diff options
Diffstat (limited to 'fs/f2fs/file.c')
| -rw-r--r-- | fs/f2fs/file.c | 2627 |
1 files changed, 1921 insertions, 706 deletions
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 0d4da644df3b..82cda1258227 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -21,6 +21,10 @@ #include <linux/uuid.h> #include <linux/file.h> #include <linux/nls.h> +#include <linux/sched/signal.h> +#include <linux/fileattr.h> +#include <linux/fadvise.h> +#include <linux/iomap.h> #include "f2fs.h" #include "node.h" @@ -28,17 +32,19 @@ #include "xattr.h" #include "acl.h" #include "gc.h" -#include "trace.h" +#include "iostat.h" #include <trace/events/f2fs.h> +#include <uapi/linux/f2fs.h> static vm_fault_t f2fs_filemap_fault(struct vm_fault *vmf) { struct inode *inode = file_inode(vmf->vma->vm_file); vm_fault_t ret; - down_read(&F2FS_I(inode)->i_mmap_sem); ret = filemap_fault(vmf); - up_read(&F2FS_I(inode)->i_mmap_sem); + if (!ret) + f2fs_update_iostat(F2FS_I_SB(inode), inode, + APP_MAPPED_READ_IO, F2FS_BLKSIZE); trace_f2fs_filemap_fault(inode, vmf->pgoff, (unsigned long)ret); @@ -54,6 +60,12 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf) bool need_alloc = true; int err = 0; + if (unlikely(IS_IMMUTABLE(inode))) + return VM_FAULT_SIGBUS; + + if (is_inode_flag_set(inode, FI_COMPRESS_RELEASED)) + return VM_FAULT_SIGBUS; + if (unlikely(f2fs_cp_error(sbi))) { err = -EIO; goto err; @@ -64,6 +76,10 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf) goto err; } + err = f2fs_convert_inline_inode(inode); + if (err) + goto err; + #ifdef CONFIG_F2FS_FS_COMPRESSION if (f2fs_compressed_file(inode)) { int ret = f2fs_is_compressed_cluster(inode, page->index); @@ -72,10 +88,6 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf) err = ret; goto err; } else if (ret) { - if (ret < F2FS_I(inode)->i_cluster_size) { - err = -EAGAIN; - goto err; - } need_alloc = false; } } @@ -89,7 +101,7 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf) f2fs_bug_on(sbi, f2fs_has_inline_data(inode)); file_update_time(vmf->vma->vm_file); - down_read(&F2FS_I(inode)->i_mmap_sem); + filemap_invalidate_lock_shared(inode->i_mapping); lock_page(page); if (unlikely(page->mapping != inode->i_mapping || page_offset(page) > i_size_read(inode) || @@ -101,18 +113,24 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf) if (need_alloc) { /* block allocation */ - __do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, true); + f2fs_do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, true); set_new_dnode(&dn, inode, NULL, NULL, 0); err = f2fs_get_block(&dn, page->index); + f2fs_do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, false); + } + +#ifdef CONFIG_F2FS_FS_COMPRESSION + if (!need_alloc) { + set_new_dnode(&dn, inode, NULL, NULL, 0); + err = f2fs_get_dnode_of_data(&dn, page->index, LOOKUP_NODE); f2fs_put_dnode(&dn); - __do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, false); - if (err) { - unlock_page(page); - goto out_sem; - } + } +#endif + if (err) { + unlock_page(page); + goto out_sem; } - /* fill the page */ f2fs_wait_on_page_writeback(page, DATA, false, true); /* wait for GCed page writeback via META_MAPPING */ @@ -136,12 +154,12 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf) if (!PageUptodate(page)) SetPageUptodate(page); - f2fs_update_iostat(sbi, APP_MAPPED_IO, F2FS_BLKSIZE); + f2fs_update_iostat(sbi, inode, APP_MAPPED_IO, F2FS_BLKSIZE); f2fs_update_time(sbi, REQ_TIME); trace_f2fs_vm_page_mkwrite(page, DATA); out_sem: - up_read(&F2FS_I(inode)->i_mmap_sem); + filemap_invalidate_unlock_shared(inode->i_mapping); sb_end_pagefault(inode->i_sb); err: @@ -158,9 +176,11 @@ static int get_parent_ino(struct inode *inode, nid_t *pino) { struct dentry *dentry; - inode = igrab(inode); - dentry = d_find_any_alias(inode); - iput(inode); + /* + * Make sure to get the non-deleted alias. The alias associated with + * the open file descriptor being fsync()'ed may be deleted already. + */ + dentry = d_find_alias(inode); if (!dentry) return 0; @@ -217,13 +237,13 @@ static void try_to_fix_pino(struct inode *inode) struct f2fs_inode_info *fi = F2FS_I(inode); nid_t pino; - down_write(&fi->i_sem); + f2fs_down_write(&fi->i_sem); if (file_wrong_pino(inode) && inode->i_nlink == 1 && get_parent_ino(inode, &pino)) { f2fs_i_pino_write(inode, pino); file_got_pino(inode); } - up_write(&fi->i_sem); + f2fs_up_write(&fi->i_sem); } static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end, @@ -241,8 +261,7 @@ static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end, }; unsigned int seq_id = 0; - if (unlikely(f2fs_readonly(inode->i_sb) || - is_sbi_flag_set(sbi, SBI_CP_DISABLED))) + if (unlikely(f2fs_readonly(inode->i_sb))) return 0; trace_f2fs_sync_file_enter(inode); @@ -256,7 +275,7 @@ static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end, ret = file_write_and_wait_range(file, start, end); clear_inode_flag(inode, FI_NEED_IPU); - if (ret) { + if (ret || is_sbi_flag_set(sbi, SBI_CP_DISABLED)) { trace_f2fs_sync_file_exit(inode, cp_reason, datasync, ret); return ret; } @@ -281,15 +300,27 @@ static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end, f2fs_exist_written_data(sbi, ino, UPDATE_INO)) goto flush_out; goto out; + } else { + /* + * for OPU case, during fsync(), node can be persisted before + * data when lower device doesn't support write barrier, result + * in data corruption after SPO. + * So for strict fsync mode, force to use atomic write sematics + * to keep write order in between data/node and last node to + * avoid potential data corruption. + */ + if (F2FS_OPTION(sbi).fsync_mode == + FSYNC_MODE_STRICT && !atomic) + atomic = true; } go_write: /* * Both of fdatasync() and fsync() are able to be recovered from * sudden-power-off. */ - down_read(&F2FS_I(inode)->i_sem); + f2fs_down_read(&F2FS_I(inode)->i_sem); cp_reason = need_do_checkpoint(inode); - up_read(&F2FS_I(inode)->i_sem); + f2fs_up_read(&F2FS_I(inode)->i_sem); if (cp_reason) { /* all the dirty node pages should be flushed for POR */ @@ -341,7 +372,8 @@ sync_nodes: f2fs_remove_ino_entry(sbi, ino, APPEND_INO); clear_inode_flag(inode, FI_APPEND_WRITE); flush_out: - if (!atomic && F2FS_OPTION(sbi).fsync_mode != FSYNC_MODE_NOBARRIER) + if ((!atomic && F2FS_OPTION(sbi).fsync_mode != FSYNC_MODE_NOBARRIER) || + (atomic && !test_opt(sbi, NOBARRIER) && f2fs_sb_has_blkzoned(sbi))) ret = f2fs_issue_flush(sbi, inode->i_ino); if (!ret) { f2fs_remove_ino_entry(sbi, ino, UPDATE_INO); @@ -351,7 +383,6 @@ flush_out: f2fs_update_time(sbi, REQ_TIME); out: trace_f2fs_sync_file_exit(inode, cp_reason, datasync, ret); - f2fs_trace_ios(NULL, 1); return ret; } @@ -362,32 +393,15 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) return f2fs_do_sync_file(file, start, end, datasync, false); } -static pgoff_t __get_first_dirty_index(struct address_space *mapping, - pgoff_t pgofs, int whence) -{ - struct page *page; - int nr_pages; - - if (whence != SEEK_DATA) - return 0; - - /* find first dirty page index */ - nr_pages = find_get_pages_tag(mapping, &pgofs, PAGECACHE_TAG_DIRTY, - 1, &page); - if (!nr_pages) - return ULONG_MAX; - pgofs = page->index; - put_page(page); - return pgofs; -} - -static bool __found_offset(struct f2fs_sb_info *sbi, block_t blkaddr, - pgoff_t dirty, pgoff_t pgofs, int whence) +static bool __found_offset(struct address_space *mapping, block_t blkaddr, + pgoff_t index, int whence) { switch (whence) { case SEEK_DATA: - if ((blkaddr == NEW_ADDR && dirty == pgofs) || - __is_valid_data_blkaddr(blkaddr)) + if (__is_valid_data_blkaddr(blkaddr)) + return true; + if (blkaddr == NEW_ADDR && + xa_get_mark(&mapping->i_pages, index, PAGECACHE_TAG_DIRTY)) return true; break; case SEEK_HOLE: @@ -403,7 +417,7 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence) struct inode *inode = file->f_mapping->host; loff_t maxbytes = inode->i_sb->s_maxbytes; struct dnode_of_data dn; - pgoff_t pgofs, end_offset, dirty; + pgoff_t pgofs, end_offset; loff_t data_ofs = offset; loff_t isize; int err = 0; @@ -415,16 +429,18 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence) goto fail; /* handle inline data case */ - if (f2fs_has_inline_data(inode) || f2fs_has_inline_dentry(inode)) { - if (whence == SEEK_HOLE) + if (f2fs_has_inline_data(inode)) { + if (whence == SEEK_HOLE) { data_ofs = isize; - goto found; + goto found; + } else if (whence == SEEK_DATA) { + data_ofs = offset; + goto found; + } } pgofs = (pgoff_t)(offset >> PAGE_SHIFT); - dirty = __get_first_dirty_index(inode->i_mapping, pgofs, whence); - for (; data_ofs < isize; data_ofs = (loff_t)pgofs << PAGE_SHIFT) { set_new_dnode(&dn, inode, NULL, NULL, 0); err = f2fs_get_dnode_of_data(&dn, pgofs, LOOKUP_NODE); @@ -448,8 +464,7 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence) data_ofs = (loff_t)pgofs << PAGE_SHIFT) { block_t blkaddr; - blkaddr = datablock_addr(dn.inode, - dn.node_page, dn.ofs_in_node); + blkaddr = f2fs_data_blkaddr(&dn); if (__is_valid_data_blkaddr(blkaddr) && !f2fs_is_valid_blkaddr(F2FS_I_SB(inode), @@ -458,7 +473,7 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence) goto fail; } - if (__found_offset(F2FS_I_SB(inode), blkaddr, dirty, + if (__found_offset(file->f_mapping, blkaddr, pgofs, whence)) { f2fs_put_dnode(&dn); goto found; @@ -484,6 +499,9 @@ static loff_t f2fs_llseek(struct file *file, loff_t offset, int whence) struct inode *inode = file->f_mapping->host; loff_t maxbytes = inode->i_sb->s_maxbytes; + if (f2fs_compressed_file(inode)) + maxbytes = max_file_blocks(inode) << F2FS_BLKSIZE_BITS; + switch (whence) { case SEEK_SET: case SEEK_CUR: @@ -503,7 +521,6 @@ static loff_t f2fs_llseek(struct file *file, loff_t offset, int whence) static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma) { struct inode *inode = file_inode(file); - int err; if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) return -EIO; @@ -511,11 +528,6 @@ static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma) if (!f2fs_is_compress_backend_ready(inode)) return -EOPNOTSUPP; - /* we don't need to use inline_data strictly */ - err = f2fs_convert_inline_inode(inode); - if (err) - return err; - file_accessed(file); vma->vm_ops = &f2fs_file_vm_ops; set_inode_flag(inode, FI_MMAP_FILE); @@ -551,6 +563,7 @@ void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count) bool compressed_cluster = false; int cluster_index = 0, valid_blocks = 0; int cluster_size = F2FS_I(dn->inode)->i_cluster_size; + bool released = !atomic_read(&F2FS_I(dn->inode)->i_compr_blocks); if (IS_INODE(dn->node_page) && f2fs_has_extra_attr(dn->inode)) base = get_extra_isize(dn->inode); @@ -589,7 +602,9 @@ void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count) clear_inode_flag(dn->inode, FI_FIRST_BLOCK_WRITTEN); f2fs_invalidate_blocks(sbi, blkaddr); - nr_free++; + + if (!released || blkaddr != COMPRESS_ADDR) + nr_free++; } if (compressed_cluster) @@ -637,9 +652,6 @@ static int truncate_partial_data_page(struct inode *inode, u64 from, return 0; } - if (f2fs_compressed_file(inode)) - return 0; - page = f2fs_get_lock_data_page(inode, index, true); if (IS_ERR(page)) return PTR_ERR(page) == -ENOENT ? 0 : PTR_ERR(page); @@ -655,7 +667,7 @@ truncate_out: return 0; } -static int do_truncate_blocks(struct inode *inode, u64 from, bool lock) +int f2fs_do_truncate_blocks(struct inode *inode, u64 from, bool lock) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct dnode_of_data dn; @@ -668,7 +680,7 @@ static int do_truncate_blocks(struct inode *inode, u64 from, bool lock) free_from = (pgoff_t)F2FS_BLK_ALIGN(from); - if (free_from >= sbi->max_file_blocks) + if (free_from >= max_file_blocks(inode)) goto free_partial; if (lock) @@ -723,23 +735,39 @@ free_partial: int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock) { u64 free_from = from; + int err; +#ifdef CONFIG_F2FS_FS_COMPRESSION /* * for compressed file, only support cluster size * aligned truncation. */ - if (f2fs_compressed_file(inode)) { - size_t cluster_shift = PAGE_SHIFT + - F2FS_I(inode)->i_log_cluster_size; - size_t cluster_mask = (1 << cluster_shift) - 1; + if (f2fs_compressed_file(inode)) + free_from = round_up(from, + F2FS_I(inode)->i_cluster_size << PAGE_SHIFT); +#endif - free_from = from >> cluster_shift; - if (from & cluster_mask) - free_from++; - free_from <<= cluster_shift; + err = f2fs_do_truncate_blocks(inode, free_from, lock); + if (err) + return err; + +#ifdef CONFIG_F2FS_FS_COMPRESSION + /* + * For compressed file, after release compress blocks, don't allow write + * direct, but we should allow write direct after truncate to zero. + */ + if (f2fs_compressed_file(inode) && !free_from + && is_inode_flag_set(inode, FI_COMPRESS_RELEASED)) + clear_inode_flag(inode, FI_COMPRESS_RELEASED); + + if (from != free_from) { + err = f2fs_truncate_partial_cluster(inode, from, lock); + if (err) + return err; } +#endif - return do_truncate_blocks(inode, free_from, lock); + return 0; } int f2fs_truncate(struct inode *inode) @@ -760,6 +788,10 @@ int f2fs_truncate(struct inode *inode) return -EIO; } + err = f2fs_dquot_initialize(inode); + if (err) + return err; + /* we should check inline_data size */ if (!f2fs_may_inline_data(inode)) { err = f2fs_convert_inline_inode(inode); @@ -776,12 +808,40 @@ int f2fs_truncate(struct inode *inode) return 0; } -int f2fs_getattr(const struct path *path, struct kstat *stat, - u32 request_mask, unsigned int query_flags) +static