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>
858 lines
26 KiB
C
858 lines
26 KiB
C
/*
|
|
* fs/f2fs/segment.h
|
|
*
|
|
* 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/blkdev.h>
|
|
#include <linux/backing-dev.h>
|
|
|
|
/* constant macro */
|
|
#define NULL_SEGNO ((unsigned int)(~0))
|
|
#define NULL_SECNO ((unsigned int)(~0))
|
|
|
|
#define DEF_RECLAIM_PREFREE_SEGMENTS 5 /* 5% over total segments */
|
|
#define DEF_MAX_RECLAIM_PREFREE_SEGMENTS 4096 /* 8GB in maximum */
|
|
|
|
#define F2FS_MIN_SEGMENTS 9 /* SB + 2 (CP + SIT + NAT) + SSA + MAIN */
|
|
|
|
/* L: Logical segment # in volume, R: Relative segment # in main area */
|
|
#define GET_L2R_SEGNO(free_i, segno) ((segno) - (free_i)->start_segno)
|
|
#define GET_R2L_SEGNO(free_i, segno) ((segno) + (free_i)->start_segno)
|
|
|
|
#define IS_DATASEG(t) ((t) <= CURSEG_COLD_DATA)
|
|
#define IS_NODESEG(t) ((t) >= CURSEG_HOT_NODE)
|
|
|
|
#define IS_HOT(t) ((t) == CURSEG_HOT_NODE || (t) == CURSEG_HOT_DATA)
|
|
#define IS_WARM(t) ((t) == CURSEG_WARM_NODE || (t) == CURSEG_WARM_DATA)
|
|
#define IS_COLD(t) ((t) == CURSEG_COLD_NODE || (t) == CURSEG_COLD_DATA)
|
|
|
|
#define IS_CURSEG(sbi, seg) \
|
|
(((seg) == CURSEG_I(sbi, CURSEG_HOT_DATA)->segno) || \
|
|
((seg) == CURSEG_I(sbi, CURSEG_WARM_DATA)->segno) || \
|
|
((seg) == CURSEG_I(sbi, CURSEG_COLD_DATA)->segno) || \
|
|
((seg) == CURSEG_I(sbi, CURSEG_HOT_NODE)->segno) || \
|
|
((seg) == CURSEG_I(sbi, CURSEG_WARM_NODE)->segno) || \
|
|
((seg) == CURSEG_I(sbi, CURSEG_COLD_NODE)->segno))
|
|
|
|
#define IS_CURSEC(sbi, secno) \
|
|
(((secno) == CURSEG_I(sbi, CURSEG_HOT_DATA)->segno / \
|
|
(sbi)->segs_per_sec) || \
|
|
((secno) == CURSEG_I(sbi, CURSEG_WARM_DATA)->segno / \
|
|
(sbi)->segs_per_sec) || \
|
|
((secno) == CURSEG_I(sbi, CURSEG_COLD_DATA)->segno / \
|
|
(sbi)->segs_per_sec) || \
|
|
((secno) == CURSEG_I(sbi, CURSEG_HOT_NODE)->segno / \
|
|
(sbi)->segs_per_sec) || \
|
|
((secno) == CURSEG_I(sbi, CURSEG_WARM_NODE)->segno / \
|
|
(sbi)->segs_per_sec) || \
|
|
((secno) == CURSEG_I(sbi, CURSEG_COLD_NODE)->segno / \
|
|
(sbi)->segs_per_sec)) \
|
|
|
|
#define MAIN_BLKADDR(sbi) \
|
|
(SM_I(sbi) ? SM_I(sbi)->main_blkaddr : \
|
|
le32_to_cpu(F2FS_RAW_SUPER(sbi)->main_blkaddr))
|
|
#define SEG0_BLKADDR(sbi) \
|
|
(SM_I(sbi) ? SM_I(sbi)->seg0_blkaddr : \
|
|
le32_to_cpu(F2FS_RAW_SUPER(sbi)->segment0_blkaddr))
|
|
|
|
#define MAIN_SEGS(sbi) (SM_I(sbi)->main_segments)
|
|
#define MAIN_SECS(sbi) ((sbi)->total_sections)
|
|
|
|
#define TOTAL_SEGS(sbi) \
|
|
(SM_I(sbi) ? SM_I(sbi)->segment_count : \
|
|
le32_to_cpu(F2FS_RAW_SUPER(sbi)->segment_count))
|
|
#define TOTAL_BLKS(sbi) (TOTAL_SEGS(sbi) << (sbi)->log_blocks_per_seg)
|
|
|
|
#define MAX_BLKADDR(sbi) (SEG0_BLKADDR(sbi) + TOTAL_BLKS(sbi))
|
|
#define SEGMENT_SIZE(sbi) (1ULL << ((sbi)->log_blocksize + \
|
|
(sbi)->log_blocks_per_seg))
|
|
|
|
