diff options
Diffstat (limited to 'fs')
299 files changed, 7616 insertions, 4240 deletions
diff --git a/fs/9p/cache.h b/fs/9p/cache.h index 2f96754..247e47e 100644 --- a/fs/9p/cache.h +++ b/fs/9p/cache.h @@ -21,6 +21,7 @@ */ #ifndef _9P_CACHE_H +#define _9P_CACHE_H #ifdef CONFIG_9P_FSCACHE #include <linux/fscache.h> #include <linux/spinlock.h> diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index 3abc447..7bf835f 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -161,7 +161,7 @@ static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl) if ((fl->fl_flags & FL_POSIX) != FL_POSIX) BUG(); - res = posix_lock_file_wait(filp, fl); + res = locks_lock_file_wait(filp, fl); if (res < 0) goto out; @@ -231,7 +231,8 @@ out_unlock: if (res < 0 && fl->fl_type != F_UNLCK) { fl_type = fl->fl_type; fl->fl_type = F_UNLCK; - res = posix_lock_file_wait(filp, fl); + /* Even if this fails we want to return the remote error */ + locks_lock_file_wait(filp, fl); fl->fl_type = fl_type; } out: diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index b1dc518..699941e 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -1368,9 +1368,6 @@ v9fs_vfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rde dir->i_ino, dentry, mode, MAJOR(rdev), MINOR(rdev)); - if (!new_valid_dev(rdev)) - return -EINVAL; - /* build extension */ if (S_ISBLK(mode)) sprintf(name, "b %u %u", MAJOR(rdev), MINOR(rdev)); diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index e8aa57d..cb899af 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -829,9 +829,6 @@ v9fs_vfs_mknod_dotl(struct inode *dir, struct dentry *dentry, umode_t omode, dir->i_ino, dentry, omode, MAJOR(rdev), MINOR(rdev)); - if (!new_valid_dev(rdev)) - return -EINVAL; - v9ses = v9fs_inode2v9ses(dir); dir_dentry = dentry->d_parent; dfid = v9fs_fid_lookup(dir_dentry); diff --git a/fs/Makefile b/fs/Makefile index f79cf40..79f5225 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -63,10 +63,11 @@ obj-$(CONFIG_DLM) += dlm/ # Do not add any filesystems before this line obj-$(CONFIG_FSCACHE) += fscache/ obj-$(CONFIG_REISERFS_FS) += reiserfs/ -obj-$(CONFIG_EXT2_FS) += ext2/ -# We place ext4 after ext2 so plain ext2 root fs's are mounted using ext2 -# unless explicitly requested by rootfstype obj-$(CONFIG_EXT4_FS) += ext4/ +# We place ext4 before ext2 so that clean ext3 root fs's do NOT mount using the +# ext2 driver, which doesn't know about journalling! Explicitly request ext2 +# by giving the rootfstype= parameter. +obj-$(CONFIG_EXT2_FS) += ext2/ obj-$(CONFIG_JBD2) += jbd2/ obj-$(CONFIG_CRAMFS) += cramfs/ obj-$(CONFIG_SQUASHFS) += squashfs/ diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 6b65996..3a93755 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -35,6 +35,7 @@ #include <linux/utsname.h> #include <linux/coredump.h> #include <linux/sched.h> +#include <linux/dax.h> #include <asm/uaccess.h> #include <asm/param.h> #include <asm/page.h> @@ -487,7 +488,7 @@ static inline int arch_elf_pt_proc(struct elfhdr *ehdr, } /** - * arch_check_elf() - check a PT_LOPROC..PT_HIPROC ELF program header + * arch_check_elf() - check an ELF executable * @ehdr: The main ELF header * @has_interp: True if the ELF has an interpreter, else false. * @state: Architecture-specific state preserved throughout the process @@ -759,16 +760,16 @@ static int load_elf_binary(struct linux_binprm *bprm) */ would_dump(bprm, interpreter); - retval = kernel_read(interpreter, 0, bprm->buf, - BINPRM_BUF_SIZE); - if (retval != BINPRM_BUF_SIZE) { + /* Get the exec headers */ + retval = kernel_read(interpreter, 0, + (void *)&loc->interp_elf_ex, + sizeof(loc->interp_elf_ex)); + if (retval != sizeof(loc->interp_elf_ex)) { if (retval >= 0) retval = -EIO; goto out_free_dentry; } - /* Get the exec headers */ - loc->interp_elf_ex = *((struct elfhdr *)bprm->buf); break; } elf_ppnt++; @@ -1236,6 +1237,15 @@ static unsigned long vma_dump_size(struct vm_area_struct *vma, if (vma->vm_flags & VM_DONTDUMP) return 0; + /* support for DAX */ + if (vma_is_dax(vma)) { + if ((vma->vm_flags & VM_SHARED) && FILTER(DAX_SHARED)) + goto whole; + if (!