mirror of
https://github.com/torvalds/linux.git
synced 2024-11-27 22:51:35 +00:00
c9b60788fc
This patch add to do sanity check with below field: - cp_pack_total_block_count - blkaddr of data/node - extent info - Overview BUG() in verify_block_addr() when writing to a corrupted f2fs image - Reproduce (4.18 upstream kernel) - POC (poc.c) static void activity(char *mpoint) { char *foo_bar_baz; int err; static int buf[8192]; memset(buf, 0, sizeof(buf)); err = asprintf(&foo_bar_baz, "%s/foo/bar/baz", mpoint); int fd = open(foo_bar_baz, O_RDWR | O_TRUNC, 0777); if (fd >= 0) { write(fd, (char *)buf, sizeof(buf)); fdatasync(fd); close(fd); } } int main(int argc, char *argv[]) { activity(argv[1]); return 0; } - Kernel message [ 689.349473] F2FS-fs (loop0): Mounted with checkpoint version = 3 [ 699.728662] WARNING: CPU: 0 PID: 1309 at fs/f2fs/segment.c:2860 f2fs_inplace_write_data+0x232/0x240 [ 699.728670] Modules linked in: snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_pcm snd_timer snd mac_hid i2c_piix4 soundcore ib_iser rdma_cm iw_cm ib_cm ib_core iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx raid1 raid0 multipath linear 8139too crct10dif_pclmul crc32_pclmul qxl drm_kms_helper syscopyarea aesni_intel sysfillrect sysimgblt fb_sys_fops ttm drm aes_x86_64 crypto_simd cryptd 8139cp glue_helper mii pata_acpi floppy [ 699.729056] CPU: 0 PID: 1309 Comm: a.out Not tainted 4.18.0-rc1+ #4 [ 699.729064] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.729074] RIP: 0010:f2fs_inplace_write_data+0x232/0x240 [ 699.729076] Code: ff e9 cf fe ff ff 49 8d 7d 10 e8 39 45 ad ff 4d 8b 7d 10 be 04 00 00 00 49 8d 7f 48 e8 07 49 ad ff 45 8b 7f 48 e9 fb fe ff ff <0f> 0b f0 41 80 4d 48 04 e9 65 fe ff ff 90 66 66 66 66 90 55 48 8d [ 699.729130] RSP: 0018:ffff8801f43af568 EFLAGS: 00010202 [ 699.729139] RAX: 000000000000003f RBX: ffff8801f43af7b8 RCX: ffffffffb88c9113 [ 699.729142] RDX: 0000000000000003 RSI: dffffc0000000000 RDI: ffff8802024e5540 [ 699.729144] RBP: ffff8801f43af590 R08: 0000000000000009 R09: ffffffffffffffe8 [ 699.729147] R10: 0000000000000001 R11: ffffed0039b0596a R12: ffff8802024e5540 [ 699.729149] R13: ffff8801f0335500 R14: ffff8801e3e7a700 R15: ffff8801e1ee4450 [ 699.729154] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.729156] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.729159] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.729171] Call Trace: [ 699.729192] f2fs_do_write_data_page+0x2e2/0xe00 [ 699.729203] ? f2fs_should_update_outplace+0xd0/0xd0 [ 699.729238] ? memcg_drain_all_list_lrus+0x280/0x280 [ 699.729269] ? __radix_tree_replace+0xa3/0x120 [ 699.729276] __write_data_page+0x5c7/0xe30 [ 699.729291] ? kasan_check_read+0x11/0x20 [ 699.729310] ? page_mapped+0x8a/0x110 [ 699.729321] ? page_mkclean+0xe9/0x160 [ 699.729327] ? f2fs_do_write_data_page+0xe00/0xe00 [ 699.729331] ? invalid_page_referenced_vma+0x130/0x130 [ 699.729345] ? clear_page_dirty_for_io+0x332/0x450 [ 699.729351] f2fs_write_cache_pages+0x4ca/0x860 [ 699.729358] ? __write_data_page+0xe30/0xe30 [ 699.729374] ? percpu_counter_add_batch+0x22/0xa0 [ 699.729380] ? kasan_check_write+0x14/0x20 [ 699.729391] ? _raw_spin_lock+0x17/0x40 [ 699.729403] ? f2fs_mark_inode_dirty_sync.part.18+0x16/0x30 [ 699.729413] ? iov_iter_advance+0x113/0x640 [ 699.729418] ? f2fs_write_end+0x133/0x2e0 [ 699.729423] ? balance_dirty_pages_ratelimited+0x239/0x640 [ 699.729428] f2fs_write_data_pages+0x329/0x520 [ 699.729433] ? generic_perform_write+0x250/0x320 [ 699.729438] ? f2fs_write_cache_pages+0x860/0x860 [ 699.729454] ? current_time+0x110/0x110 [ 699.729459] ? f2fs_preallocate_blocks+0x1ef/0x370 [ 699.729464] do_writepages+0x37/0xb0 [ 699.729468] ? f2fs_write_cache_pages+0x860/0x860 [ 699.729472] ? do_writepages+0x37/0xb0 [ 699.729478] __filemap_fdatawrite_range+0x19a/0x1f0 [ 699.729483] ? delete_from_page_cache_batch+0x4e0/0x4e0 [ 699.729496] ? __vfs_write+0x2b2/0x410 [ 699.729501] file_write_and_wait_range+0x66/0xb0 [ 699.729506] f2fs_do_sync_file+0x1f9/0xd90 [ 699.729511] ? truncate_partial_data_page+0x290/0x290 [ 699.729521] ? __sb_end_write+0x30/0x50 [ 699.729526] ? vfs_write+0x20f/0x260 [ 699.729530] f2fs_sync_file+0x9a/0xb0 [ 699.729534] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.729548] vfs_fsync_range+0x68/0x100 [ 699.729554] ? __fget_light+0xc9/0xe0 [ 699.729558] do_fsync+0x3d/0x70 [ 699.729562] __x64_sys_fdatasync+0x24/0x30 [ 699.729585] do_syscall_64+0x78/0x170 [ 699.729595] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 699.729613] RIP: 0033:0x7f9bf930d800 [ 699.729615] Code: 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 83 3d 49 bf 2c 00 00 75 10 b8 4b 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 be 78 01 00 48 89 04 24 [ 699.729668] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.729673] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.729675] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.729678] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.729680] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.729683] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.729687] ---[ end trace 4ce02f25ff7d3df5 ]--- [ 699.729782] ------------[ cut here ]------------ [ 699.729785] kernel BUG at fs/f2fs/segment.h:654! [ 699.731055] invalid opcode: 0000 [#1] SMP KASAN PTI [ 699.732104] CPU: 0 PID: 1309 Comm: a.out Tainted: G W 4.18.0-rc1+ #4 [ 699.733684] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.735611] RIP: 0010:f2fs_submit_page_bio+0x29b/0x730 [ 699.736649] Code: 54 49 8d bd 18 04 00 00 e8 b2 59 af ff 41 8b 8d 18 04 00 00 8b 45 b8 41 d3 e6 44 01 f0 4c 8d 73 14 41 39 c7 0f 82 37 fe ff ff <0f> 0b 65 8b 05 2c 04 77 47 89 c0 48 0f a3 05 52 c1 d5 01 0f 92 c0 [ 699.740524] RSP: 0018:ffff8801f43af508 EFLAGS: 00010283 [ 699.741573] RAX: 0000000000000000 RBX: ffff8801f43af7b8 RCX: ffffffffb88a7cef [ 699.743006] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8801e3e7a64c [ 699.744426] RBP: ffff8801f43af558 R08: ffffed003e066b55 R09: ffffed003e066b55 [ 699.745833] R10: 0000000000000001 R11: ffffed003e066b54 R12: ffffea0007876940 [ 699.747256] R13: ffff8801f0335500 R14: ffff8801e3e7a600 R15: 0000000000000001 [ 699.748683] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.750293] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.751462] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.752874] Call Trace: [ 699.753386] ? f2fs_inplace_write_data+0x93/0x240 [ 699.754341] f2fs_inplace_write_data+0xd2/0x240 [ 699.755271] f2fs_do_write_data_page+0x2e2/0xe00 [ 699.756214] ? f2fs_should_update_outplace+0xd0/0xd0 [ 699.757215] ? memcg_drain_all_list_lrus+0x280/0x280 [ 699.758209] ? __radix_tree_replace+0xa3/0x120 [ 699.759164] __write_data_page+0x5c7/0xe30 [ 699.760002] ? kasan_check_read+0x11/0x20 [ 699.760823] ? page_mapped+0x8a/0x110 [ 699.761573] ? page_mkclean+0xe9/0x160 [ 699.762345] ? f2fs_do_write_data_page+0xe00/0xe00 [ 699.763332] ? invalid_page_referenced_vma+0x130/0x130 [ 699.764374] ? clear_page_dirty_for_io+0x332/0x450 [ 699.765347] f2fs_write_cache_pages+0x4ca/0x860 [ 699.766276] ? __write_data_page+0xe30/0xe30 [ 699.767161] ? percpu_counter_add_batch+0x22/0xa0 [ 699.768112] ? kasan_check_write+0x14/0x20 [ 699.768951] ? _raw_spin_lock+0x17/0x40 [ 699.769739] ? f2fs_mark_inode_dirty_sync.part.18+0x16/0x30 [ 699.770885] ? iov_iter_advance+0x113/0x640 [ 699.771743] ? f2fs_write_end+0x133/0x2e0 [ 699.772569] ? balance_dirty_pages_ratelimited+0x239/0x640 [ 699.773680] f2fs_write_data_pages+0x329/0x520 [ 699.774603] ? generic_perform_write+0x250/0x320 [ 699.775544] ? f2fs_write_cache_pages+0x860/0x860 [ 699.776510] ? current_time+0x110/0x110 [ 699.777299] ? f2fs_preallocate_blocks+0x1ef/0x370 [ 699.778279] do_writepages+0x37/0xb0 [ 699.779026] ? f2fs_write_cache_pages+0x860/0x860 [ 699.779978] ? do_writepages+0x37/0xb0 [ 699.780755] __filemap_fdatawrite_range+0x19a/0x1f0 [ 