Linux-Fsdevel Archive on lore.kernel.org
 help / color / Atom feed
From: Andiry Xu <jix024@eng.ucsd.edu>
To: linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-nvdimm@lists.01.org
Cc: dan.j.williams@intel.com, andy.rudoff@intel.com,
	coughlan@redhat.com, swanson@cs.ucsd.edu, david@fromorbit.com,
	jack@suse.com, swhiteho@redhat.com, miklos@szeredi.hu,
	andiry.xu@gmail.com, Andiry Xu <jix024@cs.ucsd.edu>
Subject: [RFC v2 45/83] Log operation: file inode log lookup and assign
Date: Sat, 10 Mar 2018 10:18:26 -0800
Message-ID: <1520705944-6723-46-git-send-email-jix024@eng.ucsd.edu> (raw)
In-Reply-To: <1520705944-6723-1-git-send-email-jix024@eng.ucsd.edu>

From: Andiry Xu <jix024@cs.ucsd.edu>

After NOVA appends file write entry to commit new writes,
it updates the file offset radix tree, finds the old entries (if overwrite)
and reclaims the stale data blocks.

Signed-off-by: Andiry Xu <jix024@cs.ucsd.edu>
---
 fs/nova/log.c  | 108 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 fs/nova/log.h  |   5 +++
 fs/nova/nova.h |  64 ++++++++++++++++++++++++++++++++++
 3 files changed, 177 insertions(+)

diff --git a/fs/nova/log.c b/fs/nova/log.c
index d150f2e..451be27 100644
--- a/fs/nova/log.c
+++ b/fs/nova/log.c
@@ -102,6 +102,50 @@ static inline int nova_invalidate_write_entry(struct super_block *sb,
 							reassign, num_free);
 }
 
+unsigned int nova_free_old_entry(struct super_block *sb,
+	struct nova_inode_info_header *sih,
+	struct nova_file_write_entry *entry,
+	unsigned long pgoff, unsigned int num_free,
+	bool delete_dead, u64 epoch_id)
+{
+	unsigned long old_nvmm;
+	timing_t free_time;
+
+	if (!entry)
+		return 0;
+
+	NOVA_START_TIMING(free_old_t, free_time);
+
+	old_nvmm = get_nvmm(sb, sih, entry, pgoff);
+
+	if (!delete_dead)
+		nova_invalidate_write_entry(sb, entry, 1, num_free);
+
+	nova_dbgv("%s: pgoff %lu, free %u blocks\n",
+				__func__, pgoff, num_free);
+	nova_free_data_blocks(sb, sih, old_nvmm, num_free);
+
+	sih->i_blocks -= num_free;
+
+	NOVA_END_TIMING(free_old_t, free_time);
+	return num_free;
+}
+
+struct nova_file_write_entry *nova_find_next_entry(struct super_block *sb,
+	struct nova_inode_info_header *sih, pgoff_t pgoff)
+{
+	struct nova_file_write_entry *entry = NULL;
+	struct nova_file_write_entry *entries[1];
+	int nr_entries;
+
+	nr_entries = radix_tree_gang_lookup(&sih->tree,
+					(void **)entries, pgoff, 1);
+	if (nr_entries == 1)
+		entry = entries[0];
+
+	return entry;
+}
+
 static void nova_update_setattr_entry(struct inode *inode,
 	struct nova_setattr_logentry *entry,
 	struct nova_log_entry_info *entry_info)
@@ -568,6 +612,70 @@ int nova_append_link_change_entry(struct super_block *sb,
 	return ret;
 }
 
