diff --git a/Documentation/ABI/testing/sysfs-fs-f2fs b/Documentation/ABI/testing/sysfs-fs-f2fs index 1a6cd5397129..bd8a0d19abe6 100644 --- a/Documentation/ABI/testing/sysfs-fs-f2fs +++ b/Documentation/ABI/testing/sysfs-fs-f2fs @@ -318,3 +318,8 @@ Date: September 2019 Contact: "Hridya Valsaraju" Description: Average number of valid blocks. Available when CONFIG_F2FS_STAT_FS=y. + +What: /sys/fs/f2fs//mounted_time_sec +Date: February 2020 +Contact: "Jaegeuk Kim" +Description: Show the mounted time in secs of this partition. diff --git a/Documentation/filesystems/f2fs.rst b/Documentation/filesystems/f2fs.rst index d681203728d7..87d794bc75a4 100644 --- a/Documentation/filesystems/f2fs.rst +++ b/Documentation/filesystems/f2fs.rst @@ -243,8 +243,8 @@ checkpoint=%s[:%u[%]] Set to "disable" to turn off checkpointing. Set to "enabl hide up to all remaining free space. The actual space that would be unusable can be viewed at /sys/fs/f2fs//unusable This space is reclaimed once checkpoint=enable. -compress_algorithm=%s Control compress algorithm, currently f2fs supports "lzo" - and "lz4" algorithm. +compress_algorithm=%s Control compress algorithm, currently f2fs supports "lzo", + "lz4" and "zstd" algorithm. compress_log_size=%u Support configuring compress cluster size, the size will be 4KB * (1 << %u), 16KB is minimum size, also it's default size. diff --git a/fs/f2fs/Kconfig b/fs/f2fs/Kconfig index f0faada30f30..bb68d21e1f8c 100644 --- a/fs/f2fs/Kconfig +++ b/fs/f2fs/Kconfig @@ -118,3 +118,12 @@ config F2FS_FS_LZ4 default y help Support LZ4 compress algorithm, if unsure, say Y. + +config F2FS_FS_ZSTD + bool "ZSTD compression support" + depends on F2FS_FS_COMPRESSION + select ZSTD_COMPRESS + select ZSTD_DECOMPRESS + default y + help + Support ZSTD compress algorithm, if unsure, say Y. diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index 44e84ac5c941..852890b72d6a 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -50,9 +50,6 @@ repeat: return page; } -/* - * We guarantee no failure on the returned page. - */ static struct page *__get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index, bool is_meta) { @@ -206,7 +203,7 @@ bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi, } /* - * Readahead CP/NAT/SIT/SSA pages + * Readahead CP/NAT/SIT/SSA/POR pages */ int f2fs_ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, int type, bool sync) @@ -898,7 +895,7 @@ int f2fs_get_valid_checkpoint(struct f2fs_sb_info *sbi) return -ENOMEM; /* * Finding out valid cp block involves read both - * sets( cp pack1 and cp pack 2) + * sets( cp pack 1 and cp pack 2) */ cp_start_blk_no = le32_to_cpu(fsb->cp_blkaddr); cp1 = validate_checkpoint(sbi, cp_start_blk_no, &cp1_version); @@ -1250,20 +1247,20 @@ static void unblock_operations(struct f2fs_sb_info *sbi) f2fs_unlock_all(sbi); } -void f2fs_wait_on_all_pages_writeback(struct f2fs_sb_info *sbi) +void f2fs_wait_on_all_pages(struct f2fs_sb_info *sbi, int type) { DEFINE_WAIT(wait); for (;;) { prepare_to_wait(&sbi->cp_wait, &wait, TASK_UNINTERRUPTIBLE); - if (!get_pages(sbi, F2FS_WB_CP_DATA)) + if (!get_pages(sbi, type)) break; if (unlikely(f2fs_cp_error(sbi))) break; - io_schedule_timeout(5*HZ); + io_schedule_timeout(DEFAULT_IO_TIMEOUT); } finish_wait(&sbi->cp_wait, &wait); } @@ -1301,10 +1298,14 @@ static void update_ckpt_flags(struct f2fs_sb_info *sbi, struct cp_control *cpc) else __clear_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG); - if (is_sbi_flag_set(sbi, SBI_NEED_FSCK) || - is_sbi_flag_set(sbi, SBI_IS_RESIZEFS)) + if (is_sbi_flag_set(sbi, SBI_NEED_FSCK)) __set_ckpt_flags(ckpt, CP_FSCK_FLAG); + if (is_sbi_flag_set(sbi, SBI_IS_RESIZEFS)) + __set_ckpt_flags(ckpt, CP_RESIZEFS_FLAG); + else + __clear_ckpt_flags(ckpt, CP_RESIZEFS_FLAG); + if (is_sbi_flag_set(sbi, SBI_CP_DISABLED)) __set_ckpt_flags(ckpt, CP_DISABLED_FLAG); else @@ -1384,13 +1385,8 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) /* Flush all the NAT/SIT pages */ f2fs_sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO); - f2fs_bug_on(sbi, get_pages(sbi, F2FS_DIRTY_META) && - !f2fs_cp_error(sbi)); - /* - * modify checkpoint - * version number is already updated - */ + /* start to update checkpoint, cp ver is already updated previously */ ckpt->elapsed_time = cpu_to_le64(get_mtime(sbi, true)); ckpt->free_segment_count = cpu_to_le32(free_segments(sbi)); for (i = 0; i < NR_CURSEG_NODE_TYPE; i++) { @@ -1493,11 +1489,11 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) /* Here, we have one bio having CP pack except cp pack 2 page */ f2fs_sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO); - f2fs_bug_on(sbi, get_pages(sbi, F2FS_DIRTY_META) && - !f2fs_cp_error(sbi)); + /* Wait for all dirty meta pages to be submitted for IO */ + f2fs_wait_on_all_pages(sbi, F2FS_DIRTY_META); /* wait for previous submitted meta pages writeback */ - f2fs_wait_on_all_pages_writeback(sbi); + f2fs_wait_on_all_pages(sbi, F2FS_WB_CP_DATA); /* flush all device cache */ err = f2fs_flush_device_cache(sbi); @@ -1506,7 +1502,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) /* barrier and flush checkpoint cp pack 2 page if it can */ commit_checkpoint(sbi, ckpt, start_blk); - f2fs_wait_on_all_pages_writeback(sbi); + f2fs_wait_on_all_pages(sbi, F2FS_WB_CP_DATA); /* * invalidate intermediate page cache borrowed from meta inode which are @@ -1543,9 +1539,6 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) return unlikely(f2fs_cp_error(sbi)) ? -EIO : 0; } -/* - * We guarantee that this checkpoint procedure will not fail. - */ int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) { struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); @@ -1613,7 +1606,6 @@ int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) f2fs_flush_sit_entries(sbi, cpc); - /* unlock all the fs_lock[] in do_checkpoint() */ err = do_checkpoint(sbi, cpc); if (err) f2fs_release_discard_addrs(sbi); @@ -1626,7 +1618,7 @@ stop: if (cpc->reason & CP_RECOVERY) f2fs_notice(sbi, "checkpoint: version = %llx", ckpt_ver); - /* do checkpoint periodically */ + /* update CP_TIME to trigger checkpoint periodically */ f2fs_update_time(sbi, CP_TIME); trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish checkpoint"); out: diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c index d8a64be90a50..df7b2d15eacd 100644 --- a/fs/f2fs/compress.c +++ b/fs/f2fs/compress.c @@ -11,6 +11,7 @@ #include #include #include +#include #include "f2fs.h" #include "node.h" @@ -20,6 +21,8 @@ struct f2fs_compress_ops { int (*init_compress_ctx)(struct compress_ctx *cc); void (*destroy_compress_ctx)(struct compress_ctx *cc); int (*compress_pages)(struct compress_ctx *cc); + int (*init_decompress_ctx)(struct decompress_io_ctx *dic); + void (*destroy_decompress_ctx)(struct decompress_io_ctx *dic); int (*decompress_pages)(struct decompress_io_ctx *dic); }; @@ -52,7 +55,7 @@ bool f2fs_is_compressed_page(struct page *page) } static void f2fs_set_compressed_page(struct page *page, - struct inode *inode, pgoff_t index, void *data, refcount_t *r) + struct inode *inode, pgoff_t index, void *data) { SetPagePrivate(page); set_page_private(page, (unsigned long)data); @@ -60,8 +63,6 @@ static void f2fs_set_compressed_page(struct page *page, /* i_crypto_info and iv index */ page->index = index; page->mapping = inode->i_mapping; - if (r) - refcount_inc(r); } static void f2fs_put_compressed_page(struct page *page) @@ -291,6 +292,165 @@ static const struct f2fs_compress_ops f2fs_lz4_ops = { }; #endif +#ifdef CONFIG_F2FS_FS_ZSTD +#define F2FS_ZSTD_DEFAULT_CLEVEL 1 + +static int zstd_init_compress_ctx(struct compress_ctx *cc) +{ + ZSTD_parameters params; + ZSTD_CStream *stream; + void *workspace; + unsigned int workspace_size; + + params = ZSTD_getParams(F2FS_ZSTD_DEFAULT_CLEVEL, cc->rlen, 0); + workspace_size = ZSTD_CStreamWorkspaceBound(params.cParams); + + workspace = f2fs_kvmalloc(F2FS_I_SB(cc->inode), + workspace_size, GFP_NOFS); + if (!workspace) + return -ENOMEM; + + stream = ZSTD_initCStream(params, 0, workspace, workspace_size); + if (!stream) { + printk_ratelimited("%sF2FS-fs (%s): %s ZSTD_initCStream failed\n", + KERN_ERR, F2FS_I_SB(cc->inode)->sb->s_id, + __func__); + kvfree(workspace); + return -EIO; + } + + cc->private = workspace; + cc->private2 = stream; + + cc->clen = cc->rlen - PAGE_SIZE - COMPRESS_HEADER_SIZE; + return 0; +} + +static void zstd_destroy_compress_ctx(struct compress_ctx *cc) +{ + kvfree(cc->private); + cc->private = NULL; + cc->private2 = NULL; +} + +static int zstd_compress_pages(struct compress_ctx *cc) +{ + ZSTD_CStream *stream = cc->private2; + ZSTD_inBuffer inbuf; + ZSTD_outBuffer outbuf; + int src_size = cc->rlen; + int dst_size = src_size - PAGE_SIZE - COMPRESS_HEADER_SIZE; + int ret; + + inbuf.pos = 0; + inbuf.src = cc->rbuf; + inbuf.size = src_size; + + outbuf.pos = 0; + outbuf.dst = cc->cbuf->cdata; + outbuf.size = dst_size; + + ret = ZSTD_compressStream(stream, &outbuf, &inbuf); + if (ZSTD_isError(ret)) { + printk_ratelimited("%sF2FS-fs (%s): %s ZSTD_compressStream failed, ret: %d\n", + KERN_ERR, F2FS_I_SB(cc->inode)->sb->s_id, + __func__, ZSTD_getErrorCode(ret)); + return -EIO; + } + + ret = ZSTD_endStream(stream, &outbuf); + if (ZSTD_isError(ret)) { + printk_ratelimited("%sF2FS-fs (%s): %s ZSTD_endStream returned %d\n", + KERN_ERR, F2FS_I_SB(cc->inode)->sb->s_id, + __func__, ZSTD_getErrorCode(ret)); + return -EIO; + } + + cc->clen = outbuf.pos; + return 0; +} + +static int zstd_init_decompress_ctx(struct decompress_io_ctx *dic) +{ + ZSTD_DStream *stream; + void *workspace; + unsigned int workspace_size; + + workspace_size = ZSTD_DStreamWorkspaceBound(MAX_COMPRESS_WINDOW_SIZE); + + workspace = f2fs_kvmalloc(F2FS_I_SB(dic->inode), + workspace_size, GFP_NOFS); + if (!workspace) + return -ENOMEM; + + stream = ZSTD_initDStream(MAX_COMPRESS_WINDOW_SIZE, + workspace, workspace_size); + if (!stream) { + printk_ratelimited("%sF2FS-fs (%s): %s ZSTD_initDStream failed\n", + KERN_ERR, F2FS_I_SB(dic->inode)->sb->s_id, + __func__); + kvfree(workspace); + return -EIO; + } + + dic->private = workspace; + dic->private2 = stream; + + return 0; +} + +static void zstd_destroy_decompress_ctx(struct decompress_io_ctx *dic) +{ + kvfree(dic->private); + dic->private = NULL; + dic->private2 = NULL; +} + +static int zstd_decompress_pages(struct decompress_io_ctx *dic) +{ + ZSTD_DStream *stream = dic->private2; + ZSTD_inBuffer inbuf; + ZSTD_outBuffer outbuf; + int ret; + + inbuf.pos = 0; + inbuf.src = dic->cbuf->cdata; + inbuf.size = dic->clen; + + outbuf.pos = 0; + outbuf.dst = dic->rbuf; + outbuf.size = dic->rlen; + + ret = ZSTD_decompressStream(stream, &outbuf, &inbuf); + if (ZSTD_isError(ret)) { + printk_ratelimited("%sF2FS-fs (%s): %s ZSTD_compressStream failed, ret: %d\n", + KERN_ERR, F2FS_I_SB(dic->inode)->sb->s_id, + __func__, ZSTD_getErrorCode(ret)); + return -EIO; + } + + if (dic->rlen != outbuf.pos) { + printk_ratelimited("%sF2FS-fs (%s): %s ZSTD invalid rlen:%zu, " + "expected:%lu\n", KERN_ERR, + F2FS_I_SB(dic->inode)->sb->s_id, + __func__, dic->rlen, + PAGE_SIZE << dic->log_cluster_size); + return -EIO; + } + + return 0; +} + +static const struct f2fs_compress_ops f2fs_zstd_ops = { + .init_compress_ctx = zstd_init_compress_ctx, + .destroy_compress_ctx = zstd_destroy_compress_ctx, + .compress_pages = zstd_compress_pages, + .init_decompress_ctx = zstd_init_decompress_ctx, + .destroy_decompress_ctx = zstd_destroy_decompress_ctx, + .decompress_pages = zstd_decompress_pages, +}; +#endif + static const struct f2fs_compress_ops *f2fs_cops[COMPRESS_MAX] = { #ifdef CONFIG_F2FS_FS_LZO &f2fs_lzo_ops, @@ -302,6 +462,11 @@ static const struct f2fs_compress_ops *f2fs_cops[COMPRESS_MAX] = { #else NULL, #endif +#ifdef CONFIG_F2FS_FS_ZSTD + &f2fs_zstd_ops, +#else + NULL, +#endif }; bool f2fs_is_compress_backend_ready(struct inode *inode) @@ -334,9 +499,11 @@ static int f2fs_compress_pages(struct compress_ctx *cc) trace_f2fs_compress_pages_start(cc->inode, cc->cluster_idx, cc->cluster_size, fi->i_compress_algorithm); - ret = cops->init_compress_ctx(cc); - if (ret) - goto out; + if (cops->init_compress_ctx) { + ret = cops->init_compress_ctx(cc); + if (ret) + goto out; + } max_len = COMPRESS_HEADER_SIZE + cc->clen; cc->nr_cpages = DIV_ROUND_UP(max_len, PAGE_SIZE); @@ -380,21 +547,27 @@ static int