#define START_BLOCK(sbi, segno) (SEG0_BLKADDR(sbi) + \
|
|
(GET_R2L_SEGNO(FREE_I(sbi), segno) << (sbi)->log_blocks_per_seg))
|
|
|
|
#define NEXT_FREE_BLKADDR(sbi, curseg) \
|
|
(START_BLOCK(sbi, (curseg)->segno) + (curseg)->next_blkoff)
|
|
|
|
#define GET_SEGOFF_FROM_SEG0(sbi, blk_addr) ((blk_addr) - SEG0_BLKADDR(sbi))
|
|
#define GET_SEGNO_FROM_SEG0(sbi, blk_addr) \
|
|
(GET_SEGOFF_FROM_SEG0(sbi, blk_addr) >> (sbi)->log_blocks_per_seg)
|
|
#define GET_BLKOFF_FROM_SEG0(sbi, blk_addr) \
|
|
(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)) ? \
|
|
NULL_SEGNO : GET_L2R_SEGNO(FREE_I(sbi), \
|
|
GET_SEGNO_FROM_SEG0(sbi, blk_addr)))
|
|
#define BLKS_PER_SEC(sbi) \
|
|
((sbi)->segs_per_sec * (sbi)->blocks_per_seg)
|
|
#define GET_SEC_FROM_SEG(sbi, segno) \
|
|
((segno) / (sbi)->segs_per_sec)
|
|
#define GET_SEG_FROM_SEC(sbi, secno) \
|
|
((secno) * (sbi)->segs_per_sec)
|
|
#define GET_ZONE_FROM_SEC(sbi, secno) \
|
|
((secno) / (sbi)->secs_per_zone)
|
|
#define GET_ZONE_FROM_SEG(sbi, segno) \
|
|
GET_ZONE_FROM_SEC(sbi, GET_SEC_FROM_SEG(sbi, segno))
|
|
|
|
#define GET_SUM_BLOCK(sbi, segno) \
|
|
((sbi)->sm_info->ssa_blkaddr + (segno))
|
|
|
|
#define GET_SUM_TYPE(footer) ((footer)->entry_type)
|
|
#define SET_SUM_TYPE(footer, type) ((footer)->entry_type = (type))
|
|
|
|
#define SIT_ENTRY_OFFSET(sit_i, segno) \
|
|
((segno) % (sit_i)->sents_per_block)
|
|
#define SIT_BLOCK_OFFSET(segno) \
|
|
((segno) / SIT_ENTRY_PER_BLOCK)
|
|
#define START_SEGNO(segno) \
|
|
(SIT_BLOCK_OFFSET(segno) * SIT_ENTRY_PER_BLOCK)
|
|
#define SIT_BLK_CNT(sbi) \
|
|
((MAIN_SEGS(sbi) + SIT_ENTRY_PER_BLOCK - 1) / SIT_ENTRY_PER_BLOCK)
|
|
#define f2fs_bitmap_size(nr) \
|
|
(BITS_TO_LONGS(nr) * sizeof(unsigned long))
|
|
|
|
#define SECTOR_FROM_BLOCK(blk_addr) \
|
|
(((sector_t)blk_addr) << F2FS_LOG_SECTORS_PER_BLOCK)
|
|
#define SECTOR_TO_BLOCK(sectors) \
|
|
((sectors) >> F2FS_LOG_SECTORS_PER_BLOCK)
|
|
|
|
/*
|
|
* indicate a block allocation direction: RIGHT and LEFT.
|
|
* RIGHT means allocating new sections towards the end of volume.
|
|
* LEFT means the opposite direction.
|
|
*/
|
|
enum {
|
|
ALLOC_RIGHT = 0,
|
|
ALLOC_LEFT
|
|
};
|
|
|
|
/*
|
|
* In the victim_sel_policy->alloc_mode, there are two block allocation modes.
|
|
* LFS writes data sequentially with cleaning operations.
|
|
* SSR (Slack Space Recycle) reuses obsolete space without cleaning operations.
|
|
*/
|
|
enum {
|
|
LFS = 0,
|
|
SSR
|
|
};
|
|
|
|
/*
|
|
* In the victim_sel_policy->gc_mode, there are two gc, aka cleaning, modes.
|
|
* GC_CB is based on cost-benefit algorithm.
|
|
* GC_GREEDY is based on greedy algorithm.
|
|
*/
|
|
enum {
|
|
GC_CB = 0,
|
|
GC_GREEDY,
|
|
ALLOC_NEXT,
|
|
FLUSH_DEVICE,
|
|
MAX_GC_POLICY,
|
|
};
|
|
|
|
/*
|
|
* BG_GC means the background cleaning job.
|
|
* FG_GC means the on-demand cleaning job.
|
|
* FORCE_FG_GC means on-demand cleaning job in background.
