Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752496Ab1C1Kep (ORCPT ); Mon, 28 Mar 2011 06:34:45 -0400 Received: from mailout3.samsung.com ([203.254.224.33]:26011 "EHLO mailout3.samsung.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752061Ab1C1Keo (ORCPT ); Mon, 28 Mar 2011 06:34:44 -0400 Date: Mon, 28 Mar 2011 19:34:31 +0900 From: Kyungmin Park Subject: [PATCH v6] fat: Batched discard support for fat To: OGAWA Hirofumi , linux-kernel@vger.kernel.org Cc: linux-fsdevel@vger.kernel.org, Lukas Czerner Message-id: <20110328103431.GA22323@july> MIME-version: 1.0 Content-type: text/plain; charset=us-ascii Content-transfer-encoding: 7BIT Content-disposition: inline User-Agent: Mutt/1.5.17 (2007-11-01) X-OriginalArrivalTime: 28 Mar 2011 10:34:40.0784 (UTC) FILETIME=[BEA5C100:01CBED33] Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 6577 Lines: 250 From: Kyungmin Park FAT supports batched discard as ext4. Cited from Lukas words. "The current solution is not ideal because of its bad performance impact. So basic idea to improve things is to avoid discarding every time some blocks are freed. and instead batching is together into bigger trims, which tends to be more effective." You can find an information in detail at following URLs. http://lwn.net/Articles/397538/ http://lwn.net/Articles/383933/ Clearify the meaning of "len" (Cited form Lukas mail) Let the "O" be free (bytes, blocks, whatever), and "=" be used. Now, we have a filesystem like this. OOOO==O===OO===OOOOO==O===O===OOOOOOO=== ^ ^ 0 40 This is how it supposed to wotk if you have called FITIRM with parameters: start = 0 minlen = 2 len = 20 So you will go through (blocks, bytes...) 0 -> 20 OOOO==O===OO===OOOOO==O===O===OOOOOOO=== ^ ^ 0 20 So, you will call discard on extents: 0-3 You'll skip 6 because is smaller than minlen 10-11 15-19 instead of 0-3 10-11 15-19 30-36 Signed-off-by: Kyungmin Park --- Changelog v6: Check the user input tightly Fix cyclic trim routine from OGAWA Changelog v5: Exit when start cluster is grater than max cluster Changelog v4: Simplify the exit condition Changelog v3: Adjust the minlen from queue discard_granularity Use the corrent len usage Changelog v2: Use the given start and len as Lukas comments Check the queue supports discard feature --- diff --git a/fs/fat/fat.h b/fs/fat/fat.h index f504089..08b53e1 100644 --- a/fs/fat/fat.h +++ b/fs/fat/fat.h @@ -299,6 +299,7 @@ extern int fat_alloc_clusters(struct inode *inode, int *cluster, int nr_cluster); extern int fat_free_clusters(struct inode *inode, int cluster); extern int fat_count_free_clusters(struct super_block *sb); +extern int fat_trim_fs(struct super_block *sb, struct fstrim_range *range); /* fat/file.c */ extern long fat_generic_ioctl(struct file *filp, unsigned int cmd, diff --git a/fs/fat/fatent.c b/fs/fat/fatent.c index b47d2c9..81efef2 100644 --- a/fs/fat/fatent.c +++ b/fs/fat/fatent.c @@ -1,6 +1,8 @@ /* * Copyright (C) 2004, OGAWA Hirofumi * Released under GPL v2. + * + * Batched discard support by Kyungmin Park */ #include @@ -541,6 +543,16 @@ out: return err; } +static int fat_issue_discard(struct super_block *sb, int cluster, int nr_clus) +{ + struct msdos_sb_info *sbi = MSDOS_SB(sb); + sector_t block, nr_blocks; + + block = fat_clus_to_blknr(sbi, cluster); + nr_blocks = nr_clus * sbi->sec_per_clus; + return sb_issue_discard(sb, block, nr_blocks, GFP_NOFS, 0); +} + int fat_free_clusters(struct