f2fs_compress_pages(struct compress_ctx *cc) } cc->cbuf->clen = cpu_to_le32(cc->clen); - cc->cbuf->chksum = cpu_to_le32(0); for (i = 0; i < COMPRESS_DATA_RESERVED_SIZE; i++) cc->cbuf->reserved[i] = cpu_to_le32(0); + nr_cpages = DIV_ROUND_UP(cc->clen + COMPRESS_HEADER_SIZE, PAGE_SIZE); + + /* zero out any unused part of the last page */ + memset(&cc->cbuf->cdata[cc->clen], 0, + (nr_cpages * PAGE_SIZE) - (cc->clen + COMPRESS_HEADER_SIZE)); + vunmap(cc->cbuf); vunmap(cc->rbuf); - nr_cpages = DIV_ROUND_UP(cc->clen + COMPRESS_HEADER_SIZE, PAGE_SIZE); - for (i = nr_cpages; i < cc->nr_cpages; i++) { f2fs_put_compressed_page(cc->cpages[i]); cc->cpages[i] = NULL; } + if (cops->destroy_compress_ctx) + cops->destroy_compress_ctx(cc); + cc->nr_cpages = nr_cpages; trace_f2fs_compress_pages_end(cc->inode, cc->cluster_idx, @@ -413,7 +586,8 @@ out_free_cpages: kfree(cc->cpages); cc->cpages = NULL; destroy_compress_ctx: - cops->destroy_compress_ctx(cc); + if (cops->destroy_compress_ctx) + cops->destroy_compress_ctx(cc); out: trace_f2fs_compress_pages_end(cc->inode, cc->cluster_idx, cc->clen, ret); @@ -447,10 +621,16 @@ void f2fs_decompress_pages(struct bio *bio, struct page *page, bool verity) goto out_free_dic; } + if (cops->init_decompress_ctx) { + ret = cops->init_decompress_ctx(dic); + if (ret) + goto out_free_dic; + } + dic->rbuf = vmap(dic->tpages, dic->cluster_size, VM_MAP, PAGE_KERNEL); if (!dic->rbuf) { ret = -ENOMEM; - goto out_free_dic; + goto destroy_decompress_ctx; } dic->cbuf = vmap(dic->cpages, dic->nr_cpages, VM_MAP, PAGE_KERNEL_RO); @@ -473,7 +653,12 @@ out_vunmap_cbuf: vunmap(dic->cbuf); out_vunmap_rbuf: vunmap(dic->rbuf); +destroy_decompress_ctx: + if (cops->destroy_decompress_ctx) + cops->destroy_decompress_ctx(dic); out_free_dic: + if (verity) + refcount_set(&dic->ref, dic->nr_cpages); if (!verity) f2fs_decompress_end_io(dic->rpages, dic->cluster_size, ret, false); @@ -532,8 +717,7 @@ static bool __cluster_may_compress(struct compress_ctx *cc) return true; } -/* return # of compressed block addresses */ -static int f2fs_compressed_blocks(struct compress_ctx *cc) +static int __f2fs_cluster_blocks(struct compress_ctx *cc, bool compr) { struct dnode_of_data dn; int ret; @@ -554,10 +738,15 @@ static int f2fs_compressed_blocks(struct compress_ctx *cc) for (i = 1; i < cc->cluster_size; i++) { block_t blkaddr; - blkaddr = datablock_addr(dn.inode, + blkaddr = data_blkaddr(dn.inode, dn.node_page, dn.ofs_in_node + i); - if (blkaddr != NULL_ADDR) - ret++; + if (compr) { + if (__is_valid_data_blkaddr(blkaddr)) + ret++; + } else { + if (blkaddr != NULL_ADDR) + ret++; + } } } fail: @@ -565,6 +754,18 @@ fail: return ret; } +/* return # of compressed blocks in compressed cluster */ +static int f2fs_compressed_blocks(struct compress_ctx *cc) +{ + return __f2fs_cluster_blocks(cc, true); +} + +/* return # of valid blocks in compressed cluster */ +static int f2fs_cluster_blocks(struct compress_ctx *cc, bool compr) +{ + return __f2fs_cluster_blocks(cc, false); +} + int f2fs_is_compressed_cluster(struct inode *inode, pgoff_t index) { struct compress_ctx cc = { @@ -574,7 +775,7 @@ int f2fs_is_compressed_cluster(struct inode *inode, pgoff_t index) .cluster_idx = index >> F2FS_I(inode)->i_log_cluster_size, }; - return f2fs_compressed_blocks(&cc); + return f2fs_cluster_blocks(&cc, false); } static bool cluster_may_compress(struct compress_ctx *cc) @@ -623,7 +824,7 @@ static int prepare_compress_overwrite(struct compress_ctx *cc, bool prealloc; retry: - ret = f2fs_compressed_blocks(cc); + ret = f2fs_cluster_blocks(cc, false); if (ret <= 0) return ret; @@ -653,7 +854,7 @@ retry: struct bio *bio = NULL; ret = f2fs_read_multi_pages(cc, &bio, cc->cluster_size, - &last_block_in_bio, false); + &last_block_in_bio, false, true); f2fs_destroy_compress_ctx(cc); if (ret) goto release_pages; @@ -772,7 +973,6 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc, .encrypted_page = NULL, .compressed_page = NULL, .submitted = false, - .need_lock = LOCK_RETRY, .io_type = io_type, .io_wbc = wbc, .encrypted = f2fs_encrypted_file(cc->inode), @@ -785,16 +985,17 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc, loff_t psize; int i, err; - set_new_dnode(&dn, cc->inode, NULL, NULL, 0); + if (!f2fs_trylock_op(sbi)) + return -EAGAIN; - f2fs_lock_op(sbi); + set_new_dnode(&dn, cc->inode, NULL, NULL, 0); err = f2fs_get_dnode_of_data(&dn, start_idx, LOOKUP_NODE); if (err) goto out_unlock_op; for (i = 0; i < cc->cluster_size; i++) { - if (datablock_addr(dn.inode, dn.node_page, + if (data_blkaddr(dn.inode, dn.node_page, dn.ofs_in_node + i) == NULL_ADDR) goto out_put_dnode; } @@ -813,7 +1014,7 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc, cic->magic = F2FS_COMPRESSED_PAGE_MAGIC; cic->inode = inode; - refcount_set(&cic->ref, 1); + refcount_set(&cic->ref, cc->nr_cpages); cic->rpages = f2fs_kzalloc(sbi, sizeof(struct page *) << cc->log_cluster_size, GFP_NOFS); if (!cic->rpages) @@ -823,8 +1024,7 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc, for (i = 0; i < cc->nr_cpages; i++) { f2fs_set_compressed_page(cc->cpages[i], inode, - cc->rpages[i + 1]->index, - cic, i ? &cic->ref : NULL); + cc->rpages[i + 1]->index, cic); fio.compressed_page = cc->cpages[i]; if (fio.encrypted) { fio.page = cc->rpages[i + 1]; @@ -843,9 +1043,8 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc, for (i = 0; i < cc->cluster_size; i++, dn.ofs_in_node++) { block_t blkaddr; - blkaddr = datablock_addr(dn.inode, dn.node_page, - dn.ofs_in_node); - fio.page = cic->rpages[i]; + blkaddr = f2fs_data_blkaddr(&dn); + fio.page = cc->rpages[i]; fio.old_blkaddr = blkaddr; /* cluster header */ @@ -895,10 +1094,10 @@ unlock_continue: f2fs_put_dnode(&dn); f2fs_unlock_op(sbi); - down_write(&fi->i_sem); + spin_lock(&fi->i_size_lock); if (fi->last_disk_size < psize) fi->last_disk_size = psize; - up_write(&fi->i_sem); + spin_unlock(&fi->i_size_lock); f2fs_put_rpages(cc); f2fs_destroy_compress_ctx(cc); @@ -984,24 +1183,30 @@ retry_write: unlock_page(cc->rpages[i]); ret = 0; } else if (ret == -EAGAIN) { + /* + * for quota file, just redirty left pages to + * avoid deadlock caused by cluster update race + * from foreground operation. + */ + if (IS_NOQUOTA(cc->inode)) { + err = 0; + goto out_err; + } ret = 0; cond_resched(); - congestion_wait(BLK_RW_ASYNC, HZ/50); + congestion_wait(BLK_RW_ASYNC, + DEFAULT_IO_TIMEOUT); lock_page(cc->rpages[i]); clear_page_dirty_for_io(cc->rpages[i]); goto retry_write; } err = ret; - goto out_fail; + goto out_err; } *submitted += _submitted; } return 0; - -out_fail: - /* TODO: revoke partially updated block addresses */ - BUG_ON(compr_blocks); out_err: for (++i; i < cc->cluster_size; i++) { if (!cc->rpages[i]) @@ -1069,7 +1274,7 @@ struct decompress_io_ctx *f2fs_alloc_dic(struct compress_ctx *cc) dic->magic = F2FS_COMPRESSED_PAGE_MAGIC; dic->inode = cc->inode; - refcount_set(&dic->ref, 1); + refcount_set(&dic->ref, cc->nr_cpages); dic->cluster_idx = cc->cluster_idx; dic->cluster_size = cc->cluster_size; dic->log_cluster_size = cc->log_cluster_size; @@ -1093,8 +1298,7 @@ struct decompress_io_ctx *f2fs_alloc_dic(struct compress_ctx *cc) goto out_free; f2fs_set_compressed_page(page, cc->inode, - start_idx + i + 1, - dic, i ? &dic->ref : NULL); + start_idx + i + 1, dic); dic->cpages[i] = page; } @@ -1104,20 +1308,16 @@ struct decompress_io_ctx *f2fs_alloc_dic(struct compress_ctx *cc) goto out_free; for (i = 0; i < dic->cluster_size; i++) { - if (cc->rpages[i]) + if (cc->rpages[i]) { + dic->tpages[i] = cc->rpages[i]; continue; + } dic->tpages[i] = f2fs_grab_page(); if (!dic->tpages[i]) goto out_free; } - for (i = 0; i < dic->cluster_size; i++) { - if (dic->tpages[i]) - continue; - dic->tpages[i] = cc->rpages[i]; - } - return dic; out_free: @@ -1133,7 +1333,10 @@ void f2fs_free_dic(struct decompress_io_ctx *dic) for (i = 0; i < dic->cluster_size; i++) { if (dic->rpages[i]) continue; - f2fs_put_page(dic->tpages[i], 1); + if (!dic->tpages[i]) + continue; + unlock_page(dic->tpages[i]); + put_page(dic->tpages[i]); } kfree(dic->tpages); } @@ -1162,15 +1365,17 @@ void f2fs_decompress_end_io(struct page **rpages, if (!rpage) continue; - if (err || PageError(rpage)) { - ClearPageUptodate(rpage); - ClearPageError(rpage); - } else { - if (!verity || fsverity_verify_page(rpage)) - SetPageUptodate(rpage); - else - SetPageError(rpage); + if (err || PageError(rpage)) + goto clear_uptodate; + + if (!verity || fsverity_verify_page(rpage)) { + SetPageUptodate(rpage); + goto unlock; } +clear_uptodate: + ClearPageUptodate(rpage); + ClearPageError(rpage); +unlock: unlock_page(rpage); } } diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index b27b72107911..cdf2f626bea7 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -54,17 +54,13 @@ static inline struct bio *__f2fs_bio_alloc(gfp_t gfp_mask, return bio_alloc_bioset(gfp_mask, nr_iovecs, &f2fs_bioset); } -struct bio *f2fs_bio_alloc(struct f2fs_sb_info *sbi, int npages, bool no_fail) +struct bio *f2fs_bio_alloc(struct f2fs_sb_info *sbi, int npages, bool noio) { - struct bio *bio; - - if (no_fail) { + if (noio) { /* No failure on bio allocation */ - bio = __f2fs_bio_alloc(GFP_NOIO, npages); - if (!bio) - bio = __f2fs_bio_alloc(GFP_NOIO | __GFP_NOFAIL, npages); - return bio; + return __f2fs_bio_alloc(GFP_NOIO, npages); } + if (time_to_inject(sbi, FAULT_ALLOC_BIO)) { f2fs_show_injection_info(sbi, FAULT_ALLOC_BIO); return NULL; @@ -143,6 +139,8 @@ static void __read_end_io(struct bio *bio, bool compr, bool verity) f2fs_decompress_pages(bio, page, verity); continue; } + if (verity) + continue; #endif /* PG_error was set if any post_read step failed */ @@ -191,12 +189,38 @@ static void f2fs_verify_pages(struct page **rpages, unsigned int cluster_size) static void f2fs_verify_bio(struct bio *bio) { - struct page *page = bio_first_page_all(bio); - struct decompress_io_ctx *dic = - (struct decompress_io_ctx *)page_private(page); + struct bio_vec *bv; + struct bvec_iter_all iter_all; - f2fs_verify_pages(dic->rpages, dic->cluster_size); - f2fs_free_dic(dic); + bio_for_each_segment_all(bv, bio, iter_all) { + struct page *page = bv->bv_page; + struct decompress_io_ctx *dic; + + dic = (struct decompress_io_ctx *)page_private(page); + + if (dic) { + if (refcount_dec_not_one(&dic->ref)) + continue; + f2fs_verify_pages(dic->rpages, + dic->cluster_size); + f2fs_free_dic(dic); + continue; + } + + if (bio->bi_status || PageError(page)) + goto clear_uptodate; + + if (fsverity_verify_page(page)) { + SetPageUptodate(page); + goto unlock; + } +clear_uptodate: + ClearPageUptodate(page); + ClearPageError(page); +unlock: + dec_page_count(F2FS_P_SB(page), __read_io_type(page)); + unlock_page(page); + } } #endif @@ -364,9 +388,6 @@ static void f2fs_write_end_io(struct bio *bio) bio_put(bio); } -/* - * Return true, if pre_bio's bdev is same as its target device. - */ struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi, block_t blk_addr, struct bio *bio) { @@ -403,6 +424,9 @@ int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr) return 0; } +/* + * Return true, if pre_bio's bdev is same as its target device. + */ static bool __same_bdev(struct f2fs_sb_info *sbi, block_t blk_addr, struct bio *bio) { @@ -410,9 +434,6 @@ static bool __same_bdev(struct f2fs_sb_info *sbi, return bio->bi_disk == b->bd_disk && bio->bi_partno == b->bd_partno; } -/* - * Low-level block read/write IO operations. - */ static struct bio *__bio_alloc(struct f2fs_io_info *fio, int npages) { struct f2fs_sb_info *sbi = fio->sbi; @@ -445,7 +466,7 @@ static inline void __submit_bio(struct f2fs_sb_info *sbi, if (type != DATA && type != NODE) goto submit_io; - if (test_opt(sbi, LFS) && current->plug) + if (f2fs_lfs_mode(sbi) && current->plug) blk_finish_plug(current->plug); if (F2FS_IO_ALIGNED(sbi)) @@ -928,14 +949,15 @@ static inline bool f2fs_need_verity(const struct inode *inode, pgoff_t idx) static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr, unsigned nr_pages, unsigned op_flag, - pgoff_t first_idx) + pgoff_t first_idx, bool for_write) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct bio *bio; struct bio_post_read_ctx *ctx; unsigned int post_read_steps = 0; - bio = f2fs_bio_alloc(sbi, min_t(int, nr_pages, BIO_MAX_PAGES), false); + bio = f2fs_bio_alloc(sbi, min_t(int, nr_pages, BIO_MAX_PAGES), + for_write); if (!bio) return ERR_PTR(-ENOMEM); f2fs_target_device(sbi, blkaddr, bio); @@ -970,12 +992,12 @@ static void f2fs_release_read_bio(struct bio *bio) /* This can handle encryption stuffs */ static int f2fs_submit_page_read(struct inode *inode, struct page *page, - block_t blkaddr) + block_t blkaddr, bool for_write) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct bio *bio; - bio = f2fs_grab_read_bio(inode, blkaddr, 1, 0, page->index); + bio = f2fs_grab_read_bio(inode, blkaddr, 1, 0, page->index, for_write); if (IS_ERR(bio)) return PTR_ERR(bio); @@ -1047,8 +1069,7 @@ int f2fs_reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count) f2fs_wait_on_page_writeback(dn->node_page, NODE, true, true); for (; count > 0; dn->ofs_in_node++) { - block_t blkaddr = datablock_addr(dn->inode, - dn->node_page, dn->ofs_in_node); + block_t blkaddr = f2fs_data_blkaddr(dn); if (blkaddr == NULL_ADDR) { dn->data_blkaddr = NEW_ADDR; __set_data_blkaddr(dn); @@ -1162,7 +1183,7 @@ got_it: return page; } - err = f2fs_submit_page_read(inode, page, dn.data_blkaddr); + err = f2fs_submit_page_read(inode, page, dn.data_blkaddr, for_write); if (err) goto put_err; return page; @@ -1300,8 +1321,7 @@ static int __allocate_data_block(struct dnode_of_data *dn, int seg_type) if (err) return err; - dn->data_blkaddr = datablock_addr(dn->inode, - dn->node_page, dn->ofs_in_node); + dn->data_blkaddr = f2fs_data_blkaddr(dn); if (dn->data_blkaddr != NULL_ADDR) goto alloc; @@ -1388,13 +1408,9 @@ void __do_map_lock(struct f2fs_sb_info *sbi, int flag, bool lock) } /* - * f2fs_map_blocks() now supported readahead/bmap/rw direct_IO with - * f2fs_map_blocks structure. - * If original data blocks are allocated, then give them to blockdev. - * Otherwise, - * a. preallocate requested block addresses - * b. do not use extent cache for better performance - * c. give the block addresses to blockdev + * f2fs_map_blocks() tries to find or build mapping relationship which + * maps continuous logical blocks to physical blocks, and return such + * info via f2fs_map_blocks structure. */ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map, int create, int flag) @@ -1422,7 +1438,7 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map, end = pgofs + maxblocks; if (!create && f2fs_lookup_extent_cache(inode, pgofs, &ei)) { - if (test_opt(sbi, LFS) && flag == F2FS_GET_BLOCK_DIO && + if (f2fs_lfs_mode(sbi) && flag == F2FS_GET_BLOCK_DIO && map->m_may_create) goto next_dnode; @@ -1467,7 +1483,7 @@ next_dnode: end_offset = ADDRS_PER_PAGE(dn.node_page, inode); next_block: - 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)) { @@ -1477,7 +1493,7 @@ next_block: if (__is_valid_data_blkaddr(blkaddr)) { /* use out-place-update for driect IO under LFS mode */ - if (test_opt(sbi, LFS) && flag == F2FS_GET_BLOCK_DIO && + if (f2fs_lfs_mode(sbi) && flag == F2FS_GET_BLOCK_DIO && map->m_may_create) { err = __allocate_data_block(&dn, map->m_seg_type); if (err) @@ -1980,7 +1996,8 @@ submit_and_realloc: } if (bio == NULL) { bio = f2fs_grab_read_bio(inode, block_nr, nr_pages, - is_readahead ? REQ_RAHEAD : 0, page->index); + is_readahead ? REQ_RAHEAD : 0, page->index, + false); if (IS_ERR(bio)) { ret = PTR_ERR(bio); bio = NULL; @@ -2015,7 +2032,7 @@ out: #ifdef CONFIG_F2FS_FS_COMPRESSION int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret, unsigned nr_pages, sector_t *last_block_in_bio, - bool is_readahead) + bool is_readahead, bool for_write) { struct dnode_of_data dn; struct inode *inode = cc->inode; @@ -2031,7 +2048,8 @@ int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret, f2fs_bug_on(sbi, f2fs_cluster_is_empty(cc)); - last_block_in_file = (i_size_read(inode) + blocksize - 1) >> blkbits; + last_block_in_file = (f2fs_readpage_limit(inode) + + blocksize - 1) >> blkbits; /* get rid of pages beyond EOF */ for (i = 0; i < cc->cluster_size; i++) { @@ -2067,7 +2085,7 @@ int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret, for (i = 1; i < cc->cluster_size; i++) { block_t blkaddr; - blkaddr = datablock_addr(dn.inode, dn.node_page, + blkaddr = data_blkaddr(dn.inode, dn.node_page, dn.ofs_in_node + i); if (!__is_valid_data_blkaddr(blkaddr)) @@ -2096,7 +2114,7 @@ int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret, struct page *page = dic->cpages[i]; block_t blkaddr; - blkaddr = datablock_addr(dn.inode, dn.node_page, + blkaddr = data_blkaddr(dn.inode, dn.node_page, dn.ofs_in_node + i + 1); if (bio && !page_is_mergeable(sbi, bio, @@ -2109,7 +2127,7 @@ submit_and_realloc: if (!bio) { bio = f2fs_grab_read_bio(inode, blkaddr, nr_pages, is_readahead ? REQ_RAHEAD : 0, - page->index); + page->index, for_write); if (IS_ERR(bio)) { ret = PTR_ERR(bio); bio = NULL; @@ -2210,7 +2228,7 @@ int f2fs_mpage_readpages(struct address_space *mapping, ret = f2fs_read_multi_pages(&cc, &bio, max_nr_pages, &last_block_in_bio, - is_readahead); + is_readahead, false); f2fs_destroy_compress_ctx(&cc); if (ret) goto set_error_page; @@ -2253,7 +2271,7 @@ next_page: ret = f2fs_read_multi_pages(&cc, &bio, max_nr_pages, &last_block_in_bio, - is_readahead); + is_readahead, false); f2fs_destroy_compress_ctx(&cc); } } @@ -2326,7 +2344,7 @@ retry_encrypt: /* flush pending IOs and wait for a while in the ENOMEM case */ if (PTR_ERR(fio->encrypted_page) == -ENOMEM) { f2fs_flush_merged_writes(fio->sbi); - congestion_wait(BLK_RW_ASYNC, HZ/50); + congestion_wait(BLK_RW_ASYNC, DEFAULT_IO_TIMEOUT); gfp_flags |= __GFP_NOFAIL; goto retry_encrypt; } @@ -2397,7 +2415,7 @@ bool f2fs_should_update_outplace(struct inode *inode, struct f2fs_io_info *fio) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - if (test_opt(sbi, LFS)) + if (f2fs_lfs_mode(sbi)) return true; if (S_ISDIR(inode->i_mode)) return true; @@ -2647,10 +2665,10 @@ write: if (err) { file_set_keep_isize(inode); } else { - down_write(&F2FS_I(inode)->i_sem); + spin_lock(&F2FS_I(inode)->i_size_lock); if (F2FS_I(inode)->last_disk_size < psize) F2FS_I(inode)->last_disk_size = psize; - up_write(&F2FS_I(inode)->i_sem); + spin_unlock(&F2FS_I(inode)->i_size_lock); } done: @@ -2917,7 +2935,7 @@ result: if (wbc->sync_mode == WB_SYNC_ALL) { cond_resched(); congestion_wait(BLK_RW_ASYNC, - HZ/50); + DEFAULT_IO_TIMEOUT); goto retry_write; } goto next; @@ -2973,15 +2991,17 @@ next: static inline bool __should_serialize_io(struct inode *inode, struct writeback_control *wbc) { - if (!S_ISREG(inode->i_mode)) - return false; - if (f2fs_compressed_file(inode)) - return true; - if (IS_NOQUOTA(inode)) - return false; /* to avoid deadlock in path of data flush */ if (F2FS_I(inode)->cp_task) return false; + + if (!S_ISREG(inode->i_mode)) + return false; + if (IS_NOQUOTA(inode)) + return false; + + if (f2fs_compressed_file(inode)) + return true; if (wbc->sync_mode != WB_SYNC_ALL) return true; if (get_dirty_pages(inode) >= SM_I(F2FS_I_SB(inode))->min_seq_blocks) @@ -3283,7 +3303,7 @@ repeat: err = -EFSCORRUPTED; goto fail; } - err = f2fs_submit_page_read(inode, page, blkaddr); + err = f2fs_submit_page_read(inode, page, blkaddr, true); if (err) goto fail; @@ -3464,7 +3484,8 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) err = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter, rw == WRITE ? get_data_block_dio_write : get_data_block_dio, NULL, f2fs_dio_submit_bio, - DIO_LOCKING | DIO_SKIP_HOLES); + rw == WRITE ? DIO_LOCKING | DIO_SKIP_HOLES : + DIO_SKIP_HOLES); if (do_opu) up_read(&fi->i_gc_rwsem[READ]); @@ -3861,7 +3882,7 @@ void f2fs_destroy_post_read_wq(struct f2fs_sb_info *sbi) int __init f2fs_init_bio_entry_cache(void) { - bio_entry_slab = f2fs_kmem_cache_create("bio_entry_slab", + bio_entry_slab = f2fs_kmem_cache_create("f2fs_bio_entry_slab", sizeof(struct bio_entry)); if (!bio_entry_slab) return -ENOMEM; diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c index 6b89eae5e4ca..0dbcb0f9c019 100644 --- a/fs/f2fs/debug.c +++ b/fs/f2fs/debug.c @@ -301,6 +301,9 @@ static int stat_show(struct seq_file *s, void *v) si->ssa_area_segs, si->main_area_segs); seq_printf(s, "(OverProv:%d Resv:%d)]\n\n", si->overp_segs, si->rsvd_segs); + seq_printf(s, "Current Time Sec: %llu / Mounted Time Sec: %llu\n\n", + ktime_get_boottime_seconds(), + SIT_I(si->sbi)->mounted_time); if (test_opt(si->sbi, DISCARD)) seq_printf(s, "Utilization: %u%% (%u valid blocks, %u discard blocks)\n", si->utilization, si->valid_count, si->discard_blks); diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index 27d0dd7a16d6..44bfc464df78 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -471,7 +471,6 @@ struct page *f2fs_init_inode_metadata(struct inode *inode, struct inode *dir, struct page *dpage) { struct page *page; - int dummy_encrypt = DUMMY_ENCRYPTION_ENABLED(F2FS_I_SB(dir)); int err; if (is_inode_flag_set(inode, FI_NEW_INODE)) { @@ -498,8 +497,7 @@ struct page *f2fs_init_inode_metadata(struct inode *inode, struct inode *dir, if (err) goto put_error; - if ((IS_ENCRYPTED(dir) || dummy_encrypt) && - f2fs_may_encrypt(inode)) { + if (IS_ENCRYPTED(inode)) { err = fscrypt_inherit_context(dir, inode, page, false); if (err) goto put_error; @@ -850,12 +848,6 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page, 0); set_page_dirty(page); - dir->i_ctime = dir->i_mtime = current_time(dir); - f2fs_mark_inode_dirty_sync(dir, false); - - if (inode) - f2fs_drop_nlink(dir, inode); - if (bit_pos == NR_DENTRY_IN_BLOCK && !f2fs_truncate_hole(dir, page->index, page->index + 1)) { f2fs_clear_page_cache_dirty_tag(page); @@ -867,6 +859,12 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page, f2fs_remove_dirty_inode(dir); } f2fs_put_page(page, 1); + + dir->i_ctime = dir->i_mtime = current_time(dir); + f2fs_mark_inode_dirty_sync(dir, false); + + if (inode) + f2fs_drop_nlink(dir, inode); } bool f2fs_empty_dir(struct inode *dir) diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 088c3e7a1080..ba470d5687fe 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -75,7 +75,6 @@ extern const char *f2fs_fault_name[FAULT_MAX]; /* * For mount options */ -#define F2FS_MOUNT_BG_GC 0x00000001 #define F2FS_MOUNT_DISABLE_ROLL_FORWARD 0x00000002 #define F2FS_MOUNT_DISCARD 0x00000004 #define F2FS_MOUNT_NOHEAP 0x00000008 @@ -89,11 +88,8 @@ extern const char *f2fs_fault_name[FAULT_MAX]; #define F2FS_MOUNT_NOBARRIER 0x00000800 #define F2FS_MOUNT_FASTBOOT 0x00001000 #define F2FS_MOUNT_EXTENT_CACHE 0x00002000 -#define F2FS_MOUNT_FORCE_FG_GC 0x00004000 #define F2FS_MOUNT_DATA_FLUSH 0x00008000 #define F2FS_MOUNT_FAULT_INJECTION 0x00010000 -#define F2FS_MOUNT_ADAPTIVE 0x00020000 -#define F2FS_MOUNT_LFS 0x00040000 #define F2FS_MOUNT_USRQUOTA 0x00080000 #define F2FS_MOUNT_GRPQUOTA 0x00100000 #define F2FS_MOUNT_PRJQUOTA 0x00200000 @@ -101,6 +97,7 @@ extern const char *f2fs_fault_name[FAULT_MAX]; #define F2FS_MOUNT_INLINE_XATTR_SIZE 0x00800000 #define F2FS_MOUNT_RESERVE_ROOT 0x01000000 #define F2FS_MOUNT_DISABLE_CHECKPOINT 0x02000000 +#define F2FS_MOUNT_NORECOVERY 0x04000000 #define F2FS_OPTION(sbi) ((sbi)->mount_opt) #define clear_opt(sbi, option) (F2FS_OPTION(sbi).opt &= ~F2FS_MOUNT_##option) @@ -139,6 +136,8 @@ struct f2fs_mount_info { int whint_mode; int alloc_mode; /* segment allocation policy */ int fsync_mode; /* fsync policy */ + int fs_mode; /* fs mode: LFS or ADAPTIVE */ + int bggc_mode; /* bggc mode: off, on or sync */ bool test_dummy_encryption; /* test dummy encryption */ block_t unusable_cap; /* Amount of space allowed to be * unusable when disabling checkpoint @@ -332,8 +331,8 @@ struct discard_policy { bool io_aware; /* issue discard in idle time */ bool sync; /* submit discard with REQ_SYNC flag */ bool ordered; /* issue discard by lba order */ + bool timeout; /* discard timeout for put_super */ unsigned int granularity; /* discard granularity */ - int timeout; /* discard timeout for put_super */ }; struct discard_cmd_control { @@ -428,6 +427,7 @@ static inline bool __has_cursum_space(struct f2fs_journal *journal, #define F2FS_IOC_GET_PIN_FILE _IOR(F2FS_IOCTL_MAGIC, 14, __u32) #define F2FS_IOC_PRECACHE_EXTENTS _IO(F2FS_IOCTL_MAGIC, 15) #define F2FS_IOC_RESIZE_FS _IOW(F2FS_IOCTL_MAGIC, 16, __u64) +#define F2FS_IOC_GET_COMPRESS_BLOCKS _IOR(F2FS_IOCTL_MAGIC, 17, __u64) #define F2FS_IOC_GET_VOLUME_NAME FS_IOC_GETFSLABEL #define F2FS_IOC_SET_VOLUME_NAME FS_IOC_SETFSLABEL @@ -560,6 +560,9 @@ enum { #define DEFAULT_RETRY_IO_COUNT 