Message ID | 20181106064122.6154-3-lufq.fnst@cn.fujitsu.com (mailing list archive) |
---|---|
State | New, archived |
Headers | show |
Series | Btrfs In-band De-duplication | expand |
вт, 6 нояб. 2018 г. в 9:41, Lu Fengqi <lufq.fnst@cn.fujitsu.com>: > > From: Wang Xiaoguang <wangxg.fnst@cn.fujitsu.com> > > Add generic function to initialize dedupe info. > > Signed-off-by: Qu Wenruo <quwenruo@cn.fujitsu.com> > Signed-off-by: Wang Xiaoguang <wangxg.fnst@cn.fujitsu.com> > Reviewed-by: Josef Bacik <jbacik@fb.com> > Signed-off-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com> > --- > fs/btrfs/Makefile | 2 +- > fs/btrfs/dedupe.c | 169 +++++++++++++++++++++++++++++++++++++ > fs/btrfs/dedupe.h | 12 +++ > include/uapi/linux/btrfs.h | 3 + > 4 files changed, 185 insertions(+), 1 deletion(-) > create mode 100644 fs/btrfs/dedupe.c > > diff --git a/fs/btrfs/Makefile b/fs/btrfs/Makefile > index ca693dd554e9..78fdc87dba39 100644 > --- a/fs/btrfs/Makefile > +++ b/fs/btrfs/Makefile > @@ -10,7 +10,7 @@ btrfs-y += super.o ctree.o extent-tree.o print-tree.o root-tree.o dir-item.o \ > export.o tree-log.o free-space-cache.o zlib.o lzo.o zstd.o \ > compression.o delayed-ref.o relocation.o delayed-inode.o scrub.o \ > reada.o backref.o ulist.o qgroup.o send.o dev-replace.o raid56.o \ > - uuid-tree.o props.o free-space-tree.o tree-checker.o > + uuid-tree.o props.o free-space-tree.o tree-checker.o dedupe.o > > btrfs-$(CONFIG_BTRFS_FS_POSIX_ACL) += acl.o > btrfs-$(CONFIG_BTRFS_FS_CHECK_INTEGRITY) += check-integrity.o > diff --git a/fs/btrfs/dedupe.c b/fs/btrfs/dedupe.c > new file mode 100644 > index 000000000000..06523162753d > --- /dev/null > +++ b/fs/btrfs/dedupe.c > @@ -0,0 +1,169 @@ > +// SPDX-License-Identifier: GPL-2.0 > +/* > + * Copyright (C) 2016 Fujitsu. All rights reserved. > + */ > + > +#include "ctree.h" > +#include "dedupe.h" > +#include "btrfs_inode.h" > +#include "delayed-ref.h" > + > +struct inmem_hash { > + struct rb_node hash_node; > + struct rb_node bytenr_node; > + struct list_head lru_list; > + > + u64 bytenr; > + u32 num_bytes; > + > + u8 hash[]; > +}; > + > +static struct btrfs_dedupe_info * > +init_dedupe_info(struct btrfs_ioctl_dedupe_args *dargs) > +{ > + struct btrfs_dedupe_info *dedupe_info; > + > + dedupe_info = kzalloc(sizeof(*dedupe_info), GFP_NOFS); > + if (!dedupe_info) > + return ERR_PTR(-ENOMEM); > + > + dedupe_info->hash_algo = dargs->hash_algo; > + dedupe_info->backend = dargs->backend; > + dedupe_info->blocksize = dargs->blocksize; > + dedupe_info->limit_nr = dargs->limit_nr; > + > + /* only support SHA256 yet */ > + dedupe_info->dedupe_driver = crypto_alloc_shash("sha256", 0, 0); > + if (IS_ERR(dedupe_info->dedupe_driver)) { > + kfree(dedupe_info); > + return ERR_CAST(dedupe_info->dedupe_driver); > + } > + > + dedupe_info->hash_root = RB_ROOT; > + dedupe_info->bytenr_root = RB_ROOT; > + dedupe_info->current_nr = 0; > + INIT_LIST_HEAD(&dedupe_info->lru_list); > + mutex_init(&dedupe_info->lock); > + > + return dedupe_info; > +} > + > +/* > + * Helper to check if parameters are valid. > + * The first invalid field will be set to (-1), to info user which parameter > + * is invalid. > + * Except dargs->limit_nr or dargs->limit_mem, in that case, 0 will returned > + * to info user, since user can specify any value to limit, except 0. > + */ > +static int check_dedupe_parameter(struct btrfs_fs_info *fs_info, > + struct btrfs_ioctl_dedupe_args *dargs) > +{ > + u64 blocksize = dargs->blocksize; > + u64 limit_nr = dargs->limit_nr; > + u64 limit_mem = dargs->limit_mem; > + u16 hash_algo = dargs->hash_algo; > + u8 backend = dargs->backend; > + > + /* > + * Set all reserved fields to -1, allow user to detect > + * unsupported optional parameters. > + */ > + memset(dargs->__unused, -1, sizeof(dargs->__unused)); > + if (blocksize > BTRFS_DEDUPE_BLOCKSIZE_MAX || > + blocksize < BTRFS_DEDUPE_BLOCKSIZE_MIN || > + blocksize < fs_info->sectorsize || > + !is_power_of_2(blocksize) || > + blocksize < PAGE_SIZE) { > + dargs->blocksize = (u64)-1; > + return -EINVAL; > + } > + if (hash_algo >= ARRAY_SIZE(btrfs_hash_sizes)) { > + dargs->hash_algo = (u16)-1; > + return -EINVAL; > + } > + if (backend >= BTRFS_DEDUPE_BACKEND_COUNT) { > + dargs->backend = (u8)-1; > + return -EINVAL; > + } > + > + /* Backend specific check */ > + if (backend == BTRFS_DEDUPE_BACKEND_INMEMORY) { > + /* only one limit is accepted for enable*/ > + if (dargs->limit_nr && dargs->limit_mem) { > + dargs->limit_nr = 0; > + dargs->limit_mem = 0; > + return -EINVAL; > + } > + > + if (!limit_nr && !limit_mem) > + dargs->limit_nr = BTRFS_DEDUPE_LIMIT_NR_DEFAULT; > + else { > + u64 tmp = (u64)-1; > + > + if (limit_mem) { > + tmp = div_u64(limit_mem, > + (sizeof(struct inmem_hash)) + > + btrfs_hash_sizes[hash_algo]); > + /* Too small limit_mem to fill a hash item */ > + if (!tmp) { > + dargs->limit_mem = 0; > + dargs->limit_nr = 0; > + return -EINVAL; > + } > + } > + if (!limit_nr) > + limit_nr = (u64)-1; > + > + dargs->limit_nr = min(tmp, limit_nr); > + } > + } > + if (backend == BTRFS_DEDUPE_BACKEND_ONDISK) > + dargs->limit_nr = 0; > + > + return 0; > +} > + > +int btrfs_dedupe_enable(struct btrfs_fs_info *fs_info, > + struct btrfs_ioctl_dedupe_args *dargs) > +{ > + struct btrfs_dedupe_info *dedupe_info; > + int ret = 0; > + > + ret = check_dedupe_parameter(fs_info, dargs); > + if (ret < 0) > + return ret; > + > + dedupe_info = fs_info->dedupe_info; > + if (dedupe_info) { > + /* Check if we are re-enable for different dedupe config */ > + if (dedupe_info->blocksize != dargs->blocksize || > + dedupe_info->hash_algo != dargs->hash_algo || > + dedupe_info->backend != dargs->backend) { > + btrfs_dedupe_disable(fs_info); > + goto enable; > + } > + > + /* On-fly limit change is OK */ > + mutex_lock(&dedupe_info->lock); > + fs_info->dedupe_info->limit_nr = dargs->limit_nr; > + mutex_unlock(&dedupe_info->lock); > + return 0; > + } > + > +enable: > + dedupe_info = init_dedupe_info(dargs); > + if (IS_ERR(dedupe_info)) > + return PTR_ERR(dedupe_info); > + fs_info->dedupe_info = dedupe_info; > + /* We must ensure dedupe_bs is modified after dedupe_info */ > + smp_wmb(); > + fs_info->dedupe_enabled = 1; > + return ret; > +} > + > +int btrfs_dedupe_disable(struct btrfs_fs_info *fs_info) > +{ > + /* Place holder for bisect, will be implemented in later patches */ > + return 0; > +} > diff --git a/fs/btrfs/dedupe.h b/fs/btrfs/dedupe.h > index 222ce7b4d827..87f5b7ce7766 100644 > --- a/fs/btrfs/dedupe.h > +++ b/fs/btrfs/dedupe.h > @@ -52,6 +52,18 @@ static inline int btrfs_dedupe_hash_hit(struct btrfs_dedupe_hash *hash) > return (hash && hash->bytenr); > } > > +static inline int btrfs_dedupe_hash_size(u16 algo) > +{ > + if (WARN_ON(algo >= ARRAY_SIZE(btrfs_hash_sizes))) > + return -EINVAL; > + return sizeof(struct btrfs_dedupe_hash) + btrfs_hash_sizes[algo]; > +} > + > +static inline struct btrfs_dedupe_hash *btrfs_dedupe_alloc_hash(u16 algo) > +{ > + return kzalloc(btrfs_dedupe_hash_size(algo), GFP_NOFS); > +} > + > /* > * Initial inband dedupe info > * Called at dedupe enable time. > diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h > index 9cd15d2a40aa..ba879ac931f2 100644 > --- a/include/uapi/linux/btrfs.h > +++ b/include/uapi/linux/btrfs.h > @@ -683,6 +683,9 @@ struct btrfs_ioctl_get_dev_stats { > /* Hash algorithm, only support SHA256 yet */ > #define BTRFS_DEDUPE_HASH_SHA256 0 > > +/* Default dedupe limit on number of hash */ > +#define BTRFS_DEDUPE_LIMIT_NR_DEFAULT (32 * 1024) > + > /* > * This structure is used for dedupe enable/disable/configure > * and status ioctl. > -- > 2.19.1 > > > Reviewed-by: Timofey Titovets <nefelim4ag@gmail.com> Thanks.