bool f2fs_force_buffered_io(struct inode *inode, int rw) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + + if (!fscrypt_dio_supported(inode)) + return true; + if (fsverity_active(inode)) + return true; + if (f2fs_compressed_file(inode)) + return true; + + /* disallow direct IO if any of devices has unaligned blksize */ + if (f2fs_is_multi_device(sbi) && !sbi->aligned_blksize) + return true; + /* + * for blkzoned device, fallback direct IO to buffered IO, so + * all IOs can be serialized by log-structured write. + */ + if (f2fs_sb_has_blkzoned(sbi) && (rw == WRITE)) + return true; + if (f2fs_lfs_mode(sbi) && rw == WRITE && F2FS_IO_ALIGNED(sbi)) + return true; + if (is_sbi_flag_set(sbi, SBI_CP_DISABLED)) + return true; + + return false; +} + +int f2fs_getattr(struct user_namespace *mnt_userns, const struct path *path, + struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); struct f2fs_inode_info *fi = F2FS_I(inode); - struct f2fs_inode *ri; + struct f2fs_inode *ri = NULL; unsigned int flags; if (f2fs_has_extra_attr(inode) && @@ -792,7 +852,27 @@ int f2fs_getattr(const struct path *path, struct kstat *stat, stat->btime.tv_nsec = fi->i_crtime.tv_nsec; } + /* + * Return the DIO alignment restrictions if requested. We only return + * this information when requested, since on encrypted files it might + * take a fair bit of work to get if the file wasn't opened recently. + * + * f2fs sometimes supports DIO reads but not DIO writes. STATX_DIOALIGN + * cannot represent that, so in that case we report no DIO support. + */ + if ((request_mask & STATX_DIOALIGN) && S_ISREG(inode->i_mode)) { + unsigned int bsize = i_blocksize(inode); + + stat->result_mask |= STATX_DIOALIGN; + if (!f2fs_force_buffered_io(inode, WRITE)) { + stat->dio_mem_align = bsize; + stat->dio_offset_align = bsize; + } + } + flags = fi->i_flags; + if (flags & F2FS_COMPR_FL) + stat->attributes |= STATX_ATTR_COMPRESSED; if (flags & F2FS_APPEND_FL) stat->attributes |= STATX_ATTR_APPEND; if (IS_ENCRYPTED(inode)) @@ -804,13 +884,14 @@ int f2fs_getattr(const struct path *path, struct kstat *stat, if (IS_VERITY(inode)) stat->attributes |= STATX_ATTR_VERITY; - stat->attributes_mask |= (STATX_ATTR_APPEND | + stat->attributes_mask |= (STATX_ATTR_COMPRESSED | + STATX_ATTR_APPEND | STATX_ATTR_ENCRYPTED | STATX_ATTR_IMMUTABLE | STATX_ATTR_NODUMP | STATX_ATTR_VERITY); - generic_fillattr(inode, stat); + generic_fillattr(mnt_userns, inode, stat); /* we need to show initial sectors used for inline_data/dentries */ if ((S_ISREG(inode->i_mode) && f2fs_has_inline_data(inode)) || @@ -821,14 +902,13 @@ int f2fs_getattr(const struct path *path, struct kstat *stat, } #ifdef CONFIG_F2FS_FS_POSIX_ACL -static void __setattr_copy(struct inode *inode, const struct iattr *attr) +static void __setattr_copy(struct user_namespace *mnt_userns, + struct inode *inode, const struct iattr *attr) { unsigned int ia_valid = attr->ia_valid; - if (ia_valid & ATTR_UID) - inode->i_uid = attr->ia_uid; - if (ia_valid & ATTR_GID) - inode->i_gid = attr->ia_gid; + i_uid_update(mnt_userns, attr, inode); + i_gid_update(mnt_userns, attr, inode); if (ia_valid & ATTR_ATIME) inode->i_atime = attr->ia_atime; if (ia_valid & ATTR_MTIME) @@ -837,8 +917,10 @@ static void __setattr_copy(struct inode *inode, const struct iattr *attr) inode->i_ctime = attr->ia_ctime; if (ia_valid & ATTR_MODE) { umode_t mode = attr->ia_mode; + vfsgid_t vfsgid = i_gid_into_vfsgid(mnt_userns, inode); - if (!in_group_p(inode->i_gid) && !capable(CAP_FSETID)) + if (!vfsgid_in_group_p(vfsgid) && + !capable_wrt_inode_uidgid(mnt_userns, inode, CAP_FSETID)) mode &= ~S_ISGID; set_acl_inode(inode, mode); } @@ -847,7 +929,8 @@ static void __setattr_copy(struct inode *inode, const struct iattr *attr) #define __setattr_copy setattr_copy #endif -int f2fs_setattr(struct dentry *dentry, struct iattr *attr) +int f2fs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *attr) { struct inode *inode = d_inode(dentry); int err; @@ -855,11 +938,19 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr) if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) return -EIO; + if (unlikely(IS_IMMUTABLE(inode))) + return -EPERM; + + if (unlikely(IS_APPEND(inode) && + (attr->ia_valid & (ATTR_MODE | ATTR_UID | + ATTR_GID | ATTR_TIMES_SET)))) + return -EPERM; + if ((attr->ia_valid & ATTR_SIZE) && !f2fs_is_compress_backend_ready(inode)) return -EOPNOTSUPP; - err = setattr_prepare(dentry, attr); + err = setattr_prepare(mnt_userns, dentry, attr); if (err) return err; @@ -871,17 +962,15 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr) if (err) return err; - if (is_quota_modification(inode, attr)) { - err = dquot_initialize(inode); + if (is_quota_modification(mnt_userns, inode, attr)) { + err = f2fs_dquot_initialize(inode); if (err) return err; } - if ((attr->ia_valid & ATTR_UID && - !uid_eq(attr->ia_uid, inode->i_uid)) || - (attr->ia_valid & ATTR_GID && - !gid_eq(attr->ia_gid, inode->i_gid))) { + if (i_uid_needs_update(mnt_userns, attr, inode) || + i_gid_needs_update(mnt_userns, attr, inode)) { f2fs_lock_op(F2FS_I_SB(inode)); - err = dquot_transfer(inode, attr); + err = dquot_transfer(mnt_userns, inode, attr); if (err) { set_sbi_flag(F2FS_I_SB(inode), SBI_QUOTA_NEED_REPAIR); @@ -892,10 +981,8 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr) * update uid/gid under lock_op(), so that dquot and inode can * be updated atomically. */ - if (attr->ia_valid & ATTR_UID) - inode->i_uid = attr->ia_uid; - if (attr->ia_valid & ATTR_GID) - inode->i_gid = attr->ia_gid; + i_uid_update(mnt_userns, attr, inode); + i_gid_update(mnt_userns, attr, inode); f2fs_mark_inode_dirty_sync(inode, true); f2fs_unlock_op(F2FS_I_SB(inode)); } @@ -913,8 +1000,8 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr) return err; } - down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); - down_write(&F2FS_I(inode)->i_mmap_sem); + f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + filemap_invalidate_lock(inode->i_mapping); truncate_setsize(inode, attr->ia_size); @@ -924,23 +1011,25 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr) * do not trim all blocks after i_size if target size is * larger than i_size. */ - up_write(&F2FS_I(inode)->i_mmap_sem); - up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + filemap_invalidate_unlock(inode->i_mapping); + f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); if (err) return err; - down_write(&F2FS_I(inode)->i_sem); + spin_lock(&F2FS_I(inode)->i_size_lock); inode->i_mtime = inode->i_ctime = current_time(inode); F2FS_I(inode)->last_disk_size = i_size_read(inode); - up_write(&F2FS_I(inode)->i_sem); + spin_unlock(&F2FS_I(inode)->i_size_lock); } - __setattr_copy(inode, attr); + __setattr_copy(mnt_userns, inode, attr); if (attr->ia_valid & ATTR_MODE) { - err = posix_acl_chmod(inode, f2fs_get_inode_mode(inode)); - if (err || is_inode_flag_set(inode, FI_ACL_MODE)) { - inode->i_mode = F2FS_I(inode)->i_acl_mode; + err = posix_acl_chmod(mnt_userns, inode, f2fs_get_inode_mode(inode)); + + if (is_inode_flag_set(inode, FI_ACL_MODE)) { + if (!err) + inode->i_mode = F2FS_I(inode)->i_acl_mode; clear_inode_flag(inode, FI_ACL_MODE); } } @@ -959,10 +1048,10 @@ const struct inode_operations f2fs_file_inode_operations = { .setattr = f2fs_setattr, .get_acl = f2fs_get_acl, .set_acl = f2fs_set_acl, -#ifdef CONFIG_F2FS_FS_XATTR .listxattr = f2fs_listxattr, -#endif .fiemap = f2fs_fiemap, + .fileattr_get = f2fs_fileattr_get, + .fileattr_set = f2fs_fileattr_set, }; static int fill_zero(struct inode *inode, pgoff_t index, @@ -1057,7 +1146,6 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len) } if (pg_start < pg_end) { - struct address_space *mapping = inode->i_mapping; loff_t blk_start, blk_end; struct f2fs_sb_info *sbi = F2FS_I_SB(inode); @@ -1066,18 +1154,17 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len) blk_start = (loff_t)pg_start << PAGE_SHIFT; blk_end = (loff_t)pg_end << PAGE_SHIFT; - down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); - down_write(&F2FS_I(inode)->i_mmap_sem); + f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + filemap_invalidate_lock(inode->i_mapping); - truncate_inode_pages_range(mapping, blk_start, - blk_end - 1); + truncate_pagecache_range(inode, blk_start, blk_end - 1); f2fs_lock_op(sbi); ret = f2fs_truncate_hole(inode, pg_start, pg_end); f2fs_unlock_op(sbi); - up_write(&F2FS_I(inode)->i_mmap_sem); - up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + filemap_invalidate_unlock(inode->i_mapping); + f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); } } @@ -1109,19 +1196,19 @@ next_dnode: done = min((pgoff_t)ADDRS_PER_PAGE(dn.node_page, inode) - dn.ofs_in_node, len); for (i = 0; i < done; i++, blkaddr++, do_replace++, dn.ofs_in_node++) { - *blkaddr = datablock_addr(dn.inode, - dn.node_page, dn.ofs_in_node); + *blkaddr = f2fs_data_blkaddr(&dn); if (__is_valid_data_blkaddr(*blkaddr) && !f2fs_is_valid_blkaddr(sbi, *blkaddr, DATA_GENERIC_ENHANCE)) { f2fs_put_dnode(&dn); + f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR); return -EFSCORRUPTED; } if (!f2fs_is_checkpointed_data(sbi, *blkaddr)) { - if (test_opt(sbi, LFS)) { + if (f2fs_lfs_mode(sbi)) { f2fs_put_dnode(&dn); return -EOPNOTSUPP; } @@ -1189,7 +1276,7 @@ static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode, if (ret) return ret; - ret = f2fs_get_node_info(sbi, dn.nid, &ni); + ret = f2fs_get_node_info(sbi, dn.nid, &ni, false); if (ret) { f2fs_put_dnode(&dn); return ret; @@ -1199,8 +1286,7 @@ static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode, ADDRS_PER_PAGE(dn.node_page, dst_inode) - dn.ofs_in_node, len - i); do { - dn.data_blkaddr = datablock_addr(dn.inode, - dn.node_page, dn.ofs_in_node); + dn.data_blkaddr = f2fs_data_blkaddr(&dn); f2fs_truncate_data_blocks_range(&dn, 1); if (do_replace[i]) { @@ -1234,7 +1320,7 @@ static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode, f2fs_put_page(psrc, 1); return PTR_ERR(pdst); } - f2fs_copy_page(psrc, pdst); + memcpy_page(pdst, 0, psrc, 0, PAGE_SIZE); set_page_dirty(pdst); f2fs_put_page(pdst, 1); f2fs_put_page(psrc, 1); @@ -1312,8 +1398,8 @@ static int f2fs_do_collapse(struct inode *inode, loff_t offset, loff_t len) f2fs_balance_fs(sbi, true); /* avoid gc operation during block exchange */ - down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); - down_write(&F2FS_I(inode)->i_mmap_sem); + f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + filemap_invalidate_lock(inode->i_mapping); f2fs_lock_op(sbi); f2fs_drop_extent_tree(inode); @@ -1321,8 +1407,8 @@ static int f2fs_do_collapse(struct inode *inode, loff_t offset, loff_t len) ret = __exchange_data_block(inode, inode, end, start, nrpages - end, true); f2fs_unlock_op(sbi); - up_write(&F2FS_I(inode)->i_mmap_sem); - up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + filemap_invalidate_unlock(inode->i_mapping); + f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); return ret; } @@ -1352,15 +1438,13 @@ static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len) return ret; /* write out all moved pages, if possible */ - down_write(&F2FS_I(inode)->i_mmap_sem); + filemap_invalidate_lock(inode->i_mapping); filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX); truncate_pagecache(inode, offset); new_size = i_size_read(inode) - len; - truncate_pagecache(inode, new_size); - ret = f2fs_truncate_blocks(inode, new_size, true); - up_write(&F2FS_I(inode)->i_mmap_sem); + filemap_invalidate_unlock(inode->i_mapping); if (!ret) f2fs_i_size_write(inode, new_size); return ret; @@ -1376,8 +1460,7 @@ static int f2fs_do_zero_range(struct dnode_of_data *dn, pgoff_t start, int ret; for (; index < end; index++, dn->ofs_in_node++) { - if (datablock_addr(dn->inode, dn->node_page, - dn->ofs_in_node) == NULL_ADDR) + if (f2fs_data_blkaddr(dn) == NULL_ADDR) count++; } @@ -1388,8 +1471,7 @@ static int f2fs_do_zero_range(struct dnode_of_data *dn, pgoff_t start, dn->ofs_in_node = ofs_in_node; for (index = start; index < end; index++, dn->ofs_in_node++) { - dn->data_blkaddr = datablock_addr(dn->inode, - dn->node_page, dn->ofs_in_node); + dn->data_blkaddr = f2fs_data_blkaddr(dn); /* * f2fs_reserve_new_blocks will not guarantee entire block * allocation. @@ -1398,11 +1480,20 @@ static int f2fs_do_zero_range(struct dnode_of_data *dn, pgoff_t start, ret = -ENOSPC; break; } - if (dn->data_blkaddr != NEW_ADDR) { - f2fs_invalidate_blocks(sbi, dn->data_blkaddr); - dn->data_blkaddr = NEW_ADDR; - f2fs_set_data_blkaddr(dn); + + if (dn->data_blkaddr == NEW_ADDR) + continue; + + if (!f2fs_is_valid_blkaddr(sbi, dn->data_blkaddr, + DATA_GENERIC_ENHANCE)) { + ret = -EFSCORRUPTED; + f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR); + break; } + + f2fs_invalidate_blocks(sbi, dn->data_blkaddr); + dn->data_blkaddr = NEW_ADDR; + f2fs_set_data_blkaddr(dn); } f2fs_update_extent_cache_range(dn, start, 0, index - start); @@ -1461,8 +1552,8 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len, unsigned int end_offset; pgoff_t end; - down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); - down_write(&F2FS_I(inode)->i_mmap_sem); + f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + filemap_invalidate_lock(mapping); truncate_pagecache_range(inode, (loff_t)index << PAGE_SHIFT, @@ -1474,8 +1565,8 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len, ret = f2fs_get_dnode_of_data(&dn, index, ALLOC_NODE); if (ret) { f2fs_unlock_op(sbi); - up_write(&F2FS_I(inode)->i_mmap_sem); - up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + filemap_invalidate_unlock(mapping); + f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); goto out; } @@ -1486,8 +1577,8 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len, f2fs_put_dnode(&dn); f2fs_unlock_op(sbi); - up_write(&F2FS_I(inode)->i_mmap_sem); - up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + filemap_invalidate_unlock(mapping); + f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); f2fs_balance_fs(sbi, dn.node_changed); @@ -1521,6 +1612,7 @@ out: static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct address_space *mapping = inode->i_mapping; pgoff_t nr, pg_start, pg_end, delta, idx; loff_t new_size; int ret = 0; @@ -1543,14 +1635,14 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len) f2fs_balance_fs(sbi, true); - down_write(&F2FS_I(inode)->i_mmap_sem); + filemap_invalidate_lock(mapping); ret = f2fs_truncate_blocks(inode, i_size_read(inode), true); - up_write(&F2FS_I(inode)->i_mmap_sem); + filemap_invalidate_unlock(mapping); if (ret) return ret; /* write out all dirty pages from offset */ - ret = filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX); + ret = filemap_write_and_wait_range(mapping, offset, LLONG_MAX); if (ret) return ret; @@ -1560,8 +1652,8 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len) idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); /* avoid gc operation during block exchange */ - down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); - down_write(&F2FS_I(inode)->i_mmap_sem); + f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + filemap_invalidate_lock(mapping); truncate_pagecache(inode, offset); while (!ret && idx > pg_start) { @@ -1577,14 +1669,14 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len) idx + delta, nr, false); f2fs_unlock_op(sbi); } - up_write(&F2FS_I(inode)->i_mmap_sem); - up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + filemap_invalidate_unlock(mapping); + f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); /* write out all moved pages, if possible */ - down_write(&F2FS_I(inode)->i_mmap_sem); - filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX); + filemap_invalidate_lock(mapping); + filemap_write_and_wait_range(mapping, offset, LLONG_MAX); truncate_pagecache(inode, offset); - up_write(&F2FS_I(inode)->i_mmap_sem); + filemap_invalidate_unlock(mapping); if (!ret) f2fs_i_size_write(inode, new_size); @@ -1598,9 +1690,15 @@ static int expand_inode_data(struct inode *inode, loff_t offset, struct f2fs_map_blocks map = { .m_next_pgofs = NULL, .m_next_extent = NULL, .m_seg_type = NO_CHECK_TYPE, .m_may_create = true }; - pgoff_t pg_end; + struct f2fs_gc_control gc_control = { .victim_segno = NULL_SEGNO, + .init_gc_type = FG_GC, + .should_migrate_blocks = false, + .err_gc_skipped = true, + .nr_free_secs = 0 }; + pgoff_t pg_start, pg_end; loff_t new_size = i_size_read(inode); loff_t off_end; + block_t expanded = 0; int err; err = inode_newsize_ok(inode, (len + offset)); @@ -1613,11 +1711,12 @@ static int expand_inode_data(struct inode *inode, loff_t offset, f2fs_balance_fs(sbi, true); + pg_start = ((unsigned long long)offset) >> PAGE_SHIFT; pg_end = ((unsigned long long)offset + len) >> PAGE_SHIFT; off_end = (offset + len) & (PAGE_SIZE - 1); - map.m_lblk = ((unsigned long long)offset) >> PAGE_SHIFT; - map.m_len = pg_end - map.m_lblk; + map.m_lblk = pg_start; + map.m_len = pg_end - pg_start; if (off_end) map.m_len++; @@ -1625,47 +1724,50 @@ static int expand_inode_data(struct inode *inode, loff_t offset, return 0; if (f2fs_is_pinned_file(inode)) { - block_t len = (map.m_len >> sbi->log_blocks_per_seg) << - sbi->log_blocks_per_seg; - block_t done = 0; - - if (map.m_len % sbi->blocks_per_seg) - len += sbi->blocks_per_seg; + block_t sec_blks = CAP_BLKS_PER_SEC(sbi); + block_t sec_len = roundup(map.m_len, sec_blks); - map.m_len = sbi->blocks_per_seg; + map.m_len = sec_blks; next_alloc: if (has_not_enough_free_secs(sbi, 0, GET_SEC_FROM_SEG(sbi, overprovision_segments(sbi)))) { - down_write(&sbi->gc_lock); - err = f2fs_gc(sbi, true, false, NULL_SEGNO); - if (err && err != -ENODATA && err != -EAGAIN) + f2fs_down_write(&sbi->gc_lock); + err = f2fs_gc(sbi, &gc_control); + if (err && err != -ENODATA) goto out_err; } - down_write(&sbi->pin_sem); + f2fs_down_write(&sbi->pin_sem); + + f2fs_lock_op(sbi); + f2fs_allocate_new_section(sbi, CURSEG_COLD_DATA_PINNED, false); + f2fs_unlock_op(sbi); + map.m_seg_type = CURSEG_COLD_DATA_PINNED; - f2fs_allocate_new_segments(sbi, CURSEG_COLD_DATA); err = f2fs_map_blocks(inode, &map, 1, F2FS_GET_BLOCK_PRE_DIO); - up_write(&sbi->pin_sem); + file_dont_truncate(inode); + + f2fs_up_write(&sbi->pin_sem); - done += map.m_len; - len -= map.m_len; + expanded += map.m_len; + sec_len -= map.m_len; map.m_lblk += map.m_len; - if (!err && len) + if (!err && sec_len) goto next_alloc; - map.m_len = done; + map.m_len = expanded; } else { err = f2fs_map_blocks(inode, &map, 1, F2FS_GET_BLOCK_PRE_AIO); + expanded = map.m_len; } out_err: if (err) { pgoff_t last_off; - if (!map.m_len) + if (!expanded) return err; - last_off = map.m_lblk + map.m_len - 1; + last_off = pg_start + expanded - 1; /* update new size to the failed position */ new_size = (last_off == pg_end) ? offset + len : @@ -1705,7 +1807,11 @@ static long f2fs_fallocate(struct file *file, int mode, (mode & (FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_INSERT_RANGE))) return -EOPNOTSUPP; - if (f2fs_compressed_file(inode) && + /* + * Pinned file should not support partial trucation since the block + * can be used by applications. + */ + if ((f2fs_compressed_file(inode) || f2fs_is_pinned_file(inode)) && (mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE | FALLOC_FL_INSERT_RANGE))) return -EOPNOTSUPP; @@ -1717,6 +1823,10 @@ static long f2fs_fallocate(struct file *file, int mode, inode_lock(inode); + ret = file_modified(file); + if (ret) + goto out; + if (mode & FALLOC_FL_PUNCH_HOLE) { if (offset >= inode->i_size) goto out; @@ -1755,16 +1865,7 @@ static int f2fs_release_file(struct inode *inode, struct file *filp) atomic_read(&inode->i_writecount) != 1) return 0; - /* some remained atomic pages should discarded */ - if (f2fs_is_atomic_file(inode)) - f2fs_drop_inmem_pages(inode); - if (f2fs_is_volatile_file(inode)) { - set_inode_flag(inode, FI_DROP_CACHE); - filemap_fdatawrite(inode->i_mapping); - clear_inode_flag(inode, FI_DROP_CACHE); - clear_inode_flag(inode, FI_VOLATILE_FILE); - stat_dec_volatile_write(inode); - } + f2fs_abort_atomic_write(inode, true); return 0; } @@ -1778,21 +1879,24 @@ static int f2fs_file_flush(struct file *file, fl_owner_t id) * until all the writers close its file. Since this should be done * before dropping file lock, it needs to do in ->flush. */ - if (f2fs_is_atomic_file(inode) && - F2FS_I(inode)->inmem_task == current) - f2fs_drop_inmem_pages(inode); + if (F2FS_I(inode)->atomic_write_task == current) + f2fs_abort_atomic_write(inode, true); return 0; } static int f2fs_setflags_common(struct inode *inode, u32 iflags, u32 mask) { struct f2fs_inode_info *fi = F2FS_I(inode); + u32 masked_flags = fi->i_flags & mask; + + /* mask can be shrunk by flags_valid selector */ + iflags &= mask; /* Is it quota file? Do not allow user to mess with it */ if (IS_NOQUOTA(inode)) return -EPERM; - if ((iflags ^ fi->i_flags) & F2FS_CASEFOLD_FL) { + if ((iflags ^ masked_flags) & F2FS_CASEFOLD_FL) { if (!f2fs_sb_has_casefold(F2FS_I_SB(inode))) return -EOPNOTSUPP; if (!f2fs_empty_dir(inode)) @@ -1806,29 +1910,19 @@ static int f2fs_setflags_common(struct inode *inode, u32 iflags, u32 mask) return -EINVAL; } - if ((iflags ^ fi->i_flags) & F2FS_COMPR_FL) { - if (S_ISREG(inode->i_mode) && - (fi->i_flags & F2FS_COMPR_FL || i_size_read(inode) || - F2FS_HAS_BLOCKS(inode))) - return -EINVAL; - if (iflags & F2FS_NOCOMP_FL) - return -EINVAL; - if (iflags & F2FS_COMPR_FL) { - int err = f2fs_convert_inline_inode(inode); - - if (err) - return err; - + if ((iflags ^ masked_flags) & F2FS_COMPR_FL) { + if (masked_flags & F2FS_COMPR_FL) { + if (!f2fs_disable_compressed_file(inode)) + return -EINVAL; + } else { if (!f2fs_may_compress(inode)) return -EINVAL; - - set_compress_context(inode); + if (S_ISREG(inode->i_mode) && F2FS_HAS_BLOCKS(inode)) + return -EINVAL; + if (set_compress_context(inode)) + return -EOPNOTSUPP; } } - if ((iflags ^ fi->i_flags) & F2FS_NOCOMP_FL) { - if (fi->i_flags & F2FS_COMPR_FL) - return -EINVAL; - } fi->i_flags = iflags | (fi->i_flags & ~mask); f2fs_bug_on(F2FS_I_SB(inode), (fi->i_flags & F2FS_COMPR_FL) && @@ -1845,13 +1939,16 @@ static int f2fs_setflags_common(struct inode *inode, u32 iflags, u32 mask) return 0; } -/* FS_IOC_GETFLAGS and FS_IOC_SETFLAGS support */ +/* FS_IOC_[GS]ETFLAGS and FS_IOC_FS[GS]ETXATTR support */ /* * To make a new on-disk f2fs i_flag gettable via FS_IOC_GETFLAGS, add an entry * for it to f2fs_fsflags_map[], and add its FS_*_FL equivalent to * F2FS_GETTABLE_FS_FL. To also make it settable via FS_IOC_SETFLAGS, also add * its FS_*_FL equivalent to F2FS_SETTABLE_FS_FL. + * + * Translating flags to fsx_flags value used by FS_IOC_FSGETXATTR and + * FS_IOC_FSSETXATTR is done by the VFS. */ static const struct { @@ -1926,67 +2023,6 @@ static inline u32 f2fs_fsflags_to_iflags(u32 fsflags) return iflags; } -static int f2fs_ioc_getflags(struct file *filp, unsigned long arg) -{ - struct inode *inode = file_inode(filp); - struct f2fs_inode_info *fi = F2FS_I(inode); - u32 fsflags = f2fs_iflags_to_fsflags(fi->i_flags); - - if (IS_ENCRYPTED(inode)) - fsflags |= FS_ENCRYPT_FL; - if (IS_VERITY(inode)) - fsflags |= FS_VERITY_FL; - if (f2fs_has_inline_data(inode) || f2fs_has_inline_dentry(inode)) - fsflags |= FS_INLINE_DATA_FL; - if (is_inode_flag_set(inode, FI_PIN_FILE)) - fsflags |= FS_NOCOW_FL; - - fsflags &= F2FS_GETTABLE_FS_FL; - - return put_user(fsflags, (int __user *)arg); -} - -static int f2fs_ioc_setflags(struct file *filp, unsigned long arg) -{ - struct inode *inode = file_inode(filp); - struct f2fs_inode_info *fi = F2FS_I(inode); - u32 fsflags, old_fsflags; - u32 iflags; - int ret; - - if (!inode_owner_or_capable(inode)) - return -EACCES; - - if (get_user(fsflags, (int __user *)arg)) - return -EFAULT; - - if (fsflags & ~F2FS_GETTABLE_FS_FL) - return -EOPNOTSUPP; - fsflags &= F2FS_SETTABLE_FS_FL; - - iflags = f2fs_fsflags_to_iflags(fsflags); - if (f2fs_mask_flags(inode->i_mode, iflags) != iflags) - return -EOPNOTSUPP; - - ret = mnt_want_write_file(filp); - if (ret) - return ret; - - inode_lock(inode); - - old_fsflags = f2fs_iflags_to_fsflags(fi->i_flags); - ret = vfs_ioc_setflags_prepare(inode, old_fsflags, fsflags); - if (ret) - goto out; - - ret = f2fs_setflags_common(inode, iflags, - f2fs_fsflags_to_iflags(F2FS_SETTABLE_FS_FL)); -out: - inode_unlock(inode); - mnt_drop_write_file(filp); - return ret; -} - static int f2fs_ioc_getversion(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); @@ -1997,11 +2033,13 @@ static int f2fs_ioc_getversion(struct file *filp, unsigned long arg) static int f2fs_ioc_start_atomic_write(struct file *filp) { struct inode *inode = file_inode(filp); + struct user_namespace *mnt_userns = file_mnt_user_ns(filp); struct f2fs_inode_info *fi = F2FS_I(inode); struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct inode *pinode; int ret; - if (!inode_owner_or_capable(inode)) + if (!inode_owner_or_capable(mnt_userns, inode)) return -EACCES; if (!S_ISREG(inode->i_mode)) @@ -2016,47 +2054,60 @@ static int f2fs_ioc_start_atomic_write(struct file *filp) inode_lock(inode); - f2fs_disable_compressed_file(inode); - - if (f2fs_is_atomic_file(inode)) { - if (is_inode_flag_set(inode, FI_ATOMIC_REVOKE_REQUEST)) - ret = -EINVAL; + if (!f2fs_disable_compressed_file(inode)) { + ret = -EINVAL; goto out; } + if (f2fs_is_atomic_file(inode)) + goto out; + ret = f2fs_convert_inline_inode(inode); if (ret) goto out; - down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + f2fs_down_write(&fi->i_gc_rwsem[WRITE]); /* * Should wait end_io to count F2FS_WB_CP_DATA correctly by * f2fs_is_atomic_file. */ if (get_dirty_pages(inode)) - f2fs_warn(F2FS_I_SB(inode), "Unexpected flush for atomic writes: ino=%lu, npages=%u", + f2fs_warn(sbi, "Unexpected flush for atomic writes: ino=%lu, npages=%u", inode->i_ino, get_dirty_pages(inode)); ret = filemap_write_and_wait_range(inode->i_mapping, 0, LLONG_MAX); if (ret) { - up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + f2fs_up_write(&fi->i_gc_rwsem[WRITE]); goto out; } - spin_lock(&sbi->inode_lock[ATOMIC_FILE]); - if (list_empty(&fi->inmem_ilist)) - list_add_tail(&fi->inmem_ilist, &sbi->inode_list[ATOMIC_FILE]); - sbi->atomic_files++; - spin_unlock(&sbi->inode_lock[ATOMIC_FILE]); + /* Create a COW inode for atomic write */ + pinode = f2fs_iget(inode->i_sb, fi->i_pino); + if (IS_ERR(pinode)) { + f2fs_up_write(&fi->i_gc_rwsem[WRITE]); + ret = PTR_ERR(pinode); + goto out; + } + + ret = f2fs_get_tmpfile(mnt_userns, pinode, &fi->cow_inode); + iput(pinode); + if (ret) { + f2fs_up_write(&fi->i_gc_rwsem[WRITE]); + goto out; + } + f2fs_i_size_write(fi->cow_inode, i_size_read(inode)); + + stat_inc_atomic_inode(inode); - /* add inode in inmem_list first and set atomic_file */ set_inode_flag(inode, FI_ATOMIC_FILE); - clear_inode_flag(inode, FI_ATOMIC_REVOKE_REQUEST); - up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + set_inode_flag(fi->cow_inode, FI_COW_FILE); + clear_inode_flag(fi->cow_inode, FI_INLINE_DATA); + f2fs_up_write(&fi->i_gc_rwsem[WRITE]); - f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); - F2FS_I(inode)->inmem_task = current; + f2fs_update_time(sbi, REQ_TIME); + fi->atomic_write_task = current; stat_update_max_atomic_write(inode); + fi->atomic_write_cnt = 0; out: inode_unlock(inode); mnt_drop_write_file(filp); @@ -2066,9 +2117,10 @@ out: static int f2fs_ioc_commit_atomic_write(struct file *filp) { struct inode *inode = file_inode(filp); + struct user_namespace *mnt_userns = file_mnt_user_ns(filp); int ret; - if (!inode_owner_or_capable(inode)) + if (!inode_owner_or_capable(mnt_userns, inode)) return -EACCES; ret = mnt_want_write_file(filp); @@ -2079,119 +2131,39 @@ static int f2fs_ioc_commit_atomic_write(struct file *filp) inode_lock(inode); - if (f2fs_is_volatile_file(inode)) { - ret = -EINVAL; - goto err_out; - } - if (f2fs_is_atomic_file(inode)) { - ret = f2fs_commit_inmem_pages(inode); + ret = f2fs_commit_atomic_write(inode); if (ret) - goto err_out; + goto unlock_out; ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true); if (!ret) - f2fs_drop_inmem_pages(inode); + f2fs_abort_atomic_write(inode, false); } else { ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 1, false); } -err_out: - if (is_inode_flag_set(inode, FI_ATOMIC_REVOKE_REQUEST)) { - clear_inode_flag(inode, FI_ATOMIC_REVOKE_REQUEST); - ret = -EINVAL; - } +unlock_out: inode_unlock(inode); mnt_drop_write_file(filp); return ret; } -static int f2fs_ioc_start_volatile_write(struct file *filp) +static int f2fs_ioc_abort_atomic_write(struct file *filp) { struct inode *inode = file_inode(filp); + struct user_namespace *mnt_userns = file_mnt_user_ns(filp); int ret; - if (!inode_owner_or_capable(inode)) + if (!inode_owner_or_capable(mnt_userns, inode)) return -EACCES; - if (!S_ISREG(inode->i_mode)) - return -EINVAL; - ret = mnt_want_write_file(filp); if (ret) return ret; inode_lock(inode); - if (f2fs_is_volatile_file(inode)) - goto out; - - ret = f2fs_convert_inline_inode(inode); - if (ret) - goto out; - - stat_inc_volatile_write(inode); - stat_update_max_volatile_write(inode); - - set_inode_flag(inode, FI_VOLATILE_FILE); - f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); -out: - inode_unlock(inode); - mnt_drop_write_file(filp); - return ret; -} - -static int f2fs_ioc_release_volatile_write(struct file *filp) -{ - struct inode *inode = file_inode(filp); - int ret; - - if (!inode_owner_or_capable(inode)) - return -EACCES; - - ret = mnt_want_write_file(filp); - if (ret) - return ret; - - inode_lock(inode); - - if (!f2fs_is_volatile_file(inode)) - goto out; - - if (!f2fs_is_first_block_written(inode)) { - ret = truncate_partial_data_page(inode, 0, true); - goto out; - } - - ret = punch_hole(inode, 0, F2FS_BLKSIZE); -out: - inode_unlock(inode); - mnt_drop_write_file(filp); - return ret; -} - -static int f2fs_ioc_abort_volatile_write(struct file *filp) -{ - struct inode *inode = file_inode(filp); - int ret; - - if (!inode_owner_or_capable(inode)) - return -EACCES; - - ret = mnt_want_write_file(filp); - if (ret) - return ret; - - inode_lock(inode); - - if (f2fs_is_atomic_file(inode)) - f2fs_drop_inmem_pages(inode); - if (f2fs_is_volatile_file(inode)) { - clear_inode_flag(inode, FI_VOLATILE_FILE); - stat_dec_volatile_write(inode); - ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true); - } - - clear_inode_flag(inode, FI_ATOMIC_REVOKE_REQUEST); + f2fs_abort_atomic_write(inode, true); inode_unlock(inode); @@ -2216,38 +2188,42 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg) if (in != F2FS_GOING_DOWN_FULLSYNC) { ret = mnt_want_write_file(filp); - if (ret) + if (ret) { + if (ret == -EROFS) { + ret = 0; + f2fs_stop_checkpoint(sbi, false, + STOP_CP_REASON_SHUTDOWN); + set_sbi_flag(sbi, SBI_IS_SHUTDOWN); + trace_f2fs_shutdown(sbi, in, ret); + } return ret; + } } switch (in) { case F2FS_GOING_DOWN_FULLSYNC: - sb = freeze_bdev(sb->s_bdev); - if (IS_ERR(sb)) { - ret = PTR_ERR(sb); + ret = freeze_bdev(sb->s_bdev); + if (ret) goto out; - } - if (sb) { - f2fs_stop_checkpoint(sbi, false); - set_sbi_flag(sbi, SBI_IS_SHUTDOWN); - thaw_bdev(sb->s_bdev, sb); - } + f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_SHUTDOWN); + set_sbi_flag(sbi, SBI_IS_SHUTDOWN); + thaw_bdev(sb->s_bdev); break; case F2FS_GOING_DOWN_METASYNC: /* do checkpoint only */ ret = f2fs_sync_fs(sb, 1); if (ret) goto out; - f2fs_stop_checkpoint(sbi, false); + f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_SHUTDOWN); set_sbi_flag(sbi, SBI_IS_SHUTDOWN); break; case F2FS_GOING_DOWN_NOSYNC: - f2fs_stop_checkpoint(sbi, false); + f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_SHUTDOWN); set_sbi_flag(sbi, SBI_IS_SHUTDOWN); break; case F2FS_GOING_DOWN_METAFLUSH: f2fs_sync_meta_pages(sbi, META, LONG_MAX, FS_META_IO); - f2fs_stop_checkpoint(sbi, false); + f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_SHUTDOWN); set_sbi_flag(sbi, SBI_IS_SHUTDOWN); break; case F2FS_GOING_DOWN_NEED_FSCK: @@ -2282,7 +2258,6 @@ static int f2fs_ioc_fitrim(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); struct super_block *sb = inode->i_sb; - struct request_queue *q = bdev_get_queue(sb->s_bdev); struct fstrim_range range; int ret; @@ -2301,7 +2276,7 @@ static int f2fs_ioc_fitrim(struct file *filp, unsigned long arg) return ret; range.minlen = max((unsigned int)range.minlen, - q->limits.discard_granularity); + bdev_discard_granularity(sb->s_bdev)); ret = f2fs_trim_fs(F2FS_SB(sb), &range); mnt_drop_write_file(filp); if (ret < 0) @@ -2356,7 +2331,7 @@ static int f2fs_ioc_get_encryption_pwsalt(struct file *filp, unsigned long arg) if (err) return err; - down_write(&sbi->sb_lock); + f2fs_down_write(&sbi->sb_lock); if (uuid_is_nonzero(sbi->raw_super->encrypt_pw_salt)) goto got_it; @@ -2375,7 +2350,7 @@ got_it: 16)) err = -EFAULT; out_err: - up_write(&sbi->sb_lock); + f2fs_up_write(&sbi->sb_lock); mnt_drop_write_file(filp); return err; } @@ -2423,10 +2398,22 @@ static int f2fs_ioc_get_encryption_key_status(struct file *filp, return fscrypt_ioctl_get_key_status(filp, (void __user *)arg); } +static int f2fs_ioc_get_encryption_nonce(struct file *filp, unsigned long arg) +{ + if (!f2fs_sb_has_encrypt(F2FS_I_SB(file_inode(filp)))) + return -EOPNOTSUPP; + + return fscrypt_ioctl_get_nonce(filp, (void __user *)arg); +} + static int f2fs_ioc_gc(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct f2fs_gc_control gc_control = { .victim_segno = NULL_SEGNO, + .no_bg_gc = false, + .should_migrate_blocks = false, + .nr_free_secs = 0 }; __u32 sync; int ret; @@ -2444,40 +2431,41 @@ static int f2fs_ioc_gc(struct file *filp, unsigned long arg) return ret; if (!sync) { - if (!down_write_trylock(&sbi->gc_lock)) { + if (!f2fs_down_write_trylock(&sbi->gc_lock)) { ret = -EBUSY; goto out; } } else { - down_write(&sbi->gc_lock); + f2fs_down_write(&sbi->gc_lock); } - ret = f2fs_gc(sbi, sync, true, NULL_SEGNO); + gc_control.init_gc_type = sync ? FG_GC : BG_GC; + gc_control.err_gc_skipped = sync; + ret = f2fs_gc(sbi, &gc_control); out: mnt_drop_write_file(filp); return ret; } -static int f2fs_ioc_gc_range(struct file *filp, unsigned long arg) +static int __f2fs_ioc_gc_range(struct file *filp, struct f2fs_gc_range *range) { - struct inode *inode = file_inode(filp); - struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - struct f2fs_gc_range range; + struct f2fs_sb_info *sbi = F2FS_I_SB(file_inode(filp)); + struct f2fs_gc_control gc_control = { + .init_gc_type = range->sync ? FG_GC : BG_GC, + .no_bg_gc = false, + .should_migrate_blocks = false, + .err_gc_skipped = range->sync, + .nr_free_secs = 0 }; u64 end; int ret; if (!capable(CAP_SYS_ADMIN)) return -EPERM; - - if (copy_from_user(&range, (struct f2fs_gc_range __user *)arg, - sizeof(range))) - return -EFAULT; - if (f2fs_readonly(sbi->sb)) return -EROFS; - end = range.start + range.len; - if (end < range.start || range.start < MAIN_BLKADDR(sbi) || + end = range->start + range->len; + if (end < range->start || range->start < MAIN_BLKADDR(sbi) || end >= MAX_BLKADDR(sbi)) return -EINVAL; @@ -2486,24 +2474,40 @@ static int f2fs_ioc_gc_range(struct file *filp, unsigned long arg) return ret; do_more: - if (!range.sync) { - if (!down_write_trylock(&sbi->gc_lock)) { + if (!range->sync) { + if (!f2fs_down_write_trylock(&sbi->gc_lock)) { ret = -EBUSY; goto out; } } else { - down_write(&sbi->gc_lock); + f2fs_down_write(&sbi->gc_lock); } - ret = f2fs_gc(sbi, range.sync, true, GET_SEGNO(sbi, range.start)); - range.start += BLKS_PER_SEC(sbi); - if (range.start <= end) + gc_control.victim_segno = GET_SEGNO(sbi, range->start); + ret = f2fs_gc(sbi, &gc_control); + if (ret) { + if (ret == -EBUSY) + ret = -EAGAIN; + goto out; + } + range->start += CAP_BLKS_PER_SEC(sbi); + if (range->start <= end) goto do_more; out: mnt_drop_write_file(filp); return ret; } +static int f2fs_ioc_gc_range(struct file *filp, unsigned long arg) +{ + struct f2fs_gc_range range; + + if (copy_from_user(&range, (struct f2fs_gc_range __user *)arg, + sizeof(range))) + return -EFAULT; + return __f2fs_ioc_gc_range(filp, &range); +} + static int f2fs_ioc_write_checkpoint(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); @@ -2537,7 +2541,7 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi, { struct inode *inode = file_inode(filp); struct f2fs_map_blocks map = { .m_next_extent = NULL, - .m_seg_type = NO_CHECK_TYPE , + .m_seg_type = NO_CHECK_TYPE, .m_may_create = false }; struct extent_info ei = {0, 0, 0}; pgoff_t pg_start, pg_end, next_pgofs; @@ -2547,10 +2551,6 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi, bool fragmented = false; int err; - /* if in-place-update policy is enabled, don't waste time here */ - if (f2fs_should_update_inplace(inode, NULL)) - return -EINVAL; - pg_start = range->start >> PAGE_SHIFT; pg_end = (range->start + range->len) >> PAGE_SHIFT; @@ -2558,6 +2558,13 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi, inode_lock(inode); + /* if in-place-update policy is enabled, don't waste time here */ + set_inode_flag(inode, FI_OPU_WRITE); + if (f2fs_should_update_inplace(inode, NULL)) { + err = -EINVAL; + goto out; + } + /* writeback all dirty pages in the range */ err = filemap_write_and_wait_range(inode->i_mapping, range->start, range->start + range->len - 1); @@ -2608,7 +2615,7 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi, goto out; } - sec_num = DIV_ROUND_UP(total, BLKS_PER_SEC(sbi)); + sec_num = DIV_ROUND_UP(total, CAP_BLKS_PER_SEC(sbi)); /* * make sure there are enough free section for LFS allocation, this can @@ -2639,7 +2646,7 @@ do_map: goto check; } - set_inode_flag(inode, FI_DO_DEFRAG); + set_inode_flag(inode, FI_SKIP_WRITES); idx = map.m_lblk; while (idx < map.m_lblk + map.m_len && cnt < blk_per_seg) { @@ -2652,6 +2659,7 @@ do_map: } set_page_dirty(page); + set_page_private_gcing(page); f2fs_put_page(page, 1); idx++; @@ -2664,15 +2672,16 @@ check: if (map.m_lblk < pg_end && cnt < blk_per_seg) goto do_map; - clear_inode_flag(inode, FI_DO_DEFRAG); + clear_inode_flag(inode, FI_SKIP_WRITES); err = filemap_fdatawrite(inode->i_mapping); if (err) goto out; } clear_out: - clear_inode_flag(inode, FI_DO_DEFRAG); + clear_inode_flag(inode, FI_SKIP_WRITES); out: + clear_inode_flag(inode, FI_OPU_WRITE); inode_unlock(inode); if (!err) range->len = (u64)total << PAGE_SHIFT; @@ -2704,7 +2713,7 @@ static int f2fs_ioc_defragment(struct file *filp, unsigned long arg) return -EINVAL; if (unlikely((range.start + range.len) >> PAGE_SHIFT > - sbi->max_file_blocks)) + max_file_blocks(inode))) return -EINVAL; err = mnt_want_write_file(filp); @@ -2748,6 +2757,9 @@ static int f2fs_move_file_range(struct file *file_in, loff_t pos_in, if (IS_ENCRYPTED(src) || IS_ENCRYPTED(dst)) return -EOPNOTSUPP; + if (pos_out < 0 || pos_in < 0) + return -EINVAL; + if (src == dst) { if (pos_in == pos_out) return 0; @@ -2805,10 +2817,10 @@ static int f2fs_move_file_range(struct file *file_in, loff_t pos_in, f2fs_balance_fs(sbi, true); - down_write(&F2FS_I(src)->i_gc_rwsem[WRITE]); + f2fs_down_write(&F2FS_I(src)->i_gc_rwsem[WRITE]); if (src != dst) { ret = -EBUSY; - if (!down_write_trylock(&F2FS_I(dst)->i_gc_rwsem[WRITE])) + if (!f2fs_down_write_trylock(&F2FS_I(dst)->i_gc_rwsem[WRITE])) goto out_src; } @@ -2826,9 +2838,9 @@ static int f2fs_move_file_range(struct file *file_in, loff_t pos_in, f2fs_unlock_op(sbi); if (src != dst) - up_write(&F2FS_I(dst)->i_gc_rwsem[WRITE]); + f2fs_up_write(&F2FS_I(dst)->i_gc_rwsem[WRITE]); out_src: - up_write(&F2FS_I(src)->i_gc_rwsem[WRITE]); + f2fs_up_write(&F2FS_I(src)->i_gc_rwsem[WRITE]); out_unlock: if (src != dst) inode_unlock(dst); @@ -2837,9 +2849,9 @@ out: return ret; } -static int f2fs_ioc_move_range(struct file *filp, unsigned long arg) +static int __f2fs_ioc_move_range(struct file *filp, + struct f2fs_move_range *range) { - struct f2fs_move_range range; struct fd dst; int err; @@ -2847,11 +2859,7 @@ static int f2fs_ioc_move_range(struct file *filp, unsigned long arg) !