8 /* maximum retry read IO count */ +/* congestion wait timeout value, default: 20ms */ +#define DEFAULT_IO_TIMEOUT (msecs_to_jiffies(20)) + /* maximum retry quota flush count */ #define DEFAULT_RETRY_QUOTA_FLUSH_COUNT 8 @@ -676,6 +679,44 @@ enum { MAX_GC_FAILURE }; +/* used for f2fs_inode_info->flags */ +enum { + FI_NEW_INODE, /* indicate newly allocated inode */ + FI_DIRTY_INODE, /* indicate inode is dirty or not */ + FI_AUTO_RECOVER, /* indicate inode is recoverable */ + FI_DIRTY_DIR, /* indicate directory has dirty pages */ + FI_INC_LINK, /* need to increment i_nlink */ + FI_ACL_MODE, /* indicate acl mode */ + FI_NO_ALLOC, /* should not allocate any blocks */ + FI_FREE_NID, /* free allocated nide */ + FI_NO_EXTENT, /* not to use the extent cache */ + FI_INLINE_XATTR, /* used for inline xattr */ + FI_INLINE_DATA, /* used for inline data*/ + FI_INLINE_DENTRY, /* used for inline dentry */ + FI_APPEND_WRITE, /* inode has appended data */ + FI_UPDATE_WRITE, /* inode has in-place-update data */ + FI_NEED_IPU, /* used for ipu per file */ + FI_ATOMIC_FILE, /* indicate atomic file */ + FI_ATOMIC_COMMIT, /* indicate the state of atomical committing */ + FI_VOLATILE_FILE, /* indicate volatile file */ + FI_FIRST_BLOCK_WRITTEN, /* indicate #0 data block was written */ + FI_DROP_CACHE, /* drop dirty page cache */ + FI_DATA_EXIST, /* indicate data exists */ + FI_INLINE_DOTS, /* indicate inline dot dentries */ + FI_DO_DEFRAG, /* indicate defragment is running */ + FI_DIRTY_FILE, /* indicate regular/symlink has dirty pages */ + FI_NO_PREALLOC, /* indicate skipped preallocated blocks */ + FI_HOT_DATA, /* indicate file is hot */ + FI_EXTRA_ATTR, /* indicate file has extra attribute */ + FI_PROJ_INHERIT, /* indicate file inherits projectid */ + FI_PIN_FILE, /* indicate file should not be gced */ + FI_ATOMIC_REVOKE_REQUEST, /* request to drop atomic data */ + FI_VERITY_IN_PROGRESS, /* building fs-verity Merkle tree */ + FI_COMPRESSED_FILE, /* indicate file's data can be compressed */ + FI_MMAP_FILE, /* indicate file was mmapped */ + FI_MAX, /* max flag, never be used */ +}; + struct f2fs_inode_info { struct inode vfs_inode; /* serve a vfs inode */ unsigned long i_flags; /* keep an inode flags for ioctl */ @@ -688,7 +729,7 @@ struct f2fs_inode_info { umode_t i_acl_mode; /* keep file acl mode temporarily */ /* Use below internally in f2fs*/ - unsigned long flags; /* use to pass per-file flags */ + unsigned long flags[BITS_TO_LONGS(FI_MAX)]; /* use to pass per-file flags */ struct rw_semaphore i_sem; /* protect fi info */ atomic_t dirty_pages; /* # of dirty pages */ f2fs_hash_t chash; /* hash value of given file name */ @@ -697,6 +738,7 @@ struct f2fs_inode_info { struct task_struct *cp_task; /* separate cp/wb IO stats*/ nid_t i_xattr_nid; /* node id that contains xattrs */ loff_t last_disk_size; /* lastly written file size */ + spinlock_t i_size_lock; /* protect last_disk_size */ #ifdef CONFIG_QUOTA struct dquot *i_dquot[MAXQUOTAS]; @@ -1172,6 +1214,20 @@ enum { GC_URGENT, }; +enum { + BGGC_MODE_ON, /* background gc is on */ + BGGC_MODE_OFF, /* background gc is off */ + BGGC_MODE_SYNC, /* + * background gc is on, migrating blocks + * like foreground gc + */ +}; + +enum { + FS_MODE_ADAPTIVE, /* use both lfs/ssr allocation */ + FS_MODE_LFS, /* use lfs allocation only */ +}; + enum { WHINT_MODE_OFF, /* not pass down write hints */ WHINT_MODE_USER, /* try to pass down hints given by users */ @@ -1212,13 +1268,13 @@ enum fsync_mode { enum compress_algorithm_type { COMPRESS_LZO, COMPRESS_LZ4, + COMPRESS_ZSTD, COMPRESS_MAX, }; -#define COMPRESS_DATA_RESERVED_SIZE 4 +#define COMPRESS_DATA_RESERVED_SIZE 5 struct compress_data { __le32 clen; /* compressed data size */ - __le32 chksum; /* checksum of compressed data */ __le32 reserved[COMPRESS_DATA_RESERVED_SIZE]; /* reserved */ u8 cdata[]; /* compressed data */ }; @@ -1242,6 +1298,7 @@ struct compress_ctx { size_t rlen; /* valid data length in rbuf */ size_t clen; /* valid data length in cbuf */ void *private; /* payload buffer for specified compression algorithm */ + void *private2; /* extra payload buffer */ }; /* compress context for write IO path */ @@ -1271,11 +1328,14 @@ struct decompress_io_ctx { size_t clen; /* valid data length in cbuf */ refcount_t ref; /* referrence count of compressed page */ bool failed; /* indicate IO error during decompression */ + void *private; /* payload buffer for specified decompression algorithm */ + void *private2; /* extra payload buffer */ }; #define NULL_CLUSTER ((unsigned int)(~0)) #define MIN_COMPRESS_LOG_SIZE 2 #define MAX_COMPRESS_LOG_SIZE 8 +#define MAX_COMPRESS_WINDOW_SIZE ((PAGE_SIZE) << MAX_COMPRESS_LOG_SIZE) struct f2fs_sb_info { struct super_block *sb; /* pointer to VFS super block */ @@ -1471,6 +1531,9 @@ struct f2fs_sb_info { __u32 s_chksum_seed; struct workqueue_struct *post_read_wq; /* post read workqueue */ + + struct kmem_cache *inline_xattr_slab; /* inline xattr entry */ + unsigned int inline_xattr_slab_size; /* default inline xattr slab size */ }; struct f2fs_private_dio { @@ -2211,7 +2274,7 @@ static inline void dec_valid_node_count(struct f2fs_sb_info *sbi, dquot_free_inode(inode); } else { if (unlikely(inode->i_blocks == 0)) { - f2fs_warn(sbi, "Inconsistent i_blocks, ino:%lu, iblocks:%llu", + f2fs_warn(sbi, "dec_valid_node_count: inconsistent i_blocks, ino:%lu, iblocks:%llu", inode->i_ino, (unsigned long long)inode->i_blocks); set_sbi_flag(sbi, SBI_NEED_FSCK); @@ -2379,7 +2442,7 @@ static inline __le32 *blkaddr_in_node(struct f2fs_node *node) } static inline int f2fs_has_extra_attr(struct inode *inode); -static inline block_t datablock_addr(struct inode *inode, +static inline block_t data_blkaddr(struct inode *inode, struct page *node_page, unsigned int offset) { struct f2fs_node *raw_node; @@ -2389,9 +2452,9 @@ static inline block_t datablock_addr(struct inode *inode, raw_node = F2FS_NODE(node_page); - /* from GC path only */ if (is_inode) { if (!inode) + /* from GC path only */ base = offset_in_addr(&raw_node->i); else if (f2fs_has_extra_attr(inode)) base = get_extra_isize(inode); @@ -2401,6 +2464,11 @@ static inline block_t datablock_addr(struct inode *inode, return le32_to_cpu(addr_array[base + offset]); } +static inline block_t f2fs_data_blkaddr(struct dnode_of_data *dn) +{ + return data_blkaddr(dn->inode, dn->node_page, dn->ofs_in_node); +} + static inline int f2fs_test_bit(unsigned int nr, char *addr) { int mask; @@ -2498,43 +2566,6 @@ static inline __u32 f2fs_mask_flags(umode_t mode, __u32 flags) return flags & F2FS_OTHER_FLMASK; } -/* used for f2fs_inode_info->flags */ -enum { - FI_NEW_INODE, /* indicate newly allocated inode */ - FI_DIRTY_INODE, /* indicate inode is dirty or not */ - FI_AUTO_RECOVER, /* indicate inode is recoverable */ - FI_DIRTY_DIR, /* indicate directory has dirty pages */ - FI_INC_LINK, /* need to increment i_nlink */ - FI_ACL_MODE, /* indicate acl mode */ - FI_NO_ALLOC, /* should not allocate any blocks */ - FI_FREE_NID, /* free allocated nide */ - FI_NO_EXTENT, /* not to use the extent cache */ - FI_INLINE_XATTR, /* used for inline xattr */ - FI_INLINE_DATA, /* used for inline data*/ - FI_INLINE_DENTRY, /* used for inline dentry */ - FI_APPEND_WRITE, /* inode has appended data */ - FI_UPDATE_WRITE, /* inode has in-place-update data */ - FI_NEED_IPU, /* used for ipu per file */ - FI_ATOMIC_FILE, /* indicate atomic file */ - FI_ATOMIC_COMMIT, /* indicate the state of atomical committing */ - FI_VOLATILE_FILE, /* indicate volatile file */ - FI_FIRST_BLOCK_WRITTEN, /* indicate #0 data block was written */ - FI_DROP_CACHE, /* drop dirty page cache */ - FI_DATA_EXIST, /* indicate data exists */ - FI_INLINE_DOTS, /* indicate inline dot dentries */ - FI_DO_DEFRAG, /* indicate defragment is running */ - FI_DIRTY_FILE, /* indicate regular/symlink has dirty pages */ - FI_NO_PREALLOC, /* indicate skipped preallocated blocks */ - FI_HOT_DATA, /* indicate file is hot */ - FI_EXTRA_ATTR, /* indicate file has extra attribute */ - FI_PROJ_INHERIT, /* indicate file inherits projectid */ - FI_PIN_FILE, /* indicate file should not be gced */ - FI_ATOMIC_REVOKE_REQUEST, /* request to drop atomic data */ - FI_VERITY_IN_PROGRESS, /* building fs-verity Merkle tree */ - FI_COMPRESSED_FILE, /* indicate file's data can be compressed */ - FI_MMAP_FILE, /* indicate file was mmapped */ -}; - static inline void __mark_inode_dirty_flag(struct inode *inode, int flag, bool set) { @@ -2549,27 +2580,24 @@ static inline void __mark_inode_dirty_flag(struct inode *inode, case FI_DATA_EXIST: case FI_INLINE_DOTS: case FI_PIN_FILE: - case FI_COMPRESSED_FILE: f2fs_mark_inode_dirty_sync(inode, true); } } static inline void set_inode_flag(struct inode *inode, int flag) { - if (!test_bit(flag, &F2FS_I(inode)->flags)) - set_bit(flag, &F2FS_I(inode)->flags); + test_and_set_bit(flag, F2FS_I(inode)->flags); __mark_inode_dirty_flag(inode, flag, true); } static inline int is_inode_flag_set(struct inode *inode, int flag) { - return test_bit(flag, &F2FS_I(inode)->flags); + return test_bit(flag, F2FS_I(inode)->flags); } static inline void clear_inode_flag(struct inode *inode, int flag) { - if (test_bit(flag, &F2FS_I(inode)->flags)) - clear_bit(flag, &F2FS_I(inode)->flags); + test_and_clear_bit(flag, F2FS_I(inode)->flags); __mark_inode_dirty_flag(inode, flag, false); } @@ -2660,19 +2688,19 @@ static inline void get_inline_info(struct inode *inode, struct f2fs_inode *ri) struct f2fs_inode_info *fi = F2FS_I(inode); if (ri->i_inline & F2FS_INLINE_XATTR) - set_bit(FI_INLINE_XATTR, &fi->flags); + set_bit(FI_INLINE_XATTR, fi->flags); if (ri->i_inline & F2FS_INLINE_DATA) - set_bit(FI_INLINE_DATA, &fi->flags); + set_bit(FI_INLINE_DATA, fi->flags); if (ri->i_inline & F2FS_INLINE_DENTRY) - set_bit(FI_INLINE_DENTRY, &fi->flags); + set_bit(FI_INLINE_DENTRY, fi->flags); if (ri->i_inline & F2FS_DATA_EXIST) - set_bit(FI_DATA_EXIST, &fi->flags); + set_bit(FI_DATA_EXIST, fi->flags); if (ri->i_inline & F2FS_INLINE_DOTS) - set_bit(FI_INLINE_DOTS, &fi->flags); + set_bit(FI_INLINE_DOTS, fi->flags); if (ri->i_inline & F2FS_EXTRA_ATTR) - set_bit(FI_EXTRA_ATTR, &fi->flags); + set_bit(FI_EXTRA_ATTR, fi->flags); if (ri->i_inline & F2FS_PIN_FILE) - set_bit(FI_PIN_FILE, &fi->flags); + set_bit(FI_PIN_FILE, fi->flags); } static inline void set_raw_inline(struct inode *inode, struct f2fs_inode *ri) @@ -2857,9 +2885,9 @@ static inline bool f2fs_skip_inode_update(struct inode *inode, int dsync) if (!f2fs_is_time_consistent(inode)) return false; - down_read(&F2FS_I(inode)->i_sem); + spin_lock(&F2FS_I(inode)->i_size_lock); ret = F2FS_I(inode)->last_disk_size == i_size_read(inode); - up_read(&F2FS_I(inode)->i_sem); + spin_unlock(&F2FS_I(inode)->i_size_lock); return ret; } @@ -3213,7 +3241,7 @@ void f2fs_drop_inmem_pages(struct inode *inode); void f2fs_drop_inmem_page(struct inode *inode, struct page *page); int f2fs_commit_inmem_pages(struct inode *inode); void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need); -void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi); +void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi, bool from_bg); int f2fs_issue_flush(struct f2fs_sb_info *sbi, nid_t ino); int f2fs_create_flush_cmd_control(struct f2fs_sb_info *sbi); int f2fs_flush_device_cache(struct f2fs_sb_info *sbi); @@ -3309,7 +3337,7 @@ int f2fs_get_valid_checkpoint(struct f2fs_sb_info *sbi); void f2fs_update_dirty_page(struct inode *inode, struct page *page); void f2fs_remove_dirty_inode(struct inode *inode); int f2fs_sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type); -void f2fs_wait_on_all_pages_writeback(struct f2fs_sb_info *sbi); +void f2fs_wait_on_all_pages(struct f2fs_sb_info *sbi, int type); int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc); void f2fs_init_ino_entry_info(struct f2fs_sb_info *sbi); int __init f2fs_create_checkpoint_caches(void); @@ -3320,7 +3348,7 @@ void f2fs_destroy_checkpoint_caches(void); */ int __init f2fs_init_bioset(void); void f2fs_destroy_bioset(void); -struct bio *f2fs_bio_alloc(struct f2fs_sb_info *sbi, int npages, bool no_fail); +struct bio *f2fs_bio_alloc(struct f2fs_sb_info *sbi, int npages, bool noio); int f2fs_init_bio_entry_cache(void); void f2fs_destroy_bio_entry_cache(void); void f2fs_submit_bio(struct f2fs_sb_info *sbi, @@ -3776,7 +3804,7 @@ int f2fs_write_multi_pages(struct compress_ctx *cc, int f2fs_is_compressed_cluster(struct inode *inode, pgoff_t index); int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret, unsigned nr_pages, sector_t *last_block_in_bio, - bool is_readahead); + bool is_readahead, bool for_write); struct decompress_io_ctx *f2fs_alloc_dic(struct compress_ctx *cc); void f2fs_free_dic(struct decompress_io_ctx *dic); void f2fs_decompress_end_io(struct page **rpages, @@ -3813,6 +3841,7 @@ static inline void set_compress_context(struct inode *inode) F2FS_I(inode)->i_flags |= F2FS_COMPR_FL; set_inode_flag(inode, FI_COMPRESSED_FILE); stat_inc_compr_inode(inode); + f2fs_mark_inode_dirty_sync(inode, true); } static inline u64 f2fs_disable_compressed_file(struct inode *inode) @@ -3821,12 +3850,17 @@ static inline u64 f2fs_disable_compressed_file(struct inode *inode) if (!f2fs_compressed_file(inode)) return 0; - if (fi->i_compr_blocks) - return fi->i_compr_blocks; + if (S_ISREG(inode->i_mode)) { + if (get_dirty_pages(inode)) + return 1; + if (fi->i_compr_blocks) + return fi->i_compr_blocks; + } fi->i_flags &= ~F2FS_COMPR_FL; - clear_inode_flag(inode, FI_COMPRESSED_FILE); stat_dec_compr_inode(inode); + clear_inode_flag(inode, FI_COMPRESSED_FILE); + f2fs_mark_inode_dirty_sync(inode, true); return 0; } @@ -3903,31 +3937,25 @@ static inline bool f2fs_hw_is_readonly(struct f2fs_sb_info *sbi) return false; } - -static inline void set_opt_mode(struct f2fs_sb_info *sbi, unsigned int mt) +static inline bool f2fs_lfs_mode(struct f2fs_sb_info *sbi) { - clear_opt(sbi, ADAPTIVE); - clear_opt(sbi, LFS); - - switch (mt) { - case F2FS_MOUNT_ADAPTIVE: - set_opt(sbi, ADAPTIVE); - break; - case F2FS_MOUNT_LFS: - set_opt(sbi, LFS); - break; - } + return F2FS_OPTION(sbi).fs_mode == FS_MODE_LFS; } -static inline bool f2fs_may_encrypt(struct inode *inode) +static inline bool f2fs_may_encrypt(struct inode *dir, struct inode *inode) { #ifdef CONFIG_FS_ENCRYPTION + struct f2fs_sb_info *sbi = F2FS_I_SB(dir); umode_t mode = inode->i_mode; - return (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)); -#else - return false; + /* + * If the directory encrypted or dummy encryption enabled, + * then we should encrypt the inode. + */ + if (IS_ENCRYPTED(dir) || DUMMY_ENCRYPTION_ENABLED(sbi)) + return (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)); #endif + return false; } static inline bool f2fs_may_compress(struct inode *inode) @@ -3971,7 +3999,7 @@ static inline int allow_outplace_dio(struct inode *inode, struct f2fs_sb_info *sbi = F2FS_I_SB(inode); int rw = iov_iter_rw(iter); - return (test_opt(sbi, LFS) && (rw == WRITE) && + return (f2fs_lfs_mode(sbi) && (rw == WRITE) && !block_unaligned_IO(inode, iocb, iter)); } @@ -3993,7 +4021,7 @@ static inline bool f2fs_force_buffered_io(struct inode *inode, */ if (f2fs_sb_has_blkzoned(sbi)) return true; - if (test_opt(sbi, LFS) && (rw == WRITE)) { + if (f2fs_lfs_mode(sbi) && (rw == WRITE)) { if (block_unaligned_IO(inode, iocb, iter)) return true; if (F2FS_IO_ALIGNED(sbi)) diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 351762f77840..6ab8f621a3c5 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -106,13 +106,20 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf) err = f2fs_get_block(&dn, page->index); f2fs_put_dnode(&dn); __do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, false); - if (err) { - unlock_page(page); - goto out_sem; - } } - /* fill the page */ +#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); + } +#endif + if (err) { + unlock_page(page); + goto out_sem; + } + f2fs_wait_on_page_writeback(page, DATA, false, true); /* wait for GCed page writeback via META_MAPPING */ @@ -448,8 +455,7 @@ 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), @@ -793,6 +799,8 @@ int f2fs_getattr(const struct path *path, struct kstat *stat, } 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)) @@ -804,7 +812,8 @@ 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 | @@ -929,10 +938,10 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr) 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); @@ -1109,8 +1118,7 @@ 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, @@ -1121,7 +1129,7 @@ next_dnode: if (!f2fs_is_checkpointed_data(sbi, *blkaddr)) { - if (test_opt(sbi, LFS)) { + if (f2fs_lfs_mode(sbi)) { f2fs_put_dnode(&dn); return -EOPNOTSUPP; } @@ -1199,8 +1207,7 @@ 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]) { @@ -1376,8 +1383,7 @@ 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 +1394,7 @@ 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. @@ -1787,12 +1792,15 @@ static int f2fs_file_flush(struct file *file, fl_owner_t id) 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; + + f2fs_bug_on(F2FS_I_SB(inode), (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)) @@ -1806,27 +1814,22 @@ 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 ^ masked_flags) & F2FS_COMPR_FL) { + if (masked_flags & F2FS_COMPR_FL) { + if (f2fs_disable_compressed_file(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 (!f2fs_may_compress(inode)) return -EINVAL; set_compress_context(inode); } } - if ((iflags ^ fi->i_flags) & F2FS_NOCOMP_FL) { - if (fi->i_flags & F2FS_COMPR_FL) + if ((iflags ^ masked_flags) & F2FS_NOCOMP_FL) { + if (masked_flags & F2FS_COMPR_FL) return -EINVAL; } @@ -3401,6 +3404,21 @@ out: return err; } +static int f2fs_get_compress_blocks(struct file *filp, unsigned long arg) +{ + 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 = F2FS_I(inode)->i_compr_blocks; + return put_user(blocks, (u64 __user *)arg); +} + long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { if (unlikely(f2fs_cp_error(F2FS_I_SB(file_inode(filp))))) @@ -3481,6 +3499,8 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) return f2fs_get_volume_name(filp, arg); case F2FS_IOC_SET_VOLUME_NAME: return f2fs_set_volume_name(filp, arg); + case F2FS_IOC_GET_COMPRESS_BLOCKS: + return f2fs_get_compress_blocks(filp, arg); default: return -ENOTTY; } @@ -3508,8 +3528,10 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) goto out; } - if (!f2fs_is_compress_backend_ready(inode)) - return -EOPNOTSUPP; + if (!f2fs_is_compress_backend_ready(inode)) { + ret = -EOPNOTSUPP; + goto out; + } if (iocb->ki_flags & IOCB_NOWAIT) { if (!inode_trylock(inode)) { @@ -3639,6 +3661,7 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case FS_IOC_MEASURE_VERITY: case F2FS_IOC_GET_VOLUME_NAME: case F2FS_IOC_SET_VOLUME_NAME: + case F2FS_IOC_GET_COMPRESS_BLOCKS: break; default: return -ENOIOCTLCMD; diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index db8725d473b5..26248c8936db 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -31,6 +31,8 @@ static int gc_thread_func(void *data) set_freezable(); do { + bool sync_mode; + wait_event_interruptible_timeout(*wq, kthread_should_stop() || freezing(current) || gc_th->gc_wake, @@ -101,15 +103,17 @@ static int gc_thread_func(void *data) do_gc: stat_inc_bggc_count(sbi->stat_info); + sync_mode = F2FS_OPTION(sbi).bggc_mode == BGGC_MODE_SYNC; + /* if return value is not zero, no victim was selected */ - if (f2fs_gc(sbi, test_opt(sbi, FORCE_FG_GC), true, NULL_SEGNO)) + if (f2fs_gc(sbi, sync_mode, true, NULL_SEGNO)) wait_ms = gc_th->no_gc_sleep_time; trace_f2fs_background_gc(sbi->sb, wait_ms, prefree_segments(sbi), free_segments(sbi)); /* balancing f2fs's metadata periodically */ - f2fs_balance_fs_bg(sbi); + f2fs_balance_fs_bg(sbi, true); next: sb_end_write(sbi->sb); @@ -192,7 +196,10 @@ static void select_policy(struct f2fs_sb_info *sbi, int gc_type, p->ofs_unit = sbi->segs_per_sec; } - /* we need to check every dirty segments in the FG_GC case */ + /* + * adjust candidates range, should select all dirty segments for + * foreground GC and urgent GC cases. + */ if (gc_type != FG_GC && (sbi->gc_mode != GC_URGENT) && p->max_search > sbi->max_victim_search) @@ -634,7 +641,7 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, } *nofs = ofs_of_node(node_page); - source_blkaddr = datablock_addr(NULL, node_page, ofs_in_node); + source_blkaddr = data_blkaddr(NULL, node_page, ofs_in_node); f2fs_put_page(node_page, 1); if (source_blkaddr != blkaddr) { @@ -762,7 +769,7 @@ static int move_data_block(struct inode *inode, block_t bidx, struct page *page, *mpage; block_t newaddr; int err = 0; - bool lfs_mode = test_opt(fio.sbi, LFS); + bool lfs_mode = f2fs_lfs_mode(fio.sbi); /* do not read out */ page = f2fs_grab_cache_page(inode->i_mapping, bidx, false); @@ -970,7 +977,8 @@ retry: if (err) { clear_cold_data(page); if (err == -ENOMEM) { - congestion_wait(BLK_RW_ASYNC, HZ/50); + congestion_wait(BLK_RW_ASYNC, + DEFAULT_IO_TIMEOUT); goto retry; } if (is_dirty) @@ -1018,8 +1026,8 @@ next_step: * race condition along with SSR block allocation. */ if ((gc_type == BG_GC && has_not_enough_free_secs(sbi, 0, 0)) || - get_valid_blocks(sbi, segno, false) == - sbi->blocks_per_seg) + get_valid_blocks(sbi, segno, true) == + BLKS_PER_SEC(sbi)) return submitted; if (check_valid_map(sbi, segno, off) == 0) @@ -1203,7 +1211,7 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi, if (get_valid_blocks(sbi, segno, false) == 0) goto freed; - if (__is_large_section(sbi) && + if (gc_type == BG_GC && __is_large_section(sbi) && migrated >= sbi->migration_granularity) goto skip; if (!PageUptodate(sum_page) || unlikely(f2fs_cp_error(sbi))) @@ -1233,12 +1241,12 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi, segno, gc_type); stat_inc_seg_count(sbi, type, gc_type); + migrated++; freed: if (gc_type == FG_GC && get_valid_blocks(sbi, segno, false) == 0) seg_freed++; - migrated++; if (__is_large_section(sbi) && segno + 1 < end_segno) sbi->next_victim_seg[gc_type] = segno + 1; @@ -1434,12 +1442,19 @@ static int free_segment_range(struct f2fs_sb_info *sbi, unsigned int start, static void update_sb_metadata(struct f2fs_sb_info *sbi, int secs) { struct f2fs_super_block *raw_sb = F2FS_RAW_SUPER(sbi); - int section_count = le32_to_cpu(raw_sb->section_count); - int segment_count = le32_to_cpu(raw_sb->segment_count); - int segment_count_main = le32_to_cpu(raw_sb->segment_count_main); - long long block_count = le64_to_cpu(raw_sb->block_count); + int section_count; + int segment_count; + int segment_count_main; + long long block_count; int segs = secs * sbi->segs_per_sec; + down_write(&sbi->sb_lock); + + section_count = le32_to_cpu(raw_sb->section_count); + segment_count = le32_to_cpu(raw_sb->segment_count); + segment_count_main = le32_to_cpu(raw_sb->segment_count_main); + block_count = le64_to_cpu(raw_sb->block_count); + raw_sb->section_count = cpu_to_le32(section_count + secs); raw_sb->segment_count = cpu_to_le32(segment_count + segs); raw_sb->segment_count_main = cpu_to_le32(segment_count_main + segs); @@ -1453,6 +1468,8 @@ static void update_sb_metadata(struct f2fs_sb_info *sbi, int secs) raw_sb->devs[last_dev].total_segments = cpu_to_le32(dev_segs + segs); } + + up_write(&sbi->sb_lock); } static void update_fs_metadata(struct f2fs_sb_info *sbi, int secs) @@ -1570,11 +1587,17 @@ int f2fs_resize_fs(struct f2fs_sb_info *sbi, __u64 block_count) goto out; } + mutex_lock(&sbi->cp_mutex); update_fs_metadata(sbi, -secs); clear_sbi_flag(sbi, SBI_IS_RESIZEFS); + set_sbi_flag(sbi, SBI_IS_DIRTY); + mutex_unlock(&sbi->cp_mutex); + err = f2fs_sync_fs(sbi->sb, 1); if (err) { + mutex_lock(&sbi->cp_mutex); update_fs_metadata(sbi, secs); + mutex_unlock(&sbi->cp_mutex); update_sb_metadata(sbi, secs); f2fs_commit_super(sbi, false); } diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 78c3f1d70f1d..44582a4db513 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -291,13 +291,30 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page) fi->i_flags & F2FS_COMPR_FL && F2FS_FITS_IN_INODE(ri, fi->i_extra_isize, i_log_cluster_size)) { - if (ri->i_compress_algorithm >= COMPRESS_MAX) + if (ri->i_compress_algorithm >= COMPRESS_MAX) { + f2fs_warn(sbi, "%s: inode (ino=%lx) has unsupported " + "compress algorithm: %u, run fsck to fix", + __func__, inode->i_ino, + ri->i_compress_algorithm); return false; - if (le64_to_cpu(ri->i_compr_blocks) > inode->i_blocks) + } + if (le64_to_cpu(ri->i_compr_blocks) > + SECTOR_TO_BLOCK(inode->i_blocks)) { + f2fs_warn(sbi, "%s: inode (ino=%lx) has inconsistent " + "i_compr_blocks:%llu, i_blocks:%llu, run fsck to