|
|
*/
|
|
enum {
|
|
BG_GC = 0,
|
|
FG_GC,
|
|
FORCE_FG_GC,
|
|
};
|
|
|
|
/* for a function parameter to select a victim segment */
|
|
struct victim_sel_policy {
|
|
int alloc_mode; /* LFS or SSR */
|
|
int gc_mode; /* GC_CB or GC_GREEDY */
|
|
unsigned long *dirty_segmap; /* dirty segment bitmap */
|
|
unsigned int max_search; /* maximum # of segments to search */
|
|
unsigned int offset; /* last scanned bitmap offset */
|
|
unsigned int ofs_unit; /* bitmap search unit */
|
|
unsigned int min_cost; /* minimum cost */
|
|
unsigned int min_segno; /* segment # having min. cost */
|
|
};
|
|
|
|
struct seg_entry {
|
|
unsigned int type:6; /* segment type like CURSEG_XXX_TYPE */
|
|
unsigned int valid_blocks:10; /* # of valid blocks */
|
|
unsigned int ckpt_valid_blocks:10; /* # of valid blocks last cp */
|
|
unsigned int padding:6; /* padding */
|
|
unsigned char *cur_valid_map; /* validity bitmap of blocks */
|
|
#ifdef CONFIG_F2FS_CHECK_FS
|
|
unsigned char *cur_valid_map_mir; /* mirror of current valid bitmap */
|
|
#endif
|
|
/*
|
|
* # of valid blocks and the validity bitmap stored in the the last
|
|
* checkpoint pack. This information is used by the SSR mode.
|
|
*/
|
|
unsigned char *ckpt_valid_map; /* validity bitmap of blocks last cp */
|
|
unsigned char *discard_map;
|
|
unsigned long long mtime; /* modification time of the segment */
|
|
};
|
|
|
|
struct sec_entry {
|
|
unsigned int valid_blocks; /* # of valid blocks in a section */
|
|
};
|
|
|
|
struct segment_allocation {
|
|
void (*allocate_segment)(struct f2fs_sb_info *, int, bool);
|
|
};
|
|
|
|
/*
|
|
* this value is set in page as a private data which indicate that
|
|
* the page is atomically written, and it is in inmem_pages list.
|
|
*/
|
|
#define ATOMIC_WRITTEN_PAGE ((unsigned long)-1)
|
|
#define DUMMY_WRITTEN_PAGE ((unsigned long)-2)
|
|
|
|
#define IS_ATOMIC_WRITTEN_PAGE(page) \
|
|
(page_private(page) == (unsigned long)ATOMIC_WRITTEN_PAGE)
|
|
#define IS_DUMMY_WRITTEN_PAGE(page) \
|
|
(page_private(page) == (unsigned long)DUMMY_WRITTEN_PAGE)
|
|
|
|
#define MAX_SKIP_ATOMIC_COUNT 16
|
|
|
|
struct inmem_pages {
|
|
struct list_head list;
|
|
struct page *page;
|
|
block_t old_addr; /* for revoking when fail to commit */
|
|
};
|
|
|
|
struct sit_info {
|
|
const struct segment_allocation *s_ops;
|
|
|
|
block_t sit_base_addr; /* start block address of SIT area */
|
|
block_t sit_blocks; /* # of blocks used by SIT area */
|
|
block_t written_valid_blocks; /* # of valid blocks in main area */
|
|
char *sit_bitmap; /* SIT bitmap pointer */
|
|
#ifdef CONFIG_F2FS_CHECK_FS
|
|
char *sit_bitmap_mir; /* SIT bitmap mirror */
|
|
#endif
|
|
unsigned int bitmap_size; /* SIT bitmap size */
|
|
|
|
unsigned long *tmp_map; /* bitmap for temporal use */
|
|
unsigned long *dirty_sentries_bitmap; /* bitmap for dirty sentries */
|
|
unsigned int dirty_sentries; /* # of dirty sentries */
|
|
unsigned int sents_per_block; /* # of SIT entries per block */
|
|
struct rw_semaphore sentry_lock; /* to protect SIT cache */
|
|
struct seg_entry *sentries; /* SIT segment-level cache */
|
|
struct sec_entry *sec_entries; /* SIT section-level cache */
|
|
|
|
/* for cost-benefit algorithm in cleaning procedure */
|
|
unsigned long long elapsed_time; /* elapsed time after mount */
|
|
unsigned long long mounted_time; /* mount time */
|
|
unsigned long long min_mtime; /* min. modification time */
|
|
unsigned long long max_mtime; /* max. modification time */
|
|
|
|
unsigned int last_victim[MAX_GC_POLICY]; /* last victim segment # */
|
|
};
|
|
|
|
struct free_segmap_info {
|
|
unsigned int start_segno; /* start segment number logically */
|
|
unsigned int free_segments; /* # of free segments */
