans->transid)) { iput(di_inode); break; } @@ -5245,10 +5243,10 @@ process_leaf: ctx->log_new_dentries = false; if (type == BTRFS_FT_DIR || type == BTRFS_FT_SYMLINK) log_mode = LOG_INODE_ALL; - ret = btrfs_log_inode(trans, root, di_inode, + ret = btrfs_log_inode(trans, root, BTRFS_I(di_inode), log_mode, 0, LLONG_MAX, ctx); if (!ret && - btrfs_must_commit_transaction(trans, di_inode)) + btrfs_must_commit_transaction(trans, BTRFS_I(di_inode))) ret = 1; iput(di_inode); if (ret) @@ -5297,7 +5295,7 @@ static int btrfs_log_all_parents(struct btrfs_trans_handle *trans, struct btrfs_path *path; struct btrfs_key key; struct btrfs_root *root = BTRFS_I(inode)->root; - const u64 ino = btrfs_ino(inode); + const u64 ino = btrfs_ino(BTRFS_I(inode)); path = btrfs_alloc_path(); if (!path) @@ -5365,14 +5363,14 @@ static int btrfs_log_all_parents(struct btrfs_trans_handle *trans, if (ctx) ctx->log_new_dentries = false; - ret = btrfs_log_inode(trans, root, dir_inode, + ret = btrfs_log_inode(trans, root, BTRFS_I(dir_inode), LOG_INODE_ALL, 0, LLONG_MAX, ctx); if (!ret && - btrfs_must_commit_transaction(trans, dir_inode)) + btrfs_must_commit_transaction(trans, BTRFS_I(dir_inode))) ret = 1; if (!ret && ctx && ctx->log_new_dentries) ret = log_new_dir_dentries(trans, root, - dir_inode, ctx); + BTRFS_I(dir_inode), ctx); iput(dir_inode); if (ret) goto out; @@ -5436,7 +5434,7 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans, if (ret) goto end_no_trans; - if (btrfs_inode_in_log(inode, trans->transid)) { + if (btrfs_inode_in_log(BTRFS_I(inode), trans->transid)) { ret = BTRFS_NO_LOG_SYNC; goto end_no_trans; } @@ -5445,7 +5443,8 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans, if (ret) goto end_no_trans; - ret = btrfs_log_inode(trans, root, inode, inode_only, start, end, ctx); + ret = btrfs_log_inode(trans, root, BTRFS_I(inode), inode_only, + start, end, ctx); if (ret) goto end_trans; @@ -5521,7 +5520,7 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans, break; if (BTRFS_I(inode)->generation > last_committed) { - ret = btrfs_log_inode(trans, root, inode, + ret = btrfs_log_inode(trans, root, BTRFS_I(inode), LOG_INODE_EXISTS, 0, LLONG_MAX, ctx); if (ret) @@ -5535,7 +5534,7 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans, old_parent = parent; } if (log_dentries) - ret = log_new_dir_dentries(trans, root, orig_inode, ctx); + ret = log_new_dir_dentries(trans, root, BTRFS_I(orig_inode), ctx); else ret = 0; end_trans: @@ -5730,7 +5729,7 @@ error: * inodes, etc) are done. */ void btrfs_record_unlink_dir(struct btrfs_trans_handle *trans, - struct inode *dir, struct inode *inode, + struct btrfs_inode *dir, struct btrfs_inode *inode, int for_rename) { /* @@ -5743,23 +5742,23 @@ void btrfs_record_unlink_dir(struct btrfs_trans_handle *trans, * into the file. When the file is logged we check it and * don't log the parents if the file is fully on disk. */ - mutex_lock(&BTRFS_I(inode)->log_mutex); - BTRFS_I(inode)->last_unlink_trans = trans->transid; - mutex_unlock(&BTRFS_I(inode)->log_mutex); + mutex_lock(&inode->log_mutex); + inode->last_unlink_trans = trans->transid; + mutex_unlock(&inode->log_mutex); /* * if this directory was already logged any new * names for this file/dir will get recorded */ smp_mb(); - if (BTRFS_I(dir)->logged_trans == trans->transid) + if (dir->logged_trans == trans->transid) return; /* * if the inode we're about to unlink was logged, * the log will be properly updated for any new names */ - if (BTRFS_I(inode)->logged_trans == trans->transid) + if (inode->logged_trans == trans->transid) return; /* @@ -5776,9 +5775,9 @@ void btrfs_record_unlink_dir(struct btrfs_trans_handle *trans, return; record: - mutex_lock(&BTRFS_I(dir)->log_mutex); - BTRFS_I(dir)->last_unlink_trans = trans->transid; - mutex_unlock(&BTRFS_I(dir)->log_mutex); + mutex_lock(&dir->log_mutex); + dir->last_unlink_trans = trans->transid; + mutex_unlock(&dir->log_mutex); } /* @@ -5794,11 +5793,11 @@ record: * parent root and tree of tree roots trees, etc) are done. */ void btrfs_record_snapshot_destroy(struct btrfs_trans_handle *trans, - struct inode *dir) + struct btrfs_inode *dir) { - mutex_lock(&BTRFS_I(dir)->log_mutex); - BTRFS_I(dir)->last_unlink_trans = trans->transid; - mutex_unlock(&BTRFS_I(dir)->log_mutex); + mutex_lock(&dir->log_mutex); + dir->last_unlink_trans = trans->transid; + mutex_unlock(&dir->log_mutex); } /* @@ -5809,30 +5808,28 @@ void btrfs_record_snapshot_destroy(struct btrfs_trans_handle *trans, * full transaction commit is required. */ int btrfs_log_new_name(struct btrfs_trans_handle *trans, - struct inode *inode, struct inode *old_dir, + struct btrfs_inode *inode, struct btrfs_inode *old_dir, struct dentry *parent) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - struct btrfs_root * root = BTRFS_I(inode)->root; + struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb); + struct btrfs_root *root = inode->root; /* * this will force the logging code to walk the dentry chain * up for the file */ - if (S_ISREG(inode->i_mode)) - BTRFS_I(inode)->last_unlink_trans = trans->transid; + if (S_ISREG(inode->vfs_inode.i_mode)) + inode->last_unlink_trans = trans->transid; /* * if this inode hasn't been logged and directory we're renaming it * from hasn't been logged, we don't need to log it */ - if (BTRFS_I(inode)->logged_trans <= - fs_info->last_trans_committed && - (!old_dir || BTRFS_I(old_dir)->logged_trans <= - fs_info->last_trans_committed)) + if (inode->logged_trans <= fs_info->last_trans_committed && + (!old_dir || old_dir->logged_trans <= fs_info->last_trans_committed)) return 0; - return btrfs_log_inode_parent(trans, root, inode, parent, 0, + return btrfs_log_inode_parent(trans, root, &inode->vfs_inode, parent, 0, LLONG_MAX, 1, NULL); } diff --git a/fs/btrfs/tree-log.h b/fs/btrfs/tree-log.h index ab858e31ccbc..483027f9a7f4 100644 --- a/fs/btrfs/tree-log.h +++ b/fs/btrfs/tree-log.h @@ -48,13 +48,13 @@ static inline void btrfs_init_log_ctx(struct btrfs_log_ctx *ctx, static inline void btrfs_set_log_full_commit(struct btrfs_fs_info *fs_info, struct btrfs_trans_handle *trans) { - ACCESS_ONCE(fs_info->last_trans_log_full_commit) = trans->transid; + WRITE_ONCE(fs_info->last_trans_log_full_commit, trans->transid); } static inline int btrfs_need_log_full_commit(struct btrfs_fs_info *fs_info, struct btrfs_trans_handle *trans) { - return ACCESS_ONCE(fs_info->last_trans_log_full_commit) == + return READ_ONCE(fs_info->last_trans_log_full_commit) == trans->transid; } @@ -72,19 +72,19 @@ int btrfs_log_dentry_safe(struct btrfs_trans_handle *trans, int btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans, struct btrfs_root *root, const char *name, int name_len, - struct inode *dir, u64 index); + struct btrfs_inode *dir, u64 index); int btrfs_del_inode_ref_in_log(struct btrfs_trans_handle *trans, struct btrfs_root *root, const char *name, int name_len, - struct inode *inode, u64 dirid); + struct btrfs_inode *inode, u64 dirid); void btrfs_end_log_trans(struct btrfs_root *root); int btrfs_pin_log_trans(struct btrfs_root *root); void btrfs_record_unlink_dir(struct btrfs_trans_handle *trans, - struct inode *dir, struct inode *inode, + struct btrfs_inode *dir, struct btrfs_inode *inode, int for_rename); void btrfs_record_snapshot_destroy(struct btrfs_trans_handle *trans, - struct inode *dir); + struct btrfs_inode *dir); int btrfs_log_new_name(struct btrfs_trans_handle *trans, - struct inode *inode, struct inode *old_dir, + struct btrfs_inode *inode, struct btrfs_inode *old_dir, struct dentry *parent); #endif diff --git a/fs/btrfs/ulist.c b/fs/btrfs/ulist.c index b1434bb57e36..d8edf164f81c 100644 --- a/fs/btrfs/ulist.c +++ b/fs/btrfs/ulist.c @@ -52,13 +52,13 @@ void ulist_init(struct ulist *ulist) } /** - * ulist_fini - free up additionally allocated memory for the ulist + * ulist_release - free up additionally allocated memory for the ulist * @ulist: the ulist from which to free the additional memory * * This is useful in cases where the base 'struct ulist' has been statically * allocated. */ -static void ulist_fini(struct ulist *ulist) +void ulist_release(struct ulist *ulist) { struct ulist_node *node; struct ulist_node *next; @@ -79,7 +79,7 @@ static void ulist_fini(struct ulist *ulist) */ void ulist_reinit(struct ulist *ulist) { - ulist_fini(ulist); + ulist_release(ulist); ulist_init(ulist); } @@ -105,13 +105,13 @@ struct ulist *ulist_alloc(gfp_t gfp_mask) * ulist_free - free dynamically allocated ulist * @ulist: ulist to free * - * It is not necessary to call ulist_fini before. + * It is not necessary to call ulist_release before. */ void ulist_free(struct ulist *ulist) { if (!ulist) return; - ulist_fini(ulist); + ulist_release(ulist); kfree(ulist); } diff --git a/fs/btrfs/ulist.h b/fs/btrfs/ulist.h index a01a2c45825f..53c913632733 100644 --- a/fs/btrfs/ulist.h +++ b/fs/btrfs/ulist.h @@ -19,9 +19,6 @@ * */ struct ulist_iterator { -#ifdef CONFIG_BTRFS_DEBUG - int i; -#endif struct list_head *cur_list; /* hint to start search */ }; @@ -32,10 +29,6 @@ struct ulist_node { u64 val; /* value to store */ u64 aux; /* auxiliary value saved along with the val */ -#ifdef CONFIG_BTRFS_DEBUG - int seqnum; /* sequence number this node is added */ -#endif - struct list_head list; /* used to link node */ struct rb_node rb_node; /* used to speed up search */ }; @@ -51,6 +44,7 @@ struct ulist { }; void ulist_init(struct ulist *ulist); +void ulist_release(struct ulist *ulist); void ulist_reinit(struct ulist *ulist); struct ulist *ulist_alloc(gfp_t gfp_mask); void ulist_free(struct ulist *ulist); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 3c3c69c0eee4..13e55d13045d 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -134,8 +134,7 @@ const int btrfs_raid_mindev_error[BTRFS_NR_RAID_TYPES] = { }; static int init_first_rw_device(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, - struct btrfs_device *device); + struct btrfs_fs_info *fs_info); static int btrfs_relocate_sys_chunks(struct btrfs_fs_info *fs_info); static void __btrfs_reset_dev_stats(struct btrfs_device *dev); static void btrfs_dev_stat_print_on_error(struct btrfs_device *dev); @@ -366,7 +365,7 @@ static noinline void run_scheduled_bios(struct btrfs_device *device) */ blk_start_plug(&plug); - bdi = blk_get_backing_dev_info(device->bdev); + bdi = device->bdev->bd_bdi; limit = btrfs_async_submit_limit(fs_info); limit = limit * 2 / 3; @@ -2440,7 +2439,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, char *device_path) if (seeding_dev) { mutex_lock(&fs_info->chunk_mutex); - ret = init_first_rw_device(trans, fs_info, device); + ret = init_first_rw_device(trans, fs_info); mutex_unlock(&fs_info->chunk_mutex); if (ret) { btrfs_abort_transaction(trans, ret); @@ -4584,8 +4583,7 @@ static void check_raid56_incompat_flag(struct btrfs_fs_info *info, u64 type) / sizeof(struct btrfs_stripe) + 1) static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, u64 start, - u64 type) + u64 start, u64 type) { struct btrfs_fs_info *info = trans->fs_info; struct btrfs_fs_devices *fs_devices = info->fs_devices; @@ -5009,12 +5007,11 @@ int btrfs_alloc_chunk(struct btrfs_trans_handle *trans, ASSERT(mutex_is_locked(&fs_info->chunk_mutex)); chunk_offset = find_next_chunk(fs_info); - return __btrfs_alloc_chunk(trans, fs_info, chunk_offset, type); + return __btrfs_alloc_chunk(trans, chunk_offset, type); } static noinline int init_first_rw_device(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, - struct btrfs_device *device) + struct btrfs_fs_info *fs_info) { struct btrfs_root *extent_root = fs_info->extent_root; u64 chunk_offset; @@ -5024,14 +5021,13 @@ static noinline int init_first_rw_device(struct btrfs_trans_handle *trans, chunk_offset = find_next_chunk(fs_info); alloc_profile = btrfs_get_alloc_profile(extent_root, 0); - ret = __btrfs_alloc_chunk(trans, fs_info, chunk_offset, alloc_profile); + ret = __btrfs_alloc_chunk(trans, chunk_offset, alloc_profile); if (ret) return ret; sys_chunk_offset = find_next_chunk(fs_info); alloc_profile = btrfs_get_alloc_profile(fs_info->chunk_root, 0); - ret = __btrfs_alloc_chunk(trans, fs_info, sys_chunk_offset, - alloc_profile); + ret = __btrfs_alloc_chunk(trans, sys_chunk_offset, alloc_profile); return ret; } diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c index 9621c7f2503e..b3cbf80c5acf 100644 --- a/fs/btrfs/xattr.c +++ b/fs/btrfs/xattr.c @@ -47,8 +47,8 @@ ssize_t __btrfs_getxattr(struct inode *inode, const char *name, return -ENOMEM; /* lookup the xattr by name */ - di = btrfs_lookup_xattr(NULL, root, path, btrfs_ino(inode), name, - strlen(name), 0); + di = btrfs_lookup_xattr(NULL, root, path, btrfs_ino(BTRFS_I(inode)), + name, strlen(name), 0); if (!di) { ret = -ENODATA; goto out; @@ -108,8 +108,8 @@ static int do_setxattr(struct btrfs_trans_handle *trans, path->skip_release_on_error = 1; if (!value) { - di = btrfs_lookup_xattr(trans, root, path, btrfs_ino(inode), - name, name_len, -1); + di = btrfs_lookup_xattr(trans, root, path, + btrfs_ino(BTRFS_I(inode)), name, name_len, -1); if (!di && (flags & XATTR_REPLACE)) ret = -ENODATA; else if (IS_ERR(di)) @@ -128,8 +128,8 @@ static int do_setxattr(struct btrfs_trans_handle *trans, */ if (flags & XATTR_REPLACE) { ASSERT(inode_is_locked(inode)); - di = btrfs_lookup_xattr(NULL, root, path, btrfs_ino(inode), - name, name_len, 0); + di = btrfs_lookup_xattr(NULL, root, path, + btrfs_ino(BTRFS_I(inode)), name, name_len, 0); if (!di) ret = -ENODATA; else if (IS_ERR(di)) @@ -140,7 +140,7 @@ static int do_setxattr(struct btrfs_trans_handle *trans, di = NULL; } - ret = btrfs_insert_xattr_item(trans, root, path, btrfs_ino(inode), + ret = btrfs_insert_xattr_item(trans, root, path, btrfs_ino(BTRFS_I(inode)), name, name_len, value, size); if (ret == -EOVERFLOW) { /* @@ -278,7 +278,7 @@ ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size) * NOTE: we set key.offset = 0; because we want to start with the * first xattr that we find and walk forward */ - key.objectid = btrfs_ino(inode); + key.objectid = btrfs_ino(BTRFS_I(inode)); key.type = BTRFS_XATTR_ITEM_KEY; key.offset = 0; diff --git a/fs/buffer.c b/fs/buffer.c index 0e87401cf335..28484b3ebc98 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -2395,7 +2395,7 @@ static int cont_expand_zero(struct file *file, struct address_space *mapping, loff_t pos, loff_t *bytes) { struct inode *inode = mapping->host; - unsigned blocksize = 1 << inode->i_blkbits; + unsigned int blocksize = i_blocksize(inode); struct page *page; void *fsdata; pgoff_t index, curidx; @@ -2475,8 +2475,8 @@ int cont_write_begin(struct file *file, struct address_space *mapping, get_block_t *get_block, loff_t *bytes) { struct inode *inode = mapping->host; - unsigned blocksize = 1 << inode->i_blkbits; - unsigned zerofrom; + unsigned int blocksize = i_blocksize(inode); + unsigned int zerofrom; int err; err = cont_expand_zero(file, mapping, pos, bytes); @@ -2838,7 +2838,7 @@ int nobh_truncate_page(struct address_space *mapping, struct buffer_head map_bh; int err; - blocksize = 1 << inode->i_blkbits; + blocksize = i_blocksize(inode); length = offset & (blocksize - 1); /* Block boundary? Nothing to do */ @@ -2916,7 +2916,7 @@ int block_truncate_page(struct address_space *mapping, struct buffer_head *bh; int err; - blocksize = 1 << inode->i_blkbits; + blocksize = i_blocksize(inode); length = offset & (blocksize - 1); /* Block boundary? Nothing to do */ @@ -3028,7 +3028,7 @@ sector_t generic_block_bmap(struct address_space *mapping, sector_t block, struct inode *inode = mapping->host; tmp.b_state = 0; tmp.b_blocknr = 0; - tmp.b_size = 1 << inode->i_blkbits; + tmp.b_size = i_blocksize(inode); get_block(inode, block, &tmp, 0); return tmp.b_blocknr; } diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index e4b066cd912a..7ce35aec8c76 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -751,7 +751,7 @@ static int ceph_writepages_start(struct address_space *mapping, struct pagevec pvec; int done = 0; int rc = 0; - unsigned wsize = 1 << inode->i_blkbits; + unsigned int wsize = i_blocksize(inode); struct ceph_osd_request *req = NULL; int do_sync = 0; loff_t snap_size, i_size; @@ -1386,8 +1386,9 @@ static void ceph_restore_sigs(sigset_t *oldset) /* * vm ops */ -static int ceph_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) +static int ceph_filemap_fault(struct vm_fault *vmf) { + struct vm_area_struct *vma = vmf->vma; struct inode *inode = file_inode(vma->vm_file); struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_file_info *fi = vma->vm_file->private_data; @@ -1416,7 +1417,7 @@ static int ceph_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) if ((got & (CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO)) || ci->i_inline_version == CEPH_INLINE_NONE) { current->journal_info = vma->vm_file; - ret = filemap_fault(vma, vmf); + ret = filemap_fault(vmf); current->journal_info = NULL; } else ret = -EAGAIN; @@ -1477,8 +1478,9 @@ out_restore: /* * Reuse write_begin here for simplicity. */ -static int ceph_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) +static int ceph_page_mkwrite(struct vm_fault *vmf) { + struct vm_area_struct *vma = vmf->vma; struct inode *inode = file_inode(vma->vm_file); struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_file_info *fi = vma->vm_file->private_data; diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c index ec9dbbcca3b9..9156be545b0f 100644 --- a/fs/cifs/cifs_dfs_ref.c +++ b/fs/cifs/cifs_dfs_ref.c @@ -245,7 +245,8 @@ compose_mount_options_err: * @fullpath: full path in UNC format * @ref: server's referral */ -static struct vfsmount *cifs_dfs_do_refmount(struct cifs_sb_info *cifs_sb, +static struct vfsmount *cifs_dfs_do_refmount(struct dentry *mntpt, + struct cifs_sb_info *cifs_sb, const char *fullpath, const struct dfs_info3_param *ref) { struct vfsmount *mnt; @@ -259,7 +260,7 @@ static struct vfsmount *cifs_dfs_do_refmount(struct cifs_sb_info *cifs_sb, if (IS_ERR(mountdata)) return (struct vfsmount *)mountdata; - mnt = vfs_kern_mount(&cifs_fs_type, 0, devname, mountdata); + mnt = vfs_submount(mntpt, &cifs_fs_type, devname, mountdata); kfree(mountdata); kfree(devname); return mnt; @@ -334,7 +335,7 @@ static struct vfsmount *cifs_dfs_do_automount(struct dentry *mntpt) mnt = ERR_PTR(-EINVAL); break; } - mnt = cifs_dfs_do_refmount(cifs_sb, + mnt = cifs_dfs_do_refmount(mntpt, cifs_sb, full_path, referrals + i); cifs_dbg(FYI, "%s: cifs_dfs_do_refmount:%s , mnt:%p\n", __func__, referrals[i].node_name, mnt); diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 98dc842e7245..aa3debbba826 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -3282,7 +3282,7 @@ cifs_read(struct file *file, char *read_data, size_t read_size, loff_t *offset) * sure that it doesn't change while being written back. */ static int -cifs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) +cifs_page_mkwrite(struct vm_fault *vmf) { struct page *page = vmf->page; @@ -35,6 +35,9 @@ #include <linux/iomap.h> #include "internal.h" +#define CREATE_TRACE_POINTS +#include <trace/events/fs_dax.h> + /* We choose 4096 entries - same as per-zone page wait tables */ #define DAX_WAIT_TABLE_BITS 12 #define DAX_WAIT_TABLE_ENTRIES (1 << DAX_WAIT_TABLE_BITS) @@ -922,12 +925,11 @@ static int dax_insert_mapping(struct address_space *mapping, /** * dax_pfn_mkwrite - handle first write to DAX page - * @vma: The virtual memory area where the fault occurred * @vmf: The description of the fault */ -int dax_pfn_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) +int dax_pfn_mkwrite(struct vm_fault *vmf) { - struct file *file = vma->vm_file; + struct file *file = vmf->vma->vm_file; struct address_space *mapping = file->f_mapping; void *entry, **slot; pgoff_t index = vmf->pgoff; @@ -1079,7 +1081,7 @@ dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data, */ ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter, - struct iomap_ops *ops) + const struct iomap_ops *ops) { struct address_space *mapping = iocb->ki_filp->f_mapping; struct inode *inode = mapping->host; @@ -1116,20 +1118,10 @@ static int dax_fault_return(int error) return VM_FAULT_SIGBUS; } -/** - * dax_iomap_fault - handle a page fault on a DAX file - * @vma: The virtual memory area where the fault occurred - * @vmf: The description of the fault - * @ops: iomap ops passed from the file system - * - * When a page fault occurs, filesystems may call this helper in their fault - * or mkwrite handler for DAX files. Assumes the caller has done all the - * necessary locking for the page fault to proceed successfully. - */ -int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf, - struct iomap_ops *ops) +static int dax_iomap_pte_fault(struct vm_fault *vmf, + const struct iomap_ops *ops) { - struct address_space *mapping = vma->vm_file->f_mapping; + struct address_space *mapping = vmf->vma->vm_file->f_mapping; struct inode *inode = mapping->host; unsigned long vaddr = vmf->address; loff_t pos = (loff_t)vmf->pgoff << PAGE_SHIFT; @@ -1202,11 +1194,11 @@ int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf, case IOMAP_MAPPED: if (iomap.flags & IOMAP_F_NEW) { count_vm_event(PGMAJFAULT); - mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT); + mem_cgroup_count_vm_event(vmf->vma->vm_mm, PGMAJFAULT); major = VM_FAULT_MAJOR; } error = dax_insert_mapping(mapping, iomap.bdev, sector, - PAGE_SIZE, &entry, vma, vmf); + PAGE_SIZE, &entry, vmf->vma, vmf); /* -EBUSY is fine, somebody else faulted on the same PTE */ if (error == -EBUSY) error = 0; @@ -1244,7 +1236,6 @@ int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf, } return vmf_ret; } -EXPORT_SYMBOL_GPL(dax_iomap_fault); #ifdef CONFIG_FS_DAX_PMD /* @@ -1253,21 +1244,21 @@ EXPORT_SYMBOL_GPL(dax_iomap_fault); */ #define PG_PMD_COLOUR ((PMD_SIZE >> PAGE_SHIFT) - 1) -static int dax_pmd_insert_mapping(struct vm_area_struct *vma, pmd_t *pmd, - struct vm_fault *vmf, unsigned long address, - struct iomap *iomap, loff_t pos, bool write, void **entryp) +static int dax_pmd_insert_mapping(struct vm_fault *vmf, struct iomap *iomap, + loff_t pos, void **entryp) { - struct address_space *mapping = vma->vm_file->f_mapping; + struct address_space *mapping = vmf->vma->vm_file->f_mapping; struct block_device *bdev = iomap->bdev; + struct inode *inode = mapping->host; struct blk_dax_ctl dax = { .sector = dax_iomap_sector(iomap, pos), .size = PMD_SIZE, }; long length = dax_map_atomic(bdev, &dax); - void *ret; + void *ret = NULL; if (length < 0) /* dax_map_atomic() failed */ - return VM_FAULT_FALLBACK; + goto fallback; if (length < PMD_SIZE) goto unmap_fallback; if (pfn_t_to_pfn(dax.pfn) & PG_PMD_COLOUR) @@ -1280,67 +1271,87 @@ static int dax_pmd_insert_mapping(struct vm_area_struct *vma, pmd_t *pmd, ret = dax_insert_mapping_entry(mapping, vmf, *entryp, dax.sector, RADIX_DAX_PMD); if (IS_ERR(ret)) - return VM_FAULT_FALLBACK; + goto fallback; *entryp = ret; - return vmf_insert_pfn_pmd(vma, address, pmd, dax.pfn, write); + trace_dax_pmd_insert_mapping(inode, vmf, length, dax.pfn, ret); + return vmf_insert_pfn_pmd(vmf->vma, vmf->address, vmf->pmd, + dax.pfn, vmf->flags & FAULT_FLAG_WRITE); unmap_fallback: dax_unmap_atomic(bdev, &dax); +fallback: + trace_dax_pmd_insert_mapping_fallback(inode, vmf, length, + dax.pfn, ret); return VM_FAULT_FALLBACK; } -static int dax_pmd_load_hole(struct vm_area_struct *vma, pmd_t *pmd, - struct vm_fault *vmf, unsigned long address, - struct iomap *iomap, void **entryp) +static int dax_pmd_load_hole(struct vm_fault *vmf, struct iomap *iomap, + void **entryp) { - struct address_space *mapping = vma->vm_file->f_mapping; - unsigned long pmd_addr = address & PMD_MASK; + struct address_space *mapping = vmf->vma->vm_file->f_mapping; + unsigned long pmd_addr = vmf->address & PMD_MASK; + struct inode *inode = mapping->host; struct page *zero_page; + void *ret = NULL; spinlock_t *ptl; pmd_t pmd_entry; - void *ret; - zero_page = mm_get_huge_zero_page(vma->vm_mm); + zero_page = mm_get_huge_zero_page(vmf->vma->vm_mm); if (unlikely(!zero_page)) - return VM_FAULT_FALLBACK; + goto fallback; ret = dax_insert_mapping_entry(mapping, vmf, *entryp, 0, RADIX_DAX_PMD | RADIX_DAX_HZP); if (IS_ERR(ret)) - return VM_FAULT_FALLBACK; + goto fallback; *entryp = ret; - ptl = pmd_lock(vma->vm_mm, pmd); - if (!pmd_none(*pmd)) { + ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd); + if (!pmd_none(*(vmf->pmd))) { spin_unlock(ptl); - return VM_FAULT_FALLBACK; + goto fallback; } - pmd_entry = mk_pmd(zero_page, vma->vm_page_prot); + pmd_entry = mk_pmd(zero_page, vmf->vma->vm_page_prot); pmd_entry = pmd_mkhuge(pmd_entry); - set_pmd_at(vma->vm_mm, pmd_addr, pmd, pmd_entry); + set_pmd_at(vmf->vma->vm_mm, pmd_addr, vmf->pmd, pmd_entry); spin_unlock(ptl); + trace_dax_pmd_load_hole(inode, vmf, zero_page, ret); return VM_FAULT_NOPAGE; + +fallback: + trace_dax_pmd_load_hole_fallback(inode, vmf, zero_page, ret); + return VM_FAULT_FALLBACK; } -int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address, - pmd_t *pmd, unsigned int flags, struct iomap_ops *ops) +static int dax_iomap_pmd_fault(struct vm_fault *vmf, + const struct iomap_ops *ops) { + struct vm_area_struct *vma = vmf->vma; struct address_space *mapping = vma->vm_file->f_mapping; - unsigned long pmd_addr = address & PMD_MASK; - bool write = flags & FAULT_FLAG_WRITE; + unsigned long pmd_addr = vmf->address & PMD_MASK; + bool write = vmf->flags & FAULT_FLAG_WRITE; unsigned int iomap_flags = (write ? IOMAP_WRITE : 0) | IOMAP_FAULT; struct inode *inode = mapping->host; int result = VM_FAULT_FALLBACK; struct iomap iomap = { 0 }; pgoff_t max_pgoff, pgoff; - struct vm_fault vmf; void *entry; loff_t pos; int error; + /* + * Check whether offset isn't beyond end of file now. Caller is + * supposed to hold locks serializing us with truncate / punch hole so + * this is a reliable test. + */ + pgoff = linear_page_index(vma, pmd_addr); + max_pgoff = (i_size_read(inode) - 1) >> PAGE_SHIFT; + + trace_dax_pmd_fault(inode, vmf, max_pgoff, 0); + /* Fall back to PTEs if we're going to COW */ if (write && !(vma->vm_flags & VM_SHARED)) goto fallback; @@ -1351,16 +1362,10 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address, if ((pmd_addr + PMD_SIZE) > vma->vm_end) goto fallback; - /* - * Check whether offset isn't beyond end of file now. Caller is - * supposed to hold locks serializing us with truncate / punch hole so - * this is a reliable test. - */ - pgoff = linear_page_index(vma, pmd_addr); - max_pgoff = (i_size_read(inode) - 1) >> PAGE_SHIFT; - - if (pgoff > max_pgoff) - return VM_FAULT_SIGBUS; + if (pgoff > max_pgoff) { + result = VM_FAULT_SIGBUS; + goto out; + } /* If the PMD would extend beyond the file size */ if ((pgoff | PG_PMD_COLOUR) > max_pgoff) @@ -1389,21 +1394,15 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address, if (IS_ERR(entry)) goto finish_iomap; - vmf.pgoff = pgoff; - vmf.flags = flags; - vmf.gfp_mask = mapping_gfp_mask(mapping) | __GFP_IO; - switch (iomap.type) { case IOMAP_MAPPED: - result = dax_pmd_insert_mapping(vma, pmd, &vmf, address, - &iomap, pos, write, &entry); + result = dax_pmd_insert_mapping(vmf, &iomap, pos, &entry); break; case IOMAP_UNWRITTEN: case IOMAP_HOLE: if (WARN_ON_ONCE(write)) goto unlock_entry; - result = dax_pmd_load_hole(vma, pmd, &vmf, address, &iomap, - &entry); + result = dax_pmd_load_hole(vmf, &iomap, &entry); break; default: WARN_ON_ONCE(1); @@ -1429,10 +1428,41 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address, } fallback: if (result == VM_FAULT_FALLBACK) { - split_huge_pmd(vma, pmd, address); + split_huge_pmd(vma, vmf->pmd, vmf->address); count_vm_event(THP_FAULT_FALLBACK); } +out: + trace_dax_pmd_fault_done(inode, vmf, max_pgoff, result); return result; } -EXPORT_SYMBOL_GPL(dax_iomap_pmd_fault); +#else +static int dax_iomap_pmd_fault(struct vm_fault *vmf, + const struct iomap_ops *ops) +{ + return VM_FAULT_FALLBACK; +} #endif /* CONFIG_FS_DAX_PMD */ + +/** + * dax_iomap_fault - handle a page fault on a DAX file + * @vmf: The description of the fault + * @ops: iomap ops passed from the file system + * + * When a page fault occurs, filesystems may call this helper in + * their fault handler for DAX files. dax_iomap_fault() assumes the caller + * has done all the necessary locking for page fault to proceed + * successfully. + */ +int dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size, + const struct iomap_ops *ops) +{ + switch (pe_size) { + case PE_SIZE_PTE: + return dax_iomap_pte_fault(vmf, ops); + case PE_SIZE_PMD: + return dax_iomap_pmd_fault(vmf, ops); + default: + return VM_FAULT_FALLBACK; + } +} +EXPORT_SYMBOL_GPL(dax_iomap_fault); diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index f17fcf89e18e..7fd4ec4bb214 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -187,9 +187,9 @@ static const struct super_operations debugfs_super_operations = { static struct vfsmount *debugfs_automount(struct path *path) { - struct vfsmount *(*f)(void *); - f = (struct vfsmount *(*)(void *))path->dentry->d_fsdata; - return f(d_inode(path->dentry)->i_private); + debugfs_automount_t f; + f = (debugfs_automount_t)path->dentry->d_fsdata; + return f(path->dentry, d_inode(path->dentry)->i_private); } static const struct dentry_operations debugfs_dops = { @@ -248,6 +248,42 @@ static struct file_system_type debug_fs_type = { }; MODULE_ALIAS_FS("debugfs"); +/** + * debugfs_lookup() - look up an existing debugfs file + * @name: a pointer to a string containing the name of the file to look up. + * @parent: a pointer to the parent dentry of the file. + * + * This function will return a pointer to a dentry if it succeeds. If the file + * doesn't exist or an error occurs, %NULL will be returned. The returned + * dentry must be passed to dput() when it is no longer needed. + * + * If debugfs is not enabled in the kernel, the value -%ENODEV will be + * returned. + */ +struct dentry *debugfs_lookup(const char *name, struct dentry *parent) +{ + struct dentry *dentry; + + if (IS_ERR(parent)) + return NULL; + + if (!parent) + parent = debugfs_mount->mnt_root; + + inode_lock(d_inode(parent)); + dentry = lookup_one_len(name, parent, strlen(name)); + inode_unlock(d_inode(parent)); + + if (IS_ERR(dentry)) + return NULL; + if (!d_really_is_positive(dentry)) { + dput(dentry); + return NULL; + } + return dentry; +} +EXPORT_SYMBOL_GPL(debugfs_lookup); + static struct dentry *start_creating(const char *name, struct dentry *parent) { struct dentry *dentry; @@ -504,7 +540,7 @@ EXPORT_SYMBOL_GPL(debugfs_create_dir); */ struct dentry *debugfs_create_automount(const char *name, struct dentry *parent, - struct vfsmount *(*f)(void *), + debugfs_automount_t f, void *data) { struct dentry *dentry = start_creating(name, parent); diff --git a/fs/direct-io.c b/fs/direct-io.c index c87bae4376b8..a04ebea77de8 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -587,7 +587,7 @@ static int dio_set_defer_completion(struct dio *dio) /* * Call into the fs to map some more disk blocks. We record the current number * of available blocks at sdio->blocks_available. These are in units of the - * fs blocksize, (1 << inode->i_blkbits). + * fs blocksize, i_blocksize(inode). * * The fs is allowed to map lots of blocks at once. If it wants to do that, * it uses the passed inode-relative block number as the file offset, as usual. diff --git a/fs/ecryptfs/kthread.c b/fs/ecryptfs/kthread.c index 866bb18efefe..e00d45af84ea 100644 --- a/fs/ecryptfs/kthread.c +++ b/fs/ecryptfs/kthread.c @@ -123,7 +123,7 @@ void ecryptfs_destroy_kthread(void) * @lower_dentry: Lower dentry for file to open * @lower_mnt: Lower vfsmount for file to open * - * This function gets a r/w file opened againt the lower dentry. + * This function gets a r/w file opened against the lower dentry. * * Returns zero on success; non-zero otherwise */ diff --git a/fs/eventpoll.c b/fs/eventpoll.c index bcb68fcc8445..5ec16313da1a 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1895,7 +1895,7 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, * so EPOLLEXCLUSIVE is not allowed for a EPOLL_CTL_MOD operation. * Also, we do not currently supported nested exclusive wakeups. */ - if (epds.events & EPOLLEXCLUSIVE) { + if (ep_op_has_event(op) && (epds.events & EPOLLEXCLUSIVE)) { if (op == EPOLL_CTL_MOD) goto error_tgt_fput; if (op == EPOLL_CTL_ADD && (is_file_epoll(tf.file) || diff --git a/fs/exec.c b/fs/exec.c index e57946610733..698a86094f76 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1426,12 +1426,8 @@ static void check_unsafe_exec(struct linux_binprm *bprm) struct task_struct *p = current, *t; unsigned n_fs; - if (p->ptrace) { - if (ptracer_capable(p, current_user_ns())) - bprm->unsafe |= LSM_UNSAFE_PTRACE_CAP; - else - bprm->unsafe |= LSM_UNSAFE_PTRACE; - } + if (p->ptrace) + bprm->unsafe |= LSM_UNSAFE_PTRACE; /* * This isn't strictly necessary, but it makes it harder for LSMs to @@ -1479,7 +1475,7 @@ static void bprm_fill_uid(struct linux_binprm *bprm) if (task_no_new_privs(current)) return; - inode = file_inode(bprm->file); + inode = bprm->file->f_path.dentry->d_inode; mode = READ_ONCE(inode->i_mode); if (!(mode & (S_ISUID|S_ISGID))) return; diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h index 37e2be784ac7..5e64de9c5093 100644 --- a/fs/ext2/ext2.h +++ b/fs/ext2/ext2.h @@ -814,7 +814,7 @@ extern const struct file_operations ext2_file_operations; /* inode.c */ extern const struct address_space_operations ext2_aops; extern const struct address_space_operations ext2_nobh_aops; -extern struct iomap_ops ext2_iomap_ops; +extern const struct iomap_ops ext2_iomap_ops; /* namei.c */ extern const struct inode_operations ext2_dir_inode_operations; diff --git a/fs/ext2/file.c b/fs/ext2/file.c index b0f241528a30..b21891a6bfca 100644 --- a/fs/ext2/file.c +++ b/fs/ext2/file.c @@ -87,19 +87,19 @@ out_unlock: * The default page_lock and i_size verification done by non-DAX fault paths * is sufficient because ext2 doesn't support hole punching. */ -static int ext2_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf) +static int ext2_dax_fault(struct vm_fault *vmf) { - struct inode *inode = file_inode(vma->vm_file); + struct inode *inode = file_inode(vmf->vma->vm_file); struct ext2_inode_info *ei = EXT2_I(inode); int ret; if (vmf->flags & FAULT_FLAG_WRITE) { sb_start_pagefault(inode->i_sb); - file_update_time(vma->vm_file); + file_update_time(vmf->vma->vm_file); } down_read(&ei->dax_sem); - ret = dax_iomap_fault(vma, vmf, &ext2_iomap_ops); + ret = dax_iomap_fault(vmf, PE_SIZE_PTE, &ext2_iomap_ops); up_read(&ei->dax_sem); if (vmf->flags & FAULT_FLAG_WRITE) @@ -107,16 +107,15 @@ static int ext2_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf) return ret; } -static int ext2_dax_pfn_mkwrite(struct vm_area_struct *vma, - struct vm_fault *vmf) +static int ext2_dax_pfn_mkwrite(struct vm_fault *vmf) { - struct inode *inode = file_inode(vma->vm_file); + struct inode *inode = file_inode(vmf->vma->vm_file); struct ext2_inode_info *ei = EXT2_I(inode); loff_t size; int ret; sb_start_pagefault(inode->i_sb); - file_update_time(vma->vm_file); + file_update_time(vmf->vma->vm_file); down_read(&ei->dax_sem); /* check that the faulting page hasn't raced with truncate */ @@ -124,7 +123,7 @@ static int ext2_dax_pfn_mkwrite(struct vm_area_struct *vma, if (vmf->pgoff >= size) ret = VM_FAULT_SIGBUS; else - ret = dax_pfn_mkwrite(vma, vmf); + ret = dax_pfn_mkwrite(vmf); up_read(&ei->dax_sem); sb_end_pagefault(inode->i_sb); @@ -134,7 +133,7 @@ static int ext2_dax_pfn_mkwrite(struct vm_area_struct *vma, static const struct vm_operations_struct ext2_dax_vm_ops = { .fault = ext2_dax_fault, /* - * .pmd_fault is not supported for DAX because allocation in ext2 + * .huge_fault is not supported for DAX because allocation in ext2 * cannot be reliably aligned to huge page sizes and so pmd faults * will always fail and fail back to regular faults. */ diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index f073bfca694b..128cce540645 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -842,13 +842,13 @@ ext2_iomap_end(struct inode *inode, loff_t offset, loff_t length, return 0; } -struct iomap_ops ext2_iomap_ops = { +const struct iomap_ops ext2_iomap_ops = { .iomap_begin = ext2_iomap_begin, .iomap_end = ext2_iomap_end, }; #else /* Define empty ops for !CONFIG_FS_DAX case to avoid ugly ifdefs */ -struct iomap_ops ext2_iomap_ops; +const struct iomap_ops ext2_iomap_ops; #endif /* CONFIG_FS_DAX */ int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 01d52b98f9a7..2fd17e8e4984 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2483,8 +2483,8 @@ extern int ext4_writepage_trans_blocks(struct inode *); extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks); extern int ext4_zero_partial_blocks(handle_t *handle, struct inode *inode, loff_t lstart, loff_t lend); -extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf); -extern int ext4_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf); +extern int ext4_page_mkwrite(struct vm_fault *vmf); +extern int ext4_filemap_fault(struct vm_fault *vmf); extern qsize_t *ext4_get_reserved_space(struct inode *inode); extern int ext4_get_projid(struct inode *inode, kprojid_t *projid); extern void ext4_da_update_reserve_space(struct inode *inode, @@ -3244,7 +3244,7 @@ static inline void ext4_clear_io_unwritten_flag(ext4_io_end_t *io_end) } } -extern struct iomap_ops ext4_iomap_ops; +extern const struct iomap_ops ext4_iomap_ops; #endif /* __KERNEL__ */ diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c index 37e059202cd2..e7f12a204cbc 100644 --- a/fs/ext4/extents_status.c +++ b/fs/ext4/extents_status.c @@ -84,7 +84,7 @@ * -- writeout * Writeout looks up whole page cache to see if a buffer is * mapped, If there are not very many delayed buffers, then it is - * time comsuming. + * time consuming. * * With extent status tree implementation, FIEMAP, SEEK_HOLE/DATA, * bigalloc and writeout can figure out if a block or a range of diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 87e11dfe3cde..8210c1f43556 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -253,19 +253,20 @@ out: } #ifdef CONFIG_FS_DAX -static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf) +static int ext4_dax_huge_fault(struct vm_fault *vmf, + enum page_entry_size pe_size) { int result; - struct inode *inode = file_inode(vma->vm_file); + struct inode *inode = file_inode(vmf->vma->vm_file); struct super_block *sb = inode->i_sb; bool write = vmf->flags & FAULT_FLAG_WRITE; if (write) { sb_start_pagefault(sb); - file_update_time(vma->vm_file); + file_update_time(vmf->vma->vm_file); } down_read(&EXT4_I(inode)->i_mmap_sem); - result = dax_iomap_fault(vma, vmf, &ext4_iomap_ops); + result = dax_iomap_fault(vmf, pe_size, &ext4_iomap_ops); up_read(&EXT4_I(inode)->i_mmap_sem); if (write) sb_end_pagefault(sb); @@ -273,26 +274,9 @@ static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf) return result; } -static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr, - pmd_t *pmd, unsigned int flags) +static int ext4_dax_fault(struct vm_fault *vmf) { - int result; - struct inode *inode = file_inode(vma->vm_file); - struct super_block *sb = inode->i_sb; - bool write = flags & FAULT_FLAG_WRITE; - - if (write) { - sb_start_pagefault(sb); - file_update_time(vma->vm_file); - } - down_read(&EXT4_I(inode)->i_mmap_sem); - result = dax_iomap_pmd_fault(vma, addr, pmd, flags, - &ext4_iomap_ops); - up_read(&EXT4_I(inode)->i_mmap_sem); - if (write) - sb_end_pagefault(sb); - - return result; + return ext4_dax_huge_fault(vmf, PE_SIZE_PTE); } /* @@ -304,22 +288,21 @@ static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr, * wp_pfn_shared() fails. Thus fault gets retried and things work out as * desired. */ -static int ext4_dax_pfn_mkwrite(struct vm_area_struct *vma, - struct vm_fault *vmf) +static int ext4_dax_pfn_mkwrite(struct vm_fault *vmf) { - struct inode *inode = file_inode(vma->vm_file); + struct