cregit-Linux how code gets into the kernel

Release 4.10 fs/ext4/inode.c

Directory: fs/ext4
/*
 *  linux/fs/ext4/inode.c
 *
 * Copyright (C) 1992, 1993, 1994, 1995
 * Remy Card (card@masi.ibp.fr)
 * Laboratoire MASI - Institut Blaise Pascal
 * Universite Pierre et Marie Curie (Paris VI)
 *
 *  from
 *
 *  linux/fs/minix/inode.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 *
 *  64-bit file support on 64-bit platforms by Jakub Jelinek
 *      (jj@sunsite.ms.mff.cuni.cz)
 *
 *  Assorted race fixes, rewrite of ext4_get_block() by Al Viro, 2000
 */

#include <linux/fs.h>
#include <linux/time.h>
#include <linux/highuid.h>
#include <linux/pagemap.h>
#include <linux/dax.h>
#include <linux/quotaops.h>
#include <linux/string.h>
#include <linux/buffer_head.h>
#include <linux/writeback.h>
#include <linux/pagevec.h>
#include <linux/mpage.h>
#include <linux/namei.h>
#include <linux/uio.h>
#include <linux/bio.h>
#include <linux/workqueue.h>
#include <linux/kernel.h>
#include <linux/printk.h>
#include <linux/slab.h>
#include <linux/bitops.h>
#include <linux/iomap.h>

#include "ext4_jbd2.h"
#include "xattr.h"
#include "acl.h"
#include "truncate.h"

#include <trace/events/ext4.h>


#define MPAGE_DA_EXTENT_TAIL 0x01


static __u32 ext4_inode_csum(struct inode *inode, struct ext4_inode *raw, struct ext4_inode_info *ei) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); __u32 csum; __u16 dummy_csum = 0; int offset = offsetof(struct ext4_inode, i_checksum_lo); unsigned int csum_size = sizeof(dummy_csum); csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)raw, offset); csum = ext4_chksum(sbi, csum, (__u8 *)&dummy_csum, csum_size); offset += csum_size; csum = ext4_chksum(sbi, csum, (__u8 *)raw + offset, EXT4_GOOD_OLD_INODE_SIZE - offset); if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) { offset = offsetof(struct ext4_inode, i_checksum_hi); csum = ext4_chksum(sbi, csum, (__u8 *)raw + EXT4_GOOD_OLD_INODE_SIZE, offset - EXT4_GOOD_OLD_INODE_SIZE); if (EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi)) { csum = ext4_chksum(sbi, csum, (__u8 *)&dummy_csum, csum_size); offset += csum_size; } csum = ext4_chksum(sbi, csum, (__u8 *)raw + offset, EXT4_INODE_SIZE(inode->i_sb) - offset); } return csum; }

Contributors

PersonTokensPropCommitsCommitProp
daeho jeongdaeho jeong13458.01%250.00%
darrick j. wongdarrick j. wong8938.53%125.00%
dmitriy monakhovdmitriy monakhov83.46%125.00%
Total231100.00%4100.00%


static int ext4_inode_csum_verify(struct inode *inode, struct ext4_inode *raw, struct ext4_inode_info *ei) { __u32 provided, calculated; if (EXT4_SB(inode->i_sb)->s_es->s_creator_os != cpu_to_le32(EXT4_OS_LINUX) || !ext4_has_metadata_csum(inode->i_sb)) return 1; provided = le16_to_cpu(raw->i_checksum_lo); calculated = ext4_inode_csum(inode, raw, ei); if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE && EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi)) provided |= ((__u32)le16_to_cpu(raw->i_checksum_hi)) << 16; else calculated &= 0xFFFF; return provided == calculated; }

Contributors

PersonTokensPropCommitsCommitProp
darrick j. wongdarrick j. wong12099.17%150.00%
dmitriy monakhovdmitriy monakhov10.83%150.00%
Total121100.00%2100.00%


static void ext4_inode_csum_set(struct inode *inode, struct ext4_inode *raw, struct ext4_inode_info *ei) { __u32 csum; if (EXT4_SB(inode->i_sb)->s_es->s_creator_os != cpu_to_le32(EXT4_OS_LINUX) || !ext4_has_metadata_csum(inode->i_sb)) return; csum = ext4_inode_csum(inode, raw, ei); raw->i_checksum_lo = cpu_to_le16(csum & 0xFFFF); if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE && EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi)) raw->i_checksum_hi = cpu_to_le16(csum >> 16); }

Contributors

PersonTokensPropCommitsCommitProp
darrick j. wongdarrick j. wong10399.04%150.00%
dmitriy monakhovdmitriy monakhov10.96%150.00%
Total104100.00%2100.00%


static inline int ext4_begin_ordered_truncate(struct inode *inode, loff_t new_size) { trace_ext4_begin_ordered_truncate(inode, new_size); /* * If jinode is zero, then we never opened the file for * writing, so there's no need to call * jbd2_journal_begin_ordered_truncate() since there's no * outstanding writes we need to flush. */ if (!EXT4_I(inode)->jinode) return 0; return jbd2_journal_begin_ordered_truncate(EXT4_JOURNAL(inode), EXT4_I(inode)->jinode, new_size); }

Contributors

PersonTokensPropCommitsCommitProp
jan karajan kara3259.26%250.00%
theodore tsotheodore tso2240.74%250.00%
Total54100.00%4100.00%

static void ext4_invalidatepage(struct page *page, unsigned int offset, unsigned int length); static int __ext4_journalled_writepage(struct page *page, unsigned int len); static int ext4_bh_delay_or_unwritten(handle_t *handle, struct buffer_head *bh); static int ext4_meta_trans_blocks(struct inode *inode, int lblocks, int pextents); /* * Test whether an inode is a fast symlink. */
int ext4_inode_is_fast_symlink(struct inode *inode) { int ea_blocks = EXT4_I(inode)->i_file_acl ? EXT4_CLUSTER_SIZE(inode->i_sb) >> 9 : 0; if (ext4_has_inline_data(inode)) return 0; return (S_ISLNK(inode->i_mode) && inode->i_blocks - ea_blocks == 0); }

Contributors

PersonTokensPropCommitsCommitProp
dave kleikampdave kleikamp4474.58%125.00%
zheng liuzheng liu1016.95%125.00%
yongqiang yangyongqiang yang35.08%125.00%
mingming caomingming cao23.39%125.00%
Total59100.00%4100.00%

/* * Restart the transaction associated with *handle. This does a commit, * so before we call here everything must be consistently dirtied against * this transaction. */
int ext4_truncate_restart_trans(handle_t *handle, struct inode *inode, int nblocks) { int ret; /* * Drop i_data_sem to avoid deadlock with ext4_map_blocks. At this * moment, get_block can be called only for blocks inside i_size since * page cache has been already dropped and writes are blocked by * i_mutex. So we can safely drop the i_data_sem here. */ BUG_ON(EXT4_JOURNAL(inode) == NULL); jbd_debug(2, "restarting handle %p\n", handle); up_write(&EXT4_I(inode)->i_data_sem); ret = ext4_journal_restart(handle, nblocks); down_write(&EXT4_I(inode)->i_data_sem); ext4_discard_preallocations(inode); return ret; }

Contributors

PersonTokensPropCommitsCommitProp
jan karajan kara3443.04%114.29%
dave kleikampdave kleikamp2734.18%114.29%
frank mayharfrank mayhar1012.66%114.29%
aneesh kumaraneesh kumar56.33%114.29%
mingming caomingming cao11.27%114.29%
amir goldsteinamir goldstein11.27%114.29%
theodore tsotheodore tso11.27%114.29%
Total79100.00%7100.00%

/* * Called at the last iput() if i_nlink is zero. */
void ext4_evict_inode(struct inode *inode) { handle_t *handle; int err; trace_ext4_evict_inode(inode); if (inode->i_nlink) { /* * When journalling data dirty buffers are tracked only in the * journal. So although mm thinks everything is clean and * ready for reaping the inode might still have some pages to * write in the running transaction or waiting to be * checkpointed. Thus calling jbd2_journal_invalidatepage() * (via truncate_inode_pages()) to discard these buffers can * cause data loss. Also even if we did not discard these * buffers, we would have no way to find them after the inode * is reaped and thus user could see stale data if he tries to * read them before the transaction is checkpointed. So be * careful and force everything to disk here... We use * ei->i_datasync_tid to store the newest transaction * containing inode's data. * * Note that directories do not have this problem because they * don't use page cache. */ if (inode->i_ino != EXT4_JOURNAL_INO && ext4_should_journal_data(inode) && (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode))) { journal_t *journal = EXT4_SB(inode->i_sb)->s_journal; tid_t commit_tid = EXT4_I(inode)->i_datasync_tid; jbd2_complete_transaction(journal, commit_tid); filemap_write_and_wait(&inode->i_data); } truncate_inode_pages_final(&inode->i_data); goto no_delete; } if (is_bad_inode(inode)) goto no_delete; dquot_initialize(inode); if (ext4_should_order_data(inode)) ext4_begin_ordered_truncate(inode, 0); truncate_inode_pages_final(&inode->i_data); /* * Protect us against freezing - iput() caller didn't have to have any * protection against it */ sb_start_intwrite(inode->i_sb); handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, ext4_blocks_for_truncate(inode)+3); if (IS_ERR(handle)) { ext4_std_error(inode->i_sb, PTR_ERR(handle)); /* * If we're going to skip the normal cleanup, we still need to * make sure that the in-core orphan linked list is properly * cleaned up. */ ext4_orphan_del(NULL, inode); sb_end_intwrite(inode->i_sb); goto no_delete; } if (IS_SYNC(inode)) ext4_handle_sync(handle); inode->i_size = 0; err = ext4_mark_inode_dirty(handle, inode); if (err) { ext4_warning(inode->i_sb, "couldn't mark inode dirty (err %d)", err); goto stop_handle; } if (inode->i_blocks) { err = ext4_truncate(inode); if (err) { ext4_error(inode->i_sb, "couldn't truncate inode %lu (err %d)", inode->i_ino, err); goto stop_handle; } } /* * ext4_ext_truncate() doesn't reserve any slop when it * restarts journal transactions; therefore there may not be * enough credits left in the handle to remove the inode from * the orphan list and set the dtime field. */ if (!ext4_handle_has_enough_credits(handle, 3)) { err = ext4_journal_extend(handle, 3); if (err > 0) err = ext4_journal_restart(handle, 3); if (err != 0) { ext4_warning(inode->i_sb, "couldn't extend journal (err %d)", err); stop_handle: ext4_journal_stop(handle); ext4_orphan_del(NULL, inode); sb_end_intwrite(inode->i_sb); goto no_delete; } } /* * Kill off the orphan record which ext4_truncate created. * AKPM: I think this can be inside the above `if'. * Note that ext4_orphan_del() has to be able to cope with the * deletion of a non-existent orphan - this is because we don't * know if ext4_truncate() actually created an orphan record. * (Well, we could do this if we need to, but heck - it works) */ ext4_orphan_del(handle, inode); EXT4_I(inode)->i_dtime = get_seconds(); /* * One subtle ordering requirement: if anything has gone wrong * (transaction abort, IO errors, whatever), then we can still * do these next steps (the fs will already have been marked as * having errors), but we can't free the inode if the mark_dirty * fails. */ if (ext4_mark_inode_dirty(handle, inode)) /* If that failed, just do the required in-core inode clear. */ ext4_clear_inode(inode); else ext4_free_inode(handle, inode); ext4_journal_stop(handle); sb_end_intwrite(inode->i_sb); return; no_delete: ext4_clear_inode(inode); /* We must guarantee clearing of inode... */ }

Contributors

PersonTokensPropCommitsCommitProp
theodore tsotheodore tso15936.14%842.11%
dave kleikampdave kleikamp11826.82%15.26%
jan karajan kara10624.09%315.79%
al viroal viro214.77%15.26%
christoph hellwigchristoph hellwig122.73%210.53%
mingming caomingming cao81.82%15.26%
frank mayharfrank mayhar81.82%15.26%
vegard nossumvegard nossum61.36%15.26%
johannes weinerjohannes weiner20.45%15.26%
Total440100.00%19100.00%

#ifdef CONFIG_QUOTA
qsize_t *ext4_get_reserved_space(struct inode *inode) { return &EXT4_I(inode)->i_reserved_quota; }

Contributors

PersonTokensPropCommitsCommitProp
amir goldsteinamir goldstein1680.00%150.00%
dave kleikampdave kleikamp420.00%150.00%
Total20100.00%2100.00%

#endif /* * Called with i_data_sem down, which is important since we can call * ext4_discard_preallocations() from here. */
void ext4_da_update_reserve_space(struct inode *inode, int used, int quota_claim) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_inode_info *ei = EXT4_I(inode); spin_lock(&ei->i_block_reservation_lock); trace_ext4_da_update_reserve_space(inode, used, quota_claim); if (unlikely(used > ei->i_reserved_data_blocks)) { ext4_warning(inode->i_sb, "%s: ino %lu, used %d " "with only %d reserved data blocks", __func__, inode->i_ino, used, ei->i_reserved_data_blocks); WARN_ON(1); used = ei->i_reserved_data_blocks; } /* Update per-inode reservations */ ei->i_reserved_data_blocks -= used; percpu_counter_sub(&sbi->s_dirtyclusters_counter, used); spin_unlock(&EXT4_I(inode)->i_block_reservation_lock); /* Update quota subsystem for data blocks */ if (quota_claim) dquot_claim_block(inode, EXT4_C2B(sbi, used)); else { /* * We did fallocate with an offset that is already delayed * allocated. So on delayed allocated writeback we should * not re-claim the quota for fallocated blocks. */ dquot_release_reservation_block(inode, EXT4_C2B(sbi, used)); } /* * If we have done all the pending block allocations and if * there aren't any writers on the inode, we can discard the * inode's preallocations. */ if ((ei->i_reserved_data_blocks == 0) && (atomic_read(&inode->i_writecount) == 0)) ext4_discard_preallocations(inode); }

Contributors

PersonTokensPropCommitsCommitProp
amir goldsteinamir goldstein11460.00%112.50%
dave kleikampdave kleikamp6031.58%112.50%
aditya kaliaditya kali126.32%225.00%
theodore tsotheodore tso31.58%337.50%
eric sandeeneric sandeen10.53%112.50%
Total190100.00%8100.00%


static int __check_block_validity(struct inode *inode, const char *func, unsigned int line, struct ext4_map_blocks *map) { if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), map->m_pblk, map->m_len)) { ext4_error_inode(inode, func, line, map->m_pblk, "lblock %lu mapped to illegal pblock " "(length %d)", (unsigned long) map->m_lblk, map->m_len); return -EFSCORRUPTED; } return 0; }

Contributors

PersonTokensPropCommitsCommitProp
thiemo nagelthiemo nagel3339.76%222.22%
amir goldsteinamir goldstein2631.33%111.11%
theodore tsotheodore tso1619.28%444.44%
dave kleikampdave kleikamp78.43%111.11%
darrick j. wongdarrick j. wong11.20%111.11%
Total83100.00%9100.00%


int ext4_issue_zeroout(struct inode *inode, ext4_lblk_t lblk, ext4_fsblk_t pblk, ext4_lblk_t len) { int ret; if (ext4_encrypted_inode(inode)) return fscrypt_zeroout_range(inode, lblk, pblk, len); ret = sb_issue_zeroout(inode->i_sb, pblk, len, GFP_NOFS); if (ret > 0) ret = 0; return ret; }

Contributors

PersonTokensPropCommitsCommitProp
jan karajan kara6898.55%150.00%
jaegeuk kimjaegeuk kim11.45%150.00%
Total69100.00%2100.00%

#define check_block_validity(inode, map) \ __check_block_validity((inode), __func__, __LINE__, (map)) #ifdef ES_AGGRESSIVE_TEST
static void ext4_map_blocks_es_recheck(handle_t *handle, struct inode *inode, struct ext4_map_blocks *es_map, struct ext4_map_blocks *map, int flags) { int retval; map->m_flags = 0; /* * There is a race window that the result is not the same. * e.g. xfstests #223 when dioread_nolock enables. The reason * is that we lookup a block mapping in extent status tree with * out taking i_data_sem. So at the time the unwritten extent * could be converted. */ down_read(&EXT4_I(inode)->i_data_sem); if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { retval = ext4_ext_map_blocks(handle, inode, map, flags & EXT4_GET_BLOCKS_KEEP_SIZE); } else { retval = ext4_ind_map_blocks(handle, inode, map, flags & EXT4_GET_BLOCKS_KEEP_SIZE); } up_read((&EXT4_I(inode)->i_data_sem)); /* * We don't check m_len because extent will be collpased in status * tree. So the m_len might not equal. */ if (es_map->m_lblk != map->m_lblk || es_map->m_flags != map->m_flags || es_map->m_pblk != map->m_pblk) { printk("ES cache assertion failed for inode: %lu " "es_cached ex [%d/%d/%llu/%x] != " "found ex [%d/%d/%llu/%x] retval %d flags %x\n", inode->i_ino, es_map->m_lblk, es_map->m_len, es_map->m_pblk, es_map->m_flags, map->m_lblk, map->m_len, map->m_pblk, map->m_flags, retval, flags); } }

Contributors

PersonTokensPropCommitsCommitProp
dmitriy monakhovdmitriy monakhov18199.45%150.00%
theodore tsotheodore tso10.55%150.00%
Total182100.00%2100.00%

#endif /* ES_AGGRESSIVE_TEST */ /* * The ext4_map_blocks() function tries to look up the requested blocks, * and returns if the blocks are already mapped. * * Otherwise it takes the write lock of the i_data_sem and allocate blocks * and store the allocated blocks in the result buffer head and mark it * mapped. * * If file type is extents based, it will call ext4_ext_map_blocks(), * Otherwise, call with ext4_ind_map_blocks() to handle indirect mapping * based files * * On success, it returns the number of blocks being mapped or allocated. if * create==0 and the blocks are pre-allocated and unwritten, the resulting @map * is marked as unwritten. If the create == 1, it will mark @map as mapped. * * It returns 0 if plain look up failed (blocks have not been allocated), in * that case, @map is returned as unmapped but we still do fill map->m_len to * indicate the length of a hole starting at map->m_lblk. * * It returns the error in case of allocation failure. */
int ext4_map_blocks(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, int flags) { struct extent_status es; int retval; int ret = 0; #ifdef ES_AGGRESSIVE_TEST struct ext4_map_blocks orig_map; memcpy(&orig_map, map, sizeof(*map)); #endif map->m_flags = 0; ext_debug("ext4_map_blocks(): inode %lu, flag %d, max_blocks %u," "logical block %lu\n", inode->i_ino, flags, map->m_len, (unsigned long) map->m_lblk); /* * ext4_map_blocks returns an int, and m_len is an unsigned int */ if (unlikely(map->m_len > INT_MAX)) map->m_len = INT_MAX; /* We can handle the block number less than EXT_MAX_BLOCKS */ if (unlikely(map->m_lblk >= EXT_MAX_BLOCKS)) return -EFSCORRUPTED; /* Lookup extent status tree firstly */ if (ext4_es_lookup_extent(inode, map->m_lblk, &es)) { if (ext4_es_is_written(&es) || ext4_es_is_unwritten(&es)) { map->m_pblk = ext4_es_pblock(&es) + map->m_lblk - es.es_lblk; map->m_flags |= ext4_es_is_written(&es) ? EXT4_MAP_MAPPED : EXT4_MAP_UNWRITTEN; retval = es.es_len - (map->m_lblk - es.es_lblk); if (retval > map->m_len) retval = map->m_len; map->m_len = retval; } else if (ext4_es_is_delayed(&es) || ext4_es_is_hole(&es)) { map->m_pblk = 0; retval = es.es_len - (map->m_lblk - es.es_lblk); if (retval > map->m_len) retval = map->m_len; map->m_len = retval; retval = 0; } else { BUG_ON(1); } #ifdef ES_AGGRESSIVE_TEST ext4_map_blocks_es_recheck(handle, inode, map, &orig_map, flags); #endif goto found; } /* * Try to see if we can get the block without requesting a new * file system block. */ down_read(&EXT4_I(inode)->i_data_sem); if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { retval = ext4_ext_map_blocks(handle, inode, map, flags & EXT4_GET_BLOCKS_KEEP_SIZE); } else { retval = ext4_ind_map_blocks(handle, inode, map, flags & EXT4_GET_BLOCKS_KEEP_SIZE); } if (retval > 0) { unsigned int status; if (unlikely(retval != map->m_len)) { ext4_warning(inode->i_sb, "ES len assertion failed for inode " "%lu: retval %d != map->m_len %d", inode->i_ino, retval, map->m_len); WARN_ON(1); } status = map->m_flags & EXT4_MAP_UNWRITTEN ? EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN; if (!(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) && !(status & EXTENT_STATUS_WRITTEN) && ext4_find_delalloc_range(inode, map->m_lblk, map->m_lblk + map->m_len - 1)) status |= EXTENT_STATUS_DELAYED; ret = ext4_es_insert_extent(inode, map->m_lblk, map->m_len, map->m_pblk, status); if (ret < 0) retval = ret; } up_read((&EXT4_I(inode)->i_data_sem)); found: if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) { ret = check_block_validity(inode, map); if (ret != 0) return ret; } /* If it is only a block(s) look up */ if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) return retval; /* * Returns if the blocks have already allocated * * Note that if blocks have been preallocated * ext4_ext_get_block() returns the create = 0 * with buffer head unmapped. */ if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) /* * If we need to convert extent to unwritten * we continue and do the actual work in * ext4_ext_map_blocks() */ if (!(flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN)) return retval; /* * Here we clear m_flags because after allocating an new extent, * it will be set again. */ map->m_flags &= ~EXT4_MAP_FLAGS; /* * New blocks allocate and/or writing to unwritten extent * will possibly result in updating i_data, so we take * the write lock of i_data_sem, and call get_block() * with create == 1 flag. */ down_write(&EXT4_I(inode)->i_data_sem); /* * We need to check for EXT4 here because migrate * could have changed the inode type in between */ if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { retval = ext4_ext_map_blocks(handle, inode, map, flags); } else { retval = ext4_ind_map_blocks(handle, inode, map, flags); if (retval > 0 && map->m_flags & EXT4_MAP_NEW) { /* * We allocated new blocks which will result in * i_data's format changing. Force the migrate * to fail by clearing migrate flags */ ext4_clear_inode_state(inode, EXT4_STATE_EXT_MIGRATE); } /* * Update reserved blocks/metadata blocks after successful * block allocation which had been deferred till now. We don't * support fallocate for non extent files. So we can update * reserve space here. */ if ((retval > 0) && (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)) ext4_da_update_reserve_space(inode, retval, 1); } if (retval > 0) { unsigned int status; if (unlikely(retval != map->m_len)) { ext4_warning(inode->i_sb, "ES len assertion failed for inode " "%lu: retval %d != map->m_len %d", inode->i_ino, retval, map->m_len); WARN_ON(1); } /* * We have to zeroout blocks before inserting them into extent * status tree. Otherwise someone could look them up there and * use them before they are really zeroed. We also have to * unmap metadata before zeroing as otherwise writeback can * overwrite zeros with stale data from block device. */ if (flags & EXT4_GET_BLOCKS_ZERO && map->m_flags & EXT4_MAP_MAPPED && map->m_flags & EXT4_MAP_NEW) { clean_bdev_aliases(inode->i_sb->s_bdev, map->m_pblk, map->m_len); ret = ext4_issue_zeroout(inode, map->m_lblk, map->m_pblk, map->m_len); if (ret) { retval = ret; goto out_sem; } } /* * If the extent has been zeroed out, we don't need to update * extent status tree. */ if ((flags & EXT4_GET_BLOCKS_PRE_IO) && ext4_es_lookup_extent(inode, map->m_lblk, &es)) { if (ext4_es_is_written(&es)) goto out_sem; } status = map->m_flags & EXT4_MAP_UNWRITTEN ? EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN; if (!(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) && !(status & EXTENT_STATUS_WRITTEN) && ext4_find_delalloc_range(inode, map->m_lblk, map->m_lblk + map->m_len - 1)) status |= EXTENT_STATUS_DELAYED; ret = ext4_es_insert_extent(inode, map->m_lblk, map->m_len, map->m_pblk, status); if (ret < 0) { retval = ret; goto out_sem; } } out_sem: up_write((&EXT4_I(inode)->i_data_sem)); if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) { ret = check_block_validity(inode, map); if (ret != 0) return ret; /* * Inodes with freshly allocated blocks where contents will be * visible after transaction commit must be on transaction's * ordered data list. */ if (map->m_flags & EXT4_MAP_NEW && !(map->m_flags & EXT4_MAP_UNWRITTEN) && !(flags & EXT4_GET_BLOCKS_ZERO) && !IS_NOQUOTA(inode) && ext4_should_order_data(inode)) { if (flags & EXT4_GET_BLOCKS_IO_SUBMIT) ret = ext4_jbd2_inode_add_wait(handle, inode); else ret = ext4_jbd2_inode_add_write(handle, inode); if (ret) return ret; } } return retval; }

Contributors

PersonTokensPropCommitsCommitProp
zheng liuzheng liu36234.22%721.21%
jan karajan kara18917.86%618.18%
amir goldsteinamir goldstein17516.54%13.03%
dmitriy monakhovdmitriy monakhov948.88%26.06%
dave kleikampdave kleikamp837.84%13.03%
theodore tsotheodore tso474.44%412.12%
lukas czernerlukas czerner333.12%26.06%
aneesh kumaraneesh kumar282.65%13.03%
kazuya miokazuya mio151.42%13.03%
valerie clementvalerie clement131.23%13.03%
frank mayharfrank mayhar70.66%13.03%
aditya kaliaditya kali40.38%13.03%
eric sandeeneric sandeen40.38%13.03%
darrick j. wongdarrick j. wong10.09%13.03%
seunghun leeseunghun lee10.09%13.03%
tao matao ma10.09%13.03%
allison hendersonallison henderson10.09%13.03%
Total1058100.00%33100.00%

/* * Update EXT4_MAP_FLAGS in bh->b_state. For buffer heads attached to pages * we have to be careful as someone else may be manipulating b_state as well. */
static void ext4_update_bh_state(struct buffer_head *bh, unsigned long flags) { unsigned long old_state; unsigned long new_state; flags &= EXT4_MAP_FLAGS; /* Dummy buffer_head? Set non-atomically. */ if (!bh->b_page) { bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | flags; return; } /* * Someone else may be modifying b_state. Be careful! This is ugly but * once we get rid of using bh as a container for mapping information * to pass to / from get_block functions, this can go away. */ do { old_state = READ_ONCE(bh->b_state); new_state = (old_state & ~EXT4_MAP_FLAGS) | flags; } while (unlikely( cmpxchg(&bh->b_state, old_state, new_state) != old_state)); }

Contributors

PersonTokensPropCommitsCommitProp
jan karajan kara97100.00%1100.00%
Total97100.00%1100.00%


static int _ext4_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh, int flags) { struct ext4_map_blocks map; int ret = 0; if (ext4_has_inline_data(inode)) return -ERANGE; map.m_lblk = iblock; map.m_len = bh->b_size >> inode->i_blkbits; ret = ext4_map_blocks(ext4_journal_current_handle(), inode, &map, flags); if (ret > 0) { map_bh(bh, inode->i_sb, map.m_pblk); ext4_update_bh_state(bh, map.m_flags); bh->b_size = inode->i_sb->s_blocksize * map.m_len; ret = 0; } else if (ret == 0) { /* hole case, need to fill in bh->b_size */ bh->b_size = inode->i_sb->s_blocksize * map.m_len; } return ret; }