|
|
unsigned int free_sections; /* # of free sections */
|
|
spinlock_t segmap_lock; /* free segmap lock */
|
|
unsigned long *free_segmap; /* free segment bitmap */
|
|
unsigned long *free_secmap; /* free section bitmap */
|
|
};
|
|
|
|
/* Notice: The order of dirty type is same with CURSEG_XXX in f2fs.h */
|
|
enum dirty_type {
|
|
DIRTY_HOT_DATA, /* dirty segments assigned as hot data logs */
|
|
DIRTY_WARM_DATA, /* dirty segments assigned as warm data logs */
|
|
DIRTY_COLD_DATA, /* dirty segments assigned as cold data logs */
|
|
DIRTY_HOT_NODE, /* dirty segments assigned as hot node logs */
|
|
DIRTY_WARM_NODE, /* dirty segments assigned as warm node logs */
|
|
DIRTY_COLD_NODE, /* dirty segments assigned as cold node logs */
|
|
DIRTY, /* to count # of dirty segments */
|
|
PRE, /* to count # of entirely obsolete segments */
|
|
NR_DIRTY_TYPE
|
|
};
|
|
|
|
struct dirty_seglist_info {
|
|
const struct victim_selection *v_ops; /* victim selction operation */
|
|
unsigned long *dirty_segmap[NR_DIRTY_TYPE];
|
|
struct mutex seglist_lock; /* lock for segment bitmaps */
|
|
int nr_dirty[NR_DIRTY_TYPE]; /* # of dirty segments */
|
|
unsigned long *victim_secmap; /* background GC victims */
|
|
};
|
|
|
|
/* victim selection function for cleaning and SSR */
|
|
struct victim_selection {
|
|
int (*get_victim)(struct f2fs_sb_info *, unsigned int *,
|
|
int, int, char);
|
|
};
|
|
|
|
/* for active log information */
|
|
struct curseg_info {
|
|
struct mutex curseg_mutex; /* lock for consistency */
|
|
struct f2fs_summary_block *sum_blk; /* cached summary block */
|
|
struct rw_semaphore journal_rwsem; /* protect journal area */
|
|
struct f2fs_journal *journal; /* cached journal info */
|
|
unsigned char alloc_type; /* current allocation type */
|
|
unsigned int segno; /* current segment number */
|
|
unsigned short next_blkoff; /* next block offset to write */
|
|
unsigned int zone; /* current zone number */
|
|
unsigned int next_segno; /* preallocated segment */
|
|
};
|
|
|
|
struct sit_entry_set {
|
|
struct list_head set_list; /* link with all sit sets */
|
|
unsigned int start_segno; /* start segno of sits in set */
|
|
unsigned int entry_cnt; /* the # of sit entries in set */
|
|
};
|
|
|
|
/*
|
|
* inline functions
|
|
*/
|
|
static inline struct curseg_info *CURSEG_I(struct f2fs_sb_info *sbi, int type)
|
|
{
|
|
return (struct curseg_info *)(SM_I(sbi)->curseg_array + type);
|
|
}
|
|
|
|
static inline struct seg_entry *get_seg_entry(struct f2fs_sb_info *sbi,
|
|
unsigned int segno)
|
|
{
|
|
struct sit_info *sit_i = SIT_I(sbi);
|
|
return &sit_i->sentries[segno];
|
|
}
|
|
|
|
static inline struct sec_entry *get_sec_entry(struct f2fs_sb_info *sbi,
|
|
unsigned int segno)
|
|
{
|
|
struct sit_info *sit_i = SIT_I(sbi);
|
|
return &sit_i->sec_entries[GET_SEC_FROM_SEG(sbi, segno)];
|
|
}
|
|
|
|
static inline unsigned int get_valid_blocks(struct f2fs_sb_info *sbi,
|
|
unsigned int segno, bool use_section)
|
|
{
|
|
/*
|
|
* In order to get # of valid blocks in a section instantly from many
|
|
* segments, f2fs manages two counting structures separately.
|
|
*/
|
|
if (use_section && sbi->segs_per_sec > 1)
|
|
return get_sec_entry(sbi, segno)->valid_blocks;
|
|
else
|
|
return get_seg_entry(sbi, segno)->valid_blocks;
|
|
}
|
|
|
|
static inline void seg_info_from_raw_sit(struct seg_entry *se,
|
|
struct f2fs_sit_entry *rs)
|
|
{
|
|
se->valid_blocks = GET_SIT_VBLOCKS(rs);
|
|
se->ckpt_valid_blocks = GET_SIT_VBLOCKS(rs);
|
|
memcpy(se->cur_valid_map, rs->valid_map, SIT_VBLOCK_MAP_SIZE);
|
|
memcpy(se->ckpt_valid_map, rs->valid_map, SIT_VBLOCK_MAP_SIZE);
|
|
#ifdef CONFIG_F2FS_CHECK_FS
|
|
memcpy(se->cur_valid_map_mir, rs->valid_map, SIT_VBLOCK_MAP_SIZE);