inode *inode = file_inode(vmf->vma->vm_file); struct super_block *sb = inode->i_sb; loff_t size; int ret; sb_start_pagefault(sb); - file_update_time(vma->vm_file); + file_update_time(vmf->vma->vm_file); down_read(&EXT4_I(inode)->i_mmap_sem); size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT; if (vmf->pgoff >= size) ret = VM_FAULT_SIGBUS; else - ret = dax_pfn_mkwrite(vma, vmf); + ret = dax_pfn_mkwrite(vmf); up_read(&EXT4_I(inode)->i_mmap_sem); sb_end_pagefault(sb); @@ -328,7 +311,7 @@ static int ext4_dax_pfn_mkwrite(struct vm_area_struct *vma, static const struct vm_operations_struct ext4_dax_vm_ops = { .fault = ext4_dax_fault, - .pmd_fault = ext4_dax_pmd_fault, + .huge_fault = ext4_dax_huge_fault, .page_mkwrite = ext4_dax_fault, .pfn_mkwrite = ext4_dax_pfn_mkwrite, }; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index f622d4a577e3..971f66342080 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2221,7 +2221,7 @@ static int mpage_process_page_bufs(struct mpage_da_data *mpd, { struct inode *inode = mpd->inode; int err; - ext4_lblk_t blocks = (i_size_read(inode) + (1 << inode->i_blkbits) - 1) + ext4_lblk_t blocks = (i_size_read(inode) + i_blocksize(inode) - 1) >> inode->i_blkbits; do { @@ -3450,7 +3450,7 @@ orphan_del: return ret; } -struct iomap_ops ext4_iomap_ops = { +const struct iomap_ops ext4_iomap_ops = { .iomap_begin = ext4_iomap_begin, .iomap_end = ext4_iomap_end, }; @@ -3577,7 +3577,7 @@ static ssize_t ext4_direct_IO_write(struct kiocb *iocb, struct iov_iter *iter) if (overwrite) get_block_func = ext4_dio_get_block_overwrite; else if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) || - round_down(offset, 1 << inode->i_blkbits) >= inode->i_size) { + round_down(offset, i_blocksize(inode)) >= inode->i_size) { get_block_func = ext4_dio_get_block; dio_flags = DIO_LOCKING | DIO_SKIP_HOLES; } else if (is_sync_kiocb(iocb)) { @@ -5179,7 +5179,7 @@ static void ext4_wait_for_tail_page_commit(struct inode *inode) * do. We do the check mainly to optimize the common PAGE_SIZE == * blocksize case */ - if (offset > PAGE_SIZE - (1 << inode->i_blkbits)) + if (offset > PAGE_SIZE - i_blocksize(inode)) return; while (1) { page = find_lock_page(inode->i_mapping, @@ -5821,8 +5821,9 @@ static int ext4_bh_unmapped(handle_t *handle, struct buffer_head *bh) return !buffer_mapped(bh); } -int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) +int ext4_page_mkwrite(struct vm_fault *vmf) { + struct vm_area_struct *vma = vmf->vma; struct page *page = vmf->page; loff_t size; unsigned long len; @@ -5912,13 +5913,13 @@ out: return ret; } -int ext4_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) +int ext4_filemap_fault(struct vm_fault *vmf) { - struct inode *inode = file_inode(vma->vm_file); + struct inode *inode = file_inode(vmf->vma->vm_file); int err; down_read(&EXT4_I(inode)->i_mmap_sem); - err = filemap_fault(vma, vmf); + err = filemap_fault(vmf); up_read(&EXT4_I(inode)->i_mmap_sem); return err; diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 10c62de642c6..354dc1a894c2 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -838,7 +838,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp) inode = page->mapping->host; sb = inode->i_sb; ngroups = ext4_get_groups_count(sb); - blocksize = 1 << inode->i_blkbits; + blocksize = i_blocksize(inode); blocks_per_page = PAGE_SIZE / blocksize; groups_per_page = blocks_per_page >> 1; diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index 6fc14def0c70..578f8c33fb44 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -187,7 +187,7 @@ mext_page_mkuptodate(struct page *page, unsigned from, unsigned to) if (PageUptodate(page)) return 0; - blocksize = 1 << inode->i_blkbits; + blocksize = i_blocksize(inode); if (!page_has_buffers(page)) create_empty_buffers(page, blocksize, 0); diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 49f10dce817d..1edc86e874e3 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -32,11 +32,10 @@ #include "trace.h" #include <trace/events/f2fs.h> -static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma, - struct vm_fault *vmf) +static int f2fs_vm_page_mkwrite(struct vm_fault *vmf) { struct page *page = vmf->page; - struct inode *inode = file_inode(vma->vm_file); + struct inode *inode = file_inode(vmf->vma->vm_file); struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct dnode_of_data dn; int err; @@ -58,7 +57,7 @@ static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma, f2fs_balance_fs(sbi, dn.node_changed); - file_update_time(vma->vm_file); + file_update_time(vmf->vma->vm_file); lock_page(page); if (unlikely(page->mapping != inode->i_mapping || page_offset(page) > i_size_read(inode) || diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 2401c5dabb2a..e80bfd06daf5 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -2043,12 +2043,12 @@ static void fuse_vma_close(struct vm_area_struct *vma) * - sync(2) * - try_to_free_pages() with order > PAGE_ALLOC_COSTLY_ORDER */ -static int fuse_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) +static int fuse_page_mkwrite(struct vm_fault *vmf) { struct page *page = vmf->page; - struct inode *inode = file_inode(vma->vm_file); + struct inode *inode = file_inode(vmf->vma->vm_file); - file_update_time(vma->vm_file); + file_update_time(vmf->vma->vm_file); lock_page(page); if (page->mapping != inode->i_mapping) { unlock_page(page); diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 6b039d7ce160..ed7a2e252ad8 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -143,8 +143,8 @@ static int gfs2_writepage(struct page *page, struct writeback_control *wbc) /* This is the same as calling block_write_full_page, but it also * writes pages outside of i_size */ -int gfs2_write_full_page(struct page *page, get_block_t *get_block, - struct writeback_control *wbc) +static int gfs2_write_full_page(struct page *page, get_block_t *get_block, + struct writeback_control *wbc) { struct inode * const inode = page->mapping->host; loff_t i_size = i_size_read(inode); diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index fc5da4cbe88c..01b97c012c6e 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -720,6 +720,7 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh, { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct gfs2_rgrp_list rlist; + struct gfs2_trans *tr; u64 bn, bstart; u32 blen, btotal; __be64 *p; @@ -728,6 +729,7 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh, unsigned int revokes = 0; int x; int error; + int jblocks_rqsted; error = gfs2_rindex_update(sdp); if (error) @@ -791,12 +793,17 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh, if (gfs2_rs_active(&ip->i_res)) /* needs to be done with the rgrp glock held */ gfs2_rs_deltree(&ip->i_res); - error = gfs2_trans_begin(sdp, rg_blocks + RES_DINODE + - RES_INDIRECT + RES_STATFS + RES_QUOTA, - revokes); +restart: + jblocks_rqsted = rg_blocks + RES_DINODE + + RES_INDIRECT + RES_STATFS + RES_QUOTA + + gfs2_struct2blk(sdp, revokes, sizeof(u64)); + if (jblocks_rqsted > atomic_read(&sdp->sd_log_thresh2)) + jblocks_rqsted = atomic_read(&sdp->sd_log_thresh2); + error = gfs2_trans_begin(sdp, jblocks_rqsted, revokes); if (error) goto out_rg_gunlock; + tr = current->journal_info; down_write(&ip->i_rw_mutex); gfs2_trans_add_meta(ip->i_gl, dibh); @@ -810,6 +817,16 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh, if (!*p) continue; + /* check for max reasonable journal transaction blocks */ + if (tr->tr_num_buf_new + RES_STATFS + + RES_QUOTA >= atomic_read(&sdp->sd_log_thresh2)) { + if (rg_blocks >= tr->tr_num_buf_new) + rg_blocks -= tr->tr_num_buf_new; + else + rg_blocks = 0; + break; + } + bn = be64_to_cpu(*p); if (bstart + blen == bn) @@ -827,6 +844,9 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh, *p = 0; gfs2_add_inode_blocks(&ip->i_inode, -1); } + if (p == bottom) + rg_blocks = 0; + if (bstart) { __gfs2_free_blocks(ip, bstart, blen, metadata); btotal += blen; @@ -844,6 +864,9 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh, gfs2_trans_end(sdp); + if (rg_blocks) + goto restart; + out_rg_gunlock: gfs2_glock_dq_m(rlist.rl_rgrps, rlist.rl_ghs); out_rlist: diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 016c11eaca7c..6fe2a59c6a9a 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -379,10 +379,10 @@ static int gfs2_allocate_page_backing(struct page *page) * blocks allocated on disk to back that page. */ -static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) +static int gfs2_page_mkwrite(struct vm_fault *vmf) { struct page *page = vmf->page; - struct inode *inode = file_inode(vma->vm_file); + struct inode *inode = file_inode(vmf->vma->vm_file); struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_sbd *sdp = GFS2_SB(inode); struct gfs2_alloc_parms ap = { .aflags = 0, }; @@ -399,7 +399,7 @@ static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) if (ret) goto out; - gfs2_size_hint(vma->vm_file, pos, PAGE_SIZE); + gfs2_size_hint(vmf->vma->vm_file, pos, PAGE_SIZE); gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh); ret = gfs2_glock_nq(&gh); @@ -407,7 +407,7 @@ static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) goto out_uninit; /* Update file times before taking page lock */ - file_update_time(vma->vm_file); + file_update_time(vmf->vma->vm_file); set_bit(GLF_DIRTY, &ip->i_gl->gl_flags); set_bit(GIF_SW_PAGED, &ip->i_flags); diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 94f50cac91c6..ec0848fcca02 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -658,9 +658,11 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number, struct kmem_cache *cachep; int ret, tries = 0; + rcu_read_lock(); gl = rhashtable_lookup_fast(&gl_hash_table, &name, ht_parms); if (gl && !lockref_get_not_dead(&gl->gl_lockref)) gl = NULL; + rcu_read_unlock(); *glp = gl; if (gl) @@ -728,15 +730,18 @@ again: if (ret == -EEXIST) { ret = 0; + rcu_read_lock(); tmp = rhashtable_lookup_fast(&gl_hash_table, &name, ht_parms); if (tmp == NULL || !lockref_get_not_dead(&tmp->gl_lockref)) { if (++tries < 100) { + rcu_read_unlock(); cond_resched(); goto again; } tmp = NULL; ret = -ENOMEM; } + rcu_read_unlock(); } else { WARN_ON_ONCE(ret); } @@ -1420,26 +1425,32 @@ static struct shrinker glock_shrinker = { * @sdp: the filesystem * @bucket: the bucket * + * Note that the function can be called multiple times on the same + * object. So the user must ensure that the function can cope with + * that. */ static void glock_hash_walk(glock_examiner examiner, const struct gfs2_sbd *sdp) { struct gfs2_glock *gl; - struct rhash_head *pos; - const struct bucket_table *tbl; - int i; + struct rhashtable_iter iter; - rcu_read_lock(); - tbl = rht_dereference_rcu(gl_hash_table.tbl, &gl_hash_table); - for (i = 0; i < tbl->size; i++) { - rht_for_each_entry_rcu(gl, pos, tbl, i, gl_node) { + rhashtable_walk_enter(&gl_hash_table, &iter); + + do { + gl = ERR_PTR(rhashtable_walk_start(&iter)); + if (gl) + continue; + + while ((gl = rhashtable_walk_next(&iter)) && !IS_ERR(gl)) if ((gl->gl_name.ln_sbd == sdp) && lockref_get_not_dead(&gl->gl_lockref)) examiner(gl); - } - } - rcu_read_unlock(); - cond_resched(); + + rhashtable_walk_stop(&iter); + } while (cond_resched(), gl == ERR_PTR(-EAGAIN)); + + rhashtable_walk_exit(&iter); } /** @@ -1802,16 +1813,18 @@ void gfs2_glock_exit(void) static void gfs2_glock_iter_next(struct gfs2_glock_iter *gi) { - do { - gi->gl = rhashtable_walk_next(&gi->hti); + while ((gi->gl = rhashtable_walk_next(&gi->hti))) { if (IS_ERR(gi->gl)) { if (PTR_ERR(gi->gl) == -EAGAIN) continue; gi->gl = NULL; + return; } - /* Skip entries for other sb and dead entries */ - } while ((gi->gl) && ((gi->sdp != gi->gl->gl_name.ln_sbd) || - __lockref_is_dead(&gi->gl->gl_lockref))); + /* Skip entries for other sb and dead entries */ + if (gi->sdp == gi->gl->gl_name.ln_sbd && + !__lockref_is_dead(&gi->gl->gl_lockref)) + return; + } } static void *gfs2_glock_seq_start(struct seq_file *seq, loff_t *pos) diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h index a6a3389a07fc..c45084ac642d 100644 --- a/fs/gfs2/incore.h +++ b/fs/gfs2/incore.h @@ -470,15 +470,19 @@ struct gfs2_quota_data { struct rcu_head qd_rcu; }; +enum { + TR_TOUCHED = 1, + TR_ATTACHED = 2, + TR_ALLOCED = 3, +}; + struct gfs2_trans { unsigned long tr_ip; unsigned int tr_blocks; unsigned int tr_revokes; unsigned int tr_reserved; - unsigned int tr_touched:1; - unsigned int tr_attached:1; - unsigned int tr_alloced:1; + unsigned long tr_flags; unsigned int tr_num_buf_new; unsigned int tr_num_databuf_new; @@ -794,6 +798,7 @@ struct gfs2_sbd { atomic_t sd_log_thresh1; atomic_t sd_log_thresh2; atomic_t sd_log_blks_free; + atomic_t sd_log_blks_needed; wait_queue_head_t sd_log_waitq; wait_queue_head_t sd_logd_waitq; diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 27c00a16def0..f865b96374df 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -349,6 +349,7 @@ int gfs2_log_reserve(struct gfs2_sbd *sdp, unsigned int blks) if (gfs2_assert_warn(sdp, blks) || gfs2_assert_warn(sdp, blks <= sdp->sd_jdesc->jd_blocks)) return -EINVAL; + atomic_add(blks, &sdp->sd_log_blks_needed); retry: free_blocks = atomic_read(&sdp->sd_log_blks_free); if (unlikely(free_blocks <= wanted)) { @@ -370,6 +371,7 @@ retry: wake_up(&sdp->sd_reserving_log_wait); goto retry; } + atomic_sub(blks, &sdp->sd_log_blks_needed); trace_gfs2_log_blocks(sdp, -blks); /* @@ -797,7 +799,7 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, static void gfs2_merge_trans(struct gfs2_trans *old, struct gfs2_trans *new) { - WARN_ON_ONCE(old->tr_attached != 1); + WARN_ON_ONCE(!test_bit(TR_ATTACHED, &old->tr_flags)); old->tr_num_buf_new += new->tr_num_buf_new; old->tr_num_databuf_new += new->tr_num_databuf_new; @@ -821,9 +823,9 @@ static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr) if (sdp->sd_log_tr) { gfs2_merge_trans(sdp->sd_log_tr, tr); } else if (tr->tr_num_buf_new || tr->tr_num_databuf_new) { - gfs2_assert_withdraw(sdp, tr->tr_alloced); + gfs2_assert_withdraw(sdp, test_bit(TR_ALLOCED, &tr->tr_flags)); sdp->sd_log_tr = tr; - tr->tr_attached = 1; + set_bit(TR_ATTACHED, &tr->tr_flags); } sdp->sd_log_commited_revoke += tr->tr_num_revoke - tr->tr_num_revoke_rm; @@ -891,13 +893,16 @@ void gfs2_log_shutdown(struct gfs2_sbd *sdp) static inline int gfs2_jrnl_flush_reqd(struct gfs2_sbd *sdp) { - return (atomic_read(&sdp->sd_log_pinned) >= atomic_read(&sdp->sd_log_thresh1)); + return (atomic_read(&sdp->sd_log_pinned) + + atomic_read(&sdp->sd_log_blks_needed) >= + atomic_read(&sdp->sd_log_thresh1)); } static inline int gfs2_ail_flush_reqd(struct gfs2_sbd *sdp) { unsigned int used_blocks = sdp->sd_jdesc->jd_blocks - atomic_read(&sdp->sd_log_blks_free); - return used_blocks >= atomic_read(&sdp->sd_log_thresh2); + return used_blocks + atomic_read(&sdp->sd_log_blks_needed) >= + atomic_read(&sdp->sd_log_thresh2); } /** @@ -913,12 +918,15 @@ int gfs2_logd(void *data) struct gfs2_sbd *sdp = data; unsigned long t = 1; DEFINE_WAIT(wait); + bool did_flush; while (!kthread_should_stop()) { + did_flush = false; if (gfs2_jrnl_flush_reqd(sdp) || t == 0) { gfs2_ail1_empty(sdp); gfs2_log_flush(sdp, NULL, NORMAL_FLUSH); + did_flush = true; } if (gfs2_ail_flush_reqd(sdp)) { @@ -926,9 +934,10 @@ int gfs2_logd(void *data) gfs2_ail1_wait(sdp); gfs2_ail1_empty(sdp); gfs2_log_flush(sdp, NULL, NORMAL_FLUSH); + did_flush = true; } - if (!gfs2_ail_flush_reqd(sdp)) + if (!gfs2_ail_flush_reqd(sdp) || did_flush) wake_up(&sdp->sd_log_waitq); t = gfs2_tune_get(sdp, gt_logd_secs) * HZ; diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index 49db8ef13fdf..663ffc135ef3 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -292,7 +292,7 @@ int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags, wait_on_buffer(bh); if (unlikely(!buffer_uptodate(bh))) { struct gfs2_trans *tr = current->journal_info; - if (tr && tr->tr_touched) + if (tr && test_bit(TR_TOUCHED, &tr->tr_flags)) gfs2_io_error_bh(sdp, bh); brelse(bh); *bhp = NULL; @@ -319,7 +319,7 @@ int gfs2_meta_wait(struct gfs2_sbd *sdp, struct buffer_head *bh) if (!buffer_uptodate(bh)) { struct gfs2_trans *tr = current->journal_info; - if (tr && tr->tr_touched) + if (tr && test_bit(TR_TOUCHED, &tr->tr_flags)) gfs2_io_error_bh(sdp, bh); return -EIO; } @@ -345,7 +345,7 @@ void gfs2_remove_from_journal(struct buffer_head *bh, int meta) tr->tr_num_buf_rm++; else tr->tr_num_databuf_rm++; - tr->tr_touched = 1; + set_bit(TR_TOUCHED, &tr->tr_flags); was_pinned = 1; brelse(bh); } diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index a34308df927f..b108e7ba81af 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -683,6 +683,7 @@ static int init_journal(struct gfs2_sbd *sdp, int undo) goto fail_jindex; } + atomic_set(&sdp->sd_log_blks_needed, 0); if (sdp->sd_args.ar_spectator) { sdp->sd_jdesc = gfs2_jdesc_find(sdp, 0); atomic_set(&sdp->sd_log_blks_free, sdp->sd_jdesc->jd_blocks); @@ -1226,7 +1227,7 @@ static int set_gfs2_super(struct super_block *s, void *data) * We set the bdi here to the queue backing, file systems can * overwrite this in ->fill_super() */ - s->s_bdi = &bdev_get_queue(s->s_bdev)->backing_dev_info; + s->s_bdi = bdev_get_queue(s->s_bdev)->backing_dev_info; return 0; } diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c index 0c1bde395062..affef3c066e0 100644 --- a/fs/gfs2/trans.c +++ b/fs/gfs2/trans.c @@ -48,7 +48,7 @@ int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks, tr->tr_blocks = blocks; tr->tr_revokes = revokes; tr->tr_reserved = 1; - tr->tr_alloced = 1; + set_bit(TR_ALLOCED, &tr->tr_flags); if (blocks) tr->tr_reserved += 6 + blocks; if (revokes) @@ -78,7 +78,8 @@ static void gfs2_print_trans(const struct gfs2_trans *tr) { pr_warn("Transaction created at: %pSR\n", (void *)tr->tr_ip); pr_warn("blocks=%u revokes=%u reserved=%u touched=%u\n", - tr->tr_blocks, tr->tr_revokes, tr->tr_reserved, tr->tr_touched); + tr->tr_blocks, tr->tr_revokes, tr->tr_reserved, + test_bit(TR_TOUCHED, &tr->tr_flags)); pr_warn("Buf %u/%u Databuf %u/%u Revoke %u/%u\n", tr->tr_num_buf_new, tr->tr_num_buf_rm, tr->tr_num_databuf_new, tr->tr_num_databuf_rm, @@ -89,12 +90,12 @@ void gfs2_trans_end(struct gfs2_sbd *sdp) { struct gfs2_trans *tr = current->journal_info; s64 nbuf; - int alloced = tr->tr_alloced; + int alloced = test_bit(TR_ALLOCED, &tr->tr_flags); BUG_ON(!tr); current->journal_info = NULL; - if (!tr->tr_touched) { + if (!test_bit(TR_TOUCHED, &tr->tr_flags)) { gfs2_log_release(sdp, tr->tr_reserved); if (alloced) { kfree(tr); @@ -112,8 +113,8 @@ void gfs2_trans_end(struct gfs2_sbd *sdp) gfs2_print_trans(tr); gfs2_log_commit(sdp, tr); - if (alloced && !tr->tr_attached) - kfree(tr); + if (alloced && !test_bit(TR_ATTACHED, &tr->tr_flags)) + kfree(tr); up_read(&sdp->sd_log_flush_lock); if (sdp->sd_vfs->s_flags & MS_SYNCHRONOUS) @@ -169,6 +170,10 @@ void gfs2_trans_add_data(struct gfs2_glock *gl, struct buffer_head *bh) } lock_buffer(bh); + if (buffer_pinned(bh)) { + set_bit(TR_TOUCHED, &tr->tr_flags); + goto out; + } gfs2_log_lock(sdp); bd = bh->b_private; if (bd == NULL) { @@ -182,7 +187,7 @@ void gfs2_trans_add_data(struct gfs2_glock *gl, struct buffer_head *bh) gfs2_log_lock(sdp); } gfs2_assert(sdp, bd->bd_gl == gl); - tr->tr_touched = 1; + set_bit(TR_TOUCHED, &tr->tr_flags); if (list_empty(&bd->bd_list)) { set_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags); set_bit(GLF_DIRTY, &bd->bd_gl->gl_flags); @@ -191,45 +196,24 @@ void gfs2_trans_add_data(struct gfs2_glock *gl, struct buffer_head *bh) list_add_tail(&bd->bd_list, &tr->tr_databuf); } gfs2_log_unlock(sdp); +out: unlock_buffer(bh); } -static void meta_lo_add(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd) -{ - struct gfs2_meta_header *mh; - struct gfs2_trans *tr; - enum gfs2_freeze_state state = atomic_read(&sdp->sd_freeze_state); - - tr = current->journal_info; - tr->tr_touched = 1; - if (!list_empty(&bd->bd_list)) - return; - set_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags); - set_bit(GLF_DIRTY, &bd->bd_gl->gl_flags); - mh = (struct gfs2_meta_header *)bd->bd_bh->b_data; - if (unlikely(mh->mh_magic != cpu_to_be32(GFS2_MAGIC))) { - pr_err("Attempting to add uninitialised block to journal (inplace block=%lld)\n", - (unsigned long long)bd->bd_bh->b_blocknr); - BUG(); - } - if (unlikely(state == SFS_FROZEN)) { - printk(KERN_INFO "GFS2:adding buf while frozen\n"); - gfs2_assert_withdraw(sdp, 0); - } - gfs2_pin(sdp, bd->bd_bh); - mh->__pad0 = cpu_to_be64(0); - mh->mh_jid = cpu_to_be32(sdp->sd_jdesc->jd_jid); - list_add(&bd->bd_list, &tr->tr_buf); - tr->tr_num_buf_new++; -} - void gfs2_trans_add_meta(struct gfs2_glock *gl, struct buffer_head *bh) { struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; struct gfs2_bufdata *bd; + struct gfs2_meta_header *mh; + struct gfs2_trans *tr = current->journal_info; + enum gfs2_freeze_state state = atomic_read(&sdp->sd_freeze_state); lock_buffer(bh); + if (buffer_pinned(bh)) { + set_bit(TR_TOUCHED, &tr->tr_flags); + goto out; + } gfs2_log_lock(sdp); bd = bh->b_private; if (bd == NULL) { @@ -245,8 +229,29 @@ void gfs2_trans_add_meta(struct gfs2_glock *gl, struct buffer_head *bh) gfs2_log_lock(sdp); } gfs2_assert(sdp, bd->bd_gl == gl); - meta_lo_add(sdp, bd); + set_bit(TR_TOUCHED, &tr->tr_flags); + if (!list_empty(&bd->bd_list)) + goto out_unlock; + set_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags); + set_bit(GLF_DIRTY, &bd->bd_gl->gl_flags); + mh = (struct gfs2_meta_header *)bd->bd_bh->b_data; + if (unlikely(mh->mh_magic != cpu_to_be32(GFS2_MAGIC))) { + pr_err("Attempting to add uninitialised block to journal (inplace block=%lld)\n", + (unsigned long long)bd->bd_bh->b_blocknr); + BUG(); + } + if (unlikely(state == SFS_FROZEN)) { + printk(KERN_INFO "GFS2:adding buf while frozen\n"); + gfs2_assert_withdraw(sdp, 0); + } + gfs2_pin(sdp, bd->bd_bh); + mh->__pad0 = cpu_to_be64(0); + mh->mh_jid = cpu_to_be32(sdp->sd_jdesc->jd_jid); + list_add(&bd->bd_list, &tr->tr_buf); + tr->tr_num_buf_new++; +out_unlock: gfs2_log_unlock(sdp); +out: unlock_buffer(bh); } @@ -256,7 +261,7 @@ void gfs2_trans_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd) BUG_ON(!list_empty(&bd->bd_list)); gfs2_add_revoke(sdp, bd); - tr->tr_touched = 1; + set_bit(TR_TOUCHED, &tr->tr_flags); tr->tr_num_revoke++; } diff --git a/fs/hfs/mdb.c b/fs/hfs/mdb.c index a3ec3ae7d347..482081bcdf70 100644 --- a/fs/hfs/mdb.c +++ b/fs/hfs/mdb.c @@ -38,7 +38,7 @@ static int hfs_get_last_session(struct super_block *sb, /* default values */ *start = 0; - *size = sb->s_bdev->bd_inode->i_size >> 9; + *size = i_size_read(sb->s_bdev->bd_inode) >> 9; if (HFS_SB(sb)->session >= 0) { te.cdte_track = HFS_SB(sb)->session; diff --git a/fs/hfsplus/wrapper.c b/fs/hfsplus/wrapper.c index ebb85e5f6549..e254fa0f0697 100644 --- a/fs/hfsplus/wrapper.c +++ b/fs/hfsplus/wrapper.c @@ -132,7 +132,7 @@ static int hfsplus_get_last_session(struct super_block *sb, /* default values */ *start = 0; - *size = sb->s_bdev->bd_inode->i_size >> 9; + *size = i_size_read(sb->s_bdev->bd_inode) >> 9; if (HFSPLUS_SB(sb)->session >= 0) { te.cdte_track = HFSPLUS_SB(sb)->session; diff --git a/fs/internal.h b/fs/internal.h index b63cf3af2dc2..11c6d89dce9c 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -182,7 +182,7 @@ typedef loff_t (*iomap_actor_t)(struct inode *inode, loff_t pos, loff_t len, void *data, struct iomap *iomap); loff_t iomap_apply(struct inode *inode, loff_t pos, loff_t length, - unsigned flags, struct iomap_ops *ops, void *data, + unsigned flags, const struct iomap_ops *ops, void *data, iomap_actor_t actor); /* direct-io.c: */ diff --git a/fs/iomap.c b/fs/iomap.c index a51cb4c07d4d..0f85f2410605 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -41,7 +41,7 @@ */ loff_t iomap_apply(struct inode *inode, loff_t pos, loff_t length, unsigned flags, - struct iomap_ops *ops, void *data, iomap_actor_t actor) + const struct iomap_ops *ops, void *data, iomap_actor_t actor) { struct iomap iomap = { 0 }; loff_t written = 0, ret; @@ -235,7 +235,7 @@ again: ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *iter, - struct iomap_ops *ops) + const struct iomap_ops *ops) { struct inode *inode = iocb->ki_filp->f_mapping->host; loff_t pos = iocb->ki_pos, ret = 0, written = 0; @@ -318,7 +318,7 @@ iomap_dirty_actor(struct inode *inode, loff_t pos, loff_t length, void *data, int iomap_file_dirty(struct inode *inode, loff_t pos, loff_t len, - struct iomap_ops *ops) + const struct iomap_ops *ops) { loff_t ret; @@ -398,7 +398,7 @@ iomap_zero_range_actor(struct inode *inode, loff_t pos, loff_t count, int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, - struct iomap_ops *ops) + const struct iomap_ops *ops) { loff_t ret; @@ -418,10 +418,10 @@ EXPORT_SYMBOL_GPL(iomap_zero_range); int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, - struct iomap_ops *ops) + const struct iomap_ops *ops) { - unsigned blocksize = (1 << inode->i_blkbits); - unsigned off = pos & (blocksize - 1); + unsigned int blocksize = i_blocksize(inode); + unsigned int off = pos & (blocksize - 1); /* Block boundary? Nothing to do */ if (!off) @@ -445,11 +445,10 @@ iomap_page_mkwrite_actor(struct inode *inode, loff_t pos, loff_t length, return length; } -int iomap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, - struct iomap_ops *ops) +int iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops) { struct page *page = vmf->page; - struct inode *inode = file_inode(vma->vm_file); + struct inode *inode = file_inode(vmf->vma->vm_file); unsigned long length; loff_t offset, size; ssize_t ret; @@ -545,7 +544,7 @@ iomap_fiemap_actor(struct inode *inode, loff_t pos, loff_t length, void *data, } int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fi, - loff_t start, loff_t len, struct iomap_ops *ops) + loff_t start, loff_t len, const struct iomap_ops *ops) { struct fiemap_ctx ctx; loff_t ret; @@ -736,9 +735,9 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length, void *data, struct iomap *iomap) { struct iomap_dio *dio = data; - unsigned blkbits = blksize_bits(bdev_logical_block_size(iomap->bdev)); - unsigned fs_block_size = (1 << inode->i_blkbits), pad; - unsigned align = iov_iter_alignment(dio->submit.iter); + unsigned int blkbits = blksize_bits(bdev_logical_block_size(iomap->bdev)); + unsigned int fs_block_size = i_blocksize(inode), pad; + unsigned int align = iov_iter_alignment(dio->submit.iter); struct iov_iter iter; struct bio *bio; bool need_zeroout = false; @@ -839,8 +838,8 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length, } ssize_t -iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, struct iomap_ops *ops, - iomap_dio_end_io_t end_io) +iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, + const struct iomap_ops *ops, iomap_dio_end_io_t end_io) { struct address_space *mapping = iocb->ki_filp->f_mapping; struct inode *inode = file_inode(iocb->ki_filp); diff --git a/fs/jfs/super.c b/fs/jfs/super.c index 2be7c9ce6663..c64c2574a0aa 100644 --- a/fs/jfs/super.c +++ b/fs/jfs/super.c @@ -758,7 +758,7 @@ static ssize_t jfs_quota_read(struct super_block *sb, int type, char *data, sb->s_blocksize - offset : toread; tmp_bh.b_state = 0; - tmp_bh.b_size = 1 << inode->i_blkbits; + tmp_bh.b_size = i_blocksize(inode); err = jfs_get_block(inode, blk, &tmp_bh, 0); if (err) return err; @@ -798,7 +798,7 @@ static ssize_t jfs_quota_write(struct super_block *sb, int type, sb->s_blocksize - offset : towrite; tmp_bh.b_state = 0; - tmp_bh.b_size = 1 << inode->i_blkbits; + tmp_bh.b_size = i_blocksize(inode); err = jfs_get_block(inode, blk, &tmp_bh, 1); if (err) goto out; diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index cf4c636ff4da..db5900aaa55a 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -41,6 +41,9 @@ static bool kernfs_lockdep(struct kernfs_node *kn) static int kernfs_name_locked(struct kernfs_node *kn, char *buf, size_t buflen) { + if (!kn) + return strlcpy(buf, "(null)", buflen); + return strlcpy(buf, kn->parent ? kn->name : "/", buflen); } @@ -110,6 +113,8 @@ static struct kernfs_node *kernfs_common_ancestor(struct kernfs_node *a, * kn_to: /n1/n2/n3 [depth=3] * result: /../.. * + * [3] when @kn_to is NULL result will be "(null)" + * * Returns the length of the full path. If the full length is equal to or * greater than @buflen, @buf contains the truncated path with the trailing * '\0'. On error, -errno is returned. @@ -123,6 +128,9 @@ static int kernfs_path_from_node_locked(struct kernfs_node *kn_to, size_t depth_from, depth_to, len = 0; int i, j; + if (!kn_to) + return strlcpy(buf, "(null)", buflen); + if (!kn_from) kn_from = kernfs_root(kn_to)->kn; @@ -166,6 +174,8 @@ static int kernfs_path_from_node_locked(struct kernfs_node *kn_to, * similar to strlcpy(). It returns the length of @kn's name and if @buf * isn't long enough, it's filled upto @buflen-1 and nul terminated. * + * Fills buffer with "(null)" if @kn is NULL. + * * This function can be called from any context. */ int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen) @@ -468,7 +478,7 @@ static void kernfs_drain(struct kernfs_node *kn) rwsem_release(&kn->dep_map, 1, _RET_IP_); } - kernfs_unmap_bin_file(kn); + kernfs_drain_open_files(kn); mutex_lock(&kernfs_mutex); } diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index 78219d5644e9..35043a8c4529 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -348,9 +348,9 @@ static void kernfs_vma_open(struct vm_area_struct *vma) kernfs_put_active(of->kn); } -static int kernfs_vma_fault(struct vm_area_struct *vma, struct vm_fault *vmf) +static int kernfs_vma_fault(struct vm_fault *vmf) { - struct file *file = vma->vm_file; + struct file *file = vmf->vma->vm_file; struct kernfs_open_file *of = kernfs_of(file); int ret; @@ -362,16 +362,15 @@ static int kernfs_vma_fault(struct vm_area_struct *vma, struct vm_fault *vmf) ret = VM_FAULT_SIGBUS; if (of->vm_ops->fault) - ret = of->vm_ops->fault(vma, vmf); + ret = of->vm_ops->fault(vmf); kernfs_put_active(of->kn); return ret; } -static int kernfs_vma_page_mkwrite(struct vm_area_struct *vma, - struct vm_fault *vmf) +static int kernfs_vma_page_mkwrite(struct vm_fault *vmf) { - struct file *file = vma->vm_file; + struct file *file = vmf->vma->vm_file; struct kernfs_open_file *of = kernfs_of(file); int ret; @@ -383,7 +382,7 @@ static int kernfs_vma_page_mkwrite(struct vm_area_struct *vma, ret = 0; if (of->vm_ops->page_mkwrite) - ret = of->vm_ops->page_mkwrite(vma, vmf); + ret = of->vm_ops->page_mkwrite(vmf); else file_update_time(file); @@ -516,7 +515,7 @@ static int kernfs_fop_mmap(struct file *file, struct vm_area_struct *vma) goto out_put; rc = 0; - of->mmapped = 1; + of->mmapped = true; of->vm_ops = vma->vm_ops; vma->vm_ops = &kernfs_vm_ops; out_put: @@ -708,7 +707,8 @@ static int kernfs_fop_open(struct inode *inode, struct file *file) if (error) goto err_free; - ((struct seq_file *)file->private_data)->private = of; + of->seq_file = file->private_data; + of->seq_file->private = of; /* seq_file clears PWRITE unconditionally, restore it if WRITE */ if (file->f_mode & FMODE_WRITE) @@ -717,13 +717,22 @@ static int kernfs_fop_open(struct inode *inode, struct file *file) /* make sure we have open node struct */ error = kernfs_get_open_node(kn, of); if (error) - goto err_close; + goto err_seq_release; + + if (ops->open) { + /* nobody has access to @of yet, skip @of->mutex */ + error = ops->open(of); + if (error) + goto err_put_node; + } /* open succeeded, put active references */ kernfs_put_active(kn); return 0; -err_close: +err_put_node: + kernfs_put_open_node(kn, of); +err_seq_release: seq_release(inode, file); err_free: kfree(of->prealloc_buf); @@ -733,11 +742,41 @@ err_out: return error; } +/* used from release/drain to ensure that ->release() is called exactly once */ +static void kernfs_release_file(struct kernfs_node *kn, + struct kernfs_open_file *of) +{ + /* + * @of is guaranteed to have no other file operations in flight and + * we just want to synchronize release and drain paths. + * @kernfs_open_file_mutex is enough. @of->mutex can't be used + * here because drain path may be called from places which can + * cause circular dependency. + */ + lockdep_assert_held(&kernfs_open_file_mutex); + + if (!of->released) { + /* + * A file is never detached without being released and we + * need to be able to release files which are deactivated + * and being drained. Don't use kernfs_ops(). + */ + kn->attr.ops->release(of); + of->released = true; + } +} + static int kernfs_fop_release(struct inode *inode, struct file *filp) { struct kernfs_node *kn = filp->f_path.dentry->d_fsdata; struct kernfs_open_file *of = kernfs_of(filp); + if (kn->flags & KERNFS_HAS_RELEASE) { + mutex_lock(&kernfs_open_file_mutex); + kernfs_release_file(kn, of); + mutex_unlock(&kernfs_open_file_mutex); + } + kernfs_put_open_node(kn, of); seq_release(inode, filp); kfree(of->prealloc_buf); @@ -746,12 +785,12 @@ static int kernfs_fop_release(struct inode *inode, struct file *filp) return 0; } -void kernfs_unmap_bin_file(struct kernfs_node *kn) +void kernfs_drain_open_files(struct kernfs_node *kn) { struct kernfs_open_node *on; struct kernfs_open_file *of; - if (!(kn->flags & KERNFS_HAS_MMAP)) + if (!(kn->flags & (KERNFS_HAS_MMAP | KERNFS_HAS_RELEASE))) return; spin_lock_irq(&kernfs_open_node_lock); @@ -763,10 +802,16 @@ void kernfs_unmap_bin_file(struct kernfs_node *kn) return; mutex_lock(&kernfs_open_file_mutex); + list_for_each_entry(of, &on->files, list) { struct inode *inode = file_inode(of->file); - unmap_mapping_range(inode->i_mapping, 0, 0, 1); + + if (kn->flags & KERNFS_HAS_MMAP) + unmap_mapping_range(inode->i_mapping, 0, 0, 1); + + kernfs_release_file(kn, of); } + mutex_unlock(&kernfs_open_file_mutex); kernfs_put_open_node(kn, NULL); @@ -965,6 +1010,8 @@ struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent, kn->flags |= KERNFS_HAS_SEQ_SHOW; if (ops->mmap) kn->flags |= KERNFS_HAS_MMAP; + if (ops->release) + kn->flags |= KERNFS_HAS_RELEASE; rc = kernfs_add_one(kn); if (rc) { diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h index bfd551bbf231..3100987cf8ba 100644 --- a/fs/kernfs/kernfs-internal.h +++ b/fs/kernfs/kernfs-internal.h @@ -104,7 +104,7 @@ struct kernfs_node *kernfs_new_node(struct kernfs_node *parent, */ extern const struct file_operations kernfs_file_fops; -void kernfs_unmap_bin_file(struct kernfs_node *kn); +void kernfs_drain_open_files(struct kernfs_node *kn); /* * symlink.c diff --git a/fs/mount.h b/fs/mount.h index 2c856fc47ae3..2826543a131d 100644 --- a/fs/mount.h +++ b/fs/mount.h @@ -89,7 +89,6 @@ static inline int is_mounted(struct vfsmount *mnt) } extern struct mount *__lookup_mnt(struct vfsmount *, struct dentry *); -extern struct mount *__lookup_mnt_last(struct vfsmount *, struct dentry *); extern int __legitimize_mnt(struct vfsmount *, unsigned); extern bool legitimize_mnt(struct vfsmount *, unsigned); diff --git a/fs/mpage.c b/fs/mpage.c index 28af984a3d96..baff8f820c29 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -115,7 +115,7 @@ map_buffer_to_page(struct page *page, struct buffer_head *bh, int page_block) SetPageUptodate(page); return; } - create_empty_buffers(page, 1 << inode->i_blkbits, 0); + create_empty_buffers(page, i_blocksize(inode), 0); } head = page_buffers(page); page_bh = head; diff --git a/fs/namei.c b/fs/namei.c index ad74877e1442..da689c9c005e 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1100,7 +1100,6 @@ static int follow_automount(struct path *path, struct nameidata *nd, bool *need_mntput) { struct vfsmount *mnt; - const struct cred *old_cred; int err; if (!path->dentry->d_op || !path->dentry->d_op->d_automount) @@ -1129,9 +1128,7 @@ static int follow_automount(struct path *path, struct nameidata *nd, if (nd->total_link_count >= 40) return -ELOOP; - old_cred = override_creds(&init_cred); mnt = path->dentry->d_op->d_automount(path); - revert_creds(old_cred); if (IS_ERR(mnt)) { /* * The filesystem is allowed to return -EISDIR here to indicate @@ -2941,10 +2938,16 @@ static inline int open_to_namei_flags(int flag) static int may_o_create(const struct path *dir, struct dentry *dentry, umode_t mode) { + struct user_namespace *s_user_ns; int error = security_path_mknod(dir, dentry, mode, 0); if (error) return error; + s_user_ns = dir->dentry->d_sb->s_user_ns; + if (!kuid_has_mapping(s_user_ns, current_fsuid()) || + !kgid_has_mapping(s_user_ns, current_fsgid())) + return -EOVERFLOW; + error = inode_permission(dir->dentry->d_inode, MAY_WRITE | MAY_EXEC); if (error) return error; diff --git a/fs/namespace.c b/fs/namespace.c index 487ba30bb5c6..8bfad42c1ccf 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -637,28 +637,6 @@ struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry) } /* - * find the last mount at @dentry on vfsmount @mnt. - * mount_lock must be held. - */ -struct mount *__lookup_mnt_last(struct vfsmount *mnt, struct dentry *dentry) -{ - struct mount *p, *res = NULL; - p = __lookup_mnt(mnt, dentry); - if (!p) - goto out; - if (!(p->mnt.mnt_flags & MNT_UMOUNT)) - res = p; - hlist_for_each_entry_continue(p, mnt_hash) { - if (&p->mnt_parent->mnt != mnt || p->mnt_mountpoint != dentry) - break; - if (!(p->mnt.mnt_flags & MNT_UMOUNT)) - res = p; - } -out: - return res; -} - -/* * lookup_mnt - Return the first child mount mounted at path * * "First" means first mounted chronologically. If you create the @@ -878,6 +856,13 @@ void mnt_set_mountpoint(struct mount *mnt, hlist_add_head(&child_mnt->mnt_mp_list, &mp->m_list); } +static void __attach_mnt(struct mount *mnt, struct mount *parent) +{ + hlist_add_head_rcu(&mnt->mnt_hash, + m_hash(&parent->mnt, mnt->mnt_mountpoint)); + list_add_tail(&mnt->mnt_child, &parent->mnt_mounts); +} + /* * vfsmount lock must be held for write */ @@ -886,28 +871,45 @@ static void attach_mnt(struct mount *mnt, struct mountpoint *mp) { mnt_set_mountpoint(parent, mp, mnt); - hlist_add_head_rcu(&mnt->mnt_hash, m_hash(&parent->mnt, mp->m_dentry)); - list_add_tail(&mnt->mnt_child, &parent->mnt_mounts); + __attach_mnt(mnt, parent); } -static void attach_shadowed(struct mount *mnt, - struct mount *parent, - struct mount *shadows) +void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp, struct mount *mnt) { - if (shadows) { - hlist_add_behind_rcu(&mnt->mnt_hash, &shadows->mnt_hash); - list_add(&mnt->mnt_child, &shadows->mnt_child); - } else { - hlist_add_head_rcu(&mnt->mnt_hash, - m_hash(&parent->mnt, mnt->mnt_mountpoint)); - list_add_tail(&mnt->mnt_child, &parent->mnt_mounts); - } + struct mountpoint *old_mp = mnt->mnt_mp; + struct dentry *old_mountpoint = mnt->mnt_mountpoint; + struct mount *old_parent = mnt->mnt_parent; + + list_del_init(&mnt->mnt_child); + hlist_del_init(&mnt->mnt_mp_list); + hlist_del_init_rcu(&mnt->mnt_hash); + + attach_mnt(mnt, parent, mp); + + put_mountpoint(old_mp); + + /* + * Safely avoid even the suggestion this code might sleep or + * lock the mount hash by taking advantage of the knowledge that + * mnt_change_mountpoint will not release the final reference + * to a mountpoint. + * + * During mounting, the mount passed in as the parent mount will + * continue to use the old mountpoint and during unmounting, the + * old mountpoint will continue to exist until namespace_unlock, + * which happens well after mnt_change_mountpoint. + */ + spin_lock(&old_mountpoint->d_lock); + old_mountpoint->d_lockref.count--; + spin_unlock(&old_mountpoint->d_lock); + + mnt_add_count(old_parent, -1); } /* * vfsmount lock must be held for write */ -static void commit_tree(struct mount *mnt, struct mount *shadows) +static void commit_tree(struct mount *mnt) { struct mount *parent = mnt->mnt_parent; struct mount *m; @@ -925,7 +927,7 @@ static void commit_tree(struct mount *mnt, struct mount *shadows) n->mounts += n->pending_mounts; n->pending_mounts = 0; - attach_shadowed(mnt, parent, shadows); + __attach_mnt(mnt, parent); touch_mnt_namespace(n); } @@ -989,6 +991,21 @@ vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void } EXPORT_SYMBOL_GPL(vfs_kern_mount); +struct vfsmount * +vfs_submount(const struct dentry *mountpoint, struct file_system_type *type, + const char *name, void *data) +{ + /* Until it is worked out how to pass the user namespace + * through from the parent mount to the submount don't support + * unprivileged mounts with submounts. + */ + if (mountpoint->d_sb->s_user_ns != &init_user_ns) + return ERR_PTR(-EPERM); + + return vfs_kern_mount(type, MS_SUBMOUNT, name, data); +} +EXPORT_SYMBOL_GPL(vfs_submount); + static struct mount *clone_mnt(struct mount *old, struct dentry *root, int flag) { @@ -1764,7 +1781,6 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry, continue; for (s = r; s; s = next_mnt(s, r)) { - struct mount *t = NULL; if (!