From 2c124ddd98a9f465bba11e4ebe9b0b8d68126f48 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Sat, 16 Mar 2019 09:13:06 +0900 Subject: [PATCH 01/40] f2fs: Fix use of number of devices For a single device mount using a zoned block device, the zone information for the device is stored in the sbi->devs single entry array and sbi->s_ndevs is set to 1. This differs from a single device mount using a regular block device which does not allocate sbi->devs and sets sbi->s_ndevs to 0. However, sbi->s_devs == 0 condition is used throughout the code to differentiate a single device mount from a multi-device mount where sbi->s_ndevs is always larger than 1. This results in problems with single zoned block device volumes as these are treated as multi-device mounts but do not have the start_blk and end_blk information set. One of the problem observed is skipping of zone discard issuing resulting in write commands being issued to full zones or unaligned to a zone write pointer. Fix this problem by simply treating the cases sbi->s_ndevs == 0 (single regular block device mount) and sbi->s_ndevs == 1 (single zoned block device mount) in the same manner. This is done by introducing the helper function f2fs_is_multi_device() and using this helper in place of direct tests of sbi->s_ndevs value, improving code readability. Fixes: 7bb3a371d199 ("f2fs: Fix zoned block device support") Cc: Signed-off-by: Damien Le Moal Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/data.c | 17 +++++++++++------ fs/f2fs/f2fs.h | 13 ++++++++++++- fs/f2fs/file.c | 2 +- fs/f2fs/gc.c | 2 +- fs/f2fs/segment.c | 13 +++++++------ 5 files changed, 32 insertions(+), 15 deletions(-) diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 62c1be90d952..77608072fbd9 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -216,12 +216,14 @@ struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi, struct block_device *bdev = sbi->sb->s_bdev; int i; - for (i = 0; i < sbi->s_ndevs; i++) { - if (FDEV(i).start_blk <= blk_addr && - FDEV(i).end_blk >= blk_addr) { - blk_addr -= FDEV(i).start_blk; - bdev = FDEV(i).bdev; - break; + if (f2fs_is_multi_device(sbi)) { + for (i = 0; i < sbi->s_ndevs; i++) { + if (FDEV(i).start_blk <= blk_addr && + FDEV(i).end_blk >= blk_addr) { + blk_addr -= FDEV(i).start_blk; + bdev = FDEV(i).bdev; + break; + } } } if (bio) { @@ -235,6 +237,9 @@ int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr) { int i; + if (!f2fs_is_multi_device(sbi)) + return 0; + for (i = 0; i < sbi->s_ndevs; i++) if (FDEV(i).start_blk <= blkaddr && FDEV(i).end_blk >= blkaddr) return i; diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 6204b15e1521..24c8b7da98bc 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -1432,6 +1432,17 @@ static inline bool time_to_inject(struct f2fs_sb_info *sbi, int type) } #endif +/* + * Test if the mounted volume is a multi-device volume. + * - For a single regular disk volume, sbi->s_ndevs is 0. + * - For a single zoned disk volume, sbi->s_ndevs is 1. + * - For a multi-device volume, sbi->s_ndevs is always 2 or more. + */ +static inline bool f2fs_is_multi_device(struct f2fs_sb_info *sbi) +{ + return sbi->s_ndevs > 1; +} + /* For write statistics. Suppose sector size is 512 bytes, * and the return value is in kbytes. s is of struct f2fs_sb_info. */ @@ -3704,7 +3715,7 @@ static inline bool f2fs_force_buffered_io(struct inode *inode, if (f2fs_post_read_required(inode)) return true; - if (sbi->s_ndevs) + if (f2fs_is_multi_device(sbi)) return true; /* * for blkzoned device, fallback direct IO to buffered IO, so diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 637a9dfbd578..585ea4c120c5 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -2573,7 +2573,7 @@ static int f2fs_ioc_flush_device(struct file *filp, unsigned long arg) sizeof(range))) return -EFAULT; - if (sbi->s_ndevs <= 1 || sbi->s_ndevs - 1 <= range.dev_num || + if (!f2fs_is_multi_device(sbi) || sbi->s_ndevs - 1 <= range.dev_num || __is_large_section(sbi)) { f2fs_msg(sbi->sb, KERN_WARNING, "Can't flush %u in %d for segs_per_sec %u != 1\n", diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 3624d1336bd1..e4913bdbb0e6 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -1346,7 +1346,7 @@ void f2fs_build_gc_manager(struct f2fs_sb_info *sbi) sbi->gc_pin_file_threshold = DEF_GC_FAILED_PINNED_FILES; /* give warm/cold data area from slower device */ - if (sbi->s_ndevs && !__is_large_section(sbi)) + if (f2fs_is_multi_device(sbi) && !__is_large_section(sbi)) SIT_I(sbi)->last_victim[ALLOC_NEXT] = GET_SEGNO(sbi, FDEV(0).end_blk) + 1; } diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index cbfa80812a66..8a3d7f5ac304 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -580,7 +580,7 @@ static int submit_flush_wait(struct f2fs_sb_info *sbi, nid_t ino) int ret = 0; int i; - if (!sbi->s_ndevs) + if (!f2fs_is_multi_device(sbi)) return __submit_flush_wait(sbi, sbi->sb->s_bdev); for (i = 0; i < sbi->s_ndevs; i++) { @@ -648,7 +648,8 @@ int f2fs_issue_flush(struct f2fs_sb_info *sbi, nid_t ino) return ret; } - if (atomic_inc_return(&fcc->queued_flush) == 1 || sbi->s_ndevs > 1) { + if (atomic_inc_return(&fcc->queued_flush) == 1 || + f2fs_is_multi_device(sbi)) { ret = submit_flush_wait(sbi, ino); atomic_dec(&fcc->queued_flush); @@ -754,7 +755,7 @@ int f2fs_flush_device_cache(struct f2fs_sb_info *sbi) { int ret = 0, i; - if (!sbi->s_ndevs) + if (!f2fs_is_multi_device(sbi)) return 0; for (i = 1; i < sbi->s_ndevs; i++) { @@ -1445,7 +1446,7 @@ static int __queue_discard_cmd(struct f2fs_sb_info *sbi, trace_f2fs_queue_discard(bdev, blkstart, blklen); - if (sbi->s_ndevs) { + if (f2fs_is_multi_device(sbi)) { int devi = f2fs_target_device_index(sbi, blkstart); blkstart -= FDEV(devi).start_blk; @@ -1808,7 +1809,7 @@ static int __f2fs_issue_discard_zone(struct f2fs_sb_info *sbi, block_t lblkstart = blkstart; int devi = 0; - if (sbi->s_ndevs) { + if (f2fs_is_multi_device(sbi)) { devi = f2fs_target_device_index(sbi, blkstart); blkstart -= FDEV(devi).start_blk; } @@ -3166,7 +3167,7 @@ static void update_device_state(struct f2fs_io_info *fio) struct f2fs_sb_info *sbi = fio->sbi; unsigned int devidx; - if (!sbi->s_ndevs) + if (!f2fs_is_multi_device(sbi)) return; devidx = f2fs_target_device_index(sbi, fio->new_blkaddr); From c4c54093c71df99df764e2854f01ac8dbe522dc7 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Sat, 16 Mar 2019 09:13:07 +0900 Subject: [PATCH 02/40] f2fs: Reduce zoned block device memory usage For zoned block devices, an array of zone types for each device is allocated and initialized in order to determine if a section is stored on a sequential zone (zone reset needed) or a conventional zone (no zone reset needed and regular discard applies). Considering this usage, the zone types stored in memory can be replaced with a bitmap to indicate an equivalent information, that is, if a zone is sequential or not. This reduces the memory usage for each zoned device by roughly 8: on a 14TB disk with zones of 256 MB, the zone type array consumes 13x4KB pages while the bitmap uses only 2x4KB pages. This patch changes the f2fs_dev_info structure blkz_type field to the bitmap blkz_seq. Access to this bitmap is done using the helper function f2fs_blkz_is_seq(), which is a rewrite of the function get_blkz_type(). Signed-off-by: Damien Le Moal Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/f2fs.h | 14 +++++--------- fs/f2fs/segment.c | 36 ++++++++++++++++-------------------- fs/f2fs/super.c | 13 ++++++++----- 3 files changed, 29 insertions(+), 34 deletions(-) diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 24c8b7da98bc..3ea8caae0e95 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -1134,8 +1134,8 @@ struct f2fs_dev_info { block_t start_blk; block_t end_blk; #ifdef CONFIG_BLK_DEV_ZONED - unsigned int nr_blkz; /* Total number of zones */ - u8 *blkz_type; /* Array of zones type */ + unsigned int nr_blkz; /* Total number of zones */ + unsigned long *blkz_seq; /* Bitmap indicating sequential zones */ #endif }; @@ -3631,16 +3631,12 @@ F2FS_FEATURE_FUNCS(lost_found, LOST_FOUND); F2FS_FEATURE_FUNCS(sb_chksum, SB_CHKSUM); #ifdef CONFIG_BLK_DEV_ZONED -static inline int get_blkz_type(struct f2fs_sb_info *sbi, - struct block_device *bdev, block_t blkaddr) +static inline bool f2fs_blkz_is_seq(struct f2fs_sb_info *sbi, int devi, + block_t blkaddr) { unsigned int zno = blkaddr >> sbi->log_blocks_per_blkz; - int i; - for (i = 0; i < sbi->s_ndevs; i++) - if (FDEV(i).bdev == bdev) - return FDEV(i).blkz_type[zno]; - return -EINVAL; + return test_bit(zno, FDEV(devi).blkz_seq); } #endif diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 8a3d7f5ac304..e3bdfaf3c5f4 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -1811,40 +1811,36 @@ static int __f2fs_issue_discard_zone(struct f2fs_sb_info *sbi, if (f2fs_is_multi_device(sbi)) { devi = f2fs_target_device_index(sbi, blkstart); + if (blkstart < FDEV(devi).start_blk || + blkstart > FDEV(devi).end_blk) { + f2fs_msg(sbi->sb, KERN_ERR, "Invalid block %x", + blkstart); + return -EIO; + } blkstart -= FDEV(devi).start_blk; } - /* - * We need to know the type of the zone: for conventional zones, - * use regular discard if the drive supports it. For sequential - * zones, reset the zone write pointer. - */ - switch (get_blkz_type(sbi, bdev, blkstart)) { - - case BLK_ZONE_TYPE_CONVENTIONAL: - if (!blk_queue_discard(bdev_get_queue(bdev))) - return 0; - return __queue_discard_cmd(sbi, bdev, lblkstart, blklen); - case BLK_ZONE_TYPE_SEQWRITE_REQ: - case BLK_ZONE_TYPE_SEQWRITE_PREF: + /* For sequential zones, reset the zone write pointer */ + if (f2fs_blkz_is_seq(sbi, devi, blkstart)) { sector = SECTOR_FROM_BLOCK(blkstart); nr_sects = SECTOR_FROM_BLOCK(blklen); if (sector & (bdev_zone_sectors(bdev) - 1) || nr_sects != bdev_zone_sectors(bdev)) { - f2fs_msg(sbi->sb, KERN_INFO, - "(%d) %s: Unaligned discard attempted (block %x + %x)", + f2fs_msg(sbi->sb, KERN_ERR, + "(%d) %s: Unaligned zone reset attempted (block %x + %x)", devi, sbi->s_ndevs ? FDEV(devi).path: "", blkstart, blklen); return -EIO; } trace_f2fs_issue_reset_zone(bdev, blkstart); - return blkdev_reset_zones(bdev, sector, - nr_sects, GFP_NOFS); - default: - /* Unknown zone type: broken device ? */ - return -EIO; + return blkdev_reset_zones(bdev, sector, nr_sects, GFP_NOFS); } + + /* For conventional zones, use regular discard if supported */ + if (!blk_queue_discard(bdev_get_queue(bdev))) + return 0; + return __queue_discard_cmd(sbi, bdev, lblkstart, blklen); } #endif diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 5418b1d55a4f..d2d4c12ab004 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -1024,7 +1024,7 @@ static void destroy_device_list(struct f2fs_sb_info *sbi) for (i = 0; i < sbi->s_ndevs; i++) { blkdev_put(FDEV(i).bdev, FMODE_EXCL); #ifdef CONFIG_BLK_DEV_ZONED - kvfree(FDEV(i).blkz_type); + kvfree(FDEV(i).blkz_seq); #endif } kvfree(sbi->devs); @@ -2802,9 +2802,11 @@ static int init_blkz_info(struct f2fs_sb_info *sbi, int devi) if (nr_sectors & (bdev_zone_sectors(bdev) - 1)) FDEV(devi).nr_blkz++; - FDEV(devi).blkz_type = f2fs_kmalloc(sbi, FDEV(devi).nr_blkz, - GFP_KERNEL); - if (!FDEV(devi).blkz_type) + FDEV(devi).blkz_seq = f2fs_kzalloc(sbi, + BITS_TO_LONGS(FDEV(devi).nr_blkz) + * sizeof(unsigned long), + GFP_KERNEL); + if (!FDEV(devi).blkz_seq) return -ENOMEM; #define F2FS_REPORT_NR_ZONES 4096 @@ -2831,7 +2833,8 @@ static int init_blkz_info(struct f2fs_sb_info *sbi, int devi) } for (i = 0; i < nr_zones; i++) { - FDEV(devi).blkz_type[n] = zones[i].type; + if (zones[i].type != BLK_ZONE_TYPE_CONVENTIONAL) + set_bit(n, FDEV(devi).blkz_seq); sector += zones[i].len; n++; } From 6b25d4ac2e7ddb96a437fa5676ecac9bb27aadb4 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Sat, 16 Mar 2019 09:13:08 +0900 Subject: [PATCH 03/40] f2fs: improve discard handling with multi-device volumes f2fs_hw_support_discard() only tests if the super block device supports discard. However, for a multi-device volume, not all disks used may support discard. Improve the check performed to test all devices of the volume and report discard as supported if at least one device of the volume supports discard. To implement this, introduce the helper function f2fs_bdev_support_discard(), which returns true for zoned block devices (where discard is processed as a zone reset) and for regular disks supporting the discard command. f2fs_bdev_support_discard() is also used in __queue_discard_cmd() to handle discard command issuing for a particular device of the volume. That is, prevent issuing a discard command for block devices that do not support it. Signed-off-by: Damien Le Moal Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/f2fs.h | 20 +++++++++++++++++++- fs/f2fs/segment.c | 8 ++++---- 2 files changed, 23 insertions(+), 5 deletions(-) diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 3ea8caae0e95..ff891c5b38ec 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -3645,9 +3645,27 @@ static inline bool f2fs_hw_should_discard(struct f2fs_sb_info *sbi) return f2fs_sb_has_blkzoned(sbi); } +static inline bool f2fs_bdev_support_discard(struct block_device *bdev) +{ + return blk_queue_discard(bdev_get_queue(bdev)) || +#ifdef CONFIG_BLK_DEV_ZONED + bdev_is_zoned(bdev); +#else + 0; +#endif +} + static inline bool f2fs_hw_support_discard(struct f2fs_sb_info *sbi) { - return blk_queue_discard(bdev_get_queue(sbi->sb->s_bdev)); + int i; + + if (!f2fs_is_multi_device(sbi)) + return f2fs_bdev_support_discard(sbi->sb->s_bdev); + + for (i = 0; i < sbi->s_ndevs; i++) + if (f2fs_bdev_support_discard(FDEV(i).bdev)) + return true; + return false; } static inline bool f2fs_realtime_discard_enable(struct f2fs_sb_info *sbi) diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index e3bdfaf3c5f4..586eeedbbbbf 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -1444,6 +1444,9 @@ static int __queue_discard_cmd(struct f2fs_sb_info *sbi, { block_t lblkstart = blkstart; + if (!f2fs_bdev_support_discard(bdev)) + return 0; + trace_f2fs_queue_discard(bdev, blkstart, blklen); if (f2fs_is_multi_device(sbi)) { @@ -1838,8 +1841,6 @@ static int __f2fs_issue_discard_zone(struct f2fs_sb_info *sbi, } /* For conventional zones, use regular discard if supported */ - if (!blk_queue_discard(bdev_get_queue(bdev))) - return 0; return __queue_discard_cmd(sbi, bdev, lblkstart, blklen); } #endif @@ -1848,8 +1849,7 @@ static int __issue_discard_async(struct f2fs_sb_info *sbi, struct block_device *bdev, block_t blkstart, block_t blklen) { #ifdef CONFIG_BLK_DEV_ZONED - if (f2fs_sb_has_blkzoned(sbi) && - bdev_zoned_model(bdev) != BLK_ZONED_NONE) + if (f2fs_sb_has_blkzoned(sbi) && bdev_is_zoned(bdev)) return __f2fs_issue_discard_zone(sbi, bdev, blkstart, blklen); #endif return __queue_discard_cmd(sbi, bdev, blkstart, blklen); From 00e77f15eb1d8e4cae8050fec03f2150144629f9 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Tue, 2 Apr 2019 18:52:19 +0800 Subject: [PATCH 04/40] f2fs: fix potential recursive call when enabling data_flush As Hagbard Celine reported: Hi, this is a long standing bug that I've hit before on older kernels, but I was not able to get the syslog saved