|
|
#endif
|
|
se->type = GET_SIT_TYPE(rs);
|
|
se->mtime = le64_to_cpu(rs->mtime);
|
|
}
|
|
|
|
static inline void __seg_info_to_raw_sit(struct seg_entry *se,
|
|
struct f2fs_sit_entry *rs)
|
|
{
|
|
unsigned short raw_vblocks = (se->type << SIT_VBLOCKS_SHIFT) |
|
|
se->valid_blocks;
|
|
rs->vblocks = cpu_to_le16(raw_vblocks);
|
|
memcpy(rs->valid_map, se->cur_valid_map, SIT_VBLOCK_MAP_SIZE);
|
|
rs->mtime = cpu_to_le64(se->mtime);
|
|
}
|
|
|
|
static inline void seg_info_to_sit_page(struct f2fs_sb_info *sbi,
|
|
struct page *page, unsigned int start)
|
|
{
|
|
struct f2fs_sit_block *raw_sit;
|
|
struct seg_entry *se;
|
|
struct f2fs_sit_entry *rs;
|
|
unsigned int end = min(start + SIT_ENTRY_PER_BLOCK,
|
|
(unsigned long)MAIN_SEGS(sbi));
|
|
int i;
|
|
|
|
raw_sit = (struct f2fs_sit_block *)page_address(page);
|
|
memset(raw_sit, 0, PAGE_SIZE);
|
|
for (i = 0; i < end - start; i++) {
|
|
rs = &raw_sit->entries[i];
|
|
se = get_seg_entry(sbi, start + i);
|
|
__seg_info_to_raw_sit(se, rs);
|
|
}
|
|
}
|
|
|
|
static inline void seg_info_to_raw_sit(struct seg_entry *se,
|
|
struct f2fs_sit_entry *rs)
|
|
{
|
|
__seg_info_to_raw_sit(se, rs);
|
|
|
|
memcpy(se->ckpt_valid_map, rs->valid_map, SIT_VBLOCK_MAP_SIZE);
|
|
se->ckpt_valid_blocks = se->valid_blocks;
|
|
}
|
|
|
|
static inline unsigned int find_next_inuse(struct free_segmap_info *free_i,
|
|
unsigned int max, unsigned int segno)
|
|
{
|
|
unsigned int ret;
|
|
spin_lock(&free_i->segmap_lock);
|
|
ret = find_next_bit(free_i->free_segmap, max, segno);
|
|
spin_unlock(&free_i->segmap_lock);
|
|
return ret;
|
|
}
|
|
|
|
static inline void __set_free(struct f2fs_sb_info *sbi, unsigned int segno)
|
|
{
|
|
struct free_segmap_info *free_i = FREE_I(sbi);
|
|
unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
|
|
unsigned int start_segno = GET_SEG_FROM_SEC(sbi, secno);
|
|
unsigned int next;
|
|
|
|
spin_lock(&free_i->segmap_lock);
|
|
clear_bit(segno, free_i->free_segmap);
|
|
free_i->free_segments++;
|
|
|
|
next = find_next_bit(free_i->free_segmap,
|
|
start_segno + sbi->segs_per_sec, start_segno);
|
|
if (next >= start_segno + sbi->segs_per_sec) {
|
|
clear_bit(secno, free_i->free_secmap);
|
|
free_i->free_sections++;
|
|
}
|
|
spin_unlock(&free_i->segmap_lock);
|
|
}
|
|
|
|
static inline void __set_inuse(struct f2fs_sb_info *sbi,
|
|
unsigned int segno)
|
|
{
|
|
struct free_segmap_info *free_i = FREE_I(sbi);
|
|
unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
|
|
|
|
set_bit(segno, free_i->free_segmap);
|
|
free_i->free_segments--;
|
|
if (!test_and_set_bit(secno, free_i->free_secmap))
|
|
free_i->free_sections--;
|
|
}
|
|
|
|
static inline void __set_test_and_free(struct f2fs_sb_info *sbi,
|
|
unsigned int segno)
|
|
{
|
|
struct free_segmap_info *free_i = FREE_I(sbi);
|
|
unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
|
|
unsigned int start_segno = GET_SEG_FROM_SEC(sbi, secno);
|
|
unsigned int next;
|
|
|
|
spin_lock(&free_i->segmap_lock);
|
|
if (test_and_clear_bit(segno, free_i->free_segmap)) {
|
|
free_i->free_segments++;
|
|
|
|
next = find_next_bit(free_i->free_segmap,
|
|
start_segno + sbi->segs_per_sec, start_segno);
|
|
if (next >= start_segno + sbi->segs_per_sec) {
|
|
if (test_and_clear_bit(secno, free_i->free_secmap))
|
|
free_i->free_sections++;
|
|
}
|
|
}
|
|
spin_unlock(&free_i->segmap_lock);
|
|
}
|
|
|
|
static inline void __set_test_and_inuse(struct f2fs_sb_info *sbi,
|
|
unsigned int segno)
|
|
{
|
|
struct free_segmap_info *free_i = FREE_I(sbi);
|
|
unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
|
|
|
|
spin_lock(&free_i->segmap_lock);
|
|
if (!test_and_set_bit(segno, free_i->free_segmap)) {
|
|
free_i->free_segments--;
|