fix", + __func__, inode->i_ino, + le64_to_cpu(ri->i_compr_blocks), + SECTOR_TO_BLOCK(inode->i_blocks)); return false; + } if (ri->i_log_cluster_size < MIN_COMPRESS_LOG_SIZE || - ri->i_log_cluster_size > MAX_COMPRESS_LOG_SIZE) + ri->i_log_cluster_size > MAX_COMPRESS_LOG_SIZE) { + f2fs_warn(sbi, "%s: inode (ino=%lx) has unsupported " + "log cluster size: %u, run fsck to fix", + __func__, inode->i_ino, + ri->i_log_cluster_size); return false; + } } return true; @@ -345,7 +362,7 @@ static int do_read_inode(struct inode *inode) fi->i_flags = le32_to_cpu(ri->i_flags); if (S_ISREG(inode->i_mode)) fi->i_flags &= ~F2FS_PROJINHERIT_FL; - fi->flags = 0; + bitmap_zero(fi->flags, FI_MAX); fi->i_advise = ri->i_advise; fi->i_pino = le32_to_cpu(ri->i_pino); fi->i_dir_level = ri->i_dir_level; @@ -518,7 +535,7 @@ retry: inode = f2fs_iget(sb, ino); if (IS_ERR(inode)) { if (PTR_ERR(inode) == -ENOMEM) { - congestion_wait(BLK_RW_ASYNC, HZ/50); + congestion_wait(BLK_RW_ASYNC, DEFAULT_IO_TIMEOUT); goto retry; } } @@ -759,7 +776,7 @@ no_delete: else f2fs_inode_synced(inode); - /* ino == 0, if f2fs_new_inode() was failed t*/ + /* for the case f2fs_new_inode() was failed, .i_ino is zero, skip it */ if (inode->i_ino) invalidate_mapping_pages(NODE_MAPPING(sbi), inode->i_ino, inode->i_ino); diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index 2aa035422c0f..f54119da2217 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -75,9 +75,7 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode) set_inode_flag(inode, FI_NEW_INODE); - /* If the directory encrypted, then we should encrypt the inode. */ - if ((IS_ENCRYPTED(dir) || DUMMY_ENCRYPTION_ENABLED(sbi)) && - f2fs_may_encrypt(inode)) + if (f2fs_may_encrypt(dir, inode)) f2fs_set_encrypted_inode(inode); if (f2fs_sb_has_extra_attr(sbi)) { @@ -177,7 +175,7 @@ static inline int is_extension_exist(const unsigned char *s, const char *sub) } /* - * Set multimedia files as cold files for hot/cold data separation + * Set file's temperature for hot/cold data separation */ static inline void set_file_temperature(struct f2fs_sb_info *sbi, struct inode *inode, const unsigned char *name) @@ -876,12 +874,6 @@ static int f2fs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) if (!f2fs_is_checkpoint_ready(sbi)) return -ENOSPC; - if (IS_ENCRYPTED(dir) || DUMMY_ENCRYPTION_ENABLED(sbi)) { - int err = fscrypt_get_encryption_info(dir); - if (err) - return err; - } - return __f2fs_tmpfile(dir, dentry, mode, NULL); } diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 9d02cdcdbb07..ecbd6bd14a49 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -510,9 +510,6 @@ int f2fs_try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink) return nr - nr_shrink; } -/* - * This function always returns success - */ int f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni) { @@ -716,8 +713,7 @@ got: /* * Caller should call f2fs_put_dnode(dn). * Also, it should grab and release a rwsem by calling f2fs_lock_op() and - * f2fs_unlock_op() only if ro is not set RDONLY_NODE. - * In the case of RDONLY_NODE, we don't need to care about mutex. + * f2fs_unlock_op() only if mode is set with ALLOC_NODE. */ int f2fs_get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode) { @@ -809,8 +805,7 @@ int f2fs_get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode) dn->nid = nids[level]; dn->ofs_in_node = offset[level]; dn->node_page = npage[level]; - dn->data_blkaddr = datablock_addr(dn->inode, - dn->node_page, dn->ofs_in_node); + dn->data_blkaddr = f2fs_data_blkaddr(dn); return 0; release_pages: @@ -1188,8 +1183,9 @@ int f2fs_remove_inode_page(struct inode *inode) } if (unlikely(inode->i_blocks != 0 && inode->i_blocks != 8)) { - f2fs_warn(F2FS_I_SB(inode), "Inconsistent i_blocks, ino:%lu, iblocks:%llu", - inode->i_ino, (unsigned long long)inode->i_blocks); + f2fs_warn(F2FS_I_SB(inode), + "f2fs_remove_inode_page: inconsistent i_blocks, ino:%lu, iblocks:%llu", + inode->i_ino, (unsigned long long)inode->i_blocks); set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_FSCK); } @@ -1562,15 +1558,16 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted, if (atomic && !test_opt(sbi, NOBARRIER)) fio.op_flags |= REQ_PREFLUSH | REQ_FUA; - set_page_writeback(page); - ClearPageError(page); - + /* should add to global list before clearing PAGECACHE status */ if (f2fs_in_warm_node_list(sbi, page)) { seq = f2fs_add_fsync_node_entry(sbi, page); if (seq_id) *seq_id = seq; } + set_page_writeback(page); + ClearPageError(page); + fio.old_blkaddr = ni.blk_addr; f2fs_do_write_node_page(nid, &fio); set_node_addr(sbi, &ni, fio.new_blkaddr, is_fsync_dnode(page)); @@ -1979,7 +1976,7 @@ static int f2fs_write_node_pages(struct address_space *mapping, goto skip_write; /* balancing f2fs's metadata in background */ - f2fs_balance_fs_bg(sbi); + f2fs_balance_fs_bg(sbi, true); /* collect a number of dirty node pages and write together */ if (wbc->sync_mode != WB_SYNC_ALL && @@ -2602,7 +2599,7 @@ int f2fs_recover_inode_page(struct f2fs_sb_info *sbi, struct page *page) retry: ipage = f2fs_grab_cache_page(NODE_MAPPING(sbi), ino, false); if (!ipage) { - congestion_wait(BLK_RW_ASYNC, HZ/50); + congestion_wait(BLK_RW_ASYNC, DEFAULT_IO_TIMEOUT); goto retry; } @@ -3193,22 +3190,22 @@ void f2fs_destroy_node_manager(struct f2fs_sb_info *sbi) int __init f2fs_create_node_manager_caches(void) { - nat_entry_slab = f2fs_kmem_cache_create("nat_entry", + nat_entry_slab = f2fs_kmem_cache_create("f2fs_nat_entry", sizeof(struct nat_entry)); if (!nat_entry_slab) goto fail; - free_nid_slab = f2fs_kmem_cache_create("free_nid", + free_nid_slab = f2fs_kmem_cache_create("f2fs_free_nid", sizeof(struct free_nid)); if (!free_nid_slab) goto destroy_nat_entry; - nat_entry_set_slab = f2fs_kmem_cache_create("nat_entry_set", + nat_entry_set_slab = f2fs_kmem_cache_create("f2fs_nat_entry_set", sizeof(struct nat_entry_set)); if (!nat_entry_set_slab) goto destroy_free_nid; - fsync_node_entry_slab = f2fs_kmem_cache_create("fsync_node_entry", + fsync_node_entry_slab = f2fs_kmem_cache_create("f2fs_fsync_node_entry", sizeof(struct fsync_node_entry)); if (!fsync_node_entry_slab) goto destroy_nat_entry_set; diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index 763d5c0951d1..dd804c07eeb0 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -496,8 +496,7 @@ out: return 0; truncate_out: - if (datablock_addr(tdn.inode, tdn.node_page, - tdn.ofs_in_node) == blkaddr) + if (f2fs_data_blkaddr(&tdn) == blkaddr) f2fs_truncate_data_blocks_range(&tdn, 1); if (dn->inode->i_ino == nid && !dn->inode_page_locked) unlock_page(dn->inode_page); @@ -535,7 +534,7 @@ retry_dn: err = f2fs_get_dnode_of_data(&dn, start, ALLOC_NODE); if (err) { if (err == -ENOMEM) { - congestion_wait(BLK_RW_ASYNC, HZ/50); + congestion_wait(BLK_RW_ASYNC, DEFAULT_IO_TIMEOUT); goto retry_dn; } goto out; @@ -560,8 +559,8 @@ retry_dn: for (; start < end; start++, dn.ofs_in_node++) { block_t src, dest; - src = datablock_addr(dn.inode, dn.node_page, dn.ofs_in_node); - dest = datablock_addr(dn.inode, page, dn.ofs_in_node); + src = f2fs_data_blkaddr(&dn); + dest = data_blkaddr(dn.inode, page, dn.ofs_in_node); if (__is_valid_data_blkaddr(src) && !f2fs_is_valid_blkaddr(sbi, src, META_POR)) { @@ -618,7 +617,8 @@ retry_prev: err = check_index_in_prev_nodes(sbi, dest, &dn); if (err) { if (err == -ENOMEM) { - congestion_wait(BLK_RW_ASYNC, HZ/50); + congestion_wait(BLK_RW_ASYNC, + DEFAULT_IO_TIMEOUT); goto retry_prev; } goto err; diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index cf0eb002cfd4..b7a9421472a7 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -172,7 +172,7 @@ bool f2fs_need_SSR(struct f2fs_sb_info *sbi) int dent_secs = get_blocktype_secs(sbi, F2FS_DIRTY_DENTS); int imeta_secs = get_blocktype_secs(sbi, F2FS_DIRTY_IMETA); - if (test_opt(sbi, LFS)) + if (f2fs_lfs_mode(sbi)) return false; if (sbi->gc_mode == GC_URGENT) return true; @@ -245,7 +245,8 @@ retry: LOOKUP_NODE); if (err) { if (err == -ENOMEM) { - congestion_wait(BLK_RW_ASYNC, HZ/50); + congestion_wait(BLK_RW_ASYNC, + DEFAULT_IO_TIMEOUT); cond_resched(); goto retry; } @@ -312,7 +313,7 @@ next: skip: iput(inode); } - congestion_wait(BLK_RW_ASYNC, HZ/50); + congestion_wait(BLK_RW_ASYNC, DEFAULT_IO_TIMEOUT); cond_resched(); if (gc_failure) { if (++looped >= count) @@ -415,7 +416,8 @@ retry: err = f2fs_do_write_data_page(&fio); if (err) { if (err == -ENOMEM) { - congestion_wait(BLK_RW_ASYNC, HZ/50); + congestion_wait(BLK_RW_ASYNC, + DEFAULT_IO_TIMEOUT); cond_resched(); goto retry; } @@ -494,7 +496,7 @@ void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need) /* balance_fs_bg is able to be pending */ if (need && excess_cached_nats(sbi)) - f2fs_balance_fs_bg(sbi); + f2fs_balance_fs_bg(sbi, false); if (!f2fs_is_checkpoint_ready(sbi)) return; @@ -509,7 +511,7 @@ void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need) } } -void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi) +void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi, bool from_bg) { if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) return; @@ -538,7 +540,7 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi) excess_dirty_nats(sbi) || excess_dirty_nodes(sbi) || f2fs_time_over(sbi, CP_TIME)) { - if (test_opt(sbi, DATA_FLUSH)) { + if (test_opt(sbi, DATA_FLUSH) && from_bg) { struct blk_plug plug; mutex_lock(&sbi->flush_lock); @@ -1078,7 +1080,7 @@ static void __init_discard_policy(struct f2fs_sb_info *sbi, dpolicy->max_requests = DEF_MAX_DISCARD_REQUEST; dpolicy->io_aware_gran = MAX_PLIST_NUM; - dpolicy->timeout = 0; + dpolicy->timeout = false; if (discard_type == DPOLICY_BG) { dpolicy->min_interval = DEF_MIN_DISCARD_ISSUE_TIME; @@ -1103,6 +1105,7 @@ static void __init_discard_policy(struct f2fs_sb_info *sbi, dpolicy->io_aware = false; /* we need to issue all to keep CP_TRIMMED_FLAG */ dpolicy->granularity = 1; + dpolicy->timeout = true; } } @@ -1471,12 +1474,12 @@ static int __issue_discard_cmd(struct f2fs_sb_info *sbi, int i, issued = 0; bool io_interrupted = false; - if (dpolicy->timeout != 0) - f2fs_update_time(sbi, dpolicy->timeout); + if (dpolicy->timeout) + f2fs_update_time(sbi, UMOUNT_DISCARD_TIMEOUT); for (i = MAX_PLIST_NUM - 1; i >= 0; i--) { - if (dpolicy->timeout != 0 && - f2fs_time_over(sbi, dpolicy->timeout)) + if (dpolicy->timeout && + f2fs_time_over(sbi, UMOUNT_DISCARD_TIMEOUT)) break; if (i + 1 < dpolicy->granularity) @@ -1497,8 +1500,8 @@ static int __issue_discard_cmd(struct f2fs_sb_info *sbi, list_for_each_entry_safe(dc, tmp, pend_list, list) { f2fs_bug_on(sbi, dc->state != D_PREP); - if (dpolicy->timeout != 0 && - f2fs_time_over(sbi, dpolicy->timeout)) + if (dpolicy->timeout && + f2fs_time_over(sbi, UMOUNT_DISCARD_TIMEOUT)) break; if (dpolicy->io_aware && i < dpolicy->io_aware_gran && @@ -1677,7 +1680,6 @@ bool f2fs_issue_discard_timeout(struct f2fs_sb_info *sbi) __init_discard_policy(sbi, &dpolicy, DPOLICY_UMOUNT, dcc->discard_granularity); - dpolicy.timeout = UMOUNT_DISCARD_TIMEOUT; __issue_discard_cmd(sbi, &dpolicy); dropped = __drop_discard_cmd(sbi); @@ -1940,7 +1942,7 @@ void f2fs_clear_prefree_segments(struct f2fs_sb_info *sbi, unsigned int start = 0, end = -1; unsigned int secno, start_segno; bool force = (cpc->reason & CP_DISCARD); - bool need_align = test_opt(sbi, LFS) && __is_large_section(sbi); + bool need_align = f2fs_lfs_mode(sbi) && __is_large_section(sbi); mutex_lock(&dirty_i->seglist_lock); @@ -1972,7 +1974,7 @@ void f2fs_clear_prefree_segments(struct f2fs_sb_info *sbi, (end - 1) <= cpc->trim_end) continue; - if (!test_opt(sbi, LFS) || !__is_large_section(sbi)) { + if (!f2fs_lfs_mode(sbi) || !