(flag & CL_COPY_UNBINDABLE) && IS_MNT_UNBINDABLE(s)) { s = skip_mnt_tree(s); @@ -1786,14 +1802,7 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry, goto out; lock_mount_hash(); list_add_tail(&q->mnt_list, &res->mnt_list); - mnt_set_mountpoint(parent, p->mnt_mp, q); - if (!list_empty(&parent->mnt_mounts)) { - t = list_last_entry(&parent->mnt_mounts, - struct mount, mnt_child); - if (t->mnt_mp != p->mnt_mp) - t = NULL; - } - attach_shadowed(q, parent, t); + attach_mnt(q, parent, p->mnt_mp); unlock_mount_hash(); } } @@ -1992,10 +2001,18 @@ static int attach_recursive_mnt(struct mount *source_mnt, { HLIST_HEAD(tree_list); struct mnt_namespace *ns = dest_mnt->mnt_ns; + struct mountpoint *smp; struct mount *child, *p; struct hlist_node *n; int err; + /* Preallocate a mountpoint in case the new mounts need + * to be tucked under other mounts. + */ + smp = get_mountpoint(source_mnt->mnt.mnt_root); + if (IS_ERR(smp)) + return PTR_ERR(smp); + /* Is there space to add these mounts to the mount namespace? */ if (!parent_path) { err = count_mounts(ns, source_mnt); @@ -2022,16 +2039,19 @@ static int attach_recursive_mnt(struct mount *source_mnt, touch_mnt_namespace(source_mnt->mnt_ns); } else { mnt_set_mountpoint(dest_mnt, dest_mp, source_mnt); - commit_tree(source_mnt, NULL); + commit_tree(source_mnt); } hlist_for_each_entry_safe(child, n, &tree_list, mnt_hash) { struct mount *q; hlist_del_init(&child->mnt_hash); - q = __lookup_mnt_last(&child->mnt_parent->mnt, - child->mnt_mountpoint); - commit_tree(child, q); + q = __lookup_mnt(&child->mnt_parent->mnt, + child->mnt_mountpoint); + if (q) + mnt_change_mountpoint(child, smp, q); + commit_tree(child); } + put_mountpoint(smp); unlock_mount_hash(); return 0; @@ -2046,6 +2066,11 @@ static int attach_recursive_mnt(struct mount *source_mnt, cleanup_group_ids(source_mnt, NULL); out: ns->pending_mounts = 0; + + read_seqlock_excl(&mount_lock); + put_mountpoint(smp); + read_sequnlock_excl(&mount_lock); + return err; } @@ -2794,7 +2819,7 @@ long do_mount(const char *dev_name, const char __user *dir_name, flags &= ~(MS_NOSUID | MS_NOEXEC | MS_NODEV | MS_ACTIVE | MS_BORN | MS_NOATIME | MS_NODIRATIME | MS_RELATIME| MS_KERNMOUNT | - MS_STRICTATIME | MS_NOREMOTELOCK); + MS_STRICTATIME | MS_NOREMOTELOCK | MS_SUBMOUNT); if (flags & MS_REMOUNT) retval = do_remount(&path, flags & ~MS_REMOUNT, mnt_flags, diff --git a/fs/ncpfs/mmap.c b/fs/ncpfs/mmap.c index 39f57bef8531..0c3905e0542e 100644 --- a/fs/ncpfs/mmap.c +++ b/fs/ncpfs/mmap.c @@ -27,10 +27,9 @@ * XXX: how are we excluding truncate/invalidate here? Maybe need to lock * page? */ -static int ncp_file_mmap_fault(struct vm_area_struct *area, - struct vm_fault *vmf) +static int ncp_file_mmap_fault(struct vm_fault *vmf) { - struct inode *inode = file_inode(area->vm_file); + struct inode *inode = file_inode(vmf->vma->vm_file); char *pg_addr; unsigned int already_read; unsigned int count; @@ -90,7 +89,7 @@ static int ncp_file_mmap_fault(struct vm_area_struct *area, * -- nyc */ count_vm_event(PGMAJFAULT); - mem_cgroup_count_vm_event(area->vm_mm, PGMAJFAULT); + mem_cgroup_count_vm_event(vmf->vma->vm_mm, PGMAJFAULT); return VM_FAULT_MAJOR; } diff --git a/fs/ncpfs/sock.c b/fs/ncpfs/sock.c index f32f272ee501..97b111d79489 100644 --- a/fs/ncpfs/sock.c +++ b/fs/ncpfs/sock.c @@ -525,7 +525,7 @@ static int do_tcp_rcv(struct ncp_server *server, void *buffer, size_t len) return result; } if (result > len) { - pr_err("tcp: bug in recvmsg (%u > %Zu)\n", result, len); + pr_err("tcp: bug in recvmsg (%u > %zu)\n", result, len); return -EIO; } return result; @@ -619,7 +619,7 @@ skipdata:; goto skipdata2; } if (datalen > req->datalen + 8) { - pr_err("tcp: Unexpected reply len %d (expected at most %Zd)\n", datalen, req->datalen + 8); + pr_err("tcp: Unexpected reply len %d (expected at most %zd)\n", datalen, req->datalen + 8); server->rcv.state = 3; goto skipdata; } diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c index 2905479f214a..0ca370d23ddb 100644 --- a/fs/nfs/blocklayout/blocklayout.c +++ b/fs/nfs/blocklayout/blocklayout.c @@ -381,7 +381,7 @@ bl_write_pagelist(struct nfs_pgio_header *header, int sync) struct blk_plug plug; int i; - dprintk("%s enter, %Zu@%lld\n", __func__, count, offset); + dprintk("%s enter, %zu@%lld\n", __func__, count, offset); /* At this point, header->page_aray is a (sequential) list of nfs_pages. * We want to write each, and if there is an error set pnfs_error diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 26dbe8b0c10d..668213984d68 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -528,10 +528,10 @@ const struct address_space_operations nfs_file_aops = { * writable, implying that someone is about to modify the page through a * shared-writable mapping */ -static int nfs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) +static int nfs_vm_page_mkwrite(struct vm_fault *vmf) { struct page *page = vmf->page; - struct file *filp = vma->vm_file; + struct file *filp = vmf->vma->vm_file; struct inode *inode = file_inode(filp); unsigned pagelen; int ret = VM_FAULT_NOPAGE; diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index a3fc48ba4931..18f98e08544d 100644 --- a/fs/nfs/filelayout/filelayout.c +++ b/fs/nfs/filelayout/filelayout.c @@ -482,7 +482,7 @@ filelayout_read_pagelist(struct nfs_pgio_header *hdr) u32 j, idx; struct nfs_fh *fh; - dprintk("--> %s ino %lu pgbase %u req %Zu@%llu\n", + dprintk("--> %s ino %lu pgbase %u req %zu@%llu\n", __func__, hdr->inode->i_ino, hdr->args.pgbase, (size_t)hdr->args.count, offset); @@ -540,7 +540,7 @@ filelayout_write_pagelist(struct nfs_pgio_header *hdr, int sync) if (IS_ERR(ds_clnt)) return PNFS_NOT_ATTEMPTED; - dprintk("%s ino %lu sync %d req %Zu@%llu DS: %s cl_count %d\n", + dprintk("%s ino %lu sync %d req %zu@%llu DS: %s cl_count %d\n", __func__, hdr->inode->i_ino, sync, (size_t) hdr->args.count, offset, ds->ds_remotestr, atomic_read(&ds->ds_clp->cl_count)); diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index 0ca4af8cca5d..d6acc688df7e 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -1751,7 +1751,7 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr) int vers; struct nfs_fh *fh; - dprintk("--> %s ino %lu pgbase %u req %Zu@%llu\n", + dprintk("--> %s ino %lu pgbase %u req %zu@%llu\n", __func__, hdr->inode->i_ino, hdr->args.pgbase, (size_t)hdr->args.count, offset); @@ -1828,7 +1828,7 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync) vers = nfs4_ff_layout_ds_version(lseg, idx); - dprintk("%s ino %lu sync %d req %Zu@%llu DS: %s cl_count %d vers %d\n", + dprintk("%s ino %lu sync %d req %zu@%llu DS: %s cl_count %d vers %d\n", __func__, hdr->inode->i_ino, sync, (size_t) hdr->args.count, offset, ds->ds_remotestr, atomic_read(&ds->ds_clp->cl_count), vers); diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c index 5551e8ef67fd..e49d831c4e85 100644 --- a/fs/nfs/namespace.c +++ b/fs/nfs/namespace.c @@ -226,7 +226,7 @@ static struct vfsmount *nfs_do_clone_mount(struct nfs_server *server, const char *devname, struct nfs_clone_mount *mountdata) { - return vfs_kern_mount(&nfs_xdev_fs_type, 0, devname, mountdata); + return vfs_submount(mountdata->dentry, &nfs_xdev_fs_type, devname, mountdata); } /** diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c index d21104912676..d8b040bd9814 100644 --- a/fs/nfs/nfs4namespace.c +++ b/fs/nfs/nfs4namespace.c @@ -279,7 +279,7 @@ static struct vfsmount *try_location(struct nfs_clone_mount *mountdata, mountdata->hostname, mountdata->mnt_path); - mnt = vfs_kern_mount(&nfs4_referral_fs_type, 0, page, mountdata); + mnt = vfs_submount(mountdata->dentry, &nfs4_referral_fs_type, page, mountdata); if (!IS_ERR(mnt)) break; } diff --git a/fs/nfs/objlayout/objlayout.c b/fs/nfs/objlayout/objlayout.c index 2a4cdce939a0..8f3d2acb81c3 100644 --- a/fs/nfs/objlayout/objlayout.c +++ b/fs/nfs/objlayout/objlayout.c @@ -291,7 +291,7 @@ objlayout_read_pagelist(struct nfs_pgio_header *hdr) &hdr->args.pgbase, hdr->args.offset, hdr->args.count); - dprintk("%s: inode(%lx) offset 0x%llx count 0x%Zx eof=%d\n", + dprintk("%s: inode(%lx) offset 0x%llx count 0x%zx eof=%d\n", __func__, inode->i_ino, offset, count, hdr->res.eof); err = objio_read_pagelist(hdr); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index b00d53d13d47..006068526542 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -728,8 +728,6 @@ static void nfs_inode_remove_request(struct nfs_page *req) if (likely(head->wb_page && !PageSwapCache(head->wb_page))) { set_page_private(head->wb_page, 0); ClearPagePrivate(head->wb_page); - smp_mb__after_atomic(); - wake_up_page(head->wb_page, PG_private); clear_bit(PG_MAPPED, &head->wb_flags); } nfsi->nrequests--; diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig index 47febcf99185..20b1c17320d5 100644 --- a/fs/nfsd/Kconfig +++ b/fs/nfsd/Kconfig @@ -104,6 +104,7 @@ config NFSD_SCSILAYOUT depends on NFSD_V4 && BLOCK select NFSD_PNFS select EXPORTFS_BLOCK_OPS + select BLK_SCSI_REQUEST help This option enables support for the exporting pNFS SCSI layouts in the kernel's NFS server. The pNFS SCSI layout enables NFS diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c index 0780ff864539..92b4b41d19d2 100644 --- a/fs/nfsd/blocklayout.c +++ b/fs/nfsd/blocklayout.c @@ -10,6 +10,7 @@ #include <linux/nfsd/debug.h> #include <scsi/scsi_proto.h> #include <scsi/scsi_common.h> +#include <scsi/scsi_request.h> #include "blocklayoutxdr.h" #include "pnfs.h" @@ -23,7 +24,7 @@ nfsd4_block_proc_layoutget(struct inode *inode, const struct svc_fh *fhp, { struct nfsd4_layout_seg *seg = &args->lg_seg; struct super_block *sb = inode->i_sb; - u32 block_size = (1 << inode->i_blkbits); + u32 block_size = i_blocksize(inode); struct pnfs_block_extent *bex; struct iomap iomap; u32 device_generation = 0; @@ -180,7 +181,7 @@ nfsd4_block_proc_layoutcommit(struct inode *inode, int nr_iomaps; nr_iomaps = nfsd4_block_decode_layoutupdate(lcp->lc_up_layout, - lcp->lc_up_len, &iomaps, 1 << inode->i_blkbits); + lcp->lc_up_len, &iomaps, i_blocksize(inode)); if (nr_iomaps < 0) return nfserrno(nr_iomaps); @@ -213,6 +214,7 @@ static int nfsd4_scsi_identify_device(struct block_device *bdev, { struct request_queue *q = bdev->bd_disk->queue; struct request *rq; + struct scsi_request *req; size_t bufflen = 252, len, id_len; u8 *buf, *d, type, assoc; int error; @@ -221,23 +223,24 @@ static int nfsd4_scsi_identify_device(struct block_device *bdev, if (!buf) return -ENOMEM; - rq = blk_get_request(q, READ, GFP_KERNEL); + rq = blk_get_request(q, REQ_OP_SCSI_IN, GFP_KERNEL); if (IS_ERR(rq)) { error = -ENOMEM; goto out_free_buf; } - blk_rq_set_block_pc(rq); + req = scsi_req(rq); + scsi_req_init(rq); error = blk_rq_map_kern(q, rq, buf, bufflen, GFP_KERNEL); if (error) goto out_put_request; - rq->cmd[0] = INQUIRY; - rq->cmd[1] = 1; - rq->cmd[2] = 0x83; - rq->cmd[3] = bufflen >> 8; - rq->cmd[4] = bufflen & 0xff; - rq->cmd_len = COMMAND_SIZE(INQUIRY); + req->cmd[0] = INQUIRY; + req->cmd[1] = 1; + req->cmd[2] = 0x83; + req->cmd[3] = bufflen >> 8; + req->cmd[4] = bufflen & 0xff; + req->cmd_len = COMMAND_SIZE(INQUIRY); error = blk_execute_rq(rq->q, NULL, rq, 1); if (error) { @@ -372,7 +375,7 @@ nfsd4_scsi_proc_layoutcommit(struct inode *inode, int nr_iomaps; nr_iomaps = nfsd4_scsi_decode_layoutupdate(lcp->lc_up_layout, - lcp->lc_up_len, &iomaps, 1 << inode->i_blkbits); + lcp->lc_up_len, &iomaps, i_blocksize(inode)); if (nr_iomaps < 0) return nfserrno(nr_iomaps); diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c index 1fc07a9c70e9..e122da696f1b 100644 --- a/fs/nfsd/nfs4layouts.c +++ b/fs/nfsd/nfs4layouts.c @@ -614,6 +614,7 @@ nfsd4_cb_layout_fail(struct nfs4_layout_stateid *ls) { struct nfs4_client *clp = ls->ls_stid.sc_client; char addr_str[INET6_ADDRSTRLEN]; + static char const nfsd_recall_failed[] = "/sbin/nfsd-recall-failed"; static char *envp[] = { "HOME=/", "TERM=linux", @@ -629,12 +630,13 @@ nfsd4_cb_layout_fail(struct nfs4_layout_stateid *ls) "nfsd: client %s failed to respond to layout recall. " " Fencing..\n", addr_str); - argv[0] = "/sbin/nfsd-recall-failed"; + argv[0] = (char *)nfsd_recall_failed; argv[1] = addr_str; argv[2] = ls->ls_file->f_path.mnt->mnt_sb->s_id; argv[3] = NULL; - error = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_PROC); + error = call_usermodehelper(nfsd_recall_failed, argv, envp, + UMH_WAIT_PROC); if (error) { printk(KERN_ERR "nfsd: fence failed for client %s: %d!\n", addr_str, error); diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c index d6b97b424ad1..96fd15979cbd 100644 --- a/fs/nfsd/nfscache.c +++ b/fs/nfsd/nfscache.c @@ -578,7 +578,7 @@ nfsd_cache_append(struct svc_rqst *rqstp, struct kvec *data) struct kvec *vec = &rqstp->rq_res.head[0]; if (vec->iov_len + data->iov_len > PAGE_SIZE) { - printk(KERN_WARNING "nfsd: cached reply too large (%Zd).\n", + printk(KERN_WARNING "nfsd: cached reply too large (%zd).\n", data->iov_len); return 0; } diff --git a/fs/nilfs2/alloc.c b/fs/nilfs2/alloc.c index 2c90e285d7c6..03b8ba933eb2 100644 --- a/fs/nilfs2/alloc.c +++ b/fs/nilfs2/alloc.c @@ -34,7 +34,7 @@ static inline unsigned long nilfs_palloc_groups_per_desc_block(const struct inode *inode) { - return (1UL << inode->i_blkbits) / + return i_blocksize(inode) / sizeof(struct nilfs_palloc_group_desc); } diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c index d5c23da43513..c21e0b4454a6 100644 --- a/fs/nilfs2/btnode.c +++ b/fs/nilfs2/btnode.c @@ -50,7 +50,7 @@ nilfs_btnode_create_block(struct address_space *btnc, __u64 blocknr) brelse(bh); BUG(); } - memset(bh->b_data, 0, 1 << inode->i_blkbits); + memset(bh->b_data, 0, i_blocksize(inode)); bh->b_bdev = inode->i_sb->s_bdev; bh->b_blocknr = blocknr; set_buffer_mapped(bh); diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c index 2e315f9f2e51..06ffa135dfa6 100644 --- a/fs/nilfs2/btree.c +++ b/fs/nilfs2/btree.c @@ -119,7 +119,7 @@ nilfs_btree_node_set_nchildren(struct nilfs_btree_node *node, int nchildren) static int nilfs_btree_node_size(const struct nilfs_bmap *btree) { - return 1 << btree->b_inode->i_blkbits; + return i_blocksize(btree->b_inode); } static int nilfs_btree_nchildren_per_block(const struct nilfs_bmap *btree) @@ -1870,7 +1870,7 @@ int nilfs_btree_convert_and_insert(struct nilfs_bmap *btree, di = &dreq; ni = NULL; } else if ((n + 1) <= NILFS_BTREE_NODE_NCHILDREN_MAX( - 1 << btree->b_inode->i_blkbits)) { + nilfs_btree_node_size(btree))) { di = &dreq; ni = &nreq; } else { diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c index 547381f3ce13..c5fa3dee72fc 100644 --- a/fs/nilfs2/file.c +++ b/fs/nilfs2/file.c @@ -51,8 +51,9 @@ int nilfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) return err; } -static int nilfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) +static int nilfs_page_mkwrite(struct vm_fault *vmf) { + struct vm_area_struct *vma = vmf->vma; struct page *page = vmf->page; struct inode *inode = file_inode(vma->vm_file); struct nilfs_transaction_info ti; diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index c7f4fef9ebf5..7ffe71a8dfb9 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -51,7 +51,7 @@ void nilfs_inode_add_blocks(struct inode *inode, int n) { struct nilfs_root *root = NILFS_I(inode)->i_root; - inode_add_bytes(inode, (1 << inode->i_blkbits) * n); + inode_add_bytes(inode, i_blocksize(inode) * n); if (root) atomic64_add(n, &root->blocks_count); } @@ -60,7 +60,7 @@ void nilfs_inode_sub_blocks(struct inode *inode, int n) { struct nilfs_root *root = NILFS_I(inode)->i_root; - inode_sub_bytes(inode, (1 << inode->i_blkbits) * n); + inode_sub_bytes(inode, i_blocksize(inode) * n); if (root) atomic64_sub(n, &root->blocks_count); } diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c index d56d3a5bea88..98835ed6bef4 100644 --- a/fs/nilfs2/mdt.c +++ b/fs/nilfs2/mdt.c @@ -57,7 +57,7 @@ nilfs_mdt_insert_new_block(struct inode *inode, unsigned long block, set_buffer_mapped(bh); kaddr = kmap_atomic(bh->b_page); - memset(kaddr + bh_offset(bh), 0, 1 << inode->i_blkbits); + memset(kaddr + bh_offset(bh), 0, i_blocksize(inode)); if (init_block) init_block(inode, bh, kaddr); flush_dcache_page(bh->b_page); @@ -501,7 +501,7 @@ void nilfs_mdt_set_entry_size(struct inode *inode, unsigned int entry_size, struct nilfs_mdt_info *mi = NILFS_MDT(inode); mi->mi_entry_size = entry_size; - mi->mi_entries_per_block = (1 << inode->i_blkbits) / entry_size; + mi->mi_entries_per_block = i_blocksize(inode) / entry_size; mi->mi_first_entry_offset = DIV_ROUND_UP(header_size, entry_size); } diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index bedcae2c28e6..7d18d62e8e07 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -723,7 +723,7 @@ static size_t nilfs_lookup_dirty_data_buffers(struct inode *inode, lock_page(page); if (!page_has_buffers(page)) - create_empty_buffers(page, 1 << inode->i_blkbits, 0); + create_empty_buffers(page, i_blocksize(inode), 0); unlock_page(page); bh = head = page_buffers(page); diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index 12eeae62a2b1..e1872f36147f 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -1068,7 +1068,7 @@ nilfs_fill_super(struct super_block *sb, void *data, int silent) sb->s_time_gran = 1; sb->s_max_links = NILFS_LINK_MAX; - sb->s_bdi = &bdev_get_queue(sb->s_bdev)->backing_dev_info; + sb->s_bdi = bdev_get_queue(sb->s_bdev)->backing_dev_info; err = load_nilfs(nilfs, sb); if (err) diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index bbc175d4213d..a4c46221755e 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -31,7 +31,6 @@ static bool should_merge(struct fsnotify_event *old_fsn, static int fanotify_merge(struct list_head *list, struct fsnotify_event *event) { struct fsnotify_event *test_event; - bool do_merge = false; pr_debug("%s: list=%p event=%p\n", __func__, list, event); @@ -47,16 +46,12 @@ static int fanotify_merge(struct list_head *list, struct fsnotify_event *event) list_for_each_entry_reverse(test_event, list, list) { if (should_merge(test_event, event)) { - do_merge = true; - break; + test_event->mask |= event->mask; + return 1; } } - if (!do_merge) - return 0; - - test_event->mask |= event->mask; - return 1; + return 0; } #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS diff --git a/fs/notify/inotify/inotify.h b/fs/notify/inotify/inotify.h index a6f5907a3fee..7c461fd49c4c 100644 --- a/fs/notify/inotify/inotify.h +++ b/fs/notify/inotify/inotify.h @@ -30,3 +30,20 @@ extern int inotify_handle_event(struct fsnotify_group *group, const unsigned char *file_name, u32 cookie); extern const struct fsnotify_ops inotify_fsnotify_ops; + +#ifdef CONFIG_INOTIFY_USER +static inline void dec_inotify_instances(struct ucounts *ucounts) +{ + dec_ucount(ucounts, UCOUNT_INOTIFY_INSTANCES); +} + +static inline struct ucounts *inc_inotify_watches(struct ucounts *ucounts) +{ + return inc_ucount(ucounts->ns, ucounts->uid, UCOUNT_INOTIFY_WATCHES); +} + +static inline void dec_inotify_watches(struct ucounts *ucounts) +{ + dec_ucount(ucounts, UCOUNT_INOTIFY_WATCHES); +} +#endif diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c index 19e7ec109a75..f36c29398de3 100644 --- a/fs/notify/inotify/inotify_fsnotify.c +++ b/fs/notify/inotify/inotify_fsnotify.c @@ -165,10 +165,8 @@ static void inotify_free_group_priv(struct fsnotify_group *group) /* ideally the idr is empty and we won't hit the BUG in the callback */ idr_for_each(&group->inotify_data.idr, idr_callback, group); idr_destroy(&group->inotify_data.idr); - if (group->inotify_data.user) { - atomic_dec(&group->inotify_data.user->inotify_devs); - free_uid(group->inotify_data.user); - } + if (group->inotify_data.ucounts) + dec_inotify_instances(group->inotify_data.ucounts); } static void inotify_free_event(struct fsnotify_event *fsn_event) diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index 69d1ea3d292a..1cf41c623be1 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -44,10 +44,8 @@ #include <asm/ioctls.h> -/* these are configurable via /proc/sys/fs/inotify/ */ -static int inotify_max_user_instances __read_mostly; +/* configurable via /proc/sys/fs/inotify/ */ static int inotify_max_queued_events __read_mostly; -static int inotify_max_user_watches __read_mostly; static struct kmem_cache *inotify_inode_mark_cachep __read_mostly; @@ -60,7 +58,7 @@ static int zero; struct ctl_table inotify_table[] = { { .procname = "max_user_instances", - .data = &inotify_max_user_instances, + .data = &init_user_ns.ucount_max[UCOUNT_INOTIFY_INSTANCES], .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, @@ -68,7 +66,7 @@ struct ctl_table inotify_table[] = { }, { .procname = "max_user_watches", - .data = &inotify_max_user_watches, + .data = &init_user_ns.ucount_max[UCOUNT_INOTIFY_WATCHES], .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, @@ -500,7 +498,7 @@ void inotify_ignored_and_remove_idr(struct fsnotify_mark *fsn_mark, /* remove this mark from the idr */ inotify_remove_from_idr(group, i_mark); - atomic_dec(&group->inotify_data.user->inotify_watches); + dec_inotify_watches(group->inotify_data.ucounts); } /* ding dong the mark is dead */ @@ -584,14 +582,17 @@ static int inotify_new_watch(struct fsnotify_group *group, tmp_i_mark->fsn_mark.mask = mask; tmp_i_mark->wd = -1; - ret = -ENOSPC; - if (atomic_read(&group->inotify_data.user->inotify_watches) >= inotify_max_user_watches) - goto out_err; - ret = inotify_add_to_idr(idr, idr_lock, tmp_i_mark); if (ret) goto out_err; + /* increment the number of watches the user has */ + if (!inc_inotify_watches(group->inotify_data.ucounts)) { + inotify_remove_from_idr(group, tmp_i_mark); + ret = -ENOSPC; + goto out_err; + } + /* we are on the idr, now get on the inode */ ret = fsnotify_add_mark_locked(&tmp_i_mark->fsn_mark, group, inode, NULL, 0); @@ -601,8 +602,6 @@ static int inotify_new_watch(struct fsnotify_group *group, goto out_err; } - /* increment the number of watches the user has */ - atomic_inc(&group->inotify_data.user->inotify_watches); /* return the watch descriptor for this new mark */ ret = tmp_i_mark->wd; @@ -653,10 +652,11 @@ static struct fsnotify_group *inotify_new_group(unsigned int max_events) spin_lock_init(&group->inotify_data.idr_lock); idr_init(&group->inotify_data.idr); - group->inotify_data.user = get_current_user(); + group->inotify_data.ucounts = inc_ucount(current_user_ns(), + current_euid(), + UCOUNT_INOTIFY_INSTANCES); - if (atomic_inc_return(&group->inotify_data.user->inotify_devs) > - inotify_max_user_instances) { + if (!group->inotify_data.ucounts) { fsnotify_destroy_group(group); return ERR_PTR(-EMFILE); } @@ -819,8 +819,8 @@ static int __init inotify_user_setup(void) inotify_inode_mark_cachep = KMEM_CACHE(inotify_inode_mark, SLAB_PANIC); inotify_max_queued_events = 16384; - inotify_max_user_instances = 128; - inotify_max_user_watches = 8192; + init_user_ns.ucount_max[UCOUNT_INOTIFY_INSTANCES] = 128; + init_user_ns.ucount_max[UCOUNT_INOTIFY_WATCHES] = 8192; return 0; } diff --git a/fs/nsfs.c b/fs/nsfs.c index 8c9fb29c6673..1656843e87d2 100644 --- a/fs/nsfs.c +++ b/fs/nsfs.c @@ -7,6 +7,7 @@ #include <linux/seq_file.h> #include <linux/user_namespace.h> #include <linux/nsfs.h> +#include <linux/uaccess.h> static struct vfsmount *nsfs_mnt; @@ -163,7 +164,10 @@ int open_related_ns(struct ns_common *ns, static long ns_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { + struct user_namespace *user_ns; struct ns_common *ns = get_proc_ns(file_inode(filp)); + uid_t __user *argp; + uid_t uid; switch (ioctl) { case NS_GET_USERNS: @@ -172,6 +176,15 @@ static long ns_ioctl(struct file *filp, unsigned int ioctl, if (!ns->ops->get_parent) return -EINVAL; return open_related_ns(ns, ns->ops->get_parent); + case NS_GET_NSTYPE: + return ns->ops->type; + case NS_GET_OWNER_UID: + if (ns->ops->type != CLONE_NEWUSER) + return -EINVAL; + user_ns = container_of(ns, struct user_namespace, ns); + argp = (uid_t __user *) arg; + uid = from_kuid_munged(current_user_ns(), user_ns->owner); + return put_user(uid, argp); default: return -ENOTTY; } diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c index bed1fcb63088..dc22ba8c710f 100644 --- a/fs/ocfs2/acl.c +++ b/fs/ocfs2/acl.c @@ -283,16 +283,14 @@ int ocfs2_set_acl(handle_t *handle, int ocfs2_iop_set_acl(struct inode *inode, struct posix_acl *acl, int type) { struct buffer_head *bh = NULL; - int status = 0; + int status, had_lock; + struct ocfs2_lock_holder oh; - status = ocfs2_inode_lock(inode, &bh, 1); - if (status < 0) { - if (status != -ENOENT) - mlog_errno(status); - return status; - } + had_lock = ocfs2_inode_lock_tracker(inode, &bh, 1, &oh); + if (had_lock < 0) + return had_lock; status = ocfs2_set_acl(NULL, inode, bh, type, acl, NULL, NULL); - ocfs2_inode_unlock(inode, 1); + ocfs2_inode_unlock_tracker(inode, 1, &oh, had_lock); brelse(bh); return status; } @@ -302,21 +300,20 @@ struct posix_acl *ocfs2_iop_get_acl(struct inode *inode, int type) struct ocfs2_super *osb; struct buffer_head *di_bh = NULL; struct posix_acl *acl; - int ret; + int had_lock; + struct ocfs2_lock_holder oh; osb = OCFS2_SB(inode->i_sb); if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL)) return NULL; - ret = ocfs2_inode_lock(inode, &di_bh, 0); - if (ret < 0) { - if (ret != -ENOENT) - mlog_errno(ret); - return ERR_PTR(ret); - } + + had_lock = ocfs2_inode_lock_tracker(inode, &di_bh, 0, &oh); + if (had_lock < 0) + return ERR_PTR(had_lock); acl = ocfs2_get_acl_nolock(inode, type, di_bh); - ocfs2_inode_unlock(inode, 0); + ocfs2_inode_unlock_tracker(inode, 0, &oh, had_lock); brelse(di_bh); return acl; } diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 11556b7d93ec..88a31e9340a0 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -608,7 +608,7 @@ int ocfs2_map_page_blocks(struct page *page, u64 *p_blkno, int ret = 0; struct buffer_head *head, *bh, *wait[2], **wait_bh = wait; unsigned int block_end, block_start; - unsigned int bsize = 1 << inode->i_blkbits; + unsigned int bsize = i_blocksize(inode); if (!page_has_buffers(page)) create_empty_buffers(page, bsize, 0); diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index 7025d8c27999..3e04279446e8 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -2924,7 +2924,7 @@ again: /* * if target is down, we need to clear DLM_LOCK_RES_BLOCK_DIRTY for * another try; otherwise, we are sure the MIGRATING state is there, - * drop the unneded state which blocked threads trying to DIRTY + * drop the unneeded state which blocked threads trying to DIRTY */ spin_lock(&res->spinlock); BUG_ON(!(res->state & DLM_LOCK_RES_BLOCK_DIRTY)); diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 77d1632e905d..8dce4099a6ca 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -532,6 +532,7 @@ void ocfs2_lock_res_init_once(struct ocfs2_lock_res *res) init_waitqueue_head(&res->l_event); INIT_LIST_HEAD(&res->l_blocked_list); INIT_LIST_HEAD(&res->l_mask_waiters); + INIT_LIST_HEAD(&res->l_holders); } void ocfs2_inode_lock_res_init(struct ocfs2_lock_res *res, @@ -749,6 +750,50 @@ void ocfs2_lock_res_free(struct ocfs2_lock_res *res) res->l_flags = 0UL; } +/* + * Keep a list of processes who have interest in a lockres. + * Note: this is now only uesed for check recursive cluster locking. + */ +static inline void ocfs2_add_holder(struct ocfs2_lock_res *lockres, + struct ocfs2_lock_holder *oh) +{ + INIT_LIST_HEAD(&oh->oh_list); + oh->oh_owner_pid = get_pid(task_pid(current)); + + spin_lock(&lockres->l_lock); + list_add_tail(&oh->oh_list, &lockres->l_holders); + spin_unlock(&lockres->l_lock); +} + +static inline void ocfs2_remove_holder(struct ocfs2_lock_res *lockres, + struct ocfs2_lock_holder *oh) +{ + spin_lock(&lockres->l_lock); + list_del(&oh->oh_list); + spin_unlock(&lockres->l_lock); + + put_pid(oh->oh_owner_pid); +} + +static inline int ocfs2_is_locked_by_me(struct ocfs2_lock_res *lockres) +{ + struct ocfs2_lock_holder *oh; + struct pid *pid; + + /* look in the list of holders for one with the current task as owner */ + spin_lock(&lockres->l_lock); + pid = task_pid(current); + list_for_each_entry(oh, &lockres->l_holders, oh_list) { + if (oh->oh_owner_pid == pid) { + spin_unlock(&lockres->l_lock); + return 1; + } + } + spin_unlock(&lockres->l_lock); + + return 0; +} + static inline void ocfs2_inc_holders(struct ocfs2_lock_res *lockres, int level) { @@ -2333,8 +2378,9 @@ int ocfs2_inode_lock_full_nested(struct inode *inode, goto getbh; } - if (ocfs2_mount_local(osb)) - goto local; + if ((arg_flags & OCFS2_META_LOCK_GETBH) || + ocfs2_mount_local(osb)) + goto update; if (!(arg_flags & OCFS2_META_LOCK_RECOVERY)) ocfs2_wait_for_recovery(osb); @@ -2363,7 +2409,7 @@ int ocfs2_inode_lock_full_nested(struct inode *inode, if (!(arg_flags & OCFS2_META_LOCK_RECOVERY)) ocfs2_wait_for_recovery(osb); -local: +update: /* * We only see this flag if we're being called from * ocfs2_read_locked_inode(). It means we're locking an inode @@ -2497,6 +2543,59 @@ void ocfs2_inode_unlock(struct inode *inode, ocfs2_cluster_unlock(OCFS2_SB(inode->i_sb), lockres, level); } +/* + * This _tracker variantes are introduced to deal with the recursive cluster + * locking issue. The idea is to keep track of a lock holder on the stack of + * the current process. If there's a lock holder on the stack, we know the + * task context is already protected by cluster locking. Currently, they're + * used in some VFS entry routines. + * + * return < 0 on error, return == 0 if there's no lock holder on the stack + * before this call, return == 1 if this call would be a recursive locking. + */ +int ocfs2_inode_lock_tracker(struct inode *inode, + struct buffer_head **ret_bh, + int ex, + struct ocfs2_lock_holder *oh) +{ + int status; + int arg_flags = 0, has_locked; + struct ocfs2_lock_res *lockres; + + lockres = &OCFS2_I(inode)->ip_inode_lockres; + has_locked = ocfs2_is_locked_by_me(lockres); + /* Just get buffer head if the cluster lock has been taken */ + if (has_locked) + arg_flags = OCFS2_META_LOCK_GETBH; + + if (likely(!has_locked || ret_bh)) { + status = ocfs2_inode_lock_full(inode, ret_bh, ex, arg_flags); + if (status < 0) { + if (status != -ENOENT) + mlog_errno(status); + return status; + } + } + if (!has_locked) + ocfs2_add_holder(lockres, oh); + + return has_locked; +} + +void ocfs2_inode_unlock_tracker(struct inode *inode, + int ex, + struct ocfs2_lock_holder *oh, + int had_lock) +{ + struct ocfs2_lock_res *lockres; + + lockres = &OCFS2_I(inode)->ip_inode_lockres; + if (!had_lock) { + ocfs2_remove_holder(lockres, oh); + ocfs2_inode_unlock(inode, ex); + } +} + int ocfs2_orphan_scan_lock(struct ocfs2_super *osb, u32 *seqno) { struct ocfs2_lock_res *lockres; diff --git a/fs/ocfs2/dlmglue.h b/fs/ocfs2/dlmglue.h index d293a22c32c5..a7fc18ba0dc1 100644 --- a/fs/ocfs2/dlmglue.h +++ b/fs/ocfs2/dlmglue.h @@ -70,6 +70,11 @@ struct ocfs2_orphan_scan_lvb { __be32 lvb_os_seqno; }; +struct ocfs2_lock_holder { + struct list_head oh_list; + struct pid *oh_owner_pid; +}; + /* ocfs2_inode_lock_full() 'arg_flags' flags */ /* don't wait on recovery. */ #define OCFS2_META_LOCK_RECOVERY (0x01) @@ -77,6 +82,8 @@ struct ocfs2_orphan_scan_lvb { #define OCFS2_META_LOCK_NOQUEUE (0x02) /* don't block waiting for the downconvert thread, instead return -EAGAIN */ #define OCFS2_LOCK_NONBLOCK (0x04) +/* just get back disk inode bh if we've got cluster lock. */ +#define OCFS2_META_LOCK_GETBH (0x08) /* Locking subclasses of inode cluster lock */ enum { @@ -170,4 +177,15 @@ void ocfs2_put_dlm_debug(struct ocfs2_dlm_debug *dlm_debug); /* To set the locking protocol on module initialization */ void ocfs2_set_locking_protocol(void); + +/* The _tracker pair is used to avoid cluster recursive locking */ +int ocfs2_inode_lock_tracker(struct inode *inode, + struct buffer_head **ret_bh, + int ex, + struct ocfs2_lock_holder *oh); +void ocfs2_inode_unlock_tracker(struct inode *inode, + int ex, + struct ocfs2_lock_holder *oh, + int had_lock); + #endif /* DLMGLUE_H */ diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index c4889655d32b..8836305eb378 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -808,7 +808,7 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from, /* We know that zero_from is block aligned */ for (block_start = zero_from; block_start < zero_to; block_start = block_end) { - block_end = block_start + (1 << inode->i_blkbits); + block_end = block_start + i_blocksize(inode); /* * block_start is block-aligned. Bump it by one to force @@ -1138,6 +1138,8 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr) handle_t *handle = NULL; struct dquot *transfer_to[MAXQUOTAS] = { }; int qtype; + int had_lock; + struct ocfs2_lock_holder oh; trace_ocfs2_setattr(inode, dentry, (unsigned long long)OCFS2_I(inode)->ip_blkno, @@ -1173,11 +1175,30 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr) } } - status = ocfs2_inode_lock(inode, &bh, 1); - if (status < 0) { - if (status != -ENOENT) - mlog_errno(status); + had_lock = ocfs2_inode_lock_tracker(inode, &bh, 1, &oh); + if (had_lock < 0) { + status = had_lock; goto bail_unlock_rw; + } else if (had_lock) { + /* + * As far as we know, ocfs2_setattr() could only be the first + * VFS entry point in the call chain of recursive cluster + * locking issue. + * + * For instance: + * chmod_common() + * notify_change() + * ocfs2_setattr() + * posix_acl_chmod() + * ocfs2_iop_get_acl() + * + * But, we're not 100% sure if it's always true, because the + * ordering of the VFS entry points in the call chain is out + * of our control. So, we'd better dump the stack here to + * catch the other cases of recursive locking. + */ + mlog(ML_ERROR, "Another case of recursive locking:\n"); + dump_stack(); } inode_locked = 1; @@ -1260,8 +1281,8 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr) bail_commit: ocfs2_commit_trans(osb, handle); bail_unlock: - if (status) { - ocfs2_inode_unlock(inode, 1); + if (status && inode_locked) { + ocfs2_inode_unlock_tracker(inode, 1, &oh, had_lock); inode_locked = 0; } bail_unlock_rw: @@ -1279,7 +1300,7 @@ bail: mlog_errno(status); } if (inode_locked) - ocfs2_inode_unlock(inode, 1); + ocfs2_inode_unlock_tracker(inode, 1, &oh, had_lock); brelse(bh); return status; @@ -1320,21 +1341,32 @@ bail: int ocfs2_permission(struct inode *inode, int mask) { - int ret; + int ret, had_lock; + struct ocfs2_lock_holder oh; if (mask & MAY_NOT_BLOCK) return -ECHILD; - ret = ocfs2_inode_lock(inode, NULL, 0); - if (ret) { - if (ret != -ENOENT) - mlog_errno(ret); + had_lock = ocfs2_inode_lock_tracker(inode, NULL, 0, &oh); + if (had_lock < 0) { + ret = had_lock; goto out; + } else if (had_lock) { + /* See comments in ocfs2_setattr() for details. + * The call chain of this case could be: + * do_sys_open() + * may_open() + * inode_permission() + * ocfs2_permission() + * ocfs2_iop_get_acl() + */ + mlog(ML_ERROR, "Another case of recursive locking:\n"); + dump_stack(); } ret = generic_permission(inode, mask); - ocfs2_inode_unlock(inode, 0); + ocfs2_inode_unlock_tracker(inode, 0, &oh, had_lock); out: return ret; } diff --git a/fs/ocfs2/mmap.c b/fs/ocfs2/mmap.c index 429088786e93..098f5c712569 100644 --- a/fs/ocfs2/mmap.c +++ b/fs/ocfs2/mmap.c @@ -44,17 +44,18 @@ #include "ocfs2_trace.h" -static int ocfs2_fault(struct vm_area_struct *area, struct vm_fault *vmf) +static int ocfs2_fault(struct vm_fault *vmf) { + struct vm_area_struct *vma = vmf->vma; sigset_t oldset; int ret; ocfs2_block_signals(&oldset); - ret = filemap_fault(area, vmf); + ret = filemap_fault(vmf); ocfs2_unblock_signals(&oldset); - trace_ocfs2_fault(OCFS2_I(area->vm_file->f_mapping->host)->ip_blkno, - area, vmf->page, vmf->pgoff); + trace_ocfs2_fault(OCFS2_I(vma->vm_file->f_mapping->host)->ip_blkno, + vma, vmf->page, vmf->pgoff); return ret; } @@ -127,10 +128,10 @@ out: return ret; } -static int ocfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) +static int ocfs2_page_mkwrite(struct vm_fault *vmf) { struct page *page = vmf->page; - struct inode *inode = file_inode(vma->vm_file); + struct inode *inode = file_inode(vmf->vma->vm_file); struct buffer_head *di_bh = NULL; sigset_t oldset; int ret; @@ -160,7 +161,7 @@ static int ocfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) */ down_write(&OCFS2_I(inode)->ip_alloc_sem); - ret = __ocfs2_page_mkwrite(vma->vm_file, di_bh, page); + ret = __ocfs2_page_mkwrite(vmf->vma->vm_file, di_bh, page); up_write(&OCFS2_I(inode)->ip_alloc_sem); diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index 7e5958b0be6b..0c39d71c67a1 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -172,6 +172,7 @@ struct ocfs2_lock_res { struct list_head l_blocked_list; struct list_head l_mask_waiters; + struct list_head l_holders; unsigned long l_flags; char l_name[OCFS2_LOCK_ID_MAX_LEN]; diff --git a/fs/orangefs/devorangefs-req.c b/fs/orangefs/devorangefs-req.c index b0ced669427e..c4ab6fdf17a0 100644 --- a/fs/orangefs/devorangefs-req.c +++ b/fs/orangefs/devorangefs-req.c @@ -400,8 +400,9 @@ static ssize_t orangefs_devreq_write_iter(struct kiocb *iocb, /* remove the op from the in progress hash table */ op = orangefs_devreq_remove_op(head.tag); if (!op) { - gossip_err("WARNING: No one's waiting for tag %llu\n", - llu(head.tag)); + gossip_debug(GOSSIP_DEV_DEBUG, + "%s: No one's waiting for tag %llu\n", + __func__, llu(head.tag)); return ret; } diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c index 551bc74ed2b8..5cd617980fbf 100644 --- a/fs/orangefs/inode.c +++ b/fs/orangefs/inode.c @@ -136,12 +136,6 @@ static ssize_t orangefs_direct_IO(struct kiocb *iocb, return -EINVAL; } -struct backing_dev_info orangefs_backing_dev_info = { - .name = "orangefs", - .ra_pages = 0, - .capabilities = BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_WRITEBACK, -}; - /** ORANGEFS2 implementation of address space operations */ const struct address_space_operations orangefs_address_operations = { .readpage = orangefs_readpage, diff --git a/fs/orangefs/orangefs-bufmap.c b/fs/orangefs/orangefs-bufmap.c index 75375e90a63f..6333cbbdfef7 100644 --- a/fs/orangefs/orangefs-bufmap.c +++ b/fs/orangefs/orangefs-bufmap.c @@ -344,6 +344,11 @@ int orangefs_bufmap_initialize(struct ORANGEFS_dev_map_desc *user_desc) user_desc->size, user_desc->count); + if (user_desc->total_size < 0 || + user_desc->size < 0 || + user_desc->count < 0) + goto out; + /* * sanity check alignment and size of buffer that caller wants to * work with diff --git a/fs/orangefs/orangefs-debugfs.c b/fs/orangefs/orangefs-debugfs.c index 27e75cf28b3a..791912da97d7 100644 --- a/fs/orangefs/orangefs-debugfs.c +++ b/fs/orangefs/orangefs-debugfs.c @@ -967,13 +967,13 @@ int orangefs_debugfs_new_client_string(void __user *arg) int ret; ret = copy_from_user(&client_debug_array_string, - (void __user *)arg, - ORANGEFS_MAX_DEBUG_STRING_LEN); + (void __user *)arg, + ORANGEFS_MAX_DEBUG_STRING_LEN); if (ret != 0) { pr_info("%s: CLIENT_STRING: copy_from_user failed\n", __func__); - return -EIO; + return -EFAULT; } /* @@ -988,17 +988,18 @@ int orangefs_debugfs_new_client_string(void __user *arg) */ client_debug_array_string[ORANGEFS_MAX_DEBUG_STRING_LEN - 1] = '\0'; - + pr_info("%s: client debug array string has been received.