|
if (!test_and_set_bit(secno, free_i->free_secmap))
|
|
free_i->free_sections--;
|
|
}
|
|
spin_unlock(&free_i->segmap_lock);
|
|
}
|
|
|
|
static inline void get_sit_bitmap(struct f2fs_sb_info *sbi,
|
|
void *dst_addr)
|
|
{
|
|
struct sit_info *sit_i = SIT_I(sbi);
|
|
|
|
#ifdef CONFIG_F2FS_CHECK_FS
|
|
if (memcmp(sit_i->sit_bitmap, sit_i->sit_bitmap_mir,
|
|
sit_i->bitmap_size))
|
|
f2fs_bug_on(sbi, 1);
|
|
#endif
|
|
memcpy(dst_addr, sit_i->sit_bitmap, sit_i->bitmap_size);
|
|
}
|
|
|
|
static inline block_t written_block_count(struct f2fs_sb_info *sbi)
|
|
{
|
|
return SIT_I(sbi)->written_valid_blocks;
|
|
}
|
|
|
|
static inline unsigned int free_segments(struct f2fs_sb_info *sbi)
|
|
{
|
|
return FREE_I(sbi)->free_segments;
|
|
}
|
|
|
|
static inline int reserved_segments(struct f2fs_sb_info *sbi)
|
|
{
|
|
return SM_I(sbi)->reserved_segments;
|
|
}
|
|
|
|
static inline unsigned int free_sections(struct f2fs_sb_info *sbi)
|
|
{
|
|
return FREE_I(sbi)->free_sections;
|
|
}
|
|
|
|
static inline unsigned int prefree_segments(struct f2fs_sb_info *sbi)
|
|
{
|
|
return DIRTY_I(sbi)->nr_dirty[PRE];
|
|
}
|
|
|
|
static inline unsigned int dirty_segments(struct f2fs_sb_info *sbi)
|
|
{
|
|
return DIRTY_I(sbi)->nr_dirty[DIRTY_HOT_DATA] +
|
|
DIRTY_I(sbi)->nr_dirty[DIRTY_WARM_DATA] +
|
|
DIRTY_I(sbi)->nr_dirty[DIRTY_COLD_DATA] +
|
|
DIRTY_I(sbi)->nr_dirty[DIRTY_HOT_NODE] +
|
|
DIRTY_I(sbi)->nr_dirty[DIRTY_WARM_NODE] +
|
|
DIRTY_I(sbi)->nr_dirty[DIRTY_COLD_NODE];
|
|
}
|
|
|
|
static inline int overprovision_segments(struct f2fs_sb_info *sbi)
|
|
{
|
|
return SM_I(sbi)->ovp_segments;
|
|
}
|
|
|
|
static inline int reserved_sections(struct f2fs_sb_info *sbi)
|
|
{
|
|
return GET_SEC_FROM_SEG(sbi, (unsigned int)reserved_segments(sbi));
|
|
}
|
|
|
|
static inline bool has_curseg_enough_space(struct f2fs_sb_info *sbi)
|
|
{
|
|
unsigned int node_blocks = get_pages(sbi, F2FS_DIRTY_NODES) +
|
|
get_pages(sbi, F2FS_DIRTY_DENTS);
|
|
unsigned int dent_blocks = get_pages(sbi, F2FS_DIRTY_DENTS);
|
|
unsigned int segno, left_blocks;
|
|
int i;
|
|
|
|
/* check current node segment */
|
|
for (i = CURSEG_HOT_NODE; i <= CURSEG_COLD_NODE; i++) {
|
|
segno = CURSEG_I(sbi, i)->segno;
|
|
left_blocks = sbi->blocks_per_seg -
|
|
get_seg_entry(sbi, segno)->ckpt_valid_blocks;
|
|
|
|
if (node_blocks > left_blocks)
|
|
return false;
|
|
}
|
|
|
|
/* check current data segment */
|
|
segno = CURSEG_I(sbi, CURSEG_HOT_DATA)->segno;
|
|
left_blocks = sbi->blocks_per_seg -
|
|
get_seg_entry(sbi, segno)->ckpt_valid_blocks;
|
|
if (dent_blocks > left_blocks)
|
|
return false;
|
|
return true;
|
|
}
|
|
|
|
static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi,
|
|
int freed, int needed)
|
|
{
|
|
int node_secs = get_blocktype_secs(sbi, F2FS_DIRTY_NODES);
|
|
int dent_secs = get_blocktype_secs(sbi, F2FS_DIRTY_DENTS);
|
|
int imeta_secs = get_blocktype_secs(sbi, F2FS_DIRTY_IMETA);
|
|
|
|
if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
|
|
return false;
|
|
|
|
if (free_sections(sbi) + freed == reserved_sections(sbi) + needed &&
|
|
has_curseg_enough_space(sbi))
|
|
return false;
|
|
return (free_sections(sbi) + freed) <=
|
|
(node_secs + 2 * dent_secs + imeta_secs +
|
|
reserved_sections(sbi) + needed);
|
|
}
|
|
|
|
static inline bool excess_prefree_segs(struct f2fs_sb_info *sbi)
|
|
{
|
|
return prefree_segments(sbi) > SM_I(sbi)->rec_prefree_segments;
|
|
}
|
|
|
|
static inline int utilization(struct f2fs_sb_info *sbi)
|
|
{
|
|
return div_u64((u64)valid_user_blocks(sbi) * 100,
|
|
sbi->user_block_count);
|
|
}
|
|
|
|
/*
|
|
* Sometimes f2fs may be better to drop out-of-place update policy.
|
|
* And, users can control the policy through sysfs entries.