(filp->f_mode & FMODE_WRITE)) return -EBADF; - if (copy_from_user(&range, (struct f2fs_move_range __user *)arg, - sizeof(range))) - return -EFAULT; - - dst = fdget(range.dst_fd); + dst = fdget(range->dst_fd); if (!dst.file) return -EBADF; @@ -2864,21 +2872,25 @@ static int f2fs_ioc_move_range(struct file *filp, unsigned long arg) if (err) goto err_out; - err = f2fs_move_file_range(filp, range.pos_in, dst.file, - range.pos_out, range.len); + err = f2fs_move_file_range(filp, range->pos_in, dst.file, + range->pos_out, range->len); mnt_drop_write_file(filp); - if (err) - goto err_out; - - if (copy_to_user((struct f2fs_move_range __user *)arg, - &range, sizeof(range))) - err = -EFAULT; err_out: fdput(dst); return err; } +static int f2fs_ioc_move_range(struct file *filp, unsigned long arg) +{ + struct f2fs_move_range range; + + if (copy_from_user(&range, (struct f2fs_move_range __user *)arg, + sizeof(range))) + return -EFAULT; + return __f2fs_ioc_move_range(filp, &range); +} + static int f2fs_ioc_flush_device(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); @@ -2887,6 +2899,11 @@ static int f2fs_ioc_flush_device(struct file *filp, unsigned long arg) unsigned int start_segno = 0, end_segno = 0; unsigned int dev_start_segno = 0, dev_end_segno = 0; struct f2fs_flush_device range; + struct f2fs_gc_control gc_control = { + .init_gc_type = FG_GC, + .should_migrate_blocks = true, + .err_gc_skipped = true, + .nr_free_secs = 0 }; int ret; if (!capable(CAP_SYS_ADMIN)) @@ -2923,14 +2940,16 @@ static int f2fs_ioc_flush_device(struct file *filp, unsigned long arg) end_segno = min(start_segno + range.segments, dev_end_segno); while (start_segno < end_segno) { - if (!down_write_trylock(&sbi->gc_lock)) { + if (!f2fs_down_write_trylock(&sbi->gc_lock)) { ret = -EBUSY; goto out; } sm->last_victim[GC_CB] = end_segno + 1; sm->last_victim[GC_GREEDY] = end_segno + 1; sm->last_victim[ALLOC_NEXT] = end_segno + 1; - ret = f2fs_gc(sbi, true, true, start_segno); + + gc_control.victim_segno = start_segno; + ret = f2fs_gc(sbi, &gc_control); if (ret == -EAGAIN) ret = 0; else if (ret < 0) @@ -2971,12 +2990,11 @@ int f2fs_transfer_project_quota(struct inode *inode, kprojid_t kprojid) return err; } -static int f2fs_ioc_setproject(struct file *filp, __u32 projid) +static int f2fs_ioc_setproject(struct inode *inode, __u32 projid) { - struct inode *inode = file_inode(filp); struct f2fs_inode_info *fi = F2FS_I(inode); struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - struct page *ipage; + struct f2fs_inode *ri = NULL; kprojid_t kprojid; int err; @@ -2992,7 +3010,7 @@ static int f2fs_ioc_setproject(struct file *filp, __u32 projid) kprojid = make_kprojid(&init_user_ns, (projid_t)projid); - if (projid_eq(kprojid, F2FS_I(inode)->i_projid)) + if (projid_eq(kprojid, fi->i_projid)) return 0; err = -EPERM; @@ -3000,19 +3018,10 @@ static int f2fs_ioc_setproject(struct file *filp, __u32 projid) if (IS_NOQUOTA(inode)) return err; - ipage = f2fs_get_node_page(sbi, inode->i_ino); - if (IS_ERR(ipage)) - return PTR_ERR(ipage); + if (!F2FS_FITS_IN_INODE(ri, fi->i_extra_isize, i_projid)) + return -EOVERFLOW; - if (!F2FS_FITS_IN_INODE(F2FS_INODE(ipage), fi->i_extra_isize, - i_projid)) { - err = -EOVERFLOW; - f2fs_put_page(ipage, 1); - return err; - } - f2fs_put_page(ipage, 1); - - err = dquot_initialize(inode); + err = f2fs_dquot_initialize(inode); if (err) return err; @@ -3021,7 +3030,7 @@ static int f2fs_ioc_setproject(struct file *filp, __u32 projid) if (err) goto out_unlock; - F2FS_I(inode)->i_projid = kprojid; + fi->i_projid = kprojid; inode->i_ctime = current_time(inode); f2fs_mark_inode_dirty_sync(inode, true); out_unlock: @@ -3034,7 +3043,7 @@ int f2fs_transfer_project_quota(struct inode *inode, kprojid_t kprojid) return 0; } -static int f2fs_ioc_setproject(struct file *filp, __u32 projid) +static int f2fs_ioc_setproject(struct inode *inode, __u32 projid) { if (projid != F2FS_DEF_PROJID) return -EOPNOTSUPP; @@ -3042,123 +3051,55 @@ static int f2fs_ioc_setproject(struct file *filp, __u32 projid) } #endif -/* FS_IOC_FSGETXATTR and FS_IOC_FSSETXATTR support */ - -/* - * To make a new on-disk f2fs i_flag gettable via FS_IOC_FSGETXATTR and settable - * via FS_IOC_FSSETXATTR, add an entry for it to f2fs_xflags_map[], and add its - * FS_XFLAG_* equivalent to F2FS_SUPPORTED_XFLAGS. - */ - -static const struct { - u32 iflag; - u32 xflag; -} f2fs_xflags_map[] = { - { F2FS_SYNC_FL, FS_XFLAG_SYNC }, - { F2FS_IMMUTABLE_FL, FS_XFLAG_IMMUTABLE }, - { F2FS_APPEND_FL, FS_XFLAG_APPEND }, - { F2FS_NODUMP_FL, FS_XFLAG_NODUMP }, - { F2FS_NOATIME_FL, FS_XFLAG_NOATIME }, - { F2FS_PROJINHERIT_FL, FS_XFLAG_PROJINHERIT }, -}; - -#define F2FS_SUPPORTED_XFLAGS ( \ - FS_XFLAG_SYNC | \ - FS_XFLAG_IMMUTABLE | \ - FS_XFLAG_APPEND | \ - FS_XFLAG_NODUMP | \ - FS_XFLAG_NOATIME | \ - FS_XFLAG_PROJINHERIT) - -/* Convert f2fs on-disk i_flags to FS_IOC_FS{GET,SET}XATTR flags */ -static inline u32 f2fs_iflags_to_xflags(u32 iflags) -{ - u32 xflags = 0; - int i; - - for (i = 0; i < ARRAY_SIZE(f2fs_xflags_map); i++) - if (iflags & f2fs_xflags_map[i].iflag) - xflags |= f2fs_xflags_map[i].xflag; - - return xflags; -} - -/* Convert FS_IOC_FS{GET,SET}XATTR flags to f2fs on-disk i_flags */ -static inline u32 f2fs_xflags_to_iflags(u32 xflags) -{ - u32 iflags = 0; - int i; - - for (i = 0; i < ARRAY_SIZE(f2fs_xflags_map); i++) - if (xflags & f2fs_xflags_map[i].xflag) - iflags |= f2fs_xflags_map[i].iflag; - - return iflags; -} - -static void f2fs_fill_fsxattr(struct inode *inode, struct fsxattr *fa) +int f2fs_fileattr_get(struct dentry *dentry, struct fileattr *fa) { + struct inode *inode = d_inode(dentry); struct f2fs_inode_info *fi = F2FS_I(inode); + u32 fsflags = f2fs_iflags_to_fsflags(fi->i_flags); + + if (IS_ENCRYPTED(inode)) + fsflags |= FS_ENCRYPT_FL; + if (IS_VERITY(inode)) + fsflags |= FS_VERITY_FL; + if (f2fs_has_inline_data(inode) || f2fs_has_inline_dentry(inode)) + fsflags |= FS_INLINE_DATA_FL; + if (is_inode_flag_set(inode, FI_PIN_FILE)) + fsflags |= FS_NOCOW_FL; - simple_fill_fsxattr(fa, f2fs_iflags_to_xflags(fi->i_flags)); + fileattr_fill_flags(fa, fsflags & F2FS_GETTABLE_FS_FL); if (f2fs_sb_has_project_quota(F2FS_I_SB(inode))) fa->fsx_projid = from_kprojid(&init_user_ns, fi->i_projid); -} -static int f2fs_ioc_fsgetxattr(struct file *filp, unsigned long arg) -{ - struct inode *inode = file_inode(filp); - struct fsxattr fa; - - f2fs_fill_fsxattr(inode, &fa); - - if (copy_to_user((struct fsxattr __user *)arg, &fa, sizeof(fa))) - return -EFAULT; return 0; } -static int f2fs_ioc_fssetxattr(struct file *filp, unsigned long arg) +int f2fs_fileattr_set(struct user_namespace *mnt_userns, + struct dentry *dentry, struct fileattr *fa) { - struct inode *inode = file_inode(filp); - struct fsxattr fa, old_fa; + struct inode *inode = d_inode(dentry); + u32 fsflags = fa->flags, mask = F2FS_SETTABLE_FS_FL; u32 iflags; int err; - if (copy_from_user(&fa, (struct fsxattr __user *)arg, sizeof(fa))) - return -EFAULT; - - /* Make sure caller has proper permission */ - if (!inode_owner_or_capable(inode)) - return -EACCES; - - if (fa.fsx_xflags & ~F2FS_SUPPORTED_XFLAGS) + if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) + return -EIO; + if (!f2fs_is_checkpoint_ready(F2FS_I_SB(inode))) + return -ENOSPC; + if (fsflags & ~F2FS_GETTABLE_FS_FL) return -EOPNOTSUPP; + fsflags &= F2FS_SETTABLE_FS_FL; + if (!fa->flags_valid) + mask &= FS_COMMON_FL; - iflags = f2fs_xflags_to_iflags(fa.fsx_xflags); + iflags = f2fs_fsflags_to_iflags(fsflags); if (f2fs_mask_flags(inode->i_mode, iflags) != iflags) return -EOPNOTSUPP; - err = mnt_want_write_file(filp); - if (err) - return err; - - inode_lock(inode); - - f2fs_fill_fsxattr(inode, &old_fa); - err = vfs_ioc_fssetxattr_check(inode, &old_fa, &fa); - if (err) - goto out; - - err = f2fs_setflags_common(inode, iflags, - f2fs_xflags_to_iflags(F2FS_SUPPORTED_XFLAGS)); - if (err) - goto out; + err = f2fs_setflags_common(inode, iflags, f2fs_fsflags_to_iflags(mask)); + if (!err) + err = f2fs_ioc_setproject(inode, fa->fsx_projid); - err = f2fs_ioc_setproject(filp, fa.fsx_projid); -out: - inode_unlock(inode); - mnt_drop_write_file(filp); return err; } @@ -3203,17 +3144,17 @@ static int f2fs_ioc_set_pin_file(struct file *filp, unsigned long arg) inode_lock(inode); - if (f2fs_should_update_outplace(inode, NULL)) { - ret = -EINVAL; - goto out; - } - if (!pin) { clear_inode_flag(inode, FI_PIN_FILE); f2fs_i_gc_failures_write(inode, 0); goto done; } + if (f2fs_should_update_outplace(inode, NULL)) { + ret = -EINVAL; + goto out; + } + if (f2fs_pin_file_control(inode, false)) { ret = -EAGAIN; goto out; @@ -3223,7 +3164,7 @@ static int f2fs_ioc_set_pin_file(struct file *filp, unsigned long arg) if (ret) goto out; - if (f2fs_disable_compressed_file(inode)) { + if (!f2fs_disable_compressed_file(inode)) { ret = -EOPNOTSUPP; goto out; } @@ -3264,21 +3205,21 @@ int f2fs_precache_extents(struct inode *inode) map.m_next_extent = &m_next_extent; map.m_seg_type = NO_CHECK_TYPE; map.m_may_create = false; - end = F2FS_I_SB(inode)->max_file_blocks; + end = max_file_blocks(inode); while (map.m_lblk < end) { map.m_len = end - map.m_lblk; - down_write(&fi->i_gc_rwsem[WRITE]); + f2fs_down_write(&fi->i_gc_rwsem[WRITE]); err = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_PRECACHE); - up_write(&fi->i_gc_rwsem[WRITE]); + f2fs_up_write(&fi->i_gc_rwsem[WRITE]); if (err) return err; map.m_lblk = m_next_extent; } - return err; + return 0; } static int f2fs_ioc_precache_extents(struct file *filp, unsigned long arg) @@ -3290,7 +3231,6 @@ static int f2fs_ioc_resize_fs(struct file *filp, unsigned long arg) { struct f2fs_sb_info *sbi = F2FS_I_SB(file_inode(filp)); __u64 block_count; - int ret; if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -3302,9 +3242,7 @@ static int f2fs_ioc_resize_fs(struct file *filp, unsigned long arg) sizeof(block_count))) return -EFAULT; - ret = f2fs_resize_fs(sbi, block_count); - - return ret; + return f2fs_resize_fs(sbi, block_count); } static int f2fs_ioc_enable_verity(struct file *filp, unsigned long arg) @@ -3315,7 +3253,7 @@ static int f2fs_ioc_enable_verity(struct file *filp, unsigned long arg) if (!f2fs_sb_has_verity(F2FS_I_SB(inode))) { f2fs_warn(F2FS_I_SB(inode), - "Can't enable fs-verity on inode %lu: the verity feature is not enabled on this filesystem.\n", + "Can't enable fs-verity on inode %lu: the verity feature is not enabled on this filesystem", inode->i_ino); return -EOPNOTSUPP; } @@ -3331,7 +3269,15 @@ static int f2fs_ioc_measure_verity(struct file *filp, unsigned long arg) return fsverity_ioctl_measure(filp, (void __user *)arg); } -static int f2fs_get_volume_name(struct file *filp, unsigned long arg) +static int f2fs_ioc_read_verity_metadata(struct file *filp, unsigned long arg) +{ + if (!f2fs_sb_has_verity(F2FS_I_SB(file_inode(filp)))) + return -EOPNOTSUPP; + + return fsverity_ioctl_read_metadata(filp, (const void __user *)arg); +} + +static int f2fs_ioc_getfslabel(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); struct f2fs_sb_info *sbi = F2FS_I_SB(inode); @@ -3343,21 +3289,21 @@ static int f2fs_get_volume_name(struct file *filp, unsigned long arg) if (!vbuf) return -ENOMEM; - down_read(&sbi->sb_lock); + f2fs_down_read(&sbi->sb_lock); count = utf16s_to_utf8s(sbi->raw_super->volume_name, ARRAY_SIZE(sbi->raw_super->volume_name), UTF16_LITTLE_ENDIAN, vbuf, MAX_VOLUME_NAME); - up_read(&sbi->sb_lock); + f2fs_up_read(&sbi->sb_lock); if (copy_to_user((char __user *)arg, vbuf, min(FSLABEL_MAX, count))) err = -EFAULT; - kvfree(vbuf); + kfree(vbuf); return err; } -static int f2fs_set_volume_name(struct file *filp, unsigned long arg) +static int f2fs_ioc_setfslabel(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); struct f2fs_sb_info *sbi = F2FS_I_SB(inode); @@ -3375,7 +3321,7 @@ static int f2fs_set_volume_name(struct file *filp, unsigned long arg) if (err) goto out; - down_write(&sbi->sb_lock); + f2fs_down_write(&sbi->sb_lock); memset(sbi->raw_super->volume_name, 0, sizeof(sbi->raw_super->volume_name)); @@ -3385,7 +3331,7 @@ static int f2fs_set_volume_name(struct file *filp, unsigned long arg) err = f2fs_commit_super(sbi, false); - up_write(&sbi->sb_lock); + f2fs_up_write(&sbi->sb_lock); mnt_drop_write_file(filp); out: @@ -3393,39 +3339,815 @@ out: return err; } -long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) +static int f2fs_get_compress_blocks(struct file *filp, unsigned long arg) { - if (unlikely(f2fs_cp_error(F2FS_I_SB(file_inode(filp))))) - return -EIO; - if (!f2fs_is_checkpoint_ready(F2FS_I_SB(file_inode(filp)))) - return -ENOSPC; + struct inode *inode = file_inode(filp); + __u64 blocks; + + if (!f2fs_sb_has_compression(F2FS_I_SB(inode))) + return -EOPNOTSUPP; + + if (!f2fs_compressed_file(inode)) + return -EINVAL; + + blocks = atomic_read(&F2FS_I(inode)->i_compr_blocks); + return put_user(blocks, (u64 __user *)arg); +} + +static int release_compress_blocks(struct dnode_of_data *dn, pgoff_t count) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); + unsigned int released_blocks = 0; + int cluster_size = F2FS_I(dn->inode)->i_cluster_size; + block_t blkaddr; + int i; + + for (i = 0; i < count; i++) { + blkaddr = data_blkaddr(dn->inode, dn->node_page, + dn->ofs_in_node + i); + + if (!