699.781746] ? delete_from_page_cache_batch+0x4e0/0x4e0 [ 699.782820] ? __vfs_write+0x2b2/0x410 [ 699.783597] file_write_and_wait_range+0x66/0xb0 [ 699.784540] f2fs_do_sync_file+0x1f9/0xd90 [ 699.785381] ? truncate_partial_data_page+0x290/0x290 [ 699.786415] ? __sb_end_write+0x30/0x50 [ 699.787204] ? vfs_write+0x20f/0x260 [ 699.787941] f2fs_sync_file+0x9a/0xb0 [ 699.788694] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.789572] vfs_fsync_range+0x68/0x100 [ 699.790360] ? __fget_light+0xc9/0xe0 [ 699.791128] do_fsync+0x3d/0x70 [ 699.791779] __x64_sys_fdatasync+0x24/0x30 [ 699.792614] do_syscall_64+0x78/0x170 [ 699.793371] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 699.794406] RIP: 0033:0x7f9bf930d800 [ 699.795134] Code: 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 83 3d 49 bf 2c 00 00 75 10 b8 4b 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 be 78 01 00 48 89 04 24 [ 699.798960] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.800483] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.801923] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.803373] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.804798] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.806233] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.807667] Modules linked in: snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_pcm snd_timer snd mac_hid i2c_piix4 soundcore ib_iser rdma_cm iw_cm ib_cm ib_core iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx raid1 raid0 multipath linear 8139too crct10dif_pclmul crc32_pclmul qxl drm_kms_helper syscopyarea aesni_intel sysfillrect sysimgblt fb_sys_fops ttm drm aes_x86_64 crypto_simd cryptd 8139cp glue_helper mii pata_acpi floppy [ 699.817079] ---[ end trace 4ce02f25ff7d3df6 ]--- [ 699.818068] RIP: 0010:f2fs_submit_page_bio+0x29b/0x730 [ 699.819114] Code: 54 49 8d bd 18 04 00 00 e8 b2 59 af ff 41 8b 8d 18 04 00 00 8b 45 b8 41 d3 e6 44 01 f0 4c 8d 73 14 41 39 c7 0f 82 37 fe ff ff <0f> 0b 65 8b 05 2c 04 77 47 89 c0 48 0f a3 05 52 c1 d5 01 0f 92 c0 [ 699.822919] RSP: 0018:ffff8801f43af508 EFLAGS: 00010283 [ 699.823977] RAX: 0000000000000000 RBX: ffff8801f43af7b8 RCX: ffffffffb88a7cef [ 699.825436] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8801e3e7a64c [ 699.826881] RBP: ffff8801f43af558 R08: ffffed003e066b55 R09: ffffed003e066b55 [ 699.828292] R10: 0000000000000001 R11: ffffed003e066b54 R12: ffffea0007876940 [ 699.829750] R13: ffff8801f0335500 R14: ffff8801e3e7a600 R15: 0000000000000001 [ 699.831192] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.832793] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.833981] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.835556] ================================================================== [ 699.837029] BUG: KASAN: stack-out-of-bounds in update_stack_state+0x38c/0x3e0 [ 699.838462] Read of size 8 at addr ffff8801f43af970 by task a.out/1309 [ 699.840086] CPU: 0 PID: 1309 Comm: a.out Tainted: G D W 4.18.0-rc1+ #4 [ 699.841603] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.843475] Call Trace: [ 699.843982] dump_stack+0x7b/0xb5 [ 699.844661] print_address_description+0x70/0x290 [ 699.845607] kasan_report+0x291/0x390 [ 699.846351] ? update_stack_state+0x38c/0x3e0 [ 699.853831] __asan_load8+0x54/0x90 [ 699.854569] update_stack_state+0x38c/0x3e0 [ 699.855428] ? __read_once_size_nocheck.constprop.7+0x20/0x20 [ 699.856601] ? __save_stack_trace+0x5e/0x100 [ 699.857476] unwind_next_frame.part.5+0x18e/0x490 [ 699.858448] ? unwind_dump+0x290/0x290 [ 699.859217] ? clear_page_dirty_for_io+0x332/0x450 [ 699.860185] __unwind_start+0x106/0x190 [ 699.860974] __save_stack_trace+0x5e/0x100 [ 699.861808] ? __save_stack_trace+0x5e/0x100 [ 699.862691] ? unlink_anon_vmas+0xba/0x2c0 [ 699.863525] save_stack_trace+0x1f/0x30 [ 699.864312] save_stack+0x46/0xd0 [ 699.864993] ? __alloc_pages_slowpath+0x1420/0x1420 [ 699.865990] ? flush_tlb_mm_range+0x15e/0x220 [ 699.866889] ? kasan_check_write+0x14/0x20 [ 699.867724] ? __dec_node_state+0x92/0xb0 [ 699.868543] ? lock_page_memcg+0x85/0xf0 [ 699.869350] ? unlock_page_memcg+0x16/0x80 [ 699.870185] ? page_remove_rmap+0x198/0x520 [ 699.871048] ? mark_page_accessed+0x133/0x200 [ 699.871930] ? _cond_resched+0x1a/0x50 [ 699.872700] ? unmap_page_range+0xcd4/0xe50 [ 699.873551] ? rb_next+0x58/0x80 [ 699.874217] ? rb_next+0x58/0x80 [ 699.874895] __kasan_slab_free+0x13c/0x1a0 [ 699.875734] ? unlink_anon_vmas+0xba/0x2c0 [ 699.876563] kasan_slab_free+0xe/0x10 [ 699.877315] kmem_cache_free+0x89/0x1e0 [ 699.878095] unlink_anon_vmas+0xba/0x2c0 [ 699.878913] free_pgtables+0x101/0x1b0 [ 699.879677] exit_mmap+0x146/0x2a0 [ 699.880378] ? __ia32_sys_munmap+0x50/0x50 [ 699.881214] ? kasan_check_read+0x11/0x20 [ 699.882052] ? mm_update_next_owner+0x322/0x380 [ 699.882985] mmput+0x8b/0x1d0 [ 699.883602] do_exit+0x43a/0x1390 [ 699.884288] ? mm_update_next_owner+0x380/0x380 [ 699.885212] ? f2fs_sync_file+0x9a/0xb0 [ 699.885995] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.886877] ? vfs_fsync_range+0x68/0x100 [ 699.887694] ? __fget_light+0xc9/0xe0 [ 699.888442] ? do_fsync+0x3d/0x70 [ 699.889118] ? __x64_sys_fdatasync+0x24/0x30 [ 699.889996] rewind_stack_do_exit+0x17/0x20 [ 699.890860] RIP: 0033:0x7f9bf930d800 [ 699.891585] Code: Bad RIP value. [ 699.892268] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.893781] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.895220] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.896643] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.898069] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.899505] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.901241] The buggy address belongs to the page: [ 699.902215] page:ffffea0007d0ebc0 count:0 mapcount:0 mapping:0000000000000000 index:0x0 [ 699.903811] flags: 0x2ffff0000000000() [ 699.904585] raw: 02ffff0000000000 0000000000000000 ffffffff07d00101 0000000000000000 [ 699.906125] raw: 0000000000000000 0000000000240000 00000000ffffffff 0000000000000000 [ 699.907673] page dumped because: kasan: bad access detected [ 699.909108] Memory state around the buggy address: [ 699.910077] ffff8801f43af800: 00 f1 f1 f1 f1 00 f4 f4 f4 f3 f3 f3 f3 00 00 00 [ 699.911528] ffff8801f43af880: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 699.912953] >ffff8801f43af900: 00 00 00 00 00 00 00 00 f1 01 f4 f4 f4 f2 f2 f2 [ 699.914392] ^ [ 699.915758] ffff8801f43af980: f2 00 f4 f4 00 00 00 00 f2 00 00 00 00 00 00 00 [ 699.917193] ffff8801f43afa00: 00 00 00 00 00 00 00 00 00 f3 f3 f3 00 00 00 00 [ 699.918634] ================================================================== - Location https://elixir.bootlin.com/linux/v4.18-rc1/source/fs/f2fs/segment.h#L644 Reported-by Wen Xu <wen.xu@gatech.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
1523 lines
37 KiB
C
1523 lines
37 KiB
C
/*
|
|
* fs/f2fs/checkpoint.c
|
|
*
|
|
* Copyright (c) 2012 Samsung Electronics Co., Ltd.
|
|
* http://www.samsung.com/
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify
|
|
* it under the terms of the GNU General Public License version 2 as
|
|
* published by the Free Software Foundation.
|
|
*/
|
|
#include <linux/fs.h>
|
|
#include <linux/bio.h>
|
|
#include <linux/mpage.h>
|
|
#include <linux/writeback.h>
|
|
#include <linux/blkdev.h>
|
|
#include <linux/f2fs_fs.h>
|
|
#include <linux/pagevec.h>
|
|
#include <linux/swap.h>
|
|
|
|
#include "f2fs.h"
|
|
#include "node.h"
|
|
#include "segment.h"
|
|
#include "trace.h"
|
|
#include <trace/events/f2fs.h>
|
|
|
|
static struct kmem_cache *ino_entry_slab;
|
|
struct kmem_cache *f2fs_inode_entry_slab;
|
|
|
|
void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io)
|
|
{
|
|
f2fs_build_fault_attr(sbi, 0);
|
|
set_ckpt_flags(sbi, CP_ERROR_FLAG);
|
|
if (!end_io)
|
|
f2fs_flush_merged_writes(sbi);
|
|
}
|
|
|
|
/*
|
|
* We guarantee no failure on the returned page.