\n", __func__); if (!help_string_initialized) { /* Build a proper debug help string. */ - if (orangefs_prepare_debugfs_help_string(0)) { + ret = orangefs_prepare_debugfs_help_string(0); + if (ret) { gossip_err("%s: no debug help string \n", __func__); - return -EIO; + return ret; } } @@ -1011,7 +1012,7 @@ int orangefs_debugfs_new_client_string(void __user *arg) help_string_initialized++; - return ret; + return 0; } int orangefs_debugfs_new_debug(void __user *arg) diff --git a/fs/orangefs/orangefs-dev-proto.h b/fs/orangefs/orangefs-dev-proto.h index a3d84ffee905..f380f9ed1b28 100644 --- a/fs/orangefs/orangefs-dev-proto.h +++ b/fs/orangefs/orangefs-dev-proto.h @@ -50,8 +50,7 @@ * Misc constants. Please retain them as multiples of 8! * Otherwise 32-64 bit interactions will be messed up :) */ -#define ORANGEFS_MAX_DEBUG_STRING_LEN 0x00000400 -#define ORANGEFS_MAX_DEBUG_ARRAY_LEN 0x00000800 +#define ORANGEFS_MAX_DEBUG_STRING_LEN 0x00000800 /* * The maximum number of directory entries in a single request is 96. diff --git a/fs/orangefs/orangefs-kernel.h b/fs/orangefs/orangefs-kernel.h index 3bf803d732c5..70355a9a2596 100644 --- a/fs/orangefs/orangefs-kernel.h +++ b/fs/orangefs/orangefs-kernel.h @@ -529,7 +529,6 @@ extern spinlock_t orangefs_htable_ops_in_progress_lock; extern int hash_table_size; extern const struct address_space_operations orangefs_address_operations; -extern struct backing_dev_info orangefs_backing_dev_info; extern const struct inode_operations orangefs_file_inode_operations; extern const struct file_operations orangefs_file_operations; extern const struct inode_operations orangefs_symlink_inode_operations; diff --git a/fs/orangefs/orangefs-mod.c b/fs/orangefs/orangefs-mod.c index 4113eb0495bf..c1b5174cb5a9 100644 --- a/fs/orangefs/orangefs-mod.c +++ b/fs/orangefs/orangefs-mod.c @@ -80,11 +80,6 @@ static int __init orangefs_init(void) int ret = -1; __u32 i = 0; - ret = bdi_init(&orangefs_backing_dev_info); - - if (ret) - return ret; - if (op_timeout_secs < 0) op_timeout_secs = 0; @@ -94,7 +89,7 @@ static int __init orangefs_init(void) /* initialize global book keeping data structures */ ret = op_cache_initialize(); if (ret < 0) - goto err; + goto out; ret = orangefs_inode_cache_initialize(); if (ret < 0) @@ -181,9 +176,6 @@ cleanup_inode: cleanup_op: op_cache_finalize(); -err: - bdi_destroy(&orangefs_backing_dev_info); - out: return ret; } @@ -207,8 +199,6 @@ static void __exit orangefs_exit(void) kfree(orangefs_htable_ops_in_progress); - bdi_destroy(&orangefs_backing_dev_info); - pr_info("orangefs: module version %s unloaded\n", ORANGEFS_VERSION); } diff --git a/fs/orangefs/orangefs-sysfs.c b/fs/orangefs/orangefs-sysfs.c index 084954448f18..afd2f523b283 100644 --- a/fs/orangefs/orangefs-sysfs.c +++ b/fs/orangefs/orangefs-sysfs.c @@ -91,6 +91,13 @@ * Description: * Readahead cache buffer count and size. * + * What: /sys/fs/orangefs/readahead_readcnt + * Date: Jan 2017 + * Contact: Martin Brandenburg <martin@omnibond.com> + * Description: + * Number of buffers (in multiples of readahead_size) + * which can be read ahead for a single file at once. + * * What: /sys/fs/orangefs/acache/... * Date: Jun 2015 * Contact: Martin Brandenburg <martin@omnibond.com> @@ -329,7 +336,8 @@ static ssize_t sysfs_service_op_show(struct kobject *kobj, if (!(orangefs_features & ORANGEFS_FEATURE_READAHEAD) && (!strcmp(attr->attr.name, "readahead_count") || !strcmp(attr->attr.name, "readahead_size") || - !strcmp(attr->attr.name, "readahead_count_size"))) { + !strcmp(attr->attr.name, "readahead_count_size") || + !strcmp(attr->attr.name, "readahead_readcnt"))) { rc = -EINVAL; goto out; } @@ -360,6 +368,11 @@ static ssize_t sysfs_service_op_show(struct kobject *kobj, "readahead_count_size")) new_op->upcall.req.param.op = ORANGEFS_PARAM_REQUEST_OP_READAHEAD_COUNT_SIZE; + + else if (!strcmp(attr->attr.name, + "readahead_readcnt")) + new_op->upcall.req.param.op = + ORANGEFS_PARAM_REQUEST_OP_READAHEAD_READCNT; } else if (!strcmp(kobj->name, ACACHE_KOBJ_ID)) { if (!strcmp(attr->attr.name, "timeout_msecs")) new_op->upcall.req.param.op = @@ -542,7 +555,8 @@ static ssize_t sysfs_service_op_store(struct kobject *kobj, if (!(orangefs_features & ORANGEFS_FEATURE_READAHEAD) && (!strcmp(attr->attr.name, "readahead_count") || !strcmp(attr->attr.name, "readahead_size") || - !strcmp(attr->attr.name, "readahead_count_size"))) { + !strcmp(attr->attr.name, "readahead_count_size") || + !strcmp(attr->attr.name, "readahead_readcnt"))) { rc = -EINVAL; goto out; } @@ -609,6 +623,15 @@ static ssize_t sysfs_service_op_store(struct kobject *kobj, new_op->upcall.req.param.u.value32[0] = val1; new_op->upcall.req.param.u.value32[1] = val2; goto value_set; + } else if (!strcmp(attr->attr.name, + "readahead_readcnt")) { + if ((val >= 0)) { + new_op->upcall.req.param.op = + ORANGEFS_PARAM_REQUEST_OP_READAHEAD_READCNT; + } else { + rc = 0; + goto out; + } } } else if (!strcmp(kobj->name, ACACHE_KOBJ_ID)) { @@ -812,6 +835,10 @@ static struct orangefs_attribute readahead_count_size_attribute = __ATTR(readahead_count_size, 0664, sysfs_service_op_show, sysfs_service_op_store); +static struct orangefs_attribute readahead_readcnt_attribute = + __ATTR(readahead_readcnt, 0664, sysfs_service_op_show, + sysfs_service_op_store); + static struct orangefs_attribute perf_counter_reset_attribute = __ATTR(perf_counter_reset, 0664, @@ -838,6 +865,7 @@ static struct attribute *orangefs_default_attrs[] = { &readahead_count_attribute.attr, &readahead_size_attribute.attr, &readahead_count_size_attribute.attr, + &readahead_readcnt_attribute.attr, &perf_counter_reset_attribute.attr, &perf_history_size_attribute.attr, &perf_time_interval_secs_attribute.attr, diff --git a/fs/orangefs/orangefs-utils.c b/fs/orangefs/orangefs-utils.c index 06af81f71e10..9b96b99539d6 100644 --- a/fs/orangefs/orangefs-utils.c +++ b/fs/orangefs/orangefs-utils.c @@ -306,7 +306,7 @@ int orangefs_inode_getattr(struct inode *inode, int new, int bypass) break; case S_IFDIR: inode->i_size = PAGE_SIZE; - orangefs_inode->blksize = (1 << inode->i_blkbits); + orangefs_inode->blksize = i_blocksize(inode); spin_lock(&inode->i_lock); inode_set_bytes(inode, inode->i_size); spin_unlock(&inode->i_lock); @@ -316,7 +316,7 @@ int orangefs_inode_getattr(struct inode *inode, int new, int bypass) if (new) { inode->i_size = (loff_t)strlen(new_op-> downcall.resp.getattr.link_target); - orangefs_inode->blksize = (1 << inode->i_blkbits); + orangefs_inode->blksize = i_blocksize(inode); ret = strscpy(orangefs_inode->link_target, new_op->downcall.resp.getattr.link_target, ORANGEFS_NAME_MAX); diff --git a/fs/orangefs/upcall.h b/fs/orangefs/upcall.h index af0b0e36d559..b8249f8fdd80 100644 --- a/fs/orangefs/upcall.h +++ b/fs/orangefs/upcall.h @@ -182,6 +182,7 @@ enum orangefs_param_request_op { ORANGEFS_PARAM_REQUEST_OP_READAHEAD_SIZE = 26, ORANGEFS_PARAM_REQUEST_OP_READAHEAD_COUNT = 27, ORANGEFS_PARAM_REQUEST_OP_READAHEAD_COUNT_SIZE = 28, + ORANGEFS_PARAM_REQUEST_OP_READAHEAD_READCNT = 29, }; struct orangefs_param_request_s { diff --git a/fs/pnode.c b/fs/pnode.c index 06a793f4ae38..5bc7896d122a 100644 --- a/fs/pnode.c +++ b/fs/pnode.c @@ -322,6 +322,21 @@ out: return ret; } +static struct mount *find_topper(struct mount *mnt) +{ + /* If there is exactly one mount covering mnt completely return it. */ + struct mount *child; + + if (!list_is_singular(&mnt->mnt_mounts)) + return NULL; + + child = list_first_entry(&mnt->mnt_mounts, struct mount, mnt_child); + if (child->mnt_mountpoint != mnt->mnt.mnt_root) + return NULL; + + return child; +} + /* * return true if the refcount is greater than count */ @@ -342,9 +357,8 @@ static inline int do_refcount_check(struct mount *mnt, int count) */ int propagate_mount_busy(struct mount *mnt, int refcnt) { - struct mount *m, *child; + struct mount *m, *child, *topper; struct mount *parent = mnt->mnt_parent; - int ret = 0; if (mnt == parent) return do_refcount_check(mnt, refcnt); @@ -359,12 +373,24 @@ int propagate_mount_busy(struct mount *mnt, int refcnt) for (m = propagation_next(parent, parent); m; m = propagation_next(m, parent)) { - child = __lookup_mnt_last(&m->mnt, mnt->mnt_mountpoint); - if (child && list_empty(&child->mnt_mounts) && - (ret = do_refcount_check(child, 1))) - break; + int count = 1; + child = __lookup_mnt(&m->mnt, mnt->mnt_mountpoint); + if (!child) + continue; + + /* Is there exactly one mount on the child that covers + * it completely whose reference should be ignored? + */ + topper = find_topper(child); + if (topper) + count += 1; + else if (!list_empty(&child->mnt_mounts)) + continue; + + if (do_refcount_check(child, count)) + return 1; } - return ret; + return 0; } /* @@ -381,7 +407,7 @@ void propagate_mount_unlock(struct mount *mnt) for (m = propagation_next(parent, parent); m; m = propagation_next(m, parent)) { - child = __lookup_mnt_last(&m->mnt, mnt->mnt_mountpoint); + child = __lookup_mnt(&m->mnt, mnt->mnt_mountpoint); if (child) child->mnt.mnt_flags &= ~MNT_LOCKED; } @@ -399,9 +425,11 @@ static void mark_umount_candidates(struct mount *mnt) for (m = propagation_next(parent, parent); m; m = propagation_next(m, parent)) { - struct mount *child = __lookup_mnt_last(&m->mnt, + struct mount *child = __lookup_mnt(&m->mnt, mnt->mnt_mountpoint); - if (child && (!IS_MNT_LOCKED(child) || IS_MNT_MARKED(m))) { + if (!child || (child->mnt.mnt_flags & MNT_UMOUNT)) + continue; + if (!IS_MNT_LOCKED(child) || IS_MNT_MARKED(m)) { SET_MNT_MARK(child); } } @@ -420,8 +448,8 @@ static void __propagate_umount(struct mount *mnt) for (m = propagation_next(parent, parent); m; m = propagation_next(m, parent)) { - - struct mount *child = __lookup_mnt_last(&m->mnt, + struct mount *topper; + struct mount *child = __lookup_mnt(&m->mnt, mnt->mnt_mountpoint); /* * umount the child only if the child has no children @@ -430,6 +458,15 @@ static void __propagate_umount(struct mount *mnt) if (!child || !IS_MNT_MARKED(child)) continue; CLEAR_MNT_MARK(child); + + /* If there is exactly one mount covering all of child + * replace child with that mount. + */ + topper = find_topper(child); + if (topper) + mnt_change_mountpoint(child->mnt_parent, child->mnt_mp, + topper); + if (list_empty(&child->mnt_mounts)) { list_del_init(&child->mnt_child); child->mnt.mnt_flags |= MNT_UMOUNT; diff --git a/fs/pnode.h b/fs/pnode.h index 550f5a8b4fcf..dc87e65becd2 100644 --- a/fs/pnode.h +++ b/fs/pnode.h @@ -49,6 +49,8 @@ int get_dominating_id(struct mount *mnt, const struct path *root); unsigned int mnt_get_count(struct mount *mnt); void mnt_set_mountpoint(struct mount *, struct mountpoint *, struct mount *); +void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp, + struct mount *mnt); struct mount *copy_tree(struct mount *, struct dentry *, int); bool is_path_reachable(struct mount *, struct dentry *, const struct path *root); diff --git a/fs/proc/base.c b/fs/proc/base.c index b1f7d30e96c2..1e1e182d571b 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -292,101 +292,69 @@ static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf, } } else { /* - * Command line (1 string) occupies ARGV and maybe - * extends into ENVP. - */ - if (len1 + len2 <= *pos) - goto skip_argv_envp; - if (len1 <= *pos) - goto skip_argv; - - p = arg_start + *pos; - len = len1 - *pos; - while (count > 0 && len > 0) { - unsigned int _count, l; - int nr_read; - bool final; - - _count = min3(count, len, PAGE_SIZE); - nr_read = access_remote_vm(mm, p, page, _count, 0); - if (nr_read < 0) - rv = nr_read; - if (nr_read <= 0) - goto out_free_page; - - /* - * Command line can be shorter than whole ARGV - * even if last "marker" byte says it is not. - */ - final = false; - l = strnlen(page, nr_read); - if (l < nr_read) { - nr_read = l; - final = true; - } - - if (copy_to_user(buf, page, nr_read)) { - rv = -EFAULT; - goto out_free_page; - } - - p += nr_read; - len -= nr_read; - buf += nr_read; - count -= nr_read; - rv += nr_read; - - if (final) - goto out_free_page; - } -skip_argv: - /* * Command line (1 string) occupies ARGV and * extends into ENVP. */ - if (len1 <= *pos) { - p = env_start + *pos - len1; - len = len1 + len2 - *pos; - } else { - p = env_start; - len = len2; + struct { + unsigned long p; + unsigned long len; + } cmdline[2] = { + { .p = arg_start, .len = len1 }, + { .p = env_start, .len = len2 }, + }; + loff_t pos1 = *pos; + unsigned int i; + + i = 0; + while (i < 2 && pos1 >= cmdline[i].len) { + pos1 -= cmdline[i].len; + i++; } - while (count > 0 && len > 0) { - unsigned int _count, l; - int nr_read; - bool final; - - _count = min3(count, len, PAGE_SIZE); - nr_read = access_remote_vm(mm, p, page, _count, 0); - if (nr_read < 0) - rv = nr_read; - if (nr_read <= 0) - goto out_free_page; - - /* Find EOS. */ - final = false; - l = strnlen(page, nr_read); - if (l < nr_read) { - nr_read = l; - final = true; + while (i < 2) { + p = cmdline[i].p + pos1; + len = cmdline[i].len - pos1; + while (count > 0 && len > 0) { + unsigned int _count, l; + int nr_read; + bool final; + + _count = min3(count, len, PAGE_SIZE); + nr_read = access_remote_vm(mm, p, page, _count, 0); + if (nr_read < 0) + rv = nr_read; + if (nr_read <= 0) + goto out_free_page; + + /* + * Command line can be shorter than whole ARGV + * even if last "marker" byte says it is not. + */ + final = false; + l = strnlen(page, nr_read); + if (l < nr_read) { + nr_read = l; + final = true; + } + + if (copy_to_user(buf, page, nr_read)) { + rv = -EFAULT; + goto out_free_page; + } + + p += nr_read; + len -= nr_read; + buf += nr_read; + count -= nr_read; + rv += nr_read; + + if (final) + goto out_free_page; } - if (copy_to_user(buf, page, nr_read)) { - rv = -EFAULT; - goto out_free_page; - } - - p += nr_read; - len -= nr_read; - buf += nr_read; - count -= nr_read; - rv += nr_read; - - if (final) - goto out_free_page; + /* Only first chunk can be read partially. */ + pos1 = 0; + i++; } -skip_argv_envp: - ; } out_free_page: @@ -729,11 +697,11 @@ static int proc_pid_permission(struct inode *inode, int mask) task = get_proc_task(inode); if (!task) return -ESRCH; - has_perms = has_pid_permissions(pid, task, 1); + has_perms = has_pid_permissions(pid, task, HIDEPID_NO_ACCESS); put_task_struct(task); if (!has_perms) { - if (pid->hide_pid == 2) { + if (pid->hide_pid == HIDEPID_INVISIBLE) { /* * Let's make getdents(), stat(), and open() * consistent with each other. If a process @@ -798,7 +766,7 @@ struct mm_struct *proc_mem_open(struct inode *inode, unsigned int mode) if (!IS_ERR_OR_NULL(mm)) { /* ensure this mm_struct can't be freed */ - atomic_inc(&mm->mm_count); + mmgrab(mm); /* but do not pin its memory */ mmput(mm); } @@ -845,7 +813,7 @@ static ssize_t mem_rw(struct file *file, char __user *buf, return -ENOMEM; copied = 0; - if (!atomic_inc_not_zero(&mm->mm_users)) + if (!mmget_not_zero(mm)) goto free; /* Maybe we should limit FOLL_FORCE to actual ptrace users? */ @@ -953,7 +921,7 @@ static ssize_t environ_read(struct file *file, char __user *buf, return -ENOMEM; ret = 0; - if (!atomic_inc_not_zero(&mm->mm_users)) + if (!mmget_not_zero(mm)) goto free; down_read(&mm->mmap_sem); @@ -1096,7 +1064,7 @@ static int __set_oom_adj(struct file *file, int oom_adj, bool legacy) if (p) { if (atomic_read(&p->mm->mm_users) > 1) { mm = p->mm; - atomic_inc(&mm->mm_count); + mmgrab(mm); } task_unlock(p); } @@ -1667,12 +1635,63 @@ const struct inode_operations proc_pid_link_inode_operations = { /* building an inode */ +void task_dump_owner(struct task_struct *task, mode_t mode, + kuid_t *ruid, kgid_t *rgid) +{ + /* Depending on the state of dumpable compute who should own a + * proc file for a task. + */ + const struct cred *cred; + kuid_t uid; + kgid_t gid; + + /* Default to the tasks effective ownership */ + rcu_read_lock(); + cred = __task_cred(task); + uid = cred->euid; + gid = cred->egid; + rcu_read_unlock(); + + /* + * Before the /proc/pid/status file was created the only way to read + * the effective uid of a /process was to stat /proc/pid. Reading + * /proc/pid/status is slow enough that procps and other packages + * kept stating /proc/pid. To keep the rules in /proc simple I have + * made this apply to all per process world readable and executable + * directories. + */ + if (mode != (S_IFDIR|S_IRUGO|S_IXUGO)) { + struct mm_struct *mm; + task_lock(task); + mm = task->mm; + /* Make non-dumpable tasks owned by some root */ + if (mm) { + if (get_dumpable(mm) != SUID_DUMP_USER) { + struct user_namespace *user_ns = mm->user_ns; + + uid = make_kuid(user_ns, 0); + if (!uid_valid(uid)) + uid = GLOBAL_ROOT_UID; + + gid = make_kgid(user_ns, 0); + if (!gid_valid(gid)) + gid = GLOBAL_ROOT_GID; + } + } else { + uid = GLOBAL_ROOT_UID; + gid = GLOBAL_ROOT_GID; + } + task_unlock(task); + } + *ruid = uid; + *rgid = gid; +} + struct inode *proc_pid_make_inode(struct super_block * sb, struct task_struct *task, umode_t mode) { struct inode * inode; struct proc_inode *ei; - const struct cred *cred; /* We need a new inode */ @@ -1694,13 +1713,7 @@ struct inode *proc_pid_make_inode(struct super_block * sb, if (!ei->pid) goto out_unlock; - if (task_dumpable(task)) { - rcu_read_lock(); - cred = __task_cred(task); - inode->i_uid = cred->euid; - inode->i_gid = cred->egid; - rcu_read_unlock(); - } + task_dump_owner(task, 0, &inode->i_uid, &inode->i_gid); security_task_to_inode(task, inode); out: @@ -1715,7 +1728,6 @@ int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) { struct inode *inode = d_inode(dentry); struct task_struct *task; - const struct cred *cred; struct pid_namespace *pid = dentry->d_sb->s_fs_info; generic_fillattr(inode, stat); @@ -1725,7 +1737,7 @@ int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) stat->gid = GLOBAL_ROOT_GID; task = pid_task(proc_pid(inode), PIDTYPE_PID); if (task) { - if (!has_pid_permissions(pid, task, 2)) { + if (!has_pid_permissions(pid, task, HIDEPID_INVISIBLE)) { rcu_read_unlock(); /* * This doesn't prevent learning whether PID exists, @@ -1733,12 +1745,7 @@ int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) */ return -ENOENT; } - if ((inode->i_mode == (S_IFDIR|S_IRUGO|S_IXUGO)) || - task_dumpable(task)) { - cred = __task_cred(task); - stat->uid = cred->euid; - stat->gid = cred->egid; - } + task_dump_owner(task, inode->i_mode, &stat->uid, &stat->gid); } rcu_read_unlock(); return 0; @@ -1754,18 +1761,11 @@ int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) * Rewrite the inode's ownerships here because the owning task may have * performed a setuid(), etc. * - * Before the /proc/pid/status file was created the only way to read - * the effective uid of a /process was to stat /proc/pid. Reading - * /proc/pid/status is slow enough that procps and other packages - * kept stating /proc/pid. To keep the rules in /proc simple I have - * made this apply to all per process world readable and executable - * directories. */ int pid_revalidate(struct dentry *dentry, unsigned int flags) { struct inode *inode; struct task_struct *task; - const struct cred *cred; if (flags & LOOKUP_RCU) return -ECHILD; @@ -1774,17 +1774,8 @@ int pid_revalidate(struct dentry *dentry, unsigned int flags) task = get_proc_task(inode); if (task) { - if ((inode->i_mode == (S_IFDIR|S_IRUGO|S_IXUGO)) || - task_dumpable(task)) { - rcu_read_lock(); - cred = __task_cred(task); - inode->i_uid = cred->euid; - inode->i_gid = cred->egid; - rcu_read_unlock(); - } else { - inode->i_uid = GLOBAL_ROOT_UID; - inode->i_gid = GLOBAL_ROOT_GID; - } + task_dump_owner(task, inode->i_mode, &inode->i_uid, &inode->i_gid); + inode->i_mode &= ~(S_ISUID | S_ISGID); security_task_to_inode(task, inode); put_task_struct(task); @@ -1881,7 +1872,6 @@ static int map_files_d_revalidate(struct dentry *dentry, unsigned int flags) bool exact_vma_exists = false; struct mm_struct *mm = NULL; struct task_struct *task; - const struct cred *cred; struct inode *inode; int status = 0; @@ -1906,16 +1896,8 @@ static int map_files_d_revalidate(struct dentry *dentry, unsigned int flags) mmput(mm); if (exact_vma_exists) { - if (task_dumpable(task)) { - rcu_read_lock(); - cred = __task_cred(task); - inode->i_uid = cred->euid; - inode->i_gid = cred->egid; - rcu_read_unlock(); - } else { - inode->i_uid = GLOBAL_ROOT_UID; - inode->i_gid = GLOBAL_ROOT_GID; - } + task_dump_owner(task, 0, &inode->i_uid, &inode->i_gid); + security_task_to_inode(task, inode); status = 1; } @@ -2488,6 +2470,12 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf, length = -ESRCH; if (!task) goto out_no_task; + + /* A task may only write its own attributes. */ + length = -EACCES; + if (current != task) + goto out; + if (count > PAGE_SIZE) count = PAGE_SIZE; @@ -2503,14 +2491,13 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf, } /* Guard against adverse ptrace interaction */ - length = mutex_lock_interruptible(&task->signal->cred_guard_mutex); + length = mutex_lock_interruptible(¤t->signal->cred_guard_mutex); if (length < 0) goto out_free; - length = security_setprocattr(task, - (char*)file->f_path.dentry->d_name.name, + length = security_setprocattr(file->f_path.dentry->d_name.name, page, count); - mutex_unlock(&task->signal->cred_guard_mutex); + mutex_unlock(¤t->signal->cred_guard_mutex); out_free: kfree(page); out: @@ -3181,7 +3168,7 @@ int proc_pid_readdir(struct file *file, struct dir_context *ctx) int len; cond_resched(); - if (!has_pid_permissions(ns, iter.task, 2)) + if (!has_pid_permissions(ns, iter.task, HIDEPID_INVISIBLE)) continue; len = snprintf(name, sizeof(name), "%d", iter.tgid); diff --git a/fs/proc/fd.c b/fs/proc/fd.c index 4274f83bf100..00ce1531b2f5 100644 --- a/fs/proc/fd.c +++ b/fs/proc/fd.c @@ -84,7 +84,6 @@ static int tid_fd_revalidate(struct dentry *dentry, unsigned int flags) { struct files_struct *files; struct task_struct *task; - const struct cred *cred; struct inode *inode; unsigned int fd; @@ -108,16 +107,7 @@ static int tid_fd_revalidate(struct dentry *dentry, unsigned int flags) rcu_read_unlock(); put_files_struct(files); - if (task_dumpable(task)) { - rcu_read_lock(); - cred = __task_cred(task); - inode->i_uid = cred->euid; - inode->i_gid = cred->egid; - rcu_read_unlock(); - } else { - inode->i_uid = GLOBAL_ROOT_UID; - inode->i_gid = GLOBAL_ROOT_GID; - } + task_dump_owner(task, 0, &inode->i_uid, &inode->i_gid); if (S_ISLNK(inode->i_mode)) { unsigned i_mode = S_IFLNK; diff --git a/fs/proc/generic.c b/fs/proc/generic.c index f6a01f09f79d..06c73904d497 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -57,9 +57,9 @@ static struct proc_dir_entry *pde_subdir_find(struct proc_dir_entry *dir, struct rb_node *node = dir->subdir.rb_node; while (node) { - struct proc_dir_entry *de = container_of(node, - struct proc_dir_entry, - subdir_node); + struct proc_dir_entry *de = rb_entry(node, + struct proc_dir_entry, + subdir_node); int result = proc_match(len, name, de); if (result < 0) @@ -80,8 +80,9 @@ static bool pde_subdir_insert(struct proc_dir_entry *dir, /* Figure out where to put new node */ while (*new) { - struct proc_dir_entry *this = - container_of(*new, struct proc_dir_entry, subdir_node); + struct proc_dir_entry *this = rb_entry(*new, + struct proc_dir_entry, + subdir_node); int result = proc_match(de->namelen, de->name, this); parent = *new; diff --git a/fs/proc/inode.c b/fs/proc/inode.c index 842a5ff5b85c..2cc7a8030275 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -43,10 +43,11 @@ static void proc_evict_inode(struct inode *inode) de = PDE(inode); if (de) pde_put(de); + head = PROC_I(inode)->sysctl; if (head) { RCU_INIT_POINTER(PROC_I(inode)->sysctl, NULL); - sysctl_head_put(head); + proc_sys_evict_inode(inode, head); } } @@ -106,7 +107,7 @@ static int proc_show_options(struct seq_file *seq, struct dentry *root) if (!gid_eq(pid->pid_gid, GLOBAL_ROOT_GID)) seq_printf(seq, ",gid=%u", from_kgid_munged(&init_user_ns, pid->pid_gid)); - if (pid->hide_pid != 0) + if (pid->hide_pid != HIDEPID_OFF) seq_printf(seq, ",hidepid=%u", pid->hide_pid); return 0; diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 2de5194ba378..5d6960f5f1c0 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -65,6 +65,7 @@ struct proc_inode { struct proc_dir_entry *pde; struct ctl_table_header *sysctl; struct ctl_table *sysctl_entry; + struct list_head sysctl_inodes; const struct proc_ns_operations *ns_ops; struct inode vfs_inode; }; @@ -97,20 +98,8 @@ static inline struct task_struct *get_proc_task(struct inode *inode) return get_pid_task(proc_pid(inode), PIDTYPE_PID); } -static inline int task_dumpable(struct task_struct *task) -{ - int dumpable = 0; - struct mm_struct *mm; - - task_lock(task); - mm = task->mm; - if (mm) - dumpable = get_dumpable(mm); - task_unlock(task); - if (dumpable == SUID_DUMP_USER) - return 1; - return 0; -} +void task_dump_owner(struct task_struct *task, mode_t mode, + kuid_t *ruid, kgid_t *rgid); static inline unsigned name_to_int(const struct qstr *qstr) { @@ -249,10 +238,12 @@ extern void proc_thread_self_init(void); */ #ifdef CONFIG_PROC_SYSCTL extern int proc_sys_init(void); -extern void sysctl_head_put(struct ctl_table_header *); +extern void proc_sys_evict_inode(struct inode *inode, + struct ctl_table_header *head); #else static inline void proc_sys_init(void) { } -static inline void sysctl_head_put(struct ctl_table_header *head) { } +static inline void proc_sys_evict_inode(struct inode *inode, + struct ctl_table_header *head) { } #endif /* diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index 0b80ad87b4d6..ea9f3d1ae830 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -373,7 +373,10 @@ static void elf_kcore_store_hdr(char *bufp, int nphdr, int dataoff) phdr->p_flags = PF_R|PF_W|PF_X; phdr->p_offset = kc_vaddr_to_offset(m->addr) + dataoff; phdr->p_vaddr = (size_t)m->addr; - phdr->p_paddr = 0; + if (m->type == KCORE_RAM || m->type == KCORE_TEXT) + phdr->p_paddr = __pa(m->addr); + else + phdr->p_paddr = (elf_addr_t)-1; phdr->p_filesz = phdr->p_memsz = m->size; phdr->p_align = PAGE_SIZE; } diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index d4e37acd4821..3e64c6502dc8 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -190,6 +190,7 @@ static void init_header(struct ctl_table_header *head, head->set = set; head->parent = NULL; head->node = node; + INIT_LIST_HEAD(&head->inodes); if (node) { struct ctl_table *entry; for (entry = table; entry->procname; entry++, node++) @@ -259,6 +260,27 @@ static void unuse_table(struct ctl_table_header *p) complete(p->unregistering); } +/* called under sysctl_lock */ +static void proc_sys_prune_dcache(struct ctl_table_header *head) +{ + struct inode *inode, *prev = NULL; + struct proc_inode *ei; + + rcu_read_lock(); + list_for_each_entry_rcu(ei, &head->inodes, sysctl_inodes) { + inode = igrab(&ei->vfs_inode); + if (inode) { + rcu_read_unlock(); + iput(prev); + prev = inode; + d_prune_aliases(inode); + rcu_read_lock(); + } + } + rcu_read_unlock(); + iput(prev); +} + /* called under sysctl_lock, will reacquire if has to wait */ static void start_unregistering(struct ctl_table_header *p) { @@ -272,31 +294,22 @@ static void start_unregistering(struct ctl_table_header *p) p->unregistering = &wait; spin_unlock(&sysctl_lock); wait_for_completion(&wait); - spin_lock(&sysctl_lock); } else { /* anything non-NULL; we'll never dereference it */ p->unregistering = ERR_PTR(-EINVAL); + spin_unlock(&sysctl_lock); } /* + * Prune dentries for unregistered sysctls: namespaced sysctls + * can have duplicate names and contaminate dcache very badly. + */ + proc_sys_prune_dcache(p); + /* * do not remove from the list until nobody holds it; walking the * list in do_sysctl() relies on that. */ - erase_header(p); -} - -static void sysctl_head_get(struct ctl_table_header *head) -{ spin_lock(&sysctl_lock); - head->count++; - spin_unlock(&sysctl_lock); -} - -void sysctl_head_put(struct ctl_table_header *head) -{ - spin_lock(&sysctl_lock); - if (!--head->count) - kfree_rcu(head, rcu); - spin_unlock(&sysctl_lock); + erase_header(p); } static struct ctl_table_header *sysctl_head_grab(struct ctl_table_header *head) @@ -440,10 +453,20 @@ static struct inode *proc_sys_make_inode(struct super_block *sb, inode->i_ino = get_next_ino(); - sysctl_head_get(head); ei = PROC_I(inode); + + spin_lock(&sysctl_lock); + if (unlikely(head->unregistering)) { + spin_unlock(&sysctl_lock); + iput(inode); + inode = NULL; + goto out; + } ei->sysctl = head; ei->sysctl_entry = table; + list_add_rcu(&ei->sysctl_inodes, &head->inodes); + head->count++; + spin_unlock(&sysctl_lock); inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode); inode->i_mode = table->mode; @@ -466,6 +489,15 @@ out: return inode; } +void proc_sys_evict_inode(struct inode *inode, struct ctl_table_header *head) +{ + spin_lock(&sysctl_lock); + list_del_rcu(&PROC_I(inode)->sysctl_inodes); + if (!--head->count) + kfree_rcu(head, rcu); + spin_unlock(&sysctl_lock); +} + static struct ctl_table_header *grab_header(struct inode *inode) { struct ctl_table_header *head = PROC_I(inode)->sysctl; diff --git a/fs/proc/root.c b/fs/proc/root.c index 1988440b2049..b90da888b81a 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -58,7 +58,8 @@ int proc_parse_options(char *options, struct pid_namespace *pid) case Opt_hidepid: if (match_int(&args[0], &option)) return 0; - if (option < 0 || option > 2) { + if (option < HIDEPID_OFF || + option > HIDEPID_INVISIBLE) { pr_err("proc: hidepid value must be between 0 and 2.\n"); return 0; } diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 8f96a49178d0..ee3efb229ef6 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -167,7 +167,7 @@ static void *m_start(struct seq_file *m, loff_t *ppos) return ERR_PTR(-ESRCH); mm = priv->mm; - if (!mm || !atomic_inc_not_zero(&mm->mm_users)) + if (!mm || !mmget_not_zero(mm)) return NULL; down_read(&mm->mmap_sem); @@ -1352,7 +1352,7 @@ static ssize_t pagemap_read(struct file *file, char __user *buf, unsigned long end_vaddr; int ret = 0, copied = 0; - if (!mm || !atomic_inc_not_zero(&mm->mm_users)) + if (!mm || !mmget_not_zero(mm)) goto out; ret = -EINVAL; diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c index 37175621e890..1ef97cfcf422 100644 --- a/fs/proc/task_nommu.c +++ b/fs/proc/task_nommu.c @@ -219,7 +219,7 @@ static void *m_start(struct seq_file *m, loff_t *pos) return ERR_PTR(-ESRCH); mm = priv->mm; - if (!mm || !atomic_inc_not_zero(&mm->mm_users)) + if (!mm || !mmget_not_zero(mm)) return NULL; down_read(&mm->mmap_sem); diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index 5105b1599981..885d445afa0d 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -265,10 +265,10 @@ static ssize_t read_vmcore(struct file *file, char __user *buffer, * On s390 the fault handler is used for memory regions that can't be mapped * directly with remap_pfn_range(). */ -static int mmap_vmcore_fault(struct vm_area_struct *vma, struct vm_fault *vmf) +static int mmap_vmcore_fault(struct vm_fault *vmf) { #ifdef CONFIG_S390 - struct address_space *mapping = vma->vm_file->f_mapping; + struct address_space *mapping = vmf->vma->vm_file->f_mapping; pgoff_t index = vmf->pgoff; struct page *page; loff_t offset; @@ -388,7 +388,7 @@ static int remap_oldmem_pfn_checked(struct vm_area_struct *vma, } return 0; fail: - do_munmap(vma->vm_mm, from, len); + do_munmap(vma->vm_mm, from, len, NULL); return -EAGAIN; } @@ -481,7 +481,7 @@ static int mmap_vmcore(struct file *file, struct vm_area_struct *vma) return 0; fail: - do_munmap(vma->vm_mm, vma->vm_start, len); + do_munmap(vma->vm_mm, vma->vm_start, len, NULL); return -EAGAIN; } #else diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index 729677e18e36..efab7b64925b 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -342,31 +342,35 @@ static int compress_lz4(const void *in, void *out, size_t inlen, size_t outlen) { int ret; - ret = lz4_compress(in, inlen, out, &outlen, workspace); - if (ret) { - pr_err("lz4_compress error, ret = %d!\n", ret); + ret = LZ4_compress_default(in, out, inlen, outlen, workspace); + if (!ret) { + pr_err("LZ4_compress_default error; compression failed!\n"); return -EIO; } - return outlen; + return ret; } static int decompress_lz4(void *in, void *out, size_t inlen, size_t outlen) { int ret; - ret = lz4_decompress_unknownoutputsize(in, inlen, out, &outlen); - if (ret) { - pr_err("lz4_decompress error, ret = %d!\n", ret); + ret = LZ4_decompress_safe(in, out, inlen, outlen); + if (ret < 0) { + /* + * LZ4_decompress_safe will return an error code + * (< 0) if decompression failed + */ + pr_err("LZ4_decompress_safe error, ret = %d!\n", ret); return -EIO; } - return outlen; + return ret; } static void allocate_lz4(void) { - big_oops_buf_sz = lz4_compressbound(psinfo->bufsize); + big_oops_buf_sz = LZ4_compressBound(psinfo->bufsize); big_oops_buf = kmalloc(big_oops_buf_sz, GFP_KERNEL); if (big_oops_buf) { workspace = kmalloc(LZ4_MEM_COMPRESS, GFP_KERNEL); diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index 1d887efaaf71..11f918d34b1e 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -133,7 +133,8 @@ ramoops_get_next_prz(struct persistent_ram_zone *przs[], uint *c, uint max, struct persistent_ram_zone *prz; int i = (*c)++; - if (i >= max) + /* Give up if we never existed or have hit the end. */ + if (!przs || i >= max) return NULL; prz = przs[i]; @@ -280,7 +281,7 @@ static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type, 1, id, type, PSTORE_TYPE_PMSG, 0); /* ftrace is last since it may want to dynamically allocate memory. */ - if (!prz_ok(prz) && cxt->fprzs) { + if (!prz_ok(prz)) { if (!(cxt->flags & RAMOOPS_FLAG_FTRACE_PER_CPU)) { prz = ramoops_get_next_prz(cxt->fprzs, &cxt->ftrace_read_cnt, 1, id, type, diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c index a857338b7dab..bc927e30bdcc 100644 --- a/fs/pstore/ram_core.c +++ b/fs/pstore/ram_core.c @@ -467,8 +467,7 @@ static int persistent_ram_buffer_map(phys_addr_t start, phys_addr_t size, } static int persistent_ram_post_init(struct persistent_ram_zone *prz, u32 sig, - struct persistent_ram_ecc_info *ecc_info, - unsigned long flags) + struct persistent_ram_ecc_info *ecc_info) { int ret; @@ -494,10 +493,9 @@ static int persistent_ram_post_init(struct persistent_ram_zone *prz, u32 sig, prz->buffer->sig); } + /* Rewind missing or invalid memory area. */ prz->buffer->sig = sig; persistent_ram_zap(prz); - prz->buffer_lock = __RAW_SPIN_LOCK_UNLOCKED(buffer_lock); - prz->flags = flags; return 0; } @@ -533,11 +531,15 @@ struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size, goto err; } + /* Initialize general buffer state. */ + prz->buffer_lock = __RAW_SPIN_LOCK_UNLOCKED(buffer_lock); + prz->flags = flags; + ret = persistent_ram_buffer_map(start, size, prz, memtype); if (ret) goto err; - ret = persistent_ram_post_init(prz, sig, ecc_info, flags); + ret = persistent_ram_post_init(prz, sig, ecc_info); if (ret) goto err; diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c index 2f8c5c9bdaf6..b396eb09f288 100644 --- a/fs/reiserfs/file.c +++ b/fs/reiserfs/file.c @@ -189,7 +189,7 @@ int reiserfs_commit_page(struct inode *inode, struct page *page, int ret = 0; th.t_trans_id = 0; - blocksize = 1 << inode->i_blkbits; + blocksize = i_blocksize(inode); if (logit) { reiserfs_write_lock(s); diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index cfeae9b0a2b7..a6ab9d64ea1b 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -525,7 +525,7 @@ static int reiserfs_get_blocks_direct_io(struct inode *inode, * referenced in convert_tail_for_hole() that may be called from * reiserfs_get_block() */ - bh_result->b_size = (1 << inode->i_blkbits); + bh_result->b_size = i_blocksize(inode); ret = reiserfs_get_block(inode, iblock, bh_result, create | GET_BLOCK_NO_DANGLE); diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index e314cb30a181..feabcde0290d 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -1166,7 +1166,7 @@ static int reiserfs_parse_options(struct super_block *s, if (!strcmp(arg, "auto")) { /* From JFS code, to auto-get the size. */ *blocks = - s->s_bdev->bd_inode->i_size >> s-> + i_size_read(s->s_bdev->bd_inode) >> s-> s_blocksize_bits; } else { *blocks = simple_strtoul(arg, &p, 0); diff --git a/fs/squashfs/lz4_wrapper.c b/fs/squashfs/lz4_wrapper.c index ff4468bd18b0..95da65366548 100644 --- a/fs/squashfs/lz4_wrapper.c +++ b/fs/squashfs/lz4_wrapper.c @@ -97,7 +97,6 @@ static int lz4_uncompress(struct squashfs_sb_info *msblk, void *strm, struct squashfs_lz4 *stream = strm; void *buff = stream->input, *data; int avail, i, bytes = length, res; - size_t dest_len = output->length; for (i = 0; i < b; i++) { avail = min(bytes, msblk->devblksize - offset); @@ -108,12 +107,13 @@ static int lz4_uncompress(struct squashfs_sb_info *msblk, void *strm, put_bh(bh[i]); } - res = lz4_decompress_unknownoutputsize(stream->input, length, - stream->output, &dest_len); - if (res) + res = LZ4_decompress_safe(stream->input, stream->output, + length, output->length); + + if (res < 0) return -EIO; - bytes = dest_len; + bytes = res; data = squashfs_first_page(output); buff = stream->output; while (data) { @@ -128,7 +128,7 @@ static int lz4_uncompress(struct squashfs_sb_info *msblk, void *strm, } squashfs_finish_page(output); - return dest_len; + return res; } const struct squashfs_decompressor squashfs_lz4_comp_ops = { diff --git a/fs/stat.c b/fs/stat.c index a268b7f27adf..3f14d1ef0868 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -31,7 +31,7 @@ void generic_fillattr(struct inode *inode, struct kstat *stat) stat->atime = inode->i_atime; stat->mtime = inode->i_mtime; stat->ctime = inode->i_ctime; - stat->blksize = (1 << inode->i_blkbits); + stat->blksize = i_blocksize(inode); stat->blocks = inode->i_blocks; } diff --git a/fs/super.c b/fs/super.c index 1709ed029a2c..b8b6a086c03b 100644 --- a/fs/super.c +++ b/fs/super.c @@ -469,7 +469,7 @@ struct super_block *sget_userns(struct file_system_type *type, struct super_block *old; int err; - if (!(flags & MS_KERNMOUNT) && + if (!(flags & (MS_KERNMOUNT|MS_SUBMOUNT)) && !(type->fs_flags & FS_USERNS_MOUNT) && !capable(CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); @@ -499,7 +499,7 @@ retry: } if (!s) { spin_unlock(&sb_lock); - s = alloc_super(type, flags, user_ns); + s = alloc_super(type, (flags & ~MS_SUBMOUNT), user_ns); if (!s) return ERR_PTR(-ENOMEM); goto retry; @@ -540,8 +540,15 @@ struct super_block *sget(struct file_system_type *type, { struct user_namespace *user_ns = current_user_ns(); + /* We don't yet pass the user namespace of the parent + * mount through to here so always use &init_user_ns + * until that changes. + */ + if (flags & MS_SUBMOUNT) + user_ns = &init_user_ns; + /* Ensure the requestor has permissions over the target filesystem */ - if (!(flags & MS_KERNMOUNT) && !ns_capable(user_ns, CAP_SYS_ADMIN)) + if (!