+int nova_assign_write_entry(struct super_block *sb,
+	struct nova_inode_info_header *sih,
+	struct nova_file_write_entry *entry,
+	bool free)
+{
+	struct nova_file_write_entry *old_entry;
+	struct nova_file_write_entry *start_old_entry = NULL;
+	void **pentry;
+	unsigned long start_pgoff = entry->pgoff;
+	unsigned long start_old_pgoff = 0;
+	unsigned int num = entry->num_pages;
+	unsigned int num_free = 0;
+	unsigned long curr_pgoff;
+	int i;
+	int ret = 0;
+	timing_t assign_time;
+
+	NOVA_START_TIMING(assign_t, assign_time);
+	for (i = 0; i < num; i++) {
+		curr_pgoff = start_pgoff + i;
+
+		pentry = radix_tree_lookup_slot(&sih->tree, curr_pgoff);
+		if (pentry) {
+			old_entry = radix_tree_deref_slot(pentry);
+			if (old_entry != start_old_entry) {
+				if (start_old_entry && free)
+					nova_free_old_entry(sb, sih,
+							start_old_entry,
+							start_old_pgoff,
+							num_free, false,
+							entry->epoch_id);
+				nova_invalidate_write_entry(sb,
+						start_old_entry, 1, 0);
+
+				start_old_entry = old_entry;
+				start_old_pgoff = curr_pgoff;
+				num_free = 1;
+			} else {
+				num_free++;
+			}
+
+			radix_tree_replace_slot(&sih->tree, pentry, entry);
+		} else {
+			ret = radix_tree_insert(&sih->tree, curr_pgoff, entry);
+			if (ret) {
+				nova_dbg("%s: ERROR %d\n", __func__, ret);
+				goto out;
+			}
+		}
+	}
+
+	if (start_old_entry && free)
+		nova_free_old_entry(sb, sih, start_old_entry,
+					start_old_pgoff, num_free, false,
+					entry->epoch_id);
+
+	nova_invalidate_write_entry(sb, start_old_entry, 1, 0);
+
+out:
+	NOVA_END_TIMING(assign_t, assign_time);
+
+	return ret;
+}
+
 int nova_inplace_update_write_entry(struct super_block *sb,
 	struct inode *inode, struct nova_file_write_entry *entry,
 	struct nova_log_entry_info *entry_info)
diff --git a/fs/nova/log.h b/fs/nova/log.h
index 2548083..f5149f7 100644
--- a/fs/nova/log.h
+++ b/fs/nova/log.h
@@ -398,4 +398,9 @@ int nova_free_contiguous_log_blocks(struct super_block *sb,
 int nova_free_inode_log(struct super_block *sb, struct nova_inode *pi,
 	struct nova_inode_info_header *sih);
 
+void nova_print_nova_log(struct super_block *sb,
+	struct nova_inode_info_header *sih);
+void nova_print_nova_log_pages(struct super_block *sb,
+	struct nova_inode_info_header *sih);
+
 #endif
diff --git a/fs/nova/nova.h b/fs/nova/nova.h
index 6cf3c33..8f085cf 100644
--- a/fs/nova/nova.h
+++ b/fs/nova/nova.h
@@ -342,6 +342,70 @@ static inline int old_entry_freeable(struct super_block *sb, u64 epoch_id)
 
 #include "balloc.h"
 
+static inline struct nova_file_write_entry *
+nova_get_write_entry(struct super_block *sb,
+	struct nova_inode_info_header *sih, unsigned long blocknr)
+{
+	struct nova_file_write_entry *entry;
+
+	entry = radix_tree_lookup(&sih->tree, blocknr);
+
+	return entry;
+}
+
+
+/*
+ * Find data at a file offset (pgoff) in the data pointed to by a write log
+ * entry.
+ */
+static inline unsigned long get_nvmm(struct super_block *sb,
+	struct nova_inode_info_header *sih,
+	struct nova_file_write_entry *entry, unsigned long pgoff)
+{
+	/* entry is already verified before this call and resides in dram
+	 * or we can do memcpy_mcsafe here but have to avoid double copy and
+	 * verification of the entry.
+	 */
+	if (entry->pgoff > pgoff || (unsigned long) entry->pgoff +
+			(unsigned long) entry->num_pages <= pgoff) {
+		struct nova_sb_info *sbi = NOVA_SB(sb);
+		u64 curr;
+
+		curr = nova_get_addr_off(sbi, entry);
+		nova_dbg("Entry ERROR: inode %lu, curr 0x%llx, pgoff %lu, entry pgoff %llu, num %u\n",
+			sih->ino,
+			curr, pgoff, entry->pgoff, entry->num_pages);
+		nova_print_nova_log_pages(sb, sih);
+		nova_print_nova_log(sb, sih);
+		NOVA_ASSERT(0);
+	}
+
+	return (unsigned long) (entry->block >> PAGE_SHIFT) + pgoff
+		- entry->pgoff;
+}
+
+static inline u64 nova_find_nvmm_block(struct super_block *sb,
+	struct nova_inode_info_header *sih, struct nova_file_write_entry *entry,
+	unsigned long blocknr)
+{
+	unsigned long nvmm;
+	struct nova_file_write_entry *entryc, entry_copy;
+
+	if (!entry) {
+		entry = nova_get_write_entry(sb, sih, blocknr);
+		if (!entry)
+			return 0;
+	}
+
+	entryc = &entry_copy;
+	if (memcpy_mcsafe(entryc, entry,
+			sizeof(struct nova_file_write_entry)) < 0)
+		return 0;
+
+	nvmm = get_nvmm(sb, sih, entryc, blocknr);
+	return nvmm << PAGE_SHIFT;
+}
+
 static inline unsigned long
 nova_get_numblocks(unsigned short btype)
 {
-- 
2.7.4