__is_valid_data_blkaddr(blkaddr)) + continue; + if (unlikely(!f2fs_is_valid_blkaddr(sbi, blkaddr, + DATA_GENERIC_ENHANCE))) { + f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR); + return -EFSCORRUPTED; + } + } + + while (count) { + int compr_blocks = 0; + + for (i = 0; i < cluster_size; i++, dn->ofs_in_node++) { + blkaddr = f2fs_data_blkaddr(dn); + + if (i == 0) { + if (blkaddr == COMPRESS_ADDR) + continue; + dn->ofs_in_node += cluster_size; + goto next; + } + + if (__is_valid_data_blkaddr(blkaddr)) + compr_blocks++; + + if (blkaddr != NEW_ADDR) + continue; + + dn->data_blkaddr = NULL_ADDR; + f2fs_set_data_blkaddr(dn); + } + + f2fs_i_compr_blocks_update(dn->inode, compr_blocks, false); + dec_valid_block_count(sbi, dn->inode, + cluster_size - compr_blocks); + + released_blocks += cluster_size - compr_blocks; +next: + count -= cluster_size; + } + + return released_blocks; +} + +static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + pgoff_t page_idx = 0, last_idx; + unsigned int released_blocks = 0; + int ret; + int writecount; + + if (!f2fs_sb_has_compression(F2FS_I_SB(inode))) + return -EOPNOTSUPP; + + if (!f2fs_compressed_file(inode)) + return -EINVAL; + + if (f2fs_readonly(sbi->sb)) + return -EROFS; + + ret = mnt_want_write_file(filp); + if (ret) + return ret; + + f2fs_balance_fs(F2FS_I_SB(inode), true); + + inode_lock(inode); + + writecount = atomic_read(&inode->i_writecount); + if ((filp->f_mode & FMODE_WRITE && writecount != 1) || + (!(filp->f_mode & FMODE_WRITE) && writecount)) { + ret = -EBUSY; + goto out; + } + + if (is_inode_flag_set(inode, FI_COMPRESS_RELEASED)) { + ret = -EINVAL; + goto out; + } + + ret = filemap_write_and_wait_range(inode->i_mapping, 0, LLONG_MAX); + if (ret) + goto out; + + set_inode_flag(inode, FI_COMPRESS_RELEASED); + inode->i_ctime = current_time(inode); + f2fs_mark_inode_dirty_sync(inode, true); + + if (!atomic_read(&F2FS_I(inode)->i_compr_blocks)) + goto out; + + f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + filemap_invalidate_lock(inode->i_mapping); + + last_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); + + while (page_idx < last_idx) { + struct dnode_of_data dn; + pgoff_t end_offset, count; + + set_new_dnode(&dn, inode, NULL, NULL, 0); + ret = f2fs_get_dnode_of_data(&dn, page_idx, LOOKUP_NODE); + if (ret) { + if (ret == -ENOENT) { + page_idx = f2fs_get_next_page_offset(&dn, + page_idx); + ret = 0; + continue; + } + break; + } + + end_offset = ADDRS_PER_PAGE(dn.node_page, inode); + count = min(end_offset - dn.ofs_in_node, last_idx - page_idx); + count = round_up(count, F2FS_I(inode)->i_cluster_size); + + ret = release_compress_blocks(&dn, count); + + f2fs_put_dnode(&dn); + + if (ret < 0) + break; + + page_idx += count; + released_blocks += ret; + } + + filemap_invalidate_unlock(inode->i_mapping); + f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); +out: + inode_unlock(inode); + + mnt_drop_write_file(filp); + + if (ret >= 0) { + ret = put_user(released_blocks, (u64 __user *)arg); + } else if (released_blocks && + atomic_read(&F2FS_I(inode)->i_compr_blocks)) { + set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_warn(sbi, "%s: partial blocks were released i_ino=%lx " + "iblocks=%llu, released=%u, compr_blocks=%u, " + "run fsck to fix.", + __func__, inode->i_ino, inode->i_blocks, + released_blocks, + atomic_read(&F2FS_I(inode)->i_compr_blocks)); + } + + return ret; +} + +static int reserve_compress_blocks(struct dnode_of_data *dn, pgoff_t count) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); + unsigned int reserved_blocks = 0; + int cluster_size = F2FS_I(dn->inode)->i_cluster_size; + block_t blkaddr; + int i; + + for (i = 0; i < count; i++) { + blkaddr = data_blkaddr(dn->inode, dn->node_page, + dn->ofs_in_node + i); + + if (!__is_valid_data_blkaddr(blkaddr)) + continue; + if (unlikely(!f2fs_is_valid_blkaddr(sbi, blkaddr, + DATA_GENERIC_ENHANCE))) { + f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR); + return -EFSCORRUPTED; + } + } + + while (count) { + int compr_blocks = 0; + blkcnt_t reserved; + int ret; + + for (i = 0; i < cluster_size; i++, dn->ofs_in_node++) { + blkaddr = f2fs_data_blkaddr(dn); + + if (i == 0) { + if (blkaddr == COMPRESS_ADDR) + continue; + dn->ofs_in_node += cluster_size; + goto next; + } + + if (__is_valid_data_blkaddr(blkaddr)) { + compr_blocks++; + continue; + } + + dn->data_blkaddr = NEW_ADDR; + f2fs_set_data_blkaddr(dn); + } + + reserved = cluster_size - compr_blocks; + ret = inc_valid_block_count(sbi, dn->inode, &reserved); + if (ret) + return ret; + + if (reserved != cluster_size - compr_blocks) + return -ENOSPC; + + f2fs_i_compr_blocks_update(dn->inode, compr_blocks, true); + + reserved_blocks += reserved; +next: + count -= cluster_size; + } + + return reserved_blocks; +} +static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + pgoff_t page_idx = 0, last_idx; + unsigned int reserved_blocks = 0; + int ret; + + if (!f2fs_sb_has_compression(F2FS_I_SB(inode))) + return -EOPNOTSUPP; + + if (!f2fs_compressed_file(inode)) + return -EINVAL; + + if (f2fs_readonly(sbi->sb)) + return -EROFS; + + ret = mnt_want_write_file(filp); + if (ret) + return ret; + + if (atomic_read(&F2FS_I(inode)->i_compr_blocks)) + goto out; + + f2fs_balance_fs(F2FS_I_SB(inode), true); + + inode_lock(inode); + + if (!is_inode_flag_set(inode, FI_COMPRESS_RELEASED)) { + ret = -EINVAL; + goto unlock_inode; + } + + f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + filemap_invalidate_lock(inode->i_mapping); + + last_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); + + while (page_idx < last_idx) { + struct dnode_of_data dn; + pgoff_t end_offset, count; + + set_new_dnode(&dn, inode, NULL, NULL, 0); + ret = f2fs_get_dnode_of_data(&dn, page_idx, LOOKUP_NODE); + if (ret) { + if (ret == -ENOENT) { + page_idx = f2fs_get_next_page_offset(&dn, + page_idx); + ret = 0; + continue; + } + break; + } + + end_offset = ADDRS_PER_PAGE(dn.node_page, inode); + count = min(end_offset - dn.ofs_in_node, last_idx - page_idx); + count = round_up(count, F2FS_I(inode)->i_cluster_size); + + ret = reserve_compress_blocks(&dn, count); + + f2fs_put_dnode(&dn); + + if (ret < 0) + break; + + page_idx += count; + reserved_blocks += ret; + } + + filemap_invalidate_unlock(inode->i_mapping); + f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + + if (ret >= 0) { + clear_inode_flag(inode, FI_COMPRESS_RELEASED); + inode->i_ctime = current_time(inode); + f2fs_mark_inode_dirty_sync(inode, true); + } +unlock_inode: + inode_unlock(inode); +out: + mnt_drop_write_file(filp); + + if (ret >= 0) { + ret = put_user(reserved_blocks, (u64 __user *)arg); + } else if (reserved_blocks && + atomic_read(&F2FS_I(inode)->i_compr_blocks)) { + set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_warn(sbi, "%s: partial blocks were released i_ino=%lx " + "iblocks=%llu, reserved=%u, compr_blocks=%u, " + "run fsck to fix.", + __func__, inode->i_ino, inode->i_blocks, + reserved_blocks, + atomic_read(&F2FS_I(inode)->i_compr_blocks)); + } + + return ret; +} + +static int f2fs_secure_erase(struct block_device *bdev, struct inode *inode, + pgoff_t off, block_t block, block_t len, u32 flags) +{ + sector_t sector = SECTOR_FROM_BLOCK(block); + sector_t nr_sects = SECTOR_FROM_BLOCK(len); + int ret = 0; + + if (flags & F2FS_TRIM_FILE_DISCARD) { + if (bdev_max_secure_erase_sectors(bdev)) + ret = blkdev_issue_secure_erase(bdev, sector, nr_sects, + GFP_NOFS); + else + ret = blkdev_issue_discard(bdev, sector, nr_sects, + GFP_NOFS); + } + + if (!ret && (flags & F2FS_TRIM_FILE_ZEROOUT)) { + if (IS_ENCRYPTED(inode)) + ret = fscrypt_zeroout_range(inode, off, block, len); + else + ret = blkdev_issue_zeroout(bdev, sector, nr_sects, + GFP_NOFS, 0); + } + + return ret; +} + +static int f2fs_sec_trim_file(struct file *filp, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct address_space *mapping = inode->i_mapping; + struct block_device *prev_bdev = NULL; + struct f2fs_sectrim_range range; + pgoff_t index, pg_end, prev_index = 0; + block_t prev_block = 0, len = 0; + loff_t end_addr; + bool to_end = false; + int ret = 0; + + if (!(filp->f_mode & FMODE_WRITE)) + return -EBADF; + + if (copy_from_user(&range, (struct f2fs_sectrim_range __user *)arg, + sizeof(range))) + return -EFAULT; + + if (range.flags == 0 || (range.flags & ~F2FS_TRIM_FILE_MASK) || + !S_ISREG(inode->i_mode)) + return -EINVAL; + + if (((range.flags & F2FS_TRIM_FILE_DISCARD) && + !f2fs_hw_support_discard(sbi)) || + ((range.flags & F2FS_TRIM_FILE_ZEROOUT) && + IS_ENCRYPTED(inode) && f2fs_is_multi_device(sbi))) + return -EOPNOTSUPP; + + file_start_write(filp); + inode_lock(inode); + + if (f2fs_is_atomic_file(inode) || f2fs_compressed_file(inode) || + range.start >= inode->i_size) { + ret = -EINVAL; + goto err; + } + + if (range.len == 0) + goto err; + + if (inode->i_size - range.start > range.len) { + end_addr = range.start + range.len; + } else { + end_addr = range.len == (u64)-1 ? + sbi->sb->s_maxbytes : inode->i_size; + to_end = true; + } + + if (!IS_ALIGNED(range.start, F2FS_BLKSIZE) || + (!to_end && !IS_ALIGNED(end_addr, F2FS_BLKSIZE))) { + ret = -EINVAL; + goto err; + } + + index = F2FS_BYTES_TO_BLK(range.start); + pg_end = DIV_ROUND_UP(end_addr, F2FS_BLKSIZE); + + ret = f2fs_convert_inline_inode(inode); + if (ret) + goto err; + + f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + filemap_invalidate_lock(mapping); + + ret = filemap_write_and_wait_range(mapping, range.start, + to_end ? LLONG_MAX : end_addr - 1); + if (ret) + goto out; + + truncate_inode_pages_range(mapping, range.start, + to_end ? -1 : end_addr - 1); + + while (index < pg_end) { + struct dnode_of_data dn; + pgoff_t end_offset, count; + int i; + + set_new_dnode(&dn, inode, NULL, NULL, 0); + ret = f2fs_get_dnode_of_data(&dn, index, LOOKUP_NODE); + if (ret) { + if (ret == -ENOENT) { + index = f2fs_get_next_page_offset(&dn, index); + continue; + } + goto out; + } + + end_offset = ADDRS_PER_PAGE(dn.node_page, inode); + count = min(end_offset - dn.ofs_in_node, pg_end - index); + for (i = 0; i < count; i++, index++, dn.ofs_in_node++) { + struct block_device *cur_bdev; + block_t blkaddr = f2fs_data_blkaddr(&dn); + + if (!__is_valid_data_blkaddr(blkaddr)) + continue; + + if (!f2fs_is_valid_blkaddr(sbi, blkaddr, + DATA_GENERIC_ENHANCE)) { + ret = -EFSCORRUPTED; + f2fs_put_dnode(&dn); + f2fs_handle_error(sbi, + ERROR_INVALID_BLKADDR); + goto out; + } + + cur_bdev = f2fs_target_device(sbi, blkaddr, NULL); + if (f2fs_is_multi_device(sbi)) { + int di = f2fs_target_device_index(sbi, blkaddr); + + blkaddr -= FDEV(di).start_blk; + } + + if (len) { + if (prev_bdev == cur_bdev && + index == prev_index + len && + blkaddr == prev_block + len) { + len++; + } else { + ret = f2fs_secure_erase(prev_bdev, + inode, prev_index, prev_block, + len, range.flags); + if (ret) { + f2fs_put_dnode(&dn); + goto out; + } + + len = 0; + } + } + + if (!len) { + prev_bdev = cur_bdev; + prev_index = index; + prev_block = blkaddr; + len = 1; + } + } + + f2fs_put_dnode(&dn); + + if (fatal_signal_pending(current)) { + ret = -EINTR; + goto out; + } + cond_resched(); + } + + if (len) + ret = f2fs_secure_erase(prev_bdev, inode, prev_index, + prev_block, len, range.flags); +out: + filemap_invalidate_unlock(mapping); + f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); +err: + inode_unlock(inode); + file_end_write(filp); + + return ret; +} + +static int f2fs_ioc_get_compress_option(struct file *filp, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + struct f2fs_comp_option option; + + if (!f2fs_sb_has_compression(F2FS_I_SB(inode))) + return -EOPNOTSUPP; + + inode_lock_shared(inode); + + if (!f2fs_compressed_file(inode)) { + inode_unlock_shared(inode); + return -ENODATA; + } + + option.algorithm = F2FS_I(inode)->i_compress_algorithm; + option.log_cluster_size = F2FS_I(inode)->i_log_cluster_size; + + inode_unlock_shared(inode); + + if (copy_to_user((struct f2fs_comp_option __user *)arg, &option, + sizeof(option))) + return -EFAULT; + + return 0; +} + +static int f2fs_ioc_set_compress_option(struct file *filp, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct f2fs_comp_option option; + int ret = 0; + + if (!f2fs_sb_has_compression(sbi)) + return -EOPNOTSUPP; + + if (!(filp->f_mode & FMODE_WRITE)) + return -EBADF; + + if (copy_from_user(&option, (struct f2fs_comp_option __user *)arg, + sizeof(option))) + return -EFAULT; + + if (!f2fs_compressed_file(inode) || + option.log_cluster_size < MIN_COMPRESS_LOG_SIZE || + option.log_cluster_size > MAX_COMPRESS_LOG_SIZE || + option.algorithm >= COMPRESS_MAX) + return -EINVAL; + + file_start_write(filp); + inode_lock(inode); + + if (f2fs_is_mmap_file(inode) || get_dirty_pages(inode)) { + ret = -EBUSY; + goto out; + } + + if (inode->i_size != 0) { + ret = -EFBIG; + goto out; + } + + F2FS_I(inode)->i_compress_algorithm = option.algorithm; + F2FS_I(inode)->i_log_cluster_size = option.log_cluster_size; + F2FS_I(inode)->i_cluster_size = 1 << option.log_cluster_size; + f2fs_mark_inode_dirty_sync(inode, true); + + if (!f2fs_is_compress_backend_ready(inode)) + f2fs_warn(sbi, "compression algorithm is successfully set, " + "but current kernel doesn't support this algorithm."); +out: + inode_unlock(inode); + file_end_write(filp); + + return ret; +} + +static int redirty_blocks(struct inode *inode, pgoff_t page_idx, int len) +{ + DEFINE_READAHEAD(ractl, NULL, NULL, inode->i_mapping, page_idx); + struct address_space *mapping = inode->i_mapping; + struct page *page; + pgoff_t redirty_idx = page_idx; + int i, page_len = 0, ret = 0; + + page_cache_ra_unbounded(&ractl, len, 0); + + for (i = 0; i < len; i++, page_idx++) { + page = read_cache_page(mapping, page_idx, NULL, NULL); + if (IS_ERR(page)) { + ret = PTR_ERR(page); + break; + } + page_len++; + } + + for (i = 0; i < page_len; i++, redirty_idx++) { + page = find_lock_page(mapping, redirty_idx); + + /* It will never fail, when page has pinned above */ + f2fs_bug_on(F2FS_I_SB(inode), !page); + + set_page_dirty(page); + f2fs_put_page(page, 1); + f2fs_put_page(page, 0); + } + + return ret; +} + +static int f2fs_ioc_decompress_file(struct file *filp, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct f2fs_inode_info *fi = F2FS_I(inode); + pgoff_t page_idx = 0, last_idx; + unsigned int blk_per_seg = sbi->blocks_per_seg; + int cluster_size = fi->i_cluster_size; + int count, ret; + + if (!f2fs_sb_has_compression(sbi) || + F2FS_OPTION(sbi).compress_mode != COMPR_MODE_USER) + return -EOPNOTSUPP; + + if (!