|
|
*/
|
|
struct page *f2fs_grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index)
|
|
{
|
|
struct address_space *mapping = META_MAPPING(sbi);
|
|
struct page *page = NULL;
|
|
repeat:
|
|
page = f2fs_grab_cache_page(mapping, index, false);
|
|
if (!page) {
|
|
cond_resched();
|
|
goto repeat;
|
|
}
|
|
f2fs_wait_on_page_writeback(page, META, true);
|
|
if (!PageUptodate(page))
|
|
SetPageUptodate(page);
|
|
return page;
|
|
}
|
|
|
|
/*
|
|
* We guarantee no failure on the returned page.
|
|
*/
|
|
static struct page *__get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index,
|
|
bool is_meta)
|
|
{
|
|
struct address_space *mapping = META_MAPPING(sbi);
|
|
struct page *page;
|
|
struct f2fs_io_info fio = {
|
|
.sbi = sbi,
|
|
.type = META,
|
|
.op = REQ_OP_READ,
|
|
.op_flags = REQ_META | REQ_PRIO,
|
|
.old_blkaddr = index,
|
|
.new_blkaddr = index,
|
|
.encrypted_page = NULL,
|
|
.is_meta = is_meta,
|
|
};
|
|
|
|
if (unlikely(!is_meta))
|
|
fio.op_flags &= ~REQ_META;
|
|
repeat:
|
|
page = f2fs_grab_cache_page(mapping, index, false);
|
|
if (!page) {
|
|
cond_resched();
|
|
goto repeat;
|
|
}
|
|
if (PageUptodate(page))
|
|
goto out;
|
|
|
|
fio.page = page;
|
|
|
|
if (f2fs_submit_page_bio(&fio)) {
|
|
memset(page_address(page), 0, PAGE_SIZE);
|
|
f2fs_stop_checkpoint(sbi, false);
|
|
f2fs_bug_on(sbi, 1);
|
|
return page;
|
|
}
|
|
|
|
lock_page(page);
|
|
if (unlikely(page->mapping != mapping)) {
|
|
f2fs_put_page(page, 1);
|
|
goto repeat;
|
|
}
|
|
|
|
/*
|
|
* if there is any IO error when accessing device, make our filesystem
|
|
* readonly and make sure do not write checkpoint with non-uptodate
|
|
* meta page.
|
|
*/
|
|
if (unlikely(!PageUptodate(page))) {
|
|
memset(page_address(page), 0, PAGE_SIZE);
|
|
f2fs_stop_checkpoint(sbi, false);
|
|
}
|
|
out:
|
|
return page;
|
|
}
|
|
|
|
struct page *f2fs_get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index)
|
|
{
|
|
return __get_meta_page(sbi, index, true);
|
|
}
|
|
|
|
/* for POR only */
|
|
struct page *f2fs_get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index)
|
|
{
|
|
return __get_meta_page(sbi, index, false);
|
|
}
|
|
|
|
bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
|
|
block_t blkaddr, int type)
|
|
{
|
|
switch (type) {
|
|
case META_NAT:
|
|
break;
|
|
case META_SIT:
|
|
if (unlikely(blkaddr >= SIT_BLK_CNT(sbi)))
|
|
return false;
|
|
break;
|
|
case META_SSA:
|
|
if (unlikely(blkaddr >= MAIN_BLKADDR(sbi) ||
|
|
blkaddr < SM_I(sbi)->ssa_blkaddr))
|
|
return false;
|
|
break;
|
|
case META_CP:
|
|
if (unlikely(blkaddr >= SIT_I(sbi)->sit_base_addr ||
|
|
blkaddr < __start_cp_addr(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);
|
|
}
|
|
return false;
|
|
}
|
|
break;
|
|
case META_GENERIC:
|
|
if (unlikely(blkaddr < SEG0_BLKADDR(sbi) ||
|
|
blkaddr >= MAIN_BLKADDR(sbi)))
|
|
return false;
|
|
break;
|
|
default:
|
|
BUG();
|
|
}
|
|
|
|
return true;
|
|
}
|
|
|
|
/*
|
|
* Readahead CP/NAT/SIT/SSA pages
|
|
*/
|
|
int f2fs_ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
|
|
int type, bool sync)
|
|
{
|
|
struct page *page;
|
|
block_t blkno = start;
|
|
struct f2fs_io_info fio = {
|
|
.sbi = sbi,
|
|
.type = META,
|
|
.op = REQ_OP_READ,
|
|
.op_flags = sync ? (REQ_META | REQ_PRIO) : REQ_RAHEAD,
|
|
.encrypted_page = NULL,
|
|
.in_list = false,
|
|
.is_meta = (type != META_POR),
|
|
};
|
|
struct blk_plug plug;
|
|
|
|
if (unlikely(type == META_POR))
|
|
fio.op_flags &= ~REQ_META;
|
|
|
|
blk_start_plug(&plug);
|
|
for (; nrpages-- > 0; blkno++) {
|
|
|
|
if (!f2fs_is_valid_blkaddr(sbi, blkno, type))
|
|
goto out;
|
|
|
|
switch (type) {
|
|
case META_NAT:
|
|
if (unlikely(blkno >=
|
|
NAT_BLOCK_OFFSET(NM_I(sbi)->max_nid)))
|
|
blkno = 0;
|
|
/* get nat block addr */
|
|
fio.new_blkaddr = current_nat_addr(sbi,
|
|
blkno * NAT_ENTRY_PER_BLOCK);
|
|
break;
|
|
case META_SIT:
|
|
/* get sit block addr */
|
|
fio.new_blkaddr = current_sit_addr(sbi,
|
|
blkno * SIT_ENTRY_PER_BLOCK);
|
|
break;
|
|
case META_SSA:
|
|
case META_CP:
|
|
case META_POR:
|
|
fio.new_blkaddr = blkno;
|
|
break;
|
|
default:
|
|
BUG();
|
|
}
|
|
|
|
page = f2fs_grab_cache_page(META_MAPPING(sbi),
|
|
fio.new_blkaddr, false);
|
|
if (!page)
|
|
continue;
|
|
if (PageUptodate(page)) {
|
|
f2fs_put_page(page, 1);
|
|
continue;
|
|
}
|
|
|
|
fio.page = page;
|
|
f2fs_submit_page_bio(&fio);
|
|
f2fs_put_page(page, 0);
|
|
}
|
|
out:
|
|
blk_finish_plug(&plug);
|
|
return blkno - start;
|
|
}
|
|
|
|
void f2fs_ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index)
|
|
{
|
|
struct page *page;
|
|
bool readahead = false;
|
|
|
|
page = find_get_page(META_MAPPING(sbi), index);
|
|
if (!page || !PageUptodate(page))
|
|
readahead = true;
|
|
f2fs_put_page(page, 0);
|
|
|
|
if (readahead)
|
|
f2fs_ra_meta_pages(sbi, index, BIO_MAX_PAGES, META_POR, true);
|
|
}
|
|
|
|
static int __f2fs_write_meta_page(struct page *page,
|
|
struct writeback_control *wbc,
|
|
enum iostat_type io_type)
|
|
{
|
|
struct f2fs_sb_info *sbi = F2FS_P_SB(page);
|
|
|
|
trace_f2fs_writepage(page, META);
|
|
|
|
if (unlikely(f2fs_cp_error(sbi)))
|
|
goto redirty_out;
|
|
if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
|
|
goto redirty_out;
|
|
if (wbc->for_reclaim && page->index < GET_SUM_BLOCK(sbi, 0))
|
|
goto redirty_out;
|
|
|
|
f2fs_do_write_meta_page(sbi, page, io_type);
|
|
dec_page_count(sbi, F2FS_DIRTY_META);
|
|
|
|
if (wbc->for_reclaim)
|
|
f2fs_submit_merged_write_cond(sbi, page->mapping->host,
|
|
0, page->index, META);
|
|
|
|
unlock_page(page);
|
|
|
|
if (unlikely(f2fs_cp_error(sbi)))
|
|
f2fs_submit_merged_write(sbi, META);
|
|
|
|
return 0;
|
|
|
|
redirty_out:
|
|
redirty_page_for_writepage(wbc, page);
|
|
return AOP_WRITEPAGE_ACTIVATE;
|
|
}
|
|
|
|
static int f2fs_write_meta_page(struct page *page,
|
|
struct writeback_control *wbc)
|
|
{
|
|
return __f2fs_write_meta_page(page, wbc, FS_META_IO);
|
|
}
|
|
|
|
static int f2fs_write_meta_pages(struct address_space *mapping,
|
|
struct writeback_control *wbc)
|
|
{
|
|
struct f2fs_sb_info *sbi = F2FS_M_SB(mapping);
|
|
long diff, written;
|
|
|
|
if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
|
|
goto skip_write;
|
|
|
|
/* collect a number of dirty meta pages and write together */
|
|
if (wbc->for_kupdate ||
|
|
get_pages(sbi, F2FS_DIRTY_META) < nr_pages_to_skip(sbi, META))
|
|
goto skip_write;
|
|
|
|
/* if locked failed, cp will flush dirty pages instead */
|
|
if (!mutex_trylock(&sbi->cp_mutex))
|
|
goto skip_write;
|
|
|
|
trace_f2fs_writepages(mapping->host, wbc, META);
|
|
diff = nr_pages_to_write(sbi, META, wbc);
|
|
written = f2fs_sync_meta_pages(sbi, META, wbc->nr_to_write, FS_META_IO);
|
|
mutex_unlock(&sbi->cp_mutex);
|
|
wbc->nr_to_write = max((long)0, wbc->nr_to_write - written - diff);
|
|
return 0;
|
|
|
|
skip_write:
|
|
wbc->pages_skipped += get_pages(sbi, F2FS_DIRTY_META);
|
|
trace_f2fs_writepages(mapping->host, wbc, META);
|
|
return 0;
|
|
}
|
|
|
|
