All of lore.kernel.org
 help / color / mirror / Atom feed
From: Qu Wenruo <quwenruo@cn.fujitsu.com>
To: linux-btrfs@vger.kernel.org
Cc: Wang Xiaoguang <wangxg.fnst@cn.fujitsu.com>
Subject: [PATCH v12.2 11/15] btrfs: dedupe: Add ioctl for inband dedupelication
Date: Tue, 19 Jul 2016 16:50:46 +0800	[thread overview]
Message-ID: <20160719085050.30564-12-quwenruo@cn.fujitsu.com> (raw)
In-Reply-To: <20160719085050.30564-1-quwenruo@cn.fujitsu.com>

From: Wang Xiaoguang <wangxg.fnst@cn.fujitsu.com>

Add ioctl interface for inband dedupelication, which includes:
1) enable
2) disable
3) status

And a pseudo RO compat flag, to imply that btrfs now supports inband
dedup.
However we don't add any ondisk format change, it's just a pseudo RO
compat flag.

All these ioctl interfaces are state-less, which means caller don't need
to bother previous dedupe state before calling them, and only need to
care the final desired state.

For example, if user want to enable dedupe with specified block size and
limit, just fill the ioctl structure and call enable ioctl.
No need to check if dedupe is already running.

These ioctls will handle things like re-configure or disable quite well.

Also, for invalid parameters, enable ioctl interface will set the field
of the first encounted invalid parameter to (-1) to inform caller.
While for limit_nr/limit_mem, the value will be (0).

Signed-off-by: Qu Wenruo <quwenruo@cn.fujitsu.com>
Signed-off-by: Wang Xiaoguang <wangxg.fnst@cn.fujitsu.com>
---
 fs/btrfs/dedupe.c          | 50 ++++++++++++++++++++++++++++++++++
 fs/btrfs/dedupe.h          | 17 ++++++++----
 fs/btrfs/disk-io.c         |  3 ++
 fs/btrfs/ioctl.c           | 68 ++++++++++++++++++++++++++++++++++++++++++++++
 fs/btrfs/sysfs.c           |  2 ++
 include/uapi/linux/btrfs.h | 12 +++++++-
 6 files changed, 146 insertions(+), 6 deletions(-)

diff --git a/fs/btrfs/dedupe.c b/fs/btrfs/dedupe.c
index 6296b65..ad1bb82 100644
--- a/fs/btrfs/dedupe.c
+++ b/fs/btrfs/dedupe.c
@@ -41,6 +41,35 @@ static inline struct inmem_hash *inmem_alloc_hash(u16 algo)
 			GFP_NOFS);
 }
 
+void btrfs_dedupe_status(struct btrfs_fs_info *fs_info,
+			 struct btrfs_ioctl_dedupe_args *dargs)
+{
+	struct btrfs_dedupe_info *dedupe_info = fs_info->dedupe_info;
+
+	if (!fs_info->dedupe_enabled || !dedupe_info) {
+		dargs->status = 0;
+		dargs->blocksize = 0;
+		dargs->backend = 0;
+		dargs->hash_algo = 0;
+		dargs->limit_nr = 0;
+		dargs->current_nr = 0;
+		memset(dargs->__unused, -1, sizeof(dargs->__unused));
+		return;
+	}
+	mutex_lock(&dedupe_info->lock);
+	dargs->status = 1;
+	dargs->blocksize = dedupe_info->blocksize;
+	dargs->backend = dedupe_info->backend;
+	dargs->hash_algo = dedupe_info->hash_algo;
+	dargs->limit_nr = dedupe_info->limit_nr;
+	dargs->limit_mem = dedupe_info->limit_nr *
+		(sizeof(struct inmem_hash) +
+		 btrfs_hash_sizes[dedupe_info->hash_algo]);
+	dargs->current_nr = dedupe_info->current_nr;
+	mutex_unlock(&dedupe_info->lock);
+	memset(dargs->__unused, -1, sizeof(dargs->__unused));
+}
+
 static int init_dedupe_info(struct btrfs_dedupe_info **ret_info,
 			    struct btrfs_ioctl_dedupe_args *dargs)
 {
@@ -420,6 +449,27 @@ static void unblock_all_writers(struct btrfs_fs_info *fs_info)
 	percpu_up_write(sb->s_writers.rw_sem + SB_FREEZE_WRITE - 1);
 }
 