(filp->f_mode & FMODE_WRITE)) + return -EBADF; + + if (!f2fs_compressed_file(inode)) + return -EINVAL; + + f2fs_balance_fs(F2FS_I_SB(inode), true); + + file_start_write(filp); + inode_lock(inode); + + if (!f2fs_is_compress_backend_ready(inode)) { + ret = -EOPNOTSUPP; + goto out; + } + + if (is_inode_flag_set(inode, FI_COMPRESS_RELEASED)) { + ret = -EINVAL; + goto out; + } + + ret = filemap_write_and_wait_range(inode->i_mapping, 0, LLONG_MAX); + if (ret) + goto out; + + if (!atomic_read(&fi->i_compr_blocks)) + goto out; + + last_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); + + count = last_idx - page_idx; + while (count) { + int len = min(cluster_size, count); + + ret = redirty_blocks(inode, page_idx, len); + if (ret < 0) + break; + + if (get_dirty_pages(inode) >= blk_per_seg) + filemap_fdatawrite(inode->i_mapping); + + count -= len; + page_idx += len; + } + + if (!ret) + ret = filemap_write_and_wait_range(inode->i_mapping, 0, + LLONG_MAX); + + if (ret) + f2fs_warn(sbi, "%s: The file might be partially decompressed (errno=%d). Please delete the file.", + __func__, ret); +out: + inode_unlock(inode); + file_end_write(filp); + + return ret; +} + +static int f2fs_ioc_compress_file(struct file *filp, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + pgoff_t page_idx = 0, last_idx; + unsigned int blk_per_seg = sbi->blocks_per_seg; + int cluster_size = F2FS_I(inode)->i_cluster_size; + int count, ret; + + if (!f2fs_sb_has_compression(sbi) || + F2FS_OPTION(sbi).compress_mode != COMPR_MODE_USER) + return -EOPNOTSUPP; + + if (!(filp->f_mode & FMODE_WRITE)) + return -EBADF; + + if (!f2fs_compressed_file(inode)) + return -EINVAL; + + f2fs_balance_fs(F2FS_I_SB(inode), true); + + file_start_write(filp); + inode_lock(inode); + + if (!f2fs_is_compress_backend_ready(inode)) { + ret = -EOPNOTSUPP; + goto out; + } + + if (is_inode_flag_set(inode, FI_COMPRESS_RELEASED)) { + ret = -EINVAL; + goto out; + } + + ret = filemap_write_and_wait_range(inode->i_mapping, 0, LLONG_MAX); + if (ret) + goto out; + + set_inode_flag(inode, FI_ENABLE_COMPRESS); + + last_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); + + count = last_idx - page_idx; + while (count) { + int len = min(cluster_size, count); + + ret = redirty_blocks(inode, page_idx, len); + if (ret < 0) + break; + + if (get_dirty_pages(inode) >= blk_per_seg) + filemap_fdatawrite(inode->i_mapping); + + count -= len; + page_idx += len; + } + + if (!ret) + ret = filemap_write_and_wait_range(inode->i_mapping, 0, + LLONG_MAX); + + clear_inode_flag(inode, FI_ENABLE_COMPRESS); + + if (ret) + f2fs_warn(sbi, "%s: The file might be partially compressed (errno=%d). Please delete the file.", + __func__, ret); +out: + inode_unlock(inode); + file_end_write(filp); + + return ret; +} + +static long __f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) +{ switch (cmd) { - case F2FS_IOC_GETFLAGS: - return f2fs_ioc_getflags(filp, arg); - case F2FS_IOC_SETFLAGS: - return f2fs_ioc_setflags(filp, arg); - case F2FS_IOC_GETVERSION: + case FS_IOC_GETVERSION: return f2fs_ioc_getversion(filp, arg); case F2FS_IOC_START_ATOMIC_WRITE: return f2fs_ioc_start_atomic_write(filp); case F2FS_IOC_COMMIT_ATOMIC_WRITE: return f2fs_ioc_commit_atomic_write(filp); + case F2FS_IOC_ABORT_ATOMIC_WRITE: + return f2fs_ioc_abort_atomic_write(filp); case F2FS_IOC_START_VOLATILE_WRITE: - return f2fs_ioc_start_volatile_write(filp); case F2FS_IOC_RELEASE_VOLATILE_WRITE: - return f2fs_ioc_release_volatile_write(filp); - case F2FS_IOC_ABORT_VOLATILE_WRITE: - return f2fs_ioc_abort_volatile_write(filp); + return -EOPNOTSUPP; case F2FS_IOC_SHUTDOWN: return f2fs_ioc_shutdown(filp, arg); case FITRIM: return f2fs_ioc_fitrim(filp, arg); - case F2FS_IOC_SET_ENCRYPTION_POLICY: + case FS_IOC_SET_ENCRYPTION_POLICY: return f2fs_ioc_set_encryption_policy(filp, arg); - case F2FS_IOC_GET_ENCRYPTION_POLICY: + case FS_IOC_GET_ENCRYPTION_POLICY: return f2fs_ioc_get_encryption_policy(filp, arg); - case F2FS_IOC_GET_ENCRYPTION_PWSALT: + case FS_IOC_GET_ENCRYPTION_PWSALT: return f2fs_ioc_get_encryption_pwsalt(filp, arg); case FS_IOC_GET_ENCRYPTION_POLICY_EX: return f2fs_ioc_get_encryption_policy_ex(filp, arg); @@ -3437,6 +4159,8 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) return f2fs_ioc_remove_encryption_key_all_users(filp, arg); case FS_IOC_GET_ENCRYPTION_KEY_STATUS: return f2fs_ioc_get_encryption_key_status(filp, arg); + case FS_IOC_GET_ENCRYPTION_NONCE: + return f2fs_ioc_get_encryption_nonce(filp, arg); case F2FS_IOC_GARBAGE_COLLECT: return f2fs_ioc_gc(filp, arg); case F2FS_IOC_GARBAGE_COLLECT_RANGE: @@ -3451,10 +4175,6 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) return f2fs_ioc_flush_device(filp, arg); case F2FS_IOC_GET_FEATURES: return f2fs_ioc_get_features(filp, arg); - case F2FS_IOC_FSGETXATTR: - return f2fs_ioc_fsgetxattr(filp, arg); - case F2FS_IOC_FSSETXATTR: - return f2fs_ioc_fssetxattr(filp, arg); case F2FS_IOC_GET_PIN_FILE: return f2fs_ioc_get_pin_file(filp, arg); case F2FS_IOC_SET_PIN_FILE: @@ -3467,172 +4187,666 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) return f2fs_ioc_enable_verity(filp, arg); case FS_IOC_MEASURE_VERITY: return f2fs_ioc_measure_verity(filp, arg); - case F2FS_IOC_GET_VOLUME_NAME: - return f2fs_get_volume_name(filp, arg); - case F2FS_IOC_SET_VOLUME_NAME: - return f2fs_set_volume_name(filp, arg); + case FS_IOC_READ_VERITY_METADATA: + return f2fs_ioc_read_verity_metadata(filp, arg); + case FS_IOC_GETFSLABEL: + return f2fs_ioc_getfslabel(filp, arg); + case FS_IOC_SETFSLABEL: + return f2fs_ioc_setfslabel(filp, arg); + case F2FS_IOC_GET_COMPRESS_BLOCKS: + return f2fs_get_compress_blocks(filp, arg); + case F2FS_IOC_RELEASE_COMPRESS_BLOCKS: + return f2fs_release_compress_blocks(filp, arg); + case F2FS_IOC_RESERVE_COMPRESS_BLOCKS: + return f2fs_reserve_compress_blocks(filp, arg); + case F2FS_IOC_SEC_TRIM_FILE: + return f2fs_sec_trim_file(filp, arg); + case F2FS_IOC_GET_COMPRESS_OPTION: + return f2fs_ioc_get_compress_option(filp, arg); + case F2FS_IOC_SET_COMPRESS_OPTION: + return f2fs_ioc_set_compress_option(filp, arg); + case F2FS_IOC_DECOMPRESS_FILE: + return f2fs_ioc_decompress_file(filp, arg); + case F2FS_IOC_COMPRESS_FILE: + return f2fs_ioc_compress_file(filp, arg); default: return -ENOTTY; } } -static ssize_t f2fs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) +long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) +{ + if (unlikely(f2fs_cp_error(F2FS_I_SB(file_inode(filp))))) + return -EIO; + if (!f2fs_is_checkpoint_ready(F2FS_I_SB(file_inode(filp)))) + return -ENOSPC; + + return __f2fs_ioctl(filp, cmd, arg); +} + +/* + * Return %true if the given read or write request should use direct I/O, or + * %false if it should use buffered I/O. + */ +static bool f2fs_should_use_dio(struct inode *inode, struct kiocb *iocb, + struct iov_iter *iter) +{ + unsigned int align; + + if (!(iocb->ki_flags & IOCB_DIRECT)) + return false; + + if (f2fs_force_buffered_io(inode, iov_iter_rw(iter))) + return false; + + /* + * Direct I/O not aligned to the disk's logical_block_size will be + * attempted, but will fail with -EINVAL. + * + * f2fs additionally requires that direct I/O be aligned to the + * filesystem block size, which is often a stricter requirement. + * However, f2fs traditionally falls back to buffered I/O on requests + * that are logical_block_size-aligned but not fs-block aligned. + * + * The below logic implements this behavior. + */ + align = iocb->ki_pos | iov_iter_alignment(iter); + if (!IS_ALIGNED(align, i_blocksize(inode)) && + IS_ALIGNED(align, bdev_logical_block_size(inode->i_sb->s_bdev))) + return false; + + return true; +} + +static int f2fs_dio_read_end_io(struct kiocb *iocb, ssize_t size, int error, + unsigned int flags) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(file_inode(iocb->ki_filp)); + + dec_page_count(sbi, F2FS_DIO_READ); + if (error) + return error; + f2fs_update_iostat(sbi, NULL, APP_DIRECT_READ_IO, size); + return 0; +} + +static const struct iomap_dio_ops f2fs_iomap_dio_read_ops = { + .end_io = f2fs_dio_read_end_io, +}; + +static ssize_t f2fs_dio_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct f2fs_inode_info *fi = F2FS_I(inode); + const loff_t pos = iocb->ki_pos; + const size_t count = iov_iter_count(to); + struct iomap_dio *dio; + ssize_t ret; + + if (count == 0) + return 0; /* skip atime update */ + + trace_f2fs_direct_IO_enter(inode, iocb, count, READ); + + if (iocb->ki_flags & IOCB_NOWAIT) { + if (!f2fs_down_read_trylock(&fi->i_gc_rwsem[READ])) { + ret = -EAGAIN; + goto out; + } + } else { + f2fs_down_read(&fi->i_gc_rwsem[READ]); + } + + /* + * We have to use __iomap_dio_rw() and iomap_dio_complete() instead of + * the higher-level function iomap_dio_rw() in order to ensure that the + * F2FS_DIO_READ counter will be decremented correctly in all cases. + */ + inc_page_count(sbi, F2FS_DIO_READ); + dio = __iomap_dio_rw(iocb, to, &f2fs_iomap_ops, + &f2fs_iomap_dio_read_ops, 0, NULL, 0); + if (IS_ERR_OR_NULL(dio)) { + ret = PTR_ERR_OR_ZERO(dio); + if (ret != -EIOCBQUEUED) + dec_page_count(sbi, F2FS_DIO_READ); + } else { + ret = iomap_dio_complete(dio); + } + + f2fs_up_read(&fi->i_gc_rwsem[READ]); + + file_accessed(file); +out: + trace_f2fs_direct_IO_exit(inode, pos, count, READ, ret); + return ret; +} + +static ssize_t f2fs_file_read_iter(struct kiocb *iocb, struct iov_iter *to) +{ + struct inode *inode = file_inode(iocb->ki_filp); + const loff_t pos = iocb->ki_pos; + ssize_t ret; if (!f2fs_is_compress_backend_ready(inode)) return -EOPNOTSUPP; - return generic_file_read_iter(iocb, iter); + if (trace_f2fs_dataread_start_enabled()) { + char *p = f2fs_kmalloc(F2FS_I_SB(inode), PATH_MAX, GFP_KERNEL); + char *path; + + if (!p) + goto skip_read_trace; + + path = dentry_path_raw(file_dentry(iocb->ki_filp), p, PATH_MAX); + if (IS_ERR(path)) { + kfree(p); + goto skip_read_trace; + } + + trace_f2fs_dataread_start(inode, pos, iov_iter_count(to), + current->pid, path, current->comm); + kfree(p); + } +skip_read_trace: + if (f2fs_should_use_dio(inode, iocb, to)) { + ret = f2fs_dio_read_iter(iocb, to); + } else { + ret = filemap_read(iocb, to, 0); + if (ret > 0) + f2fs_update_iostat(F2FS_I_SB(inode), inode, + APP_BUFFERED_READ_IO, ret); + } + if (trace_f2fs_dataread_end_enabled()) + trace_f2fs_dataread_end(inode, pos, ret); + return ret; } -static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) +static ssize_t f2fs_write_checks(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file); - ssize_t ret; + ssize_t count; + int err; - if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) { - ret = -EIO; - goto out; + if (IS_IMMUTABLE(inode)) + return -EPERM; + + if (is_inode_flag_set(inode, FI_COMPRESS_RELEASED)) + return -EPERM; + + count = generic_write_checks(iocb, from); + if (count <= 0) + return count; + + err = file_modified(file); + if (err) + return err; + return count; +} + +/* + * Preallocate blocks for a write request, if it is possible and helpful to do + * so. Returns a positive number if blocks may have been preallocated, 0 if no + * blocks were preallocated, or a negative errno value if something went + * seriously wrong. Also sets FI_PREALLOCATED_ALL on the inode if *all* the + * requested blocks (not just some of them) have been allocated. + */ +static int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *iter, + bool dio) +{ + struct inode *inode = file_inode(iocb->ki_filp); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + const loff_t pos = iocb->ki_pos; + const size_t count = iov_iter_count(iter); + struct f2fs_map_blocks map = {}; + int flag; + int ret; + + /* If it will be an out-of-place direct write, don't bother. */ + if (dio && f2fs_lfs_mode(sbi)) + return 0; + /* + * Don't preallocate holes aligned to DIO_SKIP_HOLES which turns into + * buffered IO, if DIO meets any holes. + */ + if (dio && i_size_read(inode) && + (F2FS_BYTES_TO_BLK(pos) < F2FS_BLK_ALIGN(i_size_read(inode)))) + return 0; + + /* No-wait I/O can't allocate blocks. */ + if (iocb->ki_flags & IOCB_NOWAIT) + return 0; + + /* If it will be a short write, don't bother. */ + if (fault_in_iov_iter_readable(iter, count)) + return 0; + + if (f2fs_has_inline_data(inode)) { + /* If the data will fit inline, don't bother. */ + if (pos + count <= MAX_INLINE_DATA(inode)) + return 0; + ret = f2fs_convert_inline_inode(inode); + if (ret) + return ret; } - if (!f2fs_is_compress_backend_ready(inode)) + /* Do not preallocate blocks that will be written partially in 4KB. */ + map.m_lblk = F2FS_BLK_ALIGN(pos); + map.m_len = F2FS_BYTES_TO_BLK(pos + count); + if (map.m_len > map.m_lblk) + map.m_len -= map.m_lblk; + else + map.m_len = 0; + map.m_may_create = true; + if (dio) { + map.m_seg_type = f2fs_rw_hint_to_seg_type(inode->i_write_hint); + flag = F2FS_GET_BLOCK_PRE_DIO; + } else { + map.m_seg_type = NO_CHECK_TYPE; + flag = F2FS_GET_BLOCK_PRE_AIO; + } + + ret = f2fs_map_blocks(inode, &map, 1, flag); + /* -ENOSPC|-EDQUOT are fine to report the number of allocated blocks. */ + if (ret < 0 && !