__is_large_section(sbi)) { f2fs_issue_discard(sbi, START_BLOCK(sbi, start), (end - start) << sbi->log_blocks_per_seg); continue; @@ -2801,7 +2803,7 @@ next: blk_finish_plug(&plug); mutex_unlock(&dcc->cmd_lock); trimmed += __wait_all_discard_cmd(sbi, NULL); - congestion_wait(BLK_RW_ASYNC, HZ/50); + congestion_wait(BLK_RW_ASYNC, DEFAULT_IO_TIMEOUT); goto next; } skip: @@ -2830,7 +2832,7 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range) struct discard_policy dpolicy; unsigned long long trimmed = 0; int err = 0; - bool need_align = test_opt(sbi, LFS) && __is_large_section(sbi); + bool need_align = f2fs_lfs_mode(sbi) && __is_large_section(sbi); if (start >= MAX_BLKADDR(sbi) || range->len < sbi->blocksize) return -EINVAL; @@ -3193,7 +3195,7 @@ static void update_device_state(struct f2fs_io_info *fio) static void do_write_page(struct f2fs_summary *sum, struct f2fs_io_info *fio) { int type = __get_segment_type(fio); - bool keep_order = (test_opt(fio->sbi, LFS) && type == CURSEG_COLD_DATA); + bool keep_order = (f2fs_lfs_mode(fio->sbi) && type == CURSEG_COLD_DATA); if (keep_order) down_read(&fio->sbi->io_order_lock); @@ -4071,7 +4073,7 @@ static int build_sit_info(struct f2fs_sb_info *sbi) sit_i->dirty_sentries = 0; sit_i->sents_per_block = SIT_ENTRY_PER_BLOCK; sit_i->elapsed_time = le64_to_cpu(sbi->ckpt->elapsed_time); - sit_i->mounted_time = ktime_get_real_seconds(); + sit_i->mounted_time = ktime_get_boottime_seconds(); init_rwsem(&sit_i->sentry_lock); return 0; } @@ -4678,7 +4680,7 @@ int f2fs_build_segment_manager(struct f2fs_sb_info *sbi) if (sm_info->rec_prefree_segments > DEF_MAX_RECLAIM_PREFREE_SEGMENTS) sm_info->rec_prefree_segments = DEF_MAX_RECLAIM_PREFREE_SEGMENTS; - if (!test_opt(sbi, LFS)) + if (!f2fs_lfs_mode(sbi)) sm_info->ipu_policy = 1 << F2FS_IPU_FSYNC; sm_info->min_ipu_util = DEF_MIN_IPU_UTIL; sm_info->min_fsync_blocks = DEF_MIN_FSYNC_BLOCKS; @@ -4830,22 +4832,22 @@ void f2fs_destroy_segment_manager(struct f2fs_sb_info *sbi) int __init f2fs_create_segment_manager_caches(void) { - discard_entry_slab = f2fs_kmem_cache_create("discard_entry", + discard_entry_slab = f2fs_kmem_cache_create("f2fs_discard_entry", sizeof(struct discard_entry)); if (!discard_entry_slab) goto fail; - discard_cmd_slab = f2fs_kmem_cache_create("discard_cmd", + discard_cmd_slab = f2fs_kmem_cache_create("f2fs_discard_cmd", sizeof(struct discard_cmd)); if (!discard_cmd_slab) goto destroy_discard_entry; - sit_entry_set_slab = f2fs_kmem_cache_create("sit_entry_set", + sit_entry_set_slab = f2fs_kmem_cache_create("f2fs_sit_entry_set", sizeof(struct sit_entry_set)); if (!sit_entry_set_slab) goto destroy_discard_cmd; - inmem_entry_slab = f2fs_kmem_cache_create("inmem_page_entry", + inmem_entry_slab = f2fs_kmem_cache_create("f2fs_inmem_page_entry", sizeof(struct inmem_pages)); if (!inmem_entry_slab) goto destroy_sit_entry_set; diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h index 459dc3901a57..7a83bd530812 100644 --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -756,7 +756,7 @@ static inline unsigned long long get_mtime(struct f2fs_sb_info *sbi, bool base_time) { struct sit_info *sit_i = SIT_I(sbi); - time64_t diff, now = ktime_get_real_seconds(); + time64_t diff, now = ktime_get_boottime_seconds(); if (now >= sit_i->mounted_time) return sit_i->elapsed_time + now - sit_i->mounted_time; diff --git a/fs/f2fs/shrinker.c b/fs/f2fs/shrinker.c index a467aca29cfe..d66de5999a26 100644 --- a/fs/f2fs/shrinker.c +++ b/fs/f2fs/shrinker.c @@ -58,7 +58,7 @@ unsigned long f2fs_shrink_count(struct shrinker *shrink, /* count extent cache entries */ count += __count_extent_cache(sbi); - /* shrink clean nat cache entries */ + /* count clean nat cache entries */ count += __count_nat_entries(sbi); /* count free nids cache entries */ diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index d398b2d90c6c..f2dfc21c6abb 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -428,14 +428,11 @@ static int parse_options(struct super_block *sb, char *options) if (!name) return -ENOMEM; if (strlen(name) == 2 && !strncmp(name, "on", 2)) { - set_opt(sbi, BG_GC); - clear_opt(sbi, FORCE_FG_GC); + F2FS_OPTION(sbi).bggc_mode = BGGC_MODE_ON; } else if (strlen(name) == 3 && !strncmp(name, "off", 3)) { - clear_opt(sbi, BG_GC); - clear_opt(sbi, FORCE_FG_GC); + F2FS_OPTION(sbi).bggc_mode = BGGC_MODE_OFF; } else if (strlen(name) == 4 && !strncmp(name, "sync", 4)) { - set_opt(sbi, BG_GC); - set_opt(sbi, FORCE_FG_GC); + F2FS_OPTION(sbi).bggc_mode = BGGC_MODE_SYNC; } else { kvfree(name); return -EINVAL; @@ -447,7 +444,7 @@ static int parse_options(struct super_block *sb, char *options) break; case Opt_norecovery: /* this option mounts f2fs with ro */ - set_opt(sbi, DISABLE_ROLL_FORWARD); + set_opt(sbi, NORECOVERY); if (!f2fs_readonly(sb)) return -EINVAL; break; @@ -601,10 +598,10 @@ static int parse_options(struct super_block *sb, char *options) kvfree(name); return -EINVAL; } - set_opt_mode(sbi, F2FS_MOUNT_ADAPTIVE); + F2FS_OPTION(sbi).fs_mode = FS_MODE_ADAPTIVE; } else if (strlen(name) == 3 && !strncmp(name, "lfs", 3)) { - set_opt_mode(sbi, F2FS_MOUNT_LFS); + F2FS_OPTION(sbi).fs_mode = FS_MODE_LFS; } else { kvfree(name); return -EINVAL; @@ -833,6 +830,10 @@ static int parse_options(struct super_block *sb, char *options) !strcmp(name, "lz4")) { F2FS_OPTION(sbi).compress_algorithm = COMPRESS_LZ4; + } else if (strlen(name) == 4 && + !strcmp(name, "zstd")) { + F2FS_OPTION(sbi).compress_algorithm = + COMPRESS_ZSTD; } else { kfree(name); return -EINVAL; @@ -905,7 +906,7 @@ static int parse_options(struct super_block *sb, char *options) } #endif - if (F2FS_IO_SIZE_BITS(sbi) && !test_opt(sbi, LFS)) { + if (F2FS_IO_SIZE_BITS(sbi) && !f2fs_lfs_mode(sbi)) { f2fs_err(sbi, "Should set mode=lfs with %uKB-sized IO", F2FS_IO_SIZE_KB(sbi)); return -EINVAL; @@ -935,7 +936,7 @@ static int parse_options(struct super_block *sb, char *options) } } - if (test_opt(sbi, DISABLE_CHECKPOINT) && test_opt(sbi, LFS)) { + if (test_opt(sbi, DISABLE_CHECKPOINT) && f2fs_lfs_mode(sbi)) { f2fs_err(sbi, "LFS not compatible with checkpoint=disable\n"); return -EINVAL; } @@ -961,6 +962,7 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb) /* Initialize f2fs-specific inode info */ atomic_set(&fi->dirty_pages, 0); init_rwsem(&fi->i_sem); + spin_lock_init(&fi->i_size_lock); INIT_LIST_HEAD(&fi->dirty_list); INIT_LIST_HEAD(&fi->gdirty_list); INIT_LIST_HEAD(&fi->inmem_ilist); @@ -1173,7 +1175,7 @@ static void f2fs_put_super(struct super_block *sb) /* our cp_error case, we can wait for any writeback page */ f2fs_flush_merged_writes(sbi); - f2fs_wait_on_all_pages_writeback(sbi); + f2fs_wait_on_all_pages(sbi, F2FS_WB_CP_DATA); f2fs_bug_on(sbi, sbi->fsync_node_num); @@ -1205,6 +1207,7 @@ static void f2fs_put_super(struct super_block *sb) kvfree(sbi->raw_super); destroy_device_list(sbi); + f2fs_destroy_xattr_caches(sbi); mempool_destroy(sbi->write_io_dummy); #ifdef CONFIG_QUOTA for (i = 0; i < MAXQUOTAS; i++) @@ -1421,6 +1424,9 @@ static inline void f2fs_show_compress_options(struct seq_file *seq, case COMPRESS_LZ4: algtype = "lz4"; break; + case COMPRESS_ZSTD: + algtype = "zstd"; + break; } seq_printf(seq, ",compress_algorithm=%s", algtype); @@ -1437,16 +1443,17 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) { struct f2fs_sb_info *sbi = F2FS_SB(root->d_sb); - if (!f2fs_readonly(sbi->sb) && test_opt(sbi, BG_GC)) { - if (test_opt(sbi, FORCE_FG_GC)) - seq_printf(seq, ",background_gc=%s", "sync"); - else - seq_printf(seq, ",background_gc=%s", "on"); - } else { + if (F2FS_OPTION(sbi).bggc_mode == BGGC_MODE_SYNC) + seq_printf(seq, ",background_gc=%s", "sync"); + else if (F2FS_OPTION(sbi).bggc_mode == BGGC_MODE_ON) + seq_printf(seq, ",background_gc=%s", "on"); + else if (F2FS_OPTION(sbi).bggc_mode == BGGC_MODE_OFF) seq_printf(seq, ",background_gc=%s", "off"); - } + if (test_opt(sbi, DISABLE_ROLL_FORWARD)) seq_puts(seq, ",disable_roll_forward"); + if (test_opt(sbi, NORECOVERY)) + seq_puts(seq, ",norecovery"); if (test_opt(sbi, DISCARD)) seq_puts(seq, ",discard"); else @@ -1498,9 +1505,9 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) seq_puts(seq, ",data_flush"); seq_puts(seq, ",mode="); - if (test_opt(sbi, ADAPTIVE)) + if (F2FS_OPTION(sbi).fs_mode == FS_MODE_ADAPTIVE) seq_puts(seq, "adaptive"); - else if (test_opt(sbi, LFS)) + else if (F2FS_OPTION(sbi).fs_mode == FS_MODE_LFS) seq_puts(seq, "lfs"); seq_printf(seq, ",active_logs=%u", F2FS_OPTION(sbi).active_logs); if (test_opt(sbi, RESERVE_ROOT)) @@ -1571,11 +1578,11 @@ static void default_options(struct f2fs_sb_info *sbi) F2FS_OPTION(sbi).test_dummy_encryption = false; F2FS_OPTION(sbi).s_resuid = make_kuid(&init_user_ns, F2FS_DEF_RESUID); F2FS_OPTION(sbi).s_resgid = make_kgid(&init_user_ns, F2FS_DEF_RESGID); - F2FS_OPTION(sbi).compress_algorithm = COMPRESS_LZO; + F2FS_OPTION(sbi).compress_algorithm = COMPRESS_LZ4; F2FS_OPTION(sbi).compress_log_size = MIN_COMPRESS_LOG_SIZE; F2FS_OPTION(sbi).compress_ext_cnt = 0; + F2FS_OPTION(sbi).bggc_mode = BGGC_MODE_ON; - set_opt(sbi, BG_GC); set_opt(sbi, INLINE_XATTR); set_opt(sbi, INLINE_DATA); set_opt(sbi, INLINE_DENTRY); @@ -1587,9 +1594,9 @@ static void default_options(struct f2fs_sb_info *sbi) set_opt(sbi, FLUSH_MERGE); set_opt(sbi, DISCARD); if (f2fs_sb_has_blkzoned(sbi)) - set_opt_mode(sbi, F2FS_MOUNT_LFS); + F2FS_OPTION(sbi).fs_mode = FS_MODE_LFS; else - set_opt_mode(sbi, F2FS_MOUNT_ADAPTIVE); + F2FS_OPTION(sbi).fs_mode = FS_MODE_ADAPTIVE; #ifdef CONFIG_F2FS_FS_XATTR set_opt(sbi, XATTR_USER); @@ -1658,7 +1665,7 @@ static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi) out_unlock: up_write(&sbi->gc_lock); restore_flag: - sbi->sb->s_flags = s_flags; /* Restore MS_RDONLY status */ + sbi->sb->s_flags = s_flags; /* Restore SB_RDONLY status */ return err; } @@ -1781,7 +1788,8 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) * or if background_gc = off is passed in mount * option. Also sync the filesystem. */ - if ((*flags & SB_RDONLY) || !test_opt(sbi, BG_GC)) { + if ((*flags & SB_RDONLY) || + F2FS_OPTION(sbi).bggc_mode == BGGC_MODE_OFF) { if (sbi->gc_thread) { f2fs_stop_gc_thread(sbi); need_restart_gc = true; @@ -1886,7 +1894,8 @@ repeat: page = read_cache_page_gfp(mapping, blkidx, GFP_NOFS); if (IS_ERR(page)) { if (PTR_ERR(page) == -ENOMEM) { - congestion_wait(BLK_RW_ASYNC, HZ/50); + congestion_wait(BLK_RW_ASYNC, + DEFAULT_IO_TIMEOUT); goto repeat; } set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR); @@ -1928,6 +1937,7 @@ static ssize_t f2fs_quota_write(struct super_block *sb, int type, int offset = off & (sb->s_blocksize - 1); size_t towrite = len; struct page *page; + void *fsdata = NULL; char *kaddr; int err = 0; int tocopy; @@ -1937,10 +1947,11 @@ static ssize_t f2fs_quota_write(struct super_block *sb, int type, towrite); retry: err = a_ops->write_begin(NULL, mapping, off, tocopy, 0, - &page, NULL); + &page, &fsdata); if (unlikely(err)) { if (err == -ENOMEM) { - congestion_wait(BLK_RW_ASYNC, HZ/50); + congestion_wait(BLK_RW_ASYNC, + DEFAULT_IO_TIMEOUT); goto retry; } set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR); @@ -1953,7 +1964,7 @@ retry: flush_dcache_page(page); a_ops->write_end(NULL, mapping, off, tocopy, tocopy, - page, NULL); + page, fsdata); offset = 0; towrite -= tocopy; off += tocopy; @@ -3457,12 +3468,17 @@ try_onemore: } } + /* init per sbi slab cache */ + err = f2fs_init_xattr_caches(sbi); + if (err) + goto free_io_dummy; + /* get an inode for meta space */ sbi->meta_inode = f2fs_iget(sb, F2FS_META_INO(sbi)); if (IS_ERR(sbi->meta_inode)) { f2fs_err(sbi, "Failed to read F2FS meta data inode"); err = PTR_ERR(sbi->meta_inode); - goto free_io_dummy; + goto free_xattr_cache; } err = f2fs_get_valid_checkpoint(sbi); @@ -3590,7 +3606,7 @@ try_onemore: f2fs_err(sbi, "Cannot turn on quotas: error %d", err); } #endif - /* if there are nt orphan nodes free them */ + /* if there are any orphan inodes, free them */ err = f2fs_recover_orphan_inodes(sbi); if (err) goto free_meta; @@ -3599,7 +3615,8 @@ try_onemore: goto reset_checkpoint; /* recover fsynced data */ - if (!test_opt(sbi, DISABLE_ROLL_FORWARD)) { + if (!test_opt(sbi, DISABLE_ROLL_FORWARD) && + !test_opt(sbi, NORECOVERY)) { /* * mount should be failed, when device has readonly mode, and * previous checkpoint was not done by clean system shutdown. @@ -3665,7 +3682,7 @@ reset_checkpoint: * If filesystem is not mounted as read-only then * do start the gc_thread. */ - if (test_opt(sbi, BG_GC) && !f2fs_readonly(sb)) { + if (F2FS_OPTION(sbi).bggc_mode != BGGC_MODE_OFF && !f2fs_readonly(sb)) { /* After POR, we can run background GC thread.