long f2fs_sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type,
|
|
long nr_to_write, enum iostat_type io_type)
|
|
{
|
|
struct address_space *mapping = META_MAPPING(sbi);
|
|
pgoff_t index = 0, prev = ULONG_MAX;
|
|
struct pagevec pvec;
|
|
long nwritten = 0;
|
|
int nr_pages;
|
|
struct writeback_control wbc = {
|
|
.for_reclaim = 0,
|
|
};
|
|
struct blk_plug plug;
|
|
|
|
pagevec_init(&pvec);
|
|
|
|
blk_start_plug(&plug);
|
|
|
|
while ((nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
|
|
PAGECACHE_TAG_DIRTY))) {
|
|
int i;
|
|
|
|
for (i = 0; i < nr_pages; i++) {
|
|
struct page *page = pvec.pages[i];
|
|
|
|
if (prev == ULONG_MAX)
|
|
prev = page->index - 1;
|
|
if (nr_to_write != LONG_MAX && page->index != prev + 1) {
|
|
pagevec_release(&pvec);
|
|
goto stop;
|
|
}
|
|
|
|
lock_page(page);
|
|
|
|
if (unlikely(page->mapping != mapping)) {
|
|
continue_unlock:
|
|
unlock_page(page);
|
|
continue;
|
|
}
|
|
if (!PageDirty(page)) {
|
|
/* someone wrote it for us */
|
|
goto continue_unlock;
|
|
}
|
|
|
|
f2fs_wait_on_page_writeback(page, META, true);
|
|
|
|
BUG_ON(PageWriteback(page));
|
|
if (!clear_page_dirty_for_io(page))
|
|
goto continue_unlock;
|
|
|
|
if (__f2fs_write_meta_page(page, &wbc, io_type)) {
|
|
unlock_page(page);
|
|
break;
|
|
}
|
|
nwritten++;
|
|
prev = page->index;
|
|
if (unlikely(nwritten >= nr_to_write))
|
|
break;
|
|
}
|
|
pagevec_release(&pvec);
|
|
cond_resched();
|
|
}
|
|
stop:
|
|
if (nwritten)
|
|
f2fs_submit_merged_write(sbi, type);
|
|
|
|
blk_finish_plug(&plug);
|
|
|
|
return nwritten;
|
|
}
|
|
|
|
static int f2fs_set_meta_page_dirty(struct page *page)
|
|
{
|
|
trace_f2fs_set_page_dirty(page, META);
|
|
|
|
if (!PageUptodate(page))
|
|
SetPageUptodate(page);
|
|
if (!PageDirty(page)) {
|
|
__set_page_dirty_nobuffers(page);
|
|
inc_page_count(F2FS_P_SB(page), F2FS_DIRTY_META);
|
|
SetPagePrivate(page);
|
|
f2fs_trace_pid(page);
|
|
return 1;
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
const struct address_space_operations f2fs_meta_aops = {
|
|
.writepage = f2fs_write_meta_page,
|
|
.writepages = f2fs_write_meta_pages,
|
|
.set_page_dirty = f2fs_set_meta_page_dirty,
|
|
.invalidatepage = f2fs_invalidate_page,
|
|
.releasepage = f2fs_release_page,
|
|
#ifdef CONFIG_MIGRATION
|
|
.migratepage = f2fs_migrate_page,
|
|
#endif
|
|
};
|
|
|
|
static void __add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino,
|
|
unsigned int devidx, int type)
|
|
{
|
|
struct inode_management *im = &sbi->im[type];
|
|
struct ino_entry *e, *tmp;
|
|
|
|
tmp = f2fs_kmem_cache_alloc(ino_entry_slab, GFP_NOFS);
|
|
|
|
radix_tree_preload(GFP_NOFS | __GFP_NOFAIL);
|
|
|
|
spin_lock(&im->ino_lock);
|
|
e = radix_tree_lookup(&im->ino_root, ino);
|
|
if (!e) {
|
|
e = tmp;
|
|
if (unlikely(radix_tree_insert(&im->ino_root, ino, e)))
|
|
f2fs_bug_on(sbi, 1);
|
|
|
|
memset(e, 0, sizeof(struct ino_entry));
|
|
e->ino = ino;
|
|
|
|
list_add_tail(&e->list, &im->ino_list);
|
|
if (type != ORPHAN_INO)
|
|
im->ino_num++;
|
|
}
|
|
|
|
if (type == FLUSH_INO)
|
|
f2fs_set_bit(devidx, (char *)&e->dirty_device);
|
|
|
|
spin_unlock(&im->ino_lock);
|
|
radix_tree_preload_end();
|
|
|
|
if (e != tmp)
|
|
kmem_cache_free(ino_entry_slab, tmp);
|
|
}
|
|
|
|
static void __remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
|
|
{
|
|
struct inode_management *im = &sbi->im[type];
|
|
struct ino_entry *e;
|
|
|
|
spin_lock(&im->ino_lock);
|
|
e = radix_tree_lookup(&im->ino_root, ino);
|
|
if (e) {
|
|
list_del(&e->list);
|
|
radix_tree_delete(&im->ino_root, ino);
|
|
im->ino_num--;
|
|
spin_unlock(&im->ino_lock);
|
|
kmem_cache_free(ino_entry_slab, e);
|
|
return;
|
|
}
|
|
spin_unlock(&im->ino_lock);
|
|
}
|
|
|
|
void f2fs_add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
|
|
{
|
|
/* add new dirty ino entry into list */
|
|
__add_ino_entry(sbi, ino, 0, type);
|
|
}
|
|
|
|
void f2fs_remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
|
|
{
|
|
/* remove dirty ino entry from list */
|
|
__remove_ino_entry(sbi, ino, type);
|
|
}
|
|
|
|
/* mode should be APPEND_INO or UPDATE_INO */
|
|
bool f2fs_exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode)
|
|
{
|
|
struct inode_management *im = &sbi->im[mode];
|
|
struct ino_entry *e;
|
|
|
|
spin_lock(&im->ino_lock);
|
|
e = radix_tree_lookup(&im->ino_root, ino);
|
|
spin_unlock(&im->ino_lock);
|
|
return e ? true : false;
|
|
}
|
|
|
|
void f2fs_release_ino_entry(struct f2fs_sb_info *sbi, bool all)
|
|
{
|
|
struct ino_entry *e, *tmp;
|
|
int i;
|
|
|
|
for (i = all ? ORPHAN_INO : APPEND_INO; i < MAX_INO_ENTRY; i++) {
|
|
struct inode_management *im = &sbi->im[i];
|
|
|
|
spin_lock(&im->ino_lock);
|
|
list_for_each_entry_safe(e, tmp, &im->ino_list, list) {
|
|
list_del(&e->list);
|
|
radix_tree_delete(&im->ino_root, e->ino);
|
|
kmem_cache_free(ino_entry_slab, e);
|
|
im->ino_num--;
|
|
}
|
|
spin_unlock(&im->ino_lock);
|
|
}
|
|
}
|
|
|
|
void f2fs_set_dirty_device(struct f2fs_sb_info *sbi, nid_t ino,
|
|
unsigned int devidx, int type)
|
|
{
|
|
__add_ino_entry(sbi, ino, devidx, type);
|
|
}
|
|
|
|
bool f2fs_is_dirty_device(struct f2fs_sb_info *sbi, nid_t ino,
|
|
unsigned int devidx, int type)
|
|
{
|
|
struct inode_management *im = &sbi->im[type];
|
|
struct ino_entry *e;
|
|
bool is_dirty = false;
|
|
|
|
spin_lock(&im->ino_lock);
|
|
e = radix_tree_lookup(&im->ino_root, ino);
|
|
if (e && f2fs_test_bit(devidx, (char *)&e->dirty_device))
|
|
is_dirty = true;
|
|
spin_unlock(&im->ino_lock);
|
|
return is_dirty;
|
|
}
|
|
|
|
int f2fs_acquire_orphan_inode(struct f2fs_sb_info *sbi)
|
|
{
|
|
struct inode_management *im = &sbi->im[ORPHAN_INO];
|
|
int err = 0;
|
|
|
|
spin_lock(&im->ino_lock);
|
|
|
|
#ifdef CONFIG_F2FS_FAULT_INJECTION
|
|
if (time_to_inject(sbi, FAULT_ORPHAN)) {
|
|
spin_unlock(&im->ino_lock);
|
|
f2fs_show_injection_info(FAULT_ORPHAN);
|
|
return -ENOSPC;
|
|
}
|
|
#endif
|
|
if (unlikely(im->ino_num >= sbi->max_orphans))
|
|
err = -ENOSPC;
|
|
else
|
|
im->ino_num++;
|
|
spin_unlock(&im->ino_lock);
|
|
|
|
return err;
|
|
}
|
|
|
|
void f2fs_release_orphan_inode(struct f2fs_sb_info *sbi)
|
|
{
|
|
struct inode_management *im = &sbi->im[ORPHAN_INO];
|
|
|
|
spin_lock(&im->ino_lock);
|
|
f2fs_bug_on(sbi, im->ino_num == 0);
|
|
im->ino_num--;
|
|
spin_unlock(&im->ino_lock);
|
|
}
|
|
|
|
void f2fs_add_orphan_inode(struct inode *inode)
|
|
{
|
|
/* add new orphan ino entry into list */
|
|
__add_ino_entry(F2FS_I_SB(inode), inode->i_ino, 0, ORPHAN_INO);
|
|
f2fs_update_inode_page(inode);
|
|
}
|
|
|
|
void f2fs_remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
|
|
{
|
|
/* remove orphan entry from orphan list */
|
|
__remove_ino_entry(sbi, ino, ORPHAN_INO);
|
|
}
|
|
|
|
static int recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
|
|
{
|
|
struct inode *inode;
|
|
struct node_info ni;
|
|
int err;
|
|
|
|
inode = f2fs_iget_retry(sbi->sb, ino);
|
|
if (IS_ERR(inode)) {
|
|
/*
|
|
* there should be a bug that we can't find the entry
|
|
* to orphan inode.