Contributors

PersonTokensPropCommitsCommitProp
amir goldsteinamir goldstein5134.00%110.00%
dave kleikampdave kleikamp4328.67%110.00%
ross zwislerross zwisler2416.00%110.00%
tao matao ma117.33%110.00%
theodore tsotheodore tso74.67%110.00%
jan karajan kara64.00%220.00%
aneesh kumaraneesh kumar42.67%110.00%
frank mayharfrank mayhar32.00%110.00%
eric sandeeneric sandeen10.67%110.00%
Total150100.00%10100.00%


int ext4_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh, int create) { return _ext4_get_block(inode, iblock, bh, create ? EXT4_GET_BLOCKS_CREATE : 0); }

Contributors

PersonTokensPropCommitsCommitProp
dave kleikampdave kleikamp1951.35%133.33%
amir goldsteinamir goldstein1643.24%133.33%
aneesh kumaraneesh kumar25.41%133.33%
Total37100.00%3100.00%

/* * Get block function used when preparing for buffered write if we require * creating an unwritten extent if blocks haven't been allocated. The extent * will be converted to written after the IO is complete. */
int ext4_get_block_unwritten(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { ext4_debug("ext4_get_block_unwritten: inode %lu, create flag %d\n", inode->i_ino, create); return _ext4_get_block(inode, iblock, bh_result, EXT4_GET_BLOCKS_IO_CREATE_EXT); }

Contributors

PersonTokensPropCommitsCommitProp
jan karajan kara2454.55%125.00%
dave kleikampdave kleikamp1840.91%125.00%
amir goldsteinamir goldstein12.27%125.00%
theodore tsotheodore tso12.27%125.00%
Total44100.00%4100.00%

/* Maximum number of blocks we map for direct IO at once. */ #define DIO_MAX_BLOCKS 4096 /* * Get blocks function for the cases that need to start a transaction - * generally difference cases of direct IO and DAX IO. It also handles retries * in case of ENOSPC. */
static int ext4_get_block_trans(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int flags) { int dio_credits; handle_t *handle; int retries = 0; int ret; /* Trim mapping request to maximum we can map at once for DIO */ if (bh_result->b_size >> inode->i_blkbits > DIO_MAX_BLOCKS) bh_result->b_size = DIO_MAX_BLOCKS << inode->i_blkbits; dio_credits = ext4_chunk_trans_blocks(inode, bh_result->b_size >> inode->i_blkbits); retry: handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, dio_credits); if (IS_ERR(handle)) return PTR_ERR(handle); ret = _ext4_get_block(inode, iblock, bh_result, flags); ext4_journal_stop(handle); if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) goto retry; return ret; }

Contributors

PersonTokensPropCommitsCommitProp
jan karajan kara13494.37%240.00%
theodore tsotheodore tso53.52%240.00%
dave kleikampdave kleikamp32.11%120.00%
Total142100.00%5100.00%

/* Get block function for DIO reads and writes to inodes without extents */
int ext4_dio_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh, int create) { /* We don't expect handle for direct IO */ WARN_ON_ONCE(ext4_journal_current_handle()); if (!create) return _ext4_get_block(inode, iblock, bh, 0); return ext4_get_block_trans(inode, iblock, bh, EXT4_GET_BLOCKS_CREATE); }

Contributors

PersonTokensPropCommitsCommitProp
jan karajan kara4985.96%350.00%
dave kleikampdave kleikamp58.77%116.67%
amir goldsteinamir goldstein23.51%116.67%
theodore tsotheodore tso11.75%116.67%
Total57100.00%6100.00%

/* * Get block function for AIO DIO writes when we create unwritten extent if * blocks are not allocated yet. The extent will be converted to written * after IO is complete. */
static int ext4_dio_get_block_unwritten_async(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { int ret; /* We don't expect handle for direct IO */ WARN_ON_ONCE(ext4_journal_current_handle()); ret = ext4_get_block_trans(inode, iblock, bh_result, EXT4_GET_BLOCKS_IO_CREATE_EXT); /* * When doing DIO using unwritten extents, we need io_end to convert * unwritten extents to written on IO completion. We allocate io_end * once we spot unwritten extent and store it in b_private. Generic * DIO code keeps b_private set and furthermore passes the value to * our completion callback in 'private' argument. */ if (!ret && buffer_unwritten(bh_result)) { if (!bh_result->b_private) { ext4_io_end_t *io_end; io_end = ext4_init_io_end(inode, GFP_KERNEL); if (!io_end) return -ENOMEM; bh_result->b_private = io_end; ext4_set_io_unwritten_flag(inode, io_end); } set_buffer_defer_completion(bh_result); } return ret; }

Contributors

PersonTokensPropCommitsCommitProp
jan karajan kara8173.64%444.44%
dave kleikampdave kleikamp2320.91%111.11%
frank mayharfrank mayhar21.82%111.11%
amir goldsteinamir goldstein21.82%111.11%
theodore tsotheodore tso21.82%222.22%
Total110100.00%9100.00%

/* * Get block function for non-AIO DIO writes when we create unwritten extent if * blocks are not allocated yet. The extent will be converted to written * after IO is complete from ext4_ext_direct_IO() function. */
static int ext4_dio_get_block_unwritten_sync(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { int ret; /* We don't expect handle for direct IO */ WARN_ON_ONCE(ext4_journal_current_handle()); ret = ext4_get_block_trans(inode, iblock, bh_result, EXT4_GET_BLOCKS_IO_CREATE_EXT); /* * Mark inode as having pending DIO writes to unwritten extents. * ext4_ext_direct_IO() checks this flag and converts extents to * written. */ if (!ret && buffer_unwritten(bh_result)) ext4_set_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN); return ret; }

Contributors

PersonTokensPropCommitsCommitProp
jan karajan kara3959.09%342.86%
dave kleikampdave kleikamp2131.82%114.29%
amir goldsteinamir goldstein46.06%114.29%
theodore tsotheodore tso11.52%114.29%
jiaying zhangjiaying zhang11.52%114.29%
Total66100.00%7100.00%


static int ext4_dio_get_block_overwrite(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { int ret; ext4_debug("ext4_dio_get_block_overwrite: inode %lu, create flag %d\n", inode->i_ino, create); /* We don't expect handle for direct IO */ WARN_ON_ONCE(ext4_journal_current_handle()); ret = _ext4_get_block(inode, iblock, bh_result, 0); /* * Blocks should have been preallocated! ext4_file_write_iter() checks * that. */ WARN_ON_ONCE(!buffer_mapped(bh_result) || buffer_unwritten(bh_result)); return ret; }

Contributors

PersonTokensPropCommitsCommitProp
jan karajan kara4662.16%250.00%
amir goldsteinamir goldstein1621.62%125.00%
dave kleikampdave kleikamp1216.22%125.00%
Total74100.00%4100.00%

/* * `handle' can be NULL if create is zero */
struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode, ext4_lblk_t block, int map_flags) { struct ext4_map_blocks map; struct buffer_head *bh; int create = map_flags & EXT4_GET_BLOCKS_CREATE; int err; J_ASSERT(handle != NULL || create == 0); map.m_lblk = block; map.m_len = 1; err = ext4_map_blocks(handle, inode, &map, map_flags); if (err == 0) return create ? ERR_PTR(-ENOSPC) : NULL; if (err < 0) return ERR_PTR(err); bh = sb_getblk(inode->i_sb, map.m_pblk); if (unlikely(!bh)) return ERR_PTR(-ENOMEM); if (map.m_flags & EXT4_MAP_NEW) { J_ASSERT(create != 0); J_ASSERT(handle != NULL); /* * Now that we do not always journal data, we should * keep in mind whether this should always journal the * new buffer as metadata. For now, regular file * writes use ext4_get_block instead, so it's not a * problem. */ lock_buffer(bh); BUFFER_TRACE(bh, "call get_create_access"); err = ext4_journal_get_create_access(handle, bh); if (unlikely(err)) { unlock_buffer(bh); goto errout; } if (!buffer_uptodate(bh)) { memset(bh->b_data, 0, inode->i_sb->s_blocksize); set_buffer_uptodate(bh); } unlock_buffer(bh); BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata"); err = ext4_handle_dirty_metadata(handle, inode, bh); if (unlikely(err)) goto errout; } else BUFFER_TRACE(bh, "not a new buffer"); return bh; errout: brelse(bh); return ERR_PTR(err); }

Contributors

PersonTokensPropCommitsCommitProp
dave kleikampdave kleikamp11540.35%17.14%
amir goldsteinamir goldstein8830.88%17.14%
theodore tsotheodore tso6723.51%642.86%
namhyung kimnamhyung kim62.11%17.14%
wang shilongwang shilong31.05%17.14%
frank mayharfrank mayhar31.05%17.14%
aneesh kumaraneesh kumar10.35%17.14%
mingming caomingming cao10.35%17.14%
liang xieliang xie10.35%17.14%
Total285100.00%14100.00%


struct buffer_head *ext4_bread(handle_t *handle, struct inode *inode, ext4_lblk_t block, int map_flags) { struct buffer_head *bh; bh = ext4_getblk(handle, inode, block, map_flags); if (IS_ERR(bh)) return bh; if (!bh || buffer_uptodate(bh)) return bh; ll_rw_block(REQ_OP_READ, REQ_META | REQ_PRIO, 1, &bh); wait_on_buffer(bh); if (buffer_uptodate(bh)) return bh; put_bh(bh); return ERR_PTR(-EIO); }

Contributors

PersonTokensPropCommitsCommitProp
dave kleikampdave kleikamp3937.50%19.09%
amir goldsteinamir goldstein3533.65%19.09%
theodore tsotheodore tso1918.27%327.27%
jiaying zhangjiaying zhang43.85%19.09%
christoph hellwigchristoph hellwig32.88%218.18%
michael christiemichael christie21.92%19.09%
aneesh kumaraneesh kumar10.96%19.09%
alex tomasalex tomas10.96%19.09%
Total104100.00%11100.00%


int ext4_walk_page_buffers(handle_t *handle, struct buffer_head *head, unsigned from, unsigned to, int *partial, int (*fn)(handle_t *handle, struct buffer_head *bh)) { struct buffer_head *bh; unsigned block_start, block_end; unsigned blocksize = head->b_size; int err, ret = 0; struct buffer_head *next; for (bh = head, block_start = 0; ret == 0 && (bh != head || !block_start); block_start = block_end, bh = next) { next = bh->b_this_page; block_end = block_start + blocksize; if (block_end <= from || block_start >= to) { if (partial && !buffer_uptodate(bh)) *partial = 1; continue; } err = (*fn)(handle, bh); if (!ret) ret = err; } return ret; }

Contributors

PersonTokensPropCommitsCommitProp
amir goldsteinamir goldstein12374.10%133.33%
dave kleikampdave kleikamp4225.30%133.33%
tao matao ma10.60%133.33%
Total166100.00%3100.00%

/* * To preserve ordering, it is essential that the hole instantiation and * the data write be encapsulated in a single transaction. We cannot * close off a transaction and start a new one between the ext4_get_block() * and the commit_write(). So doing the jbd2_journal_start at the start of * prepare_write() is the right place. * * Also, this function can nest inside ext4_writepage(). In that case, we * *know* that ext4_writepage() has generated enough buffer credits to do the * whole page. So we won't block on the journal in that case, which is good, * because the caller may be PF_MEMALLOC. * * By accident, ext4 can be reentered when a transaction is open via * quota file writes. If we were to commit the transaction while thus * reentered, there can be a deadlock - we would be holding a quota * lock, and the commit would never complete if another thread had a * transaction open and was blocking on the quota lock - a ranking * violation. * * So what we do is to rely on the fact that jbd2_journal_stop/journal_start * will _not_ run commit under these circumstances because handle->h_ref * is elevated. We'll still have enough credits for the tiny quotafile * write. */
int do_journal_get_write_access(handle_t *handle, struct buffer_head *bh) { int dirty = buffer_dirty(bh); int ret; if (!buffer_mapped(bh) || buffer_freed(bh)) return 0; /* * __block_write_begin() could have dirtied some buffers. Clean * the dirty bit as jbd2_journal_get_write_access() could complain * otherwise about fs integrity issues. Setting of the dirty bit * by __block_write_begin() isn't a real problem here as we clear * the bit before releasing a page lock and thus writeback cannot * ever write the buffer. */ if (dirty) clear_buffer_dirty(bh); BUFFER_TRACE(bh, "get write access"); ret = ext4_journal_get_write_access(handle, bh); if (!ret && dirty) ret = ext4_handle_dirty_metadata(handle, NULL, bh); return ret; }

Contributors

PersonTokensPropCommitsCommitProp
amir goldsteinamir goldstein4551.14%114.29%
dave kleikampdave kleikamp3034.09%114.29%
liang xieliang xie77.95%114.29%
theodore tsotheodore tso33.41%228.57%
jan karajan kara22.27%114.29%
peter huewepeter huewe11.14%114.29%
Total88100.00%7100.00%

#ifdef CONFIG_EXT4_FS_ENCRYPTION
static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len, get_block_t *get_block) { unsigned from = pos & (PAGE_SIZE - 1); unsigned to = from + len; struct inode *inode = page->mapping->host; unsigned block_start, block_end; sector_t block; int err = 0; unsigned blocksize = inode->i_sb->s_blocksize; unsigned bbits; struct buffer_head *bh, *head, *wait[2], **wait_bh = wait; bool decrypt = false; BUG_ON(!PageLocked(page)); BUG_ON(from > PAGE_SIZE); BUG_ON(to > PAGE_SIZE); BUG_ON(from > to); if (!page_has_buffers(page)) create_empty_buffers(page, blocksize, 0); head = page_buffers(page); bbits = ilog2(blocksize); block = (sector_t)page->index << (PAGE_SHIFT - bbits); for (bh = head, block_start = 0; bh != head || !block_start; block++, block_start = block_end, bh = bh->b_this_page) { block_end = block_start + blocksize; if (block_end <= from || block_start >= to) { if (PageUptodate(page)) { if (!buffer_uptodate(bh)) set_buffer_uptodate(bh); } continue; } if (buffer_new(bh)) clear_buffer_new(bh); if (!buffer_mapped(bh)) { WARN_ON(bh->b_size != blocksize); err = get_block(inode, block, bh, 1); if (err) break; if (buffer_new(bh)) { clean_bdev_bh_alias(bh); if (PageUptodate(page)) { clear_buffer_new(bh); set_buffer_uptodate(bh); mark_buffer_dirty(bh); continue; } if (block_end > to || block_start < from) zero_user_segments(page, to, block_end, block_start, from); continue; } } if (PageUptodate(page)) { if (!buffer_uptodate(bh)) set_buffer_uptodate(bh); continue; } if (!buffer_uptodate(bh) && !buffer_delay(bh) && !buffer_unwritten(bh) && (block_start < from || block_end > to)) { ll_rw_block(REQ_OP_READ, 0, 1, &bh); *wait_bh++ = bh; decrypt = ext4_encrypted_inode(inode) && S_ISREG(inode->i_mode); } } /* * If we issued read requests, let them complete. */ while (wait_bh > wait) { wait_on_buffer(*--wait_bh); if (!buffer_uptodate(*wait_bh)) err = -EIO; } if (unlikely(err)) page_zero_new_buffers(page, from, to); else if (decrypt) err = fscrypt_decrypt_page(page->mapping->host, page, PAGE_SIZE, 0, page->index); return err; }

Contributors

PersonTokensPropCommitsCommitProp
michael halcrowmichael halcrow47390.44%17.69%
dave kleikampdave kleikamp152.87%17.69%
david gstirdavid gstir142.68%323.08%
amir goldsteinamir goldstein61.15%17.69%
kirill a. shutemovkirill a. shutemov40.76%17.69%
jan karajan kara30.57%215.38%
michael christiemichael christie30.57%17.69%
liang xieliang xie20.38%17.69%
theodore tsotheodore tso20.38%17.69%
jaegeuk kimjaegeuk kim10.19%17.69%
Total523100.00%13100.00%

#endif
static int ext4_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) { struct inode *inode = mapping->host; int ret, needed_blocks; handle_t *handle; int retries = 0; struct page *page; pgoff_t index; unsigned from, to; trace_ext4_write_begin(inode, pos, len, flags); /* * Reserve one block more for addition to orphan list in case * we allocate blocks but write fails for some reason */ needed_blocks = ext4_writepage_trans_blocks(inode) + 1; index = pos >> PAGE_SHIFT; from = pos & (PAGE_SIZE - 1); to = from + len; if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) { ret = ext4_try_to_write_inline_data(mapping, inode, pos, len, flags, pagep); if (ret < 0) return ret; if (ret == 1) return 0; } /* * grab_cache_page_write_begin() can take a long time if the * system is thrashing due to memory pressure, or if the page * is being written back. So grab it first before we start * the transaction handle. This also allows us to allocate * the page (if needed) without using GFP_NOFS. */ retry_grab: page = grab_cache_page_write_begin(mapping, index, flags); if (!page) return -ENOMEM; unlock_page(page); retry_journal: handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, needed_blocks); if (IS_ERR(handle)) { put_page(page); return PTR_ERR(handle); } lock_page(page); if (page->mapping != mapping) { /* The page got truncated from under us */ unlock_page(page); put_page(page); ext4_journal_stop(handle); goto retry_grab; } /* In case writeback began while the page was unlocked */ wait_for_stable_page(page); #ifdef CONFIG_EXT4_FS_ENCRYPTION if (ext4_should_dioread_nolock(inode)) ret = ext4_block_write_begin(page, pos, len, ext4_get_block_unwritten); else ret = ext4_block_write_begin(page, pos, len, ext4_get_block); #else if (ext4_should_dioread_nolock(inode)) ret = __block_write_begin(page, pos, len, ext4_get_block_unwritten); else ret = __block_write_begin(page, pos, len, ext4_get_block); #endif if (!ret && ext4_should_journal_data(inode)) { ret = ext4_walk_page_buffers(handle, page_buffers(page), from, to, NULL, do_journal_get_write_access); } if (ret) { unlock_page(page); /* * __block_write_begin may have instantiated a few blocks * outside i_size. Trim these off again. Don't need * i_size_read because we hold i_mutex. * * Add inode to orphan list in case we crash before * truncate finishes */ if (pos + len > inode->i_size && ext4_can_truncate(inode)) ext4_orphan_add(handle, inode); ext4_journal_stop(handle); if (pos + len > inode->i_size) { ext4_truncate_failed_write(inode); /* * If truncate failed early the inode might * still be on the orphan list; we need to * make sure the inode is removed from the * orphan list in that case. */ if (inode->i_nlink) ext4_orphan_del(NULL, inode); } if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) goto retry_journal; put_page(page); return ret; } *pagep = page; return ret; }

Contributors

PersonTokensPropCommitsCommitProp
amir goldsteinamir goldstein14931.37%15.00%
theodore tsotheodore tso10121.26%525.00%
dave kleikampdave kleikamp8217.26%15.00%
tao matao ma428.84%15.00%
michael halcrowmichael halcrow408.42%15.00%
aneesh kumaraneesh kumar316.53%210.00%
jiaying zhangjiaying zhang81.68%15.00%
jan karajan kara81.68%315.00%
kirill a. shutemovkirill a. shutemov51.05%15.00%
alex tomasalex tomas40.84%15.00%
mingming caomingming cao20.42%15.00%
dmitriy monakhovdmitriy monakhov20.42%15.00%
eric sandeeneric sandeen10.21%15.00%
Total475100.00%20100.00%

/* For write_end() in data=journal mode */
static int write_end_fn(handle_t *handle, struct buffer_head *bh) { int ret; if (!buffer_mapped(bh) || buffer_freed(bh)) return 0; set_buffer_uptodate(bh); ret = ext4_handle_dirty_metadata(handle, NULL, bh); clear_buffer_meta(bh); clear_buffer_prio(bh); return ret; }

Contributors

PersonTokensPropCommitsCommitProp
theodore tsotheodore tso2336.51%360.00%
amir goldsteinamir goldstein2031.75%120.00%
aneesh kumaraneesh kumar2031.75%120.00%
Total63100.00%5100.00%

/* * We need to pick up the new inode size which generic_commit_write gave us * `file' can be NULL - eg, when called from page_symlink(). * * ext4 never places buffers on inode->i_mapping->private_list. metadata * buffers are managed internally. */
static int ext4_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { handle_t *handle = ext4_journal_current_handle(); struct inode *inode = mapping->host; loff_t old_size = inode->i_size; int ret = 0, ret2; int i_size_changed = 0; trace_ext4_write_end(inode, pos, len, copied); if (ext4_has_inline_data(inode)) { ret = ext4_write_inline_data_end(inode, pos, len, copied, page); if (ret < 0) goto errout; copied = ret; } else copied = block_write_end(file, mapping, pos, len, copied, page, fsdata); /* * it's important to update i_size while still holding page lock: * page writeout could otherwise come in and zero beyond i_size. */ i_size_changed = ext4_update_inode_size(inode, pos + copied); unlock_page(page); put_page(page); if (old_size < pos) pagecache_isize_extended(inode, old_size, pos); /* * Don't mark the inode dirty under page lock. First, it unnecessarily * makes the holding time of page lock longer. Second, it forces lock * ordering of page lock and transaction start for journaling * filesystems. */ if (i_size_changed) ext4_mark_inode_dirty(handle, inode); if (pos + len > inode->i_size && ext4_can_truncate(inode)) /* if we have allocated more blocks and copied * less. We will have blocks allocated outside * inode->i_size. So truncate them */ ext4_orphan_add(handle, inode); errout: ret2 = ext4_journal_stop(handle); if (!ret) ret = ret2; if (pos + len > inode->i_size) { ext4_truncate_failed_write(inode); /* * If truncate failed early the inode might still be * on the orphan list; we need to make sure the inode * is removed from the orphan list in that case. */ if (inode->i_nlink) ext4_orphan_del(NULL, inode); } return ret ? ret : copied; }

Contributors

PersonTokensPropCommitsCommitProp
amir goldsteinamir goldstein7628.68%14.35%
theodore tsotheodore tso5821.89%1043.48%
aneesh kumaraneesh kumar4215.85%521.74%
zheng liuzheng liu2910.94%14.35%
wang xiaoguangwang xiaoguang228.30%14.35%
tao matao ma207.55%14.35%
mingming caomingming cao103.77%14.35%
dmitriy monakhovdmitriy monakhov72.64%28.70%
kirill a. shutemovkirill a. shutemov10.38%14.35%
Total265100.00%23100.00%

/* * This is a private version of page_zero_new_buffers() which doesn't * set the buffer to be dirty, since in data=journalled mode we need * to call ext4_handle_dirty_metadata() instead. */
static void zero_new_buffers(struct page *page, unsigned from, unsigned to) { unsigned int block_start = 0, block_end; struct buffer_head *head, *bh; bh = head = page_buffers(page); do { block_end = block_start + bh->b_size; if (buffer_new(bh)) { if (block_end > from && block_start < to) { if (!PageUptodate(page)) { unsigned start, size; start = max(from, block_start); size = min(to, block_end) - start; zero_user(page, start, size); set_buffer_uptodate(bh); } clear_buffer_new(bh); } } block_start = block_end; bh = bh->b_this_page; } while (bh != head); }

Contributors

PersonTokensPropCommitsCommitProp
theodore tsotheodore tso145100.00%1100.00%
Total145100.00%1100.00%


static int ext4_journalled_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { handle_t *handle = ext4_journal_current_handle(); struct inode *inode = mapping->host; loff_t old_size = inode->i_size; int ret = 0, ret2; int partial = 0; unsigned from, to; int size_changed = 0; trace_ext4_journalled_write_end(inode, pos, len, copied); from = pos & (PAGE_SIZE - 1); to = from + len; BUG_ON(!ext4_handle_valid(handle)); if (ext4_has_inline_data(inode)) copied = ext4_write_inline_data_end(inode, pos, len, copied, page); else { if (copied < len) { if (!PageUptodate(page)) copied = 0; zero_new_buffers(page, from+copied, to); } ret = ext4_walk_page_buffers(handle, page_buffers(page), from, to, &partial, write_end_fn); if (!partial) SetPageUptodate(page); } size_changed = ext4_update_inode_size(inode, pos + copied); ext4_set_inode_state(inode, EXT4_STATE_JDATA); EXT4_I(inode)->i_datasync_tid = handle->h_transaction->t_tid; unlock_page(page); put_page(page); if (old_size < pos) pagecache_isize_extended(inode, old_size, pos); if (size_changed) { ret2 = ext4_mark_inode_dirty(handle, inode); if (!ret) ret = ret2; } if (pos + len > inode->i_size && ext4_can_truncate(inode)) /* if we have allocated more blocks and copied * less. We will have blocks allocated outside * inode->i_size. So truncate them */ ext4_orphan_add(handle, inode); ret2 = ext4_journal_stop(handle); if (!ret) ret = ret2; if (pos + len > inode->i_size) { ext4_truncate_failed_write(inode); /* * If truncate failed early the inode might still be * on the orphan list; we need to make sure the inode * is removed from the orphan list in that case. */ if (inode->i_nlink) ext4_orphan_del(NULL, inode); } return ret ? ret : copied; }

Contributors

PersonTokensPropCommitsCommitProp
amir goldsteinamir goldstein16545.96%17.14%
dave kleikampdave kleikamp6217.27%17.14%
theodore tsotheodore tso349.47%214.29%
tao matao ma267.24%214.29%
wang xiaoguangwang xiaoguang226.13%17.14%
jan karajan kara226.13%214.29%
dmitriy monakhovdmitriy monakhov164.46%214.29%
curt wohlgemuthcurt wohlgemuth92.51%17.14%
kirill a. shutemovkirill a. shutemov20.56%17.14%
mingming caomingming cao10.28%17.14%
Total359100.00%14100.00%

/* * Reserve space for a single cluster */
static int ext4_da_reserve_space(struct inode *inode) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_inode_info *ei = EXT4_I(inode); int ret; /* * We will charge metadata quota at writeout time; this saves * us from metadata over-estimation, though we may go over by * a small amount in the end. Here we just reserve for data. */ ret = dquot_reserve_block(inode, EXT4_C2B(sbi, 1)); if (ret) return ret; spin_lock(&ei->i_block_reservation_lock); if (ext4_claim_free_clusters(sbi, 1, 0)) { spin_unlock(&ei->i_block_reservation_lock); dquot_release_reservation_block(inode, EXT4_C2B(sbi, 1)); return -ENOSPC; } ei->i_reserved_data_blocks++; trace_ext4_da_reserve_space(inode); spin_unlock(&ei->i_block_reservation_lock); return 0; /* success */ }

Contributors

PersonTokensPropCommitsCommitProp
amir goldsteinamir goldstein5241.60%114.29%
theodore tsotheodore tso4636.80%342.86%
dave kleikampdave kleikamp2016.00%114.29%
eric whitneyeric whitney54.00%114.29%
aditya kaliaditya kali21.60%114.29%
Total125100.00%7100.00%


static void ext4_da_release_space(struct inode *inode, int to_free) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_inode_info *ei = EXT4_I(inode); if (!to_free) return; /* Nothing to release, exit */ spin_lock(&EXT4_I(inode)->i_block_reservation_lock); trace_ext4_da_release_space(inode, to_free); if (unlikely(to_free > ei->i_reserved_data_blocks)) { /* * if there aren't enough reserved blocks, then the * counter is messed up somewhere. Since this * function is called from invalidate page, it's * harmless to return without any action. */ ext4_warning(inode->i_sb, "ext4_da_release_space: " "ino %lu, to_free %d with only %d reserved " "data blocks", inode->i_ino, to_free, ei->i_reserved_data_blocks); WARN_ON(1); to_free = ei->i_reserved_data_blocks; } ei->i_reserved_data_blocks -= to_free; /* update fs dirty data blocks counter */ percpu_counter_sub(&sbi->s_dirtyclusters_counter, to_free); spin_unlock(&EXT4_I(inode)->i_block_reservation_lock); dquot_release_reservation_block(inode, EXT4_C2B(sbi, to_free)); }