because of the nature of the bug. This time I had booted form a pen-drive, and was able to save the log to it's efi-partition. What i did to trigger it was to create a partition and format it f2fs, then mount it with options: "rw,relatime,lazytime,background_gc=on,disable_ext_identify,discard,heap,user_xattr,inline_xattr,acl,inline_data,inline_dentry,flush_merge,data_flush,extent_cache,mode=adaptive,active_logs=6,whint_mode=fs-based,alloc_mode=default,fsync_mode=strict". Then I unpacked a big .tar.xz to the partition (I used a gentoo-stage3-tarball as I was in process of installing Gentoo). Same options just without data_flush gives no problems. Mar 20 20:54:01 usbgentoo kernel: FAT-fs (nvme0n1p4): Volume was not properly unmounted. Some data may be corrupt. Please run fsck. Mar 20 21:05:23 usbgentoo kernel: kworker/dying (1588) used greatest stack depth: 12064 bytes left Mar 20 21:06:40 usbgentoo kernel: BUG: stack guard page was hit at 00000000a4b0733c (stack is 0000000056016422..0000000096e7463f) Mar 20 21:06:40 usbgentoo kernel: kernel stack overflow ...... Mar 20 21:06:40 usbgentoo kernel: Call Trace: Mar 20 21:06:40 usbgentoo kernel: read_node_page+0x71/0xf0 Mar 20 21:06:40 usbgentoo kernel: ? xas_load+0x8/0x50 Mar 20 21:06:40 usbgentoo kernel: __get_node_page+0x73/0x2a0 Mar 20 21:06:40 usbgentoo kernel: f2fs_get_dnode_of_data+0x34e/0x580 Mar 20 21:06:40 usbgentoo kernel: f2fs_write_inline_data+0x5e/0x2a0 Mar 20 21:06:40 usbgentoo kernel: __write_data_page+0x421/0x690 Mar 20 21:06:40 usbgentoo kernel: f2fs_write_cache_pages+0x1cf/0x460 Mar 20 21:06:40 usbgentoo kernel: f2fs_write_data_pages+0x2b3/0x2e0 Mar 20 21:06:40 usbgentoo kernel: ? f2fs_inode_chksum_verify+0x1d/0xc0 Mar 20 21:06:40 usbgentoo kernel: ? read_node_page+0x71/0xf0 Mar 20 21:06:40 usbgentoo kernel: do_writepages+0x3c/0xd0 Mar 20 21:06:40 usbgentoo kernel: __filemap_fdatawrite_range+0x7c/0xb0 Mar 20 21:06:40 usbgentoo kernel: f2fs_sync_dirty_inodes+0xf2/0x200 Mar 20 21:06:40 usbgentoo kernel: f2fs_balance_fs_bg+0x2a3/0x2c0 Mar 20 21:06:40 usbgentoo kernel: ? f2fs_inode_dirtied+0x21/0xc0 Mar 20 21:06:40 usbgentoo kernel: f2fs_balance_fs+0xd6/0x2b0 Mar 20 21:06:40 usbgentoo kernel: __write_data_page+0x4fb/0x690 ...... Mar 20 21:06:40 usbgentoo kernel: __writeback_single_inode+0x2a1/0x340 Mar 20 21:06:40 usbgentoo kernel: ? soft_cursor+0x1b4/0x220 Mar 20 21:06:40 usbgentoo kernel: writeback_sb_inodes+0x1d5/0x3e0 Mar 20 21:06:40 usbgentoo kernel: __writeback_inodes_wb+0x58/0xa0 Mar 20 21:06:40 usbgentoo kernel: wb_writeback+0x250/0x2e0 Mar 20 21:06:40 usbgentoo kernel: ? 0xffffffff8c000000 Mar 20 21:06:40 usbgentoo kernel: ? cpumask_next+0x16/0x20 Mar 20 21:06:40 usbgentoo kernel: wb_workfn+0x2f6/0x3b0 Mar 20 21:06:40 usbgentoo kernel: ? __switch_to_asm+0x40/0x70 Mar 20 21:06:40 usbgentoo kernel: process_one_work+0x1f5/0x3f0 Mar 20 21:06:40 usbgentoo kernel: worker_thread+0x28/0x3c0 Mar 20 21:06:40 usbgentoo kernel: ? rescuer_thread+0x330/0x330 Mar 20 21:06:40 usbgentoo kernel: kthread+0x10e/0x130 Mar 20 21:06:40 usbgentoo kernel: ? kthread_create_on_node+0x60/0x60 Mar 20 21:06:40 usbgentoo kernel: ret_from_fork+0x35/0x40 The root cause is that we run into an infinite recursive calling in between f2fs_balance_fs_bg and writepage() as described below: - f2fs_write_data_pages --- A - __write_data_page - f2fs_balance_fs - f2fs_balance_fs_bg --- B - f2fs_sync_dirty_inodes - filemap_fdatawrite - f2fs_write_data_pages --- A ... - f2fs_balance_fs_bg --- B ... In order to fix this issue, let's detect such condition in __write_data_page() and just skip calling f2fs_balance_fs() recursively. Reported-by: Hagbard Celine Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/checkpoint.c | 6 ++---- fs/f2fs/data.c | 3 ++- 2 files changed, 4 insertions(+), 5 deletions(-) diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index 06554ea87b0a..2e666641e651 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -1010,13 +1010,11 @@ retry: if (inode) { unsigned long cur_ino = inode->i_ino; - if (is_dir) - F2FS_I(inode)->cp_task = current; + F2FS_I(inode)->cp_task = current; filemap_fdatawrite(inode->i_mapping); - if (is_dir) - F2FS_I(inode)->cp_task = NULL; + F2FS_I(inode)->cp_task = NULL; iput(inode); /* We need to give cpu to another writers. */ diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 77608072fbd9..fac9a27a9928 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -2031,7 +2031,8 @@ out: } unlock_page(page); - if (!S_ISDIR(inode->i_mode) && !IS_NOQUOTA(inode)) + if (!S_ISDIR(inode->i_mode) && !IS_NOQUOTA(inode) && + !F2FS_I(inode)->cp_task) f2fs_balance_fs(sbi, need_balance_fs); if (unlikely(f2fs_cp_error(sbi))) { From 7e37cc9d7161bbf50ce9b2ea1199171200a3cb22 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Tue, 2 Apr 2019 18:52:20 +0800 Subject: [PATCH 05/40] f2fs: add comment for conditional compilation statement Commit af033b2aa8a8 ("f2fs: guarantee journalled quota data by checkpoint") added function is_journalled_quota() in f2fs.h, but it located outside of _LINUX_F2FS_H macro coverage, it has been fixed with commit 0af725fcb77a ("f2fs: fix wrong #endif"). But anyway, in order to avoid making same mistake latter, let's add single line comment to notice which #if the last #endif is corresponding to. Signed-off-by: Chao Yu [Jaegeuk Kim: Remove unnecessary empty EOL] Signed-off-by: Jaegeuk Kim --- fs/f2fs/f2fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index ff891c5b38ec..bff01195445c 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -3766,4 +3766,4 @@ static inline bool is_journalled_quota(struct f2fs_sb_info *sbi) return false; } -#endif +#endif /* _LINUX_F2FS_H */ From 5bed19fbbba026bf211376b1481354097c4a5e27 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Tue, 2 Apr 2019 18:52:22 +0800 Subject: [PATCH 06/40] f2fs: add tracepoint for f2fs_file_write_iter() This patch adds tracepoint for f2fs_file_write_iter(). Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/file.c | 28 +++++++++++++++++++--------- include/trace/events/f2fs.h | 31 +++++++++++++++++++++++++++++++ 2 files changed, 50 insertions(+), 9 deletions(-) diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 585ea4c120c5..89801fd2cd03 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -2811,15 +2811,21 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) struct inode *inode = file_inode(file); ssize_t ret; - if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) - return -EIO; + if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) { + ret = -EIO; + goto out; + } - if ((iocb->ki_flags & IOCB_NOWAIT) && !(iocb->ki_flags & IOCB_DIRECT)) - return -EINVAL; + if ((iocb->ki_flags & IOCB_NOWAIT) && !(iocb->ki_flags & IOCB_DIRECT)) { + ret = -EINVAL; + goto out; + } if (!inode_trylock(inode)) { - if (iocb->ki_flags & IOCB_NOWAIT) - return -EAGAIN; + if (iocb->ki_flags & IOCB_NOWAIT) { + ret = -EAGAIN; + goto out; + } inode_lock(inode); } @@ -2842,7 +2848,8 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) clear_inode_flag(inode, FI_NO_PREALLOC); inode_unlock(inode); - return -EAGAIN; + ret = -EAGAIN; + goto out; } } else { @@ -2853,7 +2860,8 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) if (err) { clear_inode_flag(inode, FI_NO_PREALLOC); inode_unlock(inode); - return err; + ret = err; + goto out; } } ret = __generic_file_write_iter(iocb, from); @@ -2867,7 +2875,9 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) f2fs_update_iostat(F2FS_I_SB(inode), APP_WRITE_IO, ret); } inode_unlock(inode); - +out: + trace_f2fs_file_write_iter(inode, iocb->ki_pos, + iov_iter_count(from), ret); if (ret > 0) { ssize_t err; diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index fe009522f4e1..87d5ce6a674c 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -525,6 +525,37 @@ TRACE_EVENT(f2fs_truncate_partial_nodes, __entry->err) ); +TRACE_EVENT(f2fs_file_write_iter, + + TP_PROTO(struct inode *inode, unsigned long offset, + unsigned long length, int ret), + + TP_ARGS(inode, offset, length, ret), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(unsigned long, offset) + __field(unsigned long, length) + __field(int, ret) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->offset = offset; + __entry->length = length; + __entry->ret = ret; + ), + + TP_printk("dev = (%d,%d), ino = %lu, " + "offset = %lu, length = %lu, written(err) = %d", + show_dev_ino(__entry), + __entry->offset, + __entry->length, + __entry->ret) +); + TRACE_EVENT(f2fs_map_blocks, TP_PROTO(struct inode *inode, struct f2fs_map_blocks *map, int ret), From 5047402dec0e624023fa579f477550739b2046bb Mon Sep 17 00:00:00 2001 From: Hariprasad Kelam Date: Sat, 6 Apr 2019 16:29:36 +0530 Subject: [PATCH 07/40] f2fs: data: fix warning Using plain integer as NULL pointer changed passing function argument "0 to NULL" to fix below sparse warning fs/f2fs/data.c:426:47: warning: Using plain integer as NULL pointer Signed-off-by: Hariprasad Kelam Reviewed-by: Chao Yu Reviewed-by: Mukesh Ojha Signed-off-by: Jaegeuk Kim --- fs/f2fs/data.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index fac9a27a9928..72f52bee9f8c 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -422,7 +422,7 @@ static void __submit_merged_write_cond(struct f2fs_sb_info *sbi, void f2fs_submit_merged_write(struct f2fs_sb_info *sbi, enum page_type type) { - __submit_merged_write_cond(sbi, NULL, 0, 0, type, true); + __submit_merged_write_cond(sbi, NULL, NULL, 0, type, true); } void f2fs_submit_merged_write_cond(struct f2fs_sb_info *sbi, From b9973998d9df3fd91f9e8cd00b50bafeaaafa9cb Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Wed, 10 Apr 2019 18:45:50 +0800 Subject: [PATCH 08/40] f2fs: fix to avoid deadloop in foreground GC As Jungyeon reported in bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=203211 - Overview When mounting the attached crafted image and making a new file, I got this error and the error messages keep repeating. The image is intentionally fuzzed from a normal f2fs image for testing and I run with option CONFIG_F2FS_CHECK_FS on. - Reproduces mkdir test mount -t f2fs tmp.img test cd test touch t - Messages [ 58.820451] F2FS-fs (sdb): Inconsistent segment (1) type [1, 0] in SSA and SIT [ 58.821485] F2FS-fs (sdb): Inconsistent segment (1) type [1, 0] in SSA and SIT [ 58.822530] F2FS-fs (sdb): Inconsistent segment (1) type [1, 0] in SSA and SIT [ 58.823571] F2FS-fs (sdb): Inconsistent segment (1) type [1, 0] in SSA and SIT [ 58.824616] F2FS-fs (sdb): Inconsistent segment (1) type [1, 0] in SSA and SIT [ 58.825640] F2FS-fs (sdb): Inconsistent segment (1) type [1, 0] in SSA and SIT [ 58.826663] F2FS-fs (sdb): Inconsistent segment (1) type [1, 0] in SSA and SIT [ 58.827698] F2FS-fs (sdb): Inconsistent segment (1) type [1, 0] in SSA and SIT [ 58.828719] F2FS-fs (sdb): Inconsistent segment (1) type [1, 0] in SSA and SIT [ 58.829759] F2FS-fs (sdb): Inconsistent segment (1) type [1, 0] in SSA and SIT [ 58.830783] F2FS-fs (sdb): Inconsistent segment (1) type [1, 0] in SSA and SIT [ 58.831828] F2FS-fs (sdb): Inconsistent segment (1) type [1, 0] in SSA and SIT [ 58.832869] F2FS-fs (sdb): Inconsistent segment (1) type [1, 0] in SSA and SIT [ 58.833888] F2FS-fs (sdb): Inconsistent segment (1) type [1, 0] in SSA and SIT [ 58.834945] F2FS-fs (sdb): Inconsistent segment (1) type [1, 0] in SSA and SIT [ 58.835996] F2FS-fs (sdb): Inconsistent segment (1) type [1, 0] in SSA and SIT [ 58.837028] F2FS-fs (sdb): Inconsistent segment (1) type [1, 0] in SSA and SIT [ 58.838051] F2FS-fs (sdb): Inconsistent segment (1) type [1, 0] in SSA and SIT [ 58.839072] F2FS-fs (sdb): Inconsistent segment (1) type [1, 0] in SSA and SIT [ 58.840100] F2FS-fs (sdb): Inconsistent segment (1) type [1, 0] in SSA and SIT [ 58.841147] F2FS-fs (sdb): Inconsistent segment (1) type [1, 0] in SSA and SIT [ 58.842186] F2FS-fs (sdb): Inconsistent segment (1) type [1, 0] in SSA and SIT [ 58.843214] F2FS-fs (sdb): Inconsistent segment (1) type [1, 0] in SSA and SIT [ 58.844267] F2FS-fs (sdb): Inconsistent segment (1) type [1, 0] in SSA and SIT [ 58.845282] F2FS-fs (sdb): Inconsistent segment (1) type [1, 0] in SSA and SIT [ 58.846305] F2FS-fs (sdb): Inconsistent segment (1) type [1, 0] in SSA and SIT [ 58.847341] F2FS-fs (sdb): Inconsistent segment (1) type [1, 0] in SSA and SIT ... (repeating) During GC, if segment type stored in SSA and SIT is inconsistent, we just skip migrating current segment directly, since we need to know the exact type to decide the migration function we use. So in foreground GC, we will easily run into a infinite loop as we may select the same victim segment which has inconsistent type due to greedy policy. In order to end up this, we choose to shutdown filesystem. For backgrond GC, we need to do that as well, so that we can avoid latter potential infinite looped foreground GC. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/gc.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index e4913bdbb0e6..62b9f39b25c5 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -1175,6 +1175,7 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi, "type [%d, %d] in SSA and SIT", segno, type, GET_SUM_TYPE((&sum->footer))); set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_stop_checkpoint(sbi, false); goto skip; } From 0d7333632d794355cd5478ab6c672c0dcadb9be7 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Wed, 10 Apr 2019 18:45:26 +0800 Subject: [PATCH 09/40] f2fs: fix error path of recovery There are some places in where we missed to unlock page or unlock page incorrectly, fix them. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/recovery.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index aa3f5633a20c..c2644c68337f 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -317,8 +317,10 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head, break; } - if (!is_recoverable_dnode(page)) + if (!is_recoverable_dnode(page)) { + f2fs_put_page(page, 1); break; + } if (!is_fsync_dnode(page)) goto next; @@ -330,8 +332,10 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head, if (!check_only && IS_INODE(page) && is_dent_dnode(page)) { err = f2fs_recover_inode_page(sbi, page); - if (err) + if (err) { + f2fs_put_page(page, 1); break; + } quota_inode = true; } @@ -347,6 +351,7 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head, err = 0; goto next; } + f2fs_put_page(page, 1); break; } } @@ -362,6 +367,7 @@ next: "%s: detect looped node chain, " "blkaddr:%u, next:%u", __func__, blkaddr, next_blkaddr_of_node(page)); + f2fs_put_page(page, 1); err = -EINVAL; break; } @@ -372,7 +378,6 @@ next: f2fs_ra_meta_pages_cond(sbi, blkaddr); } - f2fs_put_page(page, 1); return err; } @@ -658,8 +663,10 @@ static int recover_data(struct f2fs_sb_info *sbi, struct list_head *inode_list, */ if (IS_INODE(page)) { err = recover_inode(entry->inode, page); - if (err) + if (err) { + f2fs_put_page(page, 1); break; + } } if (entry->last_dentry == blkaddr) { err = recover_dentry(entry->inode, page, dir_list); From 9bc578bf83ee6fd250046d1ced1cf130f573b618 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Thu, 11 Apr 2019 11:48:09 +0800 Subject: [PATCH 10/40] f2fs: fix to retrieve inline xattr space With below mkfs and mount option, generic/339 of fstest will report that scratch image becomes corrupted. MKFS_OPTIONS -- -O extra_attr -O project_quota -O inode_checksum -O flexible_inline_xattr -O inode_crtime -f /dev/zram1 MOUNT_OPTIONS -- -o acl,user_xattr -o discard,noinline_xattr /dev/zram1 /mnt/scratch_f2fs [ASSERT] (f2fs_check_dirent_position:1315) --> Wrong position of dirent pino:1970, name: (...) level:8, dir_level:0, pgofs:951, correct range:[900, 901] In old kernel, inline data and directory always reserved 200 bytes in inode layout, even if inline_xattr is disabled, then new kernel tries to retrieve that space for non-inline xattr inode, but for inline dentry, its layout size should be fixed, so we just keep that reserved space. But the problem here is that, after inline dentry conversion, inline dentry layout no longer exists, if we still reserve inline xattr space, after dents updates, there will be a hole in inline xattr space, which can break hierarchy hash directory structure. This patch fixes this issue by retrieving inline xattr space after inline dentry conversion. Fixes: 6afc662e68b5 ("f2fs: support flexible inline xattr size") Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/inline.