|
|
*/
|
|
f2fs_bug_on(sbi, PTR_ERR(inode) == -ENOENT);
|
|
return PTR_ERR(inode);
|
|
}
|
|
|
|
err = dquot_initialize(inode);
|
|
if (err) {
|
|
iput(inode);
|
|
goto err_out;
|
|
}
|
|
|
|
clear_nlink(inode);
|
|
|
|
/* truncate all the data during iput */
|
|
iput(inode);
|
|
|
|
f2fs_get_node_info(sbi, ino, &ni);
|
|
|
|
/* ENOMEM was fully retried in f2fs_evict_inode. */
|
|
if (ni.blk_addr != NULL_ADDR) {
|
|
err = -EIO;
|
|
goto err_out;
|
|
}
|
|
return 0;
|
|
|
|
err_out:
|
|
set_sbi_flag(sbi, SBI_NEED_FSCK);
|
|
f2fs_msg(sbi->sb, KERN_WARNING,
|
|
"%s: orphan failed (ino=%x), run fsck to fix.",
|
|
__func__, ino);
|
|
return err;
|
|
}
|
|
|
|
int f2fs_recover_orphan_inodes(struct f2fs_sb_info *sbi)
|
|
{
|
|
block_t start_blk, orphan_blocks, i, j;
|
|
unsigned int s_flags = sbi->sb->s_flags;
|
|
int err = 0;
|
|
#ifdef CONFIG_QUOTA
|
|
int quota_enabled;
|
|
#endif
|
|
|
|
if (!is_set_ckpt_flags(sbi, CP_ORPHAN_PRESENT_FLAG))
|
|
return 0;
|
|
|
|
if (s_flags & SB_RDONLY) {
|
|
f2fs_msg(sbi->sb, KERN_INFO, "orphan cleanup on readonly fs");
|
|
sbi->sb->s_flags &= ~SB_RDONLY;
|
|
}
|
|
|
|
#ifdef CONFIG_QUOTA
|
|
/* Needed for iput() to work correctly and not trash data */
|
|
sbi->sb->s_flags |= SB_ACTIVE;
|
|
|
|
/* Turn on quotas so that they are updated correctly */
|
|
quota_enabled = f2fs_enable_quota_files(sbi, s_flags & SB_RDONLY);
|
|
#endif
|
|
|
|
start_blk = __start_cp_addr(sbi) + 1 + __cp_payload(sbi);
|
|
orphan_blocks = __start_sum_addr(sbi) - 1 - __cp_payload(sbi);
|
|
|
|
f2fs_ra_meta_pages(sbi, start_blk, orphan_blocks, META_CP, true);
|
|
|
|
for (i = 0; i < orphan_blocks; i++) {
|
|
struct page *page = f2fs_get_meta_page(sbi, start_blk + i);
|
|
struct f2fs_orphan_block *orphan_blk;
|
|
|
|
orphan_blk = (struct f2fs_orphan_block *)page_address(page);
|
|
for (j = 0; j < le32_to_cpu(orphan_blk->entry_count); j++) {
|
|
nid_t ino = le32_to_cpu(orphan_blk->ino[j]);
|
|
err = recover_orphan_inode(sbi, ino);
|
|
if (err) {
|
|
f2fs_put_page(page, 1);
|
|
goto out;
|
|
}
|
|
}
|
|
f2fs_put_page(page, 1);
|
|
}
|
|
/* clear Orphan Flag */
|
|
clear_ckpt_flags(sbi, CP_ORPHAN_PRESENT_FLAG);
|
|
out:
|
|
#ifdef CONFIG_QUOTA
|
|
/* Turn quotas off */
|
|
if (quota_enabled)
|
|
f2fs_quota_off_umount(sbi->sb);
|
|
#endif
|
|
sbi->sb->s_flags = s_flags; /* Restore SB_RDONLY status */
|
|
|
|
return err;
|
|
}
|
|
|
|
static void write_orphan_inodes(struct f2fs_sb_info *sbi, block_t start_blk)
|
|
{
|
|
struct list_head *head;
|
|
struct f2fs_orphan_block *orphan_blk = NULL;
|
|
unsigned int nentries = 0;
|
|
unsigned short index = 1;
|
|
unsigned short orphan_blocks;
|
|
struct page *page = NULL;
|
|
struct ino_entry *orphan = NULL;
|
|
struct inode_management *im = &sbi->im[ORPHAN_INO];
|
|
|
|
orphan_blocks = GET_ORPHAN_BLOCKS(im->ino_num);
|
|
|
|
/*
|
|
* we don't need to do spin_lock(&im->ino_lock) here, since all the
|
|
* orphan inode operations are covered under f2fs_lock_op().
|
|
* And, spin_lock should be avoided due to page operations below.
|
|
*/
|
|
head = &im->ino_list;
|
|
|
|
/* loop for each orphan inode entry and write them in Jornal block */
|
|
list_for_each_entry(orphan, head, list) {
|
|
if (!page) {
|
|
page = f2fs_grab_meta_page(sbi, start_blk++);
|
|
orphan_blk =
|
|
(struct f2fs_orphan_block *)page_address(page);
|
|
memset(orphan_blk, 0, sizeof(*orphan_blk));
|
|
}
|
|
|
|
orphan_blk->ino[nentries++] = cpu_to_le32(orphan->ino);
|
|
|
|
if (nentries == F2FS_ORPHANS_PER_BLOCK) {
|
|
/*
|
|
* an orphan block is full of 1020 entries,
|
|
* then we need to flush current orphan blocks
|
|
* and bring another one in memory
|
|
*/
|
|
orphan_blk->blk_addr = cpu_to_le16(index);
|
|
orphan_blk->blk_count = cpu_to_le16(orphan_blocks);
|
|
orphan_blk->entry_count = cpu_to_le32(nentries);
|
|
set_page_dirty(page);
|
|
f2fs_put_page(page, 1);
|
|
index++;
|
|
nentries = 0;
|
|
page = NULL;
|
|
}
|
|
}
|
|
|
|
if (page) {
|
|
orphan_blk->blk_addr = cpu_to_le16(index);
|
|
orphan_blk->blk_count = cpu_to_le16(orphan_blocks);
|
|
orphan_blk->entry_count = cpu_to_le32(nentries);
|
|
set_page_dirty(page);
|
|
f2fs_put_page(page, 1);
|
|
}
|
|
}
|
|
|
|
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;
|
|
|
|
*cp_page = f2fs_get_meta_page(sbi, 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))) {
|
|
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)) {
|
|
f2fs_msg(sbi->sb, KERN_WARNING, "invalid crc value");
|
|
return -EINVAL;
|
|
}
|
|
|
|
*version = cur_cp_version(*cp_block);
|
|
return 0;
|
|
}
|
|
|
|
static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
|
|
block_t cp_addr, unsigned long long *version)
|
|
{
|
|
struct page *cp_page_1 = NULL, *cp_page_2 = NULL;
|
|
struct f2fs_checkpoint *cp_block = NULL;
|
|
unsigned long long cur_version = 0, pre_version = 0;
|
|
int err;
|
|
|
|
err = get_checkpoint_version(sbi, cp_addr, &cp_block,
|
|
&cp_page_1, version);
|
|
if (err)
|
|
goto invalid_cp1;
|
|
|
|
if (le32_to_cpu(cp_block->cp_pack_total_block_count) >
|
|
sbi->blocks_per_seg) {
|
|
f2fs_msg(sbi->sb, KERN_WARNING,
|
|
"invalid cp_pack_total_block_count:%u",
|
|
le32_to_cpu(cp_block->cp_pack_total_block_count));
|
|
goto invalid_cp1;
|
|
}
|
|
pre_version = *version;
|
|
|
|
cp_addr += le32_to_cpu(cp_block->cp_pack_total_block_count) - 1;
|
|
err = get_checkpoint_version(sbi, cp_addr, &cp_block,
|
|
&cp_page_2, version);
|
|
if (err)
|
|
goto invalid_cp2;
|
|
cur_version = *version;
|
|
|
|
if (cur_version == pre_version) {
|
|
*version = cur_version;
|
|
f2fs_put_page(cp_page_2, 1);
|
|
return cp_page_1;
|
|
}
|
|
invalid_cp2:
|
|
f2fs_put_page(cp_page_2, 1);
|
|
invalid_cp1:
|
|
f2fs_put_page(cp_page_1, 1);
|
|
return NULL;
|
|
}
|
|
|
|
int f2fs_get_valid_checkpoint(struct f2fs_sb_info *sbi)
|
|
{
|
|
struct f2fs_checkpoint *cp_block;
|
|
struct f2fs_super_block *fsb = sbi->raw_super;
|
|
struct page *cp1, *cp2, *cur_page;
|
|
unsigned long blk_size = sbi->blocksize;
|
|
unsigned long long cp1_version = 0, cp2_version = 0;
|
|
unsigned long long cp_start_blk_no;
|
|
unsigned int cp_blks = 1 + __cp_payload(sbi);
|
|
block_t cp_blk_no;
|
|
int i;
|
|
|
|
sbi->ckpt = f2fs_kzalloc(sbi, array_size(blk_size, cp_blks),
|
|
GFP_KERNEL);
|
|
if (!sbi->ckpt)
|
|
return -ENOMEM;
|
|
/*
|
|
* Finding out valid cp block involves read both
|
|
* sets( cp pack1 and cp pack 2)
|
|
*/
|
|
cp_start_blk_no = le32_to_cpu(fsb->cp_blkaddr);
|
|