Contributors

PersonTokensPropCommitsCommitProp
amir goldsteinamir goldstein9262.59%114.29%
dave kleikampdave kleikamp4530.61%114.29%
aditya kaliaditya kali53.40%114.29%
theodore tsotheodore tso32.04%342.86%
frank mayharfrank mayhar21.36%114.29%
Total147100.00%7100.00%


static void ext4_da_page_release_reservation(struct page *page, unsigned int offset, unsigned int length) { int to_release = 0, contiguous_blks = 0; struct buffer_head *head, *bh; unsigned int curr_off = 0; struct inode *inode = page->mapping->host; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); unsigned int stop = offset + length; int num_clusters; ext4_fsblk_t lblk; BUG_ON(stop > PAGE_SIZE || stop < length); head = page_buffers(page); bh = head; do { unsigned int next_off = curr_off + bh->b_size; if (next_off > stop) break; if ((offset <= curr_off) && (buffer_delay(bh))) { to_release++; contiguous_blks++; clear_buffer_delay(bh); } else if (contiguous_blks) { lblk = page->index << (PAGE_SHIFT - inode->i_blkbits); lblk += (curr_off >> inode->i_blkbits) - contiguous_blks; ext4_es_remove_extent(inode, lblk, contiguous_blks); contiguous_blks = 0; } curr_off = next_off; } while ((bh = bh->b_this_page) != head); if (contiguous_blks) { lblk = page->index << (PAGE_SHIFT - inode->i_blkbits); lblk += (curr_off >> inode->i_blkbits) - contiguous_blks; ext4_es_remove_extent(inode, lblk, contiguous_blks); } /* If we have released all the blocks belonging to a cluster, then we * need to release the reserved space for that cluster. */ num_clusters = EXT4_NUM_B2C(sbi, to_release); while (num_clusters > 0) { lblk = (page->index << (PAGE_SHIFT - inode->i_blkbits)) + ((num_clusters - 1) << sbi->s_cluster_bits); if (sbi->s_cluster_ratio == 1 || !ext4_find_delalloc_cluster(inode, lblk)) ext4_da_release_space(inode, 1); num_clusters--; } }

Contributors

PersonTokensPropCommitsCommitProp
lukas czernerlukas czerner9629.54%228.57%
aditya kaliaditya kali9027.69%114.29%
amir goldsteinamir goldstein7121.85%114.29%
dave kleikampdave kleikamp3510.77%114.29%
zheng liuzheng liu298.92%114.29%
kirill a. shutemovkirill a. shutemov41.23%114.29%
Total325100.00%7100.00%

/* * Delayed allocation stuff */ struct mpage_da_data { struct inode *inode; struct writeback_control *wbc; pgoff_t first_page; /* The first page to write */ pgoff_t next_page; /* Current page to examine */ pgoff_t last_page; /* Last page to examine */ /* * Extent to map - this can be after first_page because that can be * fully mapped. We somewhat abuse m_flags to store whether the extent * is delalloc or unwritten. */ struct ext4_map_blocks map; struct ext4_io_submit io_submit; /* IO submission data */ };
static void mpage_release_unused_pages(struct mpage_da_data *mpd, bool invalidate) { int nr_pages, i; pgoff_t index, end; struct pagevec pvec; struct inode *inode = mpd->inode; struct address_space *mapping = inode->i_mapping; /* This is necessary when next_page == 0. */ if (mpd->first_page >= mpd->next_page) return; index = mpd->first_page; end = mpd->next_page - 1; if (invalidate) { ext4_lblk_t start, last; start = index << (PAGE_SHIFT - inode->i_blkbits); last = end << (PAGE_SHIFT - inode->i_blkbits); ext4_es_remove_extent(inode, start, last - start + 1); } pagevec_init(&pvec, 0); while (index <= end) { nr_pages = pagevec_lookup(&pvec, mapping, index, PAGEVEC_SIZE); if (nr_pages == 0) break; for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; if (page->index > end) break; BUG_ON(!PageLocked(page)); BUG_ON(PageWriteback(page)); if (invalidate) { if (page_mapped(page)) clear_page_dirty_for_io(page); block_invalidatepage(page, 0, PAGE_SIZE); ClearPageUptodate(page); } unlock_page(page); } index = pvec.pages[nr_pages - 1]->index + 1; pagevec_release(&pvec); } }

Contributors

PersonTokensPropCommitsCommitProp
jan karajan kara11844.03%330.00%
amir goldsteinamir goldstein8230.60%110.00%
dave kleikampdave kleikamp4215.67%110.00%
wangguangwangguang124.48%110.00%
nick pigginnick piggin72.61%110.00%
kirill a. shutemovkirill a. shutemov31.12%110.00%
aneesh kumaraneesh kumar31.12%110.00%
christoph hellwigchristoph hellwig10.37%110.00%
Total268100.00%10100.00%


static void ext4_print_free_blocks(struct inode *inode) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct super_block *sb = inode->i_sb; struct ext4_inode_info *ei = EXT4_I(inode); ext4_msg(sb, KERN_CRIT, "Total free blocks count %lld", EXT4_C2B(EXT4_SB(inode->i_sb), ext4_count_free_clusters(sb))); ext4_msg(sb, KERN_CRIT, "Free/Dirty block details"); ext4_msg(sb, KERN_CRIT, "free_blocks=%lld", (long long) EXT4_C2B(EXT4_SB(sb), percpu_counter_sum(&sbi->s_freeclusters_counter))); ext4_msg(sb, KERN_CRIT, "dirty_blocks=%lld", (long long) EXT4_C2B(EXT4_SB(sb), percpu_counter_sum(&sbi->s_dirtyclusters_counter))); ext4_msg(sb, KERN_CRIT, "Block reservation details"); ext4_msg(sb, KERN_CRIT, "i_reserved_data_blocks=%u", ei->i_reserved_data_blocks); return; }

Contributors

PersonTokensPropCommitsCommitProp
jan karajan kara12378.85%111.11%
dave kleikampdave kleikamp117.05%111.11%
amir goldsteinamir goldstein106.41%111.11%
aneesh kumaraneesh kumar53.21%222.22%
jiaying zhangjiaying zhang31.92%111.11%
nick pigginnick piggin21.28%111.11%
andrew mortonandrew morton10.64%111.11%
yongqiang yangyongqiang yang10.64%111.11%
Total156100.00%9100.00%


static int ext4_bh_delay_or_unwritten(handle_t *handle, struct buffer_head *bh) { return (buffer_delay(bh) || buffer_unwritten(bh)) && buffer_dirty(bh); }

Contributors

PersonTokensPropCommitsCommitProp
jan karajan kara2781.82%150.00%
dave kleikampdave kleikamp618.18%150.00%
Total33100.00%2100.00%

/* * This function is grabs code from the very beginning of * ext4_map_blocks, but assumes that the caller is from delayed write * time. This function looks up the requested blocks and sets the * buffer delay bit under the protection of i_data_sem. */
static int ext4_da_map_blocks(struct inode *inode, sector_t iblock, struct ext4_map_blocks *map, struct buffer_head *bh) { struct extent_status es; int retval; sector_t invalid_block = ~((sector_t) 0xffff); #ifdef ES_AGGRESSIVE_TEST struct ext4_map_blocks orig_map; memcpy(&orig_map, map, sizeof(*map)); #endif if (invalid_block < ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es)) invalid_block = ~0; map->m_flags = 0; ext_debug("ext4_da_map_blocks(): inode %lu, max_blocks %u," "logical block %lu\n", inode->i_ino, map->m_len, (unsigned long) map->m_lblk); /* Lookup extent status tree firstly */ if (ext4_es_lookup_extent(inode, iblock, &es)) { if (ext4_es_is_hole(&es)) { retval = 0; down_read(&EXT4_I(inode)->i_data_sem); goto add_delayed; } /* * Delayed extent could be allocated by fallocate. * So we need to check it. */ if (ext4_es_is_delayed(&es) && !ext4_es_is_unwritten(&es)) { map_bh(bh, inode->i_sb, invalid_block); set_buffer_new(bh); set_buffer_delay(bh); return 0; } map->m_pblk = ext4_es_pblock(&es) + iblock - es.es_lblk; retval = es.es_len - (iblock - es.es_lblk); if (retval > map->m_len) retval = map->m_len; map->m_len = retval; if (ext4_es_is_written(&es)) map->m_flags |= EXT4_MAP_MAPPED; else if (ext4_es_is_unwritten(&es)) map->m_flags |= EXT4_MAP_UNWRITTEN; else BUG_ON(1); #ifdef ES_AGGRESSIVE_TEST ext4_map_blocks_es_recheck(NULL, inode, map, &orig_map, 0); #endif return retval; } /* * Try to see if we can get the block without requesting a new * file system block. */ down_read(&EXT4_I(inode)->i_data_sem); if (ext4_has_inline_data(inode)) retval = 0; else if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) retval = ext4_ext_map_blocks(NULL, inode, map, 0); else retval = ext4_ind_map_blocks(NULL, inode, map, 0); add_delayed: if (retval == 0) { int ret; /* * XXX: __block_prepare_write() unmaps passed block, * is it OK? */ /* * If the block was allocated from previously allocated cluster, * then we don't need to reserve it again. However we still need * to reserve metadata for every block we're going to write. */ if (EXT4_SB(inode->i_sb)->s_cluster_ratio == 1 || !ext4_find_delalloc_cluster(inode, map->m_lblk)) { ret = ext4_da_reserve_space(inode); if (ret) { /* not enough space to reserve */ retval = ret; goto out_unlock; } } ret = ext4_es_insert_extent(inode, map->m_lblk, map->m_len, ~0, EXTENT_STATUS_DELAYED); if (ret) { retval = ret; goto out_unlock; } map_bh(bh, inode->i_sb, invalid_block); set_buffer_new(bh); set_buffer_delay(bh); } else if (retval > 0) { int ret; unsigned int status; if (unlikely(retval != map->m_len)) { ext4_warning(inode->i_sb, "ES len assertion failed for inode " "%lu: retval %d != map->m_len %d", inode->i_ino, retval, map->m_len); WARN_ON(1); } status = map->m_flags & EXT4_MAP_UNWRITTEN ? EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN; ret = ext4_es_insert_extent(inode, map->m_lblk, map->m_len, map->m_pblk, status); if (ret != 0) retval = ret; } out_unlock: up_read((&EXT4_I(inode)->i_data_sem)); return retval; }

Contributors

PersonTokensPropCommitsCommitProp
jan karajan kara42070.47%419.05%
aneesh kumaraneesh kumar518.56%14.76%
amir goldsteinamir goldstein427.05%14.76%
dave kleikampdave kleikamp274.53%14.76%
zheng liuzheng liu244.03%314.29%
theodore tsotheodore tso142.35%628.57%
lukas czernerlukas czerner91.51%29.52%
nick pigginnick piggin50.84%14.76%
eric sandeeneric sandeen30.50%14.76%
eric whitneyeric whitney10.17%14.76%
Total596100.00%21100.00%

/* * This is a special get_block_t callback which is used by * ext4_da_write_begin(). It will either return mapped block or * reserve space for a single block. * * For delayed buffer_head we have BH_Mapped, BH_New, BH_Delay set. * We also have b_blocknr = -1 and b_bdev initialized properly * * For unwritten buffer_head we have BH_Mapped, BH_New, BH_Unwritten set. * We also have b_blocknr = physicalblock mapping unwritten extent and b_bdev * initialized properly. */
int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, struct buffer_head *bh, int create) { struct ext4_map_blocks map; int ret = 0; BUG_ON(create == 0); BUG_ON(bh->b_size != inode->i_sb->s_blocksize); map.m_lblk = iblock; map.m_len = 1; /* * first, we need to know whether the block is allocated already * preallocated blocks are unmapped but should treated * the same as allocated blocks. */ ret = ext4_da_map_blocks(inode, iblock, &map, bh); if (ret <= 0) return ret; map_bh(bh, inode->i_sb, map.m_pblk); ext4_update_bh_state(bh, map.m_flags); if (buffer_unwritten(bh)) { /* A delayed write to unwritten bh should be marked * new and mapped. Mapped ensures that we don't do * get_block multiple times when we write to the same * offset and new ensures that we do proper zero out * for partial write. */ set_buffer_new(bh); set_buffer_mapped(bh); } return 0; }

Contributors

PersonTokensPropCommitsCommitProp
jan karajan kara9874.81%342.86%
amir goldsteinamir goldstein1410.69%114.29%
dave kleikampdave kleikamp118.40%114.29%
aneesh kumaraneesh kumar75.34%114.29%
theodore tsotheodore tso10.76%114.29%
Total131100.00%7100.00%


static int bget_one(handle_t *handle, struct buffer_head *bh) { get_bh(bh); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
jan karajan kara1982.61%125.00%
nick pigginnick piggin28.70%125.00%
mingming caomingming cao14.35%125.00%
aneesh kumaraneesh kumar14.35%125.00%
Total23100.00%4100.00%


static int bput_one(handle_t *handle, struct buffer_head *bh) { put_bh(bh); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
jan karajan kara1982.61%133.33%
aneesh kumaraneesh kumar313.04%133.33%
dave kleikampdave kleikamp14.35%133.33%
Total23100.00%3100.00%


static int __ext4_journalled_writepage(struct page *page, unsigned int len) { struct address_space *mapping = page->mapping; struct inode *inode = mapping->host; struct buffer_head *page_bufs = NULL; handle_t *handle = NULL; int ret = 0, err = 0; int inline_data = ext4_has_inline_data(inode); struct buffer_head *inode_bh = NULL; ClearPageChecked(page); if (inline_data) { BUG_ON(page->index != 0); BUG_ON(len > ext4_get_max_inline_size(inode)); inode_bh = ext4_journalled_write_inline_data(inode, len, page); if (inode_bh == NULL) goto out; } else { page_bufs = page_buffers(page); if (!page_bufs) { BUG(); goto out; } ext4_walk_page_buffers(handle, page_bufs, 0, len, NULL, bget_one); } /* * We need to release the page lock before we start the * journal, so grab a reference so the page won't disappear * out from under us. */ get_page(page); unlock_page(page); handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, ext4_writepage_trans_blocks(inode)); if (IS_ERR(handle)) { ret = PTR_ERR(handle); put_page(page); goto out_no_pagelock; } BUG_ON(!ext4_handle_valid(handle)); lock_page(page); put_page(page); if (page->mapping != mapping) { /* The page got truncated from under us */ ext4_journal_stop(handle); ret = 0; goto out; } if (inline_data) { BUFFER_TRACE(inode_bh, "get write access"); ret = ext4_journal_get_write_access(handle, inode_bh); err = ext4_handle_dirty_metadata(handle, inode, inode_bh); } else { ret = ext4_walk_page_buffers(handle, page_bufs, 0, len, NULL, do_journal_get_write_access); err = ext4_walk_page_buffers(handle, page_bufs, 0, len, NULL, write_end_fn); } if (ret == 0) ret = err; EXT4_I(inode)->i_datasync_tid = handle->h_transaction->t_tid; err = ext4_journal_stop(handle); if (!ret) ret = err; if (!ext4_has_inline_data(inode)) ext4_walk_page_buffers(NULL, page_bufs, 0, len, NULL, bput_one); ext4_set_inode_state(inode, EXT4_STATE_JDATA); out: unlock_page(page); out_no_pagelock: brelse(inode_bh); return ret; }

Contributors

PersonTokensPropCommitsCommitProp
jan karajan kara23558.02%210.00%
theodore tsotheodore tso5714.07%420.00%
zheng liuzheng liu4210.37%15.00%
mingming caomingming cao245.93%315.00%
dmitriy monakhovdmitriy monakhov163.95%210.00%
amir goldsteinamir goldstein112.72%15.00%
liang xieliang xie71.73%15.00%
aditya kaliaditya kali51.23%15.00%
christoph hellwigchristoph hellwig30.74%15.00%
dave kleikampdave kleikamp20.49%15.00%
li zefanli zefan10.25%15.00%
aneesh kumaraneesh kumar10.25%15.00%
alex tomasalex tomas10.25%15.00%
Total405100.00%20100.00%

/* * Note that we don't need to start a transaction unless we're journaling data * because we should have holes filled from ext4_page_mkwrite(). We even don't * need to file the inode to the transaction's list in ordered mode because if * we are writing back data added by write(), the inode is already there and if * we are writing back data modified via mmap(), no one guarantees in which * transaction the data will hit the disk. In case we are journaling data, we * cannot start transaction directly because transaction start ranks above page * lock so we have to do some magic. * * This function can get called via... * - ext4_writepages after taking page lock (have journal handle) * - journal_submit_inode_data_buffers (no journal handle) * - shrink_page_list via the kswapd/direct reclaim (no journal handle) * - grab_page_cache when doing write_begin (have journal handle) * * We don't do any block allocation in this function. If we have page with * multiple blocks we need to write those buffer_heads that are mapped. This * is important for mmaped based write. So if we do with blocksize 1K * truncate(f, 1024); * a = mmap(f, 0, 4096); * a[0] = 'a'; * truncate(f, 4096); * we have in the page first buffer_head mapped via page_mkwrite call back * but other buffer_heads would be unmapped but dirty (dirty done via the * do_wp_page). So writepage should write the first block. If we modify * the mmap area beyond 1024 we will again get a page_fault and the * page_mkwrite callback will do the block allocation and mark the * buffer_heads mapped. * * We redirty the page if we have any buffer_heads that is either delay or * unwritten in the page. * * We can get recursively called as show below. * * ext4_writepage() -> kmalloc() -> __alloc_pages() -> page_launder() -> * ext4_writepage() * * But since we don't do any block allocation we should not deadlock. * Page also have the dirty flag cleared so we don't get recurive page_lock. */
static int ext4_writepage(struct page *page, struct writeback_control *wbc) { int ret = 0; loff_t size; unsigned int len; struct buffer_head *page_bufs = NULL; struct inode *inode = page->mapping->host; struct ext4_io_submit io_submit; bool keep_towrite = false; trace_ext4_writepage(page); size = i_size_read(inode); if (page->index == size >> PAGE_SHIFT) len = size & ~PAGE_MASK; else len = PAGE_SIZE; page_bufs = page_buffers(page); /* * We cannot do block allocation or other extent handling in this * function. If there are buffers needing that, we have to redirty * the page. But we may reach here when we do a journal commit via * journal_submit_inode_data_buffers() and in that case we must write * allocated buffers to achieve data=ordered mode guarantees. * * Also, if there is only one buffer per page (the fs block * size == the page size), if one buffer needs block * allocation or needs to modify the extent tree to clear the * unwritten flag, we know that the page can't be written at * all, so we might as well refuse the write immediately. * Unfortunately if the block size != page size, we can't as * easily detect this case using ext4_walk_page_buffers(), but * for the extremely common case, this is an optimization that * skips a useless round trip through ext4_bio_write_page(). */ if (ext4_walk_page_buffers(NULL, page_bufs, 0, len, NULL, ext4_bh_delay_or_unwritten)) { redirty_page_for_writepage(wbc, page); if ((current->flags & PF_MEMALLOC) || (inode->i_sb->s_blocksize == PAGE_SIZE)) { /* * For memory cleaning there's no point in writing only * some buffers. So just bail out. Warn if we came here * from direct reclaim. */ WARN_ON_ONCE((current->flags & (PF_MEMALLOC|PF_KSWAPD)) == PF_MEMALLOC); unlock_page(page); return 0; } keep_towrite = true; } if (PageChecked(page) && ext4_should_journal_data(inode)) /* * It's mmapped pagecache. Add buffers and journal it. There * doesn't seem much point in redirtying the page here. */ return __ext4_journalled_writepage(page, len); ext4_io_submit_init(&io_submit, wbc); io_submit.io_end = ext4_init_io_end(inode, GFP_NOFS); if (!io_submit.io_end) { redirty_page_for_writepage(wbc, page); unlock_page(page); return -ENOMEM; } ret = ext4_bio_write_page(&io_submit, page, len, wbc, keep_towrite); ext4_io_submit(&io_submit); /* Drop io_end reference we got from init */ ext4_put_io_end_defer(io_submit.io_end); return ret; }

Contributors

PersonTokensPropCommitsCommitProp
jan karajan kara17865.20%15.56%
aditya kaliaditya kali217.69%211.11%
theodore tsotheodore tso186.59%316.67%
tao matao ma165.86%15.56%
namjae jeonnamjae jeon114.03%15.56%
mingming caomingming cao114.03%316.67%
lukas czernerlukas czerner41.47%15.56%
zheng liuzheng liu41.47%316.67%
amir goldsteinamir goldstein41.47%15.56%
kirill a. shutemovkirill a. shutemov41.47%15.56%
aneesh kumaraneesh kumar20.73%15.56%
Total273100.00%18100.00%


static int mpage_submit_page(struct mpage_da_data *mpd, struct page *page) { int len; loff_t size = i_size_read(mpd->inode); int err; BUG_ON(page->index != mpd->first_page); if (page->index == size >> PAGE_SHIFT) len = size & ~PAGE_MASK; else len = PAGE_SIZE; clear_page_dirty_for_io(page); err = ext4_bio_write_page(&mpd->io_submit, page, len, mpd->wbc, false); if (!err) mpd->wbc->nr_to_write--; mpd->first_page++; return err; }

Contributors

PersonTokensPropCommitsCommitProp
jan karajan kara10595.45%133.33%
kirill a. shutemovkirill a. shutemov32.73%133.33%
namjae jeonnamjae jeon21.82%133.33%
Total110100.00%3100.00%

#define BH_FLAGS ((1 << BH_Unwritten) | (1 << BH_Delay)) /* * mballoc gives us at most this number of blocks... * XXX: That seems to be only a limitation of ext4_mb_normalize_request(). * The rest of mballoc seems to handle chunks up to full group size. */ #define MAX_WRITEPAGES_EXTENT_LEN 2048 /* * mpage_add_bh_to_extent - try to add bh to extent of blocks to map * * @mpd - extent of blocks * @lblk - logical number of the block in the file * @bh - buffer head we want to add to the extent * * The function is used to collect contig. blocks in the same state. If the * buffer doesn't require mapping for writeback and we haven't started the * extent of buffers to map yet, the function returns 'true' immediately - the * caller can write the buffer right away. Otherwise the function returns true * if the block has been added to the extent, false if the block couldn't be * added. */
static bool mpage_add_bh_to_extent(struct mpage_da_data *mpd, ext4_lblk_t lblk, struct buffer_head *bh) { struct ext4_map_blocks *map = &mpd->map; /* Buffer that doesn't need mapping for writeback? */ if (!buffer_dirty(bh) || !buffer_mapped(bh) || (!buffer_delay(bh) && !buffer_unwritten(bh))) { /* So far no extent to map => we write the buffer right away */ if (map->m_len == 0) return true; return false; } /* First block in the extent? */ if (map->m_len == 0) { map->m_lblk = lblk; map->m_len = 1; map->m_flags = bh->b_state & BH_FLAGS; return true; } /* Don't go larger than mballoc is willing to allocate */ if (map->m_len >= MAX_WRITEPAGES_EXTENT_LEN) return false; /* Can we merge the block to our big extent? */ if (lblk == map->m_lblk + map->m_len && (bh->b_state & BH_FLAGS) == map->m_flags) { map->m_len++; return true; } return false; }

Contributors

PersonTokensPropCommitsCommitProp
jan karajan kara13583.85%250.00%
zheng liuzheng liu159.32%125.00%
dmitriy monakhovdmitriy monakhov116.83%125.00%
Total161100.00%4100.00%

/* * mpage_process_page_bufs - submit page buffers for IO or add them to extent * * @mpd - extent of blocks for mapping * @head - the first buffer in the page * @bh - buffer we should start processing from * @lblk - logical number of the block in the file corresponding to @bh * * Walk through page buffers from @bh upto @head (exclusive) and either submit * the page for IO if all buffers in this page were mapped and there's no * accumulated extent of buffers to map or add buffers in the page to the * extent of buffers to map. The function returns 1 if the caller can continue * by processing the next page, 0 if it should stop adding buffers to the * extent to map because we cannot extend it anymore. It can also return value * < 0 in case of error during IO submission. */
static int mpage_process_page_bufs(struct mpage_da_data *mpd, struct buffer_head *head, struct buffer_head *bh, ext4_lblk_t lblk) { struct inode *inode = mpd->inode; int err; ext4_lblk_t blocks = (i_size_read(inode) + (1 << inode->i_blkbits) - 1) >> inode->i_blkbits; do { BUG_ON(buffer_locked(bh)); if (lblk >= blocks || !mpage_add_bh_to_extent(mpd, lblk, bh)) { /* Found extent to map? */ if (mpd->map.m_len) return 0; /* Everything mapped so far and we hit EOF */ break; } } while (lblk++, (bh = bh->b_this_page) != head); /* So far everything mapped? Submit the page for IO. */ if (mpd->map.m_len == 0) { err = mpage_submit_page(mpd, head->b_page); if (err < 0) return err; } return lblk < blocks; }

Contributors

PersonTokensPropCommitsCommitProp
jan karajan kara13887.90%342.86%
aditya kaliaditya kali117.01%114.29%
zheng liuzheng liu53.18%114.29%
amir goldsteinamir goldstein21.27%114.29%
aneesh kumaraneesh kumar10.64%114.29%
Total157100.00%7100.00%

/* * mpage_map_buffers - update buffers corresponding to changed extent and * submit fully mapped pages for IO * * @mpd - description of extent to map, on return next extent to map * * Scan buffers corresponding to changed extent (we expect corresponding pages * to be already locked) and update buffer state according to new extent state. * We map delalloc buffers to their physical location, clear unwritten bits, * and mark buffers as uninit when we perform writes to unwritten extents * and do extent conversion after IO is finished. If the last page is not fully * mapped, we update @map to the next extent in the last page that needs * mapping. Otherwise we submit the page for IO. */
static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd) { struct pagevec pvec; int nr_pages, i; struct inode *inode = mpd->inode; struct buffer_head *head, *bh; int bpp_bits = PAGE_SHIFT - inode->i_blkbits; pgoff_t start, end; ext4_lblk_t lblk; sector_t pblock; int err; start = mpd->map.m_lblk >> bpp_bits; end = (mpd->map.m_lblk + mpd->map.m_len - 1) >> bpp_bits; lblk = start << bpp_bits; pblock = mpd->map.m_pblk; pagevec_init(&pvec, 0); while (start <= end) { nr_pages = pagevec_lookup(&pvec, inode->i_mapping, start, PAGEVEC_SIZE); if (nr_pages == 0) break; for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; if (page->index > end) break; /* Up to 'end' pages must be contiguous */ BUG_ON(page->index != start); bh = head = page_buffers(page); do { if (lblk < mpd->map.m_lblk) continue; if (lblk >= mpd->map.m_lblk + mpd->map.m_len) { /* * Buffer after end of mapped extent. * Find next buffer in the page to map. */ mpd->map.m_len = 0; mpd->map.m_flags = 0; /* * FIXME: If dioread_nolock supports * blocksize < pagesize, we need to make * sure we add size mapped so far to * io_end->size as the following call * can submit the page for IO. */ err = mpage_process_page_bufs(mpd, head, bh, lblk); pagevec_release(&pvec); if (err > 0) err = 0; return err; } if (buffer_delay(bh)) { clear_buffer_delay(bh); bh->b_blocknr = pblock++; } clear_buffer_unwritten(bh); } while (lblk++, (bh = bh->b_this_page) != head); /* * FIXME: This is going to break if dioread_nolock * supports blocksize < pagesize as we will try to * convert potentially unmapped parts of inode. */ mpd->io_submit.io_end->size += PAGE_SIZE; /* Page fully mapped - let IO run! */ err = mpage_submit_page(mpd, page); if (err < 0) { pagevec_release(&pvec); return err; } start++; } pagevec_release(&pvec); } /* Extent fully mapped and matches with page boundary. We are done. */ mpd->map.m_len = 0; mpd->map.m_flags = 0; return 0; }