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c index 8d3d0022cef8..8f0ca5920e53 100644 --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -420,6 +420,14 @@ static int f2fs_move_inline_dirents(struct inode *dir, struct page *ipage, stat_dec_inline_dir(dir); clear_inode_flag(dir, FI_INLINE_DENTRY); + /* + * should retrieve reserved space which was used to keep + * inline_dentry's structure for backward compatibility. + */ + if (!f2fs_sb_has_flexible_inline_xattr(F2FS_I_SB(dir)) && + !f2fs_has_inline_xattr(dir)) + F2FS_I(dir)->i_inline_xattr_size = 0; + f2fs_i_depth_write(dir, 1); if (i_size_read(dir) < PAGE_SIZE) f2fs_i_size_write(dir, PAGE_SIZE); @@ -501,6 +509,15 @@ static int f2fs_move_rehashed_dirents(struct inode *dir, struct page *ipage, stat_dec_inline_dir(dir); clear_inode_flag(dir, FI_INLINE_DENTRY); + + /* + * should retrieve reserved space which was used to keep + * inline_dentry's structure for backward compatibility. + */ + if (!f2fs_sb_has_flexible_inline_xattr(F2FS_I_SB(dir)) && + !f2fs_has_inline_xattr(dir)) + F2FS_I(dir)->i_inline_xattr_size = 0; + kvfree(backup_dentry); return 0; recover: From b5bc76046b10165f119770e412763867bd0b7e94 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Thu, 11 Apr 2019 11:48:10 +0800 Subject: [PATCH 11/40] f2fs: fix to use inline space only if inline_xattr is enable With below mkfs and mount option: MKFS_OPTIONS -- -O extra_attr -O project_quota -O inode_checksum -O flexible_inline_xattr -O inode_crtime -f MOUNT_OPTIONS -- -o noinline_xattr We may miss xattr data with below testcase: - mkdir dir - setfattr -n "user.name" -v 0 dir - for ((i = 0; i < 190; i++)) do touch dir/$i; done - umount - mount - getfattr -n "user.name" dir user.name: No such attribute The root cause is that we persist xattr data into reserved inline xattr space, even if inline_xattr is not enable in inline directory inode, after inline dentry conversion, reserved space no longer exists, so that xattr data missed. Let's use inline xattr space only if inline_xattr flag is set on inode to fix this iusse. Fixes: 6afc662e68b5 ("f2fs: support flexible inline xattr size") Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/f2fs.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index bff01195445c..101f336cef4b 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -2636,7 +2636,9 @@ static inline void *inline_xattr_addr(struct inode *inode, struct page *page) static inline int inline_xattr_size(struct inode *inode) { - return get_inline_xattr_addrs(inode) * sizeof(__le32); + if (f2fs_has_inline_xattr(inode)) + return get_inline_xattr_addrs(inode) * sizeof(__le32); + return 0; } static inline int f2fs_has_inline_data(struct inode *inode) From 5caebe607e13714aee254895b52fde9b830b7c88 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Mon, 15 Apr 2019 15:28:30 +0800 Subject: [PATCH 12/40] f2fs: fix to avoid panic in dec_valid_block_count() As Jungyeon reported in bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=203209 - Overview When mounting the attached crafted image and running program, I got this error. Additionally, it hangs on sync after the this script. The image is intentionally fuzzed from a normal f2fs image for testing and I enabled option CONFIG_F2FS_CHECK_FS on. - Reproduces cc poc_01.c ./run.sh f2fs sync kernel BUG at fs/f2fs/f2fs.h:1788! RIP: 0010:f2fs_truncate_data_blocks_range+0x342/0x350 Call Trace: f2fs_truncate_blocks+0x36d/0x3c0 f2fs_truncate+0x88/0x110 f2fs_setattr+0x3e1/0x460 notify_change+0x2da/0x400 do_truncate+0x6d/0xb0 do_sys_ftruncate+0xf1/0x160 do_syscall_64+0x43/0xf0 entry_SYSCALL_64_after_hwframe+0x44/0xa9 The reason is dec_valid_block_count() will trigger kernel panic due to inconsistent count in between inode.i_blocks and actual block. To avoid panic, let's just print debug message and set SBI_NEED_FSCK to give a hint to fsck for latter repairing. Signed-off-by: Chao Yu [Jaegeuk Kim: fix build warning and add unlikely] Signed-off-by: Jaegeuk Kim --- fs/f2fs/f2fs.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 101f336cef4b..2516e64ca739 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -1855,6 +1855,7 @@ enospc: return -ENOSPC; } +void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...); static inline void dec_valid_block_count(struct f2fs_sb_info *sbi, struct inode *inode, block_t count) @@ -1863,13 +1864,21 @@ static inline void dec_valid_block_count(struct f2fs_sb_info *sbi, spin_lock(&sbi->stat_lock); f2fs_bug_on(sbi, sbi->total_valid_block_count < (block_t) count); - f2fs_bug_on(sbi, inode->i_blocks < sectors); sbi->total_valid_block_count -= (block_t)count; if (sbi->reserved_blocks && sbi->current_reserved_blocks < sbi->reserved_blocks) sbi->current_reserved_blocks = min(sbi->reserved_blocks, sbi->current_reserved_blocks + count); spin_unlock(&sbi->stat_lock); + if (unlikely(inode->i_blocks < sectors)) { + f2fs_msg(sbi->sb, KERN_WARNING, + "Inconsistent i_blocks, ino:%lu, iblocks:%llu, sectors:%llu", + inode->i_ino, + (unsigned long long)inode->i_blocks, + (unsigned long long)sectors); + set_sbi_flag(sbi, SBI_NEED_FSCK); + return; + } f2fs_i_blocks_write(inode, count, false, true); } @@ -2905,7 +2914,6 @@ static inline void f2fs_update_iostat(struct f2fs_sb_info *sbi, bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type); -void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...); static inline void verify_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type) { From 02fb7afdd5f038306934994bcfa2eaf4a9b7feda Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Mon, 15 Apr 2019 15:28:31 +0800 Subject: [PATCH 13/40] f2fs: fix to avoid panic in dec_valid_node_count() As Jungyeon reported in bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=203213 - Overview When mounting the attached crafted image and running program, I got this error. Additionally, it hangs on sync after running the this script. The image is intentionally fuzzed from a normal f2fs image for testing and I enabled option CONFIG_F2FS_CHECK_FS on. - Reproduces mkdir test mount -t f2fs tmp.img test cp a.out test cd test sudo ./a.out sync kernel BUG at fs/f2fs/f2fs.h:2012! RIP: 0010:truncate_node+0x2c9/0x2e0 Call Trace: f2fs_truncate_xattr_node+0xa1/0x130 f2fs_remove_inode_page+0x82/0x2d0 f2fs_evict_inode+0x2a3/0x3a0 evict+0xba/0x180 __dentry_kill+0xbe/0x160 dentry_kill+0x46/0x180 dput+0xbb/0x100 do_renameat2+0x3c9/0x550 __x64_sys_rename+0x17/0x20 do_syscall_64+0x43/0xf0 entry_SYSCALL_64_after_hwframe+0x44/0xa9 The reason is dec_valid_node_count() will trigger kernel panic due to inconsistent count in between inode.i_blocks and actual block. To avoid panic, let's just print debug message and set SBI_NEED_FSCK to give a hint to fsck for latter repairing. Signed-off-by: Chao Yu [Jaegeuk Kim: fix build warning and add unlikely] Signed-off-by: Jaegeuk Kim --- fs/f2fs/f2fs.h | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 2516e64ca739..bcc38835d7a5 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -2095,7 +2095,6 @@ static inline void dec_valid_node_count(struct f2fs_sb_info *sbi, f2fs_bug_on(sbi, !sbi->total_valid_block_count); f2fs_bug_on(sbi, !sbi->total_valid_node_count); - f2fs_bug_on(sbi, !is_inode && !inode->i_blocks); sbi->total_valid_node_count--; sbi->total_valid_block_count--; @@ -2105,10 +2104,19 @@ static inline void dec_valid_node_count(struct f2fs_sb_info *sbi, spin_unlock(&sbi->stat_lock); - if (is_inode) + if (is_inode) { dquot_free_inode(inode); - else + } else { + if (unlikely(inode->i_blocks == 0)) { + f2fs_msg(sbi->sb, KERN_WARNING, + "Inconsistent i_blocks, ino:%lu, iblocks:%llu", + inode->i_ino, + (unsigned long long)inode->i_blocks); + set_sbi_flag(sbi, SBI_NEED_FSCK); + return; + } f2fs_i_blocks_write(inode, 1, false, true); + } } static inline unsigned int valid_node_count(struct f2fs_sb_info *sbi) From 9b4fc7359ca20fa1bb8c532d88afec8ec356619c Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Mon, 15 Apr 2019 15:26:31 +0800 Subject: [PATCH 14/40] f2fs: fix wrong __is_meta_io() macro This patch changes codes as below: - don't use is_read_io() as a condition to judge the meta IO. - use .is_por to replace .is_meta to indicate IO is from recovery explicitly. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/checkpoint.c | 4 ++-- fs/f2fs/data.c | 3 ++- fs/f2fs/f2fs.h | 5 ++--- 3 files changed, 6 insertions(+), 6 deletions(-) diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index 2e666641e651..5492afd66dff 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -66,7 +66,7 @@ static struct page *__get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index, .old_blkaddr = index, .new_blkaddr = index, .encrypted_page = NULL, - .is_meta = is_meta, + .is_por = !is_meta, }; int err; @@ -190,7 +190,7 @@ int f2fs_ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, REQ_RAHEAD, .encrypted_page = NULL, .in_list = false, - .is_meta = (type != META_POR), + .is_por = (type == META_POR), }; struct blk_plug plug; diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 72f52bee9f8c..04158e0ec45c 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -450,7 +450,8 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio) fio->encrypted_page : fio->page; if (!f2fs_is_valid_blkaddr(fio->sbi, fio->new_blkaddr, - __is_meta_io(fio) ? META_GENERIC : DATA_GENERIC)) + fio->is_por ? META_POR : + (__is_meta_io(fio) ? META_GENERIC : DATA_GENERIC))) return -EFAULT; trace_f2fs_submit_page_bio(page, fio); diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index bcc38835d7a5..33da1e15c063 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -1107,7 +1107,7 @@ struct f2fs_io_info { bool submitted; /* indicate IO submission */ int need_lock; /* indicate we need to lock cp_rwsem */ bool in_list; /* indicate fio is in io_list */ - bool is_meta; /* indicate borrow meta inode mapping or not */ + bool is_por; /* indicate IO is from recovery or not */ bool retry; /* need to reallocate block address */ enum iostat_type io_type; /* io type */ struct writeback_control *io_wbc; /* writeback control */ @@ -2917,8 +2917,7 @@ static inline void f2fs_update_iostat(struct f2fs_sb_info *sbi, #define __is_large_section(sbi) ((sbi)->segs_per_sec > 1) -#define __is_meta_io(fio) (PAGE_TYPE_OF_BIO((fio)->type) == META && \ - (!is_read_io((fio)->op) || (fio)->is_meta)) +#define __is_meta_io(fio) (PAGE_TYPE_OF_BIO((fio)->type) == META) bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type); From 299dea1adf40b5916a40fe47506c59ef8a1851d1 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Mon, 15 Apr 2019 15:28:32 +0800 Subject: [PATCH 15/40] f2fs: remove new blank line of f2fs kernel message Just removing '\n' in f2fs_msg(, "\n") to avoid redundant new blank line. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/file.c | 4 ++-- fs/f2fs/super.c | 8 ++++---- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 89801fd2cd03..ed2d525c1769 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -2576,7 +2576,7 @@ static int f2fs_ioc_flush_device(struct file *filp, unsigned long arg) if (!f2fs_is_multi_device(sbi) || sbi->s_ndevs - 1 <= range.dev_num || __is_large_section(sbi)) { f2fs_msg(sbi->sb, KERN_WARNING, - "Can't flush %u in %d for segs_per_sec %u != 1\n", + "Can't flush %u in %d for segs_per_sec %u != 1", range.dev_num, sbi->s_ndevs, sbi->segs_per_sec); return -EINVAL; @@ -2638,7 +2638,7 @@ int f2fs_pin_file_control(struct inode *inode, bool inc) if (fi->i_gc_failures[GC_FAILURE_PIN] > sbi->gc_pin_file_threshold) { f2fs_msg(sbi->sb, KERN_WARNING, - "%s: Enable GC = ino %lx after %x GC trials\n", + "%s: Enable GC = ino %lx after %x GC trials", __func__, inode->i_ino, fi->i_gc_failures[GC_FAILURE_PIN]); clear_inode_flag(inode, FI_PIN_FILE); diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index d2d4c12ab004..dd5658b1750f 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -2458,7 +2458,7 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, /* Currently, support only 4KB page cache size */ if (F2FS_BLKSIZE != PAGE_SIZE) { f2fs_msg(sb, KERN_INFO, - "Invalid page_cache_size (%lu), supports only 4KB\n", + "Invalid page_cache_size (%lu), supports only 4KB", PAGE_SIZE); return 1; } @@ -2467,7 +2467,7 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, blocksize = 1 << le32_to_cpu(raw_super->log_blocksize); if (blocksize != F2FS_BLKSIZE) { f2fs_msg(sb, KERN_INFO, - "Invalid blocksize (%u), supports only 4KB\n", + "Invalid blocksize (%u), supports only 4KB", blocksize); return 1; } @@ -2475,7 +2475,7 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, /* check log blocks per segment */ if (le32_to_cpu(raw_super->log_blocks_per_seg) != 9) { f2fs_msg(sb, KERN_INFO, - "Invalid log blocks per segment (%u)\n", + "Invalid log blocks per segment (%u)", le32_to_cpu(raw_super->log_blocks_per_seg)); return 1; } @@ -3121,7 +3121,7 @@ try_onemore: #ifndef CONFIG_BLK_DEV_ZONED if (f2fs_sb_has_blkzoned(sbi)) { f2fs_msg(sb, KERN_ERR, - "Zoned block device support is not enabled\n"); + "Zoned block device support is not enabled"); err = -EOPNOTSUPP; goto free_sb_buf; } From c0bcbe425670ffc671f5f31c3092661cfda0b1bc Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Mon, 15 Apr 2019 15:28:33 +0800 Subject: [PATCH 16/40] f2fs: fix to clear dirty inode in error path of f2fs_iget() As Jungyeon reported in bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=203217 - Overview When mounting the attached crafted image and running program, I got this error. Additionally, it hangs on sync after running the program. The image is intentionally fuzzed from a normal f2fs image for testing and I enabled option CONFIG_F2FS_CHECK_FS on. - Reproduces cc poc_test_05.c mkdir test mount -t f2fs tmp.img test sudo ./a.out sync - Messages kernel BUG at fs/f2fs/inode.c:707! RIP: 0010:f2fs_evict_inode+0x33f/0x3a0 Call Trace: evict+0xba/0x180 f2fs_iget+0x598/0xdf0 f2fs_lookup+0x136/0x320 __lookup_slow+0x92/0x140 lookup_slow+0x30/0x50 walk_component+0x1c1/0x350 path_lookupat+0x62/0x200 filename_lookup+0xb3/0x1a0 do_readlinkat+0x56/0x110 __x64_sys_readlink+0x16/0x20 do_syscall_64+0x43/0xf0 entry_SYSCALL_64_after_hwframe+0x44/0xa9 During inode loading, __recover_inline_status() can recovery inode status and set inode dirty, once we failed in following process, it will fail the check in f2fs_evict_inode, result in trigger BUG_ON(). Let's clear dirty inode in error path of f2fs_iget() to avoid panic. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/inode.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index d33f860c4e63..ce5a5a579042 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -488,6 +488,7 @@ make_now: return inode; bad_inode: + f2fs_inode_synced(inode); iget_failed(inode); trace_f2fs_iget_exit(inode, ret); return ERR_PTR(ret); From 9a080abdc30b76a991339510cf17d54e2cf42601 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Mon, 15 Apr 2019 15:28:34 +0800 Subject: [PATCH 17/40] f2fs: fix to avoid panic in f2fs_remove_inode_page() As Jungyeon reported in bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=203219 - Overview When mounting the attached crafted image and running program, I got this error. Additionally, it hangs on sync after running the program. The image is intentionally fuzzed from a normal f2fs image for testing and I enabled option CONFIG_F2FS_CHECK_FS on. - Reproduces cc poc_06.c mkdir test mount -t f2fs tmp.img test cp a.out test cd test sudo ./a.out sync - Messages kernel BUG at fs/f2fs/node.c:1183! RIP: 0010:f2fs_remove_inode_page+0x294/0x2d0 Call Trace: f2fs_evict_inode+0x2a3/0x3a0 evict+0xba/0x180 __dentry_kill+0xbe/0x160 dentry_kill+0x46/0x180 dput+0xbb/0x100 do_renameat2+0x3c9/0x550 __x64_sys_rename+0x17/0x20 do_syscall_64+0x43/0xf0 entry_SYSCALL_64_after_hwframe+0x44/0xa9 The reason is f2fs_remove_inode_page() will trigger kernel panic due to inconsistent i_blocks value of inode. To avoid panic, let's just print debug message and set SBI_NEED_FSCK to give a hint to fsck for latter repairing of potential image corruption. Signed-off-by: Chao Yu [Jaegeuk Kim: fix build warning and add unlikely] Signed-off-by: Jaegeuk Kim --- fs/f2fs/node.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index f527c2b08798..45488ca85966 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -1179,8 +1179,14 @@ int f2fs_remove_inode_page(struct inode *inode) f2fs_put_dnode(&dn); return -EIO; } - f2fs_bug_on(F2FS_I_SB(inode), - inode->i_blocks != 0 && inode->i_blocks != 8); + + if (unlikely(inode->i_blocks != 0 && inode->i_blocks != 8)) { + f2fs_msg(F2FS_I_SB(inode)->sb, KERN_WARNING, + "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); + } /* will put inode & node pages */ err = truncate_node(&dn); From c60f9c6ced33ba070c73445cc958298504aa57f8 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Mon, 15 Apr 2019 15:28:35 +0800 Subject: [PATCH 18/40] f2fs: fix to do checksum even if inode page is uptodate As Jungyeon reported in bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=203221 - Overview When mounting the attached crafted image and running program, this error is reported. The image is intentionally fuzzed from a normal f2fs image for testing and I enabled option CONFIG_F2FS_CHECK_FS on. - Reproduces cc poc_07.c mkdir test mount -t f2fs tmp.img test cp a.out test cd test sudo ./a.out - Messages kernel BUG at fs/f2fs/node.c:1279! RIP: 0010:read_node_page+0xcf/0xf0 Call Trace: __get_node_page+0x6b/0x2f0 f2fs_iget+0x8f/0xdf0 f2fs_lookup+0x136/0x320 __lookup_slow+0x92/0x140 lookup_slow+0x30/0x50 walk_component+0x1c1/0x350 path_lookupat+0x62/0x200 filename_lookup+0xb3/0x1a0 do_fchmodat+0x3e/0xa0 __x64_sys_chmod+0x12/0x20 do_syscall_64+0x43/0xf0 entry_SYSCALL_64_after_hwframe+0x44/0xa9 On below paths, we can have opportunity to readahead inode page - gc_node_segment -> f2fs_ra_node_page - gc_data_segment -> f2fs_ra_node_page - f2fs_fill_dentries -> f2fs_ra_node_page Unlike synchronized read, on readahead path, we can set page uptodate before verifying page's checksum, then read_node_page() will trigger kernel panic once it encounters a uptodated page w/ incorrect checksum. So considering readahead scenario, we have to do checksum each time when loading inode page even if it is uptodated. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/inode.c | 4 ++-- fs/f2fs/node.c | 7 ++++--- 2 files changed, 6 insertions(+), 5 deletions(-) diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index ce5a5a579042..0ad0087d3878 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -177,8 +177,8 @@ bool f2fs_inode_chksum_verify(struct f2fs_sb_info *sbi, struct page *page) if (provided != calculated) f2fs_msg(sbi->sb, KERN_WARNING, - "checksum invalid, ino = %x, %x vs. %x", - ino_of_node(page), provided, calculated); + "checksum invalid, nid = %lu, ino_of_node = %x, %x vs. %x", + page->index, ino_of_node(page), provided, calculated); return provided == calculated; } diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 45488ca85966..32d479f5c977 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -1281,9 +1281,10 @@ static int read_node_page(struct page *page, int op_flags) int err; if (PageUptodate(page)) { -#ifdef CONFIG_F2FS_CHECK_FS - f2fs_bug_on(sbi, !f2fs_inode_chksum_verify(sbi, page)); -#endif + if (!f2fs_inode_chksum_verify(sbi, page)) { + ClearPageUptodate(page); + return -EBADMSG; + } return LOCKED_PAGE; } From 65f109d717d4bd03864fc0b0c3ab30b37a005d30 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Mon, 15 Apr 2019 15:28:36 +0800 Subject: [PATCH 19/40] f2fs: fix to do sanity check on free nid As Jungyeon reported in bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=203225 - Overview When mounting the attached crafted image and unmounting it, following errors are reported. Additionally, it hangs on sync after unmounting. The image is intentionally fuzzed from a normal f2fs image for testing. Compile options for F2FS are as follows. CONFIG_F2FS_FS=y CONFIG_F2FS_STAT_FS=y CONFIG_F2FS_FS_XATTR=y CONFIG_F2FS_FS_POSIX_ACL=y CONFIG_F2FS_CHECK_FS=y - Reproduces mkdir test mount -t f2fs tmp.img test touch test/t umount test sync - Messages kernel BUG at fs/f2fs/node.c:3073! RIP: 0010:f2fs_destroy_node_manager+0x2f0/0x300 Call Trace: f2fs_put_super+0xf4/0x270 generic_shutdown_super+0x62/0x110 kill_block_super+0x1c/0x50 kill_f2fs_super+0xad/0xd0 deactivate_locked_super+0x35/0x60 cleanup_mnt+0x36/0x70 task_work_run+0x75/0x90 exit_to_usermode_loop+0x93/0xa0 do_syscall_64+0xba/0xf0 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0010:f2fs_destroy_node_manager+0x2f0/0x300 NAT table is corrupted, so reserved meta/node inode ids were added into free list incorrectly, during file creation, since reserved id has cached in inode hash, so it fails the creation and preallocated nid can not be released later, result in kernel panic. To fix this issue, let's do nid boundary check during free nid loading. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/node.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 32d479f5c977..9f2015be5585 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -2088,6 +2088,9 @@ static bool add_free_nid(struct f2fs_sb_info *sbi, if (unlikely(nid == 0)) return false; + if (unlikely(f2fs_check_nid_range(sbi, nid))) + return false; + i = f2fs_kmem_cache_alloc(free_nid_slab, GFP_NOFS); i->nid = nid; i->state = FREE_NID; From 4ffbe8fee8a4e0b0f0835d32f1ec050c0499dd05 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Mon, 15 Apr 2019 15:28:37 +0800 Subject: [PATCH 20/40] f2fs: fix to avoid panic in do_recover_data() As Jungyeon reported in bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=203227 - Overview When mounting the attached crafted image, following errors are reported. Additionally, it hangs on sync after trying to mount it. The image is intentionally fuzzed from a normal f2fs image for testing. Compile options for F2FS are as follows. CONFIG_F2FS_FS=y CONFIG_F2FS_STAT_FS=y CONFIG_F2FS_FS_XATTR=y CONFIG_F2FS_FS_POSIX_ACL=y CONFIG_F2FS_CHECK_FS=y - Reproduces mkdir test mount -t f2fs tmp.img test sync - Messages kernel BUG at fs/f2fs/recovery.c:549! RIP: 0010:recover_data+0x167a/0x1780 Call Trace: f2fs_recover_fsync_data+0x613/0x710 f2fs_fill_super+0x1043/0x1aa0 mount_bdev+0x16d/0x1a0 mount_fs+0x4a/0x170 vfs_kern_mount+0x5d/0x100 do_mount+0x200/0xcf0 ksys_mount+0x79/0xc0 __x64_sys_mount+0x1c/0x20 do_syscall_64+0x43/0xf0 entry_SYSCALL_64_after_hwframe+0x44/0xa9 During recovery, if ofs_of_node is inconsistent in between recovered node page and original checkpointed node page, let's just fail recovery instead of making kernel panic. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/recovery.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index c2644c68337f..cdbb5f0eb999 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -543,7 +543,15 @@ retry_dn: goto err; f2fs_bug_on(sbi, ni.ino != ino_of_node(page)); - f2fs_bug_on(sbi, ofs_of_node(dn.node_page) != ofs_of_node(page)); + + if (ofs_of_node(dn.node_page) != ofs_of_node(page)) { + f2fs_msg(sbi->sb, KERN_WARNING, + "Inconsistent ofs_of_node, ino:%lu, ofs:%u, %u", + inode->i_ino, ofs_of_node(dn.node_page), + ofs_of_node(page)); + err = -EFAULT; + goto err; + } for (; start < end; start++, dn.ofs_in_node++) { block_t src, dest; From 1c3e295f67d0ab05a8ecd071b4607711d94faa9f Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Mon, 15 Apr 2019 15:30:50 +0800 Subject: [PATCH 21/40] f2fs: fix to do sanity check on valid node/block count As Jungyeon reported in bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=203229 - Overview When mounting the attached crafted image, following errors are reported. Additionally, it hangs on sync after trying to mount it. The image is intentionally fuzzed from a normal f2fs image for testing. Compile options for F2FS are as follows. CONFIG_F2FS_FS=y CONFIG_F2FS_STAT_FS=y CONFIG_F2FS_FS_XATTR=y CONFIG_F2FS_FS_POSIX_ACL=y CONFIG_F2FS_CHECK_FS=y - Reproduces mkdir test mount -t f2fs tmp.img test sync - Kernel message kernel BUG at fs/f2fs/recovery.c:591! RIP: 0010:recover_data+0x12d8/0x1780 Call Trace: f2fs_recover_fsync_data+0x613/0x710 f2fs_fill_super+0x1043/0x1aa0 mount_bdev+0x16d/0x1a0 mount_fs+0x4a/0x170 vfs_kern_mount+0x5d/0x100 do_mount+0x200/0xcf0 ksys_mount+0x79/0xc0 __x64_sys_mount+0x1c/0x20 do_syscall_64+0x43/0xf0 entry_SYSCALL_64_after_hwframe+0x44/0xa9 With corrupted image wihch has out-of-range valid node/block count, during recovery, once we failed due to no free space, it will trigger kernel panic. Adding sanity check on valid node/block count in f2fs_sanity_check_ckpt() to detect such condition, so that potential panic can be avoided. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/super.c | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index dd5658b1750f..6d9ee5e9c515 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -2596,7 +2596,8 @@ int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi) unsigned int log_blocks_per_seg; unsigned int segment_count_main; unsigned int cp_pack_start_sum, cp_payload; - block_t user_block_count; + block_t user_block_count, valid_user_blocks; + block_t avail_node_count, valid_node_count; int i, j; total = le32_to_cpu(raw_super->segment_count); @@ -2631,6 +2632,24 @@ int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi) return 1; } + valid_user_blocks = le64_to_cpu(ckpt->valid_block_count); + if (valid_user_blocks > user_block_count) { + f2fs_msg(sbi->sb, KERN_ERR, + "Wrong valid_user_blocks: %u, user_block_count: %u", + valid_user_blocks, user_block_count); + return 1; + } + + valid_node_count = le32_to_cpu(ckpt->valid_node_count); + avail_node_count = sbi->total_node_count - sbi->nquota_files - + F2FS_RESERVED_NODE_NUM; + if (valid_node_count > avail_node_count) { + f2fs_msg(sbi->sb, KERN_ERR, + "Wrong valid_node_count: %u, avail_node_count: %u", + valid_node_count, avail_node_count); + return 1; + } + main_segs = le32_to_cpu(raw_super->segment_count_main); blocks_per_seg = sbi->blocks_per_seg; From d6fe88aef4c1d27d7228bc7a30a3452559492fb8 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Mon, 15 Apr 2019 15:30:51 +0800 Subject: [PATCH 22/40] f2fs: fix to do sanity check on valid block count of segment As Jungyeon reported in bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=203233 - Overview When mounting the attached crafted image and running program, following errors are reported. Additionally, it hangs on sync after running program. The image is intentionally fuzzed from a normal f2fs image for testing. Compile options for F2FS are as follows. CONFIG_F2FS_FS=y CONFIG_F2FS_STAT_FS=y CONFIG_F2FS_FS_XATTR=y CONFIG_F2FS_FS_POSIX_ACL=y CONFIG_F2FS_CHECK_FS=y - Reproduces cc poc_13.c mkdir test mount -t f2fs tmp.img test cp a.out test cd test sudo ./a.out sync - Kernel messages F2FS-fs (sdb): Bitmap was wrongly set, blk:4608 kernel BUG at fs/f2fs/segment.c:2102! RIP: 0010:update_sit_entry+0x394/0x410 Call Trace: f2fs_allocate_data_block+0x16f/0x660 do_write_page+0x62/0x170 f2fs_do_write_node_page+0x33/0xa0 __write_node_page+0x270/0x4e0 f2fs_sync_node_pages+0x5df/0x670 f2fs_write_checkpoint+0x372/0x1400 f2fs_sync_fs+0xa3/0x130 f2fs_do_sync_file+0x1a6/0x810 do_fsync+0x33/0x60 __x64_sys_fsync+0xb/0x10 do_syscall_64+0x43/0xf0 entry_SYSCALL_64_after_hwframe+0x44/0xa9 sit.vblocks and sum valid block count in sit.valid_map may be inconsistent, segment w/ zero vblocks will be treated as free segment, while allocating in free segment, we may allocate a free block, if its bitmap is valid previously, it can cause kernel crash due to bitmap verification failure. Anyway, to avoid further serious metadata inconsistence and corruption, it is necessary and worth to detect SIT inconsistence. So let's enable check_block_count() to verify vblocks and valid_map all the time rather than do it only CONFIG_F2FS_CHECK_FS is enabled. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/segment.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h index 5c7ed0442d6e..6f48e0763279 100644 --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -672,7 +672,6 @@ static inline void verify_block_addr(struct f2fs_io_info *fio, block_t blk_addr) static inline int check_block_count(struct f2fs_sb_info *sbi, int segno, struct f2fs_sit_entry *raw_sit) { -#ifdef CONFIG_F2FS_CHECK_FS bool is_valid = test_bit_le(0, raw_sit->valid_map) ? true : false; int valid_blocks = 0; int cur_pos = 0, next_pos; @@ -699,7 +698,7 @@ static inline int check_block_count(struct f2fs_sb_info *sbi, set_sbi_flag(sbi, SBI_NEED_FSCK); return -EINVAL; } -#endif + /* check segment usage, and check boundary of a given segment number */ if (unlikely(GET_SIT_VBLOCKS(raw_sit) > sbi->blocks_per_seg || segno > TOTAL_SEGS(sbi) - 1)) { From 5f2085bab2e23256677538ff6098572367cb03fa Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Mon, 15 Apr 2019 15:30:52 +0800 Subject: [PATCH 23/40] f2fs: fix to avoid panic in f2fs_inplace_write_data() As Jungyeon reported in bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=203239 - Overview When mounting the attached crafted image and running program, following errors are reported. Additionally, it hangs on sync after running program. The image is intentionally fuzzed from a normal f2fs image for testing. Compile options for F2FS are as follows. CONFIG_F2FS_FS=y CONFIG_F2FS_STAT_FS=y CONFIG_F2FS_FS_XATTR=y CONFIG_F2FS_FS_POSIX_ACL=y CONFIG_F2FS_CHECK_FS=y - Reproduces cc poc_15.c ./run.sh f2fs sync - Kernel messages ------------[ cut here ]------------ kernel BUG at fs/f2fs/segment.c:3162! RIP: 0010:f2fs_inplace_write_data+0x12d/0x160 Call Trace: f2fs_do_write_data_page+0x3c1/0x820 __write_data_page+0x156/0x720 f2fs_write_cache_pages+0x20d/0x460 f2fs_write_data_pages+0x1b4/0x300 do_writepages+0x15/0x60 __filemap_fdatawrite_range+0x7c/0xb0 file_write_and_wait_range+0x2c/0x80 f2fs_do_sync_file+0x102/0x810 do_fsync+0x33/0x60 __x64_sys_fsync+0xb/0x10 do_syscall_64+0x43/0xf0 entry_SYSCALL_64_after_hwframe+0x44/0xa9 The reason is f2fs_inplace_write_data() will trigger kernel panic due to data block locates in node type segment. To avoid panic, let's just return error code and set SBI_NEED_FSCK to give a hint to fsck for latter repairing. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/segment.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 586eeedbbbbf..e7ed26474f15 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -3261,13 +3261,18 @@ int f2fs_inplace_write_data(struct f2fs_io_info *fio) { int err; struct f2fs_sb_info *sbi = fio->sbi; + unsigned int segno; fio->new_blkaddr = fio->old_blkaddr; /* i/o temperature is needed for passing down write hints */ __get_segment_type(fio); - f2fs_bug_on(sbi, !IS_DATASEG(get_seg_entry(sbi, - GET_SEGNO(sbi, fio->new_blkaddr))->type)); + segno = GET_SEGNO(sbi, fio->new_blkaddr); + + if (!IS_DATASEG(get_seg_entry(sbi, segno)->type)) { + set_sbi_flag(sbi, SBI_NEED_FSCK); + return -EFAULT; + } stat_inc_inplace_blocks(fio->sbi); From 2c8359eee2adce42d9814b1ee223a7a8664a0766 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Mon, 15 Apr 2019 15:30:53 +0800 Subject: [PATCH 24/40] f2fs: fix to set FI_UPDATE_WRITE correctly This patch fixes to set FI_UPDATE_WRITE only if in-place IO was issued. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/data.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 04158e0ec45c..045159a77329 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -1868,9 +1868,10 @@ got_it: true); if (PageWriteback(page)) end_page_writeback(page); + } else { + set_inode_flag(inode, FI_UPDATE_WRITE); } trace_f2fs_do_write_data_page(fio->page, IPU); - set_inode_flag(inode, FI_UPDATE_WRITE); return err; } From 8ac217148510d64a5bb66af85a3494801e833161 Mon Sep 17 00:00:00 2001 From: Park Ju Hyung Date: Wed, 17 Apr 2019 18:57:38 +0900 Subject: [PATCH 25/40] f2fs: mark is_extension_exist() inline The caller set_file_temperature() is marked as inline as well. It doesn't make much sense to leave is_extension_exist() un-inlined. Signed-off-by: Park Ju Hyung Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/namei.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index 1e8a21fdb6a2..be71f8598d81 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -143,7 +143,7 @@ fail_drop: return ERR_PTR(err); } -static int is_extension_exist(const unsigned char *s, const char *sub) +static inline int is_extension_exist(const unsigned char *s, const char *sub) { size_t slen = strlen(s); size_t sublen = strlen(sub); From c351f529e2200e21c54fc1e7200b2a3ec22761f3 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Mon, 25 Mar 2019 21:07:30 +0800 Subject: [PATCH 26/40] f2fs: introduce f2fs_read_single_page() for cleanup This patch introduces f2fs_read_single_page() to wrap core operations of reading one page in f2fs_mpage_readpages(). In addition, if we failed in f2fs_mpage_readpages(), propagate error number to f2fs_read_data_page(), for f2fs_read_data_pages() path, always return success. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/data.c | 214 +++++++++++++++++++++++++++---------------------- 1 file changed, 118 insertions(+), 96 deletions(-) diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 045159a77329..f3da9e0b0662 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -1502,6 +1502,118 @@ out: return ret; } +static int f2fs_read_single_page(struct inode *inode, struct page *page, + unsigned nr_pages, + struct f2fs_map_blocks *map, + struct bio **bio_ret, + sector_t *last_block_in_bio, + bool is_readahead) +{ + struct bio *bio = *bio_ret; + const unsigned blkbits = inode->i_blkbits; + const unsigned blocksize = 1 << blkbits; + sector_t block_in_file; + sector_t last_block; + sector_t last_block_in_file; + sector_t block_nr; + int ret = 0; + + block_in_file = (sector_t)page->index; + last_block = block_in_file + nr_pages; + last_block_in_file = (i_size_read(inode) + blocksize - 1) >> + blkbits; + if (last_block > last_block_in_file) + last_block = last_block_in_file; + + /* just zeroing out page which is beyond EOF */ + if (block_in_file >= last_block) + goto zero_out; + /* + * Map blocks using the previous result first. + */ + if ((map->m_flags & F2FS_MAP_MAPPED) && + block_in_file > map->m_lblk && + block_in_file < (map->m_lblk + map->m_len)) + goto got_it; + + /* + * Then do more f2fs_map_blocks() calls until we are + * done with this page. + */ + map->m_lblk = block_in_file; + map->m_len = last_block - block_in_file; + + ret = f2fs_map_blocks(inode, map, 0, F2FS_GET_BLOCK_DEFAULT); + if (ret) + goto out; +got_it: + if ((map->m_flags & F2FS_MAP_MAPPED)) { + block_nr = map->m_pblk + block_in_file - map->m_lblk; + SetPageMappedToDisk(page); + + if (!PageUptodate(page) && !cleancache_get_page(page)) { + SetPageUptodate(page); + goto confused; + } + + if (!f2fs_is_valid_blkaddr(F2FS_I_SB(inode), block_nr, + DATA_GENERIC)) { + ret = -EFAULT; + goto out; + } + } else { +zero_out: + zero_user_segment(page, 0, PAGE_SIZE); + if (!PageUptodate(page)) + SetPageUptodate(page); + unlock_page(page); + goto out; + } + + /* + * This page will go to BIO. Do we need to send this + * BIO off first? + */ + if (bio && (*last_block_in_bio != block_nr - 1 || + !__same_bdev(F2FS_I_SB(inode), block_nr, bio))) { +submit_and_realloc: + __submit_bio(F2FS_I_SB(inode), bio, DATA); + bio = NULL; + } + if (bio == NULL) { + bio = f2fs_grab_read_bio(inode, block_nr, nr_pages, + is_readahead ? REQ_RAHEAD : 0); + if (IS_ERR(bio)) { + ret = PTR_ERR(bio); + bio = NULL; + goto out; + } + } + + /* + * If the page is under writeback, we need to wait for + * its completion to see the correct decrypted data. + */ + f2fs_wait_on_block_writeback(inode, block_nr); + + if (bio_add_page(bio, page, blocksize, 0) < blocksize) + goto submit_and_realloc; + + inc_page_count(F2FS_I_SB(inode), F2FS_RD_DATA); + ClearPageError(page); + *last_block_in_bio = block_nr; + goto out; +confused: + if (bio) { + __submit_bio(F2FS_I_SB(inode), bio, DATA); + bio = NULL; + } + unlock_page(page); +out: + *bio_ret = bio; + return ret; +} + /* * This function was originally taken from fs/mpage.c, and customized for f2fs. * Major change was from block_size == page_size in f2fs by default. @@ -1518,13 +1630,8 @@ static int f2fs_mpage_readpages(struct address_space *mapping, struct bio *bio = NULL; sector_t last_block_in_bio = 0; struct inode *inode = mapping->host; - const unsigned blkbits = inode->i_blkbits; - const unsigned blocksize = 1 << blkbits; - sector_t block_in_file; - sector_t last_block; - sector_t last_block_in_file; - sector_t block_nr; struct f2fs_map_blocks map; + int ret = 0; map.m_pblk = 0; map.m_lblk = 0; @@ -1546,98 +1653,13 @@ static int f2fs_mpage_readpages(struct address_space *mapping, goto next_page; } - block_in_file = (sector_t)page->index; - last_block = block_in_file + nr_pages; - last_block_in_file = (i_size_read(inode) + blocksize - 1) >> - blkbits; - if (last_block > last_block_in_file) - last_block = last_block_in_file; - - /* just zeroing out page which is beyond EOF */ - if (block_in_file >= last_block) - goto zero_out; - /* - * Map blocks using the previous result first. - */ - if ((map.m_flags & F2FS_MAP_MAPPED) && - block_in_file > map.m_lblk && - block_in_file < (map.m_lblk + map.m_len)) - goto got_it; - - /* - * Then do more f2fs_map_blocks() calls until we are - * done with this page. - */ - map.m_lblk = block_in_file; - map.m_len = last_block - block_in_file; - - if (f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_DEFAULT)) - goto set_error_page; -got_it: - if ((map.m_flags & F2FS_MAP_MAPPED)) { - block_nr = map.m_pblk + block_in_file - map.m_lblk; - SetPageMappedToDisk(page); - - if (!PageUptodate(page) && !cleancache_get_page(page)) { - SetPageUptodate(page); - goto confused; - } - - if (!f2fs_is_valid_blkaddr(F2FS_I_SB(inode), block_nr, - DATA_GENERIC)) - goto set_error_page; - } else { -zero_out: + ret = f2fs_read_single_page(inode, page, nr_pages, &map, &bio, + &last_block_in_bio, is_readahead); + if (ret) { + SetPageError(page); zero_user_segment(page, 0, PAGE_SIZE); - if (!PageUptodate(page)) - SetPageUptodate(page); unlock_page(page); - goto next_page; } - - /* - * This page will go to BIO. Do we need to send this - * BIO off first? - */ - if (bio && (last_block_in_bio != block_nr - 1 || - !__same_bdev(F2FS_I_SB(inode), block_nr, bio))) { -submit_and_realloc: - __submit_bio(F2FS_I_SB(inode), bio, DATA); - bio = NULL; - } - if (bio == NULL) { - bio = f2fs_grab_read_bio(inode, block_nr, nr_pages, - is_readahead ? REQ_RAHEAD : 0); - if (IS_ERR(bio)) { - bio = NULL; - goto set_error_page; - } - } - - /* - * If the page is under writeback, we need to wait for - * its completion to see the correct decrypted data. - */ - f2fs_wait_on_block_writeback(inode, block_nr); - - if (bio_add_page(bio, page, blocksize, 0) < blocksize) - goto submit_and_realloc; - - inc_page_count(F2FS_I_SB(inode), F2FS_RD_DATA); - ClearPageError(page); - last_block_in_bio = block_nr; - goto next_page; -set_error_page: - SetPageError(page); - zero_user_segment(page, 0, PAGE_SIZE); - unlock_page(page); - goto next_page; -confused: - if (bio) { - __submit_bio(F2FS_I_SB(inode), bio, DATA); - bio = NULL; - } - unlock_page(page); next_page: if (pages) put_page(page); @@ -1645,7 +1667,7 @@ next_page: BUG_ON(pages && !list_empty(pages)); if (bio) __submit_bio(F2FS_I_SB(inode), bio, DATA); - return 0; + return pages ? 0 : ret; } static int f2fs_read_data_page(struct file *file, struct page *page) From e3057056de1061b68ae697d4b7343f128ae4dd30 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Mon, 25 Mar 2019 21:08:19 +0800 Subject: [PATCH 27/40] f2fs: allow address pointer number of dnode aligning to specified size This patch expands scalability of dnode layout, it allows address pointer number of dnode aligning to specified size (now, the size is one byte by default), and later the number can align to compress cluster size (1 << n bytes, n=[2,..)), it can avoid cluster acrossing two dnode, making design of compress meta layout simple. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/f2fs.h | 11 ++++++++++- fs/f2fs/file.c | 7 ++++--- fs/f2fs/gc.c | 2 +- fs/f2fs/node.c | 10 +++++----- fs/f2fs/super.c | 2 +- include/linux/f2fs_fs.h | 7 ++++--- 6 files changed, 25 insertions(+), 14 deletions(-) diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 33da1e15c063..ca4fe42d9e48 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -2638,9 +2638,18 @@ static inline int f2fs_has_inline_xattr(struct inode *inode) return is_inode_flag_set(inode, FI_INLINE_XATTR); } +#define ALIGN_DOWN(x, a) __ALIGN_KERNEL((x) - ((a) - 1), (a)) + static inline unsigned int addrs_per_inode(struct inode *inode) { - return CUR_ADDRS_PER_INODE(inode) - get_inline_xattr_addrs(inode); + unsigned int addrs = CUR_ADDRS_PER_INODE(inode) - + get_inline_xattr_addrs(inode); + return ALIGN_DOWN(addrs, 1); +} + +static inline unsigned int addrs_per_block(struct inode *inode) +{ + return ALIGN_DOWN(DEF_ADDRS_PER_BLOCK, 1); } static inline void *inline_xattr_addr(struct inode *inode, struct page *page) diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index ed2d525c1769..59ea9f55691d 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -555,7 +555,7 @@ void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count) void f2fs_truncate_data_blocks(struct dnode_of_data *dn) { - f2fs_truncate_data_blocks_range(dn, ADDRS_PER_BLOCK); + f2fs_truncate_data_blocks_range(dn, ADDRS_PER_BLOCK(dn->inode)); } static int truncate_partial_data_page(struct inode *inode, u64 from, @@ -1013,7 +1013,8 @@ next_dnode: } else if (ret == -ENOENT) { if (dn.max_level == 0) return -ENOENT; - done = min((pgoff_t)ADDRS_PER_BLOCK - dn.ofs_in_node, len); + done = min((pgoff_t)ADDRS_PER_BLOCK(inode) - dn.ofs_in_node, + len); blkaddr += done; do_replace += done; goto next; @@ -1164,7 +1165,7 @@ static int __exchange_data_block(struct inode *src_inode, int ret; while (len) { - olen = min((pgoff_t)4 * ADDRS_PER_BLOCK, len); + olen = min((pgoff_t)4 * ADDRS_PER_BLOCK(src_inode), len); src_blkaddr = f2fs_kvzalloc(F2FS_I_SB(src_inode), array_size(olen, sizeof(block_t)), diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 62b9f39b25c5..620a23830d67 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -591,7 +591,7 @@ block_t f2fs_start_bidx_of_node(unsigned int node_ofs, struct inode *inode) int dec = (node_ofs - indirect_blks - 3) / (NIDS_PER_BLOCK + 1); bidx = node_ofs - 5 - dec; } - return bidx * ADDRS_PER_BLOCK + ADDRS_PER_INODE(inode); + return bidx * ADDRS_PER_BLOCK(inode) + ADDRS_PER_INODE(inode); } static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 9f2015be5585..145b9409a3c9 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -600,9 +600,9 @@ static void f2fs_ra_node_pages(struct page *parent, int start, int n) pgoff_t f2fs_get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs) { const long direct_index = ADDRS_PER_INODE(dn->inode); - const long direct_blks = ADDRS_PER_BLOCK; - const long indirect_blks = ADDRS_PER_BLOCK * NIDS_PER_BLOCK; - unsigned int skipped_unit = ADDRS_PER_BLOCK; + const long direct_blks = ADDRS_PER_BLOCK(dn->inode); + const long indirect_blks = ADDRS_PER_BLOCK(dn->inode) * NIDS_PER_BLOCK; + unsigned int skipped_unit = ADDRS_PER_BLOCK(dn->inode); int cur_level = dn->cur_level; int max_level = dn->max_level; pgoff_t base = 0; @@ -636,9 +636,9 @@ static int get_node_path(struct inode *inode, long block, int offset[4], unsigned int noffset[4]) { const long direct_index = ADDRS_PER_INODE(inode); - const long direct_blks = ADDRS_PER_BLOCK; + const long direct_blks = ADDRS_PER_BLOCK(inode); const long dptrs_per_blk = NIDS_PER_BLOCK; - const long indirect_blks = ADDRS_PER_BLOCK * NIDS_PER_BLOCK; + const long indirect_blks = ADDRS_PER_BLOCK(inode) * NIDS_PER_BLOCK; const long dindirect_blks = indirect_blks * NIDS_PER_BLOCK; int n = 0; int level = 0; diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 6d9ee5e9c515..0e2b93cf905b 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -2280,7 +2280,7 @@ static const struct export_operations f2fs_export_ops = { static loff_t max_file_blocks(void) { loff_t result = 0; - loff_t leaf_count = ADDRS_PER_BLOCK; + loff_t leaf_count = DEF_ADDRS_PER_BLOCK; /* * note: previously, result is equal to (DEF_ADDRS_PER_INODE - diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index b19433738690..de2ca1906c49 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -198,11 +198,12 @@ struct f2fs_extent { get_extra_isize(inode)) #define DEF_NIDS_PER_INODE 5 /* Node IDs in an Inode */ #define ADDRS_PER_INODE(inode) addrs_per_inode(inode) -#define ADDRS_PER_BLOCK 1018 /* Address Pointers in a Direct Block */ +#define DEF_ADDRS_PER_BLOCK 1018 /* Address Pointers in a Direct Block */ +#define ADDRS_PER_BLOCK(inode) addrs_per_block(inode) #define NIDS_PER_BLOCK 1018 /* Node IDs in an Indirect Block */ #define ADDRS_PER_PAGE(page, inode) \ - (IS_INODE(page) ? ADDRS_PER_INODE(inode) : ADDRS_PER_BLOCK) + (IS_INODE(page) ? ADDRS_PER_INODE(inode) : ADDRS_PER_BLOCK(inode)) #define NODE_DIR1_BLOCK (DEF_ADDRS_PER_INODE + 1) #define NODE_DIR2_BLOCK (DEF_ADDRS_PER_INODE + 2) @@ -267,7 +268,7 @@ struct f2fs_inode { } __packed; struct direct_node { - __le32 addr[ADDRS_PER_BLOCK]; /* array of data block address */ + __le32 addr[DEF_ADDRS_PER_BLOCK]; /* array of data block address */ } __packed; struct indirect_node { From 12a9d38a0b11b036604e22bc4e7760bac7536eef Mon Sep 17 00:00:00 2001 From: Youngjun Yoo Date: Sat, 20 Apr 2019 22:51:36 +0900 Subject: [PATCH 28/40] f2fs: insert space before the open parenthesis '(' Modify coding style ERROR: space required before the open parenthesis '(' Signed-off-by: Youngjun Yoo Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/acl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c index 7ebf7b958f9e..0fcef04511f7 100644 --- a/fs/f2fs/acl.c +++ b/fs/f2fs/acl.c @@ -288,7 +288,7 @@ static int f2fs_acl_create_masq(struct posix_acl *acl, umode_t *mode_p) /* assert(atomic_read(acl->a_refcount) == 1); */ FOREACH_ACL_ENTRY(pa, acl, pe) { - switch(pa->e_tag) { + switch (pa->e_tag) { case ACL_USER_OBJ: pa->e_perm &= (mode >> 6) | ~S_IRWXO; mode &= (pa->e_perm << 6) | ~S_IRWXU; From a3df88564441a4bfb0e0284c3de50606a23a1b83 Mon Sep 17 00:00:00 2001 From: Youngjun Yoo Date: Sat, 20 Apr 2019 22:50:40 +0900 Subject: [PATCH 29/40] f2fs: Replace spaces with tab Modify coding style ERROR: code indent should use tabs where possible Signed-off-by: Youngjun Yoo Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/acl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c index 0fcef04511f7..3d7b46d82929 100644 --- a/fs/f2fs/acl.c +++ b/fs/f2fs/acl.c @@ -329,7 +329,7 @@ static int f2fs_acl_create_masq(struct posix_acl *acl, umode_t *mode_p) } *mode_p = (*mode_p & ~S_IRWXUGO) | mode; - return not_equiv; + return not_equiv; } static int f2fs_acl_create(struct inode *dir, umode_t *mode, From ad199c5f600f35d7ab757fdf425d2a8b2bef2dc3 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Mon, 22 Apr 2019 17:33:52 +0800 Subject: [PATCH 30/40] f2fs: allow unfixed f2fs_checkpoint.checksum_offset Previously, f2fs_checkpoint.checksum_offset points fixed position of f2fs_checkpoint structure: "#define CP_CHKSUM_OFFSET 4092" It is unnecessary, and it breaks the consecutiveness of nat and sit bitmap stored across checkpoint park block and payload blocks. This patch allows f2fs to handle unfixed .checksum_offset. In addition, for the case checksum value is stored in the middle of checkpoint park, calculating checksum value with superposition method like we did for inode_checksum. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/checkpoint.c | 27 +++++++++++++++++++++------ include/linux/f2fs_fs.h | 4 ++++ 2 files changed, 25 insertions(+), 6 deletions(-) diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index 5492afd66dff..94b432d28bcc 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -759,13 +759,27 @@ static void write_orphan_inodes(struct f2fs_sb_info *sbi, block_t start_blk) } } +static __u32 f2fs_checkpoint_chksum(struct f2fs_sb_info *sbi, + struct f2fs_checkpoint *ckpt) +{ + unsigned int chksum_ofs = le32_to_cpu(ckpt->checksum_offset); + __u32 chksum; + + chksum = f2fs_crc32(sbi, ckpt, chksum_ofs); + if (chksum_ofs < CP_CHKSUM_OFFSET) { + chksum_ofs += sizeof(chksum); + chksum = f2fs_chksum(sbi, chksum, (__u8 *)ckpt + chksum_ofs, + F2FS_BLKSIZE - chksum_ofs); + } + return chksum; +} + static int get_checkpoint_version(struct f2fs_sb_info *sbi, block_t cp_addr, struct f2fs_checkpoint **cp_block, struct page **cp_page, unsigned long long *version) { - unsigned long blk_size = sbi->blocksize; size_t crc_offset = 0; - __u32 crc = 0; + __u32 crc; *cp_page = f2fs_get_meta_page(sbi, cp_addr); if (IS_ERR(*cp_page)) @@ -774,15 +788,16 @@ static int get_checkpoint_version(struct f2fs_sb_info *sbi, block_t cp_addr, *cp_block = (struct f2fs_checkpoint *)page_address(*cp_page); crc_offset = le32_to_cpu((*cp_block)->checksum_offset); - if (crc_offset > (blk_size - sizeof(__le32))) { + if (crc_offset < CP_MIN_CHKSUM_OFFSET || + crc_offset > CP_CHKSUM_OFFSET) { f2fs_put_page(*cp_page, 1); f2fs_msg(sbi->sb, KERN_WARNING, "invalid crc_offset: %zu", crc_offset); return -EINVAL; } - crc = cur_cp_crc(*cp_block); - if (!f2fs_crc_valid(sbi, crc, *cp_block, crc_offset)) { + crc = f2fs_checkpoint_chksum(sbi, *cp_block); + if (crc != cur_cp_crc(*cp_block)) { f2fs_put_page(*cp_page, 1); f2fs_msg(sbi->sb, KERN_WARNING, "invalid crc value"); return -EINVAL; @@ -1390,7 +1405,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) get_sit_bitmap(sbi, __bitmap_ptr(sbi, SIT_BITMAP)); get_nat_bitmap(sbi, __bitmap_ptr(sbi, NAT_BITMAP)); - crc32 = f2fs_crc32(sbi, ckpt, le32_to_cpu(ckpt->checksum_offset)); + crc32 = f2fs_checkpoint_chksum(sbi, ckpt); *((__le32 *)((unsigned char *)ckpt + le32_to_cpu(ckpt->checksum_offset))) = cpu_to_le32(crc32); diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index de2ca1906c49..de8f11461536 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -164,6 +164,10 @@ struct f2fs_checkpoint { unsigned char sit_nat_version_bitmap[1]; } __packed; +#define CP_CHKSUM_OFFSET 4092 /* default chksum offset in checkpoint */ +#define CP_MIN_CHKSUM_OFFSET \ + (offsetof(struct f2fs_checkpoint, sit_nat_version_bitmap)) + /* * For orphan inode management */ From a90ff12b2ff5aba6f9ae77d4d79c21c9131c2a35 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Mon, 22 Apr 2019 17:33:53 +0800 Subject: [PATCH 31/40] f2fs: relocate chksum_offset for large_nat_bitmap feature For large_nat_bitmap feature, there is a design flaw: Previous: struct f2fs_checkpoint layout: +--------------------------+ 0x0000 | checkpoint_ver | | ...... | | checksum_offset |------+ | ...... | | | sit_nat_version_bitmap[] |<-----|-------+ | ...... | | | | checksum_value |<-----+ | +--------------------------+ 0x1000 | | | nat_bitmap + sit_bitmap | payload blocks | | | | | +--------------------------|<-------------+ Obviously, if nat_bitmap size + sit_bitmap size is larger than MAX_BITMAP_SIZE_IN_CKPT, nat_bitmap or sit_bitmap may overlap checkpoint checksum's position, once checkpoint() is triggered from kernel, nat or sit bitmap will be damaged by checksum field. In order to fix this, let's relocate checksum_value's position to the head of sit_nat_version_bitmap as below, then nat/sit bitmap and chksum value update will become safe. After: struct f2fs_checkpoint layout: +--------------------------+ 0x0000 | checkpoint_ver | | ...... | | checksum_offset |------+ | ...... | | | sit_nat_version_bitmap[] |<-----+ | ...... |<-------------+ | | | +--------------------------+ 0x1000 | | | nat_bitmap + sit_bitmap | payload blocks | | | | | +--------------------------|<-------------+ Related report and discussion: https://sourceforge.net/p/linux-f2fs/mailman/message/36642346/ Reported-by: Park Ju Hyung Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/checkpoint.c | 11 +++++++++++ fs/f2fs/f2fs.h | 6 +++++- 2 files changed, 16 insertions(+), 1 deletion(-) diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index 94b432d28bcc..1ec8d8f1afc9 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -796,6 +796,17 @@ static int get_checkpoint_version(struct f2fs_sb_info *sbi, block_t cp_addr, return -EINVAL; } + if (__is_set_ckpt_flags(*cp_block, CP_LARGE_NAT_BITMAP_FLAG)) { + if (crc_offset != CP_MIN_CHKSUM_OFFSET) { + f2fs_put_page(*cp_page, 1); + f2fs_msg(sbi->sb, KERN_WARNING, + "layout of large_nat_bitmap is deprecated, " + "run fsck to repair, chksum_offset: %zu", + crc_offset); + return -EINVAL; + } + } + crc = f2fs_checkpoint_chksum(sbi, *cp_block); if (crc != cur_cp_crc(*cp_block)) { f2fs_put_page(*cp_page, 1); diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index ca4fe42d9e48..a0b75a483a67 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -1976,7 +1976,11 @@ static inline void *__bitmap_ptr(struct f2fs_sb_info *sbi, int flag) if (is_set_ckpt_flags(sbi, CP_LARGE_NAT_BITMAP_FLAG)) { offset = (flag == SIT_BITMAP) ? le32_to_cpu(ckpt->nat_ver_bitmap_bytesize) : 0; - return &ckpt->sit_nat_version_bitmap + offset; + /* + * if large_nat_bitmap feature is enabled, leave checksum + * protection for all nat/sit bitmaps. + */ + return &ckpt->sit_nat_version_bitmap + offset + sizeof(__le32); } if (__cp_payload(sbi) > 0) { From 25f68cbbdb86de89b6541dac53b595976c6f73c7 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Mon, 22 Apr 2019 20:22:36 +0800 Subject: [PATCH 32/40] f2fs: fix to consider multiple device for readonly check This patch introduce f2fs_hw_is_readonly() to check whether lower device is readonly or not, it adapts multiple device scenario. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/f2fs.h | 14 ++++++++++++++ fs/f2fs/super.c | 2 +- 2 files changed, 15 insertions(+), 1 deletion(-) diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index a0b75a483a67..b86bea0d684a 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -3704,6 +3704,20 @@ static inline bool f2fs_realtime_discard_enable(struct f2fs_sb_info *sbi) f2fs_hw_should_discard(sbi); } +static inline bool f2fs_hw_is_readonly(struct f2fs_sb_info *sbi) +{ + int i; + + if (!f2fs_is_multi_device(sbi)) + return bdev_read_only(sbi->sb->s_bdev); + + for (i = 0; i < sbi->s_ndevs; i++) + if (bdev_read_only(FDEV(i).bdev)) + return true; + return false; +} + + static inline void set_opt_mode(struct f2fs_sb_info *sbi, unsigned int mt) { clear_opt(sbi, ADAPTIVE); diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 0e2b93cf905b..91f442e12f70 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -3384,7 +3384,7 @@ try_onemore: * mount should be failed, when device has readonly mode, and * previous checkpoint was not done by clean system shutdown. */ - if (bdev_read_only(sb->s_bdev) && + if (f2fs_hw_is_readonly(sbi) && !is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG)) { err = -EROFS; goto free_meta; From 04139be9047a38180876cd393ae0589e5fe77a88 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Mon, 22 Apr 2019 20:22:37 +0800 Subject: [PATCH 33/40] f2fs: fix to skip recovery on readonly device As Park Ju Hyung reported in mailing list: https://sourceforge.net/p/linux-f2fs/mailman/message/36639787/ generic_make_request: Trying to write to read-only block-device loop0 (partno 0) WARNING: CPU: 0 PID: 23437 at block/blk-core.c:2174 generic_make_request_checks+0x594/0x630 generic_make_request+0x46/0x3d0 submit_bio+0x30/0x110 __submit_merged_bio+0x68/0x390 f2fs_submit_page_write+0x1bb/0x7f0 f2fs_do_write_meta_page+0x7f/0x160 __f2fs_write_meta_page+0x70/0x140 f2fs_sync_meta_pages+0x140/0x250 f2fs_write_checkpoint+0x5c5/0x17b0 f2fs_sync_fs+0x9c/0x110 sync_filesystem+0x66/0x80 f2fs_recover_fsync_data+0x790/0xa30 f2fs_fill_super+0xe4e/0x1980 mount_bdev+0x518/0x610 mount_fs+0x34/0x13f vfs_kern_mount.part.11+0x4f/0x120 do_mount+0x2d1/0xe40 __x64_sys_mount+0xbf/0xe0 do_syscall_64+0x4a/0xf0 entry_SYSCALL_64_after_hwframe+0x44/0xa9 print_req_error: I/O error, dev loop0, sector 4096 If block device is readonly, we should never trigger write IO from filesystem layer, but previously, orphan and journal recovery didn't consider such condition, result in triggering above warning, fix it. Reported-by: Park Ju Hyung Tested-by: Park Ju Hyung Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/checkpoint.c | 6 ++++++ fs/f2fs/super.c | 15 +++++++++++---- 2 files changed, 17 insertions(+), 4 deletions(-) diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index 1ec8d8f1afc9..8a9e61b3341a 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -645,6 +645,12 @@ int f2fs_recover_orphan_inodes(struct f2fs_sb_info *sbi) if (!is_set_ckpt_flags(sbi, CP_ORPHAN_PRESENT_FLAG)) return 0; + if (bdev_read_only(sbi->sb->s_bdev)) { + f2fs_msg(sbi->sb, KERN_INFO, "write access " + "unavailable, skipping orphan cleanup"); + return 0; + } + if (s_flags & MS_RDONLY) { f2fs_msg(sbi->sb, KERN_INFO, "orphan cleanup on readonly fs"); sbi->sb->s_flags &= ~MS_RDONLY; diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 91f442e12f70..b904418bb902 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -3384,10 +3384,17 @@ try_onemore: * mount should be failed, when device has readonly mode, and * previous checkpoint was not done by clean system shutdown. */ - if (f2fs_hw_is_readonly(sbi) && - !is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG)) { - err = -EROFS; - goto free_meta; + if (f2fs_hw_is_readonly(sbi)) { + if (!is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG)) { + err = -EROFS; + f2fs_msg(sb, KERN_ERR, + "Need to recover fsync data, but " + "write access unavailable"); + goto free_meta; + } + f2fs_msg(sbi->sb, KERN_INFO, "write access " + "unavailable, skipping recovery"); + goto reset_checkpoint; } if (need_fsck) From b6bb1574fce64337e3cf85c66f2666809892ee37 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Mon, 22 Apr 2019 20:22:38 +0800 Subject: [PATCH 34/40] f2fs: fix to be aware of readonly device in write_checkpoint() As Park Ju Hyung reported: Probably unrelated but a similar issue: Warning appears upon unmounting a corrupted R/O f2fs loop image. Should be a trivial issue to fix as well :) [ 2373.758424] ------------[ cut here ]------------ [ 2373.758428] generic_make_request: Trying to write to read-only block-device loop1 (partno 0) [ 2373.758455] WARNING: CPU: 1 PID: 13950 at block/blk-core.c:2174 generic_make_request_checks+0x590/0x630 [ 2373.758556] CPU: 1 PID: 13950 Comm: umount Tainted: G O 4.19.35-zen+ #1 [ 2373.758558] Hardware name: System manufacturer System Product Name/ROG MAXIMUS X HERO (WI-FI AC), BIOS 1704 09/14/2018 [ 2373.758564] RIP: 0010:generic_make_request_checks+0x590/0x630 [ 2373.758567] Code: 5c 03 00 00 48 8d 74 24 08 48 89 df c6 05 b5 cd 36 01 01 e8 c2 90 01 00 48 89 c6 44 89 ea 48 c7 c7 98 64 59 82 e8 d5 9b a7 ff <0f> 0b 48 8b 7b 08 e9 f2 fa ff ff 41 8b 86 98 02 00 00 49 8b 16 89 [ 2373.758570] RSP: 0018:ffff8882bdb43950 EFLAGS: 00010282 [ 2373.758573] RAX: 0000000000000050 RBX: ffff8887244c6700 RCX: 0000000000000006 [ 2373.758575] RDX: 0000000000000007 RSI: 0000000000000086 RDI: ffff88884ec56340 [ 2373.758577] RBP: ffff888849c426c0 R08: 0000000000000004 R09: 00000000000003ba [ 2373.758579] R10: 0000000000000001 R11: 0000000000000029 R12: 0000000000001000 [ 2373.758581] R13: 0000000000000000 R14: ffff888844a2e800 R15: ffff8882bdb43ac0 [ 2373.758584] FS: 00007fc0d114f8c0(0000) GS:ffff88884ec40000(0000) knlGS:0000000000000000 [ 2373.758586] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 2373.758588] CR2: 00007fc0d1ad12c0 CR3: 00000002bdb82003 CR4: 00000000003606e0 [ 2373.758590] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 2373.758592] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 2373.758593] Call Trace: [ 2373.758602] ? generic_make_request+0x46/0x3d0 [ 2373.758608] ? wait_woken+0x80/0x80 [ 2373.758612] ? mempool_alloc+0xb7/0x1a0 [ 2373.758618] ? submit_bio+0x30/0x110 [ 2373.758622] ? bvec_alloc+0x7c/0xd0 [ 2373.758628] ? __submit_merged_bio+0x68/0x390 [ 2373.758633] ? f2fs_submit_page_write+0x1bb/0x7f0 [ 2373.758638] ? f2fs_do_write_meta_page+0x7f/0x160 [ 2373.758642] ? __f2fs_write_meta_page+0x70/0x140 [ 2373.758647] ? f2fs_sync_meta_pages+0x140/0x250 [ 2373.758653] ? f2fs_write_checkpoint+0x5c5/0x17b0 [ 2373.758657] ? f2fs_sync_fs+0x9c/0x110 [ 2373.758664] ? sync_filesystem+0x66/0x80 [ 2373.758667] ? generic_shutdown_super+0x1d/0x100 [ 2373.758670] ? kill_block_super+0x1c/0x40 [ 2373.758674] ? kill_f2fs_super+0x64/0xb0 [ 2373.758678] ? deactivate_locked_super+0x2d/0xb0 [ 2373.758682] ? cleanup_mnt+0x65/0xa0 [ 2373.758688] ? task_work_run+0x7f/0xa0 [ 2373.758693] ? exit_to_usermode_loop+0x9c/0xa0 [ 2373.758698] ? do_syscall_64+0xc7/0xf0 [ 2373.758703] ? entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 2373.758706] ---[ end trace 5d3639907c56271b ]--- [ 2373.758780] print_req_error: I/O error, dev loop1, sector 143048 [ 2373.758800] print_req_error: I/O error, dev loop1, sector 152200 [ 2373.758808] print_req_error: I/O error, dev loop1, sector 8192 [ 2373.758819] print_req_error: I/O error, dev loop1, sector 12272 This patch adds to detect readonly device in write_checkpoint() to avoid trigger write IOs on it. Reported-by: Park Ju Hyung Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/checkpoint.