cp1 = validate_checkpoint(sbi, cp_start_blk_no, &cp1_version);
|
|
|
|
/* The second checkpoint pack should start at the next segment */
|
|
cp_start_blk_no += ((unsigned long long)1) <<
|
|
le32_to_cpu(fsb->log_blocks_per_seg);
|
|
cp2 = validate_checkpoint(sbi, cp_start_blk_no, &cp2_version);
|
|
|
|
if (cp1 && cp2) {
|
|
if (ver_after(cp2_version, cp1_version))
|
|
cur_page = cp2;
|
|
else
|
|
cur_page = cp1;
|
|
} else if (cp1) {
|
|
cur_page = cp1;
|
|
} else if (cp2) {
|
|
cur_page = cp2;
|
|
} else {
|
|
goto fail_no_cp;
|
|
}
|
|
|
|
cp_block = (struct f2fs_checkpoint *)page_address(cur_page);
|
|
memcpy(sbi->ckpt, cp_block, blk_size);
|
|
|
|
/* Sanity checking of checkpoint */
|
|
if (f2fs_sanity_check_ckpt(sbi))
|
|
goto free_fail_no_cp;
|
|
|
|
if (cur_page == cp1)
|
|
sbi->cur_cp_pack = 1;
|
|
else
|
|
sbi->cur_cp_pack = 2;
|
|
|
|
if (cp_blks <= 1)
|
|
goto done;
|
|
|
|
cp_blk_no = le32_to_cpu(fsb->cp_blkaddr);
|
|
if (cur_page == cp2)
|
|
cp_blk_no += 1 << le32_to_cpu(fsb->log_blocks_per_seg);
|
|
|
|
for (i = 1; i < cp_blks; i++) {
|
|
void *sit_bitmap_ptr;
|
|
unsigned char *ckpt = (unsigned char *)sbi->ckpt;
|
|
|
|
cur_page = f2fs_get_meta_page(sbi, cp_blk_no + i);
|
|
sit_bitmap_ptr = page_address(cur_page);
|
|
memcpy(ckpt + i * blk_size, sit_bitmap_ptr, blk_size);
|
|
f2fs_put_page(cur_page, 1);
|
|
}
|
|
done:
|
|
f2fs_put_page(cp1, 1);
|
|
f2fs_put_page(cp2, 1);
|
|
return 0;
|
|
|
|
free_fail_no_cp:
|
|
f2fs_put_page(cp1, 1);
|
|
f2fs_put_page(cp2, 1);
|
|
fail_no_cp:
|
|
kfree(sbi->ckpt);
|
|
return -EINVAL;
|
|
}
|
|
|
|
static void __add_dirty_inode(struct inode *inode, enum inode_type type)
|
|
{
|
|
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
|
|
int flag = (type == DIR_INODE) ? FI_DIRTY_DIR : FI_DIRTY_FILE;
|
|
|
|
if (is_inode_flag_set(inode, flag))
|
|
return;
|
|
|
|
set_inode_flag(inode, flag);
|
|
if (!f2fs_is_volatile_file(inode))
|
|
list_add_tail(&F2FS_I(inode)->dirty_list,
|
|
&sbi->inode_list[type]);
|
|
stat_inc_dirty_inode(sbi, type);
|
|
}
|
|
|
|
static void __remove_dirty_inode(struct inode *inode, enum inode_type type)
|
|
{
|
|
int flag = (type == DIR_INODE) ? FI_DIRTY_DIR : FI_DIRTY_FILE;
|
|
|
|
if (get_dirty_pages(inode) || !is_inode_flag_set(inode, flag))
|
|
return;
|
|
|
|
list_del_init(&F2FS_I(inode)->dirty_list);
|
|
clear_inode_flag(inode, flag);
|
|
stat_dec_dirty_inode(F2FS_I_SB(inode), type);
|
|
}
|
|
|
|
void f2fs_update_dirty_page(struct inode *inode, struct page *page)
|
|
{
|
|
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
|
|
enum inode_type type = S_ISDIR(inode->i_mode) ? DIR_INODE : FILE_INODE;
|
|
|
|
if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode) &&
|
|
!S_ISLNK(inode->i_mode))
|
|
return;
|
|
|
|
spin_lock(&sbi->inode_lock[type]);
|
|
if (type != FILE_INODE || test_opt(sbi, DATA_FLUSH))
|
|
__add_dirty_inode(inode, type);
|
|
inode_inc_dirty_pages(inode);
|
|
spin_unlock(&sbi->inode_lock[type]);
|
|
|
|
SetPagePrivate(page);
|
|
f2fs_trace_pid(page);
|
|
}
|
|
|
|
void f2fs_remove_dirty_inode(struct inode *inode)
|
|
{
|
|
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
|
|
enum inode_type type = S_ISDIR(inode->i_mode) ? DIR_INODE : FILE_INODE;
|
|
|
|
if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode) &&
|
|
!S_ISLNK(inode->i_mode))
|
|
return;
|
|
|
|
if (type == FILE_INODE && !test_opt(sbi, DATA_FLUSH))
|
|
return;
|
|
|
|
spin_lock(&sbi->inode_lock[type]);
|
|
__remove_dirty_inode(inode, type);
|
|
spin_unlock(&sbi->inode_lock[type]);
|
|
}
|
|
|
|
int f2fs_sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type)
|
|
{
|
|
struct list_head *head;
|
|
struct inode *inode;
|
|
struct f2fs_inode_info *fi;
|
|
bool is_dir = (type == DIR_INODE);
|
|
unsigned long ino = 0;
|
|
|
|
trace_f2fs_sync_dirty_inodes_enter(sbi->sb, is_dir,
|
|
get_pages(sbi, is_dir ?
|
|
F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA));
|
|
retry:
|
|
if (unlikely(f2fs_cp_error(sbi)))
|
|
return -EIO;
|
|
|
|
spin_lock(&sbi->inode_lock[type]);
|
|
|
|
head = &sbi->inode_list[type];
|
|
if (list_empty(head)) {
|
|
spin_unlock(&sbi->inode_lock[type]);
|
|
trace_f2fs_sync_dirty_inodes_exit(sbi->sb, is_dir,
|
|
get_pages(sbi, is_dir ?
|
|
F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA));
|
|
return 0;
|
|
}
|
|
fi = list_first_entry(head, struct f2fs_inode_info, dirty_list);
|
|
inode = igrab(&fi->vfs_inode);
|
|
spin_unlock(&sbi->inode_lock[type]);
|
|
if (inode) {
|
|
unsigned long cur_ino = inode->i_ino;
|
|
|
|
if (is_dir)
|
|
F2FS_I(inode)->cp_task = current;
|
|
|
|
filemap_fdatawrite(inode->i_mapping);
|
|
|
|
if (is_dir)
|
|
F2FS_I(inode)->cp_task = NULL;
|
|
|
|
iput(inode);
|
|
/* We need to give cpu to another writers. */
|
|
if (ino == cur_ino)
|
|
cond_resched();
|
|
else
|
|
ino = cur_ino;
|
|
} else {
|
|
/*
|
|
* We should submit bio, since it exists several
|
|
* wribacking dentry pages in the freeing inode.
|
|
*/
|
|
f2fs_submit_merged_write(sbi, DATA);
|
|
cond_resched();
|
|
}
|
|
goto retry;
|
|
}
|
|
|
|
int f2fs_sync_inode_meta(struct f2fs_sb_info *sbi)
|
|
{
|
|
struct list_head *head = &sbi->inode_list[DIRTY_META];
|
|
struct inode *inode;
|
|
struct f2fs_inode_info *fi;
|
|
s64 total = get_pages(sbi, F2FS_DIRTY_IMETA);
|
|
|
|
while (total--) {
|
|
if (unlikely(f2fs_cp_error(sbi)))
|
|
return -EIO;
|
|
|
|
spin_lock(&sbi->inode_lock[DIRTY_META]);
|
|
if (list_empty(head)) {
|
|
spin_unlock(&sbi->inode_lock[DIRTY_META]);
|
|
return 0;
|
|
}
|
|
fi = list_first_entry(head, struct f2fs_inode_info,
|
|
gdirty_list);
|
|
inode = igrab(&fi->vfs_inode);
|
|
spin_unlock(&sbi->inode_lock[DIRTY_META]);
|
|
if (inode) {
|
|
sync_inode_metadata(inode, 0);
|
|
|
|
/* it's on eviction */
|
|
if (is_inode_flag_set(inode, FI_DIRTY_INODE))
|
|
f2fs_update_inode_page(inode);
|
|
iput(inode);
|
|
}
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
static void __prepare_cp_block(struct f2fs_sb_info *sbi)
|
|
{
|
|
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
|
|
struct f2fs_nm_info *nm_i = NM_I(sbi);
|
|
nid_t last_nid = nm_i->next_scan_nid;
|
|
|
|
next_free_nid(sbi, &last_nid);
|
|
ckpt->valid_block_count = cpu_to_le64(valid_user_blocks(sbi));
|
|
ckpt->valid_node_count = cpu_to_le32(valid_node_count(sbi));
|
|
ckpt->valid_inode_count = cpu_to_le32(valid_inode_count(sbi));
|
|
ckpt->next_free_nid = cpu_to_le32(last_nid);
|
|
}
|
|
|
|
/*
|
|
* Freeze all the FS-operations for checkpoint.