((ret == -ENOSPC || ret == -EDQUOT) && map.m_len > 0)) + return ret; + if (ret == 0) + set_inode_flag(inode, FI_PREALLOCATED_ALL); + return map.m_len; +} + +static ssize_t f2fs_buffered_write_iter(struct kiocb *iocb, + struct iov_iter *from) +{ + struct file *file = iocb->ki_filp; + struct inode *inode = file_inode(file); + ssize_t ret; + + if (iocb->ki_flags & IOCB_NOWAIT) return -EOPNOTSUPP; + current->backing_dev_info = inode_to_bdi(inode); + ret = generic_perform_write(iocb, from); + current->backing_dev_info = NULL; + + if (ret > 0) { + iocb->ki_pos += ret; + f2fs_update_iostat(F2FS_I_SB(inode), inode, + APP_BUFFERED_IO, ret); + } + return ret; +} + +static int f2fs_dio_write_end_io(struct kiocb *iocb, ssize_t size, int error, + unsigned int flags) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(file_inode(iocb->ki_filp)); + + dec_page_count(sbi, F2FS_DIO_WRITE); + if (error) + return error; + f2fs_update_iostat(sbi, NULL, APP_DIRECT_IO, size); + return 0; +} + +static const struct iomap_dio_ops f2fs_iomap_dio_write_ops = { + .end_io = f2fs_dio_write_end_io, +}; + +static ssize_t f2fs_dio_write_iter(struct kiocb *iocb, struct iov_iter *from, + bool *may_need_sync) +{ + struct file *file = iocb->ki_filp; + struct inode *inode = file_inode(file); + struct f2fs_inode_info *fi = F2FS_I(inode); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + const bool do_opu = f2fs_lfs_mode(sbi); + const loff_t pos = iocb->ki_pos; + const ssize_t count = iov_iter_count(from); + unsigned int dio_flags; + struct iomap_dio *dio; + ssize_t ret; + + trace_f2fs_direct_IO_enter(inode, iocb, count, WRITE); + if (iocb->ki_flags & IOCB_NOWAIT) { - if (!inode_trylock(inode)) { + /* f2fs_convert_inline_inode() and block allocation can block */ + if (f2fs_has_inline_data(inode) || + !f2fs_overwrite_io(inode, pos, count)) { + ret = -EAGAIN; + goto out; + } + + if (!f2fs_down_read_trylock(&fi->i_gc_rwsem[WRITE])) { + ret = -EAGAIN; + goto out; + } + if (do_opu && !f2fs_down_read_trylock(&fi->i_gc_rwsem[READ])) { + f2fs_up_read(&fi->i_gc_rwsem[WRITE]); ret = -EAGAIN; goto out; } } else { - inode_lock(inode); + ret = f2fs_convert_inline_inode(inode); + if (ret) + goto out; + + f2fs_down_read(&fi->i_gc_rwsem[WRITE]); + if (do_opu) + f2fs_down_read(&fi->i_gc_rwsem[READ]); } - ret = generic_write_checks(iocb, from); - if (ret > 0) { - bool preallocated = false; - size_t target_size = 0; - int err; - - if (iov_iter_fault_in_readable(from, iov_iter_count(from))) - set_inode_flag(inode, FI_NO_PREALLOC); - - if ((iocb->ki_flags & IOCB_NOWAIT)) { - if (!f2fs_overwrite_io(inode, iocb->ki_pos, - iov_iter_count(from)) || - f2fs_has_inline_data(inode) || - f2fs_force_buffered_io(inode, iocb, from)) { - clear_inode_flag(inode, FI_NO_PREALLOC); - inode_unlock(inode); - ret = -EAGAIN; + /* + * We have to use __iomap_dio_rw() and iomap_dio_complete() instead of + * the higher-level function iomap_dio_rw() in order to ensure that the + * F2FS_DIO_WRITE counter will be decremented correctly in all cases. + */ + inc_page_count(sbi, F2FS_DIO_WRITE); + dio_flags = 0; + if (pos + count > inode->i_size) + dio_flags |= IOMAP_DIO_FORCE_WAIT; + dio = __iomap_dio_rw(iocb, from, &f2fs_iomap_ops, + &f2fs_iomap_dio_write_ops, dio_flags, NULL, 0); + if (IS_ERR_OR_NULL(dio)) { + ret = PTR_ERR_OR_ZERO(dio); + if (ret == -ENOTBLK) + ret = 0; + if (ret != -EIOCBQUEUED) + dec_page_count(sbi, F2FS_DIO_WRITE); + } else { + ret = iomap_dio_complete(dio); + } + + if (do_opu) + f2fs_up_read(&fi->i_gc_rwsem[READ]); + f2fs_up_read(&fi->i_gc_rwsem[WRITE]); + + if (ret < 0) + goto out; + if (pos + ret > inode->i_size) + f2fs_i_size_write(inode, pos + ret); + if (!do_opu) + set_inode_flag(inode, FI_UPDATE_WRITE); + + if (iov_iter_count(from)) { + ssize_t ret2; + loff_t bufio_start_pos = iocb->ki_pos; + + /* + * The direct write was partial, so we need to fall back to a + * buffered write for the remainder. + */ + + ret2 = f2fs_buffered_write_iter(iocb, from); + if (iov_iter_count(from)) + f2fs_write_failed(inode, iocb->ki_pos); + if (ret2 < 0) + goto out; + + /* + * Ensure that the pagecache pages are written to disk and + * invalidated to preserve the expected O_DIRECT semantics. + */ + if (ret2 > 0) { + loff_t bufio_end_pos = bufio_start_pos + ret2 - 1; + + ret += ret2; + + ret2 = filemap_write_and_wait_range(file->f_mapping, + bufio_start_pos, + bufio_end_pos); + if (ret2 < 0) goto out; - } - goto write; + invalidate_mapping_pages(file->f_mapping, + bufio_start_pos >> PAGE_SHIFT, + bufio_end_pos >> PAGE_SHIFT); } + } else { + /* iomap_dio_rw() already handled the generic_write_sync(). */ + *may_need_sync = false; + } +out: + trace_f2fs_direct_IO_exit(inode, pos, count, WRITE, ret); + return ret; +} - if (is_inode_flag_set(inode, FI_NO_PREALLOC)) - goto write; +static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) +{ + struct inode *inode = file_inode(iocb->ki_filp); + const loff_t orig_pos = iocb->ki_pos; + const size_t orig_count = iov_iter_count(from); + loff_t target_size; + bool dio; + bool may_need_sync = true; + int preallocated; + ssize_t ret; - if (iocb->ki_flags & IOCB_DIRECT) { - /* - * Convert inline data for Direct I/O before entering - * f2fs_direct_IO(). - */ - err = f2fs_convert_inline_inode(inode); - if (err) - goto out_err; - /* - * If force_buffere_io() is true, we have to allocate - * blocks all the time, since f2fs_direct_IO will fall - * back to buffered IO. - */ - if (!f2fs_force_buffered_io(inode, iocb, from) && - allow_outplace_dio(inode, iocb, from)) - goto write; - } - preallocated = true; - target_size = iocb->ki_pos + iov_iter_count(from); + if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) { + ret = -EIO; + goto out; + } - err = f2fs_preallocate_blocks(iocb, from); - if (err) { -out_err: - clear_inode_flag(inode, FI_NO_PREALLOC); - inode_unlock(inode); - ret = err; + if (!f2fs_is_compress_backend_ready(inode)) { + ret = -EOPNOTSUPP; + goto out; + } + + if (iocb->ki_flags & IOCB_NOWAIT) { + if (!inode_trylock(inode)) { + ret = -EAGAIN; goto out; } -write: - ret = __generic_file_write_iter(iocb, from); - clear_inode_flag(inode, FI_NO_PREALLOC); + } else { + inode_lock(inode); + } + + ret = f2fs_write_checks(iocb, from); + if (ret <= 0) + goto out_unlock; - /* if we couldn't write data, we should deallocate blocks. */ - if (preallocated && i_size_read(inode) < target_size) - f2fs_truncate(inode); + /* Determine whether we will do a direct write or a buffered write. */ + dio = f2fs_should_use_dio(inode, iocb, from); - if (ret > 0) - f2fs_update_iostat(F2FS_I_SB(inode), APP_WRITE_IO, ret); + /* Possibly preallocate the blocks for the write. */ + target_size = iocb->ki_pos + iov_iter_count(from); + preallocated = f2fs_preallocate_blocks(iocb, from, dio); + if (preallocated < 0) { + ret = preallocated; + } else { + if (trace_f2fs_datawrite_start_enabled()) { + char *p = f2fs_kmalloc(F2FS_I_SB(inode), + PATH_MAX, GFP_KERNEL); + char *path; + + if (!p) + goto skip_write_trace; + path = dentry_path_raw(file_dentry(iocb->ki_filp), + p, PATH_MAX); + if (IS_ERR(path)) { + kfree(p); + goto skip_write_trace; + } + trace_f2fs_datawrite_start(inode, orig_pos, orig_count, + current->pid, path, current->comm); + kfree(p); + } +skip_write_trace: + /* Do the actual write. */ + ret = dio ? + f2fs_dio_write_iter(iocb, from, &may_need_sync) : + f2fs_buffered_write_iter(iocb, from); + + if (trace_f2fs_datawrite_end_enabled()) + trace_f2fs_datawrite_end(inode, orig_pos, ret); } + + /* Don't leave any preallocated blocks around past i_size. */ + if (preallocated && i_size_read(inode) < target_size) { + f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + filemap_invalidate_lock(inode->i_mapping); + if (!f2fs_truncate(inode)) + file_dont_truncate(inode); + filemap_invalidate_unlock(inode->i_mapping); + f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + } else { + file_dont_truncate(inode); + } + + clear_inode_flag(inode, FI_PREALLOCATED_ALL); +out_unlock: inode_unlock(inode); out: - trace_f2fs_file_write_iter(inode, iocb->ki_pos, - iov_iter_count(from), ret); - if (ret > 0) + trace_f2fs_file_write_iter(inode, orig_pos, orig_count, ret); + if (ret > 0 && may_need_sync) ret = generic_write_sync(iocb, ret); return ret; } +static int f2fs_file_fadvise(struct file *filp, loff_t offset, loff_t len, + int advice) +{ + struct address_space *mapping; + struct backing_dev_info *bdi; + struct inode *inode = file_inode(filp); + int err; + + if (advice == POSIX_FADV_SEQUENTIAL) { + if (S_ISFIFO(inode->i_mode)) + return -ESPIPE; + + mapping = filp->f_mapping; + if (!mapping || len < 0) + return -EINVAL; + + bdi = inode_to_bdi(mapping->host); + filp->f_ra.ra_pages = bdi->ra_pages * + F2FS_I_SB(inode)->seq_file_ra_mul; + spin_lock(&filp->f_lock); + filp->f_mode &= ~FMODE_RANDOM; + spin_unlock(&filp->f_lock); + return 0; + } + + err = generic_fadvise(filp, offset, len, advice); + if (!err && advice == POSIX_FADV_DONTNEED && + test_opt(F2FS_I_SB(inode), COMPRESS_CACHE) && + f2fs_compressed_file(inode)) + f2fs_invalidate_compress_pages(F2FS_I_SB(inode), inode->i_ino); + + return err; +} + #ifdef CONFIG_COMPAT +struct compat_f2fs_gc_range { + u32 sync; + compat_u64 start; + compat_u64 len; +}; +#define F2FS_IOC32_GARBAGE_COLLECT_RANGE _IOW(F2FS_IOCTL_MAGIC, 11,\ + struct compat_f2fs_gc_range) + +static int f2fs_compat_ioc_gc_range(struct file *file, unsigned long arg) +{ + struct compat_f2fs_gc_range __user *urange; + struct f2fs_gc_range range; + int err; + + urange = compat_ptr(arg); + err = get_user(range.sync, &urange->sync); + err |= get_user(range.start, &urange->start); + err |= get_user(range.len, &urange->len); + if (err) + return -EFAULT; + + return __f2fs_ioc_gc_range(file, &range); +} + +struct compat_f2fs_move_range { + u32 dst_fd; + compat_u64 pos_in; + compat_u64 pos_out; + compat_u64 len; +}; +#define F2FS_IOC32_MOVE_RANGE _IOWR(F2FS_IOCTL_MAGIC, 9, \ + struct compat_f2fs_move_range) + +static int f2fs_compat_ioc_move_range(struct file *file, unsigned long arg) +{ + struct compat_f2fs_move_range __user *urange; + struct f2fs_move_range range; + int err; + + urange = compat_ptr(arg); + err = get_user(range.dst_fd, &urange->dst_fd); + err |= get_user(range.pos_in, &urange->pos_in); + err |= get_user(range.pos_out, &urange->pos_out); + err |= get_user(range.len, &urange->len); + if (err) + return -EFAULT; + + return __f2fs_ioc_move_range(file, &range); +} + long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { + if (unlikely(f2fs_cp_error(F2FS_I_SB(file_inode(file))))) + return -EIO; + if (!f2fs_is_checkpoint_ready(F2FS_I_SB(file_inode(file)))) + return -ENOSPC; + switch (cmd) { - case F2FS_IOC32_GETFLAGS: - cmd = F2FS_IOC_GETFLAGS; - break; - case F2FS_IOC32_SETFLAGS: - cmd = F2FS_IOC_SETFLAGS; - break; - case F2FS_IOC32_GETVERSION: - cmd = F2FS_IOC_GETVERSION; + case FS_IOC32_GETVERSION: + cmd = FS_IOC_GETVERSION; break; + case F2FS_IOC32_GARBAGE_COLLECT_RANGE: + return f2fs_compat_ioc_gc_range(file, arg); + case F2FS_IOC32_MOVE_RANGE: + return f2fs_compat_ioc_move_range(file, arg); case F2FS_IOC_START_ATOMIC_WRITE: case F2FS_IOC_COMMIT_ATOMIC_WRITE: case F2FS_IOC_START_VOLATILE_WRITE: case F2FS_IOC_RELEASE_VOLATILE_WRITE: - case F2FS_IOC_ABORT_VOLATILE_WRITE: + case F2FS_IOC_ABORT_ATOMIC_WRITE: case F2FS_IOC_SHUTDOWN: case FITRIM: - case F2FS_IOC_SET_ENCRYPTION_POLICY: - case F2FS_IOC_GET_ENCRYPTION_PWSALT: - case F2FS_IOC_GET_ENCRYPTION_POLICY: + case FS_IOC_SET_ENCRYPTION_POLICY: + case FS_IOC_GET_ENCRYPTION_PWSALT: + case FS_IOC_GET_ENCRYPTION_POLICY: case FS_IOC_GET_ENCRYPTION_POLICY_EX: case FS_IOC_ADD_ENCRYPTION_KEY: case FS_IOC_REMOVE_ENCRYPTION_KEY: case FS_IOC_REMOVE_ENCRYPTION_KEY_ALL_USERS: case FS_IOC_GET_ENCRYPTION_KEY_STATUS: + case FS_IOC_GET_ENCRYPTION_NONCE: case F2FS_IOC_GARBAGE_COLLECT: - case F2FS_IOC_GARBAGE_COLLECT_RANGE: case F2FS_IOC_WRITE_CHECKPOINT: case F2FS_IOC_DEFRAGMENT: - case F2FS_IOC_MOVE_RANGE: case F2FS_IOC_FLUSH_DEVICE: case F2FS_IOC_GET_FEATURES: - case F2FS_IOC_FSGETXATTR: - case F2FS_IOC_FSSETXATTR: case F2FS_IOC_GET_PIN_FILE: case F2FS_IOC_SET_PIN_FILE: case F2FS_IOC_PRECACHE_EXTENTS: case F2FS_IOC_RESIZE_FS: case FS_IOC_ENABLE_VERITY: case FS_IOC_MEASURE_VERITY: - case F2FS_IOC_GET_VOLUME_NAME: - case F2FS_IOC_SET_VOLUME_NAME: + case FS_IOC_READ_VERITY_METADATA: + case FS_IOC_GETFSLABEL: + case FS_IOC_SETFSLABEL: + case F2FS_IOC_GET_COMPRESS_BLOCKS: + case F2FS_IOC_RELEASE_COMPRESS_BLOCKS: + case F2FS_IOC_RESERVE_COMPRESS_BLOCKS: + case F2FS_IOC_SEC_TRIM_FILE: + case F2FS_IOC_GET_COMPRESS_OPTION: + case F2FS_IOC_SET_COMPRESS_OPTION: + case F2FS_IOC_DECOMPRESS_FILE: + case F2FS_IOC_COMPRESS_FILE: break; default: return -ENOIOCTLCMD; } - return f2fs_ioctl(file, cmd, (unsigned long) compat_ptr(arg)); + return __f2fs_ioctl(file, cmd, (unsigned long) compat_ptr(arg)); } #endif @@ -3652,4 +4866,5 @@ const struct file_operations f2fs_file_operations = { #endif .splice_read = generic_file_splice_read, .splice_write = iter_file_splice_write, + .fadvise = f2fs_file_fadvise, }; |