inode *inode, int cluster) { struct super_block *sb = inode->i_sb; @@ -575,11 +587,7 @@ int fat_free_clusters(struct inode *inode, int cluster) if (cluster != fatent.entry + 1) { int nr_clus = fatent.entry - first_cl + 1; - sb_issue_discard(sb, - fat_clus_to_blknr(sbi, first_cl), - nr_clus * sbi->sec_per_clus, - GFP_NOFS, 0); - + fat_issue_discard(sb, first_cl, nr_clus); first_cl = cluster; } } @@ -683,3 +691,80 @@ out: unlock_fat(sbi); return err; } + +int fat_trim_fs(struct super_block *sb, struct fstrim_range *range) +{ + struct msdos_sb_info *sbi = MSDOS_SB(sb); + struct fatent_operations *ops = sbi->fatent_ops; + struct fat_entry fatent; + unsigned long reada_blocks, reada_mask, cur_block; + int err, free, count, entry; + int start, len, minlen, trimmed; + + start = range->start >> sb->s_blocksize_bits; + len = range->len >> sb->s_blocksize_bits; + len = round_down(start + len, sbi->sec_per_clus); + start = round_up(start, sbi->sec_per_clus); + minlen = range->minlen >> sb->s_blocksize_bits; + minlen = round_up(minlen, sbi->sec_per_clus); + trimmed = 0; + count = 0; + err = -EINVAL; + + if (start >= sbi->max_cluster) + goto out; + + len = (len > sbi->max_cluster) ? sbi->max_cluster : len; + + lock_fat(sbi); + + reada_blocks = FAT_READA_SIZE >> sb->s_blocksize_bits; + reada_mask = reada_blocks - 1; + cur_block = 0; + entry = 0; + free = 0; + fatent_init(&fatent); + + if (start < FAT_START_ENT) + start = FAT_START_ENT; + + fatent_set_entry(&fatent, start); + + for (count = start; count <= len; count++) { + /* readahead of fat blocks */ + if ((cur_block & reada_mask) == 0) { + unsigned long rest = sbi->fat_length - cur_block; + fat_ent_reada(sb, &fatent, min(reada_blocks, rest)); + } + cur_block++; + + err = fat_ent_read_block(sb, &fatent); + if (err) + goto out; + + do { + if (ops->ent_get(&fatent) == FAT_ENT_FREE) { + free++; + if (!entry) + entry = fatent.entry; + } else if (entry) { + if (free >= minlen) { + fat_issue_discard(sb, entry, free); + trimmed += free; + } + free = 0; + entry = 0; + } + } while (fat_ent_next(sbi, &fatent)); + } + + if (free >= minlen) { + fat_issue_discard(sb, entry, free); + trimmed += free; + } + range->len = (u64)(trimmed * sbi->sec_per_clus) << sb->s_blocksize_bits; + fatent_brelse(&fatent); +out: + unlock_fat(sbi); + return err; +} diff --git a/fs/fat/file.c b/fs/fat/file.c index 7257752..8d7901f 100644 --- a/fs/fat/file.c +++ b/fs/fat/file.c @@ -125,6 +125,36 @@ long fat_generic_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) return fat_ioctl_get_attributes(inode, user_attr); case FAT_IOCTL_SET_ATTRIBUTES: return fat_ioctl_set_attributes(filp, user_attr); + case FITRIM: + { + struct super_block *sb = inode->i_sb; + struct request_queue *q = bdev_get_queue(sb->s_bdev); + struct fstrim_range range; + int ret = 0; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (!blk_queue_discard(q)) + return -EOPNOTSUPP; + + if (copy_from_user(&range, (struct fstrim_range __user *)arg, + sizeof(range))) + return -EFAULT; + + range.minlen = max_t(unsigned int, range.minlen, + q->limits.discard_granularity); + ret = fat_trim_fs(sb, &range); + if (ret < 0) + return ret; + + if (copy_to_user((struct fstrim_range __user *)arg, &range, + sizeof(range))) + return -EFAULT; + + return 0; + } + default: return -ENOTTY; /* Inappropriate ioctl for device */ } -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/