diff --git a/fs/btrfs/Makefile b/fs/btrfs/Makefile index ca693dd554e9..78fdc87dba39 100644 --- a/fs/btrfs/Makefile +++ b/fs/btrfs/Makefile @@ -10,7 +10,7 @@ btrfs-y += super.o ctree.o extent-tree.o print-tree.o root-tree.o dir-item.o \ export.o tree-log.o free-space-cache.o zlib.o lzo.o zstd.o \ compression.o delayed-ref.o relocation.o delayed-inode.o scrub.o \ reada.o backref.o ulist.o qgroup.o send.o dev-replace.o raid56.o \ - uuid-tree.o props.o free-space-tree.o tree-checker.o + uuid-tree.o props.o free-space-tree.o tree-checker.o dedupe.o btrfs-$(CONFIG_BTRFS_FS_POSIX_ACL) += acl.o btrfs-$(CONFIG_BTRFS_FS_CHECK_INTEGRITY) += check-integrity.o diff --git a/fs/btrfs/dedupe.c b/fs/btrfs/dedupe.c new file mode 100644 index 000000000000..06523162753d --- /dev/null +++ b/fs/btrfs/dedupe.c @@ -0,0 +1,169 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2016 Fujitsu. All rights reserved. + */ + +#include "ctree.h" +#include "dedupe.h" +#include "btrfs_inode.h" +#include "delayed-ref.h" + +struct inmem_hash { + struct rb_node hash_node; + struct rb_node bytenr_node; + struct list_head lru_list; + + u64 bytenr; + u32 num_bytes; + + u8 hash[]; +}; + +static struct btrfs_dedupe_info * +init_dedupe_info(struct btrfs_ioctl_dedupe_args *dargs) +{ + struct btrfs_dedupe_info *dedupe_info; + + dedupe_info = kzalloc(sizeof(*dedupe_info), GFP_NOFS); + if (!dedupe_info) + return ERR_PTR(-ENOMEM); + + dedupe_info->hash_algo = dargs->hash_algo; + dedupe_info->backend = dargs->backend; + dedupe_info->blocksize = dargs->blocksize; + dedupe_info->limit_nr = dargs->limit_nr; + + /* only support SHA256 yet */ + dedupe_info->dedupe_driver = crypto_alloc_shash("sha256", 0, 0); + if (IS_ERR(dedupe_info->dedupe_driver)) { + kfree(dedupe_info); + return ERR_CAST(dedupe_info->dedupe_driver); + } + + dedupe_info->hash_root = RB_ROOT; + dedupe_info->bytenr_root = RB_ROOT; + dedupe_info->current_nr = 0; + INIT_LIST_HEAD(&dedupe_info->lru_list); + mutex_init(&dedupe_info->lock); + + return dedupe_info; +} + +/* + * Helper to check if parameters are valid. + * The first invalid field will be set to (-1), to info user which parameter + * is invalid. + * Except dargs->limit_nr or dargs->limit_mem, in that case, 0 will returned + * to info user, since user can specify any value to limit, except 0. + */ +static int check_dedupe_parameter(struct btrfs_fs_info *fs_info, + struct btrfs_ioctl_dedupe_args *dargs) +{ + u64 blocksize = dargs->blocksize; + u64 limit_nr = dargs->limit_nr; + u64 limit_mem = dargs->limit_mem; + u16 hash_algo = dargs->hash_algo; + u8 backend = dargs->backend; + + /* + * Set all reserved fields to -1, allow user to detect + * unsupported optional parameters. + */ + memset(dargs->__unused, -1, sizeof(dargs->__unused)); + if (blocksize > BTRFS_DEDUPE_BLOCKSIZE_MAX || + blocksize < BTRFS_DEDUPE_BLOCKSIZE_MIN || + blocksize < fs_info->sectorsize || + !is_power_of_2(blocksize) || + blocksize < PAGE_SIZE) { + dargs->blocksize = (u64)-1; + return -EINVAL; + } + if (hash_algo >= ARRAY_SIZE(btrfs_hash_sizes)) { + dargs->hash_algo = (u16)-1; + return -EINVAL; + } + if (backend >= BTRFS_DEDUPE_BACKEND_COUNT) { + dargs->backend = (u8)-1; + return -EINVAL; + } + + /* Backend specific check */ + if (backend == BTRFS_DEDUPE_BACKEND_INMEMORY) { + /* only one limit is accepted for enable*/ + if (dargs->limit_nr && dargs->limit_mem) { + dargs->limit_nr = 0; + dargs->limit_mem = 0; + return -EINVAL; + } + + if (!limit_nr && !limit_mem) + dargs->limit_nr = BTRFS_DEDUPE_LIMIT_NR_DEFAULT; + else { + u64 tmp = (u64)-1; + + if (limit_mem) { + tmp = div_u64(limit_mem, + (sizeof(struct inmem_hash)) + + btrfs_hash_sizes[hash_algo]); + /* Too small limit_mem to fill a hash item */ + if (!tmp) { + dargs->limit_mem = 0; + dargs->limit_nr = 0; + return -EINVAL; + } + } + if (!limit_nr) + limit_nr = (u64)-1; + + dargs->limit_nr = min(tmp, limit_nr); + } + } + if (backend == BTRFS_DEDUPE_BACKEND_ONDISK) + dargs->limit_nr = 0; + + return 0; +} + +int btrfs_dedupe_enable(struct btrfs_fs_info *fs_info, + struct btrfs_ioctl_dedupe_args *dargs) +{ + struct btrfs_dedupe_info *dedupe_info; + int ret = 0; + + ret = check_dedupe_parameter(fs_info, dargs); + if (ret < 0) + return ret; + + dedupe_info = fs_info->dedupe_info; + if (dedupe_info) { + /* Check if we are re-enable for different dedupe config */ + if (dedupe_info->blocksize != dargs->blocksize || + dedupe_info->hash_algo != dargs->hash_algo || + dedupe_info->backend != dargs->backend) { + btrfs_dedupe_disable(fs_info); + goto enable; + } + + /* On-fly limit change is OK */ + mutex_lock(&dedupe_info->lock); + fs_info->dedupe_info->limit_nr = dargs->limit_nr; + mutex_unlock(&dedupe_info->lock); + return 0; + } + +enable: + dedupe_info = init_dedupe_info(dargs); + if (IS_ERR(dedupe_info)) + return PTR_ERR(dedupe_info); + fs_info->dedupe_info = dedupe_info; + /* We must ensure dedupe_bs is modified after dedupe_info */ + smp_wmb(); + fs_info->dedupe_enabled = 1; + return ret; +} + +int btrfs_dedupe_disable(struct btrfs_fs_info *fs_info) +{ + /* Place holder for bisect, will be implemented in later patches */ + return 0; +} diff --git a/fs/btrfs/dedupe.h b/fs/btrfs/dedupe.h index 222ce7b4d827..87f5b7ce7766 100644 --- a/fs/btrfs/dedupe.h +++ b/fs/btrfs/dedupe.h @@ -52,6 +52,18 @@ static inline int btrfs_dedupe_hash_hit(struct btrfs_dedupe_hash *hash) return (hash && hash->bytenr); } +static inline int btrfs_dedupe_hash_size(u16 algo) +{ + if (WARN_ON(algo >= ARRAY_SIZE(btrfs_hash_sizes))) + return -EINVAL; + return sizeof(struct btrfs_dedupe_hash) + btrfs_hash_sizes[algo]; +} + +static inline struct btrfs_dedupe_hash *btrfs_dedupe_alloc_hash(u16 algo) +{ + return kzalloc(btrfs_dedupe_hash_size(algo), GFP_NOFS); +} + /* * Initial inband dedupe info * Called at dedupe enable time. diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index 9cd15d2a40aa..ba879ac931f2 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -683,6 +683,9 @@ struct btrfs_ioctl_get_dev_stats { /* Hash algorithm, only support SHA256 yet */ #define BTRFS_DEDUPE_HASH_SHA256 0 +/* Default dedupe limit on number of hash */ +#define BTRFS_DEDUPE_LIMIT_NR_DEFAULT (32 * 1024) + /* * This structure is used for dedupe enable/disable/configure * and status ioctl.