diff options
Diffstat (limited to 'fs/hugetlbfs/inode.c')
| -rw-r--r-- | fs/hugetlbfs/inode.c | 122 |
1 files changed, 81 insertions, 41 deletions
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index d44f5456eb9b..59073e9f01a4 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -46,13 +46,13 @@ static const struct inode_operations hugetlbfs_dir_inode_operations; static const struct inode_operations hugetlbfs_inode_operations; struct hugetlbfs_config { - kuid_t uid; - kgid_t gid; - umode_t mode; - long max_hpages; - long nr_inodes; - struct hstate *hstate; - long min_hpages; + struct hstate *hstate; + long max_hpages; + long nr_inodes; + long min_hpages; + kuid_t uid; + kgid_t gid; + umode_t mode; }; struct hugetlbfs_inode_info { @@ -334,7 +334,7 @@ static void remove_huge_page(struct page *page) } static void -hugetlb_vmdelete_list(struct rb_root *root, pgoff_t start, pgoff_t end) +hugetlb_vmdelete_list(struct rb_root_cached *root, pgoff_t start, pgoff_t end) { struct vm_area_struct *vma; @@ -401,9 +401,8 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, const pgoff_t end = lend >> huge_page_shift(h); struct vm_area_struct pseudo_vma; struct pagevec pvec; - pgoff_t next; + pgoff_t next, index; int i, freed = 0; - long lookup_nr = PAGEVEC_SIZE; bool truncate_op = (lend == LLONG_MAX); memset(&pseudo_vma, 0, sizeof(struct vm_area_struct)); @@ -412,33 +411,19 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, next = start; while (next < end) { /* - * Don't grab more pages than the number left in the range. - */ - if (end - next < lookup_nr) - lookup_nr = end - next; - - /* * When no more pages are found, we are done. */ - if (!pagevec_lookup(&pvec, mapping, next, lookup_nr)) + if (!pagevec_lookup_range(&pvec, mapping, &next, end - 1)) break; for (i = 0; i < pagevec_count(&pvec); ++i) { struct page *page = pvec.pages[i]; u32 hash; - /* - * The page (index) could be beyond end. This is - * only possible in the punch hole case as end is - * max page offset in the truncate case. - */ - next = page->index; - if (next >= end) - break; - + index = page->index; hash = hugetlb_fault_mutex_hash(h, current->mm, &pseudo_vma, - mapping, next, 0); + mapping, index, 0); mutex_lock(&hugetlb_fault_mutex_table[hash]); /* @@ -455,8 +440,8 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, i_mmap_lock_write(mapping); hugetlb_vmdelete_list(&mapping->i_mmap, - next * pages_per_huge_page(h), - (next + 1) * pages_per_huge_page(h)); + index * pages_per_huge_page(h), + (index + 1) * pages_per_huge_page(h)); i_mmap_unlock_write(mapping); } @@ -475,14 +460,13 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, freed++; if (!truncate_op) { if (unlikely(hugetlb_unreserve_pages(inode, - next, next + 1, 1))) + index, index + 1, 1))) hugetlb_fix_reserve_counts(inode); } unlock_page(page); mutex_unlock(&hugetlb_fault_mutex_table[hash]); } - ++next; huge_pagevec_release(&pvec); cond_resched(); } @@ -514,7 +498,7 @@ static int hugetlb_vmtruncate(struct inode *inode, loff_t offset) i_size_write(inode, offset); i_mmap_lock_write(mapping); - if (!RB_EMPTY_ROOT(&mapping->i_mmap)) + if (!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root)) hugetlb_vmdelete_list(&mapping->i_mmap, pgoff, 0); i_mmap_unlock_write(mapping); remove_inode_hugepages(inode, offset, LLONG_MAX); @@ -539,7 +523,7 @@ static long hugetlbfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) inode_lock(inode); i_mmap_lock_write(mapping); - if (!RB_EMPTY_ROOT(&mapping->i_mmap)) + if (!