*/ err = f2fs_start_gc_thread(sbi); if (err) @@ -3734,6 +3751,8 @@ free_meta_inode: make_bad_inode(sbi->meta_inode); iput(sbi->meta_inode); sbi->meta_inode = NULL; +free_xattr_cache: + f2fs_destroy_xattr_caches(sbi); free_io_dummy: mempool_destroy(sbi->write_io_dummy); free_percpu: diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index 91d649790b1b..e3bbbef9b4f0 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -109,47 +109,47 @@ static ssize_t features_show(struct f2fs_attr *a, return sprintf(buf, "0\n"); if (f2fs_sb_has_encrypt(sbi)) - len += snprintf(buf, PAGE_SIZE - len, "%s", + len += scnprintf(buf, PAGE_SIZE - len, "%s", "encryption"); if (f2fs_sb_has_blkzoned(sbi)) - len += snprintf(buf + len, PAGE_SIZE - len, "%s%s", + len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s", len ? ", " : "", "blkzoned"); if (f2fs_sb_has_extra_attr(sbi)) - len += snprintf(buf + len, PAGE_SIZE - len, "%s%s", + len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s", len ? ", " : "", "extra_attr"); if (f2fs_sb_has_project_quota(sbi)) - len += snprintf(buf + len, PAGE_SIZE - len, "%s%s", + len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s", len ? ", " : "", "projquota"); if (f2fs_sb_has_inode_chksum(sbi)) - len += snprintf(buf + len, PAGE_SIZE - len, "%s%s", + len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s", len ? ", " : "", "inode_checksum"); if (f2fs_sb_has_flexible_inline_xattr(sbi)) - len += snprintf(buf + len, PAGE_SIZE - len, "%s%s", + len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s", len ? ", " : "", "flexible_inline_xattr"); if (f2fs_sb_has_quota_ino(sbi)) - len += snprintf(buf + len, PAGE_SIZE - len, "%s%s", + len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s", len ? ", " : "", "quota_ino"); if (f2fs_sb_has_inode_crtime(sbi)) - len += snprintf(buf + len, PAGE_SIZE - len, "%s%s", + len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s", len ? ", " : "", "inode_crtime"); if (f2fs_sb_has_lost_found(sbi)) - len += snprintf(buf + len, PAGE_SIZE - len, "%s%s", + len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s", len ? ", " : "", "lost_found"); if (f2fs_sb_has_verity(sbi)) - len += snprintf(buf + len, PAGE_SIZE - len, "%s%s", + len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s", len ? ", " : "", "verity"); if (f2fs_sb_has_sb_chksum(sbi)) - len += snprintf(buf + len, PAGE_SIZE - len, "%s%s", + len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s", len ? ", " : "", "sb_checksum"); if (f2fs_sb_has_casefold(sbi)) - len += snprintf(buf + len, PAGE_SIZE - len, "%s%s", + len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s", len ? ", " : "", "casefold"); if (f2fs_sb_has_compression(sbi)) - len += snprintf(buf + len, PAGE_SIZE - len, "%s%s", + len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s", len ? ", " : "", "compression"); - len += snprintf(buf + len, PAGE_SIZE - len, "%s%s", + len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s", len ? ", " : "", "pin_file"); - len += snprintf(buf + len, PAGE_SIZE - len, "\n"); + len += scnprintf(buf + len, PAGE_SIZE - len, "\n"); return len; } @@ -185,6 +185,12 @@ static ssize_t encoding_show(struct f2fs_attr *a, return sprintf(buf, "(none)"); } +static ssize_t mounted_time_sec_show(struct f2fs_attr *a, + struct f2fs_sb_info *sbi, char *buf) +{ + return sprintf(buf, "%llu", SIT_I(sbi)->mounted_time); +} + #ifdef CONFIG_F2FS_STAT_FS static ssize_t moved_blocks_foreground_show(struct f2fs_attr *a, struct f2fs_sb_info *sbi, char *buf) @@ -233,16 +239,16 @@ static ssize_t f2fs_sbi_show(struct f2fs_attr *a, int hot_count = sbi->raw_super->hot_ext_count; int len = 0, i; - len += snprintf(buf + len, PAGE_SIZE - len, + len += scnprintf(buf + len, PAGE_SIZE - len, "cold file extension:\n"); for (i = 0; i < cold_count; i++) - len += snprintf(buf + len, PAGE_SIZE - len, "%s\n", + len += scnprintf(buf + len, PAGE_SIZE - len, "%s\n", extlist[i]); - len += snprintf(buf + len, PAGE_SIZE - len, + len += scnprintf(buf + len, PAGE_SIZE - len, "hot file extension:\n"); for (i = cold_count; i < cold_count + hot_count; i++) - len += snprintf(buf + len, PAGE_SIZE - len, "%s\n", + len += scnprintf(buf + len, PAGE_SIZE - len, "%s\n", extlist[i]); return len; } @@ -544,6 +550,7 @@ F2FS_GENERAL_RO_ATTR(features); F2FS_GENERAL_RO_ATTR(current_reserved_blocks); F2FS_GENERAL_RO_ATTR(unusable); F2FS_GENERAL_RO_ATTR(encoding); +F2FS_GENERAL_RO_ATTR(mounted_time_sec); #ifdef CONFIG_F2FS_STAT_FS F2FS_STAT_ATTR(STAT_INFO, f2fs_stat_info, cp_foreground_calls, cp_count); F2FS_STAT_ATTR(STAT_INFO, f2fs_stat_info, cp_background_calls, bg_cp_count); @@ -573,7 +580,9 @@ F2FS_FEATURE_RO_ATTR(verity, FEAT_VERITY); #endif F2FS_FEATURE_RO_ATTR(sb_checksum, FEAT_SB_CHECKSUM); F2FS_FEATURE_RO_ATTR(casefold, FEAT_CASEFOLD); +#ifdef CONFIG_F2FS_FS_COMPRESSION F2FS_FEATURE_RO_ATTR(compression, FEAT_COMPRESSION); +#endif #define ATTR_LIST(name) (&f2fs_attr_##name.attr) static struct attribute *f2fs_attrs[] = { @@ -621,6 +630,7 @@ static struct attribute *f2fs_attrs[] = { ATTR_LIST(reserved_blocks), ATTR_LIST(current_reserved_blocks), ATTR_LIST(encoding), + ATTR_LIST(mounted_time_sec), #ifdef CONFIG_F2FS_STAT_FS ATTR_LIST(cp_foreground_calls), ATTR_LIST(cp_background_calls), @@ -654,7 +664,9 @@ static struct attribute *f2fs_feat_attrs[] = { #endif ATTR_LIST(sb_checksum), ATTR_LIST(casefold), +#ifdef CONFIG_F2FS_FS_COMPRESSION ATTR_LIST(compression), +#endif NULL, }; ATTRIBUTE_GROUPS(f2fs_feat); diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c index 296b3189448a..4f6582ef7ee3 100644 --- a/fs/f2fs/xattr.c +++ b/fs/f2fs/xattr.c @@ -23,6 +23,25 @@ #include "xattr.h" #include "segment.h" +static void *xattr_alloc(struct f2fs_sb_info *sbi, int size, bool *is_inline) +{ + if (likely(size == sbi->inline_xattr_slab_size)) { + *is_inline = true; + return kmem_cache_zalloc(sbi->inline_xattr_slab, GFP_NOFS); + } + *is_inline = false; + return f2fs_kzalloc(sbi, size, GFP_NOFS); +} + +static void xattr_free(struct f2fs_sb_info *sbi, void *xattr_addr, + bool is_inline) +{ + if (is_inline) + kmem_cache_free(sbi->inline_xattr_slab, xattr_addr); + else + kvfree(xattr_addr); +} + static int f2fs_xattr_generic_get(const struct xattr_handler *handler, struct dentry *unused, struct inode *inode, const char *name, void *buffer, size_t size) @@ -301,7 +320,8 @@ static int read_xattr_block(struct inode *inode, void *txattr_addr) static int lookup_all_xattrs(struct inode *inode, struct page *ipage, unsigned int index, unsigned int len, const char *name, struct f2fs_xattr_entry **xe, - void **base_addr, int *base_size) + void **base_addr, int *base_size, + bool *is_inline) { void *cur_addr, *txattr_addr, *last_txattr_addr; void *last_addr = NULL; @@ -312,12 +332,12 @@ static int lookup_all_xattrs(struct inode *inode, struct page *ipage, if (!xnid && !inline_size) return -ENODATA; - *base_size = XATTR_SIZE(xnid, inode) + XATTR_PADDING_SIZE; - txattr_addr = f2fs_kzalloc(F2FS_I_SB(inode), *base_size, GFP_NOFS); + *base_size = XATTR_SIZE(inode) + XATTR_PADDING_SIZE; + txattr_addr = xattr_alloc(F2FS_I_SB(inode), *base_size, is_inline); if (!txattr_addr) return -ENOMEM; - last_txattr_addr = (void *)txattr_addr + XATTR_SIZE(xnid, inode); + last_txattr_addr = (void *)txattr_addr + XATTR_SIZE(inode); /* read from inline xattr */ if (inline_size) { @@ -362,7 +382,7 @@ check: *base_addr = txattr_addr; return 0; out: - kvfree(txattr_addr); + xattr_free(F2FS_I_SB(inode), txattr_addr, *is_inline); return err; } @@ -499,6 +519,7 @@ int f2fs_getxattr(struct inode *inode, int index, const char *name, unsigned int size, len; void *base_addr = NULL; int base_size; + bool is_inline; if (name == NULL) return -EINVAL; @@ -509,7 +530,7 @@ int f2fs_getxattr(struct inode *inode, int index, const char *name, down_read(&F2FS_I(inode)->i_xattr_sem); error = lookup_all_xattrs(inode, ipage, index, len, name, - &entry, &base_addr, &base_size); + &entry, &base_addr, &base_size, &is_inline); up_read(&F2FS_I(inode)->i_xattr_sem); if (error) return error; @@ -532,14 +553,13 @@ int f2fs_getxattr(struct inode *inode, int index, const char *name, } error = size; out: - kvfree(base_addr); + xattr_free(F2FS_I_SB(inode), base_addr, is_inline); return error; } ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) { struct inode *inode = d_inode(dentry); - nid_t xnid = F2FS_I(inode)->i_xattr_nid; struct f2fs_xattr_entry *entry; void *base_addr, *last_base_addr; int error = 0; @@ -551,7 +571,7 @@ ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) if (error) return error; - last_base_addr = (void *)base_addr + XATTR_SIZE(xnid, inode); + last_base_addr = (void *)base_addr + XATTR_SIZE(inode); list_for_each_xattr(entry, base_addr) { const struct xattr_handler *handler = @@ -609,7 +629,6 @@ static int __f2fs_setxattr(struct inode *inode, int index, { struct f2fs_xattr_entry *here, *last; void *base_addr, *last_base_addr; - nid_t xnid = F2FS_I(inode)->i_xattr_nid; int found, newsize; size_t len; __u32 new_hsize; @@ -633,7 +652,7 @@ static int __f2fs_setxattr(struct inode *inode, int index, if (error) return error; - last_base_addr = (void *)base_addr + XATTR_SIZE(xnid, inode); + last_base_addr = (void *)base_addr + XATTR_SIZE(inode); /* find entry with wanted name. */ here = __find_xattr(base_addr, last_base_addr, index, len, name); @@ -758,14 +777,34 @@ int f2fs_setxattr(struct inode *inode, int index, const char *name, f2fs_balance_fs(sbi, true); f2fs_lock_op(sbi); - /* protect xattr_ver */ - down_write(&F2FS_I(inode)->i_sem); down_write(&F2FS_I(inode)->i_xattr_sem); err = __f2fs_setxattr(inode, index, name, value, size, ipage, flags); up_write(&F2FS_I(inode)->i_xattr_sem); - up_write(&F2FS_I(inode)->i_sem); f2fs_unlock_op(sbi); f2fs_update_time(sbi, REQ_TIME); return err; } + +int f2fs_init_xattr_caches(struct f2fs_sb_info *sbi) +{ + dev_t dev = sbi->sb->s_bdev->bd_dev; + char slab_name[32]; + + sprintf(slab_name, "f2fs_xattr_entry-%u:%u", MAJOR(dev), MINOR(dev)); + + sbi->inline_xattr_slab_size = F2FS_OPTION(sbi).inline_xattr_size * + sizeof(__le32) + XATTR_PADDING_SIZE; + + sbi->inline_xattr_slab = f2fs_kmem_cache_create(slab_name, + sbi->inline_xattr_slab_size); + if (!sbi->inline_xattr_slab) + return -ENOMEM; + + return 0; +} + +void f2fs_destroy_xattr_caches(struct f2fs_sb_info *sbi) +{ + kmem_cache_destroy(sbi->inline_xattr_slab); +} diff --git a/fs/f2fs/xattr.h b/fs/f2fs/xattr.h index de0c600b9cab..938fcd20565d 100644 --- a/fs/f2fs/xattr.h +++ b/fs/f2fs/xattr.h @@ -49,7 +49,7 @@ struct f2fs_xattr_entry { __u8 e_name_index; __u8 e_name_len; __le16 e_value_size; /* size of attribute value */ - char e_name[0]; /* attribute name */ + char e_name[]; /* attribute name */ }; #define XATTR_HDR(ptr) ((struct f2fs_xattr_header *)(ptr)) @@ -73,7 +73,8 @@ struct f2fs_xattr_entry { entry = XATTR_NEXT_ENTRY(entry)) #define VALID_XATTR_BLOCK_SIZE (PAGE_SIZE - sizeof(struct node_footer)) #define XATTR_PADDING_SIZE (sizeof(__u32)) -#define XATTR_SIZE(x,i) (((x) ? VALID_XATTR_BLOCK_SIZE : 0) + \ +#define XATTR_SIZE(i) ((F2FS_I(i)->i_xattr_nid ? \ + VALID_XATTR_BLOCK_SIZE : 0) + \ (inline_xattr_size(i))) #define MIN_OFFSET(i) XATTR_ALIGN(inline_xattr_size(i) + \ VALID_XATTR_BLOCK_SIZE) @@ -130,6 +131,8 @@ extern int f2fs_setxattr(struct inode *, int, const char *, extern int f2fs_getxattr(struct inode *, int, const char *, void *, size_t, struct page *); extern ssize_t f2fs_listxattr(struct dentry *, char *, size_t); +extern int f2fs_init_xattr_caches(struct f2fs_sb_info *); +extern void f2fs_destroy_xattr_caches(struct f2fs_sb_info *); #else #define f2fs_xattr_handlers NULL @@ -150,6 +153,8 @@ static inline ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, { return -EOPNOTSUPP; } +static inline int f2fs_init_xattr_caches(struct f2fs_sb_info *sbi) { return 0; } +static inline void f2fs_destroy_xattr_caches(struct f2fs_sb_info *sbi) { } #endif #ifdef CONFIG_F2FS_FS_SECURITY diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index ac3f4888b3df..3c383ddd92dd 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -125,6 +125,7 @@ struct f2fs_super_block { /* * For checkpoint */ +#define CP_RESIZEFS_FLAG 0x00004000 #define CP_DISABLED_QUICK_FLAG 0x00002000 #define CP_DISABLED_FLAG 0x00001000 #define CP_QUOTA_NEED_FSCK_FLAG 0x00000800 diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index 67a97838c2a0..d97adfc327f0 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -153,7 +153,8 @@ TRACE_DEFINE_ENUM(CP_PAUSE); #define show_compress_algorithm(type) \ __print_symbolic(type, \ { COMPRESS_LZO, "LZO" }, \ - { COMPRESS_LZ4, "LZ4" }) + { COMPRESS_LZ4, "LZ4" }, \ + { COMPRESS_ZSTD, "ZSTD" }) struct f2fs_sb_info; struct f2fs_io_info;