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index 8a9e61b3341a..695e666419a7 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -1531,6 +1531,9 @@ int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) unsigned long long ckpt_ver; int err = 0; + if (f2fs_readonly(sbi->sb) || f2fs_hw_is_readonly(sbi)) + return -EROFS; + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) { if (cpc->reason != CP_PAUSE) return 0; @@ -1547,10 +1550,6 @@ int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) err = -EIO; goto out; } - if (f2fs_readonly(sbi->sb)) { - err = -EROFS; - goto out; - } trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "start block_ops"); From 9ca2000e9d76a4555beee24986600bf555e4c810 Mon Sep 17 00:00:00 2001 From: Chengguang Xu Date: Tue, 23 Apr 2019 13:08:35 +0800 Subject: [PATCH 35/40] f2fs: remove redundant check in f2fs_file_write_iter() We have already checked flag IOCB_DIRECT in the sanity check of flag IOCB_NOWAIT, so don't have to check it again here. Signed-off-by: Chengguang Xu Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/file.c | 22 +++++++++------------- 1 file changed, 9 insertions(+), 13 deletions(-) diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 59ea9f55691d..6ace6508b747 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -2839,20 +2839,16 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) if (iov_iter_fault_in_readable(from, iov_iter_count(from))) set_inode_flag(inode, FI_NO_PREALLOC); - if ((iocb->ki_flags & IOCB_NOWAIT) && - (iocb->ki_flags & IOCB_DIRECT)) { - if (!f2fs_overwrite_io(inode, iocb->ki_pos, + if ((iocb->ki_flags & IOCB_NOWAIT)) { + if (!f2fs_overwrite_io(inode, iocb->ki_pos, iov_iter_count(from)) || - f2fs_has_inline_data(inode) || - f2fs_force_buffered_io(inode, - iocb, from)) { - clear_inode_flag(inode, - FI_NO_PREALLOC); - inode_unlock(inode); - ret = -EAGAIN; - goto out; - } - + f2fs_has_inline_data(inode) || + f2fs_force_buffered_io(inode, iocb, from)) { + clear_inode_flag(inode, FI_NO_PREALLOC); + inode_unlock(inode); + ret = -EAGAIN; + goto out; + } } else { preallocated = true; target_size = iocb->ki_pos + iov_iter_count(from); From 43c33bc93b79f2767061d6e6c749dd5e5ff8998e Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Fri, 26 Apr 2019 17:57:54 +0800 Subject: [PATCH 36/40] f2fs: fix to handle error in f2fs_disable_checkpoint() In f2fs_disable_checkpoint(), it needs to detect and propagate error number returned from f2fs_write_checkpoint(). Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/super.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index b904418bb902..4f0073e2b36c 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -1505,9 +1505,12 @@ static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi) mutex_lock(&sbi->gc_mutex); cpc.reason = CP_PAUSE; set_sbi_flag(sbi, SBI_CP_DISABLED); - f2fs_write_checkpoint(sbi, &cpc); + err = f2fs_write_checkpoint(sbi, &cpc); + if (err) + goto out_unlock; sbi->unusable_block_count = 0; +out_unlock: mutex_unlock(&sbi->gc_mutex); restore_flag: sbi->sb->s_flags = s_flags; /* Restore MS_RDONLY status */ From b60ff4b3605c3e410cd1bbd814c10057cd085304 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Mon, 15 Apr 2019 15:26:32 +0800 Subject: [PATCH 37/40] f2fs: introduce DATA_GENERIC_ENHANCE Previously, f2fs_is_valid_blkaddr(, blkaddr, DATA_GENERIC) will check whether @blkaddr locates in main area or not. That check is weak, since the block address in range of main area can point to the address which is not valid in segment info table, and we can not detect such condition, we may suffer worse corruption as system continues running. So this patch introduce DATA_GENERIC_ENHANCE to enhance the sanity check which trigger SIT bitmap check rather than only range check. This patch did below changes as wel: - set SBI_NEED_FSCK in f2fs_is_valid_blkaddr(). - get rid of is_valid_data_blkaddr() to avoid panic if blkaddr is invalid. - introduce verify_fio_blkaddr() to wrap fio {new,old}_blkaddr validation check. - spread blkaddr check in: * f2fs_get_node_info() * __read_out_blkaddrs() * f2fs_submit_page_read() * ra_data_block() * do_recover_data() This patch can fix bug reported from bugzilla below: https://bugzilla.kernel.org/show_bug.cgi?id=203215 https://bugzilla.kernel.org/show_bug.cgi?id=203223 https://bugzilla.kernel.org/show_bug.cgi?id=203231 https://bugzilla.kernel.org/show_bug.cgi?id=203235 https://bugzilla.kernel.org/show_bug.cgi?id=203241 = Update by Jaegeuk Kim = DATA_GENERIC_ENHANCE enhanced to validate block addresses on read/write paths. But, xfstest/generic/446 compalins some generated kernel messages saying invalid bitmap was detected when reading a block. The reaons is, when we get the block addresses from extent_cache, there is no lock to synchronize it from truncating the blocks in parallel. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/checkpoint.c | 45 +++++++++++++++++++++++++++++++++------- fs/f2fs/data.c | 49 +++++++++++++++++++++++++++++--------------- fs/f2fs/f2fs.h | 18 ++++++++-------- fs/f2fs/file.c | 15 +++++++++++--- fs/f2fs/gc.c | 11 +++++++++- fs/f2fs/inode.c | 7 ++++--- fs/f2fs/node.c | 13 +++++++++--- fs/f2fs/recovery.c | 12 +++++++++++ fs/f2fs/segment.c | 4 ++-- fs/f2fs/segment.h | 13 ++++++------ 10 files changed, 135 insertions(+), 52 deletions(-) diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index 695e666419a7..0dcfc8b394c0 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -130,6 +130,30 @@ struct page *f2fs_get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index) return __get_meta_page(sbi, index, false); } +static bool __is_bitmap_valid(struct f2fs_sb_info *sbi, block_t blkaddr, + int type) +{ + struct seg_entry *se; + unsigned int segno, offset; + bool exist; + + if (type != DATA_GENERIC_ENHANCE && type != DATA_GENERIC_ENHANCE_READ) + return true; + + segno = GET_SEGNO(sbi, blkaddr); + offset = GET_BLKOFF_FROM_SEG0(sbi, blkaddr); + se = get_seg_entry(sbi, segno); + + exist = f2fs_test_bit(offset, se->cur_valid_map); + if (!exist && type == DATA_GENERIC_ENHANCE) { + f2fs_msg(sbi->sb, KERN_ERR, "Inconsistent error " + "blkaddr:%u, sit bitmap:%d", blkaddr, exist); + set_sbi_flag(sbi, SBI_NEED_FSCK); + WARN_ON(1); + } + return exist; +} + bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type) { @@ -151,15 +175,22 @@ bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi, return false; break; case META_POR: - case DATA_GENERIC: if (unlikely(blkaddr >= MAX_BLKADDR(sbi) || - blkaddr < MAIN_BLKADDR(sbi))) { - if (type == DATA_GENERIC) { - f2fs_msg(sbi->sb, KERN_WARNING, - "access invalid blkaddr:%u", blkaddr); - WARN_ON(1); - } + blkaddr < MAIN_BLKADDR(sbi))) return false; + break; + case DATA_GENERIC: + case DATA_GENERIC_ENHANCE: + case DATA_GENERIC_ENHANCE_READ: + if (unlikely(blkaddr >= MAX_BLKADDR(sbi) || + blkaddr < MAIN_BLKADDR(sbi))) { + f2fs_msg(sbi->sb, KERN_WARNING, + "access invalid blkaddr:%u", blkaddr); + set_sbi_flag(sbi, SBI_NEED_FSCK); + WARN_ON(1); + return false; + } else { + return __is_bitmap_valid(sbi, blkaddr, type); } break; case META_GENERIC: diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index f3da9e0b0662..f76b2282b4eb 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -450,8 +450,8 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio) fio->encrypted_page : fio->page; if (!f2fs_is_valid_blkaddr(fio->sbi, fio->new_blkaddr, - fio->is_por ? META_POR : - (__is_meta_io(fio) ? META_GENERIC : DATA_GENERIC))) + fio->is_por ? META_POR : (__is_meta_io(fio) ? + META_GENERIC : DATA_GENERIC_ENHANCE))) return -EFAULT; trace_f2fs_submit_page_bio(page, fio); @@ -501,9 +501,7 @@ next: spin_unlock(&io->io_lock); } - if (__is_valid_data_blkaddr(fio->old_blkaddr)) - verify_block_addr(fio, fio->old_blkaddr); - verify_block_addr(fio, fio->new_blkaddr); + verify_fio_blkaddr(fio); bio_page = fio->encrypted_page ? fio->encrypted_page : fio->page; @@ -560,9 +558,6 @@ static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr, struct bio_post_read_ctx *ctx; unsigned int post_read_steps = 0; - if (!f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC)) - return ERR_PTR(-EFAULT); - bio = f2fs_bio_alloc(sbi, min_t(int, nr_pages, BIO_MAX_PAGES), false); if (!bio) return ERR_PTR(-ENOMEM); @@ -590,8 +585,10 @@ static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr, static int f2fs_submit_page_read(struct inode *inode, struct page *page, block_t blkaddr) { - struct bio *bio = f2fs_grab_read_bio(inode, blkaddr, 1, 0); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct bio *bio; + bio = f2fs_grab_read_bio(inode, blkaddr, 1, 0); if (IS_ERR(bio)) return PTR_ERR(bio); @@ -603,8 +600,8 @@ static int f2fs_submit_page_read(struct inode *inode, struct page *page, return -EFAULT; } ClearPageError(page); - inc_page_count(F2FS_I_SB(inode), F2FS_RD_DATA); - __submit_bio(F2FS_I_SB(inode), bio, DATA); + inc_page_count(sbi, F2FS_RD_DATA); + __submit_bio(sbi, bio, DATA); return 0; } @@ -732,6 +729,11 @@ struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index, if (f2fs_lookup_extent_cache(inode, index, &ei)) { dn.data_blkaddr = ei.blk + index - ei.fofs; + if (!f2fs_is_valid_blkaddr(F2FS_I_SB(inode), dn.data_blkaddr, + DATA_GENERIC_ENHANCE_READ)) { + err = -EFAULT; + goto put_err; + } goto got_it; } @@ -745,6 +747,13 @@ struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index, err = -ENOENT; goto put_err; } + if (dn.data_blkaddr != NEW_ADDR && + !f2fs_is_valid_blkaddr(F2FS_I_SB(inode), + dn.data_blkaddr, + DATA_GENERIC_ENHANCE)) { + err = -EFAULT; + goto put_err; + } got_it: if (PageUptodate(page)) { unlock_page(page); @@ -1087,12 +1096,12 @@ next_block: blkaddr = datablock_addr(dn.inode, dn.node_page, dn.ofs_in_node); if (__is_valid_data_blkaddr(blkaddr) && - !f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC)) { + !f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC_ENHANCE)) { err = -EFAULT; goto sync_out; } - if (is_valid_data_blkaddr(sbi, blkaddr)) { + 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 && map->m_may_create) { @@ -1557,7 +1566,7 @@ got_it: } if (!f2fs_is_valid_blkaddr(F2FS_I_SB(inode), block_nr, - DATA_GENERIC)) { + DATA_GENERIC_ENHANCE_READ)) { ret = -EFAULT; goto out; } @@ -1837,7 +1846,7 @@ int f2fs_do_write_data_page(struct f2fs_io_info *fio) fio->old_blkaddr = ei.blk + page->index - ei.fofs; if (!f2fs_is_valid_blkaddr(fio->sbi, fio->old_blkaddr, - DATA_GENERIC)) + DATA_GENERIC_ENHANCE)) return -EFAULT; ipu_force = true; @@ -1864,7 +1873,7 @@ int f2fs_do_write_data_page(struct f2fs_io_info *fio) got_it: if (__is_valid_data_blkaddr(fio->old_blkaddr) && !f2fs_is_valid_blkaddr(fio->sbi, fio->old_blkaddr, - DATA_GENERIC)) { + DATA_GENERIC_ENHANCE)) { err = -EFAULT; goto out_writepage; } @@ -1872,7 +1881,8 @@ got_it: * If current allocation needs SSR, * it had better in-place writes for updated data. */ - if (ipu_force || (is_valid_data_blkaddr(fio->sbi, fio->old_blkaddr) && + if (ipu_force || + (__is_valid_data_blkaddr(fio->old_blkaddr) && need_inplace_update(fio))) { err = encrypt_one_page(fio); if (err) @@ -2517,6 +2527,11 @@ repeat: zero_user_segment(page, 0, PAGE_SIZE); SetPageUptodate(page); } else { + if (!f2fs_is_valid_blkaddr(sbi, blkaddr, + DATA_GENERIC_ENHANCE_READ)) { + err = -EFAULT; + goto fail; + } err = f2fs_submit_page_read(inode, page, blkaddr); if (err) goto fail; diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index b86bea0d684a..28c57052b29c 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -279,7 +279,14 @@ enum { META_SSA, META_MAX, META_POR, - DATA_GENERIC, + DATA_GENERIC, /* check range only */ + DATA_GENERIC_ENHANCE, /* strong check on range and segment bitmap */ + DATA_GENERIC_ENHANCE_READ, /* + * strong check on range and segment + * bitmap but no warning due to race + * condition of read on truncated area + * by extent_cache + */ META_GENERIC, }; @@ -2952,15 +2959,6 @@ static inline bool __is_valid_data_blkaddr(block_t blkaddr) return true; } -static inline bool is_valid_data_blkaddr(struct f2fs_sb_info *sbi, - block_t blkaddr) -{ - if (!__is_valid_data_blkaddr(blkaddr)) - return false; - verify_blkaddr(sbi, blkaddr, DATA_GENERIC); - return true; -} - static inline void f2fs_set_page_private(struct page *page, unsigned long data) { diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 6ace6508b747..3c7885501065 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -359,7 +359,7 @@ static bool __found_offset(struct f2fs_sb_info *sbi, block_t blkaddr, switch (whence) { case SEEK_DATA: if ((blkaddr == NEW_ADDR && dirty == pgofs) || - is_valid_data_blkaddr(sbi, blkaddr)) + __is_valid_data_blkaddr(blkaddr)) return true; break; case SEEK_HOLE: @@ -425,7 +425,7 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence) if (__is_valid_data_blkaddr(blkaddr) && !f2fs_is_valid_blkaddr(F2FS_I_SB(inode), - blkaddr, DATA_GENERIC)) { + blkaddr, DATA_GENERIC_ENHANCE)) { f2fs_put_dnode(&dn); goto fail; } @@ -526,7 +526,8 @@ void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count) f2fs_set_data_blkaddr(dn); if (__is_valid_data_blkaddr(blkaddr) && - !f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC)) + !f2fs_is_valid_blkaddr(sbi, blkaddr, + DATA_GENERIC_ENHANCE)) continue; f2fs_invalidate_blocks(sbi, blkaddr); @@ -1025,6 +1026,14 @@ next_dnode: 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); + + if (__is_valid_data_blkaddr(*blkaddr) && + !f2fs_is_valid_blkaddr(sbi, *blkaddr, + DATA_GENERIC_ENHANCE)) { + f2fs_put_dnode(&dn); + return -EFAULT; + } + if (!f2fs_is_checkpointed_data(sbi, *blkaddr)) { if (test_opt(sbi, LFS)) { diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 620a23830d67..e610a94c7da7 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -656,6 +656,11 @@ static int ra_data_block(struct inode *inode, pgoff_t index) if (f2fs_lookup_extent_cache(inode, index, &ei)) { dn.data_blkaddr = ei.blk + index - ei.fofs; + if (unlikely(!f2fs_is_valid_blkaddr(sbi, dn.data_blkaddr, + DATA_GENERIC_ENHANCE_READ))) { + err = -EFAULT; + goto put_page; + } goto got_it; } @@ -665,8 +670,12 @@ static int ra_data_block(struct inode *inode, pgoff_t index) goto put_page; f2fs_put_dnode(&dn); + if (!