Contributors

PersonTokensPropCommitsCommitProp
jan karajan kara30377.89%317.65%
tao matao ma369.25%15.88%
amir goldsteinamir goldstein194.88%15.88%
theodore tsotheodore tso133.34%423.53%
aneesh kumaraneesh kumar61.54%317.65%
alex tomasalex tomas51.29%15.88%
curt wohlgemuthcurt wohlgemuth30.77%15.88%
kirill a. shutemovkirill a. shutemov20.51%15.88%
dave kleikampdave kleikamp10.26%15.88%
anatol pomozovanatol pomozov10.26%15.88%
Total389100.00%17100.00%


static int mpage_map_one_extent(handle_t *handle, struct mpage_da_data *mpd) { struct inode *inode = mpd->inode; struct ext4_map_blocks *map = &mpd->map; int get_blocks_flags; int err, dioread_nolock; trace_ext4_da_write_pages_extent(inode, map); /* * Call ext4_map_blocks() to allocate any delayed allocation blocks, or * to convert an unwritten extent to be initialized (in the case * where we have written into one or more preallocated blocks). It is * possible that we're going to need more metadata blocks than * previously reserved. However we must not fail because we're in * writeback and there is nothing we can do about it so it might result * in data loss. So use reserved blocks to allocate metadata if * possible. * * We pass in the magic EXT4_GET_BLOCKS_DELALLOC_RESERVE if * the blocks in question are delalloc blocks. This indicates * that the blocks and quotas has already been checked when * the data was copied into the page cache. */ get_blocks_flags = EXT4_GET_BLOCKS_CREATE | EXT4_GET_BLOCKS_METADATA_NOFAIL | EXT4_GET_BLOCKS_IO_SUBMIT; dioread_nolock = ext4_should_dioread_nolock(inode); if (dioread_nolock) get_blocks_flags |= EXT4_GET_BLOCKS_IO_CREATE_EXT; if (map->m_flags & (1 << BH_Delay)) get_blocks_flags |= EXT4_GET_BLOCKS_DELALLOC_RESERVE; err = ext4_map_blocks(handle, inode, map, get_blocks_flags); if (err < 0) return err; if (dioread_nolock && (map->m_flags & EXT4_MAP_UNWRITTEN)) { if (!mpd->io_submit.io_end->handle && ext4_handle_valid(handle)) { mpd->io_submit.io_end->handle = handle->h_rsv_handle; handle->h_rsv_handle = NULL; } ext4_set_io_unwritten_flag(inode, mpd->io_submit.io_end); } BUG_ON(map->m_len == 0); if (map->m_flags & EXT4_MAP_NEW) { clean_bdev_aliases(inode->i_sb->s_bdev, map->m_pblk, map->m_len); } return 0; }

Contributors

PersonTokensPropCommitsCommitProp
jan karajan kara17381.99%850.00%
lukas czernerlukas czerner136.16%16.25%
amir goldsteinamir goldstein83.79%16.25%
theodore tsotheodore tso52.37%212.50%
tao matao ma52.37%16.25%
alex tomasalex tomas31.42%16.25%
jiaying zhangjiaying zhang31.42%16.25%
dave kleikampdave kleikamp10.47%16.25%
Total211100.00%16100.00%

/* * mpage_map_and_submit_extent - map extent starting at mpd->lblk of length * mpd->len and submit pages underlying it for IO * * @handle - handle for journal operations * @mpd - extent to map * @give_up_on_write - we set this to true iff there is a fatal error and there * is no hope of writing the data. The caller should discard * dirty pages to avoid infinite loops. * * The function maps extent starting at mpd->lblk of length mpd->len. If it is * delayed, blocks are allocated, if it is unwritten, we may need to convert * them to initialized or split the described range from larger unwritten * extent. Note that we need not map all the described range since allocation * can return less blocks or the range is covered by more unwritten extents. We * cannot map more because we are limited by reserved transaction credits. On * the other hand we always make sure that the last touched page is fully * mapped so that it can be written out (and thus forward progress is * guaranteed). After mapping we submit all mapped pages for IO. */
static int mpage_map_and_submit_extent(handle_t *handle, struct mpage_da_data *mpd, bool *give_up_on_write) { struct inode *inode = mpd->inode; struct ext4_map_blocks *map = &mpd->map; int err; loff_t disksize; int progress = 0; mpd->io_submit.io_end->offset = ((loff_t)map->m_lblk) << inode->i_blkbits; do { err = mpage_map_one_extent(handle, mpd); if (err < 0) { struct super_block *sb = inode->i_sb; if (EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED) goto invalidate_dirty_pages; /* * Let the uper layers retry transient errors. * In the case of ENOSPC, if ext4_count_free_blocks() * is non-zero, a commit should free up blocks. */ if ((err == -ENOMEM) || (err == -ENOSPC && ext4_count_free_clusters(sb))) { if (progress) goto update_disksize; return err; } ext4_msg(sb, KERN_CRIT, "Delayed block allocation failed for " "inode %lu at logical offset %llu with" " max blocks %u with error %d", inode->i_ino, (unsigned long long)map->m_lblk, (unsigned)map->m_len, -err); ext4_msg(sb, KERN_CRIT, "This should not happen!! Data will " "be lost\n"); if (err == -ENOSPC) ext4_print_free_blocks(inode); invalidate_dirty_pages: *give_up_on_write = true; return err; } progress = 1; /* * Update buffer state, submit mapped pages, and get us new * extent to map */ err = mpage_map_and_submit_buffers(mpd); if (err < 0) goto update_disksize; } while (map->m_len); update_disksize: /* * Update on-disk size after IO is submitted. Races with * truncate are avoided by checking i_size under i_data_sem. */ disksize = ((loff_t)mpd->first_page) << PAGE_SHIFT; if (disksize > EXT4_I(inode)->i_disksize) { int err2; loff_t i_size; down_write(&EXT4_I(inode)->i_data_sem); i_size = i_size_read(inode); if (disksize > i_size) disksize = i_size; if (disksize > EXT4_I(inode)->i_disksize) EXT4_I(inode)->i_disksize = disksize; err2 = ext4_mark_inode_dirty(handle, inode); up_write(&EXT4_I(inode)->i_data_sem); if (err2) ext4_error(inode->i_sb, "Failed to mark inode %lu dirty", inode->i_ino); if (!err) err = err2; } return err; }

Contributors

PersonTokensPropCommitsCommitProp
jan karajan kara19652.55%525.00%
theodore tsotheodore tso10628.42%630.00%
dmitriy monakhovdmitriy monakhov236.17%15.00%
aneesh kumaraneesh kumar184.83%420.00%
amir goldsteinamir goldstein143.75%15.00%
alex tomasalex tomas82.14%15.00%
mel gormanmel gorman71.88%15.00%
kirill a. shutemovkirill a. shutemov10.27%15.00%
Total373100.00%20100.00%

/* * Calculate the total number of credits to reserve for one writepages * iteration. This is called from ext4_writepages(). We map an extent of * up to MAX_WRITEPAGES_EXTENT_LEN blocks and then we go on and finish mapping * the last partial page. So in total we can map MAX_WRITEPAGES_EXTENT_LEN + * bpp - 1 blocks in bpp different extents. */
static int ext4_da_writepages_trans_blocks(struct inode *inode) { int bpp = ext4_journal_blocks_per_page(inode); return ext4_meta_trans_blocks(inode, MAX_WRITEPAGES_EXTENT_LEN + bpp - 1, bpp); }

Contributors

PersonTokensPropCommitsCommitProp
aneesh kumaraneesh kumar1957.58%250.00%
jan karajan kara1030.30%125.00%
amir goldsteinamir goldstein412.12%125.00%
Total33100.00%4100.00%

/* * mpage_prepare_extent_to_map - find & lock contiguous range of dirty pages * and underlying extent to map * * @mpd - where to look for pages * * Walk dirty pages in the mapping. If they are fully mapped, submit them for * IO immediately. When we find a page which isn't mapped we start accumulating * extent of buffers underlying these pages that needs mapping (formed by * either delayed or unwritten buffers). We also lock the pages containing * these buffers. The extent found is returned in @mpd structure (starting at * mpd->lblk with length mpd->len blocks). * * Note that this function can attach bios to one io_end structure which are * neither logically nor physically contiguous. Although it may seem as an * unnecessary complication, it is actually inevitable in blocksize < pagesize * case as we need to track IO to all buffers underlying a page in one io_end. */
static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd) { struct address_space *mapping = mpd->inode->i_mapping; struct pagevec pvec; unsigned int nr_pages; long left = mpd->wbc->nr_to_write; pgoff_t index = mpd->first_page; pgoff_t end = mpd->last_page; int tag; int i, err = 0; int blkbits = mpd->inode->i_blkbits; ext4_lblk_t lblk; struct buffer_head *head; if (mpd->wbc->sync_mode == WB_SYNC_ALL || mpd->wbc->tagged_writepages) tag = PAGECACHE_TAG_TOWRITE; else tag = PAGECACHE_TAG_DIRTY; pagevec_init(&pvec, 0); mpd->map.m_len = 0; mpd->next_page = index; while (index <= end) { nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag, min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1); if (nr_pages == 0) goto out; for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; /* * At this point, the page may be truncated or * invalidated (changing page->mapping to NULL), or * even swizzled back from swapper_space to tmpfs file * mapping. However, page->index will not change * because we have a reference on the page. */ if (page->index > end) goto out; /* * Accumulated enough dirty pages? This doesn't apply * to WB_SYNC_ALL mode. For integrity sync we have to * keep going because someone may be concurrently * dirtying pages, and we might have synced a lot of * newly appeared dirty pages, but have not synced all * of the old dirty pages. */ if (mpd->wbc->sync_mode == WB_SYNC_NONE && left <= 0) goto out; /* If we can't merge this page, we are done. */ if (mpd->map.m_len > 0 && mpd->next_page != page->index) goto out; lock_page(page); /* * If the page is no longer dirty, or its mapping no * longer corresponds to inode we are writing (which * means it has been truncated or invalidated), or the * page is already under writeback and we are not doing * a data integrity writeback, skip the page */ if (!PageDirty(page) || (PageWriteback(page) && (mpd->wbc->sync_mode == WB_SYNC_NONE)) || unlikely(page->mapping != mapping)) { unlock_page(page); continue; } wait_on_page_writeback(page); BUG_ON(PageWriteback(page)); if (mpd->map.m_len == 0) mpd->first_page = page->index; mpd->next_page = page->index + 1; /* Add all dirty buffers to mpd */ lblk = ((ext4_lblk_t)page->index) << (PAGE_SHIFT - blkbits); head = page_buffers(page); err = mpage_process_page_bufs(mpd, head, head, lblk); if (err <= 0) goto out; err = 0; left--; } pagevec_release(&pvec); cond_resched(); } return 0; out: pagevec_release(&pvec); return err; }

Contributors

PersonTokensPropCommitsCommitProp
amir goldsteinamir goldstein11828.10%14.17%
jan karajan kara10424.76%312.50%
aneesh kumaraneesh kumar10124.05%416.67%
theodore tsotheodore tso389.05%833.33%
ming leiming lei307.14%14.17%
alex tomasalex tomas133.10%14.17%
linus torvaldslinus torvalds40.95%14.17%
eric sandeeneric sandeen40.95%14.17%
jiaying zhangjiaying zhang30.71%14.17%
alexander beregalovalexander beregalov20.48%14.17%
curt wohlgemuthcurt wohlgemuth20.48%14.17%
kirill a. shutemovkirill a. shutemov10.24%14.17%
Total420100.00%24100.00%


static int __writepage(struct page *page, struct writeback_control *wbc, void *data) { struct address_space *mapping = data; int ret = ext4_writepage(page, wbc); mapping_set_error(mapping, ret); return ret; }

Contributors

PersonTokensPropCommitsCommitProp
theodore tsotheodore tso4595.74%150.00%
alex tomasalex tomas24.26%150.00%
Total47100.00%2100.00%


static int ext4_writepages(struct address_space *mapping, struct writeback_control *wbc) { pgoff_t writeback_index = 0; long nr_to_write = wbc->nr_to_write; int range_whole = 0; int cycled = 1; handle_t *handle = NULL; struct mpage_da_data mpd; struct inode *inode = mapping->host; int needed_blocks, rsv_blocks = 0, ret = 0; struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb); bool done; struct blk_plug plug; bool give_up_on_write = false; percpu_down_read(&sbi->s_journal_flag_rwsem); trace_ext4_writepages(inode, wbc); if (dax_mapping(mapping)) { ret = dax_writeback_mapping_range(mapping, inode->i_sb->s_bdev, wbc); goto out_writepages; } /* * No pages to write? This is mainly a kludge to avoid starting * a transaction for special inodes like journal inode on last iput() * because that could violate lock ordering on umount */ if (!mapping->nrpages || !mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) goto out_writepages; if (ext4_should_journal_data(inode)) { struct blk_plug plug; blk_start_plug(&plug); ret = write_cache_pages(mapping, wbc, __writepage, mapping); blk_finish_plug(&plug); goto out_writepages; } /* * If the filesystem has aborted, it is read-only, so return * right away instead of dumping stack traces later on that * will obscure the real source of the problem. We test * EXT4_MF_FS_ABORTED instead of sb->s_flag's MS_RDONLY because * the latter could be true if the filesystem is mounted * read-only, and in that case, ext4_writepages should * *never* be called, so if that ever happens, we would want * the stack trace. */ if (unlikely(sbi->s_mount_flags & EXT4_MF_FS_ABORTED)) { ret = -EROFS; goto out_writepages; } if (ext4_should_dioread_nolock(inode)) { /* * We may need to convert up to one extent per block in * the page and we may dirty the inode. */ rsv_blocks = 1 + (PAGE_SIZE >> inode->i_blkbits); } /* * If we have inline data and arrive here, it means that * we will soon create the block for the 1st page, so * we'd better clear the inline data here. */ if (ext4_has_inline_data(inode)) { /* Just inode will be modified... */ handle = ext4_journal_start(inode, EXT4_HT_INODE, 1); if (IS_ERR(handle)) { ret = PTR_ERR(handle); goto out_writepages; } BUG_ON(ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)); ext4_destroy_inline_data(handle, inode); ext4_journal_stop(handle); } if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) range_whole = 1; if (wbc->range_cyclic) { writeback_index = mapping->writeback_index; if (writeback_index) cycled = 0; mpd.first_page = writeback_index; mpd.last_page = -1; } else { mpd.first_page = wbc->range_start >> PAGE_SHIFT; mpd.last_page = wbc->range_end >> PAGE_SHIFT; } mpd.inode = inode; mpd.wbc = wbc; ext4_io_submit_init(&mpd.io_submit, wbc); retry: if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) tag_pages_for_writeback(mapping, mpd.first_page, mpd.last_page); done = false; blk_start_plug(&plug); while (!done && mpd.first_page <= mpd.last_page) { /* For each extent of pages we use new io_end */ mpd.io_submit.io_end = ext4_init_io_end(inode, GFP_KERNEL); if (!mpd.io_submit.io_end) { ret = -ENOMEM; break; } /* * We have two constraints: We find one extent to map and we * must always write out whole page (makes a difference when * blocksize < pagesize) so that we don't block on IO when we * try to write out the rest of the page. Journalled mode is * not supported by delalloc. */ BUG_ON(ext4_should_journal_data(inode)); needed_blocks = ext4_da_writepages_trans_blocks(inode); /* start a new transaction */ handle = ext4_journal_start_with_reserve(inode, EXT4_HT_WRITE_PAGE, needed_blocks, rsv_blocks); if (IS_ERR(handle)) { ret = PTR_ERR(handle); ext4_msg(inode->i_sb, KERN_CRIT, "%s: jbd2_start: " "%ld pages, ino %lu; err %d", __func__, wbc->nr_to_write, inode->i_ino, ret); /* Release allocated io_end */ ext4_put_io_end(mpd.io_submit.io_end); break; } trace_ext4_da_write_pages(inode, mpd.first_page, mpd.wbc); ret = mpage_prepare_extent_to_map(&mpd); if (!ret) { if (mpd.map.m_len) ret = mpage_map_and_submit_extent(handle, &mpd, &give_up_on_write); else { /* * We scanned the whole range (or exhausted * nr_to_write), submitted what was mapped and * didn't find anything needing mapping. We are * done. */ done = true; } } /* * Caution: If the handle is synchronous, * ext4_journal_stop() can wait for transaction commit * to finish which may depend on writeback of pages to * complete or on page lock to be released. In that * case, we have to wait until after after we have * submitted all the IO, released page locks we hold, * and dropped io_end reference (for extent conversion * to be able to complete) before stopping the handle. */ if (!ext4_handle_valid(handle) || handle->h_sync == 0) { ext4_journal_stop(handle); handle = NULL; } /* Submit prepared bio */ ext4_io_submit(&mpd.io_submit); /* Unlock pages we didn't use */ mpage_release_unused_pages(&mpd, give_up_on_write); /* * Drop our io_end reference we got from init. We have * to be careful and use deferred io_end finishing if * we are still holding the transaction as we can * release the last reference to io_end which may end * up doing unwritten extent conversion. */ if (handle) { ext4_put_io_end_defer(mpd.io_submit.io_end); ext4_journal_stop(handle); } else ext4_put_io_end(mpd.io_submit.io_end); if (ret == -ENOSPC && sbi->s_journal) { /* * Commit the transaction which would * free blocks released in the transaction * and try again */ jbd2_journal_force_commit_nested(sbi->s_journal); ret = 0; continue; } /* Fatal error - ENOMEM, EIO... */ if (ret) break; } blk_finish_plug(&plug); if (!ret && !cycled && wbc->nr_to_write > 0) { cycled = 1; mpd.last_page = writeback_index - 1; mpd.first_page = 0; goto retry; } /* Update index */ if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0)) /* * Set the writeback_index so that range_cyclic * mode will write it back later */ mapping->writeback_index = mpd.first_page; out_writepages: trace_ext4_writepages_result(inode, wbc, ret, nr_to_write - wbc->nr_to_write); percpu_up_read(&sbi->s_journal_flag_rwsem); return ret; }

Contributors

PersonTokensPropCommitsCommitProp
jan karajan kara33540.56%49.76%
amir goldsteinamir goldstein16219.61%12.44%
theodore tsotheodore tso10612.83%1024.39%
aneesh kumaraneesh kumar597.14%921.95%
alex tomasalex tomas465.57%12.44%
daeho jeongdaeho jeong242.91%12.44%
eric sandeeneric sandeen192.30%37.32%
ross zwislerross zwisler192.30%12.44%
li shaohuali shaohua161.94%12.44%
ming leiming lei141.69%12.44%
mingming caomingming cao101.21%24.88%
linus torvaldslinus torvalds40.48%12.44%
kirill a. shutemovkirill a. shutemov30.36%12.44%
jiaying zhangjiaying zhang30.36%12.44%
curt wohlgemuthcurt wohlgemuth20.24%12.44%
namjae jeonnamjae jeon20.24%12.44%
anatol pomozovanatol pomozov10.12%12.44%
tao matao ma10.12%12.44%
Total826100.00%41100.00%


static int ext4_nonda_switch(struct super_block *sb) { s64 free_clusters, dirty_clusters; struct ext4_sb_info *sbi = EXT4_SB(sb); /* * switch to non delalloc mode if we are running low * on free block. The free block accounting via percpu * counters can get slightly wrong with percpu_counter_batch getting * accumulated on each CPU without updating global counters * Delalloc need an accurate free block accounting. So switch * to non delalloc when we are near to error range. */ free_clusters = percpu_counter_read_positive(&sbi->s_freeclusters_counter); dirty_clusters = percpu_counter_read_positive(&sbi->s_dirtyclusters_counter); /* * Start pushing delalloc when 1/2 of free blocks are dirty. */ if (dirty_clusters && (free_clusters < 2 * dirty_clusters)) try_to_writeback_inodes_sb(sb, WB_REASON_FS_FREE_SPACE); if (2 * free_clusters < 3 * dirty_clusters || free_clusters < (dirty_clusters + EXT4_FREECLUSTERS_WATERMARK)) { /* * free block count is less than 150% of dirty blocks * or free blocks is less than watermark */ return 1; } return 0; }

Contributors

PersonTokensPropCommitsCommitProp
amir goldsteinamir goldstein4143.62%112.50%
theodore tsotheodore tso2021.28%337.50%
aneesh kumaraneesh kumar1414.89%112.50%
eric whitneyeric whitney1111.70%112.50%
mingming caomingming cao77.45%112.50%
miao xiemiao xie11.06%112.50%
Total94100.00%8100.00%

/* We always reserve for an inode update; the superblock could be there too */
static int ext4_da_write_credits(struct inode *inode, loff_t pos, unsigned len) { if (likely(ext4_has_feature_large_file(inode->i_sb))) return 1; if (pos + len <= 0x7fffffffULL) return 1; /* We might need to update the superblock to set LARGE_FILE */ return 2; }

Contributors

PersonTokensPropCommitsCommitProp
eric sandeeneric sandeen4697.87%150.00%
darrick j. wongdarrick j. wong12.13%150.00%
Total47100.00%2100.00%


static int ext4_da_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) { int ret, retries = 0; struct page *page; pgoff_t index; struct inode *inode = mapping->host; handle_t *handle; index = pos >> PAGE_SHIFT; if (ext4_nonda_switch(inode->i_sb) || S_ISLNK(inode->i_mode)) { *fsdata = (void *)FALL_BACK_TO_NONDELALLOC; return ext4_write_begin(file, mapping, pos, len, flags, pagep, fsdata); } *fsdata = (void *)0; trace_ext4_da_write_begin(inode, pos, len, flags); if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) { ret = ext4_da_write_inline_data_begin(mapping, inode, pos, len, flags, pagep, fsdata); if (ret < 0) return ret; if (ret == 1) return 0; } /* * grab_cache_page_write_begin() can take a long time if the * system is thrashing due to memory pressure, or if the page * is being written back. So grab it first before we start * the transaction handle. This also allows us to allocate * the page (if needed) without using GFP_NOFS. */ retry_grab: page = grab_cache_page_write_begin(mapping, index, flags); if (!page) return -ENOMEM; unlock_page(page); /* * With delayed allocation, we don't log the i_disksize update * if there is delayed block allocation. But we still need * to journalling the i_disksize update if writes to the end * of file which has an already mapped buffer. */ retry_journal: handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, ext4_da_write_credits(inode, pos, len)); if (IS_ERR(handle)) { put_page(page); return PTR_ERR(handle); } lock_page(page); if (page->mapping != mapping) { /* The page got truncated from under us */ unlock_page(page); put_page(page); ext4_journal_stop(handle); goto retry_grab; } /* In case writeback began while the page was unlocked */ wait_for_stable_page(page); #ifdef CONFIG_EXT4_FS_ENCRYPTION ret = ext4_block_write_begin(page, pos, len, ext4_da_get_block_prep); #else ret = __block_write_begin(page, pos, len, ext4_da_get_block_prep); #endif if (ret < 0) { unlock_page(page); ext4_journal_stop(handle); /* * block_write_begin may have instantiated a few blocks * outside i_size. Trim these off again. Don't need * i_size_read because we hold i_mutex. */ if (pos + len > inode->i_size) ext4_truncate_failed_write(inode); if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) goto retry_journal; put_page(page); return ret; } *pagep = page; return ret; }

Contributors

PersonTokensPropCommitsCommitProp
theodore tsotheodore tso13233.42%937.50%
amir goldsteinamir goldstein11428.86%14.17%
tao matao ma4310.89%14.17%
alex tomasalex tomas389.62%14.17%
aneesh kumaraneesh kumar246.08%416.67%
michael halcrowmichael halcrow205.06%14.17%
eric sandeeneric sandeen143.54%312.50%
mingming caomingming cao51.27%28.33%
kirill a. shutemovkirill a. shutemov41.01%14.17%
dmitriy monakhovdmitriy monakhov10.25%14.17%
Total395100.00%24100.00%

/* * Check if we should update i_disksize * when write to the end of file but not require block allocation */
static int ext4_da_should_update_i_disksize(struct page *page, unsigned long offset) { struct buffer_head *bh; struct inode *inode = page->mapping->host; unsigned int idx; int i; bh = page_buffers(page); idx = offset >> inode->i_blkbits; for (i = 0; i < idx; i++) bh = bh->b_this_page; if (!buffer_mapped(bh) || (buffer_delay(bh)) || buffer_unwritten(bh)) return 0; return 1; }

Contributors

PersonTokensPropCommitsCommitProp
amir goldsteinamir goldstein5455.10%116.67%
theodore tsotheodore tso2424.49%350.00%
aneesh kumaraneesh kumar2020.41%233.33%
Total98100.00%6100.00%


static int ext4_da_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { struct inode *inode = mapping->host; int ret = 0, ret2; handle_t *handle = ext4_journal_current_handle(); loff_t new_i_size; unsigned long start, end; int write_mode = (int)(unsigned long)fsdata; if (write_mode == FALL_BACK_TO_NONDELALLOC) return ext4_write_end(file, mapping, pos, len, copied, page, fsdata); trace_ext4_da_write_end(inode, pos, len, copied); start = pos & (PAGE_SIZE - 1); end = start + copied - 1; /* * generic_write_end() will run mark_inode_dirty() if i_size * changes. So let's piggyback the i_disksize mark_inode_dirty * into that. */ new_i_size = pos + copied; if (copied && new_i_size > EXT4_I(inode)->i_disksize) { if (ext4_has_inline_data(inode) || ext4_da_should_update_i_disksize(page, end)) { ext4_update_i_disksize(inode, new_i_size); /* We need to mark inode dirty even if * new_i_size is less that inode->i_size * bu greater than i_disksize.(hint delalloc) */ ext4_mark_inode_dirty(handle, inode); } } if (write_mode != CONVERT_INLINE_DATA && ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA) && ext4_has_inline_data(inode)) ret2 = ext4_da_write_inline_data_end(inode, pos, len, copied, page); else ret2 = generic_write_end(file, mapping, pos, len, copied, page, fsdata); copied = ret2; if (ret2 < 0) ret = ret2; ret2 = ext4_journal_stop(handle); if (!ret) ret = ret2; return ret ? ret : copied; }

Contributors

PersonTokensPropCommitsCommitProp
amir goldsteinamir goldstein12043.80%15.56%
aneesh kumaraneesh kumar8129.56%738.89%
tao matao ma3914.23%15.56%
alex tomasalex tomas186.57%15.56%
mingming caomingming cao72.55%211.11%
theodore tsotheodore tso41.46%316.67%
dmitriy monakhovdmitriy monakhov20.73%15.56%
andrea arcangeliandrea arcangeli20.73%15.56%
kirill a. shutemovkirill a. shutemov10.36%15.56%
Total274100.00%18100.00%


static void ext4_da_invalidatepage(struct page *page, unsigned int offset, unsigned int length) { /* * Drop reserved blocks */ BUG_ON(!PageLocked(page)); if (!page_has_buffers(page)) goto out; ext4_da_page_release_reservation(page, offset, length); out: ext4_invalidatepage(page, offset, length); return; }

Contributors

PersonTokensPropCommitsCommitProp
amir goldsteinamir goldstein2947.54%110.00%
aneesh kumaraneesh kumar1321.31%330.00%
lukas czernerlukas czerner914.75%220.00%
mingming caomingming cao58.20%220.00%
alex tomasalex tomas34.92%110.00%
theodore tsotheodore tso23.28%110.00%
Total61100.00%10100.00%