|
|
*/
|
|
static int block_operations(struct f2fs_sb_info *sbi)
|
|
{
|
|
struct writeback_control wbc = {
|
|
.sync_mode = WB_SYNC_ALL,
|
|
.nr_to_write = LONG_MAX,
|
|
.for_reclaim = 0,
|
|
};
|
|
struct blk_plug plug;
|
|
int err = 0;
|
|
|
|
blk_start_plug(&plug);
|
|
|
|
retry_flush_dents:
|
|
f2fs_lock_all(sbi);
|
|
/* write all the dirty dentry pages */
|
|
if (get_pages(sbi, F2FS_DIRTY_DENTS)) {
|
|
f2fs_unlock_all(sbi);
|
|
err = f2fs_sync_dirty_inodes(sbi, DIR_INODE);
|
|
if (err)
|
|
goto out;
|
|
cond_resched();
|
|
goto retry_flush_dents;
|
|
}
|
|
|
|
/*
|
|
* POR: we should ensure that there are no dirty node pages
|
|
* until finishing nat/sit flush. inode->i_blocks can be updated.
|
|
*/
|
|
down_write(&sbi->node_change);
|
|
|
|
if (get_pages(sbi, F2FS_DIRTY_IMETA)) {
|
|
up_write(&sbi->node_change);
|
|
f2fs_unlock_all(sbi);
|
|
err = f2fs_sync_inode_meta(sbi);
|
|
if (err)
|
|
goto out;
|
|
cond_resched();
|
|
goto retry_flush_dents;
|
|
}
|
|
|
|
retry_flush_nodes:
|
|
down_write(&sbi->node_write);
|
|
|
|
if (get_pages(sbi, F2FS_DIRTY_NODES)) {
|
|
up_write(&sbi->node_write);
|
|
atomic_inc(&sbi->wb_sync_req[NODE]);
|
|
err = f2fs_sync_node_pages(sbi, &wbc, false, FS_CP_NODE_IO);
|
|
atomic_dec(&sbi->wb_sync_req[NODE]);
|
|
if (err) {
|
|
up_write(&sbi->node_change);
|
|
f2fs_unlock_all(sbi);
|
|
goto out;
|
|
}
|
|
cond_resched();
|
|
goto retry_flush_nodes;
|
|
}
|
|
|
|
/*
|
|
* sbi->node_change is used only for AIO write_begin path which produces
|
|
* dirty node blocks and some checkpoint values by block allocation.
|
|
*/
|
|
__prepare_cp_block(sbi);
|
|
up_write(&sbi->node_change);
|
|
out:
|
|
blk_finish_plug(&plug);
|
|
return err;
|
|
}
|
|
|
|
static void unblock_operations(struct f2fs_sb_info *sbi)
|
|
{
|
|
up_write(&sbi->node_write);
|
|
f2fs_unlock_all(sbi);
|
|
}
|
|
|
|
static void wait_on_all_pages_writeback(struct f2fs_sb_info *sbi)
|
|
{
|
|
DEFINE_WAIT(wait);
|
|
|
|
for (;;) {
|
|
prepare_to_wait(&sbi->cp_wait, &wait, TASK_UNINTERRUPTIBLE);
|
|
|
|
if (!get_pages(sbi, F2FS_WB_CP_DATA))
|
|
break;
|
|
|
|
if (unlikely(f2fs_cp_error(sbi)))
|
|
break;
|
|
|
|
io_schedule_timeout(5*HZ);
|
|
}
|
|
finish_wait(&sbi->cp_wait, &wait);
|
|
}
|
|
|
|
static void update_ckpt_flags(struct f2fs_sb_info *sbi, struct cp_control *cpc)
|
|
{
|
|
unsigned long orphan_num = sbi->im[ORPHAN_INO].ino_num;
|
|
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
|
|
unsigned long flags;
|
|
|
|
spin_lock_irqsave(&sbi->cp_lock, flags);
|
|
|
|
if ((cpc->reason & CP_UMOUNT) &&
|
|
le32_to_cpu(ckpt->cp_pack_total_block_count) >
|
|
sbi->blocks_per_seg - NM_I(sbi)->nat_bits_blocks)
|
|
disable_nat_bits(sbi, false);
|
|
|
|
if (cpc->reason & CP_TRIMMED)
|
|
__set_ckpt_flags(ckpt, CP_TRIMMED_FLAG);
|
|
else
|
|
__clear_ckpt_flags(ckpt, CP_TRIMMED_FLAG);
|
|
|
|
if (cpc->reason & CP_UMOUNT)
|
|
__set_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
|
|
else
|
|
__clear_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
|
|
|
|
if (cpc->reason & CP_FASTBOOT)
|
|
__set_ckpt_flags(ckpt, CP_FASTBOOT_FLAG);
|
|
else
|
|
__clear_ckpt_flags(ckpt, CP_FASTBOOT_FLAG);
|
|
|
|
if (orphan_num)
|
|
__set_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG);
|
|
else
|
|
__clear_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG);
|
|
|
|
if (is_sbi_flag_set(sbi, SBI_NEED_FSCK))
|
|
__set_ckpt_flags(ckpt, CP_FSCK_FLAG);
|
|
|
|
/* set this flag to activate crc|cp_ver for recovery */
|
|
__set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG);
|
|
__clear_ckpt_flags(ckpt, CP_NOCRC_RECOVERY_FLAG);
|
|
|
|
spin_unlock_irqrestore(&sbi->cp_lock, flags);
|
|
}
|
|
|
|
static void commit_checkpoint(struct f2fs_sb_info *sbi,
|
|
void *src, block_t blk_addr)
|
|
{
|
|
struct writeback_control wbc = {
|
|
.for_reclaim = 0,
|
|
};
|
|
|
|
/*
|
|
* pagevec_lookup_tag and lock_page again will take
|
|
* some extra time. Therefore, f2fs_update_meta_pages and
|
|
* f2fs_sync_meta_pages are combined in this function.
|
|
*/
|
|
struct page *page = f2fs_grab_meta_page(sbi, blk_addr);
|
|
int err;
|
|
|
|
memcpy(page_address(page), src, PAGE_SIZE);
|
|
set_page_dirty(page);
|
|
|
|
f2fs_wait_on_page_writeback(page, META, true);
|
|
f2fs_bug_on(sbi, PageWriteback(page));
|
|
if (unlikely(!clear_page_dirty_for_io(page)))
|
|
f2fs_bug_on(sbi, 1);
|
|
|
|
/* writeout cp pack 2 page */
|
|
err = __f2fs_write_meta_page(page, &wbc, FS_CP_META_IO);
|
|
if (unlikely(err && f2fs_cp_error(sbi))) {
|
|
f2fs_put_page(page, 1);
|
|
return;
|
|
}
|
|
|
|
f2fs_bug_on(sbi, err);
|
|
f2fs_put_page(page, 0);
|
|
|
|
/* submit checkpoint (with barrier if NOBARRIER is not set) */
|
|
f2fs_submit_merged_write(sbi, META_FLUSH);
|
|
}
|
|
|
|
static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
|
|
{
|
|
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
|
|
struct f2fs_nm_info *nm_i = NM_I(sbi);
|
|
unsigned long orphan_num = sbi->im[ORPHAN_INO].ino_num, flags;
|
|
block_t start_blk;
|
|
unsigned int data_sum_blocks, orphan_blocks;
|
|
__u32 crc32 = 0;
|
|
int i;
|
|
int cp_payload_blks = __cp_payload(sbi);
|
|
struct super_block *sb = sbi->sb;
|
|
struct curseg_info *seg_i = CURSEG_I(sbi, CURSEG_HOT_NODE);
|
|
u64 kbytes_written;
|
|
int err;
|
|
|
|
/* Flush all the NAT/SIT pages */
|
|
while (get_pages(sbi, F2FS_DIRTY_META)) {
|
|
f2fs_sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO);
|
|
if (unlikely(f2fs_cp_error(sbi)))
|
|
break;
|
|
}
|
|
|
|
/*
|
|
* modify checkpoint
|
|
* version number is already updated
|
|
*/
|
|
ckpt->elapsed_time = cpu_to_le64(get_mtime(sbi, true));
|
|
ckpt->free_segment_count = cpu_to_le32(free_segments(sbi));
|
|
for (i = 0; i < NR_CURSEG_NODE_TYPE; i++) {
|
|
ckpt->cur_node_segno[i] =
|
|
cpu_to_le32(curseg_segno(sbi, i + CURSEG_HOT_NODE));
|
|
ckpt->cur_node_blkoff[i] =
|
|
cpu_to_le16(curseg_blkoff(sbi, i + CURSEG_HOT_NODE));
|
|
ckpt->alloc_type[i + CURSEG_HOT_NODE] =
|
|
curseg_alloc_type(sbi, i + CURSEG_HOT_NODE);
|
|
}
|
|
for (i = 0; i < NR_CURSEG_DATA_TYPE; i++) {
|
|
ckpt->cur_data_segno[i] =
|
|
cpu_to_le32(curseg_segno(sbi, i + CURSEG_HOT_DATA));
|
|
ckpt->cur_data_blkoff[i] =
|
|
cpu_to_le16(curseg_blkoff(sbi, i + CURSEG_HOT_DATA));
|
|
ckpt->alloc_type[i + CURSEG_HOT_DATA] =
|
|
curseg_alloc_type(sbi, i + CURSEG_HOT_DATA);
|
|
}
|
|
|
|
/* 2 cp + n data seg summary + orphan inode blocks */
|
|
data_sum_blocks = f2fs_npages_for_summary_flush(sbi, false);
|
|
spin_lock_irqsave(&sbi->cp_lock, flags);
|
|
if (data_sum_blocks < NR_CURSEG_DATA_TYPE)
|
|
__set_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG);
|
|
else
|
|
__clear_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG);
|
|
spin_unlock_irqrestore(&sbi->cp_lock, flags);
|
|
|
|
orphan_blocks = GET_ORPHAN_BLOCKS(orphan_num);
|
|