  parent reply index

Thread overview: 119+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-03-10 18:17 [RFC v2 00/83] NOVA: a new file system for persistent memory Andiry Xu
2018-03-10 18:17 ` [RFC v2 01/83] Introduction and documentation of NOVA filesystem Andiry Xu
2018-03-19 20:43   ` Randy Dunlap
2018-03-19 23:00     ` Andiry Xu
2018-04-22  8:05   ` Pavel Machek
2018-03-10 18:17 ` [RFC v2 02/83] Add nova_def.h Andiry Xu
2018-03-10 18:17 ` [RFC v2 03/83] Add super.h Andiry Xu
2018-03-15  4:54   ` Darrick J. Wong
2018-03-15  6:11     ` Andiry Xu
2018-03-15  9:05       ` Arnd Bergmann
2018-03-15 17:51         ` Andiry Xu
2018-03-15 20:04           ` Andreas Dilger
2018-03-15 20:38           ` Arnd Bergmann
2018-03-16  2:59             ` Theodore Y. Ts'o
2018-03-16  6:17               ` Andiry Xu
2018-03-16  6:30                 ` Darrick J. Wong
2018-03-16  9:19               ` Arnd Bergmann
2018-03-10 18:17 ` [RFC v2 04/83] NOVA inode definition Andiry Xu
2018-03-15  5:06   ` Darrick J. Wong
2018-03-15  6:16     ` Andiry Xu
2018-03-10 18:17 ` [RFC v2 05/83] Add NOVA filesystem definitions and useful helper routines Andiry Xu
2018-03-11 12:00   ` Nikolay Borisov
2018-03-11 19:22     ` Eric Biggers
2018-03-11 21:45       ` Andiry Xu
2018-03-19 19:39       ` Andiry Xu
2018-03-19 20:30         ` Eric Biggers
2018-03-19 21:59           ` Andiry Xu
2018-03-10 18:17 ` [RFC v2 06/83] Add inode get/read methods Andiry Xu
2018-04-23  6:12   ` Darrick J. Wong
2018-04-23 15:55     ` Andiry Xu
2018-03-10 18:17 ` [RFC v2 07/83] Initialize inode_info and rebuild inode information in nova_iget() Andiry Xu
2018-03-10 18:17 ` [RFC v2 08/83] NOVA superblock operations Andiry Xu
2018-03-10 18:17 ` [RFC v2 09/83] Add Kconfig and Makefile Andiry Xu
2018-03-11 12:15   ` Nikolay Borisov
2018-03-11 21:32     ` Andiry Xu
2018-03-10 18:17 ` [RFC v2 10/83] Add superblock integrity check Andiry Xu
2018-03-10 18:17 ` [RFC v2 11/83] Add timing and I/O statistics for performance analysis and profiling Andiry Xu
2018-03-10 18:17 ` [RFC v2 12/83] Add timing for mount and init Andiry Xu
2018-03-10 18:17 ` [RFC v2 13/83] Add remount_fs and show_options methods Andiry Xu
2018-03-10 18:17 ` [RFC v2 14/83] Add range node kmem cache Andiry Xu
2018-03-11 11:55   ` Nikolay Borisov
2018-03-11 21:31     ` Andiry Xu
2018-03-10 18:17 ` [RFC v2 15/83] Add free list data structure Andiry Xu
2018-03-10 18:17 ` [RFC v2 16/83] Initialize block map and free lists in nova_init() Andiry Xu
2018-03-11 12:12   ` Nikolay Borisov
2018-03-11 21:30     ` Andiry Xu
2018-03-10 18:17 ` [RFC v2 17/83] Add statfs support Andiry Xu
2018-03-10 18:17 ` [RFC v2 18/83] Add freelist statistics printing Andiry Xu
2018-03-10 18:18 ` [RFC v2 19/83] Add pmem block free routines Andiry Xu
2018-03-10 18:18 ` [RFC v2 20/83] Pmem block allocation routines Andiry Xu
2018-03-10 18:18 ` [RFC v2 21/83] Add log structure Andiry Xu