(flags & (MS_KERNMOUNT|MS_SUBMOUNT)) && !ns_capable(user_ns, CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); return sget_userns(type, test, set, flags, user_ns, data); @@ -1047,7 +1054,7 @@ static int set_bdev_super(struct super_block *s, void *data) * We set the bdi here to the queue backing, file systems can * overwrite this in ->fill_super() */ - s->s_bdi = &bdev_get_queue(s->s_bdev)->backing_dev_info; + s->s_bdi = bdev_get_queue(s->s_bdev)->backing_dev_info; return 0; } diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index b0d783774c96..d9ae86f96df7 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -1506,11 +1506,10 @@ static int ubifs_releasepage(struct page *page, gfp_t unused_gfp_flags) * mmap()d file has taken write protection fault and is being made writable. * UBIFS must ensure page is budgeted for. */ -static int ubifs_vm_page_mkwrite(struct vm_area_struct *vma, - struct vm_fault *vmf) +static int ubifs_vm_page_mkwrite(struct vm_fault *vmf) { struct page *page = vmf->page; - struct inode *inode = file_inode(vma->vm_file); + struct inode *inode = file_inode(vmf->vma->vm_file); struct ubifs_info *c = inode->i_sb->s_fs_info; struct timespec now = ubifs_current_time(inode); struct ubifs_budget_req req = { .new_page = 1 }; diff --git a/fs/udf/ecma_167.h b/fs/udf/ecma_167.h index 4792b771aa80..9f24bd1a9f44 100644 --- a/fs/udf/ecma_167.h +++ b/fs/udf/ecma_167.h @@ -41,7 +41,7 @@ struct charspec { uint8_t charSetType; uint8_t charSetInfo[63]; -} __attribute__ ((packed)); +} __packed; /* Character Set Type (ECMA 167r3 1/7.2.1.1) */ #define CHARSPEC_TYPE_CS0 0x00 /* (1/7.2.2) */ @@ -68,7 +68,7 @@ struct timestamp { uint8_t centiseconds; uint8_t hundredsOfMicroseconds; uint8_t microseconds; -} __attribute__ ((packed)); +} __packed; /* Type and Time Zone (ECMA 167r3 1/7.3.1) */ #define TIMESTAMP_TYPE_MASK 0xF000 @@ -82,7 +82,7 @@ struct regid { uint8_t flags; uint8_t ident[23]; uint8_t identSuffix[8]; -} __attribute__ ((packed)); +} __packed; /* Flags (ECMA 167r3 1/7.4.1) */ #define ENTITYID_FLAGS_DIRTY 0x00 @@ -95,7 +95,7 @@ struct volStructDesc { uint8_t stdIdent[VSD_STD_ID_LEN]; uint8_t structVersion; uint8_t structData[2041]; -} __attribute__ ((packed)); +} __packed; /* Standard Identifier (EMCA 167r2 2/9.1.2) */ #define VSD_STD_ID_NSR02 "NSR02" /* (3/9.1) */ @@ -114,7 +114,7 @@ struct beginningExtendedAreaDesc { uint8_t stdIdent[VSD_STD_ID_LEN]; uint8_t structVersion; uint8_t structData[2041]; -} __attribute__ ((packed)); +} __packed; /* Terminating Extended Area Descriptor (ECMA 167r3 2/9.3) */ struct terminatingExtendedAreaDesc { @@ -122,7 +122,7 @@ struct terminatingExtendedAreaDesc { uint8_t stdIdent[VSD_STD_ID_LEN]; uint8_t structVersion; uint8_t structData[2041]; -} __attribute__ ((packed)); +} __packed; /* Boot Descriptor (ECMA 167r3 2/9.4) */ struct bootDesc { @@ -140,7 +140,7 @@ struct bootDesc { __le16 flags; uint8_t reserved2[32]; uint8_t bootUse[1906]; -} __attribute__ ((packed)); +} __packed; /* Flags (ECMA 167r3 2/9.4.12) */ #define BOOT_FLAGS_ERASE 0x01 @@ -149,7 +149,7 @@ struct bootDesc { struct extent_ad { __le32 extLength; __le32 extLocation; -} __attribute__ ((packed)); +} __packed; struct kernel_extent_ad { uint32_t extLength; @@ -166,7 +166,7 @@ struct tag { __le16 descCRC; __le16 descCRCLength; __le32 tagLocation; -} __attribute__ ((packed)); +} __packed; /* Tag Identifier (ECMA 167r3 3/7.2.1) */ #define TAG_IDENT_PVD 0x0001 @@ -186,7 +186,7 @@ struct NSRDesc { uint8_t structVersion; uint8_t reserved; uint8_t structData[2040]; -} __attribute__ ((packed)); +} __packed; /* Primary Volume Descriptor (ECMA 167r3 3/10.1) */ struct primaryVolDesc { @@ -212,7 +212,7 @@ struct primaryVolDesc { __le32 predecessorVolDescSeqLocation; __le16 flags; uint8_t reserved[22]; -} __attribute__ ((packed)); +} __packed; /* Flags (ECMA 167r3 3/10.1.21) */ #define PVD_FLAGS_VSID_COMMON 0x0001 @@ -223,7 +223,7 @@ struct anchorVolDescPtr { struct extent_ad mainVolDescSeqExt; struct extent_ad reserveVolDescSeqExt; uint8_t reserved[480]; -} __attribute__ ((packed)); +} __packed; /* Volume Descriptor Pointer (ECMA 167r3 3/10.3) */ struct volDescPtr { @@ -231,7 +231,7 @@ struct volDescPtr { __le32 volDescSeqNum; struct extent_ad nextVolDescSeqExt; uint8_t reserved[484]; -} __attribute__ ((packed)); +} __packed; /* Implementation Use Volume Descriptor (ECMA 167r3 3/10.4) */ struct impUseVolDesc { @@ -239,7 +239,7 @@ struct impUseVolDesc { __le32 volDescSeqNum; struct regid impIdent; uint8_t impUse[460]; -} __attribute__ ((packed)); +} __packed; /* Partition Descriptor (ECMA 167r3 3/10.5) */ struct partitionDesc { @@ -255,7 +255,7 @@ struct partitionDesc { struct regid impIdent; uint8_t impUse[128]; uint8_t reserved[156]; -} __attribute__ ((packed)); +} __packed; /* Partition Flags (ECMA 167r3 3/10.5.3) */ #define PD_PARTITION_FLAGS_ALLOC 0x0001 @@ -291,14 +291,14 @@ struct logicalVolDesc { uint8_t impUse[128]; struct extent_ad integritySeqExt; uint8_t partitionMaps[0]; -} __attribute__ ((packed)); +} __packed; /* Generic Partition Map (ECMA 167r3 3/10.7.1) */ struct genericPartitionMap { uint8_t partitionMapType; uint8_t partitionMapLength; uint8_t partitionMapping[0]; -} __attribute__ ((packed)); +} __packed; /* Partition Map Type (ECMA 167r3 3/10.7.1.1) */ #define GP_PARTITION_MAP_TYPE_UNDEF 0x00 @@ -311,14 +311,14 @@ struct genericPartitionMap1 { uint8_t partitionMapLength; __le16 volSeqNum; __le16 partitionNum; -} __attribute__ ((packed)); +} __packed; /* Type 2 Partition Map (ECMA 167r3 3/10.7.3) */ struct genericPartitionMap2 { uint8_t partitionMapType; uint8_t partitionMapLength; uint8_t partitionIdent[62]; -} __attribute__ ((packed)); +} __packed; /* Unallocated Space Descriptor (ECMA 167r3 3/10.8) */ struct unallocSpaceDesc { @@ -326,13 +326,13 @@ struct unallocSpaceDesc { __le32 volDescSeqNum; __le32 numAllocDescs; struct extent_ad allocDescs[0]; -} __attribute__ ((packed)); +} __packed; /* Terminating Descriptor (ECMA 167r3 3/10.9) */ struct terminatingDesc { struct tag descTag; uint8_t reserved[496]; -} __attribute__ ((packed)); +} __packed; /* Logical Volume Integrity Descriptor (ECMA 167r3 3/10.10) */ struct logicalVolIntegrityDesc { @@ -346,7 +346,7 @@ struct logicalVolIntegrityDesc { __le32 freeSpaceTable[0]; __le32 sizeTable[0]; uint8_t impUse[0]; -} __attribute__ ((packed)); +} __packed; /* Integrity Type (ECMA 167r3 3/10.10.3) */ #define LVID_INTEGRITY_TYPE_OPEN 0x00000000 @@ -356,7 +356,7 @@ struct logicalVolIntegrityDesc { struct lb_addr { __le32 logicalBlockNum; __le16 partitionReferenceNum; -} __attribute__ ((packed)); +} __packed; /* ... and its in-core analog */ struct kernel_lb_addr { @@ -368,14 +368,14 @@ struct kernel_lb_addr { struct short_ad { __le32 extLength; __le32 extPosition; -} __attribute__ ((packed)); +} __packed; /* Long Allocation Descriptor (ECMA 167r3 4/14.14.2) */ struct long_ad { __le32 extLength; struct lb_addr extLocation; uint8_t impUse[6]; -} __attribute__ ((packed)); +} __packed; struct kernel_long_ad { uint32_t extLength; @@ -389,7 +389,7 @@ struct ext_ad { __le32 recordedLength; __le32 informationLength; struct lb_addr extLocation; -} __attribute__ ((packed)); +} __packed; struct kernel_ext_ad { uint32_t extLength; @@ -434,7 +434,7 @@ struct fileSetDesc { struct long_ad nextExt; struct long_ad streamDirectoryICB; uint8_t reserved[32]; -} __attribute__ ((packed)); +} __packed; /* Partition Header Descriptor (ECMA 167r3 4/14.3) */ struct partitionHeaderDesc { @@ -444,7 +444,7 @@ struct partitionHeaderDesc { struct short_ad freedSpaceTable; struct short_ad freedSpaceBitmap; uint8_t reserved[88]; -} __attribute__ ((packed)); +} __packed; /* File Identifier Descriptor (ECMA 167r3 4/14.4) */ struct fileIdentDesc { @@ -457,7 +457,7 @@ struct fileIdentDesc { uint8_t impUse[0]; uint8_t fileIdent[0]; uint8_t padding[0]; -} __attribute__ ((packed)); +} __packed; /* File Characteristics (ECMA 167r3 4/14.4.3) */ #define FID_FILE_CHAR_HIDDEN 0x01 @@ -471,7 +471,7 @@ struct allocExtDesc { struct tag descTag; __le32 previousAllocExtLocation; __le32 lengthAllocDescs; -} __attribute__ ((packed)); +} __packed; /* ICB Tag (ECMA 167r3 4/14.6) */ struct icbtag { @@ -483,7 +483,7 @@ struct icbtag { uint8_t fileType; struct lb_addr parentICBLocation; __le16 flags; -} __attribute__ ((packed)); +} __packed; /* Strategy Type (ECMA 167r3 4/14.6.2) */ #define ICBTAG_STRATEGY_TYPE_UNDEF 0x0000 @@ -531,13 +531,13 @@ struct indirectEntry { struct tag descTag; struct icbtag icbTag; struct long_ad indirectICB; -} __attribute__ ((packed)); +} __packed; /* Terminal Entry (ECMA 167r3 4/14.8) */ struct terminalEntry { struct tag descTag; struct icbtag icbTag; -} __attribute__ ((packed)); +} __packed; /* File Entry (ECMA 167r3 4/14.9) */ struct fileEntry { @@ -563,7 +563,7 @@ struct fileEntry { __le32 lengthAllocDescs; uint8_t extendedAttr[0]; uint8_t allocDescs[0]; -} __attribute__ ((packed)); +} __packed; /* Permissions (ECMA 167r3 4/14.9.5) */ #define FE_PERM_O_EXEC 0x00000001U @@ -607,7 +607,7 @@ struct extendedAttrHeaderDesc { struct tag descTag; __le32 impAttrLocation; __le32 appAttrLocation; -} __attribute__ ((packed)); +} __packed; /* Generic Format (ECMA 167r3 4/14.10.2) */ struct genericFormat { @@ -616,7 +616,7 @@ struct genericFormat { uint8_t reserved[3]; __le32 attrLength; uint8_t attrData[0]; -} __attribute__ ((packed)); +} __packed; /* Character Set Information (ECMA 167r3 4/14.10.3) */ struct charSetInfo { @@ -627,7 +627,7 @@ struct charSetInfo { __le32 escapeSeqLength; uint8_t charSetType; uint8_t escapeSeq[0]; -} __attribute__ ((packed)); +} __packed; /* Alternate Permissions (ECMA 167r3 4/14.10.4) */ struct altPerms { @@ -638,7 +638,7 @@ struct altPerms { __le16 ownerIdent; __le16 groupIdent; __le16 permission; -} __attribute__ ((packed)); +} __packed; /* File Times Extended Attribute (ECMA 167r3 4/14.10.5) */ struct fileTimesExtAttr { @@ -649,7 +649,7 @@ struct fileTimesExtAttr { __le32 dataLength; __le32 fileTimeExistence; uint8_t fileTimes; -} __attribute__ ((packed)); +} __packed; /* FileTimeExistence (ECMA 167r3 4/14.10.5.6) */ #define FTE_CREATION 0x00000001 @@ -666,7 +666,7 @@ struct infoTimesExtAttr { __le32 dataLength; __le32 infoTimeExistence; uint8_t infoTimes[0]; -} __attribute__ ((packed)); +} __packed; /* Device Specification (ECMA 167r3 4/14.10.7) */ struct deviceSpec { @@ -678,7 +678,7 @@ struct deviceSpec { __le32 majorDeviceIdent; __le32 minorDeviceIdent; uint8_t impUse[0]; -} __attribute__ ((packed)); +} __packed; /* Implementation Use Extended Attr (ECMA 167r3 4/14.10.8) */ struct impUseExtAttr { @@ -689,7 +689,7 @@ struct impUseExtAttr { __le32 impUseLength; struct regid impIdent; uint8_t impUse[0]; -} __attribute__ ((packed)); +} __packed; /* Application Use Extended Attribute (ECMA 167r3 4/14.10.9) */ struct appUseExtAttr { @@ -700,7 +700,7 @@ struct appUseExtAttr { __le32 appUseLength; struct regid appIdent; uint8_t appUse[0]; -} __attribute__ ((packed)); +} __packed; #define EXTATTR_CHAR_SET 1 #define EXTATTR_ALT_PERMS 3 @@ -716,7 +716,7 @@ struct unallocSpaceEntry { struct icbtag icbTag; __le32 lengthAllocDescs; uint8_t allocDescs[0]; -} __attribute__ ((packed)); +} __packed; /* Space Bitmap Descriptor (ECMA 167r3 4/14.12) */ struct spaceBitmapDesc { @@ -724,7 +724,7 @@ struct spaceBitmapDesc { __le32 numOfBits; __le32 numOfBytes; uint8_t bitmap[0]; -} __attribute__ ((packed)); +} __packed; /* Partition Integrity Entry (ECMA 167r3 4/14.13) */ struct partitionIntegrityEntry { @@ -735,7 +735,7 @@ struct partitionIntegrityEntry { uint8_t reserved[175]; struct regid impIdent; uint8_t impUse[256]; -} __attribute__ ((packed)); +} __packed; /* Short Allocation Descriptor (ECMA 167r3 4/14.14.1) */ @@ -753,7 +753,7 @@ struct partitionIntegrityEntry { struct logicalVolHeaderDesc { __le64 uniqueID; uint8_t reserved[24]; -} __attribute__ ((packed)); +} __packed; /* Path Component (ECMA 167r3 4/14.16.1) */ struct pathComponent { @@ -761,7 +761,7 @@ struct pathComponent { uint8_t lengthComponentIdent; __le16 componentFileVersionNum; dstring componentIdent[0]; -} __attribute__ ((packed)); +} __packed; /* File Entry (ECMA 167r3 4/14.17) */ struct extendedFileEntry { @@ -791,6 +791,6 @@ struct extendedFileEntry { __le32 lengthAllocDescs; uint8_t extendedAttr[0]; uint8_t allocDescs[0]; -} __attribute__ ((packed)); +} __packed; #endif /* _ECMA_167_H */ diff --git a/fs/udf/file.c b/fs/udf/file.c index dbcb3a4a0cb9..e04cc0cdca9d 100644 --- a/fs/udf/file.c +++ b/fs/udf/file.c @@ -176,54 +176,46 @@ long udf_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(filp); long old_block, new_block; - int result = -EINVAL; + int result; if (inode_permission(inode, MAY_READ) != 0) { udf_debug("no permission to access inode %lu\n", inode->i_ino); - result = -EPERM; - goto out; + return -EPERM; } - if (!arg) { + if (!arg && ((cmd == UDF_GETVOLIDENT) || (cmd == UDF_GETEASIZE) || + (cmd == UDF_RELOCATE_BLOCKS) || (cmd == UDF_GETEABLOCK))) { udf_debug("invalid argument to udf_ioctl\n"); - result = -EINVAL; - goto out; + return -EINVAL; } switch (cmd) { case UDF_GETVOLIDENT: if (copy_to_user((char __user *)arg, UDF_SB(inode->i_sb)->s_volume_ident, 32)) - result = -EFAULT; - else - result = 0; - goto out; + return -EFAULT; + return 0; case UDF_RELOCATE_BLOCKS: - if (!capable(CAP_SYS_ADMIN)) { - result = -EPERM; - goto out; - } - if (get_user(old_block, (long __user *)arg)) { - result = -EFAULT; - goto out; - } + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + if (get_user(old_block, (long __user *)arg)) + return -EFAULT; result = udf_relocate_blocks(inode->i_sb, old_block, &new_block); if (result == 0) result = put_user(new_block, (long __user *)arg); - goto out; + return result; case UDF_GETEASIZE: - result = put_user(UDF_I(inode)->i_lenEAttr, (int __user *)arg); - goto out; + return put_user(UDF_I(inode)->i_lenEAttr, (int __user *)arg); case UDF_GETEABLOCK: - result = copy_to_user((char __user *)arg, - UDF_I(inode)->i_ext.i_data, - UDF_I(inode)->i_lenEAttr) ? -EFAULT : 0; - goto out; + return copy_to_user((char __user *)arg, + UDF_I(inode)->i_ext.i_data, + UDF_I(inode)->i_lenEAttr) ? -EFAULT : 0; + default: + return -ENOIOCTLCMD; } -out: - return result; + return 0; } static int udf_release_file(struct inode *inode, struct file *filp) diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 0f3db71753aa..a8d8f71ef8bd 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -43,10 +43,6 @@ #include "udf_i.h" #include "udf_sb.h" -MODULE_AUTHOR("Ben Fennema"); -MODULE_DESCRIPTION("Universal Disk Format Filesystem"); -MODULE_LICENSE("GPL"); - #define EXTENT_MERGE_SIZE 5 static umode_t udf_convert_permissions(struct fileEntry *); @@ -57,14 +53,12 @@ static sector_t inode_getblk(struct inode *, sector_t, int *, int *); static int8_t udf_insert_aext(struct inode *, struct extent_position, struct kernel_lb_addr, uint32_t); static void udf_split_extents(struct inode *, int *, int, int, - struct kernel_long_ad[EXTENT_MERGE_SIZE], int *); + struct kernel_long_ad *, int *); static void udf_prealloc_extents(struct inode *, int, int, - struct kernel_long_ad[EXTENT_MERGE_SIZE], int *); -static void udf_merge_extents(struct inode *, - struct kernel_long_ad[EXTENT_MERGE_SIZE], int *); -static void udf_update_extents(struct inode *, - struct kernel_long_ad[EXTENT_MERGE_SIZE], int, int, - struct extent_position *); + struct kernel_long_ad *, int *); +static void udf_merge_extents(struct inode *, struct kernel_long_ad *, int *); +static void udf_update_extents(struct inode *, struct kernel_long_ad *, int, + int, struct extent_position *); static int udf_get_block(struct inode *, sector_t, struct buffer_head *, int); static void __udf_clear_extent_cache(struct inode *inode) @@ -111,7 +105,7 @@ static int udf_read_extent_cache(struct inode *inode, loff_t bcount, /* Add extent to extent cache */ static void udf_update_extent_cache(struct inode *inode, loff_t estart, - struct extent_position *pos, int next_epos) + struct extent_position *pos) { struct udf_inode_info *iinfo = UDF_I(inode); @@ -120,19 +114,16 @@ static void udf_update_extent_cache(struct inode *inode, loff_t estart, __udf_clear_extent_cache(inode); if (pos->bh) get_bh(pos->bh); - memcpy(&iinfo->cached_extent.epos, pos, - sizeof(struct extent_position)); + memcpy(&iinfo->cached_extent.epos, pos, sizeof(struct extent_position)); iinfo->cached_extent.lstart = estart; - if (next_epos) - switch (iinfo->i_alloc_type) { - case ICBTAG_FLAG_AD_SHORT: - iinfo->cached_extent.epos.offset -= - sizeof(struct short_ad); - break; - case ICBTAG_FLAG_AD_LONG: - iinfo->cached_extent.epos.offset -= - sizeof(struct long_ad); - } + switch (iinfo->i_alloc_type) { + case ICBTAG_FLAG_AD_SHORT: + iinfo->cached_extent.epos.offset -= sizeof(struct short_ad); + break; + case ICBTAG_FLAG_AD_LONG: + iinfo->cached_extent.epos.offset -= sizeof(struct long_ad); + break; + } spin_unlock(&iinfo->i_extent_cache_lock); } @@ -747,11 +738,8 @@ static sector_t inode_getblk(struct inode *inode, sector_t block, ~(inode->i_sb->s_blocksize - 1)); udf_write_aext(inode, &cur_epos, &eloc, elen, 1); } - brelse(prev_epos.bh); - brelse(cur_epos.bh); - brelse(next_epos.bh); newblock = udf_get_lb_pblock(inode->i_sb, &eloc, offset); - return newblock; + goto out_free; } /* Are we beyond EOF? */ @@ -774,11 +762,9 @@ static sector_t inode_getblk(struct inode *inode, sector_t block, /* Create extents for the hole between EOF and offset */ ret = udf_do_extend_file(inode, &prev_epos, laarr, offset); if (ret < 0) { - brelse(prev_epos.bh); - brelse(cur_epos.bh); - brelse(next_epos.bh); *err = ret; - return 0; + newblock = 0; + goto out_free; } c = 0; offset = 0; @@ -841,11 +827,9 @@ static sector_t inode_getblk(struct inode *inode, sector_t block, iinfo->i_location.partitionReferenceNum, goal, err); if (!newblocknum) { - brelse(prev_epos.bh); - brelse(cur_epos.bh); - brelse(next_epos.bh); *err = -ENOSPC; - return 0; + newblock = 0; + goto out_free; } if (isBeyondEOF) iinfo->i_lenExtents += inode->i_sb->s_blocksize; @@ -857,14 +841,12 @@ static sector_t inode_getblk(struct inode *inode, sector_t block, * block */ udf_split_extents(inode, &c, offset, newblocknum, laarr, &endnum); -#ifdef UDF_PREALLOCATE /* We preallocate blocks only for regular files. It also makes sense * for directories but there's a problem when to drop the * preallocation. We might use some delayed work for that but I feel * it's overengineering for a filesystem like UDF. */ if (S_ISREG(inode->i_mode)) udf_prealloc_extents(inode, c, lastblock, laarr, &endnum); -#endif /* merge any continuous blocks in laarr */ udf_merge_extents(inode, laarr, &endnum); @@ -874,15 +856,11 @@ static sector_t inode_getblk(struct inode *inode, sector_t block, * the new number of extents is less than the old number */ udf_update_extents(inode, laarr, startnum, endnum, &prev_epos); - brelse(prev_epos.bh); - brelse(cur_epos.bh); - brelse(next_epos.bh); - newblock = udf_get_pblock(inode->i_sb, newblocknum, iinfo->i_location.partitionReferenceNum, 0); if (!newblock) { *err = -EIO; - return 0; + goto out_free; } *new = 1; iinfo->i_next_alloc_block = block; @@ -893,13 +871,15 @@ static sector_t inode_getblk(struct inode *inode, sector_t block, udf_sync_inode(inode); else mark_inode_dirty(inode); - +out_free: + brelse(prev_epos.bh); + brelse(cur_epos.bh); + brelse(next_epos.bh); return newblock; } static void udf_split_extents(struct inode *inode, int *c, int offset, - int newblocknum, - struct kernel_long_ad laarr[EXTENT_MERGE_SIZE], + int newblocknum, struct kernel_long_ad *laarr, int *endnum) { unsigned long blocksize = inode->i_sb->s_blocksize; @@ -963,7 +943,7 @@ static void udf_split_extents(struct inode *inode, int *c, int offset, } static void udf_prealloc_extents(struct inode *inode, int c, int lastblock, - struct kernel_long_ad laarr[EXTENT_MERGE_SIZE], + struct kernel_long_ad *laarr, int *endnum) { int start, length = 0, currlength = 0, i; @@ -1058,8 +1038,7 @@ static void udf_prealloc_extents(struct inode *inode, int c, int lastblock, } } -static void udf_merge_extents(struct inode *inode, - struct kernel_long_ad laarr[EXTENT_MERGE_SIZE], +static void udf_merge_extents(struct inode *inode, struct kernel_long_ad *laarr, int *endnum) { int i; @@ -1158,8 +1137,7 @@ static void udf_merge_extents(struct inode *inode, } } -static void udf_update_extents(struct inode *inode, - struct kernel_long_ad laarr[EXTENT_MERGE_SIZE], +static void udf_update_extents(struct inode *inode, struct kernel_long_ad *laarr, int startnum, int endnum, struct extent_position *epos) { @@ -1215,7 +1193,7 @@ int udf_setsize(struct inode *inode, loff_t newsize) { int err; struct udf_inode_info *iinfo; - int bsize = 1 << inode->i_blkbits; + int bsize = i_blocksize(inode); if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))) @@ -1299,6 +1277,12 @@ static int udf_read_inode(struct inode *inode, bool hidden_inode) int ret = -EIO; reread: + if (iloc->partitionReferenceNum >= sbi->s_partitions) { + udf_debug("partition reference: %d > logical volume partitions: %d\n", + iloc->partitionReferenceNum, sbi->s_partitions); + return -EIO; + } + if (iloc->logicalBlockNum >= sbi->s_partmaps[iloc->partitionReferenceNum].s_partition_len) { udf_debug("block=%d, partition=%d out of range\n", @@ -1549,7 +1533,7 @@ reread: break; case ICBTAG_FILE_TYPE_SYMLINK: inode->i_data.a_ops = &udf_symlink_aops; - inode->i_op = &page_symlink_inode_operations; + inode->i_op = &udf_symlink_inode_operations; inode_nohighmem(inode); inode->i_mode = S_IFLNK | S_IRWXUGO; break; @@ -1627,6 +1611,14 @@ static int udf_sync_inode(struct inode *inode) return udf_update_inode(inode, 1); } +static void udf_adjust_time(struct udf_inode_info *iinfo, struct timespec time) +{ + if (iinfo->i_crtime.tv_sec > time.tv_sec || + (iinfo->i_crtime.tv_sec == time.tv_sec && + iinfo->i_crtime.tv_nsec > time.tv_nsec)) + iinfo->i_crtime = time; +} + static int udf_update_inode(struct inode *inode, int do_sync) { struct buffer_head *bh = NULL; @@ -1753,20 +1745,9 @@ static int udf_update_inode(struct inode *inode, int do_sync) efe->objectSize = cpu_to_le64(inode->i_size); efe->logicalBlocksRecorded = cpu_to_le64(lb_recorded); - if (iinfo->i_crtime.tv_sec > inode->i_atime.tv_sec || - (iinfo->i_crtime.tv_sec == inode->i_atime.tv_sec && - iinfo->i_crtime.tv_nsec > inode->i_atime.tv_nsec)) - iinfo->i_crtime = inode->i_atime; - - if (iinfo->i_crtime.tv_sec > inode->i_mtime.tv_sec || - (iinfo->i_crtime.tv_sec == inode->i_mtime.tv_sec && - iinfo->i_crtime.tv_nsec > inode->i_mtime.tv_nsec)) - iinfo->i_crtime = inode->i_mtime; - - if (iinfo->i_crtime.tv_sec > inode->i_ctime.tv_sec || - (iinfo->i_crtime.tv_sec == inode->i_ctime.tv_sec && - iinfo->i_crtime.tv_nsec > inode->i_ctime.tv_nsec)) - iinfo->i_crtime = inode->i_ctime; + udf_adjust_time(iinfo, inode->i_atime); + udf_adjust_time(iinfo, inode->i_mtime); + udf_adjust_time(iinfo, inode->i_ctime); udf_time_to_disk_stamp(&efe->accessTime, inode->i_atime); udf_time_to_disk_stamp(&efe->modificationTime, inode->i_mtime); @@ -2286,8 +2267,7 @@ int8_t inode_bmap(struct inode *inode, sector_t block, uint32_t *elen, sector_t *offset) { unsigned char blocksize_bits = inode->i_sb->s_blocksize_bits; - loff_t lbcount = 0, bcount = - (loff_t) block << blocksize_bits; + loff_t lbcount = 0, bcount = (loff_t) block << blocksize_bits; int8_t etype; struct udf_inode_info *iinfo; @@ -2308,7 +2288,7 @@ int8_t inode_bmap(struct inode *inode, sector_t block, lbcount += *elen; } while (lbcount <= bcount); /* update extent cache */ - udf_update_extent_cache(inode, lbcount - *elen, pos, 1); + udf_update_extent_cache(inode, lbcount - *elen, pos); *offset = (bcount + *elen - lbcount) >> blocksize_bits; return etype; diff --git a/fs/udf/lowlevel.c b/fs/udf/lowlevel.c index 6ad5a453af97..5c7ec121990d 100644 --- a/fs/udf/lowlevel.c +++ b/fs/udf/lowlevel.c @@ -58,7 +58,7 @@ unsigned long udf_get_last_block(struct super_block *sb) */ if (ioctl_by_bdev(bdev, CDROM_LAST_WRITTEN, (unsigned long) &lblock) || lblock == 0) - lblock = bdev->bd_inode->i_size >> sb->s_blocksize_bits; + lblock = i_size_read(bdev->bd_inode) >> sb->s_blocksize_bits; if (lblock) return lblock - 1; diff --git a/fs/udf/misc.c b/fs/udf/misc.c index 71d1c25f360d..3949c4bec3a3 100644 --- a/fs/udf/misc.c +++ b/fs/udf/misc.c @@ -141,8 +141,6 @@ struct genericFormat *udf_add_extendedattr(struct inode *inode, uint32_t size, iinfo->i_lenEAttr += size; return (struct genericFormat *)&ea[offset]; } - if (loc & 0x02) - ; return NULL; } diff --git a/fs/udf/namei.c b/fs/udf/namei.c index 2d65e280748b..babf48d0e553 100644 --- a/fs/udf/namei.c +++ b/fs/udf/namei.c @@ -931,7 +931,7 @@ static int udf_symlink(struct inode *dir, struct dentry *dentry, } inode->i_data.a_ops = &udf_symlink_aops; - inode->i_op = &page_symlink_inode_operations; + inode->i_op = &udf_symlink_inode_operations; inode_nohighmem(inode); if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) { diff --git a/fs/udf/osta_udf.h b/fs/udf/osta_udf.h index fbff74654df2..a4da59e38b7f 100644 --- a/fs/udf/osta_udf.h +++ b/fs/udf/osta_udf.h @@ -70,17 +70,17 @@ struct UDFIdentSuffix { uint8_t OSClass; uint8_t OSIdentifier; uint8_t reserved[4]; -} __attribute__ ((packed)); +} __packed; struct impIdentSuffix { uint8_t OSClass; uint8_t OSIdentifier; uint8_t reserved[6]; -} __attribute__ ((packed)); +} __packed; struct appIdentSuffix { uint8_t impUse[8]; -} __attribute__ ((packed)); +} __packed; /* Logical Volume Integrity Descriptor (UDF 2.50 2.2.6) */ /* Implementation Use (UDF 2.50 2.2.6.4) */ @@ -92,7 +92,7 @@ struct logicalVolIntegrityDescImpUse { __le16 minUDFWriteRev; __le16 maxUDFWriteRev; uint8_t impUse[0]; -} __attribute__ ((packed)); +} __packed; /* Implementation Use Volume Descriptor (UDF 2.50 2.2.7) */ /* Implementation Use (UDF 2.50 2.2.7.2) */ @@ -104,7 +104,7 @@ struct impUseVolDescImpUse { dstring LVInfo3[36]; struct regid impIdent; uint8_t impUse[128]; -} __attribute__ ((packed)); +} __packed; struct udfPartitionMap2 { uint8_t partitionMapType; @@ -113,7 +113,7 @@ struct udfPartitionMap2 { struct regid partIdent; __le16 volSeqNum; __le16 partitionNum; -} __attribute__ ((packed)); +} __packed; /* Virtual Partition Map (UDF 2.50 2.2.8) */ struct virtualPartitionMap { @@ -124,7 +124,7 @@ struct virtualPartitionMap { __le16 volSeqNum; __le16 partitionNum; uint8_t reserved2[24]; -} __attribute__ ((packed)); +} __packed; /* Sparable Partition Map (UDF 2.50 2.2.9) */ struct sparablePartitionMap { @@ -139,7 +139,7 @@ struct sparablePartitionMap { uint8_t reserved2[1]; __le32 sizeSparingTable; __le32 locSparingTable[4]; -} __attribute__ ((packed)); +} __packed; /* Metadata Partition Map (UDF 2.4.0 2.2.10) */ struct metadataPartitionMap { @@ -156,14 +156,14 @@ struct metadataPartitionMap { __le16 alignUnitSize; uint8_t flags; uint8_t reserved2[5]; -} __attribute__ ((packed)); +} __packed; /* Virtual Allocation Table (UDF 1.5 2.2.10) */ struct virtualAllocationTable15 { __le32 VirtualSector[0]; struct regid vatIdent; __le32 previousVATICBLoc; -} __attribute__ ((packed)); +} __packed; #define ICBTAG_FILE_TYPE_VAT15 0x00U @@ -181,7 +181,7 @@ struct virtualAllocationTable20 { __le16 reserved; uint8_t impUse[0]; __le32 vatEntry[0]; -} __attribute__ ((packed)); +} __packed; #define ICBTAG_FILE_TYPE_VAT20 0xF8U @@ -189,7 +189,7 @@ struct virtualAllocationTable20 { struct sparingEntry { __le32 origLocation; __le32 mappedLocation; -} __attribute__ ((packed)); +} __packed; struct sparingTable { struct tag descTag; @@ -199,7 +199,7 @@ struct sparingTable { __le32 sequenceNum; struct sparingEntry mapEntry[0]; -} __attribute__ ((packed)); +} __packed; /* Metadata File (and Metadata Mirror File) (UDF 2.50 2.2.13.1) */ #define ICBTAG_FILE_TYPE_MAIN 0xFA @@ -210,7 +210,7 @@ struct sparingTable { struct allocDescImpUse { __le16 flags; uint8_t impUse[4]; -} __attribute__ ((packed)); +} __packed; #define AD_IU_EXT_ERASED 0x0001 @@ -222,7 +222,7 @@ struct allocDescImpUse { struct freeEaSpace { __le16 headerChecksum; uint8_t freeEASpace[0]; -} __attribute__ ((packed)); +} __packed; /* DVD Copyright Management Information (UDF 2.50 3.3.4.5.1.2) */ struct DVDCopyrightImpUse { @@ -230,14 +230,14 @@ struct DVDCopyrightImpUse { uint8_t CGMSInfo; uint8_t dataType; uint8_t protectionSystemInfo[4]; -} __attribute__ ((packed)); +} __packed; /* Application Use Extended Attribute (UDF 2.50 3.3.4.6) */ /* FreeAppEASpace (UDF 2.50 3.3.4.6.1) */ struct freeAppEASpace { __le16 headerChecksum; uint8_t freeEASpace[0]; -} __attribute__ ((packed)); +} __packed; /* UDF Defined System Stream (UDF 2.50 3.3.7) */ #define UDF_ID_UNIQUE_ID "*UDF Unique ID Mapping Data" diff --git a/fs/udf/super.c b/fs/udf/super.c index 4942549e7dc8..14b4bc1f6801 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -264,9 +264,6 @@ static void __exit exit_udf_fs(void) destroy_inodecache(); } -module_init(init_udf_fs) -module_exit(exit_udf_fs) - static int udf_sb_alloc_partition_maps(struct super_block *sb, u32 count) { struct udf_sb_info *sbi = UDF_SB(sb); @@ -1216,7 +1213,8 @@ static int udf_load_vat(struct super_block *sb, int p_index, int type1_index) struct udf_inode_info *vati; uint32_t pos; struct virtualAllocationTable20 *vat20; - sector_t blocks = sb->s_bdev->bd_inode->i_size >> sb->s_blocksize_bits; + sector_t blocks = i_size_read(sb->s_bdev->bd_inode) >> + sb->s_blocksize_bits; udf_find_vat_block(sb, p_index, type1_index, sbi->s_last_block); if (!sbi->s_vat_inode && @@ -1806,7 +1804,7 @@ static int udf_check_anchor_block(struct super_block *sb, sector_t block, if (UDF_QUERY_FLAG(sb, UDF_FLAG_VARCONV) && udf_fixed_to_variable(block) >= - sb->s_bdev->bd_inode->i_size >> sb->s_blocksize_bits) + i_size_read(sb->s_bdev->bd_inode) >> sb->s_blocksize_bits) return -EAGAIN; bh = udf_read_tagged(sb, block, block, &ident); @@ -1868,7 +1866,7 @@ static int udf_scan_anchors(struct super_block *sb, sector_t *lastblock, last[last_count++] = *lastblock - 152; for (i = 0; i < last_count; i++) { - if (last[i] >= sb->s_bdev->bd_inode->i_size >> + if (last[i] >= i_size_read(sb->s_bdev->bd_inode) >> sb->s_blocksize_bits) continue; ret = udf_check_anchor_block(sb, last[i], fileset); @@ -1957,7 +1955,7 @@ static int udf_load_vrs(struct super_block *sb, struct udf_options *uopt, if (!nsr_off) { if (!silent) udf_warn(sb, "No VRS found\n"); - return 0; + return -EINVAL; } if (nsr_off == -1) udf_debug("Failed to read sector at offset %d. " @@ -1986,6 +1984,7 @@ static void udf_open_lvid(struct super_block *sb) struct buffer_head *bh = sbi->s_lvid_bh; struct logicalVolIntegrityDesc *lvid; struct logicalVolIntegrityDescImpUse *lvidiu; + struct timespec ts; if (!bh) return; @@ -1997,8 +1996,8 @@ static void udf_open_lvid(struct super_block *sb) mutex_lock(&sbi->s_alloc_mutex); lvidiu->impIdent.identSuffix[0] = UDF_OS_CLASS_UNIX; lvidiu->impIdent.identSuffix[1] = UDF_OS_ID_LINUX; - udf_time_to_disk_stamp(&lvid->recordingDateAndTime, - CURRENT_TIME); + ktime_get_real_ts(&ts); + udf_time_to_disk_stamp(&lvid->recordingDateAndTime, ts); lvid->integrityType = cpu_to_le32(LVID_INTEGRITY_TYPE_OPEN); lvid->descTag.descCRC = cpu_to_le16( @@ -2019,6 +2018,7 @@ static void udf_close_lvid(struct super_block *sb) struct buffer_head *bh = sbi->s_lvid_bh; struct logicalVolIntegrityDesc *lvid; struct logicalVolIntegrityDescImpUse *lvidiu; + struct timespec ts; if (!bh) return; @@ -2030,7 +2030,8 @@ static void udf_close_lvid(struct super_block *sb) mutex_lock(&sbi->s_alloc_mutex); lvidiu->impIdent.identSuffix[0] = UDF_OS_CLASS_UNIX; lvidiu->impIdent.identSuffix[1] = UDF_OS_ID_LINUX; - udf_time_to_disk_stamp(&lvid->recordingDateAndTime, CURRENT_TIME); + ktime_get_real_ts(&ts); + udf_time_to_disk_stamp(&lvid->recordingDateAndTime, ts); if (UDF_MAX_WRITE_VERSION > le16_to_cpu(lvidiu->maxUDFWriteRev)) lvidiu->maxUDFWriteRev = cpu_to_le16(UDF_MAX_WRITE_VERSION); if (sbi->s_udfrev > le16_to_cpu(lvidiu->minUDFReadRev)) @@ -2158,15 +2159,25 @@ static int udf_fill_super(struct super_block *sb, void *options, int silent) ret = udf_load_vrs(sb, &uopt, silent, &fileset); } else { uopt.blocksize = bdev_logical_block_size(sb->s_bdev); - ret = udf_load_vrs(sb, &uopt, silent, &fileset); - if (ret == -EAGAIN && uopt.blocksize != UDF_DEFAULT_BLOCKSIZE) { - if (!silent) - pr_notice("Rescanning with blocksize %d\n", - UDF_DEFAULT_BLOCKSIZE); - brelse(sbi->s_lvid_bh); - sbi->s_lvid_bh = NULL; - uopt.blocksize = UDF_DEFAULT_BLOCKSIZE; + while (uopt.blocksize <= 4096) { ret = udf_load_vrs(sb, &uopt, silent, &fileset); + if (ret < 0) { + if (!silent && ret != -EACCES) { + pr_notice("Scanning with blocksize %d failed\n", + uopt.blocksize); + } + brelse(sbi->s_lvid_bh); + sbi->s_lvid_bh = NULL; + /* + * EACCES is special - we want to propagate to + * upper layers that we cannot handle RW mount. + */ + if (ret == -EACCES) + break; + } else + break; + + uopt.blocksize <<= 1; } } if (ret < 0) { @@ -2497,3 +2508,9 @@ static unsigned int udf_count_free(struct super_block *sb) return accum; } + +MODULE_AUTHOR("Ben Fennema"); +MODULE_DESCRIPTION("Universal Disk Format Filesystem"); +MODULE_LICENSE("GPL"); +module_init(init_udf_fs) +module_exit(exit_udf_fs) diff --git a/fs/udf/symlink.c b/fs/udf/symlink.c index 8d619773056b..f7dfef53f739 100644 --- a/fs/udf/symlink.c +++ b/fs/udf/symlink.c @@ -152,9 +152,39 @@ out_unmap: return err; } +static int udf_symlink_getattr(struct vfsmount *mnt, struct dentry *dentry, + struct kstat *stat) +{ + struct inode *inode = d_backing_inode(dentry); + struct page *page; + + generic_fillattr(inode, stat); + page = read_mapping_page(inode->i_mapping, 0, NULL); + if (IS_ERR(page)) + return PTR_ERR(page); + /* + * UDF uses non-trivial encoding of symlinks so i_size does not match + * number of characters reported by readlink(2) which apparently some + * applications expect. Also POSIX says that "The value returned in the + * st_size field shall be the length of the contents of the symbolic + * link, and shall not count a trailing null if one is present." So + * let's report the length of string returned by readlink(2) for + * st_size. + */ + stat->size = strlen(page_address(page)); + put_page(page); + + return 0; +} + /* * symlinks can't do much... */ const struct address_space_operations udf_symlink_aops = { .readpage = udf_symlink_filler, }; + +const struct inode_operations udf_symlink_inode_operations = { + .get_link = page_get_link, + .getattr = udf_symlink_getattr, +}; diff --git a/fs/udf/udfdecl.h b/fs/udf/udfdecl.h index 263829ef1873..63b034984378 100644 --- a/fs/udf/udfdecl.h +++ b/fs/udf/udfdecl.h @@ -15,7 +15,6 @@ #include "udfend.h" #include "udf_i.h" -#define UDF_PREALLOCATE #define UDF_DEFAULT_PREALLOC_BLOCKS 8 extern __printf(3, 4) void _udf_err(struct super_block *sb, @@ -85,6 +84,7 @@ extern const struct inode_operations udf_dir_inode_operations; extern const struct file_operations udf_dir_operations; extern const struct inode_operations udf_file_inode_operations; extern const struct file_operations udf_file_operations; +extern const struct inode_operations udf_symlink_inode_operations; extern const struct address_space_operations udf_aops; extern const struct address_space_operations udf_adinicb_aops; extern const struct address_space_operations udf_symlink_aops; diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 43953e03c356..3c421d06a18e 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -12,6 +12,7 @@ * mm/ksm.c (mm hashing). */ +#include <linux/list.h> #include <linux/hashtable.h> #include <linux/sched.h> #include <linux/mm.h> @@ -26,6 +27,7 @@ #include <linux/mempolicy.h> #include <linux/ioctl.h> #include <linux/security.h> +#include <linux/hugetlb.h> static struct kmem_cache *userfaultfd_ctx_cachep __read_mostly; @@ -45,12 +47,16 @@ struct userfaultfd_ctx { wait_queue_head_t fault_wqh; /* waitqueue head for the pseudo fd to wakeup poll/read */ wait_queue_head_t fd_wqh; + /* waitqueue head for events */ + wait_queue_head_t event_wqh; /* a refile sequence protected by fault_pending_wqh lock */ struct seqcount refile_seq; /* pseudo fd refcounting */ atomic_t refcount; /* userfaultfd syscall flags */ unsigned int flags; + /* features requested from the userspace */ + unsigned int features; /* state machine */ enum userfaultfd_state state; /* released */ @@ -59,6 +65,19 @@ struct userfaultfd_ctx { struct mm_struct *mm; }; +struct userfaultfd_fork_ctx { + struct userfaultfd_ctx *orig; + struct userfaultfd_ctx *new; + struct list_head list; +}; + +struct userfaultfd_unmap_ctx { + struct userfaultfd_ctx *ctx; + unsigned long start; + unsigned long end; + struct list_head list; +}; + struct userfaultfd_wait_queue { struct uffd_msg msg; wait_queue_t wq; @@ -142,6 +161,8 @@ static void userfaultfd_ctx_put(struct userfaultfd_ctx *ctx) VM_BUG_ON(waitqueue_active(&ctx->fault_pending_wqh)); VM_BUG_ON(spin_is_locked(&ctx->fault_wqh.lock)); VM_BUG_ON(waitqueue_active(&ctx->fault_wqh)); + VM_BUG_ON(spin_is_locked(&ctx->event_wqh.lock)); + VM_BUG_ON(waitqueue_active(&ctx->event_wqh)); VM_BUG_ON(spin_is_locked(&ctx->fd_wqh.lock)); VM_BUG_ON(waitqueue_active(&ctx->fd_wqh)); mmdrop(ctx->mm); @@ -169,7 +190,7 @@ static inline struct uffd_msg userfault_msg(unsigned long address, msg.arg.pagefault.address = address; if (flags & FAULT_FLAG_WRITE) /* - * If UFFD_FEATURE_PAGEFAULT_FLAG_WRITE was set in the + * If UFFD_FEATURE_PAGEFAULT_FLAG_WP was set in the * uffdio_api.features and UFFD_PAGEFAULT_FLAG_WRITE * was not set in a UFFD_EVENT_PAGEFAULT, it means it * was a read fault, otherwise if set it means it's @@ -188,6 +209,49 @@ static inline struct uffd_msg userfault_msg(unsigned long address, return msg; } +#ifdef CONFIG_HUGETLB_PAGE +/* + * Same functionality as userfaultfd_must_wait below with modifications for + * hugepmd ranges. + */ +static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx, + unsigned long address, + unsigned long flags, + unsigned long reason) +{ + struct mm_struct *mm = ctx->mm; + pte_t *pte; + bool ret = true; + + VM_BUG_ON(!rwsem_is_locked(&mm->mmap_sem)); + + pte = huge_pte_offset(mm, address); + if (!pte) + goto out; + + ret = false; + + /* + * Lockless access: we're in a wait_event so it's ok if it + * changes under us. + */ + if (huge_pte_none(*pte)) + ret = true; + if (!huge_pte_write(*pte) && (reason & VM_UFFD_WP)) + ret = true; +out: + return ret; +} +#else +static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx, + unsigned long address, + unsigned long flags, + unsigned long reason) +{ + return false; /* should never get here */ +} +#endif /* CONFIG_HUGETLB_PAGE */ + /* * Verify the pagetables are still not ok after having reigstered into * the fault_pending_wqh to avoid userland having to UFFDIO_WAKE any @@ -364,8 +428,12 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason) set_current_state(blocking_state); spin_unlock(&ctx->fault_pending_wqh.lock); - must_wait = userfaultfd_must_wait(ctx, vmf->address, vmf->flags, - reason); + if (!is_vm_hugetlb_page(vmf->vma)) + must_wait = userfaultfd_must_wait(ctx, vmf->address, vmf->flags, + reason); + else + must_wait = userfaultfd_huge_must_wait(ctx, vmf->address, + vmf->flags, reason); up_read(&mm->mmap_sem); if (likely(must_wait && !ACCESS_ONCE(ctx->released) && @@ -458,6 +526,282 @@ out: return ret; } +static int userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, + struct userfaultfd_wait_queue *ewq) +{ + int ret = 0; + + ewq->ctx = ctx; + init_waitqueue_entry(&ewq->wq, current); + + spin_lock(&ctx->event_wqh.lock); + /* + * After the __add_wait_queue the uwq is visible to userland + * through poll/read(). + */ + __add_wait_queue(&ctx->event_wqh, &ewq->wq); + for (;;) { + set_current_state(TASK_KILLABLE); + if (ewq->msg.event == 0) + break; + if (ACCESS_ONCE(ctx->released) || + fatal_signal_pending(current)) { + ret = -1; + __remove_wait_queue(&ctx->event_wqh, &ewq->wq); + break; + } + + spin_unlock(&ctx->event_wqh.lock); + + wake_up_poll(&ctx->fd_wqh, POLLIN); + schedule(); + + spin_lock(&ctx->event_wqh.lock); + } + __set_current_state(TASK_RUNNING); + spin_unlock(&ctx->event_wqh.lock); + + /* + * ctx may go away after this if the userfault pseudo fd is + * already released. + */ + + userfaultfd_ctx_put(ctx); + return ret; +} + +static void userfaultfd_event_complete(struct userfaultfd_ctx *ctx, + struct userfaultfd_wait_queue *ewq) +{ + ewq->msg.event = 0; + wake_up_locked(&ctx->event_wqh); + __remove_wait_queue(&ctx->event_wqh, &ewq->wq); +} + +int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs) +{ + struct userfaultfd_ctx *ctx = NULL, *octx; + struct userfaultfd_fork_ctx *fctx; + + octx = vma->vm_userfaultfd_ctx.ctx; + if (!octx || !