__is_valid_data_blkaddr(dn.data_blkaddr)) { + err = -ENOENT; + goto put_page; + } if (unlikely(!f2fs_is_valid_blkaddr(sbi, dn.data_blkaddr, - DATA_GENERIC))) { + DATA_GENERIC_ENHANCE))) { err = -EFAULT; goto put_page; } diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 0ad0087d3878..63a0fcd84492 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -73,7 +73,7 @@ static int __written_first_block(struct f2fs_sb_info *sbi, if (!__is_valid_data_blkaddr(addr)) return 1; - if (!f2fs_is_valid_blkaddr(sbi, addr, DATA_GENERIC)) + if (!f2fs_is_valid_blkaddr(sbi, addr, DATA_GENERIC_ENHANCE)) return -EFAULT; return 0; } @@ -267,9 +267,10 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page) struct extent_info *ei = &F2FS_I(inode)->extent_tree->largest; if (ei->len && - (!f2fs_is_valid_blkaddr(sbi, ei->blk, DATA_GENERIC) || + (!f2fs_is_valid_blkaddr(sbi, ei->blk, + DATA_GENERIC_ENHANCE) || !f2fs_is_valid_blkaddr(sbi, ei->blk + ei->len - 1, - DATA_GENERIC))) { + DATA_GENERIC_ENHANCE))) { set_sbi_flag(sbi, SBI_NEED_FSCK); f2fs_msg(sbi->sb, KERN_WARNING, "%s: inode (ino=%lx) extent info [%u, %u, %u] " diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 145b9409a3c9..a39aa8856d17 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -454,7 +454,7 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni, new_blkaddr == NULL_ADDR); f2fs_bug_on(sbi, nat_get_blkaddr(e) == NEW_ADDR && new_blkaddr == NEW_ADDR); - f2fs_bug_on(sbi, is_valid_data_blkaddr(sbi, nat_get_blkaddr(e)) && + f2fs_bug_on(sbi, __is_valid_data_blkaddr(nat_get_blkaddr(e)) && new_blkaddr == NEW_ADDR); /* increment version no as node is removed */ @@ -465,7 +465,7 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni, /* change address */ nat_set_blkaddr(e, new_blkaddr); - if (!is_valid_data_blkaddr(sbi, new_blkaddr)) + if (!__is_valid_data_blkaddr(new_blkaddr)) set_nat_flag(e, IS_CHECKPOINTED, false); __set_nat_cache_dirty(nm_i, e); @@ -526,6 +526,7 @@ int f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct f2fs_nat_entry ne; struct nat_entry *e; pgoff_t index; + block_t blkaddr; int i; ni->nid = nid; @@ -569,6 +570,11 @@ int f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid, node_info_from_raw_nat(ni, &ne); f2fs_put_page(page, 1); cache: + blkaddr = le32_to_cpu(ne.block_addr); + if (__is_valid_data_blkaddr(blkaddr) && + !f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC_ENHANCE)) + return -EFAULT; + /* cache nat entry */ cache_nat_entry(sbi, nid, &ne); return 0; @@ -1550,7 +1556,8 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted, } if (__is_valid_data_blkaddr(ni.blk_addr) && - !f2fs_is_valid_blkaddr(sbi, ni.blk_addr, DATA_GENERIC)) { + !f2fs_is_valid_blkaddr(sbi, ni.blk_addr, + DATA_GENERIC_ENHANCE)) { up_read(&sbi->node_write); goto redirty_out; } diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index cdbb5f0eb999..67206eff5cca 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -559,6 +559,18 @@ retry_dn: src = datablock_addr(dn.inode, dn.node_page, dn.ofs_in_node); dest = datablock_addr(dn.inode, page, dn.ofs_in_node); + if (__is_valid_data_blkaddr(src) && + !f2fs_is_valid_blkaddr(sbi, src, META_POR)) { + err = -EFAULT; + goto err; + } + + if (__is_valid_data_blkaddr(dest) && + !f2fs_is_valid_blkaddr(sbi, dest, META_POR)) { + err = -EFAULT; + goto err; + } + /* skip recovering if dest is the same as src */ if (src == dest) continue; diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index e7ed26474f15..5b184d22cc47 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -2293,7 +2293,7 @@ bool f2fs_is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr) struct seg_entry *se; bool is_cp = false; - if (!is_valid_data_blkaddr(sbi, blkaddr)) + if (!__is_valid_data_blkaddr(blkaddr)) return true; down_read(&sit_i->sentry_lock); @@ -3415,7 +3415,7 @@ void f2fs_wait_on_block_writeback(struct inode *inode, block_t blkaddr) if (!f2fs_post_read_required(inode)) return; - if (!is_valid_data_blkaddr(sbi, blkaddr)) + if (!__is_valid_data_blkaddr(blkaddr)) return; cpage = find_lock_page(META_MAPPING(sbi), blkaddr); diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h index 6f48e0763279..429007b8036e 100644 --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -82,7 +82,7 @@ (GET_SEGOFF_FROM_SEG0(sbi, blk_addr) & ((sbi)->blocks_per_seg - 1)) #define GET_SEGNO(sbi, blk_addr) \ - ((!is_valid_data_blkaddr(sbi, blk_addr)) ? \ + ((!__is_valid_data_blkaddr(blk_addr)) ? \ NULL_SEGNO : GET_L2R_SEGNO(FREE_I(sbi), \ GET_SEGNO_FROM_SEG0(sbi, blk_addr))) #define BLKS_PER_SEC(sbi) \ @@ -656,14 +656,15 @@ static inline void check_seg_range(struct f2fs_sb_info *sbi, unsigned int segno) f2fs_bug_on(sbi, segno > TOTAL_SEGS(sbi) - 1); } -static inline void verify_block_addr(struct f2fs_io_info *fio, block_t blk_addr) +static inline void verify_fio_blkaddr(struct f2fs_io_info *fio) { struct f2fs_sb_info *sbi = fio->sbi; - if (__is_meta_io(fio)) - verify_blkaddr(sbi, blk_addr, META_GENERIC); - else - verify_blkaddr(sbi, blk_addr, DATA_GENERIC); + if (__is_valid_data_blkaddr(fio->old_blkaddr)) + verify_blkaddr(sbi, fio->old_blkaddr, __is_meta_io(fio) ? + META_GENERIC : DATA_GENERIC); + verify_blkaddr(sbi, fio->new_blkaddr, __is_meta_io(fio) ? + META_GENERIC : DATA_GENERIC_ENHANCE); } /* From 993543bcbad298a2109ccc60af35b756d8158c75 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Mon, 15 Apr 2019 15:22:19 +0800 Subject: [PATCH 38/40] f2fs: add tracepoint for f2fs_filemap_fault() This patch adds tracepoint for f2fs_filemap_fault(). Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/file.c | 2 ++ include/trace/events/f2fs.h | 26 ++++++++++++++++++++++++++ 2 files changed, 28 insertions(+) diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 3c7885501065..8a1ad6cd63c5 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -41,6 +41,8 @@ static int f2fs_filemap_fault(struct vm_area_struct *vma, err = filemap_fault(vma, vmf); up_read(&F2FS_I(inode)->i_mmap_sem); + trace_f2fs_filemap_fault(inode, vmf->pgoff, (unsigned long)err); + return err; } diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index 87d5ce6a674c..e84cbb11fe7f 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -1272,6 +1272,32 @@ DEFINE_EVENT(f2fs__page, f2fs_commit_inmem_page, TP_ARGS(page, type) ); +TRACE_EVENT(f2fs_filemap_fault, + + TP_PROTO(struct inode *inode, pgoff_t index, unsigned long ret), + + TP_ARGS(inode, index, ret), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(pgoff_t, index) + __field(unsigned long, ret) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->index = index; + __entry->ret = ret; + ), + + TP_printk("dev = (%d,%d), ino = %lu, index = %lu, ret = %lx", + show_dev_ino(__entry), + (unsigned long)__entry->index, + __entry->ret) +); + TRACE_EVENT(f2fs_writepages, TP_PROTO(struct inode *inode, struct writeback_control *wbc, int type), From ee588a7f2329744b94615a0c2571cfe810983855 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Sun, 5 May 2019 11:40:46 +0800 Subject: [PATCH 39/40] f2fs: fix to avoid potential race on sbi->unusable_block_count access/update Use sbi.stat_lock to protect sbi->unusable_block_count accesss/udpate, in order to avoid potential race on it. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/checkpoint.c | 4 ++++ fs/f2fs/segment.c | 5 ++++- fs/f2fs/super.c | 6 ++++++ 3 files changed, 14 insertions(+), 1 deletion(-) diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index 0dcfc8b394c0..c31911203019 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -1537,7 +1537,11 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) clear_sbi_flag(sbi, SBI_IS_DIRTY); clear_sbi_flag(sbi, SBI_NEED_CP); clear_sbi_flag(sbi, SBI_QUOTA_SKIP_FLUSH); + + spin_lock(&sbi->stat_lock); sbi->unusable_block_count = 0; + spin_unlock(&sbi->stat_lock); + __set_cp_next_pack(sbi); /* diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 5b184d22cc47..af4770f0672a 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -2245,8 +2245,11 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del) * before, we must track that to know how much space we * really have. */ - if (f2fs_test_bit(offset, se->ckpt_valid_map)) + if (f2fs_test_bit(offset, se->ckpt_valid_map)) { + spin_lock(&sbi->stat_lock); sbi->unusable_block_count++; + spin_unlock(&sbi->stat_lock); + } } if (f2fs_test_and_clear_bit(offset, se->discard_map)) diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 4f0073e2b36c..ea83c4aa9b9d 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -1227,10 +1227,13 @@ static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_blocks = total_count - start_count; buf->f_bfree = user_block_count - valid_user_blocks(sbi) - sbi->current_reserved_blocks; + + spin_lock(&sbi->stat_lock); if (unlikely(buf->f_bfree <= sbi->unusable_block_count)) buf->f_bfree = 0; else buf->f_bfree -= sbi->unusable_block_count; + spin_unlock(&sbi->stat_lock); if (buf->f_bfree > F2FS_OPTION(sbi).root_reserved_blocks) buf->f_bavail = buf->f_bfree - @@ -1509,7 +1512,10 @@ static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi) if (err) goto out_unlock; + spin_lock(&sbi->stat_lock); sbi->unusable_block_count = 0; + spin_unlock(&sbi->stat_lock); + out_unlock: mutex_unlock(&sbi->gc_mutex); restore_flag: From 0cba1d4c1422e3a7b86ca021534cda92a1586f11 Mon Sep 17 00:00:00 2001 From: Randall Huang Date: Thu, 11 Apr 2019 16:26:46 +0800 Subject: [PATCH 40/40] f2fs: fix to avoid accessing xattr across the boundary When we traverse xattr entries via __find_xattr(), if the raw filesystem content is faked or any hardware failure occurs, out-of-bound error can be detected by KASAN. Fix the issue by introducing boundary check. [ 38.402878] c7 1827 BUG: KASAN: slab-out-of-bounds in f2fs_getxattr+0x518/0x68c [ 38.402891] c7 1827 Read of size 4 at addr ffffffc0b6fb35dc by task [ 38.402935] c7 1827 Call trace: [ 38.402952] c7 1827 [] dump_backtrace+0x0/0x6bc [ 38.402966] c7 1827 [] show_stack+0x20/0x2c [ 38.402981] c7 1827 [] dump_stack+0xfc/0x140 [ 38.402995] c7 1827 [] print_address_description+0x80/0x2d8 [ 38.403009] c7 1827 [] kasan_report_error+0x198/0x1fc [ 38.403022] c7 1827 [] kasan_report_error+0x0/0x1fc [ 38.403037] c7 1827 [] __asan_load4+0x1b0/0x1b8 [ 38.403051] c7 1827 [] f2fs_getxattr+0x518/0x68c [ 38.403066] c7 1827 [] f2fs_xattr_generic_get+0xb0/0xd0 [ 38.403080] c7 1827 [] __vfs_getxattr+0x1f4/0x1fc [ 38.403096] c7 1827 [] inode_doinit_with_dentry+0x360/0x938 [ 38.403109] c7 1827 [] selinux_d_instantiate+0x2c/0x38 [ 38.403123] c7 1827 [] security_d_instantiate+0x68/0x98 [ 38.403136] c7 1827 [] d_splice_alias+0x58/0x348 [ 38.403149] c7 1827 [] f2fs_lookup+0x608/0x774 [ 38.403163] c7 1827 [] lookup_slow+0x1e0/0x2cc [ 38.403177] c7 1827 [] walk_component+0x160/0x520 [ 38.403190] c7 1827 [] path_lookupat+0x110/0x2b4 [ 38.403203] c7 1827 [] filename_lookup+0x1d8/0x3a8 [ 38.403216] c7 1827 [] user_path_at_empty+0x54/0x68 [ 38.403229] c7 1827 [] SyS_getxattr+0xb4/0x18c [ 38.403241] c7 1827 [] el0_svc_naked+0x34/0x38 Signed-off-by: Randall Huang [Jaegeuk Kim: Fix wrong ending boundary] Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/xattr.c | 36 +++++++++++++++++++++++++++--------- fs/f2fs/xattr.h | 2 ++ 2 files changed, 29 insertions(+), 9 deletions(-) diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c index 8c6161ea4e23..376db951b7c4 100644 --- a/fs/f2fs/xattr.c +++ b/fs/f2fs/xattr.c @@ -248,12 +248,17 @@ static inline const struct xattr_handler *f2fs_xattr_handler(int index) return handler; } -static struct f2fs_xattr_entry *__find_xattr(void *base_addr, int index, - size_t len, const char *name) +static struct f2fs_xattr_entry *__find_xattr(void *base_addr, + void *last_base_addr, int index, + size_t len, const char *name) { struct f2fs_xattr_entry *entry; list_for_each_xattr(entry, base_addr) { + if ((void *)(entry) + sizeof(__u32) > last_base_addr || + (void *)XATTR_NEXT_ENTRY(entry) > last_base_addr) + return NULL; + if (entry->e_name_index != index) continue; if (entry->e_name_len != len) @@ -343,20 +348,22 @@ static int lookup_all_xattrs(struct inode *inode, struct page *ipage, const char *name, struct f2fs_xattr_entry **xe, void **base_addr, int *base_size) { - void *cur_addr, *txattr_addr, *last_addr = NULL; + void *cur_addr, *txattr_addr, *last_txattr_addr; + void *last_addr = NULL; nid_t xnid = F2FS_I(inode)->i_xattr_nid; - unsigned int size = xnid ? VALID_XATTR_BLOCK_SIZE : 0; unsigned int inline_size = inline_xattr_size(inode); int err = 0; - if (!size && !inline_size) + if (!xnid && !inline_size) return -ENODATA; - *base_size = inline_size + size + XATTR_PADDING_SIZE; + *base_size = XATTR_SIZE(xnid, inode) + XATTR_PADDING_SIZE; txattr_addr = f2fs_kzalloc(F2FS_I_SB(inode), *base_size, GFP_NOFS); if (!txattr_addr) return -ENOMEM; + last_txattr_addr = (void *)txattr_addr + XATTR_SIZE(xnid, inode); + /* read from inline xattr */ if (inline_size) { err = read_inline_xattr(inode, ipage, txattr_addr); @@ -383,7 +390,11 @@ static int lookup_all_xattrs(struct inode *inode, struct page *ipage, else cur_addr = txattr_addr; - *xe = __find_xattr(cur_addr, index, len, name); + *xe = __find_xattr(cur_addr, last_txattr_addr, index, len, name); + if (!*xe) { + err = -EFAULT; + goto out; + } check: if (IS_XATTR_LAST_ENTRY(*xe)) { err = -ENODATA; @@ -620,7 +631,8 @@ static int __f2fs_setxattr(struct inode *inode, int index, struct page *ipage, int flags) { struct f2fs_xattr_entry *here, *last; - void *base_addr; + void *base_addr, *last_base_addr; + nid_t xnid = F2FS_I(inode)->i_xattr_nid; int found, newsize; size_t len; __u32 new_hsize; @@ -644,8 +656,14 @@ static int __f2fs_setxattr(struct inode *inode, int index, if (error) return error; + last_base_addr = (void *)base_addr + XATTR_SIZE(xnid, inode); + /* find entry with wanted name. */ - here = __find_xattr(base_addr, index, len, name); + here = __find_xattr(base_addr, last_base_addr, index, len, name); + if (!here) { + error = -EFAULT; + goto exit; + } found = IS_XATTR_LAST_ENTRY(here) ? 0 : 1; diff --git a/fs/f2fs/xattr.h b/fs/f2fs/xattr.h index 12a5ef3a607d..2909c9241145 100644 --- a/fs/f2fs/xattr.h +++ b/fs/f2fs/xattr.h @@ -71,6 +71,8 @@ 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) + \ + (inline_xattr_size(i))) #define MIN_OFFSET(i) XATTR_ALIGN(inline_xattr_size(i) + \ VALID_XATTR_BLOCK_SIZE)