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root)) hugetlb_vmdelete_list(&mapping->i_mmap, hole_start >> PAGE_SHIFT, hole_end >> PAGE_SHIFT); @@ -846,11 +830,64 @@ static int hugetlbfs_migrate_page(struct address_space *mapping, rc = migrate_huge_page_move_mapping(mapping, newpage, page); if (rc != MIGRATEPAGE_SUCCESS) return rc; - migrate_page_copy(newpage, page); + if (mode != MIGRATE_SYNC_NO_COPY) + migrate_page_copy(newpage, page); + else + migrate_page_states(newpage, page); return MIGRATEPAGE_SUCCESS; } +static int hugetlbfs_error_remove_page(struct address_space *mapping, + struct page *page) +{ + struct inode *inode = mapping->host; + + remove_huge_page(page); + hugetlb_fix_reserve_counts(inode); + return 0; +} + +/* + * Display the mount options in /proc/mounts. + */ +static int hugetlbfs_show_options(struct seq_file *m, struct dentry *root) +{ + struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(root->d_sb); + struct hugepage_subpool *spool = sbinfo->spool; + unsigned long hpage_size = huge_page_size(sbinfo->hstate); + unsigned hpage_shift = huge_page_shift(sbinfo->hstate); + char mod; + + if (!uid_eq(sbinfo->uid, GLOBAL_ROOT_UID)) + seq_printf(m, ",uid=%u", + from_kuid_munged(&init_user_ns, sbinfo->uid)); + if (!gid_eq(sbinfo->gid, GLOBAL_ROOT_GID)) + seq_printf(m, ",gid=%u", + from_kgid_munged(&init_user_ns, sbinfo->gid)); + if (sbinfo->mode != 0755) + seq_printf(m, ",mode=%o", sbinfo->mode); + if (sbinfo->max_inodes != -1) + seq_printf(m, ",nr_inodes=%lu", sbinfo->max_inodes); + + hpage_size /= 1024; + mod = 'K'; + if (hpage_size >= 1024) { + hpage_size /= 1024; + mod = 'M'; + } + seq_printf(m, ",pagesize=%lu%c", hpage_size, mod); + if (spool) { + if (spool->max_hpages != -1) + seq_printf(m, ",size=%llu", + (unsigned long long)spool->max_hpages << hpage_shift); + if (spool->min_hpages != -1) + seq_printf(m, ",min_size=%llu", + (unsigned long long)spool->min_hpages << hpage_shift); + } + return 0; +} + static int hugetlbfs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(dentry->d_sb); @@ -966,6 +1003,7 @@ static const struct address_space_operations hugetlbfs_aops = { .write_end = hugetlbfs_write_end, .set_page_dirty = hugetlbfs_set_page_dirty, .migratepage = hugetlbfs_migrate_page, + .error_remove_page = hugetlbfs_error_remove_page, }; @@ -1008,19 +1046,19 @@ static const struct super_operations hugetlbfs_ops = { .evict_inode = hugetlbfs_evict_inode, .statfs = hugetlbfs_statfs, .put_super = hugetlbfs_put_super, - .show_options = generic_show_options, + .show_options = hugetlbfs_show_options, }; -enum { NO_SIZE, SIZE_STD, SIZE_PERCENT }; +enum hugetlbfs_size_type { NO_SIZE, SIZE_STD, SIZE_PERCENT }; /* * Convert size option passed from command line to number of huge pages * in the pool specified by hstate. Size option could be in bytes * (val_type == SIZE_STD) or percentage of the pool (val_type == SIZE_PERCENT). */ -static long long +static long hugetlbfs_size_to_hpages(struct hstate *h, unsigned long long size_opt, - int val_type) + enum hugetlbfs_size_type val_type) { if (val_type == NO_SIZE) return -1; @@ -1042,7 +1080,7 @@ hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig) substring_t args[MAX_OPT_ARGS]; int option; unsigned long long max_size_opt = 0, min_size_opt = 0; - int max_val_type = NO_SIZE, min_val_type = NO_SIZE; + enum hugetlbfs_size_type max_val_type = NO_SIZE, min_val_type = NO_SIZE; if (!options) return 0; @@ -1156,8 +1194,6 @@ hugetlbfs_fill_super(struct super_block *sb, void *data, int silent) struct hugetlbfs_config config; struct hugetlbfs_sb_info *sbinfo; - save_mount_options(sb, data); - config.max_hpages = -1; /* No limit on size by default */ config.nr_inodes = -1; /* No limit on number of inodes by default */ config.uid = current_fsuid(); @@ -1178,6 +1214,10 @@ hugetlbfs_fill_super(struct super_block *sb, void *data, int silent) sbinfo->max_inodes = config.nr_inodes; sbinfo->free_inodes = config.nr_inodes; sbinfo->spool = NULL; + sbinfo->uid = config.uid; + sbinfo->gid = config.gid; + sbinfo->mode = config.mode; + /* * Allocate and initialize subpool if maximum or minimum size is * specified. Any needed reservations (for minimim size) are taken |