(octx->features & UFFD_FEATURE_EVENT_FORK)) { + vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; + vma->vm_flags &= ~(VM_UFFD_WP | VM_UFFD_MISSING); + return 0; + } + + list_for_each_entry(fctx, fcs, list) + if (fctx->orig == octx) { + ctx = fctx->new; + break; + } + + if (!ctx) { + fctx = kmalloc(sizeof(*fctx), GFP_KERNEL); + if (!fctx) + return -ENOMEM; + + ctx = kmem_cache_alloc(userfaultfd_ctx_cachep, GFP_KERNEL); + if (!ctx) { + kfree(fctx); + return -ENOMEM; + } + + atomic_set(&ctx->refcount, 1); + ctx->flags = octx->flags; + ctx->state = UFFD_STATE_RUNNING; + ctx->features = octx->features; + ctx->released = false; + ctx->mm = vma->vm_mm; + atomic_inc(&ctx->mm->mm_count); + + userfaultfd_ctx_get(octx); + fctx->orig = octx; + fctx->new = ctx; + list_add_tail(&fctx->list, fcs); + } + + vma->vm_userfaultfd_ctx.ctx = ctx; + return 0; +} + +static int dup_fctx(struct userfaultfd_fork_ctx *fctx) +{ + struct userfaultfd_ctx *ctx = fctx->orig; + struct userfaultfd_wait_queue ewq; + + msg_init(&ewq.msg); + + ewq.msg.event = UFFD_EVENT_FORK; + ewq.msg.arg.reserved.reserved1 = (unsigned long)fctx->new; + + return userfaultfd_event_wait_completion(ctx, &ewq); +} + +void dup_userfaultfd_complete(struct list_head *fcs) +{ + int ret = 0; + struct userfaultfd_fork_ctx *fctx, *n; + + list_for_each_entry_safe(fctx, n, fcs, list) { + if (!ret) + ret = dup_fctx(fctx); + list_del(&fctx->list); + kfree(fctx); + } +} + +void mremap_userfaultfd_prep(struct vm_area_struct *vma, + struct vm_userfaultfd_ctx *vm_ctx) +{ + struct userfaultfd_ctx *ctx; + + ctx = vma->vm_userfaultfd_ctx.ctx; + if (ctx && (ctx->features & UFFD_FEATURE_EVENT_REMAP)) { + vm_ctx->ctx = ctx; + userfaultfd_ctx_get(ctx); + } +} + +void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *vm_ctx, + unsigned long from, unsigned long to, + unsigned long len) +{ + struct userfaultfd_ctx *ctx = vm_ctx->ctx; + struct userfaultfd_wait_queue ewq; + + if (!ctx) + return; + + if (to & ~PAGE_MASK) { + userfaultfd_ctx_put(ctx); + return; + } + + msg_init(&ewq.msg); + + ewq.msg.event = UFFD_EVENT_REMAP; + ewq.msg.arg.remap.from = from; + ewq.msg.arg.remap.to = to; + ewq.msg.arg.remap.len = len; + + userfaultfd_event_wait_completion(ctx, &ewq); +} + +void userfaultfd_remove(struct vm_area_struct *vma, + struct vm_area_struct **prev, + unsigned long start, unsigned long end) +{ + struct mm_struct *mm = vma->vm_mm; + struct userfaultfd_ctx *ctx; + struct userfaultfd_wait_queue ewq; + + ctx = vma->vm_userfaultfd_ctx.ctx; + if (!ctx || !(ctx->features & UFFD_FEATURE_EVENT_REMOVE)) + return; + + userfaultfd_ctx_get(ctx); + up_read(&mm->mmap_sem); + + *prev = NULL; /* We wait for ACK w/o the mmap semaphore */ + + msg_init(&ewq.msg); + + ewq.msg.event = UFFD_EVENT_REMOVE; + ewq.msg.arg.remove.start = start; + ewq.msg.arg.remove.end = end; + + userfaultfd_event_wait_completion(ctx, &ewq); + + down_read(&mm->mmap_sem); +} + +static bool has_unmap_ctx(struct userfaultfd_ctx *ctx, struct list_head *unmaps, + unsigned long start, unsigned long end) +{ + struct userfaultfd_unmap_ctx *unmap_ctx; + + list_for_each_entry(unmap_ctx, unmaps, list) + if (unmap_ctx->ctx == ctx && unmap_ctx->start == start && + unmap_ctx->end == end) + return true; + + return false; +} + +int userfaultfd_unmap_prep(struct vm_area_struct *vma, + unsigned long start, unsigned long end, + struct list_head *unmaps) +{ + for ( ; vma && vma->vm_start < end; vma = vma->vm_next) { + struct userfaultfd_unmap_ctx *unmap_ctx; + struct userfaultfd_ctx *ctx = vma->vm_userfaultfd_ctx.ctx; + + if (!ctx || !(ctx->features & UFFD_FEATURE_EVENT_UNMAP) || + has_unmap_ctx(ctx, unmaps, start, end)) + continue; + + unmap_ctx = kzalloc(sizeof(*unmap_ctx), GFP_KERNEL); + if (!unmap_ctx) + return -ENOMEM; + + userfaultfd_ctx_get(ctx); + unmap_ctx->ctx = ctx; + unmap_ctx->start = start; + unmap_ctx->end = end; + list_add_tail(&unmap_ctx->list, unmaps); + } + + return 0; +} + +void userfaultfd_unmap_complete(struct mm_struct *mm, struct list_head *uf) +{ + struct userfaultfd_unmap_ctx *ctx, *n; + struct userfaultfd_wait_queue ewq; + + list_for_each_entry_safe(ctx, n, uf, list) { + msg_init(&ewq.msg); + + ewq.msg.event = UFFD_EVENT_UNMAP; + ewq.msg.arg.remove.start = ctx->start; + ewq.msg.arg.remove.end = ctx->end; + + userfaultfd_event_wait_completion(ctx->ctx, &ewq); + + list_del(&ctx->list); + kfree(ctx); + } +} + +void userfaultfd_exit(struct mm_struct *mm) +{ + struct vm_area_struct *vma = mm->mmap; + + /* + * We can do the vma walk without locking because the caller + * (exit_mm) knows it now has exclusive access + */ + while (vma) { + struct userfaultfd_ctx *ctx = vma->vm_userfaultfd_ctx.ctx; + + if (ctx && (ctx->features & UFFD_FEATURE_EVENT_EXIT)) { + struct userfaultfd_wait_queue ewq; + + userfaultfd_ctx_get(ctx); + + msg_init(&ewq.msg); + ewq.msg.event = UFFD_EVENT_EXIT; + + userfaultfd_event_wait_completion(ctx, &ewq); + + ctx->features &= ~UFFD_FEATURE_EVENT_EXIT; + } + + vma = vma->vm_next; + } +} + static int userfaultfd_release(struct inode *inode, struct file *file) { struct userfaultfd_ctx *ctx = file->private_data; @@ -522,25 +866,36 @@ wakeup: } /* fault_pending_wqh.lock must be hold by the caller */ -static inline struct userfaultfd_wait_queue *find_userfault( - struct userfaultfd_ctx *ctx) +static inline struct userfaultfd_wait_queue *find_userfault_in( + wait_queue_head_t *wqh) { wait_queue_t *wq; struct userfaultfd_wait_queue *uwq; - VM_BUG_ON(!spin_is_locked(&ctx->fault_pending_wqh.lock)); + VM_BUG_ON(!spin_is_locked(&wqh->lock)); uwq = NULL; - if (!waitqueue_active(&ctx->fault_pending_wqh)) + if (!waitqueue_active(wqh)) goto out; /* walk in reverse to provide FIFO behavior to read userfaults */ - wq = list_last_entry(&ctx->fault_pending_wqh.task_list, - typeof(*wq), task_list); + wq = list_last_entry(&wqh->task_list, typeof(*wq), task_list); uwq = container_of(wq, struct userfaultfd_wait_queue, wq); out: return uwq; } +static inline struct userfaultfd_wait_queue *find_userfault( + struct userfaultfd_ctx *ctx) +{ + return find_userfault_in(&ctx->fault_pending_wqh); +} + +static inline struct userfaultfd_wait_queue *find_userfault_evt( + struct userfaultfd_ctx *ctx) +{ + return find_userfault_in(&ctx->event_wqh); +} + static unsigned int userfaultfd_poll(struct file *file, poll_table *wait) { struct userfaultfd_ctx *ctx = file->private_data; @@ -572,10 +927,42 @@ static unsigned int userfaultfd_poll(struct file *file, poll_table *wait) smp_mb(); if (waitqueue_active(&ctx->fault_pending_wqh)) ret = POLLIN; + else if (waitqueue_active(&ctx->event_wqh)) + ret = POLLIN; + return ret; default: - BUG(); + WARN_ON_ONCE(1); + return POLLERR; + } +} + +static const struct file_operations userfaultfd_fops; + +static int resolve_userfault_fork(struct userfaultfd_ctx *ctx, + struct userfaultfd_ctx *new, + struct uffd_msg *msg) +{ + int fd; + struct file *file; + unsigned int flags = new->flags & UFFD_SHARED_FCNTL_FLAGS; + + fd = get_unused_fd_flags(flags); + if (fd < 0) + return fd; + + file = anon_inode_getfile("[userfaultfd]", &userfaultfd_fops, new, + O_RDWR | flags); + if (IS_ERR(file)) { + put_unused_fd(fd); + return PTR_ERR(file); } + + fd_install(fd, file); + msg->arg.reserved.reserved1 = 0; + msg->arg.fork.ufd = fd; + + return 0; } static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait, @@ -584,6 +971,15 @@ static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait, ssize_t ret; DECLARE_WAITQUEUE(wait, current); struct userfaultfd_wait_queue *uwq; + /* + * Handling fork event requires sleeping operations, so + * we drop the event_wqh lock, then do these ops, then + * lock it back and wake up the waiter. While the lock is + * dropped the ewq may go away so we keep track of it + * carefully. + */ + LIST_HEAD(fork_event); + struct userfaultfd_ctx *fork_nctx = NULL; /* always take the fd_wqh lock before the fault_pending_wqh lock */ spin_lock(&ctx->fd_wqh.lock); @@ -635,6 +1031,29 @@ static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait, break; } spin_unlock(&ctx->fault_pending_wqh.lock); + + spin_lock(&ctx->event_wqh.lock); + uwq = find_userfault_evt(ctx); + if (uwq) { + *msg = uwq->msg; + + if (uwq->msg.event == UFFD_EVENT_FORK) { + fork_nctx = (struct userfaultfd_ctx *) + (unsigned long) + uwq->msg.arg.reserved.reserved1; + list_move(&uwq->wq.task_list, &fork_event); + spin_unlock(&ctx->event_wqh.lock); + ret = 0; + break; + } + + userfaultfd_event_complete(ctx, uwq); + spin_unlock(&ctx->event_wqh.lock); + ret = 0; + break; + } + spin_unlock(&ctx->event_wqh.lock); + if (signal_pending(current)) { ret = -ERESTARTSYS; break; @@ -651,6 +1070,23 @@ static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait, __set_current_state(TASK_RUNNING); spin_unlock(&ctx->fd_wqh.lock); + if (!ret && msg->event == UFFD_EVENT_FORK) { + ret = resolve_userfault_fork(ctx, fork_nctx, msg); + + if (!ret) { + spin_lock(&ctx->event_wqh.lock); + if (!list_empty(&fork_event)) { + uwq = list_first_entry(&fork_event, + typeof(*uwq), + wq.task_list); + list_del(&uwq->wq.task_list); + __add_wait_queue(&ctx->event_wqh, &uwq->wq); + userfaultfd_event_complete(ctx, uwq); + } + spin_unlock(&ctx->event_wqh.lock); + } + } + return ret; } @@ -753,6 +1189,12 @@ static __always_inline int validate_range(struct mm_struct *mm, return 0; } +static inline bool vma_can_userfault(struct vm_area_struct *vma) +{ + return vma_is_anonymous(vma) || is_vm_hugetlb_page(vma) || + vma_is_shmem(vma); +} + static int userfaultfd_register(struct userfaultfd_ctx *ctx, unsigned long arg) { @@ -763,6 +1205,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, struct uffdio_register __user *user_uffdio_register; unsigned long vm_flags, new_flags; bool found; + bool non_anon_pages; unsigned long start, end, vma_end; user_uffdio_register = (struct uffdio_register __user *) arg; @@ -814,13 +1257,21 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, goto out_unlock; /* + * If the first vma contains huge pages, make sure start address + * is aligned to huge page size. + */ + if (is_vm_hugetlb_page(vma)) { + unsigned long vma_hpagesize = vma_kernel_pagesize(vma); + + if (start & (vma_hpagesize - 1)) + goto out_unlock; + } + + /* * Search for not compatible vmas. - * - * FIXME: this shall be relaxed later so that it doesn't fail - * on tmpfs backed vmas (in addition to the current allowance - * on anonymous vmas). */ found = false; + non_anon_pages = false; for (cur = vma; cur && cur->vm_start < end; cur = cur->vm_next) { cond_resched(); @@ -829,8 +1280,21 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, /* check not compatible vmas */ ret = -EINVAL; - if (cur->vm_ops) + if (!vma_can_userfault(cur)) goto out_unlock; + /* + * If this vma contains ending address, and huge pages + * check alignment. + */ + if (is_vm_hugetlb_page(cur) && end <= cur->vm_end && + end > cur->vm_start) { + unsigned long vma_hpagesize = vma_kernel_pagesize(cur); + + ret = -EINVAL; + + if (end & (vma_hpagesize - 1)) + goto out_unlock; + } /* * Check that this vma isn't already owned by a @@ -843,6 +1307,12 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, cur->vm_userfaultfd_ctx.ctx != ctx) goto out_unlock; + /* + * Note vmas containing huge pages + */ + if (is_vm_hugetlb_page(cur) || vma_is_shmem(cur)) + non_anon_pages = true; + found = true; } BUG_ON(!found); @@ -854,7 +1324,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, do { cond_resched(); - BUG_ON(vma->vm_ops); + BUG_ON(!vma_can_userfault(vma)); BUG_ON(vma->vm_userfaultfd_ctx.ctx && vma->vm_userfaultfd_ctx.ctx != ctx); @@ -912,7 +1382,8 @@ out_unlock: * userland which ioctls methods are guaranteed to * succeed on this range. */ - if (put_user(UFFD_API_RANGE_IOCTLS, + if (put_user(non_anon_pages ? UFFD_API_RANGE_IOCTLS_BASIC : + UFFD_API_RANGE_IOCTLS, &user_uffdio_register->ioctls)) ret = -EFAULT; } @@ -959,11 +1430,18 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, goto out_unlock; /* + * If the first vma contains huge pages, make sure start address + * is aligned to huge page size. + */ + if (is_vm_hugetlb_page(vma)) { + unsigned long vma_hpagesize = vma_kernel_pagesize(vma); + + if (start & (vma_hpagesize - 1)) + goto out_unlock; + } + + /* * Search for not compatible vmas. - * - * FIXME: this shall be relaxed later so that it doesn't fail - * on tmpfs backed vmas (in addition to the current allowance - * on anonymous vmas). */ found = false; ret = -EINVAL; @@ -980,7 +1458,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, * provides for more strict behavior to notice * unregistration errors. */ - if (cur->vm_ops) + if (!vma_can_userfault(cur)) goto out_unlock; found = true; @@ -994,7 +1472,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, do { cond_resched(); - BUG_ON(vma->vm_ops); + BUG_ON(!vma_can_userfault(vma)); /* * Nothing to do: this vma is already registered into this @@ -1007,6 +1485,19 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, start = vma->vm_start; vma_end = min(end, vma->vm_end); + if (userfaultfd_missing(vma)) { + /* + * Wake any concurrent pending userfault while + * we unregister, so they will not hang + * permanently and it avoids userland to call + * UFFDIO_WAKE explicitly. + */ + struct userfaultfd_wake_range range; + range.start = start; + range.len = vma_end - start; + wake_userfault(vma->vm_userfaultfd_ctx.ctx, &range); + } + new_flags = vma->vm_flags & ~(VM_UFFD_MISSING | VM_UFFD_WP); prev = vma_merge(mm, prev, start, vma_end, new_flags, vma->anon_vma, vma->vm_file, vma->vm_pgoff, @@ -1116,6 +1607,8 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx, ret = mcopy_atomic(ctx->mm, uffdio_copy.dst, uffdio_copy.src, uffdio_copy.len); mmput(ctx->mm); + } else { + return -ENOSPC; } if (unlikely(put_user(ret, &user_uffdio_copy->copy))) return -EFAULT; @@ -1178,6 +1671,14 @@ out: return ret; } +static inline unsigned int uffd_ctx_features(__u64 user_features) +{ + /* + * For the current set of features the bits just coincide + */ + return (unsigned int)user_features; +} + /* * userland asks for a certain API version and we return which bits * and ioctl commands are implemented in this kernel for such API @@ -1189,6 +1690,7 @@ static int userfaultfd_api(struct userfaultfd_ctx *ctx, struct uffdio_api uffdio_api; void __user *buf = (void __user *)arg; int ret; + __u64 features; ret = -EINVAL; if (ctx->state != UFFD_STATE_WAIT_API) @@ -1196,19 +1698,23 @@ static int userfaultfd_api(struct userfaultfd_ctx *ctx, ret = -EFAULT; if (copy_from_user(&uffdio_api, buf, sizeof(uffdio_api))) goto out; - if (uffdio_api.api != UFFD_API || uffdio_api.features) { + features = uffdio_api.features; + if (uffdio_api.api != UFFD_API || (features & ~UFFD_API_FEATURES)) { memset(&uffdio_api, 0, sizeof(uffdio_api)); if (copy_to_user(buf, &uffdio_api, sizeof(uffdio_api))) goto out; ret = -EINVAL; goto out; } + /* report all available features and ioctls to userland */ uffdio_api.features = UFFD_API_FEATURES; uffdio_api.ioctls = UFFD_API_IOCTLS; ret = -EFAULT; if (copy_to_user(buf, &uffdio_api, sizeof(uffdio_api))) goto out; ctx->state = UFFD_STATE_RUNNING; + /* only enable the requested features for this uffd context */ + ctx->features = uffd_ctx_features(features); ret = 0; out: return ret; @@ -1295,22 +1801,23 @@ static void init_once_userfaultfd_ctx(void *mem) init_waitqueue_head(&ctx->fault_pending_wqh); init_waitqueue_head(&ctx->fault_wqh); + init_waitqueue_head(&ctx->event_wqh); init_waitqueue_head(&ctx->fd_wqh); seqcount_init(&ctx->refile_seq); } /** - * userfaultfd_file_create - Creates an userfaultfd file pointer. + * userfaultfd_file_create - Creates a userfaultfd file pointer. * @flags: Flags for the userfaultfd file. * - * This function creates an userfaultfd file pointer, w/out installing + * This function creates a userfaultfd file pointer, w/out installing * it into the fd table. This is useful when the userfaultfd file is * used during the initialization of data structures that require * extra setup after the userfaultfd creation. So the userfaultfd * creation is split into the file pointer creation phase, and the * file descriptor installation phase. In this way races with * userspace closing the newly installed file descriptor can be - * avoided. Returns an userfaultfd file pointer, or a proper error + * avoided. Returns a userfaultfd file pointer, or a proper error * pointer. */ static struct file *userfaultfd_file_create(int flags) @@ -1335,11 +1842,12 @@ static struct file *userfaultfd_file_create(int flags) atomic_set(&ctx->refcount, 1); ctx->flags = flags; + ctx->features = 0; ctx->state = UFFD_STATE_WAIT_API; ctx->released = false; ctx->mm = current->mm; /* prevent the mm struct to be freed */ - atomic_inc(&ctx->mm->mm_count); + mmgrab(ctx->mm); file = anon_inode_getfile("[userfaultfd]", &userfaultfd_fops, ctx, O_RDWR | (flags & UFFD_SHARED_FCNTL_FLAGS)); diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index 9f06a211e157..369adcc18c02 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -221,20 +221,22 @@ xfs_alloc_get_rec( * Compute aligned version of the found extent. * Takes alignment and min length into account. */ -STATIC void +STATIC bool xfs_alloc_compute_aligned( xfs_alloc_arg_t *args, /* allocation argument structure */ xfs_agblock_t foundbno, /* starting block in found extent */ xfs_extlen_t foundlen, /* length in found extent */ xfs_agblock_t *resbno, /* result block number */ - xfs_extlen_t *reslen) /* result length */ + xfs_extlen_t *reslen, /* result length */ + unsigned *busy_gen) { - xfs_agblock_t bno; - xfs_extlen_t len; + xfs_agblock_t bno = foundbno; + xfs_extlen_t len = foundlen; xfs_extlen_t diff; + bool busy; /* Trim busy sections out of found extent */ - xfs_extent_busy_trim(args, foundbno, foundlen, &bno, &len); + busy = xfs_extent_busy_trim(args, &bno, &len, busy_gen); /* * If we have a largish extent that happens to start before min_agbno, @@ -259,6 +261,8 @@ xfs_alloc_compute_aligned( *resbno = bno; *reslen = len; } + + return busy; } /* @@ -737,10 +741,11 @@ xfs_alloc_ag_vextent_exact( int error; xfs_agblock_t fbno; /* start block of found extent */ xfs_extlen_t flen; /* length of found extent */ - xfs_agblock_t tbno; /* start block of trimmed extent */ - xfs_extlen_t tlen; /* length of trimmed extent */ - xfs_agblock_t tend; /* end block of trimmed extent */ + xfs_agblock_t tbno; /* start block of busy extent */ + xfs_extlen_t tlen; /* length of busy extent */ + xfs_agblock_t tend; /* end block of busy extent */ int i; /* success/failure of operation */ + unsigned busy_gen; ASSERT(args->alignment == 1); @@ -773,7 +778,9 @@ xfs_alloc_ag_vextent_exact( /* * Check for overlapping busy extents. */ - xfs_extent_busy_trim(args, fbno, flen, &tbno, &tlen); + tbno = fbno; + tlen = flen; + xfs_extent_busy_trim(args, &tbno, &tlen, &busy_gen); /* * Give up if the start of the extent is busy, or the freespace isn't @@ -853,6 +860,7 @@ xfs_alloc_find_best_extent( xfs_agblock_t sdiff; int error; int i; + unsigned busy_gen; /* The good extent is perfect, no need to search. */ if (!gdiff) @@ -866,7 +874,8 @@ xfs_alloc_find_best_extent( if (error) goto error0; XFS_WANT_CORRUPTED_GOTO(args->mp, i == 1, error0); - xfs_alloc_compute_aligned(args, *sbno, *slen, sbnoa, slena); + xfs_alloc_compute_aligned(args, *sbno, *slen, + sbnoa, slena, &busy_gen); /* * The good extent is closer than this one. @@ -955,7 +964,8 @@ xfs_alloc_ag_vextent_near( xfs_extlen_t ltlena; /* aligned ... */ xfs_agblock_t ltnew; /* useful start bno of left side */ xfs_extlen_t rlen; /* length of returned extent */ - int forced = 0; + bool busy; + unsigned busy_gen; #ifdef DEBUG /* * Randomly don't execute the first algorithm. @@ -982,6 +992,7 @@ restart: ltlen = 0; gtlena = 0; ltlena = 0; + busy = false; /* * Get a cursor for the by-size btree. @@ -1064,8 +1075,8 @@ restart: if ((error = xfs_alloc_get_rec(cnt_cur, <bno, <len, &i))) goto error0; XFS_WANT_CORRUPTED_GOTO(args->mp, i == 1, error0); - xfs_alloc_compute_aligned(args, ltbno, ltlen, - <bnoa, <lena); + busy = xfs_alloc_compute_aligned(args, ltbno, ltlen, + <bnoa, <lena, &busy_gen); if (ltlena < args->minlen) continue; if (ltbnoa < args->min_agbno || ltbnoa > args->max_agbno) @@ -1183,8 +1194,8 @@ restart: if ((error = xfs_alloc_get_rec(bno_cur_lt, <bno, <len, &i))) goto error0; XFS_WANT_CORRUPTED_GOTO(args->mp, i == 1, error0); - xfs_alloc_compute_aligned(args, ltbno, ltlen, - <bnoa, <lena); + busy |= xfs_alloc_compute_aligned(args, ltbno, ltlen, + <bnoa, <lena, &busy_gen); if (ltlena >= args->minlen && ltbnoa >= args->min_agbno) break; if ((error = xfs_btree_decrement(bno_cur_lt, 0, &i))) @@ -1199,8 +1210,8 @@ restart: if ((error = xfs_alloc_get_rec(bno_cur_gt, >bno, >len, &i))) goto error0; XFS_WANT_CORRUPTED_GOTO(args->mp, i == 1, error0); - xfs_alloc_compute_aligned(args, gtbno, gtlen, - >bnoa, >lena); + busy |= xfs_alloc_compute_aligned(args, gtbno, gtlen, + >bnoa, >lena, &busy_gen); if (gtlena >= args->minlen && gtbnoa <= args->max_agbno) break; if ((error = xfs_btree_increment(bno_cur_gt, 0, &i))) @@ -1261,9 +1272,9 @@ restart: if (bno_cur_lt == NULL && bno_cur_gt == NULL) { xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR); - if (!forced++) { + if (busy) { trace_xfs_alloc_near_busy(args); - xfs_log_force(args->mp, XFS_LOG_SYNC); + xfs_extent_busy_flush(args->mp, args->pag, busy_gen); goto restart; } trace_xfs_alloc_size_neither(args); @@ -1344,7 +1355,8 @@ xfs_alloc_ag_vextent_size( int i; /* temp status variable */ xfs_agblock_t rbno; /* returned block number */ xfs_extlen_t rlen; /* length of returned extent */ - int forced = 0; + bool busy; + unsigned busy_gen; restart: /* @@ -1353,6 +1365,7 @@ restart: cnt_cur = xfs_allocbt_init_cursor(args->mp, args->tp, args->agbp, args->agno, XFS_BTNUM_CNT); bno_cur = NULL; + busy = false; /* * Look for an entry >= maxlen+alignment-1 blocks. @@ -1362,14 +1375,13 @@ restart: goto error0; /* - * If none or we have busy extents that we cannot allocate from, then - * we have to settle for a smaller extent. In the case that there are - * no large extents, this will return the last entry in the tree unless - * the tree is empty. In the case that there are only busy large - * extents, this will return the largest small extent unless there + * If none then we have to settle for a smaller extent. In the case that + * there are no large extents, this will return the last entry in the + * tree unless the tree is empty. In the case that there are only busy + * large extents, this will return the largest small extent unless there * are no smaller extents available. */ - if (!i || forced > 1) { + if (!i) { error = xfs_alloc_ag_vextent_small(args, cnt_cur, &fbno, &flen, &i); if (error) @@ -1380,13 +1392,11 @@ restart: return 0; } ASSERT(i == 1); - xfs_alloc_compute_aligned(args, fbno, flen, &rbno, &rlen); + busy = xfs_alloc_compute_aligned(args, fbno, flen, &rbno, + &rlen, &busy_gen); } else { /* * Search for a non-busy extent that is large enough. - * If we are at low space, don't check, or if we fall of - * the end of the btree, turn off the busy check and - * restart. */ for (;;) { error = xfs_alloc_get_rec(cnt_cur, &fbno, &flen, &i); @@ -1394,8 +1404,8 @@ restart: goto error0; XFS_WANT_CORRUPTED_GOTO(args->mp, i == 1, error0); - xfs_alloc_compute_aligned(args, fbno, flen, - &rbno, &rlen); + busy = xfs_alloc_compute_aligned(args, fbno, flen, + &rbno, &rlen, &busy_gen); if (rlen >= args->maxlen) break; @@ -1407,18 +1417,13 @@ restart: /* * Our only valid extents must have been busy. * Make it unbusy by forcing the log out and - * retrying. If we've been here before, forcing - * the log isn't making the extents available, - * which means they have probably been freed in - * this transaction. In that case, we have to - * give up on them and we'll attempt a minlen - * allocation the next time around. + * retrying. */ xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR); trace_xfs_alloc_size_busy(args); - if (!forced++) - xfs_log_force(args->mp, XFS_LOG_SYNC); + xfs_extent_busy_flush(args->mp, + args->pag, busy_gen); goto restart; } } @@ -1454,8 +1459,8 @@ restart: XFS_WANT_CORRUPTED_GOTO(args->mp, i == 1, error0); if (flen < bestrlen) break; - xfs_alloc_compute_aligned(args, fbno, flen, - &rbno, &rlen); + busy = xfs_alloc_compute_aligned(args, fbno, flen, + &rbno, &rlen, &busy_gen); rlen = XFS_EXTLEN_MIN(args->maxlen, rlen); XFS_WANT_CORRUPTED_GOTO(args->mp, rlen == 0 || (rlen <= flen && rbno + rlen <= fbno + flen), @@ -1484,10 +1489,10 @@ restart: */ args->len = rlen; if (rlen < args->minlen) { - if (!forced++) { + if (busy) { xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR); trace_xfs_alloc_size_busy(args); - xfs_log_force(args->mp, XFS_LOG_SYNC); + xfs_extent_busy_flush(args->mp, args->pag, busy_gen); goto restart; } goto out_nominleft; @@ -2659,21 +2664,11 @@ xfs_alloc_vextent( args->agbno = XFS_FSB_TO_AGBNO(mp, args->fsbno); args->type = XFS_ALLOCTYPE_NEAR_BNO; /* FALLTHROUGH */ - case XFS_ALLOCTYPE_ANY_AG: - case XFS_ALLOCTYPE_START_AG: case XFS_ALLOCTYPE_FIRST_AG: /* * Rotate through the allocation groups looking for a winner. */ - if (type == XFS_ALLOCTYPE_ANY_AG) { - /* - * Start with the last place we left off. - */ - args->agno = sagno = (mp->m_agfrotor / rotorstep) % - mp->m_sb.sb_agcount; - args->type = XFS_ALLOCTYPE_THIS_AG; - flags = XFS_ALLOC_FLAG_TRYLOCK; - } else if (type == XFS_ALLOCTYPE_FIRST_AG) { + if (type == XFS_ALLOCTYPE_FIRST_AG) { /* * Start with allocation group given by bno. */ @@ -2682,8 +2677,6 @@ xfs_alloc_vextent( sagno = 0; flags = 0; } else { - if (type == XFS_ALLOCTYPE_START_AG) - args->type = XFS_ALLOCTYPE_THIS_AG; /* * Start with the given allocation group. */ @@ -2751,7 +2744,7 @@ xfs_alloc_vextent( } xfs_perag_put(args->pag); } - if (bump_rotor || (type == XFS_ALLOCTYPE_ANY_AG)) { + if (bump_rotor) { if (args->agno == sagno) mp->m_agfrotor = (mp->m_agfrotor + 1) % (mp->m_sb.sb_agcount * rotorstep); diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h index 1d0f48a501a3..2a8d0fa6fbbe 100644 --- a/fs/xfs/libxfs/xfs_alloc.h +++ b/fs/xfs/libxfs/xfs_alloc.h @@ -29,9 +29,7 @@ extern struct workqueue_struct *xfs_alloc_wq; /* * Freespace allocation types. Argument to xfs_alloc_[v]extent. */ -#define XFS_ALLOCTYPE_ANY_AG 0x01 /* allocate anywhere, use rotor */ #define XFS_ALLOCTYPE_FIRST_AG 0x02 /* ... start at ag 0 */ -#define XFS_ALLOCTYPE_START_AG 0x04 /* anywhere, start in this a.g. */ #define XFS_ALLOCTYPE_THIS_AG 0x08 /* anywhere in this a.g. */ #define XFS_ALLOCTYPE_START_BNO 0x10 /* near this block else anywhere */ #define XFS_ALLOCTYPE_NEAR_BNO 0x20 /* in this a.g. and near this block */ @@ -41,9 +39,7 @@ extern struct workqueue_struct *xfs_alloc_wq; typedef unsigned int xfs_alloctype_t; #define XFS_ALLOC_TYPES \ - { XFS_ALLOCTYPE_ANY_AG, "ANY_AG" }, \ { XFS_ALLOCTYPE_FIRST_AG, "FIRST_AG" }, \ - { XFS_ALLOCTYPE_START_AG, "START_AG" }, \ { XFS_ALLOCTYPE_THIS_AG, "THIS_AG" }, \ { XFS_ALLOCTYPE_START_BNO, "START_BNO" }, \ { XFS_ALLOCTYPE_NEAR_BNO, "NEAR_BNO" }, \ diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index bfc00de5c6f1..a9c66d47757a 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -740,15 +740,9 @@ xfs_bmap_extents_to_btree( * Fill in the root. */ block = ifp->if_broot; - if (xfs_sb_version_hascrc(&mp->m_sb)) - xfs_btree_init_block_int(mp, block, XFS_BUF_DADDR_NULL, - XFS_BMAP_CRC_MAGIC, 1, 1, ip->i_ino, - XFS_BTREE_LONG_PTRS | XFS_BTREE_CRC_BLOCKS); - else - xfs_btree_init_block_int(mp, block, XFS_BUF_DADDR_NULL, - XFS_BMAP_MAGIC, 1, 1, ip->i_ino, + xfs_btree_init_block_int(mp, block, XFS_BUF_DADDR_NULL, + XFS_BTNUM_BMAP, 1, 1, ip->i_ino, XFS_BTREE_LONG_PTRS); - /* * Need a cursor. Can't allocate until bb_level is filled in. */ @@ -804,9 +798,7 @@ try_another_ag: */ ASSERT(args.fsbno != NULLFSBLOCK); ASSERT(*firstblock == NULLFSBLOCK || - args.agno == XFS_FSB_TO_AGNO(mp, *firstblock) || - (dfops->dop_low && - args.agno > XFS_FSB_TO_AGNO(mp, *firstblock))); + args.agno >= XFS_FSB_TO_AGNO(mp, *firstblock)); *firstblock = cur->bc_private.b.firstblock = args.fsbno; cur->bc_private.b.allocated++; ip->i_d.di_nblocks++; @@ -817,13 +809,8 @@ try_another_ag: */ abp->b_ops = &xfs_bmbt_buf_ops; ablock = XFS_BUF_TO_BLOCK(abp); - if (xfs_sb_version_hascrc(&mp->m_sb)) - xfs_btree_init_block_int(mp, ablock, abp->b_bn, - XFS_BMAP_CRC_MAGIC, 0, 0, ip->i_ino, - XFS_BTREE_LONG_PTRS | XFS_BTREE_CRC_BLOCKS); - else - xfs_btree_init_block_int(mp, ablock, abp->b_bn, - XFS_BMAP_MAGIC, 0, 0, ip->i_ino, + xfs_btree_init_block_int(mp, ablock, abp->b_bn, + XFS_BTNUM_BMAP, 0, 0, ip->i_ino, XFS_BTREE_LONG_PTRS); arp = XFS_BMBT_REC_ADDR(mp, ablock, 1); @@ -1278,7 +1265,6 @@ xfs_bmap_read_extents( /* REFERENCED */ xfs_extnum_t room; /* number of entries there's room for */ - bno = NULLFSBLOCK; mp = ip->i_mount; ifp = XFS_IFORK_PTR(ip, whichfork); exntf = (whichfork != XFS_DATA_FORK) ? XFS_EXTFMT_NOSTATE : @@ -1291,9 +1277,7 @@ xfs_bmap_read_extents( ASSERT(level > 0); pp = XFS_BMAP_BROOT_PTR_ADDR(mp, block, 1, ifp->if_broot_bytes); bno = be64_to_cpu(*pp); - ASSERT(bno != NULLFSBLOCK); - ASSERT(XFS_FSB_TO_AGNO(mp, bno) < mp->m_sb.sb_agcount); - ASSERT(XFS_FSB_TO_AGBNO(mp, bno) < mp->m_sb.sb_agblocks); + /* * Go down the tree until leaf level is reached, following the first * pointer (leftmost) at each level. @@ -1864,6 +1848,7 @@ xfs_bmap_add_extent_delay_real( */ trace_xfs_bmap_pre_update(bma->ip, bma->idx, state, _THIS_IP_); xfs_bmbt_set_startblock(ep, new->br_startblock); + xfs_bmbt_set_state(ep, new->br_state); trace_xfs_bmap_post_update(bma->ip, bma->idx, state, _THIS_IP_); (*nextents)++; @@ -2202,6 +2187,7 @@ STATIC int /* error */ xfs_bmap_add_extent_unwritten_real( struct xfs_trans *tp, xfs_inode_t *ip, /* incore inode pointer */ + int whichfork, xfs_extnum_t *idx, /* extent number to update/insert */ xfs_btree_cur_t **curp, /* if *curp is null, not a btree */ xfs_bmbt_irec_t *new, /* new data to add to file extents */ @@ -2221,12 +2207,14 @@ xfs_bmap_add_extent_unwritten_real( /* left is 0, right is 1, prev is 2 */ int rval=0; /* return value (logging flags) */ int state = 0;/* state bits, accessed thru macros */ - struct xfs_mount *mp = tp->t_mountp; + struct xfs_mount *mp = ip->i_mount; *logflagsp = 0; cur = *curp; - ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK); + ifp = XFS_IFORK_PTR(ip, whichfork); + if (whichfork == XFS_COW_FORK) + state |= BMAP_COWFORK; ASSERT(*idx >= 0); ASSERT(*idx <= xfs_iext_count(ifp)); @@ -2285,7 +2273,7 @@ xfs_bmap_add_extent_unwritten_real( * Don't set contiguous if the combined extent would be too large. * Also check for all-three-contiguous being too large. */ - if (*idx < xfs_iext_count(&ip->i_df) - 1) { + if (*idx < xfs_iext_count(ifp) - 1) { state |= BMAP_RIGHT_VALID; xfs_bmbt_get_all(xfs_iext_get_ext(ifp, *idx + 1), &RIGHT); if (isnullstartblock(RIGHT.br_startblock)) @@ -2325,7 +2313,8 @@ xfs_bmap_add_extent_unwritten_real( trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); xfs_iext_remove(ip, *idx + 1, 2, state); - ip->i_d.di_nextents -= 2; + XFS_IFORK_NEXT_SET(ip, whichfork, + XFS_IFORK_NEXTENTS(ip, whichfork) - 2); if (cur == NULL) rval = XFS_ILOG_CORE | XFS_ILOG_DEXT; else { @@ -2368,7 +2357,8 @@ xfs_bmap_add_extent_unwritten_real( trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); xfs_iext_remove(ip, *idx + 1, 1, state); - ip->i_d.di_nextents--; + XFS_IFORK_NEXT_SET(ip, whichfork, + XFS_IFORK_NEXTENTS(ip, whichfork) - 1); if (cur == NULL) rval = XFS_ILOG_CORE | XFS_ILOG_DEXT; else { @@ -2403,7 +2393,8 @@ xfs_bmap_add_extent_unwritten_real( xfs_bmbt_set_state(ep, newext); trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); xfs_iext_remove(ip, *idx + 1, 1, state); - ip->i_d.di_nextents--; + XFS_IFORK_NEXT_SET(ip, whichfork, + XFS_IFORK_NEXTENTS(ip, whichfork) - 1); if (cur == NULL) rval = XFS_ILOG_CORE | XFS_ILOG_DEXT; else { @@ -2515,7 +2506,8 @@ xfs_bmap_add_extent_unwritten_real( trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); xfs_iext_insert(ip, *idx, 1, new, state); - ip->i_d.di_nextents++; + XFS_IFORK_NEXT_SET(ip, whichfork, + XFS_IFORK_NEXTENTS(ip, whichfork) + 1); if (cur == NULL) rval = XFS_ILOG_CORE | XFS_ILOG_DEXT; else { @@ -2593,7 +2585,8 @@ xfs_bmap_add_extent_unwritten_real( ++*idx; xfs_iext_insert(ip, *idx, 1, new, state); - ip->i_d.di_nextents++; + XFS_IFORK_NEXT_SET(ip, whichfork, + XFS_IFORK_NEXTENTS(ip, whichfork) + 1); if (cur == NULL) rval = XFS_ILOG_CORE | XFS_ILOG_DEXT; else { @@ -2641,7 +2634,8 @@ xfs_bmap_add_extent_unwritten_real( ++*idx; xfs_iext_insert(ip, *idx, 2, &r[0], state); - ip->i_d.di_nextents += 2; + XFS_IFORK_NEXT_SET(ip, whichfork, + XFS_IFORK_NEXTENTS(ip, whichfork) + 2); if (cur == NULL) rval = XFS_ILOG_CORE | XFS_ILOG_DEXT; else { @@ -2695,17 +2689,17 @@ xfs_bmap_add_extent_unwritten_real( } /* update reverse mappings */ - error = xfs_rmap_convert_extent(mp, dfops, ip, XFS_DATA_FORK, new); + error = xfs_rmap_convert_extent(mp, dfops, ip, whichfork, new); if (error) goto done; /* convert to a btree if necessary */ - if (xfs_bmap_needs_btree(ip, XFS_DATA_FORK)) { + if (xfs_bmap_needs_btree(ip, whichfork)) { int tmp_logflags; /* partial log flag return val */ ASSERT(cur == NULL); error = xfs_bmap_extents_to_btree(tp, ip, first, dfops, &cur, - 0, &tmp_logflags, XFS_DATA_FORK); + 0, &tmp_logflags, whichfork); *logflagsp |= tmp_logflags; if (error) goto done; @@ -2717,7 +2711,7 @@ xfs_bmap_add_extent_unwritten_real( *curp = cur; } - xfs_bmap_check_leaf_extents(*curp, ip, XFS_DATA_FORK); + xfs_bmap_check_leaf_extents(*curp, ip, whichfork); done: *logflagsp |= rval; return error; @@ -2809,7 +2803,8 @@ xfs_bmap_add_extent_hole_delay( oldlen = startblockval(left.br_startblock) + startblockval(new->br_startblock) + startblockval(right.br_startblock); - newlen = xfs_bmap_worst_indlen(ip, temp); + newlen = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp), + oldlen); xfs_bmbt_set_startblock(xfs_iext_get_ext(ifp, *idx), nullstartblock((int)newlen)); trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); @@ -2830,7 +2825,8 @@ xfs_bmap_add_extent_hole_delay( xfs_bmbt_set_blockcount(xfs_iext_get_ext(ifp, *idx), temp); oldlen = startblockval(left.br_startblock) + startblockval(new->br_startblock); - newlen = xfs_bmap_worst_indlen(ip, temp); + newlen = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp), + oldlen); xfs_bmbt_set_startblock(xfs_iext_get_ext(ifp, *idx), nullstartblock((int)newlen)); trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); @@ -2846,7 +2842,8 @@ xfs_bmap_add_extent_hole_delay( temp = new->br_blockcount + right.br_blockcount; oldlen = startblockval(new->br_startblock) + startblockval(right.br_startblock); - newlen = xfs_bmap_worst_indlen(ip, temp); + newlen = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp), + oldlen); xfs_bmbt_set_allf(xfs_iext_get_ext(ifp, *idx), new->br_startoff, nullstartblock((int)newlen), temp, right.br_state); @@ -2899,13 +2896,14 @@ xfs_bmap_add_extent_hole_real( ASSERT(!isnullstartblock(new->br_startblock)); ASSERT(!bma->cur || !(bma->cur->bc_private.b.flags & XFS_BTCUR_BPRV_WASDEL)); - ASSERT(whichfork != XFS_COW_FORK); XFS_STATS_INC(mp, xs_add_exlist); state = 0; if (whichfork == XFS_ATTR_FORK) state |= BMAP_ATTRFORK; + if (whichfork == XFS_COW_FORK) + state |= BMAP_COWFORK; /* * Check and set flags if this segment has a left neighbor. @@ -3822,17 +3820,13 @@ xfs_bmap_btalloc( * the first block that was allocated. */ ASSERT(*ap->firstblock == NULLFSBLOCK || - XFS_FSB_TO_AGNO(mp, *ap->firstblock) == - XFS_FSB_TO_AGNO(mp, args.fsbno) || - (ap->dfops->dop_low && - XFS_FSB_TO_AGNO(mp, *ap->firstblock) < - XFS_FSB_TO_AGNO(mp, args.fsbno))); + XFS_FSB_TO_AGNO(mp, *ap->firstblock) <= + XFS_FSB_TO_AGNO(mp, args.fsbno)); ap->blkno = args.fsbno; if (*ap->firstblock == NULLFSBLOCK) *ap->firstblock = args.fsbno; - ASSERT(nullfb || fb_agno == args.agno || - (ap->dfops->dop_low && fb_agno < args.agno)); + ASSERT(nullfb || fb_agno <= args.agno); ap->length = args.len; if (!(ap->flags & XFS_BMAPI_COWFORK)) ap->ip->i_d.di_nblocks += args.len; @@ -4368,10 +4362,16 @@ xfs_bmapi_allocate( bma->got.br_state = XFS_EXT_NORM; /* - * A wasdelay extent has been initialized, so shouldn't be flagged - * as unwritten. + * In the data fork, a wasdelay extent has been initialized, so + * shouldn't be flagged as unwritten. + * + * For the cow fork, however, we convert delalloc reservations + * (extents allocated for speculative preallocation) to + * allocated unwritten extents, and only convert the unwritten + * extents to real extents when we're about to write the data. */ - if (!bma->wasdel && (bma->flags & XFS_BMAPI_PREALLOC) && + if ((!bma->wasdel || (bma->flags & XFS_BMAPI_COWFORK)) && + (bma->flags & XFS_BMAPI_PREALLOC) && xfs_sb_version_hasextflgbit(&mp->m_sb)) bma->got.br_state = XFS_EXT_UNWRITTEN; @@ -4422,8 +4422,6 @@ xfs_bmapi_convert_unwritten( (XFS_BMAPI_PREALLOC | XFS_BMAPI_CONVERT)) return 0; - ASSERT(whichfork != XFS_COW_FORK); - /* * Modify (by adding) the state flag, if writing. */ @@ -4448,8 +4446,8 @@ xfs_bmapi_convert_unwritten( return error; } - error = xfs_bmap_add_extent_unwritten_real(bma->tp, bma->ip, &bma->idx, - &bma->cur, mval, bma->firstblock, bma->dfops, + error = xfs_bmap_add_extent_unwritten_real(bma->tp, bma->ip, whichfork, + &bma->idx, &bma->cur, mval, bma->firstblock, bma->dfops, &tmp_logflags); /* * Log the inode core unconditionally in the unwritten extent conversion @@ -4458,8 +4456,12 @@ xfs_bmapi_convert_unwritten( * in the transaction for the sake of fsync(), even if nothing has * changed, because fsync() will not force the log for this transaction * unless it sees the inode pinned. + * + * Note: If we're only converting cow fork extents, there aren't + * any on-disk updates to make, so we don't need to log anything. */ - bma->logflags |= tmp_logflags | XFS_ILOG_CORE; + if (whichfork != XFS_COW_FORK) + bma->logflags |= tmp_logflags | XFS_ILOG_CORE; if (error) return error; @@ -4533,15 +4535,15 @@ xfs_bmapi_write( ASSERT(*nmap >= 1); ASSERT(*nmap <= XFS_BMAP_MAX_NMAP); ASSERT(!(flags & XFS_BMAPI_IGSTATE)); - ASSERT(tp != NULL); + ASSERT(tp != NULL || + (flags & (XFS_BMAPI_CONVERT | XFS_BMAPI_COWFORK)) == + (XFS_BMAPI_CONVERT | XFS_BMAPI_COWFORK)); ASSERT(len > 0); ASSERT(XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_LOCAL); ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); ASSERT(!(flags & XFS_BMAPI_REMAP) || whichfork == XFS_DATA_FORK); ASSERT(!(flags & XFS_BMAPI_PREALLOC) || !(flags & XFS_BMAPI_REMAP)); ASSERT(!(flags & XFS_BMAPI_CONVERT) || !(flags & XFS_BMAPI_REMAP)); - ASSERT(!(flags & XFS_BMAPI_PREALLOC) || whichfork != XFS_COW_FORK); - ASSERT(!