2018-03-10 18:18 ` [RFC v2 22/83] Inode log pages allocation and reclaimation Andiry Xu
2018-03-10 18:18 ` [RFC v2 23/83] Save allocator to pmem in put_super Andiry Xu
2018-03-10 18:18 ` [RFC v2 24/83] Initialize and allocate inode table Andiry Xu
2018-03-10 18:18 ` [RFC v2 25/83] Support get normal inode address and inode table extentsion Andiry Xu
2018-03-10 18:18 ` [RFC v2 26/83] Add inode_map to track inuse inodes Andiry Xu
2018-03-10 18:18 ` [RFC v2 27/83] Save the inode inuse list to pmem upon umount Andiry Xu
2018-03-10 18:18 ` [RFC v2 28/83] Add NOVA address space operations Andiry Xu
2018-03-10 18:18 ` [RFC v2 29/83] Add write_inode and dirty_inode routines Andiry Xu
2018-03-10 18:18 ` [RFC v2 30/83] New NOVA inode allocation Andiry Xu
2018-03-10 18:18 ` [RFC v2 31/83] Add new vfs " Andiry Xu
2018-03-10 18:18 ` [RFC v2 32/83] Add log entry definitions Andiry Xu
2018-03-10 18:18 ` [RFC v2 33/83] Inode log and entry printing for debug purpose Andiry Xu
2018-03-10 18:18 ` [RFC v2 34/83] Journal: NOVA light weight journal definitions Andiry Xu
2018-03-10 18:18 ` [RFC v2 35/83] Journal: Lite journal helper routines Andiry Xu
2018-03-10 18:18 ` [RFC v2 36/83] Journal: Lite journal recovery Andiry Xu
2018-03-10 18:18 ` [RFC v2 37/83] Journal: Lite journal create and commit Andiry Xu
2018-03-10 18:18 ` [RFC v2 38/83] Journal: NOVA lite journal initialization Andiry Xu
2018-03-10 18:18 ` [RFC v2 39/83] Log operation: dentry append Andiry Xu
2018-03-10 18:18 ` [RFC v2 40/83] Log operation: file write entry append Andiry Xu
2018-03-10 18:18 ` [RFC v2 41/83] Log operation: setattr " Andiry Xu
2018-03-10 18:18 ` [RFC v2 42/83] Log operation: link change append Andiry Xu
2018-03-10 18:18 ` [RFC v2 43/83] Log operation: in-place update log entry Andiry Xu
2018-03-10 18:18 ` [RFC v2 44/83] Log operation: invalidate log entries Andiry Xu
2018-03-10 18:18 ` Andiry Xu [this message]
2018-03-10 18:18 ` [RFC v2 46/83] Dir: Add Directory radix tree insert/remove methods Andiry Xu
2018-03-10 18:18 ` [RFC v2 47/83] Dir: Add initial dentries when initializing a directory inode log Andiry Xu
2018-03-10 18:18 ` [RFC v2 48/83] Dir: Readdir operation Andiry Xu
2018-03-10 18:18 ` [RFC v2 49/83] Dir: Append create/remove dentry Andiry Xu
2018-03-10 18:18 ` [RFC v2 50/83] Inode: Add nova_evict_inode Andiry Xu
2018-03-10 18:18 ` [RFC v2 51/83] Rebuild: directory inode Andiry Xu
2018-03-10 18:18 ` [RFC v2 52/83] Rebuild: file inode Andiry Xu
2018-03-10 18:18 ` [RFC v2 53/83] Namei: lookup Andiry Xu
2018-03-10 18:18 ` [RFC v2 54/83] Namei: create and mknod Andiry Xu
2018-03-10 18:18 ` [RFC v2 55/83] Namei: mkdir Andiry Xu
2018-03-10 18:18 ` [RFC v2 56/83] Namei: link and unlink Andiry Xu
2018-03-10 18:18 ` [RFC v2 57/83] Namei: rmdir Andiry Xu
2018-03-10 18:18 ` [RFC v2 58/83] Namei: rename Andiry Xu
2018-03-10 18:18 ` [RFC v2 59/83] Namei: setattr Andiry Xu
2018-03-10 18:18 ` [RFC v2 60/83] Add special inode operations Andiry Xu