ckpt->cp_pack_start_sum = cpu_to_le32(1 + cp_payload_blks +
|
|
orphan_blocks);
|
|
|
|
if (__remain_node_summaries(cpc->reason))
|
|
ckpt->cp_pack_total_block_count = cpu_to_le32(F2FS_CP_PACKS+
|
|
cp_payload_blks + data_sum_blocks +
|
|
orphan_blocks + NR_CURSEG_NODE_TYPE);
|
|
else
|
|
ckpt->cp_pack_total_block_count = cpu_to_le32(F2FS_CP_PACKS +
|
|
cp_payload_blks + data_sum_blocks +
|
|
orphan_blocks);
|
|
|
|
/* update ckpt flag for checkpoint */
|
|
update_ckpt_flags(sbi, cpc);
|
|
|
|
/* update SIT/NAT bitmap */
|
|
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));
|
|
*((__le32 *)((unsigned char *)ckpt +
|
|
le32_to_cpu(ckpt->checksum_offset)))
|
|
= cpu_to_le32(crc32);
|
|
|
|
start_blk = __start_cp_next_addr(sbi);
|
|
|
|
/* write nat bits */
|
|
if (enabled_nat_bits(sbi, cpc)) {
|
|
__u64 cp_ver = cur_cp_version(ckpt);
|
|
block_t blk;
|
|
|
|
cp_ver |= ((__u64)crc32 << 32);
|
|
*(__le64 *)nm_i->nat_bits = cpu_to_le64(cp_ver);
|
|
|
|
blk = start_blk + sbi->blocks_per_seg - nm_i->nat_bits_blocks;
|
|
for (i = 0; i < nm_i->nat_bits_blocks; i++)
|
|
f2fs_update_meta_page(sbi, nm_i->nat_bits +
|
|
(i << F2FS_BLKSIZE_BITS), blk + i);
|
|
|
|
/* Flush all the NAT BITS pages */
|
|
while (get_pages(sbi, F2FS_DIRTY_META)) {
|
|
f2fs_sync_meta_pages(sbi, META, LONG_MAX,
|
|
FS_CP_META_IO);
|
|
if (unlikely(f2fs_cp_error(sbi)))
|
|
break;
|
|
}
|
|
}
|
|
|
|
/* write out checkpoint buffer at block 0 */
|
|
f2fs_update_meta_page(sbi, ckpt, start_blk++);
|
|
|
|
for (i = 1; i < 1 + cp_payload_blks; i++)
|
|
f2fs_update_meta_page(sbi, (char *)ckpt + i * F2FS_BLKSIZE,
|
|
start_blk++);
|
|
|
|
if (orphan_num) {
|
|
write_orphan_inodes(sbi, start_blk);
|
|
start_blk += orphan_blocks;
|
|
}
|
|
|
|
f2fs_write_data_summaries(sbi, start_blk);
|
|
start_blk += data_sum_blocks;
|
|
|
|
/* Record write statistics in the hot node summary */
|
|
kbytes_written = sbi->kbytes_written;
|
|
if (sb->s_bdev->bd_part)
|
|
kbytes_written += BD_PART_WRITTEN(sbi);
|
|
|
|
seg_i->journal->info.kbytes_written = cpu_to_le64(kbytes_written);
|
|
|
|
if (__remain_node_summaries(cpc->reason)) {
|
|
f2fs_write_node_summaries(sbi, start_blk);
|
|
start_blk += NR_CURSEG_NODE_TYPE;
|
|
}
|
|
|
|
/* update user_block_counts */
|
|
sbi->last_valid_block_count = sbi->total_valid_block_count;
|
|
percpu_counter_set(&sbi->alloc_valid_block_count, 0);
|
|
|
|
/* Here, we have one bio having CP pack except cp pack 2 page */
|
|
f2fs_sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO);
|
|
|
|
/* wait for previous submitted meta pages writeback */
|
|
wait_on_all_pages_writeback(sbi);
|
|
|
|
/* flush all device cache */
|
|
err = f2fs_flush_device_cache(sbi);
|
|
if (err)
|
|
return err;
|
|
|
|
/* barrier and flush checkpoint cp pack 2 page if it can */
|
|
commit_checkpoint(sbi, ckpt, start_blk);
|
|
wait_on_all_pages_writeback(sbi);
|
|
|
|
f2fs_release_ino_entry(sbi, false);
|
|
|
|
clear_sbi_flag(sbi, SBI_IS_DIRTY);
|
|
clear_sbi_flag(sbi, SBI_NEED_CP);
|
|
__set_cp_next_pack(sbi);
|
|
|
|
/*
|
|
* redirty superblock if metadata like node page or inode cache is
|
|
* updated during writing checkpoint.
|
|
*/
|
|
if (get_pages(sbi, F2FS_DIRTY_NODES) ||
|
|
get_pages(sbi, F2FS_DIRTY_IMETA))
|
|
set_sbi_flag(sbi, SBI_IS_DIRTY);
|
|
|
|
f2fs_bug_on(sbi, get_pages(sbi, F2FS_DIRTY_DENTS));
|
|
|
|
return unlikely(f2fs_cp_error(sbi)) ? -EIO : 0;
|
|
}
|
|
|
|
/*
|
|
* We guarantee that this checkpoint procedure will not fail.
|
|
*/
|
|
int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
|
|
{
|
|
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
|
|
unsigned long long ckpt_ver;
|
|
int err = 0;
|
|
|
|
mutex_lock(&sbi->cp_mutex);
|
|
|
|
if (!is_sbi_flag_set(sbi, SBI_IS_DIRTY) &&
|
|
((cpc->reason & CP_FASTBOOT) || (cpc->reason & CP_SYNC) ||
|
|
((cpc->reason & CP_DISCARD) && !sbi->discard_blks)))
|
|
goto out;
|
|
if (unlikely(f2fs_cp_error(sbi))) {
|
|
err = -EIO;
|
|
goto out;
|
|
}
|
|
if (f2fs_readonly(sbi->sb)) {
|
|
err = -EROFS;
|
|
goto out;
|
|
}
|
|
|
|
trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "start block_ops");
|
|
|
|
err = block_operations(sbi);
|
|
if (err)
|
|
goto out;
|
|
|
|
trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish block_ops");
|
|
|
|
f2fs_flush_merged_writes(sbi);
|
|
|
|
/* this is the case of multiple fstrims without any changes */
|
|
if (cpc->reason & CP_DISCARD) {
|
|
if (!f2fs_exist_trim_candidates(sbi, cpc)) {
|
|
unblock_operations(sbi);
|
|
goto out;
|
|
}
|
|
|
|
if (NM_I(sbi)->dirty_nat_cnt == 0 &&
|
|
SIT_I(sbi)->dirty_sentries == 0 &&
|
|
prefree_segments(sbi) == 0) {
|
|
f2fs_flush_sit_entries(sbi, cpc);
|
|
f2fs_clear_prefree_segments(sbi, cpc);
|
|
unblock_operations(sbi);
|
|
goto out;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* update checkpoint pack index
|
|
* Increase the version number so that
|
|
* SIT entries and seg summaries are written at correct place
|
|
*/
|
|
ckpt_ver = cur_cp_version(ckpt);
|
|
ckpt->checkpoint_ver = cpu_to_le64(++ckpt_ver);
|
|
|
|
/* write cached NAT/SIT entries to NAT/SIT area */
|
|
f2fs_flush_nat_entries(sbi, cpc);
|
|
f2fs_flush_sit_entries(sbi, cpc);
|
|
|
|
/* unlock all the fs_lock[] in do_checkpoint() */
|
|
err = do_checkpoint(sbi, cpc);
|
|
if (err)
|
|
f2fs_release_discard_addrs(sbi);
|
|
else
|
|
f2fs_clear_prefree_segments(sbi, cpc);
|
|
|
|
unblock_operations(sbi);
|
|
stat_inc_cp_count(sbi->stat_info);
|
|
|
|
if (cpc->reason & CP_RECOVERY)
|
|
f2fs_msg(sbi->sb, KERN_NOTICE,
|
|
"checkpoint: version = %llx", ckpt_ver);
|
|
|
|
/* do checkpoint periodically */
|
|
f2fs_update_time(sbi, CP_TIME);
|
|
trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish checkpoint");
|
|
out:
|
|
mutex_unlock(&sbi->cp_mutex);
|
|
return err;
|
|
}
|
|
|
|
void f2fs_init_ino_entry_info(struct f2fs_sb_info *sbi)
|
|
{
|
|
int i;
|
|
|
|
for (i = 0; i < MAX_INO_ENTRY; i++) {
|
|
struct inode_management *im = &sbi->im[i];
|
|
|
|
INIT_RADIX_TREE(&im->ino_root, GFP_ATOMIC);
|
|
spin_lock_init(&im->ino_lock);
|
|
INIT_LIST_HEAD(&im->ino_list);
|
|
im->ino_num = 0;
|
|
}
|
|
|
|
sbi->max_orphans = (sbi->blocks_per_seg - F2FS_CP_PACKS -
|
|
NR_CURSEG_TYPE - __cp_payload(sbi)) *
|
|
F2FS_ORPHANS_PER_BLOCK;
|
|
}
|
|
|
|
int __init f2fs_create_checkpoint_caches(void)
|
|
{
|
|
ino_entry_slab = f2fs_kmem_cache_create("f2fs_ino_entry",
|
|
sizeof(struct ino_entry));
|
|
if (!ino_entry_slab)
|
|
return -ENOMEM;
|
|
f2fs_inode_entry_slab = f2fs_kmem_cache_create("f2fs_inode_entry",
|
|
sizeof(struct inode_entry));
|
|
if (!f2fs_inode_entry_slab) {
|
|
kmem_cache_destroy(ino_entry_slab);
|
|
return -ENOMEM;
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
void f2fs_destroy_checkpoint_caches(void)
|
|
{
|
|
kmem_cache_destroy(ino_entry_slab);
|
|
kmem_cache_destroy(f2fs_inode_entry_slab);
|
|
}
|