/* * Force all delayed allocation blocks to be allocated for a given inode. */
int ext4_alloc_da_blocks(struct inode *inode) { trace_ext4_alloc_da_blocks(inode); if (!EXT4_I(inode)->i_reserved_data_blocks) return 0; /* * We do something simple for now. The filemap_flush() will * also start triggering a write of the data blocks, which is * not strictly speaking necessary (and for users of * laptop_mode, not even desirable). However, to do otherwise * would require replicating code paths in: * * ext4_writepages() -> * write_cache_pages() ---> (via passed in callback function) * __mpage_da_writepage() --> * mpage_add_bh_to_extent() * mpage_da_map_blocks() * * The problem is that write_cache_pages(), located in * mm/page-writeback.c, marks pages clean in preparation for * doing I/O, which is not desirable if we're not planning on * doing I/O at all. * * We could call write_cache_pages(), and then redirty all of * the pages by calling redirty_page_for_writepage() but that * would be ugly in the extreme. So instead we would need to * replicate parts of the code in the above functions, * simplifying them because we wouldn't actually intend to * write out the pages, but rather only collect contiguous * logical block extents, call the multi-block allocator, and * then update the buffer heads with the block allocations. * * For now, though, we'll cheat by calling filemap_flush(), * which will map the blocks, and start the I/O, but not * actually wait for the I/O to complete. */ return filemap_flush(inode->i_mapping); }

Contributors

PersonTokensPropCommitsCommitProp
amir goldsteinamir goldstein1951.35%116.67%
jiaying zhangjiaying zhang718.92%116.67%
theodore tsotheodore tso616.22%233.33%
alex tomasalex tomas38.11%116.67%
aneesh kumaraneesh kumar25.41%116.67%
Total37100.00%6100.00%

/* * bmap() is special. It gets used by applications such as lilo and by * the swapper to find the on-disk block of a specific piece of data. * * Naturally, this is dangerous if the block concerned is still in the * journal. If somebody makes a swapfile on an ext4 data-journaling * filesystem and enables swap, then they may get a nasty shock when the * data getting swapped to that swapfile suddenly gets overwritten by * the original zero's written out previously to the journal and * awaiting writeback in the kernel's buffer cache. * * So, if we see any bmap calls here on a modified, data-journaled file, * take extra steps to flush any blocks which might be in the cache. */
static sector_t ext4_bmap(struct address_space *mapping, sector_t block) { struct inode *inode = mapping->host; journal_t *journal; int err; /* * We can get here for an inline file via the FIBMAP ioctl */ if (ext4_has_inline_data(inode)) return 0; if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY) && test_opt(inode->i_sb, DELALLOC)) { /* * With delalloc we want to sync the file * so that we can make sure we allocate * blocks for file */ filemap_write_and_wait(mapping); } if (EXT4_JOURNAL(inode) && ext4_test_inode_state(inode, EXT4_STATE_JDATA)) { /* * This is a REALLY heavyweight approach, but the use of * bmap on dirty files is expected to be extremely rare: * only if we run lilo or swapon on a freshly made file * do we expect this to happen. * * (bmap requires CAP_SYS_RAWIO so this does not * represent an unprivileged user DOS attack --- we'd be * in trouble if mortal users could trigger this path at * will.) * * NB. EXT4_STATE_JDATA is not set on files other than * regular files. If somebody wants to bmap a directory * or symlink and gets confused because the buffer * hasn't yet been flushed to disk, they deserve * everything they get. */ ext4_clear_inode_state(inode, EXT4_STATE_JDATA); journal = EXT4_JOURNAL(inode); jbd2_journal_lock_updates(journal); err = jbd2_journal_flush(journal); jbd2_journal_unlock_updates(journal); if (err) return 0; } return generic_block_bmap(mapping, block, ext4_get_block); }

Contributors

PersonTokensPropCommitsCommitProp
amir goldsteinamir goldstein5440.91%110.00%
aneesh kumaraneesh kumar5037.88%440.00%
alex tomasalex tomas118.33%110.00%
tao matao ma118.33%110.00%
mingming caomingming cao43.03%110.00%
jiaying zhangjiaying zhang10.76%110.00%
eric sandeeneric sandeen10.76%110.00%
Total132100.00%10100.00%


static int ext4_readpage(struct file *file, struct page *page) { int ret = -EAGAIN; struct inode *inode = page->mapping->host; trace_ext4_readpage(page); if (ext4_has_inline_data(inode)) ret = ext4_readpage_inline(inode, page); if (ret == -EAGAIN) return ext4_mpage_readpages(page->mapping, NULL, page, 1); return ret; }

Contributors

PersonTokensPropCommitsCommitProp
tao matao ma4355.13%116.67%
mingming caomingming cao1417.95%116.67%
amir goldsteinamir goldstein911.54%116.67%
theodore tsotheodore tso810.26%116.67%
alex tomasalex tomas22.56%116.67%
julia lawalljulia lawall22.56%116.67%
Total78100.00%6100.00%


static int ext4_readpages(struct file *file, struct address_space *mapping, struct list_head *pages, unsigned nr_pages) { struct inode *inode = mapping->host; /* If the file has inline data, no need to do readpages. */ if (ext4_has_inline_data(inode)) return 0; return ext4_mpage_readpages(mapping, pages, NULL, nr_pages); }

Contributors

PersonTokensPropCommitsCommitProp
amir goldsteinamir goldstein1628.57%111.11%
theodore tsotheodore tso1526.79%333.33%
tao matao ma1323.21%111.11%
alex tomasalex tomas58.93%111.11%
dave kleikampdave kleikamp58.93%111.11%
eric sandeeneric sandeen11.79%111.11%
jiaying zhangjiaying zhang11.79%111.11%
Total56100.00%9100.00%


static void ext4_invalidatepage(struct page *page, unsigned int offset, unsigned int length) { trace_ext4_invalidatepage(page, offset, length); /* No journalling happens on data buffers when this function is used */ WARN_ON(page_has_buffers(page) && buffer_jbd(page_buffers(page))); block_invalidatepage(page, offset, length); }

Contributors

PersonTokensPropCommitsCommitProp
jan karajan kara2546.30%116.67%
amir goldsteinamir goldstein1527.78%116.67%
lukas czernerlukas czerner916.67%233.33%
theodore tsotheodore tso47.41%116.67%
alex tomasalex tomas11.85%116.67%
Total54100.00%6100.00%


static int __ext4_journalled_invalidatepage(struct page *page, unsigned int offset, unsigned int length) { journal_t *journal = EXT4_JOURNAL(page->mapping->host); trace_ext4_journalled_invalidatepage(page, offset, length); /* * If it's a full truncate we just forget about the pending dirtying */ if (offset == 0 && length == PAGE_SIZE) ClearPageChecked(page); return jbd2_journal_invalidatepage(journal, page, offset, length); }

Contributors

PersonTokensPropCommitsCommitProp
jan karajan kara3652.17%220.00%
lukas czernerlukas czerner1217.39%220.00%
amir goldsteinamir goldstein913.04%110.00%
theodore tsotheodore tso811.59%220.00%
alex tomasalex tomas22.90%110.00%
kirill a. shutemovkirill a. shutemov11.45%110.00%
eric sandeeneric sandeen11.45%110.00%
Total69100.00%10100.00%

/* Wrapper for aops... */
static void ext4_journalled_invalidatepage(struct page *page, unsigned int offset, unsigned int length) { WARN_ON(__ext4_journalled_invalidatepage(page, offset, length) < 0); }

Contributors

PersonTokensPropCommitsCommitProp
jan karajan kara2266.67%116.67%
lukas czernerlukas czerner618.18%233.33%
theodore tsotheodore tso39.09%233.33%
amir goldsteinamir goldstein26.06%116.67%
Total33100.00%6100.00%


static int ext4_releasepage(struct page *page, gfp_t wait) { journal_t *journal = EXT4_JOURNAL(page->mapping->host); trace_ext4_releasepage(page); /* Page has dirty journalled data -> cannot release */ if (PageChecked(page)) return 0; if (journal) return jbd2_journal_try_to_free_buffers(journal, page, wait); else return try_to_free_buffers(page); }

Contributors

PersonTokensPropCommitsCommitProp
amir goldsteinamir goldstein1726.56%111.11%
theodore tsotheodore tso1625.00%333.33%
zheng liuzheng liu1523.44%111.11%
jiaying zhangjiaying zhang812.50%111.11%
jan karajan kara710.94%222.22%
mingming caomingming cao11.56%111.11%
Total64100.00%9100.00%

#ifdef CONFIG_FS_DAX
static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length, unsigned flags, struct iomap *iomap) { unsigned int blkbits = inode->i_blkbits; unsigned long first_block = offset >> blkbits; unsigned long last_block = (offset + length - 1) >> blkbits; struct ext4_map_blocks map; int ret; if (WARN_ON_ONCE(ext4_has_inline_data(inode))) return -ERANGE; map.m_lblk = first_block; map.m_len = last_block - first_block + 1; if (!(flags & IOMAP_WRITE)) { ret = ext4_map_blocks(NULL, inode, &map, 0); } else { int dio_credits; handle_t *handle; int retries = 0; /* Trim mapping request to maximum we can map at once for DIO */ if (map.m_len > DIO_MAX_BLOCKS) map.m_len = DIO_MAX_BLOCKS; dio_credits = ext4_chunk_trans_blocks(inode, map.m_len); retry: /* * Either we allocate blocks and then we don't get unwritten * extent so we have reserved enough credits, or the blocks * are already allocated and unwritten and in that case * extent conversion fits in the credits as well. */ handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, dio_credits); if (IS_ERR(handle)) return PTR_ERR(handle); ret = ext4_map_blocks(handle, inode, &map, EXT4_GET_BLOCKS_CREATE_ZERO); if (ret < 0) { ext4_journal_stop(handle); if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) goto retry; return ret; } /* * If we added blocks beyond i_size, we need to make sure they * will get truncated if we crash before updating i_size in * ext4_iomap_end(). For faults we don't need to do that (and * even cannot because for orphan list operations inode_lock is * required) - if we happen to instantiate block beyond i_size, * it is because we race with truncate which has already added * the inode to the orphan list. */ if (!(flags & IOMAP_FAULT) && first_block + map.m_len > (i_size_read(inode) + (1 << blkbits) - 1) >> blkbits) { int err; err = ext4_orphan_add(handle, inode); if (err < 0) { ext4_journal_stop(handle); return err; } } ext4_journal_stop(handle); } iomap->flags = 0; iomap->bdev = inode->i_sb->s_bdev; iomap->offset = first_block << blkbits; if (ret == 0) { iomap->type = IOMAP_HOLE; iomap->blkno = IOMAP_NULL_BLOCK; iomap->length = (u64)map.m_len << blkbits; } else { if (map.m_flags & EXT4_MAP_MAPPED) { iomap->type = IOMAP_MAPPED; } else if (map.m_flags & EXT4_MAP_UNWRITTEN) { iomap->type = IOMAP_UNWRITTEN; } else { WARN_ON_ONCE(1); return -EIO; } iomap->blkno = (sector_t)map.m_pblk << (blkbits - 9); iomap->length = (u64)map.m_len << blkbits; } if (map.m_flags & EXT4_MAP_NEW) iomap->flags |= IOMAP_F_NEW; return 0; }

Contributors

PersonTokensPropCommitsCommitProp
jan karajan kara455100.00%3100.00%
Total455100.00%3100.00%


static int ext4_iomap_end(struct inode *inode, loff_t offset, loff_t length, ssize_t written, unsigned flags, struct iomap *iomap) { int ret = 0; handle_t *handle; int blkbits = inode->i_blkbits; bool truncate = false; if (!(flags & IOMAP_WRITE) || (flags & IOMAP_FAULT)) return 0; handle = ext4_journal_start(inode, EXT4_HT_INODE, 2); if (IS_ERR(handle)) { ret = PTR_ERR(handle); goto orphan_del; } if (ext4_update_inode_size(inode, offset + written)) ext4_mark_inode_dirty(handle, inode); /* * We may need to truncate allocated but not written blocks beyond EOF. */ if (iomap->offset + iomap->length > ALIGN(inode->i_size, 1 << blkbits)) { ext4_lblk_t written_blk, end_blk; written_blk = (offset + written) >> blkbits; end_blk = (offset + length) >> blkbits; if (written_blk < end_blk && ext4_can_truncate(inode)) truncate = true; } /* * Remove inode from orphan list if we were extending a inode and * everything went fine. */ if (!truncate && inode->i_nlink && !list_empty(&EXT4_I(inode)->i_orphan)) ext4_orphan_del(handle, inode); ext4_journal_stop(handle); if (truncate) { ext4_truncate_failed_write(inode); orphan_del: /* * If truncate failed early the inode might still be on the * orphan list; we need to make sure the inode is removed from * the orphan list in that case. */ if (inode->i_nlink) ext4_orphan_del(NULL, inode); } return ret; }

Contributors

PersonTokensPropCommitsCommitProp
jan karajan kara243100.00%2100.00%
Total243100.00%2100.00%

struct iomap_ops ext4_iomap_ops = { .iomap_begin = ext4_iomap_begin, .iomap_end = ext4_iomap_end, }; #endif
static int ext4_end_io_dio(struct kiocb *iocb, loff_t offset, ssize_t size, void *private) { ext4_io_end_t *io_end = private; /* if not async direct IO just return */ if (!io_end) return 0; ext_debug("ext4_end_io_dio(): io_end 0x%p " "for inode %lu, iocb 0x%p, offset %llu, size %zd\n", io_end, io_end->inode->i_ino, iocb, offset, size); /* * Error during AIO DIO. We cannot convert unwritten extents as the * data was not written. Just clear the unwritten flag and drop io_end. */ if (size <= 0) { ext4_clear_io_unwritten_flag(io_end); size = 0; } io_end->offset = offset; io_end->size = size; ext4_put_io_end(io_end); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
amir goldsteinamir goldstein3840.43%14.76%
jan karajan kara2122.34%419.05%
christoph hellwigchristoph hellwig88.51%29.52%
theodore tsotheodore tso77.45%314.29%
alex tomasalex tomas66.38%14.76%
aneesh kumaraneesh kumar55.32%419.05%
mingming caomingming cao44.26%29.52%
dave kleikampdave kleikamp22.13%14.76%
tao matao ma11.06%14.76%
zheng liuzheng liu11.06%14.76%
joe perchesjoe perches11.06%14.76%
Total94100.00%21100.00%

/* * Handling of direct IO writes. * * For ext4 extent files, ext4 will do direct-io write even to holes, * preallocated extents, and those write extend the file, no need to * fall back to buffered IO. * * For holes, we fallocate those blocks, mark them as unwritten * If those blocks were preallocated, we mark sure they are split, but * still keep the range to write as unwritten. * * The unwritten extents will be converted to written when DIO is completed. * For async direct IO, since the IO may still pending when return, we * set up an end_io call back function, which will do the conversion * when async direct IO completed. * * If the O_DIRECT write will extend the file then add this inode to the * orphan list. So recovery will truncate it back to the original size * if the machine crashes during the write. * */
static ssize_t ext4_direct_IO_write(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; struct ext4_inode_info *ei = EXT4_I(inode); ssize_t ret; loff_t offset = iocb->ki_pos; size_t count = iov_iter_count(iter); int overwrite = 0; get_block_t *get_block_func = NULL; int dio_flags = 0; loff_t final_size = offset + count; int orphan = 0; handle_t *handle; if (final_size > inode->i_size) { /* Credits for sb + inode write */ handle = ext4_journal_start(inode, EXT4_HT_INODE, 2); if (IS_ERR(handle)) { ret = PTR_ERR(handle); goto out; } ret = ext4_orphan_add(handle, inode); if (ret) { ext4_journal_stop(handle); goto out; } orphan = 1; ei->i_disksize = inode->i_size; ext4_journal_stop(handle); } BUG_ON(iocb->private == NULL); /* * Make all waiters for direct IO properly wait also for extent * conversion. This also disallows race between truncate() and * overwrite DIO as i_dio_count needs to be incremented under i_mutex. */ inode_dio_begin(inode); /* If we do a overwrite dio, i_mutex locking can be released */ overwrite = *((int *)iocb->private); if (overwrite) inode_unlock(inode); /* * For extent mapped files we could direct write to holes and fallocate. * * Allocated blocks to fill the hole are marked as unwritten to prevent * parallel buffered read to expose the stale data before DIO complete * the data IO. * * As to previously fallocated extents, ext4 get_block will just simply * mark the buffer mapped but still keep the extents unwritten. * * For non AIO case, we will convert those unwritten extents to written * after return back from blockdev_direct_IO. That way we save us from * allocating io_end structure and also the overhead of offloading * the extent convertion to a workqueue. * * For async DIO, the conversion needs to be deferred when the * IO is completed. The ext4 end_io callback function will be * called to take care of the conversion work. Here for async * case, we allocate an io_end structure to hook to the iocb. */ iocb->private = NULL; if (overwrite) get_block_func = ext4_dio_get_block_overwrite; else if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) || round_down(offset, 1 << inode->i_blkbits) >= inode->i_size) { get_block_func = ext4_dio_get_block; dio_flags = DIO_LOCKING | DIO_SKIP_HOLES; } else if (is_sync_kiocb(iocb)) { get_block_func = ext4_dio_get_block_unwritten_sync; dio_flags = DIO_LOCKING; } else { get_block_func = ext4_dio_get_block_unwritten_async; dio_flags = DIO_LOCKING; } #ifdef CONFIG_EXT4_FS_ENCRYPTION BUG_ON(ext4_encrypted_inode(inode) && S_ISREG(inode->i_mode)); #endif ret = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter, get_block_func, ext4_end_io_dio, NULL, dio_flags); if (ret > 0 && !overwrite && ext4_test_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN)) { int err; /* * for non AIO case, since the IO is already * completed, we could do the conversion right here */ err = ext4_convert_unwritten_extents(NULL, inode, offset, ret); if (err < 0) ret = err; ext4_clear_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN); } inode_dio_end(inode); /* take i_mutex locking again if we do a ovewrite dio */ if (overwrite) inode_lock(inode); if (ret < 0 && final_size > inode->i_size) ext4_truncate_failed_write(inode); /* Handle extending of i_size after direct IO write */ if (orphan) { int err; /* Credits for sb + inode write */ handle = ext4_journal_start(inode, EXT4_HT_INODE, 2); if (IS_ERR(handle)) { /* This is really bad luck. We've written the data * but cannot extend i_size. Bail out and pretend * the write failed... */ ret = PTR_ERR(handle); if (inode->i_nlink) ext4_orphan_del(NULL, inode); goto out; } if (inode->i_nlink) ext4_orphan_del(handle, inode); if (ret > 0) { loff_t end = offset + ret; if (end > inode->i_size) { ei->i_disksize = end; i_size_write(inode, end); /* * We're going to return a positive `ret' * here due to non-zero-length I/O, so there's * no way of reporting error returns from * ext4_mark_inode_dirty() to userspace. So * ignore it. */ ext4_mark_inode_dirty(handle, inode); } } err = ext4_journal_stop(handle); if (ret == 0) ret = err; } out: return ret; }

Contributors

PersonTokensPropCommitsCommitProp
jan karajan kara31255.52%620.00%
amir goldsteinamir goldstein7012.46%13.33%
zheng liuzheng liu458.01%26.67%
theodore tsotheodore tso244.27%413.33%
anatol pomozovanatol pomozov213.74%13.33%
michael halcrowmichael halcrow203.56%13.33%
jiaying zhangjiaying zhang122.14%13.33%
alex tomasalex tomas111.96%13.33%
dave kleikampdave kleikamp101.78%13.33%
mingming caomingming cao91.60%26.67%
christoph hellwigchristoph hellwig71.25%13.33%
al viroal viro61.07%310.00%
aneesh kumaraneesh kumar50.89%26.67%
linus torvaldslinus torvalds40.71%13.33%
omar sandovalomar sandoval40.71%13.33%
jens axboejens axboe10.18%13.33%
jeff moyerjeff moyer10.18%13.33%
Total562100.00%30100.00%


static ssize_t ext4_direct_IO_read(struct kiocb *iocb, struct iov_iter *iter) { struct address_space *mapping = iocb->ki_filp->f_mapping; struct inode *inode = mapping->host; size_t count = iov_iter_count(iter); ssize_t ret; /* * Shared inode_lock is enough for us - it protects against concurrent * writes & truncates and since we take care of writing back page cache, * we are protected against page writeback as well. */ inode_lock_shared(inode); ret = filemap_write_and_wait_range(mapping, iocb->ki_pos, iocb->ki_pos + count); if (ret) goto out_unlock; ret = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter, ext4_dio_get_block, NULL, NULL, 0); out_unlock: inode_unlock_shared(inode); return ret; }

Contributors

PersonTokensPropCommitsCommitProp
jan karajan kara8172.32%538.46%
amir goldsteinamir goldstein1614.29%17.69%
linus torvaldslinus torvalds43.57%17.69%
dmitriy monakhovdmitriy monakhov43.57%17.69%
alex tomasalex tomas21.79%17.69%
jiaying zhangjiaying zhang21.79%17.69%
al viroal viro10.89%17.69%
aneesh kumaraneesh kumar10.89%17.69%
mingming caomingming cao10.89%17.69%
Total112100.00%13100.00%


static ssize_t ext4_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; size_t count = iov_iter_count(iter); loff_t offset = iocb->ki_pos; ssize_t ret; #ifdef CONFIG_EXT4_FS_ENCRYPTION if (ext4_encrypted_inode(inode) && S_ISREG(inode->i_mode)) return 0; #endif /* * If we are doing data journalling we don't support O_DIRECT */ if (ext4_should_journal_data(inode)) return 0; /* Let buffer I/O handle the inline data case. */ if (ext4_has_inline_data(inode)) return 0; /* DAX uses iomap path now */ if (WARN_ON_ONCE(IS_DAX(inode))) return 0; trace_ext4_direct_IO_enter(inode, offset, count, iov_iter_rw(iter)); if (iov_iter_rw(iter) == READ) ret = ext4_direct_IO_read(iocb, iter); else ret = ext4_direct_IO_write(iocb, iter); trace_ext4_direct_IO_exit(inode, offset, count, iov_iter_rw(iter), ret); return ret; }

Contributors

PersonTokensPropCommitsCommitProp
dave kleikampdave kleikamp2715.61%15.00%
michael halcrowmichael halcrow2212.72%15.00%
jan karajan kara2011.56%210.00%
alex tomasalex tomas169.25%15.00%
al viroal viro148.09%210.00%
jiaying zhangjiaying zhang137.51%210.00%
theodore tsotheodore tso137.51%210.00%
tao matao ma116.36%15.00%
amir goldsteinamir goldstein116.36%15.00%
omar sandovalomar sandoval84.62%15.00%
christoph hellwigchristoph hellwig74.05%15.00%
mingming caomingming cao52.89%210.00%
aneesh kumaraneesh kumar42.31%15.00%
nick pigginnick piggin10.58%15.00%
eric sandeeneric sandeen10.58%15.00%
Total173100.00%20100.00%

/* * Pages can be marked dirty completely asynchronously from ext4's journalling * activity. By filemap_sync_pte(), try_to_unmap_one(), etc. We cannot do * much here because ->set_page_dirty is called under VFS locks. The page is * not necessarily locked. * * We cannot just dirty the page and leave attached buffers clean, because the * buffers' dirty state is "definitive". We cannot just set the buffers dirty * or jbddirty because all the journalling code will explode. * * So what we do is to mark the page "pending dirty" and next time writepage * is called, propagate that into the buffers appropriately. */
static int ext4_journalled_set_page_dirty(struct page *page) { SetPageChecked(page); return __set_page_dirty_nobuffers(page); }

Contributors

PersonTokensPropCommitsCommitProp
jiaying zhangjiaying zhang1359.09%116.67%
amir goldsteinamir goldstein522.73%116.67%
mingming caomingming cao14.55%116.67%
aneesh kumaraneesh kumar14.55%116.67%
dave kleikampdave kleikamp14.55%116.67%
frank mayharfrank mayhar14.55%116.67%
Total22100.00%6100.00%


static int ext4_set_page_dirty(struct page *page) { WARN_ON_ONCE(!PageLocked(page) && !PageDirty(page)); WARN_ON_ONCE(!page_has_buffers(page)); return __set_page_dirty_buffers(page); }

Contributors

PersonTokensPropCommitsCommitProp
jan karajan kara41100.00%1100.00%
Total41100.00%1100.00%

static const struct address_space_operations ext4_aops = { .readpage = ext4_readpage, .readpages = ext4_readpages, .writepage = ext4_writepage, .writepages = ext4_writepages, .write_begin = ext4_write_begin, .write_end = ext4_write_end, .set_page_dirty = ext4_set_page_dirty, .bmap = ext4_bmap, .invalidatepage = ext4_invalidatepage, .releasepage = ext4_releasepage, .direct_IO = ext4_direct_IO, .migratepage = buffer_migrate_page, .is_partially_uptodate = block_is_partially_uptodate, .error_remove_page = generic_error_remove_page, }; static const struct address_space_operations ext4_journalled_aops = { .readpage = ext4_readpage, .readpages = ext4_readpages, .writepage = ext4_writepage, .writepages = ext4_writepages, .write_begin = ext4_write_begin, .write_end = ext4_journalled_write_end, .set_page_dirty = ext4_journalled_set_page_dirty, .bmap = ext4_bmap, .invalidatepage = ext4_journalled_invalidatepage, .releasepage = ext4_releasepage, .direct_IO = ext4_direct_IO, .is_partially_uptodate = block_is_partially_uptodate, .error_remove_page = generic_error_remove_page, }; static const struct address_space_operations ext4_da_aops = { .readpage = ext4_readpage, .readpages = ext4_readpages, .writepage = ext4_writepage, .writepages = ext4_writepages, .write_begin = ext4_da_write_begin, .write_end = ext4_da_write_end, .set_page_dirty = ext4_set_page_dirty, .bmap = ext4_bmap, .invalidatepage = ext4_da_invalidatepage, .releasepage = ext4_releasepage, .direct_IO = ext4_direct_IO, .migratepage = buffer_migrate_page, .is_partially_uptodate = block_is_partially_uptodate, .error_remove_page = generic_error_remove_page, };
void ext4_set_aops(struct inode *inode) { switch (ext4_inode_journal_mode(inode)) { case EXT4_INODE_ORDERED_DATA_MODE: case EXT4_INODE_WRITEBACK_DATA_MODE: break; case EXT4_INODE_JOURNAL_DATA_MODE: inode->i_mapping->a_ops = &ext4_journalled_aops; return; default: BUG(); } if (test_opt(inode->i_sb, DELALLOC)) inode->i_mapping->a_ops = &ext4_da_aops; else inode->i_mapping->a_ops = &ext4_aops; }