|
|
* There are five policies with triggering conditions as follows.
|
|
* F2FS_IPU_FORCE - all the time,
|
|
* F2FS_IPU_SSR - if SSR mode is activated,
|
|
* F2FS_IPU_UTIL - if FS utilization is over threashold,
|
|
* F2FS_IPU_SSR_UTIL - if SSR mode is activated and FS utilization is over
|
|
* threashold,
|
|
* F2FS_IPU_FSYNC - activated in fsync path only for high performance flash
|
|
* storages. IPU will be triggered only if the # of dirty
|
|
* pages over min_fsync_blocks.
|
|
* F2FS_IPUT_DISABLE - disable IPU. (=default option)
|
|
*/
|
|
#define DEF_MIN_IPU_UTIL 70
|
|
#define DEF_MIN_FSYNC_BLOCKS 8
|
|
#define DEF_MIN_HOT_BLOCKS 16
|
|
|
|
#define SMALL_VOLUME_SEGMENTS (16 * 512) /* 16GB */
|
|
|
|
enum {
|
|
F2FS_IPU_FORCE,
|
|
F2FS_IPU_SSR,
|
|
F2FS_IPU_UTIL,
|
|
F2FS_IPU_SSR_UTIL,
|
|
F2FS_IPU_FSYNC,
|
|
F2FS_IPU_ASYNC,
|
|
};
|
|
|
|
static inline unsigned int curseg_segno(struct f2fs_sb_info *sbi,
|
|
int type)
|
|
{
|
|
struct curseg_info *curseg = CURSEG_I(sbi, type);
|
|
return curseg->segno;
|
|
}
|
|
|
|
static inline unsigned char curseg_alloc_type(struct f2fs_sb_info *sbi,
|
|
int type)
|
|
{
|
|
struct curseg_info *curseg = CURSEG_I(sbi, type);
|
|
return curseg->alloc_type;
|
|
}
|
|
|
|
static inline unsigned short curseg_blkoff(struct f2fs_sb_info *sbi, int type)
|
|
{
|
|
struct curseg_info *curseg = CURSEG_I(sbi, type);
|
|
return curseg->next_blkoff;
|
|
}
|
|
|
|
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)
|
|
{
|
|
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);
|
|
}
|
|
|
|
/*
|
|
* Summary block is always treated as an invalid block
|
|
*/
|
|
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;
|
|
|
|
/* check bitmap with valid block count */
|
|
do {
|
|
if (is_valid) {
|
|
next_pos = find_next_zero_bit_le(&raw_sit->valid_map,
|
|
sbi->blocks_per_seg,
|
|
cur_pos);
|
|
valid_blocks += next_pos - cur_pos;
|
|
} else
|
|
next_pos = find_next_bit_le(&raw_sit->valid_map,
|
|
sbi->blocks_per_seg,
|
|
cur_pos);
|
|
cur_pos = next_pos;
|
|
is_valid = !is_valid;
|
|
} while (cur_pos < sbi->blocks_per_seg);
|
|
|
|
if (unlikely(GET_SIT_VBLOCKS(raw_sit) != valid_blocks)) {
|
|
f2fs_msg(sbi->sb, KERN_ERR,
|
|
"Mismatch valid blocks %d vs. %d",
|
|
GET_SIT_VBLOCKS(raw_sit), valid_blocks);
|
|
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)) {
|
|
f2fs_msg(sbi->sb, KERN_ERR,
|
|
"Wrong valid blocks %d or segno %u",
|
|
GET_SIT_VBLOCKS(raw_sit), segno);
|
|
set_sbi_flag(sbi, SBI_NEED_FSCK);
|
|
return -EINVAL;
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
static inline pgoff_t current_sit_addr(struct f2fs_sb_info *sbi,
|
|
unsigned int start)
|
|
{
|
|
struct sit_info *sit_i = SIT_I(sbi);
|
|
unsigned int offset = SIT_BLOCK_OFFSET(start);
|
|
block_t blk_addr = sit_i->sit_base_addr + offset;
|
|
|
|
check_seg_range(sbi, start);
|
|
|
|
#ifdef CONFIG_F2FS_CHECK_FS
|
|
if (f2fs_test_bit(offset, sit_i->sit_bitmap) !=
|
|
f2fs_test_bit(offset, sit_i->sit_bitmap_mir))
|
|
f2fs_bug_on(sbi, 1);
|
|
#endif
|
|
|
|
/* calculate sit block address */
|
|
if (f2fs_test_bit(offset, sit_i->sit_bitmap))
|
|
blk_addr += sit_i->sit_blocks;
|
|
|
|
return blk_addr;
|
|
}
|
|
|
|
static inline pgoff_t next_sit_addr(struct f2fs_sb_info *sbi,
|
|
pgoff_t block_addr)
|
|
{
|
|
struct sit_info *sit_i = SIT_I(sbi);
|
|
block_addr -= sit_i->sit_base_addr;
|
|
if (block_addr < sit_i->sit_blocks)
|
|
block_addr += sit_i->sit_blocks;
|
|
else
|
|
block_addr -= sit_i->sit_blocks;
|
|
|
|