(flags & XFS_BMAPI_CONVERT) || whichfork != XFS_COW_FORK); /* zeroing is for currently only for data extents, not metadata */ ASSERT((flags & (XFS_BMAPI_METADATA | XFS_BMAPI_ZERO)) != @@ -4746,13 +4748,9 @@ error0: if (bma.cur) { if (!error) { ASSERT(*firstblock == NULLFSBLOCK || - XFS_FSB_TO_AGNO(mp, *firstblock) == + XFS_FSB_TO_AGNO(mp, *firstblock) <= XFS_FSB_TO_AGNO(mp, - bma.cur->bc_private.b.firstblock) || - (dfops->dop_low && - XFS_FSB_TO_AGNO(mp, *firstblock) < - XFS_FSB_TO_AGNO(mp, - bma.cur->bc_private.b.firstblock))); + bma.cur->bc_private.b.firstblock)); *firstblock = bma.cur->bc_private.b.firstblock; } xfs_btree_del_cursor(bma.cur, @@ -4787,34 +4785,59 @@ xfs_bmap_split_indlen( xfs_filblks_t len2 = *indlen2; xfs_filblks_t nres = len1 + len2; /* new total res. */ xfs_filblks_t stolen = 0; + xfs_filblks_t resfactor; /* * Steal as many blocks as we can to try and satisfy the worst case * indlen for both new extents. */ - while (nres > ores && avail) { - nres--; - avail--; - stolen++; - } + if (ores < nres && avail) + stolen = XFS_FILBLKS_MIN(nres - ores, avail); + ores += stolen; + + /* nothing else to do if we've satisfied the new reservation */ + if (ores >= nres) + return stolen; + + /* + * We can't meet the total required reservation for the two extents. + * Calculate the percent of the overall shortage between both extents + * and apply this percentage to each of the requested indlen values. + * This distributes the shortage fairly and reduces the chances that one + * of the two extents is left with nothing when extents are repeatedly + * split. + */ + resfactor = (ores * 100); + do_div(resfactor, nres); + len1 *= resfactor; + do_div(len1, 100); + len2 *= resfactor; + do_div(len2, 100); + ASSERT(len1 + len2 <= ores); + ASSERT(len1 < *indlen1 && len2 < *indlen2); /* - * The only blocks available are those reserved for the original - * extent and what we can steal from the extent being removed. - * If this still isn't enough to satisfy the combined - * requirements for the two new extents, skim blocks off of each - * of the new reservations until they match what is available. + * Hand out the remainder to each extent. If one of the two reservations + * is zero, we want to make sure that one gets a block first. The loop + * below starts with len1, so hand len2 a block right off the bat if it + * is zero. */ - while (nres > ores) { - if (len1) { - len1--; - nres--; + ores -= (len1 + len2); + ASSERT((*indlen1 - len1) + (*indlen2 - len2) >= ores); + if (ores && !len2 && *indlen2) { + len2++; + ores--; + } + while (ores) { + if (len1 < *indlen1) { + len1++; + ores--; } - if (nres == ores) + if (!ores) break; - if (len2) { - len2--; - nres--; + if (len2 < *indlen2) { + len2++; + ores--; } } @@ -5556,8 +5579,8 @@ __xfs_bunmapi( } del.br_state = XFS_EXT_UNWRITTEN; error = xfs_bmap_add_extent_unwritten_real(tp, ip, - &lastx, &cur, &del, firstblock, dfops, - &logflags); + whichfork, &lastx, &cur, &del, + firstblock, dfops, &logflags); if (error) goto error0; goto nodelete; @@ -5610,8 +5633,9 @@ __xfs_bunmapi( prev.br_state = XFS_EXT_UNWRITTEN; lastx--; error = xfs_bmap_add_extent_unwritten_real(tp, - ip, &lastx, &cur, &prev, - firstblock, dfops, &logflags); + ip, whichfork, &lastx, &cur, + &prev, firstblock, dfops, + &logflags); if (error) goto error0; goto nodelete; @@ -5619,8 +5643,9 @@ __xfs_bunmapi( ASSERT(del.br_state == XFS_EXT_NORM); del.br_state = XFS_EXT_UNWRITTEN; error = xfs_bmap_add_extent_unwritten_real(tp, - ip, &lastx, &cur, &del, - firstblock, dfops, &logflags); + ip, whichfork, &lastx, &cur, + &del, firstblock, dfops, + &logflags); if (error) goto error0; goto nodelete; diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c index d9be241fc86f..f93072b58a58 100644 --- a/fs/xfs/libxfs/xfs_bmap_btree.c +++ b/fs/xfs/libxfs/xfs_bmap_btree.c @@ -71,15 +71,9 @@ xfs_bmdr_to_bmbt( xfs_bmbt_key_t *tkp; __be64 *tpp; - if (xfs_sb_version_hascrc(&mp->m_sb)) - xfs_btree_init_block_int(mp, rblock, XFS_BUF_DADDR_NULL, - XFS_BMAP_CRC_MAGIC, 0, 0, ip->i_ino, - XFS_BTREE_LONG_PTRS | XFS_BTREE_CRC_BLOCKS); - else - xfs_btree_init_block_int(mp, rblock, XFS_BUF_DADDR_NULL, - XFS_BMAP_MAGIC, 0, 0, ip->i_ino, + xfs_btree_init_block_int(mp, rblock, XFS_BUF_DADDR_NULL, + XFS_BTNUM_BMAP, 0, 0, ip->i_ino, XFS_BTREE_LONG_PTRS); - rblock->bb_level = dblock->bb_level; ASSERT(be16_to_cpu(rblock->bb_level) > 0); rblock->bb_numrecs = dblock->bb_numrecs; diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c index 21e6a6ab6b9a..c3decedc9455 100644 --- a/fs/xfs/libxfs/xfs_btree.c +++ b/fs/xfs/libxfs/xfs_btree.c @@ -50,8 +50,18 @@ static const __uint32_t xfs_magics[2][XFS_BTNUM_MAX] = { XFS_BMAP_CRC_MAGIC, XFS_IBT_CRC_MAGIC, XFS_FIBT_CRC_MAGIC, XFS_REFC_CRC_MAGIC } }; -#define xfs_btree_magic(cur) \ - xfs_magics[!!((cur)->bc_flags & XFS_BTREE_CRC_BLOCKS)][cur->bc_btnum] + +__uint32_t +xfs_btree_magic( + int crc, + xfs_btnum_t btnum) +{ + __uint32_t magic = xfs_magics[crc][btnum]; + + /* Ensure we asked for crc for crc-only magics. */ + ASSERT(magic != 0); + return magic; +} STATIC int /* error (0 or EFSCORRUPTED) */ xfs_btree_check_lblock( @@ -62,10 +72,13 @@ xfs_btree_check_lblock( { int lblock_ok = 1; /* block passes checks */ struct xfs_mount *mp; /* file system mount point */ + xfs_btnum_t btnum = cur->bc_btnum; + int crc; mp = cur->bc_mp; + crc = xfs_sb_version_hascrc(&mp->m_sb); - if (xfs_sb_version_hascrc(&mp->m_sb)) { + if (crc) { lblock_ok = lblock_ok && uuid_equal(&block->bb_u.l.bb_uuid, &mp->m_sb.sb_meta_uuid) && @@ -74,7 +87,7 @@ xfs_btree_check_lblock( } lblock_ok = lblock_ok && - be32_to_cpu(block->bb_magic) == xfs_btree_magic(cur) && + be32_to_cpu(block->bb_magic) == xfs_btree_magic(crc, btnum) && be16_to_cpu(block->bb_level) == level && be16_to_cpu(block->bb_numrecs) <= cur->bc_ops->get_maxrecs(cur, level) && @@ -110,13 +123,16 @@ xfs_btree_check_sblock( struct xfs_agf *agf; /* ag. freespace structure */ xfs_agblock_t agflen; /* native ag. freespace length */ int sblock_ok = 1; /* block passes checks */ + xfs_btnum_t btnum = cur->bc_btnum; + int crc; mp = cur->bc_mp; + crc = xfs_sb_version_hascrc(&mp->m_sb); agbp = cur->bc_private.a.agbp; agf = XFS_BUF_TO_AGF(agbp); agflen = be32_to_cpu(agf->agf_length); - if (xfs_sb_version_hascrc(&mp->m_sb)) { + if (crc) { sblock_ok = sblock_ok && uuid_equal(&block->bb_u.s.bb_uuid, &mp->m_sb.sb_meta_uuid) && @@ -125,7 +141,7 @@ xfs_btree_check_sblock( } sblock_ok = sblock_ok && - be32_to_cpu(block->bb_magic) == xfs_btree_magic(cur) && + be32_to_cpu(block->bb_magic) == xfs_btree_magic(crc, btnum) && be16_to_cpu(block->bb_level) == level && be16_to_cpu(block->bb_numrecs) <= cur->bc_ops->get_maxrecs(cur, level) && @@ -810,7 +826,8 @@ xfs_btree_read_bufl( xfs_daddr_t d; /* real disk block address */ int error; - ASSERT(fsbno != NULLFSBLOCK); + if (!XFS_FSB_SANITY_CHECK(mp, fsbno)) + return -EFSCORRUPTED; d = XFS_FSB_TO_DADDR(mp, fsbno); error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, d, mp->m_bsize, lock, &bp, ops); @@ -1084,12 +1101,15 @@ xfs_btree_init_block_int( struct xfs_mount *mp, struct xfs_btree_block *buf, xfs_daddr_t blkno, - __u32 magic, + xfs_btnum_t btnum, __u16 level, __u16 numrecs, __u64 owner, unsigned int flags) { + int crc = xfs_sb_version_hascrc(&mp->m_sb); + __u32 magic = xfs_btree_magic(crc, btnum); + buf->bb_magic = cpu_to_be32(magic); buf->bb_level = cpu_to_be16(level); buf->bb_numrecs = cpu_to_be16(numrecs); @@ -1097,7 +1117,7 @@ xfs_btree_init_block_int( if (flags & XFS_BTREE_LONG_PTRS) { buf->bb_u.l.bb_leftsib = cpu_to_be64(NULLFSBLOCK); buf->bb_u.l.bb_rightsib = cpu_to_be64(NULLFSBLOCK); - if (flags & XFS_BTREE_CRC_BLOCKS) { + if (crc) { buf->bb_u.l.bb_blkno = cpu_to_be64(blkno); buf->bb_u.l.bb_owner = cpu_to_be64(owner); uuid_copy(&buf->bb_u.l.bb_uuid, &mp->m_sb.sb_meta_uuid); @@ -1110,7 +1130,7 @@ xfs_btree_init_block_int( buf->bb_u.s.bb_leftsib = cpu_to_be32(NULLAGBLOCK); buf->bb_u.s.bb_rightsib = cpu_to_be32(NULLAGBLOCK); - if (flags & XFS_BTREE_CRC_BLOCKS) { + if (crc) { buf->bb_u.s.bb_blkno = cpu_to_be64(blkno); buf->bb_u.s.bb_owner = cpu_to_be32(__owner); uuid_copy(&buf->bb_u.s.bb_uuid, &mp->m_sb.sb_meta_uuid); @@ -1123,14 +1143,14 @@ void xfs_btree_init_block( struct xfs_mount *mp, struct xfs_buf *bp, - __u32 magic, + xfs_btnum_t btnum, __u16 level, __u16 numrecs, __u64 owner, unsigned int flags) { xfs_btree_init_block_int(mp, XFS_BUF_TO_BLOCK(bp), bp->b_bn, - magic, level, numrecs, owner, flags); + btnum, level, numrecs, owner, flags); } STATIC void @@ -1140,7 +1160,7 @@ xfs_btree_init_block_cur( int level, int numrecs) { - __u64 owner; + __u64 owner; /* * we can pull the owner from the cursor right now as the different @@ -1154,7 +1174,7 @@ xfs_btree_init_block_cur( owner = cur->bc_private.a.agno; xfs_btree_init_block_int(cur->bc_mp, XFS_BUF_TO_BLOCK(bp), bp->b_bn, - xfs_btree_magic(cur), level, numrecs, + cur->bc_btnum, level, numrecs, owner, cur->bc_flags); } diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h index b69b947c4c1b..4bb62580a7fd 100644 --- a/fs/xfs/libxfs/xfs_btree.h +++ b/fs/xfs/libxfs/xfs_btree.h @@ -76,6 +76,8 @@ union xfs_btree_rec { #define XFS_BTNUM_RMAP ((xfs_btnum_t)XFS_BTNUM_RMAPi) #define XFS_BTNUM_REFC ((xfs_btnum_t)XFS_BTNUM_REFCi) +__uint32_t xfs_btree_magic(int crc, xfs_btnum_t btnum); + /* * For logging record fields. */ @@ -378,7 +380,7 @@ void xfs_btree_init_block( struct xfs_mount *mp, struct xfs_buf *bp, - __u32 magic, + xfs_btnum_t btnum, __u16 level, __u16 numrecs, __u64 owner, @@ -389,7 +391,7 @@ xfs_btree_init_block_int( struct xfs_mount *mp, struct xfs_btree_block *buf, xfs_daddr_t blkno, - __u32 magic, + xfs_btnum_t btnum, __u16 level, __u16 numrecs, __u64 owner, @@ -456,7 +458,7 @@ static inline int xfs_btree_get_level(struct xfs_btree_block *block) #define XFS_FILBLKS_MAX(a,b) max_t(xfs_filblks_t, (a), (b)) #define XFS_FSB_SANITY_CHECK(mp,fsb) \ - (XFS_FSB_TO_AGNO(mp, fsb) < mp->m_sb.sb_agcount && \ + (fsb && XFS_FSB_TO_AGNO(mp, fsb) < mp->m_sb.sb_agcount && \ XFS_FSB_TO_AGBNO(mp, fsb) < mp->m_sb.sb_agblocks) /* diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c index f2dc1a950c85..1bdf2888295b 100644 --- a/fs/xfs/libxfs/xfs_da_btree.c +++ b/fs/xfs/libxfs/xfs_da_btree.c @@ -2633,7 +2633,7 @@ out_free: /* * Readahead the dir/attr block. */ -xfs_daddr_t +int xfs_da_reada_buf( struct xfs_inode *dp, xfs_dablk_t bno, @@ -2664,7 +2664,5 @@ out_free: if (mapp != &map) kmem_free(mapp); - if (error) - return -1; - return mappedbno; + return error; } diff --git a/fs/xfs/libxfs/xfs_da_btree.h b/fs/xfs/libxfs/xfs_da_btree.h index 98c75cbe6ac2..4e29cb6a3627 100644 --- a/fs/xfs/libxfs/xfs_da_btree.h +++ b/fs/xfs/libxfs/xfs_da_btree.h @@ -201,7 +201,7 @@ int xfs_da_read_buf(struct xfs_trans *trans, struct xfs_inode *dp, xfs_dablk_t bno, xfs_daddr_t mappedbno, struct xfs_buf **bpp, int whichfork, const struct xfs_buf_ops *ops); -xfs_daddr_t xfs_da_reada_buf(struct xfs_inode *dp, xfs_dablk_t bno, +int xfs_da_reada_buf(struct xfs_inode *dp, xfs_dablk_t bno, xfs_daddr_t mapped_bno, int whichfork, const struct xfs_buf_ops *ops); int xfs_da_shrink_inode(xfs_da_args_t *args, xfs_dablk_t dead_blkno, diff --git a/fs/xfs/libxfs/xfs_dir2_node.c b/fs/xfs/libxfs/xfs_dir2_node.c index 75a557432d0f..bbd1238852b3 100644 --- a/fs/xfs/libxfs/xfs_dir2_node.c +++ b/fs/xfs/libxfs/xfs_dir2_node.c @@ -155,6 +155,42 @@ const struct xfs_buf_ops xfs_dir3_free_buf_ops = { .verify_write = xfs_dir3_free_write_verify, }; +/* Everything ok in the free block header? */ +static bool +xfs_dir3_free_header_check( + struct xfs_inode *dp, + xfs_dablk_t fbno, + struct xfs_buf *bp) +{ + struct xfs_mount *mp = dp->i_mount; + unsigned int firstdb; + int maxbests; + + maxbests = dp->d_ops->free_max_bests(mp->m_dir_geo); + firstdb = (xfs_dir2_da_to_db(mp->m_dir_geo, fbno) - + xfs_dir2_byte_to_db(mp->m_dir_geo, XFS_DIR2_FREE_OFFSET)) * + maxbests; + if (xfs_sb_version_hascrc(&mp->m_sb)) { + struct xfs_dir3_free_hdr *hdr3 = bp->b_addr; + + if (be32_to_cpu(hdr3->firstdb) != firstdb) + return false; + if (be32_to_cpu(hdr3->nvalid) > maxbests) + return false; + if (be32_to_cpu(hdr3->nvalid) < be32_to_cpu(hdr3->nused)) + return false; + } else { + struct xfs_dir2_free_hdr *hdr = bp->b_addr; + + if (be32_to_cpu(hdr->firstdb) != firstdb) + return false; + if (be32_to_cpu(hdr->nvalid) > maxbests) + return false; + if (be32_to_cpu(hdr->nvalid) < be32_to_cpu(hdr->nused)) + return false; + } + return true; +} static int __xfs_dir3_free_read( @@ -168,11 +204,22 @@ __xfs_dir3_free_read( err = xfs_da_read_buf(tp, dp, fbno, mappedbno, bpp, XFS_DATA_FORK, &xfs_dir3_free_buf_ops); + if (err || !*bpp) + return err; + + /* Check things that we can't do in the verifier. */ + if (!xfs_dir3_free_header_check(dp, fbno, *bpp)) { + xfs_buf_ioerror(*bpp, -EFSCORRUPTED); + xfs_verifier_error(*bpp); + xfs_trans_brelse(tp, *bpp); + return -EFSCORRUPTED; + } /* try read returns without an error or *bpp if it lands in a hole */ - if (!err && tp && *bpp) + if (tp) xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_DIR_FREE_BUF); - return err; + + return 0; } int diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index f272abff11e1..d41ade5d293e 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -51,8 +51,7 @@ xfs_ialloc_cluster_alignment( struct xfs_mount *mp) { if (xfs_sb_version_hasalign(&mp->m_sb) && - mp->m_sb.sb_inoalignmt >= - XFS_B_TO_FSBT(mp, mp->m_inode_cluster_size)) + mp->m_sb.sb_inoalignmt >= xfs_icluster_size_fsb(mp)) return mp->m_sb.sb_inoalignmt; return 1; } diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c index 222e103356c6..25c1e078aef6 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.c +++ b/fs/xfs/libxfs/xfs_inode_fork.c @@ -26,6 +26,7 @@ #include "xfs_inode.h" #include "xfs_trans.h" #include "xfs_inode_item.h" +#include "xfs_btree.h" #include "xfs_bmap_btree.h" #include "xfs_bmap.h" #include "xfs_error.h" @@ -429,11 +430,13 @@ xfs_iformat_btree( /* REFERENCED */ int nrecs; int size; + int level; ifp = XFS_IFORK_PTR(ip, whichfork); dfp = (xfs_bmdr_block_t *)XFS_DFORK_PTR(dip, whichfork); size = XFS_BMAP_BROOT_SPACE(mp, dfp); nrecs = be16_to_cpu(dfp->bb_numrecs); + level = be16_to_cpu(dfp->bb_level); /* * blow out if -- fork has less extents than can fit in @@ -446,7 +449,8 @@ xfs_iformat_btree( XFS_IFORK_MAXEXT(ip, whichfork) || XFS_BMDR_SPACE_CALC(nrecs) > XFS_DFORK_SIZE(dip, mp, whichfork) || - XFS_IFORK_NEXTENTS(ip, whichfork) > ip->i_d.di_nblocks)) { + XFS_IFORK_NEXTENTS(ip, whichfork) > ip->i_d.di_nblocks) || + level == 0 || level > XFS_BTREE_MAXLEVELS) { xfs_warn(mp, "corrupt inode %Lu (btree).", (unsigned long long) ip->i_ino); XFS_CORRUPTION_ERROR("xfs_iformat_btree", XFS_ERRLEVEL_LOW, @@ -497,15 +501,14 @@ xfs_iread_extents( * We know that the size is valid (it's checked in iformat_btree) */ ifp->if_bytes = ifp->if_real_bytes = 0; - ifp->if_flags |= XFS_IFEXTENTS; xfs_iext_add(ifp, 0, nextents); error = xfs_bmap_read_extents(tp, ip, whichfork); if (error) { xfs_iext_destroy(ifp); - ifp->if_flags &= ~XFS_IFEXTENTS; return error; } xfs_validate_extents(ifp, nextents, XFS_EXTFMT_INODE(ip)); + ifp->if_flags |= XFS_IFEXTENTS; return 0; } /* diff --git a/fs/xfs/libxfs/xfs_log_recover.h b/fs/xfs/libxfs/xfs_log_recover.h index d9f65e2d5cc8..29a01ec89dd0 100644 --- a/fs/xfs/libxfs/xfs_log_recover.h +++ b/fs/xfs/libxfs/xfs_log_recover.h @@ -42,7 +42,6 @@ typedef struct xlog_recover_item { xfs_log_iovec_t *ri_buf; /* ptr to regions buffer */ } xlog_recover_item_t; -struct xlog_tid; typedef struct xlog_recover { struct hlist_node r_list; xlog_tid_t r_log_tid; /* log's transaction id */ diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 631e7c0e0a29..bf65a9ea8642 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -103,9 +103,9 @@ xfs_finish_page_writeback( unsigned int bsize; ASSERT(bvec->bv_offset < PAGE_SIZE); - ASSERT((bvec->bv_offset & ((1 << inode->i_blkbits) - 1)) == 0); + ASSERT((bvec->bv_offset & (i_blocksize(inode) - 1)) == 0); ASSERT(end < PAGE_SIZE); - ASSERT((bvec->bv_len & ((1 << inode->i_blkbits) - 1)) == 0); + ASSERT((bvec->bv_len & (i_blocksize(inode) - 1)) == 0); bh = head = page_buffers(bvec->bv_page); @@ -349,7 +349,7 @@ xfs_map_blocks( { struct xfs_inode *ip = XFS_I(inode); struct xfs_mount *mp = ip->i_mount; - ssize_t count = 1 << inode->i_blkbits; + ssize_t count = i_blocksize(inode); xfs_fileoff_t offset_fsb, end_fsb; int error = 0; int bmapi_flags = XFS_BMAPI_ENTIRE; @@ -481,6 +481,12 @@ xfs_submit_ioend( struct xfs_ioend *ioend, int status) { + /* Convert CoW extents to regular */ + if (!status && ioend->io_type == XFS_IO_COW) { + status = xfs_reflink_convert_cow(XFS_I(ioend->io_inode), + ioend->io_offset, ioend->io_size); + } + /* Reserve log space if we might write beyond the on-disk inode size. */ if (!status && ioend->io_type != XFS_IO_UNWRITTEN && @@ -752,7 +758,7 @@ xfs_aops_discard_page( break; } next_buffer: - offset += 1 << inode->i_blkbits; + offset += i_blocksize(inode); } while ((bh = bh->b_this_page) != head); @@ -840,7 +846,7 @@ xfs_writepage_map( LIST_HEAD(submit_list); struct xfs_ioend *ioend, *next; struct buffer_head *bh, *head; - ssize_t len = 1 << inode->i_blkbits; + ssize_t len = i_blocksize(inode); int error = 0; int count = 0; int uptodate = 1; @@ -1204,7 +1210,7 @@ xfs_map_trim_size( offset + mapping_size >= i_size_read(inode)) { /* limit mapping to block that spans EOF */ mapping_size = roundup_64(i_size_read(inode) - offset, - 1 << inode->i_blkbits); + i_blocksize(inode)); } if (mapping_size > LONG_MAX) mapping_size = LONG_MAX; @@ -1235,7 +1241,7 @@ xfs_get_blocks( return -EIO; offset = (xfs_off_t)iblock << inode->i_blkbits; - ASSERT(bh_result->b_size >= (1 << inode->i_blkbits)); + ASSERT(bh_result->b_size >= i_blocksize(inode)); size = bh_result->b_size; if (offset >= i_size_read(inode)) @@ -1383,7 +1389,7 @@ xfs_vm_set_page_dirty( if (offset < end_offset) set_buffer_dirty(bh); bh = bh->b_this_page; - offset += 1 << inode->i_blkbits; + offset += i_blocksize(inode); } while (bh != head); } /* diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index c1417919ab0a..8b75dcea5966 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -88,7 +88,6 @@ int xfs_bmap_rtalloc( struct xfs_bmalloca *ap) /* bmap alloc argument struct */ { - xfs_alloctype_t atype = 0; /* type for allocation routines */ int error; /* error return value */ xfs_mount_t *mp; /* mount point structure */ xfs_extlen_t prod = 0; /* product factor for allocators */ @@ -155,18 +154,14 @@ xfs_bmap_rtalloc( /* * Realtime allocation, done through xfs_rtallocate_extent. */ - atype = ap->blkno == 0 ? XFS_ALLOCTYPE_ANY_AG : XFS_ALLOCTYPE_NEAR_BNO; do_div(ap->blkno, mp->m_sb.sb_rextsize); rtb = ap->blkno; ap->length = ralen; - if ((error = xfs_rtallocate_extent(ap->tp, ap->blkno, 1, ap->length, - &ralen, atype, ap->wasdel, prod, &rtb))) - return error; - if (rtb == NULLFSBLOCK && prod > 1 && - (error = xfs_rtallocate_extent(ap->tp, ap->blkno, 1, - ap->length, &ralen, atype, - ap->wasdel, 1, &rtb))) + error = xfs_rtallocate_extent(ap->tp, ap->blkno, 1, ap->length, + &ralen, ap->wasdel, prod, &rtb); + if (error) return error; + ap->blkno = rtb; if (ap->blkno != NULLFSBLOCK) { ap->blkno *= mp->m_sb.sb_rextsize; @@ -787,11 +782,9 @@ xfs_getbmap( xfs_iunlock(ip, XFS_IOLOCK_SHARED); for (i = 0; i < cur_ext; i++) { - int full = 0; /* user array is full */ - /* format results & advance arg */ - error = formatter(&arg, &out[i], &full); - if (error || full) + error = formatter(&arg, &out[i]); + if (error) break; } @@ -917,17 +910,18 @@ xfs_can_free_eofblocks(struct xfs_inode *ip, bool force) */ int xfs_free_eofblocks( - xfs_mount_t *mp, - xfs_inode_t *ip, - bool need_iolock) + struct xfs_inode *ip) { - xfs_trans_t *tp; - int error; - xfs_fileoff_t end_fsb; - xfs_fileoff_t last_fsb; - xfs_filblks_t map_len; - int nimaps; - xfs_bmbt_irec_t imap; + struct xfs_trans *tp; + int error; + xfs_fileoff_t end_fsb; + xfs_fileoff_t last_fsb; + xfs_filblks_t map_len; + int nimaps; + struct xfs_bmbt_irec imap; + struct xfs_mount *mp = ip->i_mount; + + ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL)); /* * Figure out if there are any blocks beyond the end @@ -944,6 +938,10 @@ xfs_free_eofblocks( error = xfs_bmapi_read(ip, end_fsb, map_len, &imap, &nimaps, 0); xfs_iunlock(ip, XFS_ILOCK_SHARED); + /* + * If there are blocks after the end of file, truncate the file to its + * current size to free them up. + */ if (!error && (nimaps != 0) && (imap.br_startblock != HOLESTARTBLOCK || ip->i_delayed_blks)) { @@ -954,22 +952,13 @@ xfs_free_eofblocks( if (error) return error; - /* - * There are blocks after the end of file. - * Free them up now by truncating the file to - * its current size. - */ - if (need_iolock) { - if (!xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL)) - return -EAGAIN; - } + /* wait on dio to ensure i_size has settled */ + inode_dio_wait(VFS_I(ip)); error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp); if (error) { ASSERT(XFS_FORCED_SHUTDOWN(mp)); - if (need_iolock) - xfs_iunlock(ip, XFS_IOLOCK_EXCL); return error; } @@ -997,8 +986,6 @@ xfs_free_eofblocks( } xfs_iunlock(ip, XFS_ILOCK_EXCL); - if (need_iolock) - xfs_iunlock(ip, XFS_IOLOCK_EXCL); } return error; } @@ -1393,10 +1380,16 @@ xfs_shift_file_space( xfs_fileoff_t stop_fsb; xfs_fileoff_t next_fsb; xfs_fileoff_t shift_fsb; + uint resblks; ASSERT(direction == SHIFT_LEFT || direction == SHIFT_RIGHT); if (direction == SHIFT_LEFT) { + /* + * Reserve blocks to cover potential extent merges after left + * shift operations. + */ + resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0); next_fsb = XFS_B_TO_FSB(mp, offset + len); stop_fsb = XFS_B_TO_FSB(mp, VFS_I(ip)->i_size); } else { @@ -1404,6 +1397,7 @@ xfs_shift_file_space( * If right shift, delegate the work of initialization of * next_fsb to xfs_bmap_shift_extent as it has ilock held. */ + resblks = 0; next_fsb = NULLFSBLOCK; stop_fsb = XFS_B_TO_FSB(mp, offset); } @@ -1415,7 +1409,7 @@ xfs_shift_file_space( * into the accessible region of the file. */ if (xfs_can_free_eofblocks(ip, true)) { - error = xfs_free_eofblocks(mp, ip, false); + error = xfs_free_eofblocks(ip); if (error) return error; } @@ -1445,21 +1439,14 @@ xfs_shift_file_space( } while (!error && !done) { - /* - * We would need to reserve permanent block for transaction. - * This will come into picture when after shifting extent into - * hole we found that adjacent extents can be merged which - * may lead to freeing of a block during record update. - */ - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, - XFS_DIOSTRAT_SPACE_RES(mp, 0), 0, 0, &tp); + error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0, + &tp); if (error) break; xfs_ilock(ip, XFS_ILOCK_EXCL); error = xfs_trans_reserve_quota(tp, mp, ip->i_udquot, - ip->i_gdquot, ip->i_pdquot, - XFS_DIOSTRAT_SPACE_RES(mp, 0), 0, + ip->i_gdquot, ip->i_pdquot, resblks, 0, XFS_QMOPT_RES_REGBLKS); if (error) goto out_trans_cancel; diff --git a/fs/xfs/xfs_bmap_util.h b/fs/xfs/xfs_bmap_util.h index 68a621a8e0c0..135d8267e284 100644 --- a/fs/xfs/xfs_bmap_util.h +++ b/fs/xfs/xfs_bmap_util.h @@ -35,7 +35,7 @@ int xfs_bmap_punch_delalloc_range(struct xfs_inode *ip, xfs_fileoff_t start_fsb, xfs_fileoff_t length); /* bmap to userspace formatter - copy to user & advance pointer */ -typedef int (*xfs_bmap_format_t)(void **, struct getbmapx *, int *); +typedef int (*xfs_bmap_format_t)(void **, struct getbmapx *); int xfs_getbmap(struct xfs_inode *ip, struct getbmapx *bmv, xfs_bmap_format_t formatter, void *arg); @@ -63,8 +63,7 @@ int xfs_insert_file_space(struct xfs_inode *, xfs_off_t offset, /* EOF block manipulation functions */ bool xfs_can_free_eofblocks(struct xfs_inode *ip, bool force); -int xfs_free_eofblocks(struct xfs_mount *mp, struct xfs_inode *ip, - bool need_iolock); +int xfs_free_eofblocks(struct xfs_inode *ip); int xfs_swap_extents(struct xfs_inode *ip, struct xfs_inode *tip, struct xfs_swapext *sx); diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index ac3b4db519df..8c7d01b75922 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -758,7 +758,7 @@ xfs_buf_readahead_map( int nmaps, const struct xfs_buf_ops *ops) { - if (bdi_read_congested(target->bt_bdi)) + if (bdi_read_congested(target->bt_bdev->bd_bdi)) return; xfs_buf_read_map(target, map, nmaps, @@ -1791,7 +1791,6 @@ xfs_alloc_buftarg( btp->bt_mount = mp; btp->bt_dev = bdev->bd_dev; btp->bt_bdev = bdev; - btp->bt_bdi = blk_get_backing_dev_info(bdev); if (xfs_setsize_buftarg_early(btp, bdev)) goto error; diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index 8a9d3a9599f0..3c867e5a63e1 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -109,7 +109,6 @@ typedef unsigned int xfs_buf_flags_t; typedef struct xfs_buftarg { dev_t bt_dev; struct block_device *bt_bdev; - struct backing_dev_info *bt_bdi; struct xfs_mount *bt_mount; unsigned int bt_meta_sectorsize; size_t bt_meta_sectormask; diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index 2975cb2319f4..0306168af332 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -1162,6 +1162,7 @@ xfs_buf_iodone_callbacks( */ bp->b_last_error = 0; bp->b_retries = 0; + bp->b_first_retry_time = 0; xfs_buf_do_callbacks(bp); bp->b_fspriv = NULL; diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c index 4ff499aa7338..d796ffac7296 100644 --- a/fs/xfs/xfs_discard.c +++ b/fs/xfs/xfs_discard.c @@ -208,32 +208,3 @@ xfs_ioc_trim( return -EFAULT; return 0; } - -int -xfs_discard_extents( - struct xfs_mount *mp, - struct list_head *list) -{ - struct xfs_extent_busy *busyp; - int error = 0; - - list_for_each_entry(busyp, list, list) { - trace_xfs_discard_extent(mp, busyp->agno, busyp->bno, - busyp->length); - - error = blkdev_issue_discard(mp->m_ddev_targp->bt_bdev, - XFS_AGB_TO_DADDR(mp, busyp->agno, busyp->bno), - XFS_FSB_TO_BB(mp, busyp->length), - GFP_NOFS, 0); - if (error && error != -EOPNOTSUPP) { - xfs_info(mp, - "discard failed for extent [0x%llx,%u], error %d", - (unsigned long long)busyp->bno, - busyp->length, - error); - return error; - } - } - - return 0; -} diff --git a/fs/xfs/xfs_discard.h b/fs/xfs/xfs_discard.h index 344879aea646..0f070f9e44e1 100644 --- a/fs/xfs/xfs_discard.h +++ b/fs/xfs/xfs_discard.h @@ -5,6 +5,5 @@ struct fstrim_range; struct list_head; extern int xfs_ioc_trim(struct xfs_mount *, struct fstrim_range __user *); -extern int xfs_discard_extents(struct xfs_mount *, struct list_head *); #endif /* XFS_DISCARD_H */ diff --git a/fs/xfs/xfs_extent_busy.c b/fs/xfs/xfs_extent_busy.c index 162dc186cf04..77760dbf0242 100644 --- a/fs/xfs/xfs_extent_busy.c +++ b/fs/xfs/xfs_extent_busy.c @@ -45,18 +45,7 @@ xfs_extent_busy_insert( struct rb_node **rbp; struct rb_node *parent = NULL; - new = kmem_zalloc(sizeof(struct xfs_extent_busy), KM_MAYFAIL); - if (!new) { - /* - * No Memory! Since it is now not possible to track the free - * block, make this a synchronous transaction to insure that - * the block is not reused before this transaction commits. - */ - trace_xfs_extent_busy_enomem(tp->t_mountp, agno, bno, len); - xfs_trans_set_sync(tp); - return; - } - + new = kmem_zalloc(sizeof(struct xfs_extent_busy), KM_SLEEP); new->agno = agno; new->bno = bno; new->length = len; @@ -345,25 +334,31 @@ restart: * subset of the extent that is not busy. If *rlen is smaller than * args->minlen no suitable extent could be found, and the higher level * code needs to force out the log and retry the allocation. + * + * Return the current busy generation for the AG if the extent is busy. This + * value can be used to wait for at least one of the currently busy extents + * to be cleared. Note that the busy list is not guaranteed to be empty after + * the gen is woken. The state of a specific extent must always be confirmed + * with another call to xfs_extent_busy_trim() before it can be used. */ -void +bool xfs_extent_busy_trim( struct xfs_alloc_arg *args, - xfs_agblock_t bno, - xfs_extlen_t len, - xfs_agblock_t *rbno, - xfs_extlen_t *rlen) + xfs_agblock_t *bno, + xfs_extlen_t *len, + unsigned *busy_gen) { xfs_agblock_t fbno; xfs_extlen_t flen; struct rb_node *rbp; + bool ret = false; - ASSERT(len > 0); + ASSERT(*len > 0); spin_lock(&args->pag->pagb_lock); restart: - fbno = bno; - flen = len; + fbno = *bno; + flen = *len; rbp = args->pag->pagb_tree.rb_node; while (rbp && flen >= args->minlen) { struct xfs_extent_busy *busyp = @@ -515,24 +510,25 @@ restart: flen = fend - fbno; } - spin_unlock(&args->pag->pagb_lock); +out: - if (fbno != bno || flen != len) { - trace_xfs_extent_busy_trim(args->mp, args->agno, bno, len, + if (fbno != *bno || flen != *len) { + trace_xfs_extent_busy_trim(args->mp, args->agno, *bno, *len, fbno, flen); + *bno = fbno; + *len = flen; + *busy_gen = args->pag->pagb_gen; + ret = true; } - *rbno = fbno; - *rlen = flen; - return; + spin_unlock(&args->pag->pagb_lock); + return ret; fail: /* * Return a zero extent length as failure indications. All callers * re-check if the trimmed extent satisfies the minlen requirement. */ - spin_unlock(&args->pag->pagb_lock); - trace_xfs_extent_busy_trim(args->mp, args->agno, bno, len, fbno, 0); - *rbno = fbno; - *rlen = 0; + flen = 0; + goto out; } STATIC void @@ -551,6 +547,21 @@ xfs_extent_busy_clear_one( kmem_free(busyp); } +static void +xfs_extent_busy_put_pag( + struct xfs_perag *pag, + bool wakeup) + __releases(pag->pagb_lock) +{ + if (wakeup) { + pag->pagb_gen++; + wake_up_all(&pag->pagb_wait); + } + + spin_unlock(&pag->pagb_lock); + xfs_perag_put(pag); +} + /* * Remove all extents on the passed in list from the busy extents tree. * If do_discard is set skip extents that need to be discarded, and mark @@ -565,27 +576,76 @@ xfs_extent_busy_clear( struct xfs_extent_busy *busyp, *n; struct xfs_perag *pag = NULL; xfs_agnumber_t agno = NULLAGNUMBER; + bool wakeup = false; list_for_each_entry_safe(busyp, n, list, list) { if (busyp->agno != agno) { - if (pag) { - spin_unlock(&pag->pagb_lock); - xfs_perag_put(pag); - } - pag = xfs_perag_get(mp, busyp->agno); - spin_lock(&pag->pagb_lock); + if (pag) + xfs_extent_busy_put_pag(pag, wakeup); agno = busyp->agno; + pag = xfs_perag_get(mp, agno); + spin_lock(&pag->pagb_lock); + wakeup = false; } if (do_discard && busyp->length && - !(busyp->flags & XFS_EXTENT_BUSY_SKIP_DISCARD)) + !(busyp->flags & XFS_EXTENT_BUSY_SKIP_DISCARD)) { busyp->flags = XFS_EXTENT_BUSY_DISCARDED; - else + } else { xfs_extent_busy_clear_one(mp, pag, busyp); + wakeup = true; + } } - if (pag) { - spin_unlock(&pag->pagb_lock); + if (pag) + xfs_extent_busy_put_pag(pag, wakeup); +} + +/* + * Flush out all busy extents for this AG. + */ +void +xfs_extent_busy_flush( + struct xfs_mount *mp, + struct xfs_perag *pag, + unsigned busy_gen) +{ + DEFINE_WAIT (wait); + int log_flushed = 0, error; + + trace_xfs_log_force(mp, 0, _THIS_IP_); + error = _xfs_log_force(mp, XFS_LOG_SYNC, &log_flushed); + if (error) + return; + + do { + prepare_to_wait(&pag->pagb_wait, &wait, TASK_KILLABLE); + if (busy_gen != READ_ONCE(pag->pagb_gen)) + break; + schedule(); + } while (1); + + finish_wait(&pag->pagb_wait, &wait); +} + +void +xfs_extent_busy_wait_all( + struct xfs_mount *mp) +{ + DEFINE_WAIT (wait); + xfs_agnumber_t agno; + + for (agno = 0; agno < mp->m_sb.sb_agcount; agno++) { + struct xfs_perag *pag = xfs_perag_get(mp, agno); + + do { + prepare_to_wait(&pag->pagb_wait, &wait, TASK_KILLABLE); + if (RB_EMPTY_ROOT(&pag->pagb_tree)) + break; + schedule(); + } while (1); + finish_wait(&pag->pagb_wait, &wait); + xfs_perag_put(pag); } } @@ -596,9 +656,17 @@ xfs_extent_busy_clear( int xfs_extent_busy_ag_cmp( void *priv, - struct list_head *a, - struct list_head *b) + struct list_head *l1, + struct list_head *l2) { - return container_of(a, struct xfs_extent_busy, list)->agno - - container_of(b, struct xfs_extent_busy, list)->agno; + struct xfs_extent_busy *b1 = + container_of(l1, struct xfs_extent_busy, list); + struct xfs_extent_busy *b2 = + container_of(l2, struct xfs_extent_busy, list); + s32 diff; + + diff = b1->agno - b2->agno; + if (!diff) + diff = b1->bno - b2->bno; + return diff; } diff --git a/fs/xfs/xfs_extent_busy.h b/fs/xfs/xfs_extent_busy.h index bfff284d2dcc..60195ea1b84a 100644 --- a/fs/xfs/xfs_extent_busy.h +++ b/fs/xfs/xfs_extent_busy.h @@ -58,9 +58,16 @@ void xfs_extent_busy_reuse(struct xfs_mount *mp, xfs_agnumber_t agno, xfs_agblock_t fbno, xfs_extlen_t flen, bool userdata); +bool +xfs_extent_busy_trim(struct xfs_alloc_arg *args, xfs_agblock_t *bno, + xfs_extlen_t *len, unsigned *busy_gen); + +void +xfs_extent_busy_flush(struct xfs_mount *mp, struct xfs_perag *pag, + unsigned busy_gen); + void -xfs_extent_busy_trim(struct xfs_alloc_arg *args, xfs_agblock_t bno, - xfs_extlen_t len, xfs_agblock_t *rbno, xfs_extlen_t *rlen); +xfs_extent_busy_wait_all(struct xfs_mount *mp); int xfs_extent_busy_ag_cmp(void *priv, struct list_head *a, struct list_head *b); diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index bbb9eb6811b2..35703a801372 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -527,6 +527,15 @@ xfs_file_dio_aio_write( if ((iocb->ki_pos & mp->m_blockmask) || ((iocb->ki_pos + count) & mp->m_blockmask)) { unaligned_io = 1; + + /* + * We can't properly handle unaligned direct I/O to reflink + * files yet, as we can't unshare a partial block. + */ + if (xfs_is_reflink_inode(ip)) { + trace_xfs_reflink_bounce_dio_write(ip, iocb->ki_pos, count); + return -EREMCHG; + } iolock = XFS_IOLOCK_EXCL; } else { iolock = XFS_IOLOCK_SHARED; @@ -552,14 +561,6 @@ xfs_file_dio_aio_write( } trace_xfs_file_direct_write(ip, count, iocb->ki_pos); - - /* If this is a block-aligned directio CoW, remap immediately. */ - if (xfs_is_reflink_inode(ip) && !unaligned_io) { - ret = xfs_reflink_allocate_cow_range(ip, iocb->ki_pos, count); - if (ret) - goto out; - } - ret = iomap_dio_rw(iocb, from, &xfs_iomap_ops, xfs_dio_write_end_io); out: xfs_iunlock(ip, iolock); @@ -614,8 +615,10 @@ xfs_file_buffered_aio_write( struct xfs_inode *ip = XFS_I(inode); ssize_t ret; int enospc = 0; - int iolock = XFS_IOLOCK_EXCL; + int iolock; +write_retry: + iolock = XFS_IOLOCK_EXCL; xfs_ilock(ip, iolock); ret = xfs_file_aio_write_checks(iocb, from, &iolock); @@ -625,7 +628,6 @@ xfs_file_buffered_aio_write( /* We can write back this queue in page reclaim */ current->backing_dev_info = inode_to_bdi(inode); -write_retry: trace_xfs_file_buffered_write(ip, iov_iter_count(from), iocb->ki_pos); ret = iomap_file_buffered_write(iocb, from, &xfs_iomap_ops); if (likely(ret >= 0)) @@ -641,18 +643,21 @@ write_retry: * running at the same time. */ if (ret == -EDQUOT && !enospc) { + xfs_iunlock(ip, iolock); enospc = xfs_inode_free_quota_eofblocks(ip); if (enospc) goto write_retry; enospc = xfs_inode_free_quota_cowblocks(ip); if (enospc) goto write_retry; + iolock = 0; } else if (ret == -ENOSPC && !enospc) { struct xfs_eofblocks eofb = {0}; enospc = 1; xfs_flush_inodes(ip->i_mount); - eofb.eof_scan_owner = ip->i_ino; /* for locking */ + + xfs_iunlock(ip, iolock); eofb.eof_flags = XFS_EOF_FLAGS_SYNC; xfs_icache_free_eofblocks(ip->i_mount, &eofb); goto write_retry; @@ -660,7 +665,8 @@ write_retry: current->backing_dev_info = NULL; out: - xfs_iunlock(ip, iolock); + if (iolock) + xfs_iunlock(ip, iolock); return ret; } @@ -748,7 +754,7 @@ xfs_file_fallocate( if (error) goto out_unlock; } else if (mode & FALLOC_FL_COLLAPSE_RANGE) { - unsigned blksize_mask = (1 << inode->i_blkbits) - 1; + unsigned int blksize_mask = i_blocksize(inode) - 1; if (offset & blksize_mask || len & blksize_mask) { error = -EINVAL; @@ -770,7 +776,7 @@ xfs_file_fallocate( if (error) goto out_unlock; } else if (mode & FALLOC_FL_INSERT_RANGE) { - unsigned blksize_mask = (1 << inode->i_blkbits) - 1; + unsigned int blksize_mask = i_blocksize(inode) - 1; new_size = i_size_read(inode) + len; if (offset & blksize_mask || len & blksize_mask) { @@ -908,9 +914,9 @@ xfs_dir_open( */ mode = xfs_ilock_data_map_shared(ip); if (ip->i_d.di_nextents > 0) - xfs_dir3_data_readahead(ip, 0, -1); + error = xfs_dir3_data_readahead(ip, 0, -1); xfs_iunlock(ip, mode); - return 0; + return error; } STATIC int @@ -1373,22 +1379,21 @@ xfs_file_llseek( */ STATIC int xfs_filemap_page_mkwrite( - struct vm_area_struct *vma, struct vm_fault *vmf) { - struct inode *inode = file_inode(vma->vm_file); + struct inode *inode = file_inode(vmf->vma->vm_file); int ret; trace_xfs_filemap_page_mkwrite(XFS_I(inode)); sb_start_pagefault(inode->i_sb); - file_update_time(vma->vm_file); + file_update_time(vmf->vma->vm_file); xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED); if (IS_DAX(inode)) { - ret = dax_iomap_fault(vma, vmf, &xfs_iomap_ops); + ret = dax_iomap_fault(vmf, PE_SIZE_PTE, &xfs_iomap_ops); } else { - ret = iomap_page_mkwrite(vma, vmf, &xfs_iomap_ops); + ret = iomap_page_mkwrite(vmf, &xfs_iomap_ops); ret = block_page_mkwrite_return(ret); } @@ -1400,23 +1405,22 @@ xfs_filemap_page_mkwrite( STATIC int xfs_filemap_fault( - struct vm_area_struct *vma, struct vm_fault *vmf) { - struct inode *inode = file_inode(vma->vm_file); + struct inode *inode = file_inode(vmf->vma->vm_file); int ret; trace_xfs_filemap_fault(XFS_I(inode)); /* DAX can shortcut the normal fault path on write faults! */ if ((vmf->flags & FAULT_FLAG_WRITE) && IS_DAX(inode)) - return xfs_filemap_page_mkwrite(vma, vmf); + return xfs_filemap_page_mkwrite(vmf); xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED); if (IS_DAX(inode)) - ret = dax_iomap_fault(vma, vmf, &xfs_iomap_ops); + ret = dax_iomap_fault(vmf, PE_SIZE_PTE, &xfs_iomap_ops); else - ret = filemap_fault(vma, vmf); + ret = filemap_fault(vmf); xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED); return ret; @@ -1425,36 +1429,34 @@ xfs_filemap_fault( /* * Similar to xfs_filemap_fault(), the DAX fault path can call into here on * both read and write faults. Hence we need to handle both cases. There is no - * ->pmd_mkwrite callout for huge pages, so we have a single function here to + * ->huge_mkwrite callout for huge pages, so we have a single function here to * handle both cases here. @flags carries the information on the type of fault * occuring. */ STATIC int -xfs_filemap_pmd_fault( - struct vm_area_struct *vma, - unsigned long addr, - pmd_t *pmd, - unsigned int flags) +xfs_filemap_huge_fault( + struct vm_fault *vmf, + enum page_entry_size pe_size) { - struct inode *inode = file_inode(vma->vm_file); + struct inode *inode = file_inode(vmf->vma->vm_file); struct xfs_inode *ip = XFS_I(inode); int ret; if (!IS_DAX(inode)) return VM_FAULT_FALLBACK; - trace_xfs_filemap_pmd_fault(ip); + trace_xfs_filemap_huge_fault(ip); - if (flags & FAULT_FLAG_WRITE) { + if (vmf->flags & FAULT_FLAG_WRITE) { sb_start_pagefault(inode->i_sb); - file_update_time(vma->vm_file); + file_update_time(vmf->vma->vm_file); } xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED); - ret = dax_iomap_pmd_fault(vma, addr, pmd, flags, &xfs_iomap_ops); + ret = dax_iomap_fault(vmf, pe_size, &xfs_iomap_ops); xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED); - if (flags & FAULT_FLAG_WRITE) + if (vmf->flags & FAULT_FLAG_WRITE) sb_end_pagefault(inode->i_sb); return ret; @@ -1468,11 +1470,10 @@ xfs_filemap_pmd_fault( */ static int xfs_filemap_pfn_mkwrite( - struct vm_area_struct *vma, struct vm_fault *vmf) { - struct inode *inode = file_inode(vma->vm_file); + struct inode *inode = file_inode(vmf->vma->vm_file); struct xfs_inode *ip = XFS_I(inode); int ret = VM_FAULT_NOPAGE; loff_t size; @@ -1480,7 +1481,7 @@ xfs_filemap_pfn_mkwrite( trace_xfs_filemap_pfn_mkwrite(ip); sb_start_pagefault(inode->i_sb); - file_update_time(vma->vm_file); + file_update_time(vmf->vma->vm_file); /* check if the faulting page hasn't raced with truncate */ xfs_ilock(ip, XFS_MMAPLOCK_SHARED); @@ -1488,7 +1489,7 @@ xfs_filemap_pfn_mkwrite( if (vmf->pgoff >= size) ret = VM_FAULT_SIGBUS; else if (IS_DAX(inode)) - ret = dax_pfn_mkwrite(vma, vmf); + ret = dax_pfn_mkwrite(vmf); xfs_iunlock(ip, XFS_MMAPLOCK_SHARED); sb_end_pagefault(inode->i_sb); return ret; @@ -1497,7 +1498,7 @@ xfs_filemap_pfn_mkwrite( static const struct vm_operations_struct xfs_file_vm_ops = { .fault = xfs_filemap_fault, - .pmd_fault = xfs_filemap_pmd_fault, + .huge_fault = xfs_filemap_huge_fault, .map_pages = filemap_map_pages, .page_mkwrite = xfs_filemap_page_mkwrite, .pfn_mkwrite = xfs_filemap_pfn_mkwrite, diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index 242e8091296d..6ccaae9eb0ee 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -352,12 +352,7 @@ xfs_growfs_data_private( goto error0; } - if (xfs_sb_version_hascrc(&mp->m_sb)) - xfs_btree_init_block(mp, bp, XFS_ABTB_CRC_MAGIC, 0, 1, - agno, XFS_BTREE_CRC_BLOCKS); - else - xfs_btree_init_block(mp, bp, XFS_ABTB_MAGIC, 0, 1, - agno, 0); + xfs_btree_init_block(mp, bp, XFS_BTNUM_BNO, 0, 1, agno, 0); arec = XFS_ALLOC_REC_ADDR(mp, XFS_BUF_TO_BLOCK(bp), 1); arec->ar_startblock = cpu_to_be32(mp->m_ag_prealloc_blocks); @@ -381,12 +376,7 @@ xfs_growfs_data_private( goto error0; } - if (xfs_sb_version_hascrc(&mp->m_sb)) - xfs_btree_init_block(mp, bp, XFS_ABTC_CRC_MAGIC, 0, 1, - agno, XFS_BTREE_CRC_BLOCKS); - else - xfs_btree_init_block(mp, bp, XFS_ABTC_MAGIC, 0, 1, - agno, 0); + xfs_btree_init_block(mp, bp, XFS_BTNUM_CNT, 0, 1, agno, 0); arec = XFS_ALLOC_REC_ADDR(mp, XFS_BUF_TO_BLOCK(bp), 1); arec->ar_startblock = cpu_to_be32(mp->m_ag_prealloc_blocks); @@ -413,8 +403,8 @@ xfs_growfs_data_private( goto error0; } - xfs_btree_init_block(mp, bp, XFS_RMAP_CRC_MAGIC, 0, 0, - agno, XFS_BTREE_CRC_BLOCKS); + xfs_btree_init_block(mp, bp, XFS_BTNUM_RMAP, 0, 0, + agno, 0); block = XFS_BUF_TO_BLOCK(bp); @@ -488,12 +478,7 @@ xfs_growfs_data_private( goto error0; } - if (xfs_sb_version_hascrc(&mp->m_sb)) - xfs_btree_init_block(mp, bp, XFS_IBT_CRC_MAGIC, 0, 0, - agno, XFS_BTREE_CRC_BLOCKS); - else - xfs_btree_init_block(mp, bp, XFS_IBT_MAGIC, 0, 0, - agno, 0); + xfs_btree_init_block(mp, bp, XFS_BTNUM_INO , 0, 0, agno, 0); error = xfs_bwrite(bp); xfs_buf_relse(bp); @@ -513,13 +498,8 @@ xfs_growfs_data_private( goto error0; } - if (xfs_sb_version_hascrc(&mp->m_sb)) - xfs_btree_init_block(mp, bp, XFS_FIBT_CRC_MAGIC, - 0, 0, agno, - XFS_BTREE_CRC_BLOCKS); - else - xfs_btree_init_block(mp, bp, XFS_FIBT_MAGIC, 0, - 0, agno, 0); + xfs_btree_init_block(mp, bp, XFS_BTNUM_FINO, + 0, 0, agno, 0); error = xfs_bwrite(bp); xfs_buf_relse(bp); @@ -540,9 +520,8 @@ xfs_growfs_data_private( goto error0; } - xfs_btree_init_block(mp, bp, XFS_REFC_CRC_MAGIC, - 0, 0, agno, - XFS_BTREE_CRC_BLOCKS); + xfs_btree_init_block(mp, bp, XFS_BTNUM_REFC, + 0, 0, agno, 0); error = xfs_bwrite(bp); xfs_buf_relse(bp); diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index 70ca4f608321..7234b9748c36 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -1322,13 +1322,10 @@ xfs_inode_free_eofblocks( int flags, void *args) { - int ret; + int ret = 0; struct xfs_eofblocks *eofb = args; - bool need_iolock = true; int match; - ASSERT(!eofb || (eofb && eofb->eof_scan_owner != 0)); - if (!xfs_can_free_eofblocks(ip, false)) { /* inode could be preallocated or append-only */ trace_xfs_inode_free_eofblocks_invalid(ip); @@ -1356,21 +1353,19 @@ xfs_inode_free_eofblocks( if (eofb->eof_flags & XFS_EOF_FLAGS_MINFILESIZE && XFS_ISIZE(ip) < eofb->eof_min_file_size) return 0; - - /* - * A scan owner implies we already hold the iolock. Skip it in - * xfs_free_eofblocks() to avoid deadlock. This also eliminates - * the possibility of EAGAIN being returned. - */ - if (eofb->eof_scan_owner == ip->i_ino) - need_iolock = false; } - ret = xfs_free_eofblocks(ip->i_mount, ip, need_iolock); - - /* don't revisit the inode if we're not waiting */ - if (ret == -EAGAIN && !