Contributors

PersonTokensPropCommitsCommitProp
amir goldsteinamir goldstein2635.62%228.57%
theodore tsotheodore tso1824.66%228.57%
dave kleikampdave kleikamp1621.92%114.29%
lukas czernerlukas czerner810.96%114.29%
duane griffinduane griffin56.85%114.29%
Total73100.00%7100.00%


static int __ext4_block_zero_page_range(handle_t *handle, struct address_space *mapping, loff_t from, loff_t length) { ext4_fsblk_t index = from >> PAGE_SHIFT; unsigned offset = from & (PAGE_SIZE-1); unsigned blocksize, pos; ext4_lblk_t iblock; struct inode *inode = mapping->host; struct buffer_head *bh; struct page *page; int err = 0; page = find_or_create_page(mapping, from >> PAGE_SHIFT, mapping_gfp_constraint(mapping, ~__GFP_FS)); if (!page) return -ENOMEM; blocksize = inode->i_sb->s_blocksize; iblock = index << (PAGE_SHIFT - inode->i_sb->s_blocksize_bits); if (!page_has_buffers(page)) create_empty_buffers(page, blocksize, 0); /* Find the buffer that contains "offset" */ bh = page_buffers(page); pos = blocksize; while (offset >= pos) { bh = bh->b_this_page; iblock++; pos += blocksize; } if (buffer_freed(bh)) { BUFFER_TRACE(bh, "freed: skip"); goto unlock; } if (!buffer_mapped(bh)) { BUFFER_TRACE(bh, "unmapped"); ext4_get_block(inode, iblock, bh, 0); /* unmapped? It's a hole - nothing to do */ if (!buffer_mapped(bh)) { BUFFER_TRACE(bh, "still unmapped"); goto unlock; } } /* Ok, it's mapped. Make sure it's up-to-date */ if (PageUptodate(page)) set_buffer_uptodate(bh); if (!buffer_uptodate(bh)) { err = -EIO; ll_rw_block(REQ_OP_READ, 0, 1, &bh); wait_on_buffer(bh); /* Uhhuh. Read error. Complain and punt. */ if (!buffer_uptodate(bh)) goto unlock; if (S_ISREG(inode->i_mode) && ext4_encrypted_inode(inode)) { /* We expect the key to be set. */ BUG_ON(!fscrypt_has_encryption_key(inode)); BUG_ON(blocksize != PAGE_SIZE); WARN_ON_ONCE(fscrypt_decrypt_page(page->mapping->host, page, PAGE_SIZE, 0, page->index)); } } if (ext4_should_journal_data(inode)) { BUFFER_TRACE(bh, "get write access"); err = ext4_journal_get_write_access(handle, bh); if (err) goto unlock; } zero_user(page, offset, length); BUFFER_TRACE(bh, "zeroed end of block"); if (ext4_should_journal_data(inode)) { err = ext4_handle_dirty_metadata(handle, inode, bh); } else { err = 0; mark_buffer_dirty(bh); if (ext4_should_order_data(inode)) err = ext4_jbd2_inode_add_write(handle, inode); } unlock: unlock_page(page); put_page(page); return err; }

Contributors

PersonTokensPropCommitsCommitProp
lukas czernerlukas czerner38883.98%213.33%
michael halcrowmichael halcrow388.23%16.67%
david gstirdavid gstir143.03%320.00%
kirill a. shutemovkirill a. shutemov61.30%16.67%
jon ernstjon ernst40.87%16.67%
michal hockomichal hocko30.65%16.67%
michael christiemichael christie30.65%16.67%
jaegeuk kimjaegeuk kim20.43%16.67%
jan karajan kara20.43%213.33%
ross zwislerross zwisler10.22%16.67%
matthew wilcoxmatthew wilcox10.22%16.67%
Total462100.00%15100.00%

/* * ext4_block_zero_page_range() zeros out a mapping of length 'length' * starting from file offset 'from'. The range to be zero'd must * be contained with in one block. If the specified range exceeds * the end of the block it will be shortened to end of the block * that cooresponds to 'from' */
static int ext4_block_zero_page_range(handle_t *handle, struct address_space *mapping, loff_t from, loff_t length) { struct inode *inode = mapping->host; unsigned offset = from & (PAGE_SIZE-1); unsigned blocksize = inode->i_sb->s_blocksize; unsigned max = blocksize - (offset & (blocksize - 1)); /* * correct length if it does not fall between * 'from' and the end of the block */ if (length > max || length < 0) length = max; if (IS_DAX(inode)) { return iomap_zero_range(inode, from, length, NULL, &ext4_iomap_ops); } return __ext4_block_zero_page_range(handle, mapping, from, length); }

Contributors

PersonTokensPropCommitsCommitProp
ross zwislerross zwisler10893.10%133.33%
jan karajan kara76.03%133.33%
kirill a. shutemovkirill a. shutemov10.86%133.33%
Total116100.00%3100.00%

/* * ext4_block_truncate_page() zeroes out a mapping from file offset `from' * up to the end of the block which corresponds to `from'. * This required during truncate. We need to physically zero the tail end * of that block so it doesn't yield old data if the file is later grown. */
static int ext4_block_truncate_page(handle_t *handle, struct address_space *mapping, loff_t from) { unsigned offset = from & (PAGE_SIZE-1); unsigned length; unsigned blocksize; struct inode *inode = mapping->host; blocksize = inode->i_sb->s_blocksize; length = blocksize - (offset & (blocksize - 1)); return ext4_block_zero_page_range(handle, mapping, from, length); }

Contributors

PersonTokensPropCommitsCommitProp
matthew wilcoxmatthew wilcox7697.44%133.33%
stephen hemmingerstephen hemminger11.28%133.33%
kirill a. shutemovkirill a. shutemov11.28%133.33%
Total78100.00%3100.00%


int ext4_zero_partial_blocks(handle_t *handle, struct inode *inode, loff_t lstart, loff_t length) { struct super_block *sb = inode->i_sb; struct address_space *mapping = inode->i_mapping; unsigned partial_start, partial_end; ext4_fsblk_t start, end; loff_t byte_end = (lstart + length - 1); int err = 0; partial_start = lstart & (sb->s_blocksize - 1); partial_end = byte_end & (sb->s_blocksize - 1); start = lstart >> sb->s_blocksize_bits; end = byte_end >> sb->s_blocksize_bits; /* Handle partial zero within the single block */ if (start == end && (partial_start || (partial_end != sb->s_blocksize - 1))) { err = ext4_block_zero_page_range(handle, mapping, lstart, length); return err; } /* Handle partial zero out on the start of the range */ if (partial_start) { err = ext4_block_zero_page_range(handle, mapping, lstart, sb->s_blocksize); if (err) return err; } /* Handle partial zero out on the end of the range */ if (partial_end != sb->s_blocksize - 1) err = ext4_block_zero_page_range(handle, mapping, byte_end - partial_end, partial_end + 1); return err; }

Contributors

PersonTokensPropCommitsCommitProp
lukas czernerlukas czerner203100.00%2100.00%
Total203100.00%2100.00%


int ext4_can_truncate(struct inode *inode) { if (S_ISREG(inode->i_mode)) return 1; if (S_ISDIR(inode->i_mode)) return 1; if (S_ISLNK(inode->i_mode)) return !ext4_inode_is_fast_symlink(inode); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
amir goldsteinamir goldstein3566.04%133.33%
allison hendersonallison henderson1324.53%133.33%
dave kleikampdave kleikamp59.43%133.33%
Total53100.00%3100.00%

/* * We have to make sure i_disksize gets properly updated before we truncate * page cache due to hole punching or zero range. Otherwise i_disksize update * can get lost as it may have been postponed to submission of writeback but * that will never happen after we truncate page cache. */
int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset, loff_t len) { handle_t *handle; loff_t size = i_size_read(inode); WARN_ON(!inode_is_locked(inode)); if (offset > size || offset + len < size) return 0; if (EXT4_I(inode)->i_disksize >= size) return 0; handle = ext4_journal_start(inode, EXT4_HT_MISC, 1); if (IS_ERR(handle)) return PTR_ERR(handle); ext4_update_i_disksize(inode, size); ext4_mark_inode_dirty(handle, inode); ext4_journal_stop(handle); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
jan karajan kara11199.11%150.00%
al viroal viro10.89%150.00%
Total112100.00%2100.00%

/* * ext4_punch_hole: punches a hole in a file by releasing the blocks * associated with the given offset and length * * @inode: File inode * @offset: The offset where the hole will begin * @len: The length of the hole * * Returns: 0 on success or negative on failure */
int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) { struct super_block *sb = inode->i_sb; ext4_lblk_t first_block, stop_block; struct address_space *mapping = inode->i_mapping; loff_t first_block_offset, last_block_offset; handle_t *handle; unsigned int credits; int ret = 0; if (!S_ISREG(inode->i_mode)) return -EOPNOTSUPP; trace_ext4_punch_hole(inode, offset, length, 0); /* * Write out all dirty pages to avoid race conditions * Then release them. */ if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) { ret = filemap_write_and_wait_range(mapping, offset, offset + length - 1); if (ret) return ret; } inode_lock(inode); /* No need to punch hole beyond i_size */ if (offset >= inode->i_size) goto out_mutex; /* * If the hole extends beyond i_size, set the hole * to end after the page that contains i_size */ if (offset + length > inode->i_size) { length = inode->i_size + PAGE_SIZE - (inode->i_size & (PAGE_SIZE - 1)) - offset; } if (offset & (sb->s_blocksize - 1) || (offset + length) & (sb->s_blocksize - 1)) { /* * Attach jinode to inode for jbd2 if we do any zeroing of * partial block */ ret = ext4_inode_attach_jinode(inode); if (ret < 0) goto out_mutex; } /* Wait all existing dio workers, newcomers will block on i_mutex */ ext4_inode_block_unlocked_dio(inode); inode_dio_wait(inode); /* * Prevent page faults from reinstantiating pages we have released from * page cache. */ down_write(&EXT4_I(inode)->i_mmap_sem); first_block_offset = round_up(offset, sb->s_blocksize); last_block_offset = round_down((offset + length), sb->s_blocksize) - 1; /* Now release the pages and zero block aligned part of pages*/ if (last_block_offset > first_block_offset) { ret = ext4_update_disksize_before_punch(inode, offset, length); if (ret) goto out_dio; truncate_pagecache_range(inode, first_block_offset, last_block_offset); } if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) credits = ext4_writepage_trans_blocks(inode); else credits = ext4_blocks_for_truncate(inode); handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits); if (IS_ERR(handle)) { ret = PTR_ERR(handle); ext4_std_error(sb, ret); goto out_dio; } ret = ext4_zero_partial_blocks(handle, inode, offset, length); if (ret) goto out_stop; first_block = (offset + sb->s_blocksize - 1) >> EXT4_BLOCK_SIZE_BITS(sb); stop_block = (offset + length) >> EXT4_BLOCK_SIZE_BITS(sb); /* If there are no blocks to remove, return now */ if (first_block >= stop_block) goto out_stop; down_write(&EXT4_I(inode)->i_data_sem); ext4_discard_preallocations(inode); ret = ext4_es_remove_extent(inode, first_block, stop_block - first_block); if (ret) { up_write(&EXT4_I(inode)->i_data_sem); goto out_stop; } if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) ret = ext4_ext_remove_space(inode, first_block, stop_block - 1); else ret = ext4_ind_remove_space(handle, inode, first_block, stop_block); up_write(&EXT4_I(inode)->i_data_sem); if (IS_SYNC(inode)) ext4_handle_sync(handle); inode->i_mtime = inode->i_ctime = current_time(inode); ext4_mark_inode_dirty(handle, inode); out_stop: ext4_journal_stop(handle); out_dio: up_write(&EXT4_I(inode)->i_mmap_sem); ext4_inode_resume_unlocked_dio(inode); out_mutex: inode_unlock(inode); return ret; }

Contributors

PersonTokensPropCommitsCommitProp
theodore tsotheodore tso40369.01%316.67%
jan karajan kara9315.92%316.67%
lukas czernerlukas czerner305.14%316.67%
amir goldsteinamir goldstein213.60%15.56%
dave kleikampdave kleikamp172.91%15.56%
zheng liuzheng liu122.05%211.11%
kirill a. shutemovkirill a. shutemov20.34%15.56%
ashish sangwanashish sangwan20.34%15.56%
al viroal viro20.34%15.56%
deepa dinamanideepa dinamani10.17%15.56%
allison hendersonallison henderson10.17%15.56%
Total584100.00%18100.00%


int ext4_inode_attach_jinode(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); struct jbd2_inode *jinode; if (ei->jinode || !EXT4_SB(inode->i_sb)->s_journal) return 0; jinode = jbd2_alloc_inode(GFP_KERNEL); spin_lock(&inode->i_lock); if (!ei->jinode) { if (!jinode) { spin_unlock(&inode->i_lock); return -ENOMEM; } ei->jinode = jinode; jbd2_journal_init_jbd_inode(ei->jinode, inode); jinode = NULL; } spin_unlock(&inode->i_lock); if (unlikely(jinode != NULL)) jbd2_free_inode(jinode); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
jan karajan kara131100.00%1100.00%
Total131100.00%1100.00%

/* * ext4_truncate() * * We block out ext4_get_block() block instantiations across the entire * transaction, and VFS/VM ensures that ext4_truncate() cannot run * simultaneously on behalf of the same inode. * * As we work through the truncate and commit bits of it to the journal there * is one core, guiding principle: the file's tree must always be consistent on * disk. We must be able to restart the truncate after a crash. * * The file's tree may be transiently inconsistent in memory (although it * probably isn't), but whenever we close off and commit a journal transaction, * the contents of (the filesystem + the journal) must be consistent and * restartable. It's pretty simple, really: bottom up, right to left (although * left-to-right works OK too). * * Note that at recovery time, journal replay occurs *before* the restart of * truncate against the orphan inode list. * * The committed inode has the new, desired i_size (which is the same as * i_disksize in this case). After a crash, ext4_orphan_cleanup() will see * that this inode's truncate did not complete and it will again call * ext4_truncate() to have another go. So there will be instantiated blocks * to the right of the truncation point in a crashed ext4 filesystem. But * that's fine - as long as they are linked from the inode, the post-crash * ext4_truncate() run will find them and release them. */
int ext4_truncate(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); unsigned int credits; int err = 0; handle_t *handle; struct address_space *mapping = inode->i_mapping; /* * There is a possibility that we're either freeing the inode * or it's a completely new inode. In those cases we might not * have i_mutex locked because it's not necessary. */ if (!(inode->i_state & (I_NEW|I_FREEING))) WARN_ON(!inode_is_locked(inode)); trace_ext4_truncate_enter(inode); if (!ext4_can_truncate(inode)) return 0; ext4_clear_inode_flag(inode, EXT4_INODE_EOFBLOCKS); if (inode->i_size == 0 && !test_opt(inode->i_sb, NO_AUTO_DA_ALLOC)) ext4_set_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE); if (ext4_has_inline_data(inode)) { int has_inline = 1; ext4_inline_data_truncate(inode, &has_inline); if (has_inline) return 0; } /* If we zero-out tail of the page, we have to create jinode for jbd2 */ if (inode->i_size & (inode->i_sb->s_blocksize - 1)) { if (ext4_inode_attach_jinode(inode) < 0) return 0; } if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) credits = ext4_writepage_trans_blocks(inode); else credits = ext4_blocks_for_truncate(inode); handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits); if (IS_ERR(handle)) return PTR_ERR(handle); if (inode->i_size & (inode->i_sb->s_blocksize - 1)) ext4_block_truncate_page(handle, mapping, inode->i_size); /* * We add the inode to the orphan list, so that if this * truncate spans multiple transactions, and we crash, we will * resume the truncate when the filesystem recovers. It also * marks the inode dirty, to catch the new size. * * Implication: the file must always be in a sane, consistent * truncatable state while each transaction commits. */ err = ext4_orphan_add(handle, inode); if (err) goto out_stop; down_write(&EXT4_I(inode)->i_data_sem); ext4_discard_preallocations(inode); if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) err = ext4_ext_truncate(handle, inode); else ext4_ind_truncate(handle, inode); up_write(&ei->i_data_sem); if (err) goto out_stop; if (IS_SYNC(inode)) ext4_handle_sync(handle); out_stop: /* * If this was a simple ftruncate() and the file will remain alive, * then we need to clear up the orphan record which we created above. * However, if this was a real unlink then we were called by * ext4_evict_inode(), and we allow that function to clean up the * orphan info for us. */ if (inode->i_nlink) ext4_orphan_del(handle, inode); inode->i_mtime = inode->i_ctime = current_time(inode); ext4_mark_inode_dirty(handle, inode); ext4_journal_stop(handle); trace_ext4_truncate_exit(inode); return err; }

Contributors

PersonTokensPropCommitsCommitProp
theodore tsotheodore tso24162.60%425.00%
amir goldsteinamir goldstein4311.17%16.25%
jan karajan kara287.27%16.25%
tao matao ma266.75%16.25%
dave kleikampdave kleikamp266.75%16.25%
lukas czernerlukas czerner71.82%16.25%
jiaying zhangjiaying zhang51.30%16.25%
kalpak shahkalpak shah30.78%16.25%
frank mayharfrank mayhar20.52%16.25%
deepa dinamanideepa dinamani10.26%16.25%
matthew wilcoxmatthew wilcox10.26%16.25%
wang shilongwang shilong10.26%16.25%
al viroal viro10.26%16.25%
Total385100.00%16100.00%

/* * ext4_get_inode_loc returns with an extra refcount against the inode's * underlying buffer_head on success. If 'in_mem' is true, we have all * data in memory that is needed to recreate the on-disk version of this * inode. */
static int __ext4_get_inode_loc(struct inode *inode, struct ext4_iloc *iloc, int in_mem) { struct ext4_group_desc *gdp; struct buffer_head *bh; struct super_block *sb = inode->i_sb; ext4_fsblk_t block; int inodes_per_block, inode_offset; iloc->bh = NULL; if (!ext4_valid_inum(sb, inode->i_ino)) return -EFSCORRUPTED; iloc->block_group = (inode->i_ino - 1) / EXT4_INODES_PER_GROUP(sb); gdp = ext4_get_group_desc(sb, iloc->block_group, NULL); if (!gdp) return -EIO; /* * Figure out the offset within the block group inode table */ inodes_per_block = EXT4_SB(sb)->s_inodes_per_block; inode_offset = ((inode->i_ino - 1) % EXT4_INODES_PER_GROUP(sb)); block = ext4_inode_table(sb, gdp) + (inode_offset / inodes_per_block); iloc->offset = (inode_offset % inodes_per_block) * EXT4_INODE_SIZE(sb); bh = sb_getblk(sb, block); if (unlikely(!bh)) return -ENOMEM; if (!buffer_uptodate(bh)) { lock_buffer(bh); /* * If the buffer has the write error flag, we have failed * to write out another inode in the same block. In this * case, we don't have to read the block because we may * read the old inode data successfully. */ if (buffer_write_io_error(bh) && !buffer_uptodate(bh)) set_buffer_uptodate(bh); if (buffer_uptodate(bh)) { /* someone brought it uptodate while we waited */ unlock_buffer(bh); goto has_buffer; } /* * If we have all information of the inode in memory and this * is the only valid inode in the block, we need not read the * block. */ if (in_mem) { struct buffer_head *bitmap_bh; int i, start; start = inode_offset & ~(inodes_per_block - 1); /* Is the inode bitmap in cache? */ bitmap_bh = sb_getblk(sb, ext4_inode_bitmap(sb, gdp)); if (unlikely(!bitmap_bh)) goto make_io; /* * If the inode bitmap isn't in cache then the * optimisation may end up performing two reads instead * of one, so skip it. */ if (!buffer_uptodate(bitmap_bh)) { brelse(bitmap_bh); goto make_io; } for (i = start; i < start + inodes_per_block; i++) { if (i == inode_offset) continue; if (ext4_test_bit(i, bitmap_bh->b_data)) break; } brelse(bitmap_bh); if (i == start + inodes_per_block) { /* all other inodes are free, so skip I/O */ memset(bh->b_data, 0, bh->b_size); set_buffer_uptodate(bh); unlock_buffer(bh); goto has_buffer; } } make_io: /* * If we need to do any I/O, try to pre-readahead extra * blocks from the inode table. */ if (EXT4_SB(sb)->s_inode_readahead_blks) { ext4_fsblk_t b, end, table; unsigned num; __u32 ra_blks = EXT4_SB(sb)->s_inode_readahead_blks; table = ext4_inode_table(sb, gdp); /* s_inode_readahead_blks is always a power of 2 */ b = block & ~((ext4_fsblk_t) ra_blks - 1); if (table > b) b = table; end = b + ra_blks; num = EXT4_INODES_PER_GROUP(sb); if (ext4_has_group_desc_csum(sb)) num -= ext4_itable_unused_count(sb, gdp); table += num / inodes_per_block; if (end > table) end = table; while (b <= end) sb_breadahead(sb, b++); } /* * There are other valid inodes in the buffer, this inode * has in-inode xattrs, or we don't have this inode in memory. * Read the block from disk. */ trace_ext4_load_inode(inode); get_bh(bh); bh->b_end_io = end_buffer_read_sync; submit_bh(REQ_OP_READ, REQ_META | REQ_PRIO, bh); wait_on_buffer(bh); if (!buffer_uptodate(bh)) { EXT4_ERROR_INODE_BLOCK(inode, block, "unable to read itable block"); brelse(bh); return -EIO; } } has_buffer: iloc->bh = bh; return 0; }

Contributors

PersonTokensPropCommitsCommitProp
dave kleikampdave kleikamp32855.88%14.55%
theodore tsotheodore tso19933.90%627.27%
hidehiro kawaihidehiro kawai193.24%14.55%
akinobu mitaakinobu mita61.02%14.55%
mingming caomingming cao61.02%14.55%
wang shilongwang shilong50.85%14.55%
jiaying zhangjiaying zhang50.85%14.55%
aneesh kumaraneesh kumar40.68%29.09%
tao matao ma30.51%14.55%
alexandre ratchovalexandre ratchov30.51%14.55%
christoph hellwigchristoph hellwig30.51%29.09%
laurent vivierlaurent vivier20.34%14.55%
darrick j. wongdarrick j. wong20.34%29.09%
michael christiemichael christie20.34%14.55%
Total587100.00%22100.00%


int ext4_get_inode_loc(struct inode *inode, struct ext4_iloc *iloc) { /* We have all inode data except xattrs in memory here. */ return __ext4_get_inode_loc(inode, iloc, !ext4_test_inode_state(inode, EXT4_STATE_XATTR)); }

Contributors

PersonTokensPropCommitsCommitProp
dave kleikampdave kleikamp2578.12%133.33%
mingming caomingming cao412.50%133.33%
theodore tsotheodore tso39.38%133.33%
Total32100.00%3100.00%


void ext4_set_inode_flags(struct inode *inode) { unsigned int flags = EXT4_I(inode)->i_flags; unsigned int new_fl = 0; if (flags & EXT4_SYNC_FL) new_fl |= S_SYNC; if (flags & EXT4_APPEND_FL) new_fl |= S_APPEND; if (flags & EXT4_IMMUTABLE_FL) new_fl |= S_IMMUTABLE; if (flags & EXT4_NOATIME_FL) new_fl |= S_NOATIME; if (flags & EXT4_DIRSYNC_FL) new_fl |= S_DIRSYNC; if (test_opt(inode->i_sb, DAX) && S_ISREG(inode->i_mode) && !ext4_should_journal_data(inode) && !ext4_has_inline_data(inode) && !ext4_encrypted_inode(inode)) new_fl |= S_DAX; inode_set_flags(inode, new_fl, S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC|S_DAX); }

Contributors

PersonTokensPropCommitsCommitProp
dave kleikampdave kleikamp5943.38%114.29%
theodore tsotheodore tso2820.59%228.57%
ross zwislerross zwisler2417.65%228.57%
jan karajan kara1813.24%114.29%
mingming caomingming cao75.15%114.29%
Total136100.00%7100.00%

/* Propagate flags from i_flags to EXT4_I(inode)->i_flags */
void ext4_get_inode_flags(struct ext4_inode_info *ei) { unsigned int vfs_fl; unsigned long old_fl, new_fl; do { vfs_fl = ei->vfs_inode.i_flags; old_fl = ei->i_flags; new_fl = old_fl & ~(EXT4_SYNC_FL|EXT4_APPEND_FL| EXT4_IMMUTABLE_FL|EXT4_NOATIME_FL| EXT4_DIRSYNC_FL); if (vfs_fl & S_SYNC) new_fl |= EXT4_SYNC_FL; if (vfs_fl & S_APPEND) new_fl |= EXT4_APPEND_FL; if (vfs_fl & S_IMMUTABLE) new_fl |= EXT4_IMMUTABLE_FL; if (vfs_fl & S_NOATIME) new_fl |= EXT4_NOATIME_FL; if (vfs_fl & S_DIRSYNC) new_fl |= EXT4_DIRSYNC_FL; } while (cmpxchg(&ei->i_flags, old_fl, new_fl) != old_fl); }

Contributors

PersonTokensPropCommitsCommitProp
jan karajan kara7360.33%150.00%
dmitriy monakhovdmitriy monakhov4839.67%150.00%
Total121100.00%2100.00%


static blkcnt_t ext4_inode_blocks(struct ext4_inode *raw_inode, struct ext4_inode_info *ei) { blkcnt_t i_blocks ; struct inode *inode = &(ei->vfs_inode); struct super_block *sb = inode->i_sb; if (ext4_has_feature_huge_file(sb)) { /* we are using combined 48 bit field */ i_blocks = ((u64)le16_to_cpu(raw_inode->i_blocks_high)) << 32 | le32_to_cpu(raw_inode->i_blocks_lo); if (ext4_test_inode_flag(inode, EXT4_INODE_HUGE_FILE)) { /* i_blocks represent file system block size */ return i_blocks << (inode->i_blkbits - 9); } else { return i_blocks; } } else { return le32_to_cpu(raw_inode->i_blocks_lo); } }

Contributors

PersonTokensPropCommitsCommitProp
aneesh kumaraneesh kumar10693.81%250.00%
theodore tsotheodore tso65.31%125.00%
darrick j. wongdarrick j. wong10.88%125.00%
Total113100.00%4100.00%


static inline void ext4_iget_extra_inode(struct inode *inode, struct ext4_inode *raw_inode, struct ext4_inode_info *ei) { __le32 *magic = (void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize; if (EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize + sizeof(__le32) <= EXT4_INODE_SIZE(inode->i_sb) && *magic == cpu_to_le32(EXT4_XATTR_MAGIC)) { ext4_set_inode_state(inode, EXT4_STATE_XATTR); ext4_find_inline_data_nolock(inode); } else EXT4_I(inode)->i_inline_off = 0; }

Contributors

PersonTokensPropCommitsCommitProp
tao matao ma7280.00%375.00%
eric biggerseric biggers1820.00%125.00%
Total90100.00%4100.00%


int ext4_get_projid(struct inode *inode, kprojid_t *projid) { if (!ext4_has_feature_project(inode->i_sb)) return -EOPNOTSUPP; *projid = EXT4_I(inode)->i_projid; return 0; }