+int btrfs_dedupe_cleanup(struct btrfs_fs_info *fs_info)
+{
+	struct btrfs_dedupe_info *dedupe_info;
+
+	fs_info->dedupe_enabled = 0;
+	/* same as disable */
+	smp_wmb();
+	dedupe_info = fs_info->dedupe_info;
+	fs_info->dedupe_info = NULL;
+
+	if (!dedupe_info)
+		return 0;
+
+	if (dedupe_info->backend == BTRFS_DEDUPE_BACKEND_INMEMORY)
+		inmem_destroy(dedupe_info);
+
+	crypto_free_shash(dedupe_info->dedupe_driver);
+	kfree(dedupe_info);
+	return 0;
+}
+
 int btrfs_dedupe_disable(struct btrfs_fs_info *fs_info)
 {
 	struct btrfs_dedupe_info *dedupe_info;
diff --git a/fs/btrfs/dedupe.h b/fs/btrfs/dedupe.h
index e45915a..48812cb 100644
--- a/fs/btrfs/dedupe.h
+++ b/fs/btrfs/dedupe.h
@@ -91,6 +91,15 @@ static inline struct btrfs_dedupe_hash *btrfs_dedupe_alloc_hash(u16 algo)
 int btrfs_dedupe_enable(struct btrfs_fs_info *fs_info,
 			struct btrfs_ioctl_dedupe_args *dargs);
 
+
+ /*
+ * Get inband dedupe info
+ * Since it needs to access different backends' hash size, which
+ * is not exported, we need such simple function.
+ */
+void btrfs_dedupe_status(struct btrfs_fs_info *fs_info,
+			 struct btrfs_ioctl_dedupe_args *dargs);
+
 /*
  * Disable dedupe and invalidate all its dedupe data.
  * Called at dedupe disable time.
@@ -102,12 +111,10 @@ int btrfs_dedupe_enable(struct btrfs_fs_info *fs_info,
 int btrfs_dedupe_disable(struct btrfs_fs_info *fs_info);
 
 /*
- * Get current dedupe status.
- * Return 0 for success
- * No possible error yet
+ * Cleanup current btrfs_dedupe_info
+ * Called in umount time
  */
-void btrfs_dedupe_status(struct btrfs_fs_info *fs_info,
-			 struct btrfs_ioctl_dedupe_args *dargs);
+int btrfs_dedupe_cleanup(struct btrfs_fs_info *fs_info);
 
 /*
  * Calculate hash for dedupe.
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 24c1438..a9dc881 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -50,6 +50,7 @@
 #include "sysfs.h"
 #include "qgroup.h"
 #include "compression.h"
+#include "dedupe.h"
 
 #ifdef CONFIG_X86
 #include <asm/cpufeature.h>
@@ -3904,6 +3905,8 @@ void close_ctree(struct btrfs_root *root)
 
 	btrfs_free_qgroup_config(fs_info);
 
+	btrfs_dedupe_cleanup(fs_info);
+
 	if (percpu_counter_sum(&fs_info->delalloc_bytes)) {
 		btrfs_info(fs_info, "at unmount delalloc count %lld",
 		       percpu_counter_sum(&fs_info->delalloc_bytes));
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 14ed1e9..da327f8 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -61,6 +61,7 @@
 #include "qgroup.h"
 #include "tree-log.h"
 #include "compression.h"
+#include "dedupe.h"
 
 #ifdef CONFIG_64BIT
 /* If we have a 32-bit userspace and 64-bit kernel, then the UAPI
@@ -3267,6 +3268,69 @@ ssize_t btrfs_dedupe_file_range(struct file *src_file, u64 loff, u64 olen,
 	return olen;
 }
 