return block_addr + sit_i->sit_base_addr;
|
|
}
|
|
|
|
static inline void set_to_next_sit(struct sit_info *sit_i, unsigned int start)
|
|
{
|
|
unsigned int block_off = SIT_BLOCK_OFFSET(start);
|
|
|
|
f2fs_change_bit(block_off, sit_i->sit_bitmap);
|
|
#ifdef CONFIG_F2FS_CHECK_FS
|
|
f2fs_change_bit(block_off, sit_i->sit_bitmap_mir);
|
|
#endif
|
|
}
|
|
|
|
static inline unsigned long long get_mtime(struct f2fs_sb_info *sbi,
|
|
bool base_time)
|
|
{
|
|
struct sit_info *sit_i = SIT_I(sbi);
|
|
time64_t diff, now = ktime_get_real_seconds();
|
|
|
|
if (now >= sit_i->mounted_time)
|
|
return sit_i->elapsed_time + now - sit_i->mounted_time;
|
|
|
|
/* system time is set to the past */
|
|
if (!base_time) {
|
|
diff = sit_i->mounted_time - now;
|
|
if (sit_i->elapsed_time >= diff)
|
|
return sit_i->elapsed_time - diff;
|
|
return 0;
|
|
}
|
|
return sit_i->elapsed_time;
|
|
}
|
|
|
|
static inline void set_summary(struct f2fs_summary *sum, nid_t nid,
|
|
unsigned int ofs_in_node, unsigned char version)
|
|
{
|
|
sum->nid = cpu_to_le32(nid);
|
|
sum->ofs_in_node = cpu_to_le16(ofs_in_node);
|
|
sum->version = version;
|
|
}
|
|
|
|
static inline block_t start_sum_block(struct f2fs_sb_info *sbi)
|
|
{
|
|
return __start_cp_addr(sbi) +
|
|
le32_to_cpu(F2FS_CKPT(sbi)->cp_pack_start_sum);
|
|
}
|
|
|
|
static inline block_t sum_blk_addr(struct f2fs_sb_info *sbi, int base, int type)
|
|
{
|
|
return __start_cp_addr(sbi) +
|
|
le32_to_cpu(F2FS_CKPT(sbi)->cp_pack_total_block_count)
|
|
- (base + 1) + type;
|
|
}
|
|
|
|
static inline bool sec_usage_check(struct f2fs_sb_info *sbi, unsigned int secno)
|
|
{
|
|
if (IS_CURSEC(sbi, secno) || (sbi->cur_victim_sec == secno))
|
|
return true;
|
|
return false;
|
|
}
|
|
|
|
/*
|
|
* It is very important to gather dirty pages and write at once, so that we can
|
|
* submit a big bio without interfering other data writes.
|
|
* By default, 512 pages for directory data,
|
|
* 512 pages (2MB) * 8 for nodes, and
|
|
* 256 pages * 8 for meta are set.
|
|
*/
|
|
static inline int nr_pages_to_skip(struct f2fs_sb_info *sbi, int type)
|
|
{
|
|
if (sbi->sb->s_bdi->wb.dirty_exceeded)
|
|
return 0;
|
|
|
|
if (type == DATA)
|
|
return sbi->blocks_per_seg;
|
|
else if (type == NODE)
|
|
return 8 * sbi->blocks_per_seg;
|
|
else if (type == META)
|
|
return 8 * BIO_MAX_PAGES;
|
|
else
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* When writing pages, it'd better align nr_to_write for segment size.
|
|
*/
|
|
static inline long nr_pages_to_write(struct f2fs_sb_info *sbi, int type,
|
|
struct writeback_control *wbc)
|
|
{
|
|
long nr_to_write, desired;
|
|
|
|
if (wbc->sync_mode != WB_SYNC_NONE)
|
|
return 0;
|
|
|
|
nr_to_write = wbc->nr_to_write;
|
|
desired = BIO_MAX_PAGES;
|
|
if (type == NODE)
|
|
desired <<= 1;
|
|
|
|
wbc->nr_to_write = desired;
|
|
return desired - nr_to_write;
|
|
}
|
|
|
|
static inline void wake_up_discard_thread(struct f2fs_sb_info *sbi, bool force)
|
|
{
|
|
struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
|
|
bool wakeup = false;
|
|
int i;
|
|
|
|
if (force)
|
|
goto wake_up;
|
|
|
|
mutex_lock(&dcc->cmd_lock);
|
|
for (i = MAX_PLIST_NUM - 1; i >= 0; i--) {
|
|
if (i + 1 < dcc->discard_granularity)
|
|
break;
|
|
if (!list_empty(&dcc->pend_list[i])) {
|
|
wakeup = true;
|
|
break;
|
|
}
|
|
}
|
|
mutex_unlock(&dcc->cmd_lock);
|
|
if (!wakeup)
|
|
return;
|
|
wake_up:
|
|
dcc->discard_wake = 1;
|
|
wake_up_interruptible_all(&dcc->discard_wait_queue);
|
|
}
|