Contributors

PersonTokensPropCommitsCommitProp
li xili xi4097.56%150.00%
kaho ngkaho ng12.44%150.00%
Total41100.00%2100.00%


struct inode *ext4_iget(struct super_block *sb, unsigned long ino) { struct ext4_iloc iloc; struct ext4_inode *raw_inode; struct ext4_inode_info *ei; struct inode *inode; journal_t *journal = EXT4_SB(sb)->s_journal; long ret; loff_t size; int block; uid_t i_uid; gid_t i_gid; projid_t i_projid; inode = iget_locked(sb, ino); if (!inode) return ERR_PTR(-ENOMEM); if (!(inode->i_state & I_NEW)) return inode; ei = EXT4_I(inode); iloc.bh = NULL; ret = __ext4_get_inode_loc(inode, &iloc, 0); if (ret < 0) goto bad_inode; raw_inode = ext4_raw_inode(&iloc); if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) { ei->i_extra_isize = le16_to_cpu(raw_inode->i_extra_isize); if (EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize > EXT4_INODE_SIZE(inode->i_sb) || (ei->i_extra_isize & 3)) { EXT4_ERROR_INODE(inode, "bad extra_isize %u (inode size %u)", ei->i_extra_isize, EXT4_INODE_SIZE(inode->i_sb)); ret = -EFSCORRUPTED; goto bad_inode; } } else ei->i_extra_isize = 0; /* Precompute checksum seed for inode metadata */ if (ext4_has_metadata_csum(sb)) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); __u32 csum; __le32 inum = cpu_to_le32(inode->i_ino); __le32 gen = raw_inode->i_generation; csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&inum, sizeof(inum)); ei->i_csum_seed = ext4_chksum(sbi, csum, (__u8 *)&gen, sizeof(gen)); } if (!ext4_inode_csum_verify(inode, raw_inode, ei)) { EXT4_ERROR_INODE(inode, "checksum invalid"); ret = -EFSBADCRC; goto bad_inode; } inode->i_mode = le16_to_cpu(raw_inode->i_mode); i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low); i_gid = (gid_t)le16_to_cpu(raw_inode->i_gid_low); if (ext4_has_feature_project(sb) && EXT4_INODE_SIZE(sb) > EXT4_GOOD_OLD_INODE_SIZE && EXT4_FITS_IN_INODE(raw_inode, ei, i_projid)) i_projid = (projid_t)le32_to_cpu(raw_inode->i_projid); else i_projid = EXT4_DEF_PROJID; if (!(test_opt(inode->i_sb, NO_UID32))) { i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16; i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16; } i_uid_write(inode, i_uid); i_gid_write(inode, i_gid); ei->i_projid = make_kprojid(&init_user_ns, i_projid); set_nlink(inode, le16_to_cpu(raw_inode->i_links_count)); ext4_clear_state_flags(ei); /* Only relevant on 32-bit archs */ ei->i_inline_off = 0; ei->i_dir_start_lookup = 0; ei->i_dtime = le32_to_cpu(raw_inode->i_dtime); /* We now have enough fields to check if the inode was active or not. * This is needed because nfsd might try to access dead inodes * the test is that same one that e2fsck uses * NeilBrown 1999oct15 */ if (inode->i_nlink == 0) { if ((inode->i_mode == 0 || !(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ORPHAN_FS)) && ino != EXT4_BOOT_LOADER_INO) { /* this inode is deleted */ ret = -ESTALE; goto bad_inode; } /* The only unlinked inodes we let through here have * valid i_mode and are being read by the orphan * recovery code: that's fine, we're about to complete * the process of deleting those. * OR it is the EXT4_BOOT_LOADER_INO which is * not initialized on a new filesystem. */ } ei->i_flags = le32_to_cpu(raw_inode->i_flags); inode->i_blocks = ext4_inode_blocks(raw_inode, ei); ei->i_file_acl = le32_to_cpu(raw_inode->i_file_acl_lo); if (ext4_has_feature_64bit(sb)) ei->i_file_acl |= ((__u64)le16_to_cpu(raw_inode->i_file_acl_high)) << 32; inode->i_size = ext4_isize(raw_inode); if ((size = i_size_read(inode)) < 0) { EXT4_ERROR_INODE(inode, "bad i_size value: %lld", size); ret = -EFSCORRUPTED; goto bad_inode; } ei->i_disksize = inode->i_size; #ifdef CONFIG_QUOTA ei->i_reserved_quota = 0; #endif inode->i_generation = le32_to_cpu(raw_inode->i_generation); ei->i_block_group = iloc.block_group; ei->i_last_alloc_group = ~0; /* * NOTE! The in-memory inode i_data array is in little-endian order * even on big-endian machines: we do NOT byteswap the block numbers! */ for (block = 0; block < EXT4_N_BLOCKS; block++) ei->i_data[block] = raw_inode->i_block[block]; INIT_LIST_HEAD(&ei->i_orphan); /* * Set transaction id's of transactions that have to be committed * to finish f[data]sync. We set them to currently running transaction * as we cannot be sure that the inode or some of its metadata isn't * part of the transaction - the inode could have been reclaimed and * now it is reread from disk. */ if (journal) { transaction_t *transaction; tid_t tid; read_lock(&journal->j_state_lock); if (journal->j_running_transaction) transaction = journal->j_running_transaction; else transaction = journal->j_committing_transaction; if (transaction) tid = transaction->t_tid; else tid = journal->j_commit_sequence; read_unlock(&journal->j_state_lock); ei->i_sync_tid = tid; ei->i_datasync_tid = tid; } if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) { if (ei->i_extra_isize == 0) { /* The extra space is currently unused. Use it. */ BUILD_BUG_ON(sizeof(struct ext4_inode) & 3); ei->i_extra_isize = sizeof(struct ext4_inode) - EXT4_GOOD_OLD_INODE_SIZE; } else { ext4_iget_extra_inode(inode, raw_inode, ei); } } EXT4_INODE_GET_XTIME(i_ctime, inode, raw_inode); EXT4_INODE_GET_XTIME(i_mtime, inode, raw_inode); EXT4_INODE_GET_XTIME(i_atime, inode, raw_inode); EXT4_EINODE_GET_XTIME(i_crtime, ei, raw_inode); if (likely(!test_opt2(inode->i_sb, HURD_COMPAT))) { inode->i_version = le32_to_cpu(raw_inode->i_disk_version); if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) { if (EXT4_FITS_IN_INODE(raw_inode, ei, i_version_hi)) inode->i_version |= (__u64)(le32_to_cpu(raw_inode->i_version_hi)) << 32; } } ret = 0; if (ei->i_file_acl && !ext4_data_block_valid(EXT4_SB(sb), ei->i_file_acl, 1)) { EXT4_ERROR_INODE(inode, "bad extended attribute block %llu", ei->i_file_acl); ret = -EFSCORRUPTED; goto bad_inode; } else if (!ext4_has_inline_data(inode)) { if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { if ((S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || (S_ISLNK(inode->i_mode) && !ext4_inode_is_fast_symlink(inode)))) /* Validate extent which is part of inode */ ret = ext4_ext_check_inode(inode); } else if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || (S_ISLNK(inode->i_mode) && !ext4_inode_is_fast_symlink(inode))) { /* Validate block references which are part of inode */ ret = ext4_ind_check_inode(inode); } } if (ret) goto bad_inode; if (S_ISREG(inode->i_mode)) { inode->i_op = &ext4_file_inode_operations; inode->i_fop = &ext4_file_operations; ext4_set_aops(inode); } else if (S_ISDIR(inode->i_mode)) { inode->i_op = &ext4_dir_inode_operations; inode->i_fop = &ext4_dir_operations; } else if (S_ISLNK(inode->i_mode)) { if (ext4_encrypted_inode(inode)) { inode->i_op = &ext4_encrypted_symlink_inode_operations; ext4_set_aops(inode); } else if (ext4_inode_is_fast_symlink(inode)) { inode->i_link = (char *)ei->i_data; inode->i_op = &ext4_fast_symlink_inode_operations; nd_terminate_link(ei->i_data, inode->i_size, sizeof(ei->i_data) - 1); } else { inode->i_op = &ext4_symlink_inode_operations; ext4_set_aops(inode); } inode_nohighmem(inode); } else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) || S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) { inode->i_op = &ext4_special_inode_operations; if (raw_inode->i_block[0]) init_special_inode(inode, inode->i_mode, old_decode_dev(le32_to_cpu(raw_inode->i_block[0]))); else init_special_inode(inode, inode->i_mode, new_decode_dev(le32_to_cpu(raw_inode->i_block[1]))); } else if (ino == EXT4_BOOT_LOADER_INO) { make_bad_inode(inode); } else { ret = -EFSCORRUPTED; EXT4_ERROR_INODE(inode, "bogus i_mode (%o)", inode->i_mode); goto bad_inode; } brelse(iloc.bh); ext4_set_inode_flags(inode); unlock_new_inode(inode); return inode; bad_inode: brelse(iloc.bh); iget_failed(inode); return ERR_PTR(ret); }

Contributors

PersonTokensPropCommitsCommitProp
dave kleikampdave kleikamp47532.09%12.08%
darrick j. wongdarrick j. wong22715.34%48.33%
theodore tsotheodore tso18412.43%1633.33%
david howellsdavid howells875.88%12.08%
jan karajan kara875.88%12.08%
li xili xi543.65%12.08%
jean noel cordennerjean noel cordenner533.58%12.08%
thiemo nagelthiemo nagel422.84%12.08%
al viroal viro372.50%36.25%
kalpak shahkalpak shah362.43%12.08%
aneesh kumaraneesh kumar322.16%48.33%
mingming caomingming cao221.49%12.08%
duane griffinduane griffin221.49%12.08%
tao matao ma221.49%36.25%
tilmann bubecktilmann bubeck211.42%12.08%
badari pulavartybadari pulavarty211.42%12.08%
eric w. biedermaneric w. biederman201.35%12.08%
eric biggerseric biggers201.35%12.08%
dmitriy monakhovdmitriy monakhov120.81%24.17%
miklos szeredimiklos szeredi40.27%12.08%
peter huewepeter huewe10.07%12.08%
kaho ngkaho ng10.07%12.08%
Total1480100.00%48100.00%


struct inode *ext4_iget_normal(struct super_block *sb, unsigned long ino) { if (ino < EXT4_FIRST_INO(sb) && ino != EXT4_ROOT_INO) return ERR_PTR(-EFSCORRUPTED); return ext4_iget(sb, ino); }

Contributors

PersonTokensPropCommitsCommitProp
theodore tsotheodore tso4397.73%150.00%
darrick j. wongdarrick j. wong12.27%150.00%
Total44100.00%2100.00%


static int ext4_inode_blocks_set(handle_t *handle, struct ext4_inode *raw_inode, struct ext4_inode_info *ei) { struct inode *inode = &(ei->vfs_inode); u64 i_blocks = inode->i_blocks; struct super_block *sb = inode->i_sb; if (i_blocks <= ~0U) { /* * i_blocks can be represented in a 32 bit variable * as multiple of 512 bytes */ raw_inode->i_blocks_lo = cpu_to_le32(i_blocks); raw_inode->i_blocks_high = 0; ext4_clear_inode_flag(inode, EXT4_INODE_HUGE_FILE); return 0; } if (!ext4_has_feature_huge_file(sb)) return -EFBIG; if (i_blocks <= 0xffffffffffffULL) { /* * i_blocks can be represented in a 48 bit variable * as multiple of 512 bytes */ raw_inode->i_blocks_lo = cpu_to_le32(i_blocks); raw_inode->i_blocks_high = cpu_to_le16(i_blocks >> 32); ext4_clear_inode_flag(inode, EXT4_INODE_HUGE_FILE); } else { ext4_set_inode_flag(inode, EXT4_INODE_HUGE_FILE); /* i_block is stored in file system block size */ i_blocks = i_blocks >> (inode->i_blkbits - 9); raw_inode->i_blocks_lo = cpu_to_le32(i_blocks); raw_inode->i_blocks_high = cpu_to_le16(i_blocks >> 32); } return 0; }

Contributors

PersonTokensPropCommitsCommitProp
aneesh kumaraneesh kumar14280.23%233.33%
dmitriy monakhovdmitriy monakhov1810.17%116.67%
theodore tsotheodore tso158.47%116.67%
darrick j. wongdarrick j. wong10.56%116.67%
anatol pomozovanatol pomozov10.56%116.67%
Total177100.00%6100.00%

struct other_inode { unsigned long orig_ino; struct ext4_inode *raw_inode; };
static int other_inode_match(struct inode * inode, unsigned long ino, void *data) { struct other_inode *oi = (struct other_inode *) data; if ((inode->i_ino != ino) || (inode->i_state & (I_FREEING | I_WILL_FREE | I_NEW | I_DIRTY_SYNC | I_DIRTY_DATASYNC)) || ((inode->i_state & I_DIRTY_TIME) == 0)) return 0; spin_lock(&inode->i_lock); if (((inode->i_state & (I_FREEING | I_WILL_FREE | I_NEW | I_DIRTY_SYNC | I_DIRTY_DATASYNC)) == 0) && (inode->i_state & I_DIRTY_TIME)) { struct ext4_inode_info *ei = EXT4_I(inode); inode->i_state &= ~(I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED); spin_unlock(&inode->i_lock); spin_lock(&ei->i_raw_lock); EXT4_INODE_SET_XTIME(i_ctime, inode, oi->raw_inode); EXT4_INODE_SET_XTIME(i_mtime, inode, oi->raw_inode); EXT4_INODE_SET_XTIME(i_atime, inode, oi->raw_inode); ext4_inode_csum_set(inode, oi->raw_inode, ei); spin_unlock(&ei->i_raw_lock); trace_ext4_other_inode_update_time(inode, oi->orig_ino); return -1; } spin_unlock(&inode->i_lock); return -1; }

Contributors

PersonTokensPropCommitsCommitProp
theodore tsotheodore tso230100.00%1100.00%
Total230100.00%1100.00%

/* * Opportunistically update the other time fields for other inodes in * the same inode table block. */
static void ext4_update_other_inodes_time(struct super_block *sb, unsigned long orig_ino, char *buf) { struct other_inode oi; unsigned long ino; int i, inodes_per_block = EXT4_SB(sb)->s_inodes_per_block; int inode_size = EXT4_INODE_SIZE(sb); oi.orig_ino = orig_ino; /* * Calculate the first inode in the inode table block. Inode * numbers are one-based. That is, the first inode in a block * (assuming 4k blocks and 256 byte inodes) is (n*16 + 1). */ ino = ((orig_ino - 1) & ~(inodes_per_block - 1)) + 1; for (i = 0; i < inodes_per_block; i++, ino++, buf += inode_size) { if (ino == orig_ino) continue; oi.raw_inode = (struct ext4_inode *) buf; (void) find_inode_nowait(sb, ino, other_inode_match, &oi); } }

Contributors

PersonTokensPropCommitsCommitProp
theodore tsotheodore tso128100.00%3100.00%
Total128100.00%3100.00%

/* * Post the struct inode info into an on-disk inode location in the * buffer-cache. This gobbles the caller's reference to the * buffer_head in the inode location struct. * * The caller must have write access to iloc->bh. */
static int ext4_do_update_inode(handle_t *handle, struct inode *inode, struct ext4_iloc *iloc) { struct ext4_inode *raw_inode = ext4_raw_inode(iloc); struct ext4_inode_info *ei = EXT4_I(inode); struct buffer_head *bh = iloc->bh; struct super_block *sb = inode->i_sb; int err = 0, rc, block; int need_datasync = 0, set_large_file = 0; uid_t i_uid; gid_t i_gid; projid_t i_projid; spin_lock(&ei->i_raw_lock); /* For fields not tracked in the in-memory inode, * initialise them to zero for new inodes. */ if (ext4_test_inode_state(inode, EXT4_STATE_NEW)) memset(raw_inode, 0, EXT4_SB(inode->i_sb)->s_inode_size); ext4_get_inode_flags(ei); raw_inode->i_mode = cpu_to_le16(inode->i_mode); i_uid = i_uid_read(inode); i_gid = i_gid_read(inode); i_projid = from_kprojid(&init_user_ns, ei->i_projid); if (!(test_opt(inode->i_sb, NO_UID32))) { raw_inode->i_uid_low = cpu_to_le16(low_16_bits(i_uid)); raw_inode->i_gid_low = cpu_to_le16(low_16_bits(i_gid)); /* * Fix up interoperability with old kernels. Otherwise, old inodes get * re-used with the upper 16 bits of the uid/gid intact */ if (ei->i_dtime && list_empty(&ei->i_orphan)) { raw_inode->i_uid_high = 0; raw_inode->i_gid_high = 0; } else { raw_inode->i_uid_high = cpu_to_le16(high_16_bits(i_uid)); raw_inode->i_gid_high = cpu_to_le16(high_16_bits(i_gid)); } } else { raw_inode->i_uid_low = cpu_to_le16(fs_high2lowuid(i_uid)); raw_inode->i_gid_low = cpu_to_le16(fs_high2lowgid(i_gid)); raw_inode->i_uid_high = 0; raw_inode->i_gid_high = 0; } raw_inode->i_links_count = cpu_to_le16(inode->i_nlink); EXT4_INODE_SET_XTIME(i_ctime, inode, raw_inode); EXT4_INODE_SET_XTIME(i_mtime, inode, raw_inode); EXT4_INODE_SET_XTIME(i_atime, inode, raw_inode); EXT4_EINODE_SET_XTIME(i_crtime, ei, raw_inode); err = ext4_inode_blocks_set(handle, raw_inode, ei); if (err) { spin_unlock(&ei->i_raw_lock); goto out_brelse; } raw_inode->i_dtime = cpu_to_le32(ei->i_dtime); raw_inode->i_flags = cpu_to_le32(ei->i_flags & 0xFFFFFFFF); if (likely(!test_opt2(inode->i_sb, HURD_COMPAT))) raw_inode->i_file_acl_high = cpu_to_le16(ei->i_file_acl >> 32); raw_inode->i_file_acl_lo = cpu_to_le32(ei->i_file_acl); if (ei->i_disksize != ext4_isize(raw_inode)) { ext4_isize_set(raw_inode, ei->i_disksize); need_datasync = 1; } if (ei->i_disksize > 0x7fffffffULL) { if (!ext4_has_feature_large_file(sb) || EXT4_SB(sb)->s_es->s_rev_level == cpu_to_le32(EXT4_GOOD_OLD_REV)) set_large_file = 1; } raw_inode->i_generation = cpu_to_le32(inode->i_generation); if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) { if (old_valid_dev(inode->i_rdev)) { raw_inode->i_block[0] = cpu_to_le32(old_encode_dev(inode->i_rdev)); raw_inode->i_block[1] = 0; } else { raw_inode->i_block[0] = 0; raw_inode->i_block[1] = cpu_to_le32(new_encode_dev(inode->i_rdev)); raw_inode->i_block[2] = 0; } } else if (!ext4_has_inline_data(inode)) { for (block = 0; block < EXT4_N_BLOCKS; block++) raw_inode->i_block[block] = ei->i_data[block]; } if (likely(!test_opt2(inode->i_sb, HURD_COMPAT))) { raw_inode->i_disk_version = cpu_to_le32(inode->i_version); if (ei->i_extra_isize) { if (EXT4_FITS_IN_INODE(raw_inode, ei, i_version_hi)) raw_inode->i_version_hi = cpu_to_le32(inode->i_version >> 32); raw_inode->i_extra_isize = cpu_to_le16(ei->i_extra_isize); } } BUG_ON(!ext4_has_feature_project(inode->i_sb) && i_projid != EXT4_DEF_PROJID); if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE && EXT4_FITS_IN_INODE(raw_inode, ei, i_projid)) raw_inode->i_projid = cpu_to_le32(i_projid); ext4_inode_csum_set(inode, raw_inode, ei); spin_unlock(&ei->i_raw_lock); if (inode->i_sb->s_flags & MS_LAZYTIME) ext4_update_other_inodes_time(inode->i_sb, inode->i_ino, bh->b_data); BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata"); rc = ext4_handle_dirty_metadata(handle, NULL, bh); if (!err) err = rc; ext4_clear_inode_state(inode, EXT4_STATE_NEW); if (set_large_file) { BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get write access"); err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh); if (err) goto out_brelse; ext4_update_dynamic_rev(sb); ext4_set_feature_large_file(sb); ext4_handle_sync(handle); err = ext4_handle_dirty_super(handle, sb); } ext4_update_inode_fsync_trans(handle, inode, need_datasync); out_brelse: brelse(bh); ext4_std_error(inode->i_sb, err); return err; }

Contributors

PersonTokensPropCommitsCommitProp
dave kleikampdave kleikamp47751.85%13.57%
theodore tsotheodore tso15216.52%621.43%
li xili xi646.96%27.14%
jean noel cordennerjean noel cordenner374.02%13.57%
jan karajan kara363.91%310.71%
kalpak shahkalpak shah242.61%13.57%
daeho jeongdaeho jeong232.50%13.57%
badari pulavartybadari pulavarty222.39%13.57%
eric w. biedermaneric w. biederman202.17%13.57%
mingming caomingming cao131.41%13.57%
aneesh kumaraneesh kumar131.41%310.71%
liang xieliang xie121.30%13.57%
darrick j. wongdarrick j. wong111.20%27.14%
tao matao ma111.20%13.57%
frank mayharfrank mayhar30.33%13.57%
kaho ngkaho ng10.11%13.57%
curt wohlgemuthcurt wohlgemuth10.11%13.57%
Total920100.00%28100.00%

/* * ext4_write_inode() * * We are called from a few places: * * - Within generic_file_aio_write() -> generic_write_sync() for O_SYNC files. * Here, there will be no transaction running. We wait for any running * transaction to commit. * * - Within flush work (sys_sync(), kupdate and such). * We wait on commit, if told to. * * - Within iput_final() -> write_inode_now() * We wait on commit, if told to. * * In all cases it is actually safe for us to return without doing anything, * because the inode has been copied into a raw inode buffer in * ext4_mark_inode_dirty(). This is a correctness thing for WB_SYNC_ALL * writeback. * * Note that we are absolutely dependent upon all inode dirtiers doing the * right thing: they *must* call mark_inode_dirty() after dirtying info in * which we are interested. * * It would be a bug for them to not do this. The code: * * mark_inode_dirty(inode) * stuff(); * inode->i_size = expr; * * is in error because write_inode() could occur while `stuff()' is running, * and the new i_size will be lost. Plus the inode will no longer be on the * superblock's dirty inode list. */
int ext4_write_inode(struct inode *inode, struct writeback_control *wbc) { int err; if (WARN_ON_ONCE(current->flags & PF_MEMALLOC)) return 0; if (EXT4_SB(inode->i_sb)->s_journal) { if (ext4_journal_current_handle()) { jbd_debug(1, "called recursively, non-PF_MEMALLOC!\n"); dump_stack(); return -EIO; } /* * No need to force transaction in WB_SYNC_NONE mode. Also * ext4_sync_fs() will force the commit after everything is * written. */ if (wbc->sync_mode != WB_SYNC_ALL || wbc->for_sync) return 0; err = ext4_force_commit(inode->i_sb); } else { struct ext4_iloc iloc; err = __ext4_get_inode_loc(inode, &iloc, 0); if (err) return err; /* * sync(2) will flush the whole buffer cache. No need to do * it here separately for each inode. */ if (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync) sync_dirty_buffer(iloc.bh); if (buffer_req(iloc.bh) && !buffer_uptodate(iloc.bh)) { EXT4_ERROR_INODE_BLOCK(inode, iloc.bh->b_blocknr, "IO error syncing inode"); err = -EIO; } brelse(iloc.bh); } return err; }

Contributors

PersonTokensPropCommitsCommitProp
frank mayharfrank mayhar8847.57%218.18%
dave kleikampdave kleikamp5228.11%19.09%
christoph hellwigchristoph hellwig147.57%19.09%
jan karajan kara115.95%19.09%
curt wohlgemuthcurt wohlgemuth105.41%218.18%
theodore tsotheodore tso63.24%218.18%
mingming caomingming cao42.16%218.18%
Total185100.00%11100.00%

/* * In data=journal mode ext4_journalled_invalidatepage() may fail to invalidate * buffers that are attached to a page stradding i_size and are undergoing * commit. In that case we have to wait for commit to finish and try again. */
static void ext4_wait_for_tail_page_commit(struct inode *inode) { struct page *page; unsigned offset; journal_t *journal = EXT4_SB(inode->i_sb)->s_journal; tid_t commit_tid = 0; int ret; offset = inode->i_size & (PAGE_SIZE - 1); /* * All buffers in the last page remain valid? Then there's nothing to * do. We do the check mainly to optimize the common PAGE_SIZE == * blocksize case */ if (offset > PAGE_SIZE - (1 << inode->i_blkbits)) return; while (1) { page = find_lock_page(inode->i_mapping, inode->i_size >> PAGE_SHIFT); if (!page) return; ret = __ext4_journalled_invalidatepage(page, offset, PAGE_SIZE - offset); unlock_page(page); put_page(page); if (ret != -EBUSY) return; commit_tid = 0; read_lock(&journal->j_state_lock); if (journal->j_committing_transaction) commit_tid = journal->j_committing_transaction->t_tid; read_unlock(&journal->j_state_lock); if (commit_tid) jbd2_log_wait_commit(journal, commit_tid); } }

Contributors

PersonTokensPropCommitsCommitProp
jan karajan kara16294.74%125.00%
kirill a. shutemovkirill a. shutemov63.51%250.00%
lukas czernerlukas czerner31.75%125.00%
Total171100.00%4100.00%

/* * ext4_setattr() * * Called from notify_change. * * We want to trap VFS attempts to truncate the file as soon as * possible. In particular, we want to make sure that when the VFS * shrinks i_size, we put the inode on the orphan list and modify * i_disksize immediately, so that during the subsequent flushing of * dirty pages and freeing of disk blocks, we can guarantee that any * commit will leave the blocks being flushed in an unused state on * disk. (On recovery, the inode will get truncated and the blocks will * be freed, so we have a strong guarantee that no future commit will * leave these blocks visible to the user.) * * Another thing we have to assure is that if we are in ordered mode * and inode is still attached to the committing transaction, we must * we start writeout of all the dirty pages which are being truncated. * This way we are sure that all the data written in the previous * transaction are already on disk (truncate waits for pages under * writeback). * * Called with inode->i_mutex down. */
int ext4_setattr(struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); int error, rc = 0; int orphan = 0; const unsigned int ia_valid = attr->ia_valid; error = setattr_prepare(dentry, attr); if (error) return error; if (is_quota_modification(inode, attr)) { error = dquot_initialize(inode); if (error) return error; } if ((ia_valid & ATTR_UID && !uid_eq(attr->ia_uid, inode->i_uid)) || (ia_valid & ATTR_GID && !gid_eq(attr->ia_gid, inode->i_gid))) { handle_t *handle; /* (user+group)*(old+new) structure, inode write (sb, * inode block, ? - but truncate inode update has it) */ handle = ext4_journal_start(inode, EXT4_HT_QUOTA, (EXT4_MAXQUOTAS_INIT_BLOCKS(inode->i_sb) + EXT4_MAXQUOTAS_DEL_BLOCKS(inode->i_sb)) + 3); if (IS_ERR(handle)) { error = PTR_ERR(handle); goto err_out; } error = dquot_transfer(inode, attr); if (error) { ext4_journal_stop(handle); return error; } /* Update corresponding info in inode so that everything is in * one transaction */ if (attr->ia_valid & ATTR_UID) inode->i_uid = attr->ia_uid; if (attr->ia_valid & ATTR_GID) inode->i_gid = attr->ia_gid; error = ext4_mark_inode_dirty(handle, inode); ext4_journal_stop(handle); } if (attr->ia_valid & ATTR_SIZE) { handle_t *handle; loff_t oldsize = inode->i_size; int shrink = (attr->ia_size <= inode->i_size); if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); if (attr->ia_size > sbi->s_bitmap_maxbytes) return -EFBIG; } if (!S_ISREG(inode->i_mode)) return -EINVAL; if (IS_I_VERSION(inode) && attr->ia_size != inode->i_size) inode_inc_iversion(inode); if (ext4_should_order_data(inode) && (attr->ia_size < inode->i_size)) { error = ext4_begin_ordered_truncate(inode, attr->ia_size); if (error) goto err_out; } if (attr->ia_size != inode->i_size) { handle = ext4_journal_start(inode, EXT4_HT_INODE, 3); if (IS_ERR(handle)) { error = PTR_ERR(handle); goto err_out; } if (ext4_handle_valid(handle) && shrink) { error = ext4_orphan_add(handle, inode); orphan = 1; } /* * Update c/mtime on truncate up, ext4_truncate() will * update c/mtime in shrink case below */ if (!shrink) { inode->i_mtime = current_time(inode); inode->i_ctime = inode->i_mtime; } down_write(&EXT4_I(inode)->i_data_sem); EXT4_I(inode)->i_disksize = attr->ia_size; rc = ext4_mark_inode_dirty(handle, inode); if (!error) error = rc; /* * We have to update i_size under i_data_sem together * with i_disksize to avoid races with writeback code * running ext4_wb_update_i_disksize(). */ if (!error) i_size_write(inode, attr->ia_size); up_write(&EXT4_I(inode)->i_data_sem); ext4_journal_stop(handle); if (error) { if (orphan) ext4_orphan_del(NULL, inode); goto err_out; } } if (!shrink) pagecache_isize_extended(inode, oldsize, inode->i_size); /* * Blocks are going to be removed from the inode. Wait * for dio in flight. Temporarily disable * dioread_nolock to prevent livelock. */ if (orphan) { if (!ext4_should_journal_data(inode)) { ext4_inode_block_unlocked_dio(inode); inode_dio_wait(inode); ext4_inode_resume_unlocked_dio(inode); } else ext4_wait_for_tail_page_commit(inode); } down_write(&EXT4_I(inode)->i_mmap_sem); /* * Truncate pagecache after we've waited for commit * in data=journal mode to make pages freeable. */ truncate_pagecache(inode, inode->i_size); if (shrink) { rc = ext4_truncate(inode); if (rc) error = rc; } up_write(&EXT4_I(inode)->i_mmap_sem); } if (!error) { setattr_copy(inode, attr); mark_inode_dirty(inode); } /* * If the call to ext4_truncate failed to get a transaction handle at * all, we need to clean up the in-core orphan list manually. */ if (orphan && inode->i_nlink) ext4_orphan_del(NULL, inode); if (!error && (ia_valid & ATTR_MODE)) rc = posix_acl_chmod(inode, inode->i_mode); err_out: ext4_std_error(inode->i_sb, error); if (!error) error = rc; return error; }