(flags & SYNC_WAIT)) - ret = 0; + /* + * If the caller is waiting, return -EAGAIN to keep the background + * scanner moving and revisit the inode in a subsequent pass. + */ + if (!xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL)) { + if (flags & SYNC_WAIT) + ret = -EAGAIN; + return ret; + } + ret = xfs_free_eofblocks(ip); + xfs_iunlock(ip, XFS_IOLOCK_EXCL); return ret; } @@ -1417,15 +1412,10 @@ __xfs_inode_free_quota_eofblocks( struct xfs_eofblocks eofb = {0}; struct xfs_dquot *dq; - ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL)); - /* - * Set the scan owner to avoid a potential livelock. Otherwise, the scan - * can repeatedly trylock on the inode we're currently processing. We - * run a sync scan to increase effectiveness and use the union filter to + * Run a sync scan to increase effectiveness and use the union filter to * cover all applicable quotas in a single scan. */ - eofb.eof_scan_owner = ip->i_ino; eofb.eof_flags = XFS_EOF_FLAGS_UNION|XFS_EOF_FLAGS_SYNC; if (XFS_IS_UQUOTA_ENFORCED(ip->i_mount)) { @@ -1577,12 +1567,9 @@ xfs_inode_free_cowblocks( { int ret; struct xfs_eofblocks *eofb = args; - bool need_iolock = true; int match; struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK); - ASSERT(!eofb || (eofb && eofb->eof_scan_owner != 0)); - /* * Just clear the tag if we have an empty cow fork or none at all. It's * possible the inode was fully unshared since it was originally tagged. @@ -1615,28 +1602,16 @@ xfs_inode_free_cowblocks( if (eofb->eof_flags & XFS_EOF_FLAGS_MINFILESIZE && XFS_ISIZE(ip) < eofb->eof_min_file_size) return 0; - - /* - * A scan owner implies we already hold the iolock. Skip it in - * xfs_free_eofblocks() to avoid deadlock. This also eliminates - * the possibility of EAGAIN being returned. - */ - if (eofb->eof_scan_owner == ip->i_ino) - need_iolock = false; } /* Free the CoW blocks */ - if (need_iolock) { - xfs_ilock(ip, XFS_IOLOCK_EXCL); - xfs_ilock(ip, XFS_MMAPLOCK_EXCL); - } + xfs_ilock(ip, XFS_IOLOCK_EXCL); + xfs_ilock(ip, XFS_MMAPLOCK_EXCL); ret = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF); - if (need_iolock) { - xfs_iunlock(ip, XFS_MMAPLOCK_EXCL); - xfs_iunlock(ip, XFS_IOLOCK_EXCL); - } + xfs_iunlock(ip, XFS_MMAPLOCK_EXCL); + xfs_iunlock(ip, XFS_IOLOCK_EXCL); return ret; } diff --git a/fs/xfs/xfs_icache.h b/fs/xfs/xfs_icache.h index a1e02f4708ab..8a7c849b4dea 100644 --- a/fs/xfs/xfs_icache.h +++ b/fs/xfs/xfs_icache.h @@ -27,7 +27,6 @@ struct xfs_eofblocks { kgid_t eof_gid; prid_t eof_prid; __u64 eof_min_file_size; - xfs_ino_t eof_scan_owner; }; #define SYNC_WAIT 0x0001 /* wait for i/o to complete */ @@ -102,7 +101,6 @@ xfs_fs_eofblocks_from_user( dst->eof_flags = src->eof_flags; dst->eof_prid = src->eof_prid; dst->eof_min_file_size = src->eof_min_file_size; - dst->eof_scan_owner = NULLFSINO; dst->eof_uid = INVALID_UID; if (src->eof_flags & XFS_EOF_FLAGS_UID) { diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index de32f0fe47c8..edfa6a55b064 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -1692,32 +1692,34 @@ xfs_release( if (xfs_can_free_eofblocks(ip, false)) { /* + * Check if the inode is being opened, written and closed + * frequently and we have delayed allocation blocks outstanding + * (e.g. streaming writes from the NFS server), truncating the + * blocks past EOF will cause fragmentation to occur. + * + * In this case don't do the truncation, but we have to be + * careful how we detect this case. Blocks beyond EOF show up as + * i_delayed_blks even when the inode is clean, so we need to + * truncate them away first before checking for a dirty release. + * Hence on the first dirty close we will still remove the + * speculative allocation, but after that we will leave it in + * place. + */ + if (xfs_iflags_test(ip, XFS_IDIRTY_RELEASE)) + return 0; + /* * If we can't get the iolock just skip truncating the blocks * past EOF because we could deadlock with the mmap_sem - * otherwise. We'll get another chance to drop them once the + * otherwise. We'll get another chance to drop them once the * last reference to the inode is dropped, so we'll never leak * blocks permanently. - * - * Further, check if the inode is being opened, written and - * closed frequently and we have delayed allocation blocks - * outstanding (e.g. streaming writes from the NFS server), - * truncating the blocks past EOF will cause fragmentation to - * occur. - * - * In this case don't do the truncation, either, but we have to - * be careful how we detect this case. Blocks beyond EOF show - * up as i_delayed_blks even when the inode is clean, so we - * need to truncate them away first before checking for a dirty - * release. Hence on the first dirty close we will still remove - * the speculative allocation, but after that we will leave it - * in place. */ - if (xfs_iflags_test(ip, XFS_IDIRTY_RELEASE)) - return 0; - - error = xfs_free_eofblocks(mp, ip, true); - if (error && error != -EAGAIN) - return error; + if (xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL)) { + error = xfs_free_eofblocks(ip); + xfs_iunlock(ip, XFS_IOLOCK_EXCL); + if (error) + return error; + } /* delalloc blocks after truncation means it really is dirty */ if (ip->i_delayed_blks) @@ -1904,8 +1906,11 @@ xfs_inactive( * cache. Post-eof blocks must be freed, lest we end up with * broken free space accounting. */ - if (xfs_can_free_eofblocks(ip, true)) - xfs_free_eofblocks(mp, ip, false); + if (xfs_can_free_eofblocks(ip, true)) { + xfs_ilock(ip, XFS_IOLOCK_EXCL); + xfs_free_eofblocks(ip); + xfs_iunlock(ip, XFS_IOLOCK_EXCL); + } return; } diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index c67cfb451fd3..cf1363dbf32b 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -1524,7 +1524,7 @@ out_drop_write: } STATIC int -xfs_getbmap_format(void **ap, struct getbmapx *bmv, int *full) +xfs_getbmap_format(void **ap, struct getbmapx *bmv) { struct getbmap __user *base = (struct getbmap __user *)*ap; @@ -1567,7 +1567,7 @@ xfs_ioc_getbmap( } STATIC int -xfs_getbmapx_format(void **ap, struct getbmapx *bmv, int *full) +xfs_getbmapx_format(void **ap, struct getbmapx *bmv) { struct getbmapx __user *base = (struct getbmapx __user *)*ap; diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 1aa3abd67b36..41662fb14e87 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -162,7 +162,7 @@ xfs_iomap_write_direct( xfs_fileoff_t last_fsb; xfs_filblks_t count_fsb, resaligned; xfs_fsblock_t firstfsb; - xfs_extlen_t extsz, temp; + xfs_extlen_t extsz; int nimaps; int quota_flag; int rt; @@ -203,14 +203,7 @@ xfs_iomap_write_direct( } count_fsb = last_fsb - offset_fsb; ASSERT(count_fsb > 0); - - resaligned = count_fsb; - if (unlikely(extsz)) { - if ((temp = do_mod(offset_fsb, extsz))) - resaligned += temp; - if ((temp = do_mod(resaligned, extsz))) - resaligned += extsz - temp; - } + resaligned = xfs_aligned_fsb_count(offset_fsb, count_fsb, extsz); if (unlikely(rt)) { resrtextents = qblocks = resaligned; @@ -685,7 +678,7 @@ xfs_iomap_write_allocate( int nres; if (whichfork == XFS_COW_FORK) - flags |= XFS_BMAPI_COWFORK; + flags |= XFS_BMAPI_COWFORK | XFS_BMAPI_PREALLOC; /* * Make sure that the dquots are there. @@ -1002,47 +995,31 @@ xfs_file_iomap_begin( offset_fsb = XFS_B_TO_FSBT(mp, offset); end_fsb = XFS_B_TO_FSB(mp, offset + length); - if (xfs_is_reflink_inode(ip) && - (flags & IOMAP_WRITE) && (flags & IOMAP_DIRECT)) { - shared = xfs_reflink_find_cow_mapping(ip, offset, &imap); - if (shared) { - xfs_iunlock(ip, lockmode); - goto alloc_done; - } - ASSERT(!isnullstartblock(imap.br_startblock)); - } - error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb, &imap, &nimaps, 0); if (error) goto out_unlock; - if ((flags & IOMAP_REPORT) || - (xfs_is_reflink_inode(ip) && - (flags & IOMAP_WRITE) && (flags & IOMAP_DIRECT))) { + if (flags & IOMAP_REPORT) { /* Trim the mapping to the nearest shared extent boundary. */ error = xfs_reflink_trim_around_shared(ip, &imap, &shared, &trimmed); if (error) goto out_unlock; - - /* - * We're here because we're trying to do a directio write to a - * region that isn't aligned to a filesystem block. If the - * extent is shared, fall back to buffered mode to handle the - * RMW. - */ - if (!(flags & IOMAP_REPORT) && shared) { - trace_xfs_reflink_bounce_dio_write(ip, &imap); - error = -EREMCHG; - goto out_unlock; - } } if ((flags & (IOMAP_WRITE | IOMAP_ZERO)) && xfs_is_reflink_inode(ip)) { - error = xfs_reflink_reserve_cow(ip, &imap, &shared); - if (error) - goto out_unlock; + if (flags & IOMAP_DIRECT) { + /* may drop and re-acquire the ilock */ + error = xfs_reflink_allocate_cow(ip, &imap, &shared, + &lockmode); + if (error) + goto out_unlock; + } else { + error = xfs_reflink_reserve_cow(ip, &imap, &shared); + if (error) + goto out_unlock; + } end_fsb = imap.br_startoff + imap.br_blockcount; length = XFS_FSB_TO_B(mp, end_fsb) - offset; @@ -1071,7 +1048,6 @@ xfs_file_iomap_begin( if (error) return error; -alloc_done: iomap->flags = IOMAP_F_NEW; trace_xfs_iomap_alloc(ip, offset, length, 0, &imap); } else { @@ -1102,7 +1078,19 @@ xfs_file_iomap_end_delalloc( xfs_fileoff_t end_fsb; int error = 0; - start_fsb = XFS_B_TO_FSB(mp, offset + written); + /* behave as if the write failed if drop writes is enabled */ + if (xfs_mp_drop_writes(mp)) + written = 0; + + /* + * start_fsb refers to the first unused block after a short write. If + * nothing was written, round offset down to point at the first block in + * the range. + */ + if (unlikely(!written)) + start_fsb = XFS_B_TO_FSBT(mp, offset); + else + start_fsb = XFS_B_TO_FSB(mp, offset + written); end_fsb = XFS_B_TO_FSB(mp, offset + length); /* @@ -1114,6 +1102,9 @@ xfs_file_iomap_end_delalloc( * blocks in the range, they are ours. */ if (start_fsb < end_fsb) { + truncate_pagecache_range(VFS_I(ip), XFS_FSB_TO_B(mp, start_fsb), + XFS_FSB_TO_B(mp, end_fsb) - 1); + xfs_ilock(ip, XFS_ILOCK_EXCL); error = xfs_bmap_punch_delalloc_range(ip, start_fsb, end_fsb - start_fsb); @@ -1144,7 +1135,7 @@ xfs_file_iomap_end( return 0; } -struct iomap_ops xfs_iomap_ops = { +const struct iomap_ops xfs_iomap_ops = { .iomap_begin = xfs_file_iomap_begin, .iomap_end = xfs_file_iomap_end, }; @@ -1190,6 +1181,6 @@ out_unlock: return error; } -struct iomap_ops xfs_xattr_iomap_ops = { +const struct iomap_ops xfs_xattr_iomap_ops = { .iomap_begin = xfs_xattr_iomap_begin, }; diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h index 6d45cf01fcff..00db3ecea084 100644 --- a/fs/xfs/xfs_iomap.h +++ b/fs/xfs/xfs_iomap.h @@ -33,7 +33,27 @@ void xfs_bmbt_to_iomap(struct xfs_inode *, struct iomap *, struct xfs_bmbt_irec *); xfs_extlen_t xfs_eof_alignment(struct xfs_inode *ip, xfs_extlen_t extsize); -extern struct iomap_ops xfs_iomap_ops; -extern struct iomap_ops xfs_xattr_iomap_ops; +static inline xfs_filblks_t +xfs_aligned_fsb_count( + xfs_fileoff_t offset_fsb, + xfs_filblks_t count_fsb, + xfs_extlen_t extsz) +{ + if (extsz) { + xfs_extlen_t align; + + align = do_mod(offset_fsb, extsz); + if (align) + count_fsb += align; + align = do_mod(count_fsb, extsz); + if (align) + count_fsb += extsz - align; + } + + return count_fsb; +} + +extern const struct iomap_ops xfs_iomap_ops; +extern const struct iomap_ops xfs_xattr_iomap_ops; #endif /* __XFS_IOMAP_H__*/ diff --git a/fs/xfs/xfs_log.h b/fs/xfs/xfs_log.h index b5e71072fde5..cc5a9f1574e7 100644 --- a/fs/xfs/xfs_log.h +++ b/fs/xfs/xfs_log.h @@ -124,7 +124,6 @@ struct xlog_ticket; struct xfs_log_item; struct xfs_item_ops; struct xfs_trans; -struct xfs_log_callback; xfs_lsn_t xfs_log_done(struct xfs_mount *mp, struct xlog_ticket *ticket, diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c index a4ab192e1792..82f1cbcc4de1 100644 --- a/fs/xfs/xfs_log_cil.c +++ b/fs/xfs/xfs_log_cil.c @@ -30,6 +30,9 @@ #include "xfs_trans_priv.h" #include "xfs_log.h" #include "xfs_log_priv.h" +#include "xfs_trace.h" + +struct workqueue_struct *xfs_discard_wq; /* * Allocate a new ticket. Failing to get a new ticket makes it really hard to @@ -491,6 +494,75 @@ xlog_cil_free_logvec( } } +static void +xlog_discard_endio_work( + struct work_struct *work) +{ + struct xfs_cil_ctx *ctx = + container_of(work, struct xfs_cil_ctx, discard_endio_work); + struct xfs_mount *mp = ctx->cil->xc_log->l_mp; + + xfs_extent_busy_clear(mp, &ctx->busy_extents, false); + kmem_free(ctx); +} + +/* + * Queue up the actual completion to a thread to avoid IRQ-safe locking for + * pagb_lock. Note that we need a unbounded workqueue, otherwise we might + * get the execution delayed up to 30 seconds for weird reasons. + */ +static void +xlog_discard_endio( + struct bio *bio) +{ + struct xfs_cil_ctx *ctx = bio->bi_private; + + INIT_WORK(&ctx->discard_endio_work, xlog_discard_endio_work); + queue_work(xfs_discard_wq, &ctx->discard_endio_work); +} + +static void +xlog_discard_busy_extents( + struct xfs_mount *mp, + struct xfs_cil_ctx *ctx) +{ + struct list_head *list = &ctx->busy_extents; + struct xfs_extent_busy *busyp; + struct bio *bio = NULL; + struct blk_plug plug; + int error = 0; + + ASSERT(mp->m_flags & XFS_MOUNT_DISCARD); + + blk_start_plug(&plug); + list_for_each_entry(busyp, list, list) { + trace_xfs_discard_extent(mp, busyp->agno, busyp->bno, + busyp->length); + + error = __blkdev_issue_discard(mp->m_ddev_targp->bt_bdev, + XFS_AGB_TO_DADDR(mp, busyp->agno, busyp->bno), + XFS_FSB_TO_BB(mp, busyp->length), + GFP_NOFS, 0, &bio); + if (error && error != -EOPNOTSUPP) { + xfs_info(mp, + "discard failed for extent [0x%llx,%u], error %d", + (unsigned long long)busyp->bno, + busyp->length, + error); + break; + } + } + + if (bio) { + bio->bi_private = ctx; + bio->bi_end_io = xlog_discard_endio; + submit_bio(bio); + } else { + xlog_discard_endio_work(&ctx->discard_endio_work); + } + blk_finish_plug(&plug); +} + /* * Mark all items committed and clear busy extents. We free the log vector * chains in a separate pass so that we unpin the log items as quickly as @@ -525,14 +597,10 @@ xlog_cil_committed( xlog_cil_free_logvec(ctx->lv_chain); - if (!list_empty(&ctx->busy_extents)) { - ASSERT(mp->m_flags & XFS_MOUNT_DISCARD); - - xfs_discard_extents(mp, &ctx->busy_extents); - xfs_extent_busy_clear(mp, &ctx->busy_extents, false); - } - - kmem_free(ctx); + if (!list_empty(&ctx->busy_extents)) + xlog_discard_busy_extents(mp, ctx); + else + kmem_free(ctx); } /* diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h index 2b6eec52178e..c2604a5366f2 100644 --- a/fs/xfs/xfs_log_priv.h +++ b/fs/xfs/xfs_log_priv.h @@ -257,6 +257,7 @@ struct xfs_cil_ctx { struct xfs_log_vec *lv_chain; /* logvecs being pushed */ struct xfs_log_callback log_cb; /* completion callback hook. */ struct list_head committing; /* ctx committing list */ + struct work_struct discard_endio_work; }; /* diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 9b9540db17a6..450bde68bb75 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -45,6 +45,7 @@ #include "xfs_rmap_btree.h" #include "xfs_refcount_btree.h" #include "xfs_reflink.h" +#include "xfs_extent_busy.h" static DEFINE_MUTEX(xfs_uuid_table_mutex); @@ -187,7 +188,7 @@ xfs_initialize_perag( xfs_agnumber_t *maxagi) { xfs_agnumber_t index; - xfs_agnumber_t first_initialised = 0; + xfs_agnumber_t first_initialised = NULLAGNUMBER; xfs_perag_t *pag; int error = -ENOMEM; @@ -202,22 +203,21 @@ xfs_initialize_perag( xfs_perag_put(pag); continue; } - if (!first_initialised) - first_initialised = index; pag = kmem_zalloc(sizeof(*pag), KM_MAYFAIL); if (!pag) - goto out_unwind; + goto out_unwind_new_pags; pag->pag_agno = index; pag->pag_mount = mp; spin_lock_init(&pag->pag_ici_lock); mutex_init(&pag->pag_ici_reclaim_lock); INIT_RADIX_TREE(&pag->pag_ici_root, GFP_ATOMIC); if (xfs_buf_hash_init(pag)) - goto out_unwind; + goto out_free_pag; + init_waitqueue_head(&pag->pagb_wait); if (radix_tree_preload(GFP_NOFS)) - goto out_unwind; + goto out_hash_destroy; spin_lock(&mp->m_perag_lock); if (radix_tree_insert(&mp->m_perag_tree, index, pag)) { @@ -225,10 +225,13 @@ xfs_initialize_perag( spin_unlock(&mp->m_perag_lock); radix_tree_preload_end(); error = -EEXIST; - goto out_unwind; + goto out_hash_destroy; } spin_unlock(&mp->m_perag_lock); radix_tree_preload_end(); + /* first new pag is fully initialized */ + if (first_initialised == NULLAGNUMBER) + first_initialised = index; } index = xfs_set_inode_alloc(mp, agcount); @@ -239,11 +242,16 @@ xfs_initialize_perag( mp->m_ag_prealloc_blocks = xfs_prealloc_blocks(mp); return 0; -out_unwind: +out_hash_destroy: xfs_buf_hash_destroy(pag); +out_free_pag: kmem_free(pag); - for (; index > first_initialised; index--) { +out_unwind_new_pags: + /* unwind any prior newly initialized pags */ + for (index = first_initialised; index < agcount; index++) { pag = radix_tree_delete(&mp->m_perag_tree, index); + if (!pag) + break; xfs_buf_hash_destroy(pag); kmem_free(pag); } @@ -1073,6 +1081,13 @@ xfs_unmountfs( xfs_log_force(mp, XFS_LOG_SYNC); /* + * Wait for all busy extents to be freed, including completion of + * any discard operation. + */ + xfs_extent_busy_wait_all(mp); + flush_workqueue(xfs_discard_wq); + + /* * We now need to tell the world we are unmounting. This will allow * us to detect that the filesystem is going away and we should error * out anything that we have been retrying in the background. This will diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index 7f351f706b7a..6db6fd6b82b0 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -200,11 +200,12 @@ typedef struct xfs_mount { /* * DEBUG mode instrumentation to test and/or trigger delayed allocation * block killing in the event of failed writes. When enabled, all - * buffered writes are forced to fail. All delalloc blocks in the range - * of the write (including pre-existing delalloc blocks!) are tossed as - * part of the write failure error handling sequence. + * buffered writes are silenty dropped and handled as if they failed. + * All delalloc blocks in the range of the write (including pre-existing + * delalloc blocks!) are tossed as part of the write failure error + * handling sequence. */ - bool m_fail_writes; + bool m_drop_writes; #endif } xfs_mount_t; @@ -325,13 +326,13 @@ xfs_daddr_to_agbno(struct xfs_mount *mp, xfs_daddr_t d) #ifdef DEBUG static inline bool -xfs_mp_fail_writes(struct xfs_mount *mp) +xfs_mp_drop_writes(struct xfs_mount *mp) { - return mp->m_fail_writes; + return mp->m_drop_writes; } #else static inline bool -xfs_mp_fail_writes(struct xfs_mount *mp) +xfs_mp_drop_writes(struct xfs_mount *mp) { return 0; } @@ -384,6 +385,8 @@ typedef struct xfs_perag { xfs_agino_t pagl_rightrec; spinlock_t pagb_lock; /* lock for pagb_tree */ struct rb_root pagb_tree; /* ordered tree of busy extents */ + unsigned int pagb_gen; /* generation count for pagb_tree */ + wait_queue_head_t pagb_wait; /* woken when pagb_gen changes */ atomic_t pagf_fstrms; /* # of filestreams active in this AG */ diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index 07593a362cd0..da6d08fb359c 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -82,11 +82,22 @@ * mappings are a reservation against the free space in the filesystem; * adjacent mappings can also be combined into fewer larger mappings. * + * As an optimization, the CoW extent size hint (cowextsz) creates + * outsized aligned delalloc reservations in the hope of landing out of + * order nearby CoW writes in a single extent on disk, thereby reducing + * fragmentation and improving future performance. + * + * D: --RRRRRRSSSRRRRRRRR--- (data fork) + * C: ------DDDDDDD--------- (CoW fork) + * * When dirty pages are being written out (typically in writepage), the - * delalloc reservations are converted into real mappings by allocating - * blocks and replacing the delalloc mapping with real ones. A delalloc - * mapping can be replaced by several real ones if the free space is - * fragmented. + * delalloc reservations are converted into unwritten mappings by + * allocating blocks and replacing the delalloc mapping with real ones. + * A delalloc mapping can be replaced by several unwritten ones if the + * free space is fragmented. + * + * D: --RRRRRRSSSRRRRRRRR--- + * C: ------UUUUUUU--------- * * We want to adapt the delalloc mechanism for copy-on-write, since the * write paths are similar. The first two steps (creating the reservation @@ -101,13 +112,29 @@ * Block-aligned directio writes will use the same mechanism as buffered * writes. * + * Just prior to submitting the actual disk write requests, we convert + * the extents representing the range of the file actually being written + * (as opposed to extra pieces created for the cowextsize hint) to real + * extents. This will become important in the next step: + * + * D: --RRRRRRSSSRRRRRRRR--- + * C: ------UUrrUUU--------- + * * CoW remapping must be done after the data block write completes, * because we don't want to destroy the old data fork map until we're sure * the new block has been written. Since the new mappings are kept in a * separate fork, we can simply iterate these mappings to find the ones * that cover the file blocks that we just CoW'd. For each extent, simply * unmap the corresponding range in the data fork, map the new range into - * the data fork, and remove the extent from the CoW fork. + * the data fork, and remove the extent from the CoW fork. Because of + * the presence of the cowextsize hint, however, we must be careful + * only to remap the blocks that we've actually written out -- we must + * never remap delalloc reservations nor CoW staging blocks that have + * yet to be written. This corresponds exactly to the real extents in + * the CoW fork: + * + * D: --RRRRRRrrSRRRRRRRR--- + * C: ------UU--UUU--------- * * Since the remapping operation can be applied to an arbitrary file * range, we record the need for the remap step as a flag in the ioend @@ -296,103 +323,165 @@ xfs_reflink_reserve_cow( return 0; } -/* Allocate all CoW reservations covering a range of blocks in a file. */ -static int -__xfs_reflink_allocate_cow( - struct xfs_inode *ip, - xfs_fileoff_t *offset_fsb, - xfs_fileoff_t end_fsb) +/* Convert part of an unwritten CoW extent to a real one. */ +STATIC int +xfs_reflink_convert_cow_extent( + struct xfs_inode *ip, + struct xfs_bmbt_irec *imap, + xfs_fileoff_t offset_fsb, + xfs_filblks_t count_fsb, + struct xfs_defer_ops *dfops) { - struct xfs_mount *mp = ip->i_mount; - struct xfs_bmbt_irec imap; - struct xfs_defer_ops dfops; - struct xfs_trans *tp; - xfs_fsblock_t first_block; - int nimaps = 1, error; - bool shared; - - xfs_defer_init(&dfops, &first_block); + xfs_fsblock_t first_block; + int nimaps = 1; - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, 0, 0, - XFS_TRANS_RESERVE, &tp); - if (error) - return error; + if (imap->br_state == XFS_EXT_NORM) + return 0; - xfs_ilock(ip, XFS_ILOCK_EXCL); + xfs_trim_extent(imap, offset_fsb, count_fsb); + trace_xfs_reflink_convert_cow(ip, imap); + if (imap->br_blockcount == 0) + return 0; + return xfs_bmapi_write(NULL, ip, imap->br_startoff, imap->br_blockcount, + XFS_BMAPI_COWFORK | XFS_BMAPI_CONVERT, &first_block, + 0, imap, &nimaps, dfops); +} - /* Read extent from the source file. */ - nimaps = 1; - error = xfs_bmapi_read(ip, *offset_fsb, end_fsb - *offset_fsb, - &imap, &nimaps, 0); - if (error) - goto out_unlock; - ASSERT(nimaps == 1); +/* Convert all of the unwritten CoW extents in a file's range to real ones. */ +int +xfs_reflink_convert_cow( + struct xfs_inode *ip, + xfs_off_t offset, + xfs_off_t count) +{ + struct xfs_bmbt_irec got; + struct xfs_defer_ops dfops; + struct xfs_mount *mp = ip->i_mount; + struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK); + xfs_fileoff_t offset_fsb = XFS_B_TO_FSBT(mp, offset); + xfs_fileoff_t end_fsb = XFS_B_TO_FSB(mp, offset + count); + xfs_extnum_t idx; + bool found; + int error = 0; - error = xfs_reflink_reserve_cow(ip, &imap, &shared); - if (error) - goto out_trans_cancel; + xfs_ilock(ip, XFS_ILOCK_EXCL); - if (!shared) { - *offset_fsb = imap.br_startoff + imap.br_blockcount; - goto out_trans_cancel; + /* Convert all the extents to real from unwritten. */ + for (found = xfs_iext_lookup_extent(ip, ifp, offset_fsb, &idx, &got); + found && got.br_startoff < end_fsb; + found = xfs_iext_get_extent(ifp, ++idx, &got)) { + error = xfs_reflink_convert_cow_extent(ip, &got, offset_fsb, + end_fsb - offset_fsb, &dfops); + if (error) + break; } - xfs_trans_ijoin(tp, ip, 0); - error = xfs_bmapi_write(tp, ip, imap.br_startoff, imap.br_blockcount, - XFS_BMAPI_COWFORK, &first_block, - XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK), - &imap, &nimaps, &dfops); - if (error) - goto out_trans_cancel; - - error = xfs_defer_finish(&tp, &dfops, NULL); - if (error) - goto out_trans_cancel; - - error = xfs_trans_commit(tp); - - *offset_fsb = imap.br_startoff + imap.br_blockcount; -out_unlock: + /* Finish up. */ xfs_iunlock(ip, XFS_ILOCK_EXCL); return error; -out_trans_cancel: - xfs_defer_cancel(&dfops); - xfs_trans_cancel(tp); - goto out_unlock; } -/* Allocate all CoW reservations covering a part of a file. */ +/* Allocate all CoW reservations covering a range of blocks in a file. */ int -xfs_reflink_allocate_cow_range( +xfs_reflink_allocate_cow( struct xfs_inode *ip, - xfs_off_t offset, - xfs_off_t count) + struct xfs_bmbt_irec *imap, + bool *shared, + uint *lockmode) { struct xfs_mount *mp = ip->i_mount; - xfs_fileoff_t offset_fsb = XFS_B_TO_FSBT(mp, offset); - xfs_fileoff_t end_fsb = XFS_B_TO_FSB(mp, offset + count); - int error; + xfs_fileoff_t offset_fsb = imap->br_startoff; + xfs_filblks_t count_fsb = imap->br_blockcount; + struct xfs_bmbt_irec got; + struct xfs_defer_ops dfops; + struct xfs_trans *tp = NULL; + xfs_fsblock_t first_block; + int nimaps, error = 0; + bool trimmed; + xfs_filblks_t resaligned; + xfs_extlen_t resblks = 0; + xfs_extnum_t idx; +retry: ASSERT(xfs_is_reflink_inode(ip)); - - trace_xfs_reflink_allocate_cow_range(ip, offset, count); + ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL | XFS_ILOCK_SHARED)); /* - * Make sure that the dquots are there. + * Even if the extent is not shared we might have a preallocation for + * it in the COW fork. If so use it. */ - error = xfs_qm_dqattach(ip, 0); - if (error) - return error; + if (xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &idx, &got) && + got.br_startoff <= offset_fsb) { + *shared = true; - while (offset_fsb < end_fsb) { - error = __xfs_reflink_allocate_cow(ip, &offset_fsb, end_fsb); - if (error) { - trace_xfs_reflink_allocate_cow_range_error(ip, error, - _RET_IP_); - break; + /* If we have a real allocation in the COW fork we're done. */ + if (!isnullstartblock(got.br_startblock)) { + xfs_trim_extent(&got, offset_fsb, count_fsb); + *imap = got; + goto convert; } + + xfs_trim_extent(imap, got.br_startoff, got.br_blockcount); + } else { + error = xfs_reflink_trim_around_shared(ip, imap, shared, &trimmed); + if (error || !*shared) + goto out; + } + + if (!tp) { + resaligned = xfs_aligned_fsb_count(imap->br_startoff, + imap->br_blockcount, xfs_get_cowextsz_hint(ip)); + resblks = XFS_DIOSTRAT_SPACE_RES(mp, resaligned); + + xfs_iunlock(ip, *lockmode); + error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0, &tp); + *lockmode = XFS_ILOCK_EXCL; + xfs_ilock(ip, *lockmode); + + if (error) + return error; + + error = xfs_qm_dqattach_locked(ip, 0); + if (error) + goto out; + goto retry; } + error = xfs_trans_reserve_quota_nblks(tp, ip, resblks, 0, + XFS_QMOPT_RES_REGBLKS); + if (error) + goto out; + + xfs_trans_ijoin(tp, ip, 0); + + xfs_defer_init(&dfops, &first_block); + nimaps = 1; + + /* Allocate the entire reservation as unwritten blocks. */ + error = xfs_bmapi_write(tp, ip, imap->br_startoff, imap->br_blockcount, + XFS_BMAPI_COWFORK | XFS_BMAPI_PREALLOC, &first_block, + resblks, imap, &nimaps, &dfops); + if (error) + goto out_bmap_cancel; + + /* Finish up. */ + error = xfs_defer_finish(&tp, &dfops, NULL); + if (error) + goto out_bmap_cancel; + + error = xfs_trans_commit(tp); + if (error) + return error; +convert: + return xfs_reflink_convert_cow_extent(ip, imap, offset_fsb, count_fsb, + &dfops); +out_bmap_cancel: + xfs_defer_cancel(&dfops); + xfs_trans_unreserve_quota_nblks(tp, ip, (long)resblks, 0, + XFS_QMOPT_RES_REGBLKS); +out: + if (tp) + xfs_trans_cancel(tp); return error; } @@ -641,6 +730,16 @@ xfs_reflink_end_cow( ASSERT(!isnullstartblock(got.br_startblock)); + /* + * Don't remap unwritten extents; these are + * speculatively preallocated CoW extents that have been + * allocated but have not yet been involved in a write. + */ + if (got.br_state == XFS_EXT_UNWRITTEN) { + idx--; + goto next_extent; + } + /* Unmap the old blocks in the data fork. */ xfs_defer_init(&dfops, &firstfsb); rlen = del.br_blockcount; @@ -855,13 +954,14 @@ STATIC int xfs_reflink_update_dest( struct xfs_inode *dest, xfs_off_t newlen, - xfs_extlen_t cowextsize) + xfs_extlen_t cowextsize, + bool is_dedupe) { struct xfs_mount *mp = dest->i_mount; struct xfs_trans *tp; int error; - if (newlen <= i_size_read(VFS_I(dest)) && cowextsize == 0) + if (is_dedupe && newlen <= i_size_read(VFS_I(dest)) && cowextsize == 0) return 0; error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ichange, 0, 0, 0, &tp); @@ -882,6 +982,10 @@ xfs_reflink_update_dest( dest->i_d.di_flags2 |= XFS_DIFLAG2_COWEXTSIZE; } + if (!is_dedupe) { + xfs_trans_ichgtime(tp, dest, + XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); + } xfs_trans_log_inode(tp, dest, XFS_ILOG_CORE); error = xfs_trans_commit(tp); @@ -1195,7 +1299,8 @@ xfs_reflink_remap_range( !(dest->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE)) cowextsize = src->i_d.di_cowextsize; - ret = xfs_reflink_update_dest(dest, pos_out + len, cowextsize); + ret = xfs_reflink_update_dest(dest, pos_out + len, cowextsize, + is_dedupe); out_unlock: xfs_iunlock(src, XFS_MMAPLOCK_EXCL); diff --git a/fs/xfs/xfs_reflink.h b/fs/xfs/xfs_reflink.h index aa6a4d64bd35..33ac9b8db683 100644 --- a/fs/xfs/xfs_reflink.h +++ b/fs/xfs/xfs_reflink.h @@ -28,8 +28,10 @@ extern int xfs_reflink_trim_around_shared(struct xfs_inode *ip, extern int xfs_reflink_reserve_cow(struct xfs_inode *ip, struct xfs_bmbt_irec *imap, bool *shared); -extern int xfs_reflink_allocate_cow_range(struct xfs_inode *ip, - xfs_off_t offset, xfs_off_t count); +extern int xfs_reflink_allocate_cow(struct xfs_inode *ip, + struct xfs_bmbt_irec *imap, bool *shared, uint *lockmode); +extern int xfs_reflink_convert_cow(struct xfs_inode *ip, xfs_off_t offset, + xfs_off_t count); extern bool xfs_reflink_find_cow_mapping(struct xfs_inode *ip, xfs_off_t offset, struct xfs_bmbt_irec *imap); extern void xfs_reflink_trim_irec_to_next_cow(struct xfs_inode *ip, diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c index 802bcc326d9f..c57aa7f18087 100644 --- a/fs/xfs/xfs_rtalloc.c +++ b/fs/xfs/xfs_rtalloc.c @@ -1093,7 +1093,6 @@ xfs_rtallocate_extent( xfs_extlen_t minlen, /* minimum length to allocate */ xfs_extlen_t maxlen, /* maximum length to allocate */ xfs_extlen_t *len, /* out: actual length allocated */ - xfs_alloctype_t type, /* allocation type XFS_ALLOCTYPE... */ int wasdel, /* was a delayed allocation extent */ xfs_extlen_t prod, /* extent product factor */ xfs_rtblock_t *rtblock) /* out: start block allocated */ @@ -1123,27 +1122,16 @@ xfs_rtallocate_extent( } } +retry: sumbp = NULL; - /* - * Allocate by size, or near another block, or exactly at some block. - */ - switch (type) { - case XFS_ALLOCTYPE_ANY_AG: + if (bno == 0) { error = xfs_rtallocate_extent_size(mp, tp, minlen, maxlen, len, &sumbp, &sb, prod, &r); - break; - case XFS_ALLOCTYPE_NEAR_BNO: + } else { error = xfs_rtallocate_extent_near(mp, tp, bno, minlen, maxlen, len, &sumbp, &sb, prod, &r); - break; - case XFS_ALLOCTYPE_THIS_BNO: - error = xfs_rtallocate_extent_exact(mp, tp, bno, minlen, maxlen, - len, &sumbp, &sb, prod, &r); - break; - default: - error = -EIO; - ASSERT(0); } + if (error) return error; @@ -1158,7 +1146,11 @@ xfs_rtallocate_extent( xfs_trans_mod_sb(tp, XFS_TRANS_SB_RES_FREXTENTS, -slen); else xfs_trans_mod_sb(tp, XFS_TRANS_SB_FREXTENTS, -slen); + } else if (prod > 1) { + prod = 1; + goto retry; } + *rtblock = r; return 0; } diff --git a/fs/xfs/xfs_rtalloc.h b/fs/xfs/xfs_rtalloc.h index 355dd9e1cb64..51dd3c726608 100644 --- a/fs/xfs/xfs_rtalloc.h +++ b/fs/xfs/xfs_rtalloc.h @@ -40,7 +40,6 @@ xfs_rtallocate_extent( xfs_extlen_t minlen, /* minimum length to allocate */ xfs_extlen_t maxlen, /* maximum length to allocate */ xfs_extlen_t *len, /* out: actual length allocated */ - xfs_alloctype_t type, /* allocation type XFS_ALLOCTYPE... */ int wasdel, /* was a delayed allocation extent */ xfs_extlen_t prod, /* extent product factor */ xfs_rtblock_t *rtblock); /* out: start block allocated */ @@ -122,7 +121,7 @@ int xfs_rtfree_range(struct xfs_mount *mp, struct xfs_trans *tp, #else -# define xfs_rtallocate_extent(t,b,min,max,l,a,f,p,rb) (ENOSYS) +# define xfs_rtallocate_extent(t,b,min,max,l,f,p,rb) (ENOSYS) # define xfs_rtfree_extent(t,b,l) (ENOSYS) # define xfs_rtpick_extent(m,t,l,rb) (ENOSYS) # define xfs_growfs_rt(mp,in) (ENOSYS) diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index eecbaac08eba..890862f2447c 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1956,12 +1956,20 @@ xfs_init_workqueues(void) if (!xfs_alloc_wq) return -ENOMEM; + xfs_discard_wq = alloc_workqueue("xfsdiscard", WQ_UNBOUND, 0); + if (!xfs_discard_wq) + goto out_free_alloc_wq; + return 0; +out_free_alloc_wq: + destroy_workqueue(xfs_alloc_wq); + return -ENOMEM; } STATIC void xfs_destroy_workqueues(void) { + destroy_workqueue(xfs_discard_wq); destroy_workqueue(xfs_alloc_wq); } diff --git a/fs/xfs/xfs_super.h b/fs/xfs/xfs_super.h index b6418abd85ad..5f2f32408011 100644 --- a/fs/xfs/xfs_super.h +++ b/fs/xfs/xfs_super.h @@ -73,6 +73,8 @@ extern const struct quotactl_ops xfs_quotactl_operations; extern void xfs_reinit_percpu_counters(struct xfs_mount *mp); +extern struct workqueue_struct *xfs_discard_wq; + #define XFS_M(sb) ((struct xfs_mount *)((sb)->s_fs_info)) #endif /* __XFS_SUPER_H__ */ diff --git a/fs/xfs/xfs_sysfs.c b/fs/xfs/xfs_sysfs.c index de6195e38910..80ac15fb9638 100644 --- a/fs/xfs/xfs_sysfs.c +++ b/fs/xfs/xfs_sysfs.c @@ -93,7 +93,7 @@ to_mp(struct kobject *kobject) #ifdef DEBUG STATIC ssize_t -fail_writes_store( +drop_writes_store( struct kobject *kobject, const char *buf, size_t count) @@ -107,9 +107,9 @@ fail_writes_store( return ret; if (val == 1) - mp->m_fail_writes = true; + mp->m_drop_writes = true; else if (val == 0) - mp->m_fail_writes = false; + mp->m_drop_writes = false; else return -EINVAL; @@ -117,21 +117,21 @@ fail_writes_store( } STATIC ssize_t -fail_writes_show( +drop_writes_show( struct kobject *kobject, char *buf) { struct xfs_mount *mp = to_mp(kobject); - return snprintf(buf, PAGE_SIZE, "%d\n", mp->m_fail_writes ? 1 : 0); + return snprintf(buf, PAGE_SIZE, "%d\n", mp->m_drop_writes ? 1 : 0); } -XFS_SYSFS_ATTR_RW(fail_writes); +XFS_SYSFS_ATTR_RW(drop_writes); #endif /* DEBUG */ static struct attribute *xfs_mp_attrs[] = { #ifdef DEBUG - ATTR_LIST(fail_writes), + ATTR_LIST(drop_writes), #endif NULL, }; diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index 69c5bcd9a51b..383ac227ce2c 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -687,7 +687,7 @@ DEFINE_INODE_EVENT(xfs_inode_clear_cowblocks_tag); DEFINE_INODE_EVENT(xfs_inode_free_cowblocks_invalid); DEFINE_INODE_EVENT(xfs_filemap_fault); -DEFINE_INODE_EVENT(xfs_filemap_pmd_fault); +DEFINE_INODE_EVENT(xfs_filemap_huge_fault); DEFINE_INODE_EVENT(xfs_filemap_page_mkwrite); DEFINE_INODE_EVENT(xfs_filemap_pfn_mkwrite); @@ -2245,7 +2245,6 @@ DEFINE_BTREE_CUR_EVENT(xfs_btree_overlapped_query_range); /* deferred ops */ struct xfs_defer_pending; -struct xfs_defer_intake; struct xfs_defer_ops; DECLARE_EVENT_CLASS(xfs_defer_class, @@ -3089,6 +3088,7 @@ DECLARE_EVENT_CLASS(xfs_inode_irec_class, __field(xfs_fileoff_t, lblk) __field(xfs_extlen_t, len) __field(xfs_fsblock_t, pblk) + __field(int, state) ), TP_fast_assign( __entry->dev = VFS_I(ip)->i_sb->s_dev; @@ -3096,13 +3096,15 @@ DECLARE_EVENT_CLASS(xfs_inode_irec_class, __entry->lblk = irec->br_startoff; __entry->len = irec->br_blockcount; __entry->pblk = irec->br_startblock; + __entry->state = irec->br_state; ), - TP_printk("dev %d:%d ino 0x%llx lblk 0x%llx len 0x%x pblk %llu", + TP_printk("dev %d:%d ino 0x%llx lblk 0x%llx len 0x%x pblk %llu st %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->lblk, __entry->len, - __entry->pblk) + __entry->pblk, + __entry->state) ); #define DEFINE_INODE_IREC_EVENT(name) \ DEFINE_EVENT(xfs_inode_irec_class, name, \ @@ -3242,11 +3244,11 @@ DEFINE_INODE_IREC_EVENT(xfs_reflink_trim_around_shared); DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_alloc); DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_found); DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_enospc); +DEFINE_INODE_IREC_EVENT(xfs_reflink_convert_cow); DEFINE_RW_EVENT(xfs_reflink_reserve_cow); -DEFINE_RW_EVENT(xfs_reflink_allocate_cow_range); -DEFINE_INODE_IREC_EVENT(xfs_reflink_bounce_dio_write); +DEFINE_SIMPLE_IO_EVENT(xfs_reflink_bounce_dio_write); DEFINE_IOMAP_EVENT(xfs_reflink_find_cow_mapping); DEFINE_INODE_IREC_EVENT(xfs_reflink_trim_irec); @@ -3254,7 +3256,6 @@ DEFINE_SIMPLE_IO_EVENT(xfs_reflink_cancel_cow_range); DEFINE_SIMPLE_IO_EVENT(xfs_reflink_end_cow); DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_remap); -DEFINE_INODE_ERROR_EVENT(xfs_reflink_allocate_cow_range_error); DEFINE_INODE_ERROR_EVENT(xfs_reflink_cancel_cow_range_error); DEFINE_INODE_ERROR_EVENT(xfs_reflink_end_cow_error); diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h index 61b7fbdd3ebd..1646f659b60f 100644 --- a/fs/xfs/xfs_trans.h +++ b/fs/xfs/xfs_trans.h @@ -32,7 +32,6 @@ struct xfs_mount; struct xfs_trans; struct xfs_trans_res; struct xfs_dquot_acct; -struct xfs_busy_extent; struct xfs_rud_log_item; struct xfs_rui_log_item; struct xfs_btree_cur; |