+static long btrfs_ioctl_dedupe_ctl(struct btrfs_root *root, void __user *args)
+{
+	struct btrfs_ioctl_dedupe_args *dargs;
+	struct btrfs_fs_info *fs_info = root->fs_info;
+	int ret = 0;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	dargs = memdup_user(args, sizeof(*dargs));
+	if (IS_ERR(dargs)) {
+		ret = PTR_ERR(dargs);
+		return ret;
+	}
+
+	if (dargs->cmd >= BTRFS_DEDUPE_CTL_LAST) {
+		ret = -EINVAL;
+		goto out;
+	}
+	switch (dargs->cmd) {
+	case BTRFS_DEDUPE_CTL_ENABLE:
+		mutex_lock(&fs_info->dedupe_ioctl_lock);
+		ret = btrfs_dedupe_enable(fs_info, dargs);
+		/*
+		 * Also copy the result to caller for further use
+		 * if enable succeeded.
+		 * For error case, dargs is already set up with
+		 * special values indicating error reason.
+		 */
+		if (!ret)
+			btrfs_dedupe_status(fs_info, dargs);
+		mutex_unlock(&fs_info->dedupe_ioctl_lock);
+		break;
+	case BTRFS_DEDUPE_CTL_DISABLE:
+		mutex_lock(&fs_info->dedupe_ioctl_lock);
+		ret = btrfs_dedupe_disable(fs_info);
+		btrfs_dedupe_status(fs_info, dargs);
+		mutex_unlock(&fs_info->dedupe_ioctl_lock);
+		break;
+	case BTRFS_DEDUPE_CTL_STATUS:
+		mutex_lock(&fs_info->dedupe_ioctl_lock);
+		btrfs_dedupe_status(fs_info, dargs);
+		mutex_unlock(&fs_info->dedupe_ioctl_lock);
+		break;
+	default:
+		/*
+		 * Use this return value to inform progs that kernel
+		 * doesn't support such new command.
+		 */
+		ret = -EOPNOTSUPP;
+		goto out;
+	}
+	/*
+	 * All ioctl subcommand will modify user dargs,
+	 * Don't override return value unless copy fails
+	 */
+	if (copy_to_user(args, dargs, sizeof(*dargs)))
+		ret = -EFAULT;
+out:
+	kfree(dargs);
+	return ret;
+}
+
 static int clone_finish_inode_update(struct btrfs_trans_handle *trans,
 				     struct inode *inode,
 				     u64 endoff,
@@ -5615,6 +5679,10 @@ long btrfs_ioctl(struct file *file, unsigned int
 		return btrfs_ioctl_get_fslabel(file, argp);
 	case BTRFS_IOC_SET_FSLABEL:
 		return btrfs_ioctl_set_fslabel(file, argp);
+#ifdef CONFIG_BTRFS_DEBUG
+	case BTRFS_IOC_DEDUPE_CTL:
+		return btrfs_ioctl_dedupe_ctl(root, argp);
+#endif
 	case BTRFS_IOC_GET_SUPPORTED_FEATURES:
 		return btrfs_ioctl_get_supported_features(argp);
 	case BTRFS_IOC_GET_FEATURES:
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index c656990..7b0fcca 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -206,6 +206,7 @@ BTRFS_FEAT_ATTR_INCOMPAT(raid56, RAID56);
 BTRFS_FEAT_ATTR_INCOMPAT(skinny_metadata, SKINNY_METADATA);
 BTRFS_FEAT_ATTR_INCOMPAT(no_holes, NO_HOLES);
 BTRFS_FEAT_ATTR_COMPAT_RO(free_space_tree, FREE_SPACE_TREE);
+BTRFS_FEAT_ATTR_COMPAT_RO(dedupe, DEDUPE);
 
 static struct attribute *btrfs_supported_feature_attrs[] = {
 	BTRFS_FEAT_ATTR_PTR(mixed_backref),
@@ -218,6 +219,7 @@ static struct attribute *btrfs_supported_feature_attrs[] = {
 	BTRFS_FEAT_ATTR_PTR(skinny_metadata),
 	BTRFS_FEAT_ATTR_PTR(no_holes),
 	BTRFS_FEAT_ATTR_PTR(free_space_tree),
+	BTRFS_FEAT_ATTR_PTR(dedupe),
 	NULL
 };
 
diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h
index 79130ec..02c06a7 100644
--- a/include/uapi/linux/btrfs.h
+++ b/include/uapi/linux/btrfs.h
@@ -240,6 +240,7 @@ struct btrfs_ioctl_fs_info_args {
  * struct btrfs_ioctl_feature_flags
  */
 #define BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE	(1ULL << 0)
+#define BTRFS_FEATURE_COMPAT_RO_DEDUPE		(1ULL << 1)
 
 #define BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF	(1ULL << 0)
 #define BTRFS_FEATURE_INCOMPAT_DEFAULT_SUBVOL	(1ULL << 1)
@@ -636,7 +637,14 @@ struct btrfs_ioctl_get_dev_stats {
 