Contributors

PersonTokensPropCommitsCommitProp
dave kleikampdave kleikamp32542.65%12.94%
jan karajan kara15520.34%823.53%
josef bacikjosef bacik587.61%12.94%
christoph hellwigchristoph hellwig536.96%617.65%
dmitriy monakhovdmitriy monakhov526.82%720.59%
eric sandeeneric sandeen425.51%12.94%
theodore tsotheodore tso253.28%411.76%
eryu guaneryu guan243.15%12.94%
mingming caomingming cao121.57%12.94%
eric w. biedermaneric w. biederman101.31%12.94%
david howellsdavid howells30.39%12.94%
jiaying zhangjiaying zhang20.26%12.94%
deepa dinamanideepa dinamani10.13%12.94%
Total762100.00%34100.00%


int ext4_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) { struct inode *inode; unsigned long long delalloc_blocks; inode = d_inode(dentry); generic_fillattr(inode, stat); /* * If there is inline data in the inode, the inode will normally not * have data blocks allocated (it may have an external xattr block). * Report at least one sector for such files, so tools like tar, rsync, * others doen't incorrectly think the file is completely sparse. */ if (unlikely(ext4_has_inline_data(inode))) stat->blocks += (stat->size + 511) >> 9; /* * We can't update i_blocks if the block allocation is delayed * otherwise in the case of system crash before the real block * allocation is done, we will have i_blocks inconsistent with * on-disk file blocks. * We always keep i_blocks updated together with real * allocation. But to not confuse with user, stat * will return the blocks that include the delayed allocation * blocks for this file. */ delalloc_blocks = EXT4_C2B(EXT4_SB(inode->i_sb), EXT4_I(inode)->i_reserved_data_blocks); stat->blocks += delalloc_blocks << (inode->i_sb->s_blocksize_bits - 9); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
mingming caomingming cao6661.11%120.00%
andreas dilgerandreas dilger2523.15%120.00%
tao matao ma109.26%120.00%
jan karajan kara43.70%120.00%
david howellsdavid howells32.78%120.00%
Total108100.00%5100.00%


static int ext4_index_trans_blocks(struct inode *inode, int lblocks, int pextents) { if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) return ext4_ind_trans_blocks(inode, lblocks); return ext4_ext_index_trans_blocks(inode, pextents); }

Contributors

PersonTokensPropCommitsCommitProp
mingming caomingming cao2453.33%116.67%
alex tomasalex tomas1022.22%116.67%
jan karajan kara48.89%116.67%
dave kleikampdave kleikamp36.67%116.67%
dmitriy monakhovdmitriy monakhov36.67%116.67%
amir goldsteinamir goldstein12.22%116.67%
Total45100.00%6100.00%

/* * Account for index blocks, block groups bitmaps and block group * descriptor blocks if modify datablocks and index blocks * worse case, the indexs blocks spread over different block groups * * If datablocks are discontiguous, they are possible to spread over * different block groups too. If they are contiguous, with flexbg, * they could still across block group boundary. * * Also account for superblock, inode, quota and xattr blocks */
static int ext4_meta_trans_blocks(struct inode *inode, int lblocks, int pextents) { ext4_group_t groups, ngroups = ext4_get_groups_count(inode->i_sb); int gdpblocks; int idxblocks; int ret = 0; /* * How many index blocks need to touch to map @lblocks logical blocks * to @pextents physical extents? */ idxblocks = ext4_index_trans_blocks(inode, lblocks, pextents); ret = idxblocks; /* * Now let's see how many group bitmaps and group descriptors need * to account */ groups = idxblocks + pextents; gdpblocks = groups; if (groups > ngroups) groups = ngroups; if (groups > EXT4_SB(inode->i_sb)->s_gdb_count) gdpblocks = EXT4_SB(inode->i_sb)->s_gdb_count; /* bitmaps and block group descriptor blocks */ ret += groups + gdpblocks; /* Blocks for super block, inode, quota and xattr blocks */ ret += EXT4_META_TRANS_BLOCKS(inode->i_sb); return ret; }

Contributors

PersonTokensPropCommitsCommitProp
mingming caomingming cao8671.07%120.00%
dave kleikampdave kleikamp1411.57%120.00%
theodore tsotheodore tso1411.57%240.00%
jan karajan kara75.79%120.00%
Total121100.00%5100.00%

/* * Calculate the total number of credits to reserve to fit * the modification of a single pages into a single transaction, * which may include multiple chunks of block allocations. * * This could be called via ext4_write_begin() * * We need to consider the worse case, when * one new block per extent. */
int ext4_writepage_trans_blocks(struct inode *inode) { int bpp = ext4_journal_blocks_per_page(inode); int ret; ret = ext4_meta_trans_blocks(inode, bpp, bpp); /* Account for data blocks for journalled mode */ if (ext4_should_journal_data(inode)) ret += bpp; return ret; }

Contributors

PersonTokensPropCommitsCommitProp
mingming caomingming cao4289.36%133.33%
dave kleikampdave kleikamp48.51%133.33%
jan karajan kara12.13%133.33%
Total47100.00%3100.00%

/* * Calculate the journal credits for a chunk of data modification. * * This is called from DIO, fallocate or whoever calling * ext4_map_blocks() to map/allocate a chunk of contiguous disk blocks. * * journal buffers for data blocks are not included here, as DIO * and fallocate do no need to journal data buffers. */
int ext4_chunk_trans_blocks(struct inode *inode, int nrblocks) { return ext4_meta_trans_blocks(inode, nrblocks, 1); }

Contributors

PersonTokensPropCommitsCommitProp
mingming caomingming cao23100.00%1100.00%
Total23100.00%1100.00%

/* * The caller must have previously called ext4_reserve_inode_write(). * Give this, we know that the caller already has write access to iloc->bh. */
int ext4_mark_iloc_dirty(handle_t *handle, struct inode *inode, struct ext4_iloc *iloc) { int err = 0; if (IS_I_VERSION(inode)) inode_inc_iversion(inode); /* the do_update_inode consumes one bh->b_count */ get_bh(iloc->bh); /* ext4_do_update_inode() does jbd2_journal_dirty_metadata */ err = ext4_do_update_inode(handle, inode, iloc); put_bh(iloc->bh); return err; }

Contributors

PersonTokensPropCommitsCommitProp
dave kleikampdave kleikamp5075.76%120.00%
jean noel cordennerjean noel cordenner1116.67%120.00%
mingming caomingming cao46.06%240.00%
theodore tsotheodore tso11.52%120.00%
Total66100.00%5100.00%

/* * On success, We end up with an outstanding reference count against * iloc->bh. This _must_ be cleaned up later. */
int ext4_reserve_inode_write(handle_t *handle, struct inode *inode, struct ext4_iloc *iloc) { int err; err = ext4_get_inode_loc(inode, iloc); if (!err) { BUFFER_TRACE(iloc->bh, "get_write_access"); err = ext4_journal_get_write_access(handle, iloc->bh); if (err) { brelse(iloc->bh); iloc->bh = NULL; } } ext4_std_error(inode->i_sb, err); return err; }

Contributors

PersonTokensPropCommitsCommitProp
dave kleikampdave kleikamp8494.38%150.00%
mingming caomingming cao55.62%150.00%
Total89100.00%2100.00%

/* * Expand an inode by new_extra_isize bytes. * Returns 0 on success or negative error number on failure. */
static int ext4_expand_extra_isize(struct inode *inode, unsigned int new_extra_isize, struct ext4_iloc iloc, handle_t *handle) { struct ext4_inode *raw_inode; struct ext4_xattr_ibody_header *header; if (EXT4_I(inode)->i_extra_isize >= new_extra_isize) return 0; raw_inode = ext4_raw_inode(&iloc); header = IHDR(inode, raw_inode); /* No extended attributes present */ if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR) || header->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC)) { memset((void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE, 0, new_extra_isize); EXT4_I(inode)->i_extra_isize = new_extra_isize; return 0; } /* try to expand with EAs present */ return ext4_expand_extra_isize_ea(inode, new_extra_isize, raw_inode, handle); }

Contributors

PersonTokensPropCommitsCommitProp
kalpak shahkalpak shah12296.83%133.33%
theodore tsotheodore tso32.38%133.33%
aneesh kumaraneesh kumar10.79%133.33%
Total126100.00%3100.00%

/* * What we do here is to mark the in-core inode as clean with respect to inode * dirtiness (it may still be data-dirty). * This means that the in-core inode may be reaped by prune_icache * without having to perform any I/O. This is a very good thing, * because *any* task may call prune_icache - even ones which * have a transaction open against a different journal. * * Is this cheating? Not really. Sure, we haven't written the * inode out, but prune_icache isn't a user-visible syncing function. * Whenever the user wants stuff synced (sys_sync, sys_msync, sys_fsync) * we start and wait on commits. */
int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode) { struct ext4_iloc iloc; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); static unsigned int mnt_count; int err, ret; might_sleep(); trace_ext4_mark_inode_dirty(inode, _RET_IP_); err = ext4_reserve_inode_write(handle, inode, &iloc); if (err) return err; if (EXT4_I(inode)->i_extra_isize < sbi->s_want_extra_isize && !ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND)) { /* * In nojournal mode, we can immediately attempt to expand * the inode. When journaled, we first need to obtain extra * buffer credits since we may write into the EA block * with this same handle. If journal_extend fails, then it will * only result in a minor loss of functionality for that inode. * If this is felt to be critical, then e2fsck should be run to * force a large enough s_min_extra_isize. */ if (!ext4_handle_valid(handle) || jbd2_journal_extend(handle, EXT4_DATA_TRANS_BLOCKS(inode->i_sb)) == 0) { ret = ext4_expand_extra_isize(inode, sbi->s_want_extra_isize, iloc, handle); if (ret) { if (mnt_count != le16_to_cpu(sbi->s_es->s_mnt_count)) { ext4_warning(inode->i_sb, "Unable to expand inode %lu. Delete" " some EAs or run e2fsck.", inode->i_ino); mnt_count = le16_to_cpu(sbi->s_es->s_mnt_count); } } } } return ext4_mark_iloc_dirty(handle, inode, &iloc); }

Contributors

PersonTokensPropCommitsCommitProp
kalpak shahkalpak shah11058.20%112.50%
dave kleikampdave kleikamp4423.28%112.50%
theodore tsotheodore tso105.29%225.00%
eryu guaneryu guan84.23%112.50%
eric whitneyeric whitney73.70%112.50%
aneesh kumaraneesh kumar63.17%112.50%
mingming caomingming cao42.12%112.50%
Total189100.00%8100.00%

/* * ext4_dirty_inode() is called from __mark_inode_dirty() * * We're really interested in the case where a file is being extended. * i_size has been changed by generic_commit_write() and we thus need * to include the updated inode in the current transaction. * * Also, dquot_alloc_block() will always dirty the inode when blocks * are allocated to the file. * * If the inode is marked synchronous, we don't honour that here - doing * so would cause a commit on atime updates, which we don't bother doing. * We handle synchronous inodes at the highest possible level. * * If only the I_DIRTY_TIME flag is set, we can skip everything. If * I_DIRTY_TIME and I_DIRTY_SYNC is set, the only inode fields we need * to copy into the on-disk inode structure are the timestamp files. */
void ext4_dirty_inode(struct inode *inode, int flags) { handle_t *handle; if (flags == I_DIRTY_TIME) return; handle = ext4_journal_start(inode, EXT4_HT_INODE, 2); if (IS_ERR(handle)) goto out; ext4_mark_inode_dirty(handle, inode); ext4_journal_stop(handle); out: return; }

Contributors

PersonTokensPropCommitsCommitProp
dave kleikampdave kleikamp4473.33%120.00%
theodore tsotheodore tso915.00%240.00%
mingming caomingming cao46.67%120.00%
christoph hellwigchristoph hellwig35.00%120.00%
Total60100.00%5100.00%

#if 0 /* * Bind an inode's backing buffer_head into this transaction, to prevent * it from being flushed to disk early. Unlike * ext4_reserve_inode_write, this leaves behind no bh reference and * returns no iloc structure, so the caller needs to repeat the iloc * lookup to mark the inode dirty later. */ static int ext4_pin_inode(handle_t *handle, struct inode *inode) { struct ext4_iloc iloc; int err = 0; if (handle) { err = ext4_get_inode_loc(inode, &iloc); if (!err) { BUFFER_TRACE(iloc.bh, "get_write_access"); err = jbd2_journal_get_write_access(handle, iloc.bh); if (!err) err = ext4_handle_dirty_metadata(handle, NULL, iloc.bh); brelse(iloc.bh); } } ext4_std_error(inode->i_sb, err); return err; } #endif
int ext4_change_inode_journal_flag(struct inode *inode, int val) { journal_t *journal; handle_t *handle; int err; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); /* * We have to be very careful here: changing a data block's * journaling status dynamically is dangerous. If we write a * data block to the journal, change the status and then delete * that block, we risk forgetting to revoke the old log record * from the journal and so a subsequent replay can corrupt data. * So, first we make sure that the journal is empty and that * nobody is changing anything. */ journal = EXT4_JOURNAL(inode); if (!journal) return 0; if (is_journal_aborted(journal)) return -EROFS; /* Wait for all existing dio workers */ ext4_inode_block_unlocked_dio(inode); inode_dio_wait(inode); /* * Before flushing the journal and switching inode's aops, we have * to flush all dirty data the inode has. There can be outstanding * delayed allocations, there can be unwritten extents created by * fallocate or buffered writes in dioread_nolock mode covered by * dirty data which can be converted only after flushing the dirty * data (and journalled aops don't know how to handle these cases). */ if (val) { down_write(&EXT4_I(inode)->i_mmap_sem); err = filemap_write_and_wait(inode->i_mapping); if (err < 0) { up_write(&EXT4_I(inode)->i_mmap_sem); ext4_inode_resume_unlocked_dio(inode); return err; } } percpu_down_write(&sbi->s_journal_flag_rwsem); jbd2_journal_lock_updates(journal); /* * OK, there are no updates running now, and all cached data is * synced to disk. We are now in a completely consistent state * which doesn't have anything in the journal, and we know that * no filesystem updates are running, so it is safe to modify * the inode's in-core data-journaling state flag now. */ if (val) ext4_set_inode_flag(inode, EXT4_INODE_JOURNAL_DATA); else { err = jbd2_journal_flush(journal); if (err < 0) { jbd2_journal_unlock_updates(journal); percpu_up_write(&sbi->s_journal_flag_rwsem); ext4_inode_resume_unlocked_dio(inode); return err; } ext4_clear_inode_flag(inode, EXT4_INODE_JOURNAL_DATA); } ext4_set_aops(inode); /* * Update inode->i_flags after EXT4_INODE_JOURNAL_DATA was updated. * E.g. S_DAX may get cleared / set. */ ext4_set_inode_flags(inode); jbd2_journal_unlock_updates(journal); percpu_up_write(&sbi->s_journal_flag_rwsem); if (val) up_write(&EXT4_I(inode)->i_mmap_sem); ext4_inode_resume_unlocked_dio(inode); /* Finally we can mark the inode as dirty. */ handle = ext4_journal_start(inode, EXT4_HT_INODE, 1); if (IS_ERR(handle)) return PTR_ERR(handle); err = ext4_mark_inode_dirty(handle, inode); ext4_handle_sync(handle); ext4_journal_stop(handle); ext4_std_error(inode->i_sb, err); return err; }

Contributors

PersonTokensPropCommitsCommitProp
dave kleikampdave kleikamp11739.13%17.69%
daeho jeongdaeho jeong8929.77%215.38%
jan karajan kara299.70%215.38%
yongqiang yangyongqiang yang237.69%215.38%
dmitriy monakhovdmitriy monakhov196.35%215.38%
frank mayharfrank mayhar113.68%17.69%
mingming caomingming cao93.01%215.38%
theodore tsotheodore tso20.67%17.69%
Total299100.00%13100.00%


static int ext4_bh_unmapped(handle_t *handle, struct buffer_head *bh) { return !buffer_mapped(bh); }

Contributors

PersonTokensPropCommitsCommitProp
aneesh kumaraneesh kumar22100.00%1100.00%
Total22100.00%1100.00%


int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) { struct page *page = vmf->page; loff_t size; unsigned long len; int ret; struct file *file = vma->vm_file; struct inode *inode = file_inode(file); struct address_space *mapping = inode->i_mapping; handle_t *handle; get_block_t *get_block; int retries = 0; sb_start_pagefault(inode->i_sb); file_update_time(vma->vm_file); down_read(&EXT4_I(inode)->i_mmap_sem); /* Delalloc case is easy... */ if (test_opt(inode->i_sb, DELALLOC) && !ext4_should_journal_data(inode) && !ext4_nonda_switch(inode->i_sb)) { do { ret = block_page_mkwrite(vma, vmf, ext4_da_get_block_prep); } while (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)); goto out_ret; } lock_page(page); size = i_size_read(inode); /* Page got truncated from under us? */ if (page->mapping != mapping || page_offset(page) > size) { unlock_page(page); ret = VM_FAULT_NOPAGE; goto out; } if (page->index == size >> PAGE_SHIFT) len = size & ~PAGE_MASK; else len = PAGE_SIZE; /* * Return if we have all the buffers mapped. This avoids the need to do * journal_start/journal_stop which can block and take a long time */ if (page_has_buffers(page)) { if (!ext4_walk_page_buffers(NULL, page_buffers(page), 0, len, NULL, ext4_bh_unmapped)) { /* Wait so that we don't change page under IO */ wait_for_stable_page(page); ret = VM_FAULT_LOCKED; goto out; } } unlock_page(page); /* OK, we need to fill the hole... */ if (ext4_should_dioread_nolock(inode)) get_block = ext4_get_block_unwritten; else get_block = ext4_get_block; retry_alloc: handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, ext4_writepage_trans_blocks(inode)); if (IS_ERR(handle)) { ret = VM_FAULT_SIGBUS; goto out; } ret = block_page_mkwrite(vma, vmf, get_block); if (!ret && ext4_should_journal_data(inode)) { if (ext4_walk_page_buffers(handle, page_buffers(page), 0, PAGE_SIZE, NULL, do_journal_get_write_access)) { unlock_page(page); ret = VM_FAULT_SIGBUS; ext4_journal_stop(handle); goto out; } ext4_set_inode_state(inode, EXT4_STATE_JDATA); } ext4_journal_stop(handle); if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) goto retry_alloc; out_ret: ret = block_page_mkwrite_return(ret); out: up_read(&EXT4_I(inode)->i_mmap_sem); sb_end_pagefault(inode->i_sb); return ret; }

Contributors

PersonTokensPropCommitsCommitProp
jan karajan kara22449.45%423.53%
aneesh kumaraneesh kumar16235.76%317.65%
darrick j. wongdarrick j. wong255.52%211.76%
nick pigginnick piggin173.75%15.88%
theodore tsotheodore tso91.99%211.76%
yongqiang yangyongqiang yang51.10%15.88%
kirill a. shutemovkirill a. shutemov40.88%15.88%
al viroal viro30.66%15.88%
ross zwislerross zwisler20.44%15.88%
tao matao ma20.44%15.88%
Total453100.00%17100.00%


int ext4_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) { struct inode *inode = file_inode(vma->vm_file); int err; down_read(&EXT4_I(inode)->i_mmap_sem); err = filemap_fault(vma, vmf); up_read(&EXT4_I(inode)->i_mmap_sem); return err; }

Contributors

PersonTokensPropCommitsCommitProp
jan karajan kara64100.00%1100.00%
Total64100.00%1100.00%

/* * Find the first extent at or after @lblk in an inode that is not a hole. * Search for @map_len blocks at most. The extent is returned in @result. * * The function returns 1 if we found an extent. The function returns 0 in * case there is no extent at or after @lblk and in that case also sets * @result->es_len to 0. In case of error, the error code is returned. */
int ext4_get_next_extent(struct inode *inode, ext4_lblk_t lblk, unsigned int map_len, struct extent_status *result) { struct ext4_map_blocks map; struct extent_status es = {}; int ret; map.m_lblk = lblk; map.m_len = map_len; /* * For non-extent based files this loop may iterate several times since * we do not determine full hole size. */ while (map.m_len > 0) { ret = ext4_map_blocks(NULL, inode, &map, 0); if (ret < 0) return ret; /* There's extent covering m_lblk? Just return it. */ if (ret > 0) { int status; ext4_es_store_pblock(result, map.m_pblk); result->es_lblk = map.m_lblk; result->es_len = map.m_len; if (map.m_flags & EXT4_MAP_UNWRITTEN) status = EXTENT_STATUS_UNWRITTEN; else status = EXTENT_STATUS_WRITTEN; ext4_es_store_status(result, status); return 1; } ext4_es_find_delayed_extent_range(inode, map.m_lblk, map.m_lblk + map.m_len - 1, &es); /* Is delalloc data before next block in extent tree? */ if (es.es_len && es.es_lblk < map.m_lblk + map.m_len) { ext4_lblk_t offset = 0; if (es.es_lblk < lblk) offset = lblk - es.es_lblk; result->es_lblk = es.es_lblk + offset; ext4_es_store_pblock(result, ext4_es_pblock(&es) + offset); result->es_len = es.es_len - offset; ext4_es_store_status(result, ext4_es_status(&es)); return 1; } /* There's a hole at m_lblk, advance us after it */ map.m_lblk += map.m_len; map_len -= map.m_len; map.m_len = map_len; cond_resched(); } result->es_len = 0; return 0; }

Contributors

PersonTokensPropCommitsCommitProp
jan karajan kara27494.81%450.00%
darrick j. wongdarrick j. wong93.11%112.50%
nick pigginnick piggin41.38%112.50%
yongqiang yangyongqiang yang10.35%112.50%
aneesh kumaraneesh kumar10.35%112.50%
Total289100.00%8100.00%


Overall Contributors

PersonTokensPropCommitsCommitProp
jan karajan kara658127.05%7314.90%
dave kleikampdave kleikamp335313.78%10.20%
theodore tsotheodore tso326213.41%12124.69%
amir goldsteinamir goldstein279011.47%51.02%
aneesh kumaraneesh kumar11244.62%418.37%
lukas czernerlukas czerner8363.44%173.47%
michael halcrowmichael halcrow6182.54%20.41%
zheng liuzheng liu5942.44%153.06%
darrick j. wongdarrick j. wong5922.43%71.43%
dmitriy monakhovdmitriy monakhov5252.16%224.49%
mingming caomingming cao4761.96%142.86%
tao matao ma4661.92%112.24%
kalpak shahkalpak shah2961.22%20.41%
daeho jeongdaeho jeong2701.11%51.02%
alex tomasalex tomas2270.93%20.41%
ross zwislerross zwisler1800.74%61.22%
li xili xi1580.65%20.41%
aditya kaliaditya kali1500.62%30.61%
eric sandeeneric sandeen1410.58%132.65%
frank mayharfrank mayhar1400.58%40.82%
christoph hellwigchristoph hellwig1170.48%163.27%
jean noel cordennerjean noel cordenner1010.42%10.20%
jiaying zhangjiaying zhang970.40%40.82%
david howellsdavid howells930.38%20.41%
al viroal viro860.35%91.84%
matthew wilcoxmatthew wilcox820.34%30.61%
thiemo nagelthiemo nagel820.34%20.41%
kirill a. shutemovkirill a. shutemov590.24%20.41%
josef bacikjosef bacik580.24%10.20%
eric w. biedermaneric w. biederman500.21%10.20%
ming leiming lei440.18%20.41%
wang xiaoguangwang xiaoguang440.18%10.20%
badari pulavartybadari pulavarty430.18%10.20%
nick pigginnick piggin380.16%30.61%
eric biggerseric biggers380.16%20.41%
yongqiang yangyongqiang yang330.14%51.02%
eryu guaneryu guan320.13%20.41%
duane griffinduane griffin300.12%20.41%
liang xieliang xie290.12%10.20%
curt wohlgemuthcurt wohlgemuth280.12%61.22%
david gstirdavid gstir280.12%30.61%
anatol pomozovanatol pomozov270.11%30.61%
eric whitneyeric whitney250.10%30.61%
andreas dilgerandreas dilger250.10%10.20%
tilmann bubecktilmann bubeck210.09%10.20%
allison hendersonallison henderson190.08%30.61%
hidehiro kawaihidehiro kawai190.08%10.20%
linus torvaldslinus torvalds160.07%10.20%
li shaohuali shaohua160.07%10.20%
namjae jeonnamjae jeon150.06%20.41%
kazuya miokazuya mio150.06%10.20%
valerie clementvalerie clement130.05%10.20%
omar sandovalomar sandoval120.05%10.20%
wangguangwangguang120.05%10.20%
michael christiemichael christie100.04%20.41%
wang shilongwang shilong90.04%20.41%
mel gormanmel gorman70.03%10.20%
akinobu mitaakinobu mita60.02%10.20%
namhyung kimnamhyung kim60.02%10.20%
vegard nossumvegard nossum60.02%10.20%
jaegeuk kimjaegeuk kim40.02%10.20%
jon ernstjon ernst40.02%10.20%
miklos szeredimiklos szeredi40.02%10.20%
andrew mortonandrew morton40.02%20.41%
kaho ngkaho ng30.01%10.20%
tejun heotejun heo30.01%10.20%
alexandre ratchovalexandre ratchov30.01%10.20%
deepa dinamanideepa dinamani30.01%10.20%
michal hockomichal hocko30.01%10.20%
alexander beregalovalexander beregalov20.01%10.20%
andrea arcangeliandrea arcangeli20.01%10.20%
ashish sangwanashish sangwan20.01%10.20%
julia lawalljulia lawall20.01%10.20%
peter huewepeter huewe20.01%10.20%
seunghun leeseunghun lee20.01%10.20%
johannes weinerjohannes weiner20.01%10.20%
laurent vivierlaurent vivier20.01%10.20%
lucas de marchilucas de marchi10.00%10.20%
stephen hemmingerstephen hemminger10.00%10.20%
jens axboejens axboe10.00%10.20%
joe perchesjoe perches10.00%10.20%
artem bityutskiyartem bityutskiy10.00%10.20%
li zefanli zefan10.00%10.20%
justin mattockjustin mattock10.00%10.20%
jeff moyerjeff moyer10.00%10.20%
miao xiemiao xie10.00%10.20%
Total24326100.00%490100.00%
Directory: fs/ext4
Information contained on this website is for historical information purposes only and does not indicate or represent copyright ownership.