2018-03-10 18:18 ` [RFC v2 61/83] Super: Add nova_export_ops Andiry Xu
2018-03-10 18:18 ` [RFC v2 62/83] File: getattr and file inode operations Andiry Xu
2018-03-10 18:18 ` [RFC v2 63/83] File operation: llseek Andiry Xu
2018-03-10 18:18 ` [RFC v2 64/83] File operation: open, fsync, flush Andiry Xu
2018-03-10 18:18 ` [RFC v2 65/83] File operation: read Andiry Xu
2018-03-10 18:18 ` [RFC v2 66/83] Super: Add file write item cache Andiry Xu
2018-03-10 18:18 ` [RFC v2 67/83] Dax: commit list of file write items to log Andiry Xu
2018-03-10 18:18 ` [RFC v2 68/83] File operation: copy-on-write write Andiry Xu
2018-03-10 18:18 ` [RFC v2 69/83] Super: Add module param inplace_data_updates Andiry Xu
2018-03-10 18:18 ` [RFC v2 70/83] File operation: Inplace write Andiry Xu
2018-03-10 18:18 ` [RFC v2 71/83] Symlink support Andiry Xu
2018-03-10 18:18 ` [RFC v2 72/83] File operation: fallocate Andiry Xu
2018-03-10 18:18 ` [RFC v2 73/83] Dax: Add iomap operations Andiry Xu
2018-03-10 18:18 ` [RFC v2 74/83] File operation: Mmap Andiry Xu
2018-03-10 18:18 ` [RFC v2 75/83] File operation: read/write iter Andiry Xu
2018-03-10 18:18 ` [RFC v2 76/83] Ioctl support Andiry Xu
2018-03-10 18:18 ` [RFC v2 77/83] GC: Fast garbage collection Andiry Xu
2018-03-10 18:18 ` [RFC v2 78/83] GC: Thorough " Andiry Xu
2018-03-10 18:19 ` [RFC v2 79/83] Normal recovery Andiry Xu
2018-03-10 18:19 ` [RFC v2 80/83] Failure recovery: bitmap operations Andiry Xu
2018-03-10 18:19 ` [RFC v2 81/83] Failure recovery: Inode pages recovery routines Andiry Xu
2018-03-10 18:19 ` [RFC v2 82/83] Failure recovery: Per-CPU recovery Andiry Xu
2018-03-10 18:19 ` [RFC v2 83/83] Sysfs support Andiry Xu
2018-03-15  0:33   ` Randy Dunlap
2018-03-15  6:07     ` Andiry Xu
2018-03-22 15:00   ` David Sterba
2018-03-23  0:31     ` Andiry Xu
2018-03-11  2:14 ` [RFC v2 00/83] NOVA: a new file system for persistent memory Theodore Y. Ts'o
2018-03-11  4:58   ` Andiry Xu

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=1520705944-6723-46-git-send-email-jix024@eng.ucsd.edu \
    --to=jix024@eng.ucsd.edu \
    --cc=andiry.xu@gmail.com \
    --cc=andy.rudoff@intel.com \
    --cc=coughlan@redhat.com \
    --cc=dan.j.williams@intel.com \
    --cc=david@fromorbit.com \
    --cc=jack@suse.com \
    --cc=jix024@cs.ucsd.edu \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-nvdimm@lists.01.org \
    --cc=miklos@szeredi.hu \
    --cc=swanson@cs.ucsd.edu \
    --cc=swhiteho@redhat.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

Linux-Fsdevel Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-fsdevel/0 linux-fsdevel/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-fsdevel linux-fsdevel/ https://lore.kernel.org/linux-fsdevel \
		linux-fsdevel@vger.kernel.org
	public-inbox-index linux-fsdevel

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-fsdevel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git