 /* Default dedupe limit on number of hash */
 #define BTRFS_DEDUPE_LIMIT_NR_DEFAULT	(32 * 1024)
-
+/*
+ * de-duplication control modes
+ * For re-config, re-enable will handle it
+ */
+#define BTRFS_DEDUPE_CTL_ENABLE	1
+#define BTRFS_DEDUPE_CTL_DISABLE 2
+#define BTRFS_DEDUPE_CTL_STATUS	3
+#define BTRFS_DEDUPE_CTL_LAST	4
 /*
  * This structure is used for dedupe enable/disable/configure
  * and status ioctl.
@@ -863,6 +871,8 @@ static inline char *btrfs_err_str(enum btrfs_err_code err_code)
 				    struct btrfs_ioctl_dev_replace_args)
 #define BTRFS_IOC_FILE_EXTENT_SAME _IOWR(BTRFS_IOCTL_MAGIC, 54, \
 					 struct btrfs_ioctl_same_args)
+#define BTRFS_IOC_DEDUPE_CTL	_IOWR(BTRFS_IOCTL_MAGIC, 55, \
+				      struct btrfs_ioctl_dedupe_args)
 #define BTRFS_IOC_GET_FEATURES _IOR(BTRFS_IOCTL_MAGIC, 57, \
 				   struct btrfs_ioctl_feature_flags)
 #define BTRFS_IOC_SET_FEATURES _IOW(BTRFS_IOCTL_MAGIC, 57, \
-- 
2.9.0




  parent reply	other threads:[~2016-07-19  8:51 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-07-19  8:50 [PATCH v12.2 00/15] Btrfs In-band De-duplication Qu Wenruo
2016-07-19  8:50 ` [PATCH v12.2 01/15] btrfs: expand btrfs_set_extent_delalloc() and its friends to support in-band dedupe and subpage size patchset Qu Wenruo
2016-08-09  1:19   ` Qu Wenruo
2016-09-07 14:53     ` David Sterba
2016-07-19  8:50 ` [PATCH v12.2 02/15] btrfs: dedupe: Introduce dedupe framework and its header Qu Wenruo
2016-07-19  8:50 ` [PATCH v12.2 03/15] btrfs: dedupe: Introduce function to initialize dedupe info Qu Wenruo
2016-07-25  8:17   ` kbuild test robot
2016-07-19  8:50 ` [PATCH v12.2 04/15] btrfs: dedupe: Introduce function to add hash into in-memory tree Qu Wenruo
2016-07-19  8:50 ` [PATCH v12.2 05/15] btrfs: dedupe: Introduce function to remove hash from " Qu Wenruo
2016-07-19  8:50 ` [PATCH v12.2 06/15] btrfs: delayed-ref: Add support for increasing data ref under spinlock Qu Wenruo
2016-07-19  8:50 ` [PATCH v12.2 07/15] btrfs: dedupe: Introduce function to search for an existing hash Qu Wenruo
2016-07-19  8:50 ` [PATCH v12.2 08/15] btrfs: dedupe: Implement btrfs_dedupe_calc_hash interface Qu Wenruo
2016-07-19  8:50 ` [PATCH v12.2 09/15] btrfs: ordered-extent: Add support for dedupe Qu Wenruo
2016-07-19  8:50 ` [PATCH v12.2 10/15] btrfs: dedupe: Inband in-memory only de-duplication implement Qu Wenruo
2016-07-19  8:50 ` Qu Wenruo [this message]
2016-07-19  8:50 ` [PATCH v12.2 12/15] btrfs: relocation: Enhance error handling to avoid BUG_ON Qu Wenruo
2016-07-19  8:50 ` [PATCH v12.2 13/15] btrfs: improve inode's outstanding_extents computation Qu Wenruo
2016-07-19  8:50 ` [PATCH v12.2 14/15] btrfs: dedupe: fix false ENOSPC Qu Wenruo
2016-07-19  8:50 ` [PATCH v12.2 15/15] btrfs: dedupe: Introduce new reconfigure ioctl Qu Wenruo

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20160719085050.30564-12-quwenruo@cn.fujitsu.com \
    --to=quwenruo@cn.fujitsu.com \
    --cc=linux-btrfs@vger.kernel.org \
    --cc=wangxg.fnst@cn.fujitsu.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.