(vma->vm_flags & VM_SHARED) && FILTER(DAX_PRIVATE)) + goto whole; + return 0; + } + /* Hugetlb memory check */ if (vma->vm_flags & VM_HUGETLB) { if ((vma->vm_flags & VM_SHARED) && FILTER(HUGETLB_SHARED)) diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index d3634bf..b1adb92 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -35,6 +35,7 @@ #include <linux/elf-fdpic.h> #include <linux/elfcore.h> #include <linux/coredump.h> +#include <linux/dax.h> #include <asm/uaccess.h> #include <asm/param.h> @@ -103,19 +104,36 @@ static void __exit exit_elf_fdpic_binfmt(void) core_initcall(init_elf_fdpic_binfmt); module_exit(exit_elf_fdpic_binfmt); -static int is_elf_fdpic(struct elfhdr *hdr, struct file *file) +static int is_elf(struct elfhdr *hdr, struct file *file) { if (memcmp(hdr->e_ident, ELFMAG, SELFMAG) != 0) return 0; if (hdr->e_type != ET_EXEC && hdr->e_type != ET_DYN) return 0; - if (!elf_check_arch(hdr) || !elf_check_fdpic(hdr)) + if (!elf_check_arch(hdr)) return 0; if (!file->f_op->mmap) return 0; return 1; } +#ifndef elf_check_fdpic +#define elf_check_fdpic(x) 0 +#endif + +#ifndef elf_check_const_displacement +#define elf_check_const_displacement(x) 0 +#endif + +static int is_constdisp(struct elfhdr *hdr) +{ + if (!elf_check_fdpic(hdr)) + return 1; + if (elf_check_const_displacement(hdr)) + return 1; + return 0; +} + /*****************************************************************************/ /* * read the program headers table into memory @@ -191,8 +209,18 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm) /* check that this is a binary we know how to deal with */ retval = -ENOEXEC; - if (!is_elf_fdpic(&exec_params.hdr, bprm->file)) + if (!is_elf(&exec_params.hdr, bprm->file)) + goto error; + if (!elf_check_fdpic(&exec_params.hdr)) { +#ifdef CONFIG_MMU + /* binfmt_elf handles non-fdpic elf except on nommu */ goto error; +#else + /* nommu can only load ET_DYN (PIE) ELF */ + if (exec_params.hdr.e_type != ET_DYN) + goto error; +#endif + } /* read the program header table */ retval = elf_fdpic_fetch_phdrs(&exec_params, bprm->file); @@ -269,13 +297,13 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm) } - if (elf_check_const_displacement(&exec_params.hdr)) + if (is_constdisp(&exec_params.hdr)) exec_params.flags |= ELF_FDPIC_FLAG_CONSTDISP; /* perform insanity checks on the interpreter */ if (interpreter_name) { retval = -ELIBBAD; - if (!is_elf_fdpic(&interp_params.hdr, interpreter)) + if (!is_elf(&interp_params.hdr, interpreter)) goto error; interp_params.flags = ELF_FDPIC_FLAG_PRESENT; @@ -306,9 +334,9 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm) retval = -ENOEXEC; if (stack_size == 0) - goto error; + stack_size = 131072UL; /* same as exec.c's default commit */ - if (elf_check_const_displacement(&interp_params.hdr)) + if (is_constdisp(&interp_params.hdr)) interp_params.flags |= ELF_FDPIC_FLAG_CONSTDISP; /* flush all traces of the currently running executable */ @@ -319,7 +347,10 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm) /* there's now no turning back... the old userspace image is dead, * defunct, deceased, etc. */ - set_personality(PER_LINUX_FDPIC); + if (elf_check_fdpic(&exec_params.hdr)) + set_personality(PER_LINUX_FDPIC); + else + set_personality(PER_LINUX); if (elf_read_implies_exec(&exec_params.hdr, executable_stack)) current->personality |= READ_IMPLIES_EXEC; @@ -374,10 +405,7 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm) PAGE_ALIGN(current->mm->start_brk); #else - /* create a stack and brk area big enough for everyone - * - the brk heap starts at the bottom and works up - * - the stack starts at the top and works down - */ + /* create a stack area and zero-size brk area */ stack_size = (stack_size + PAGE_SIZE - 1) & PAGE_MASK; if (stack_size < PAGE_SIZE * 2) stack_size = PAGE_SIZE * 2; @@ -400,8 +428,6 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm) current->mm->brk = current->mm->start_brk; current->mm->context.end_brk = current->mm->start_brk; - current->mm->context.end_brk += - (stack_size > PAGE_SIZE) ? (stack_size - PAGE_SIZE) : 0; current->mm->start_stack = current->mm->start_brk + stack_size; #endif @@ -1206,6 +1232,20 @@ static int maydump(struct vm_area_struct *vma, unsigned long mm_flags) return 0; } + /* support for DAX */ + if (vma_is_dax(vma)) { + if (vma->vm_flags & VM_SHARED) { + dump_ok = test_bit(MMF_DUMP_DAX_SHARED, &mm_flags); + kdcore("%08lx: %08lx: %s (DAX shared)", vma->vm_start, + vma->vm_flags, dump_ok ? "yes" : "no"); + } else { + dump_ok = test_bit(MMF_DUMP_DAX_PRIVATE, &mm_flags); + kdcore("%08lx: %08lx: %s (DAX private)", vma->vm_start, + vma->vm_flags, dump_ok ? "yes" : "no"); + } + return dump_ok; + } + /* By default, dump shared memory if mapped from an anonymous file. */ if (vma->vm_flags & VM_SHARED) { if (file_inode(vma->vm_file)->i_nlink == 0) { diff --git a/fs/block_dev.c b/fs/block_dev.c index 073bb57..0a793c7 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1075,7 +1075,7 @@ int revalidate_disk(struct gendisk *disk) if (disk->fops->revalidate_disk) ret = disk->fops->revalidate_disk(disk); - + blk_integrity_revalidate(disk); bdev = bdget_disk(disk, 0); if (!bdev) return ret; diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index ecbc63d..6dcdb2e 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -362,6 +362,12 @@ static int __resolve_indirect_ref(struct btrfs_fs_info *fs_info, goto out; } + if (btrfs_test_is_dummy_root(root)) { + srcu_read_unlock(&fs_info->subvol_srcu, index); + ret = -ENOENT; + goto out; + } + if (path->search_commit_root) root_level = btrfs_header_level(root->commit_root); else if (time_seq == (u64)-1) @@ -1828,7 +1834,6 @@ static int iterate_inode_extrefs(u64 inum, struct btrfs_root *fs_root, int found = 0; struct extent_buffer *eb; struct btrfs_inode_extref *extref; - struct extent_buffer *leaf; u32 item_size; u32 cur_offset; unsigned long ptr; @@ -1856,9 +1861,8 @@ static int iterate_inode_extrefs(u64 inum, struct btrfs_root *fs_root, btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK); btrfs_release_path(path); - leaf = path->nodes[0]; - item_size = btrfs_item_size_nr(leaf, slot); - ptr = btrfs_item_ptr_offset(leaf, slot); + item_size = btrfs_item_size_nr(eb, slot); + ptr = btrfs_item_ptr_offset(eb, slot); cur_offset = 0; while (cur_offset < item_size) { @@ -1872,7 +1876,7 @@ static int iterate_inode_extrefs(u64 inum, struct btrfs_root *fs_root, if (ret) break; - cur_offset += btrfs_inode_extref_name_len(leaf, extref); + cur_offset += btrfs_inode_extref_name_len(eb, extref); cur_offset += sizeof(*extref); } btrfs_tree_read_unlock_blocking(eb); diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h index 81220b2..0ef5cc1 100644 --- a/fs/btrfs/btrfs_inode.h +++ b/fs/btrfs/btrfs_inode.h @@ -44,8 +44,6 @@ #define BTRFS_INODE_IN_DELALLOC_LIST 9 #define BTRFS_INODE_READDIO_NEED_LOCK 10 #define BTRFS_INODE_HAS_PROPS 11 -/* DIO is ready to submit */ -#define BTRFS_INODE_DIO_READY 12 /* * The following 3 bits are meant only for the btree inode. * When any of them is set, it means an error happened while writing an diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c index 541fbfa..0340c57 100644 --- a/fs/btrfs/check-integrity.c +++ b/fs/btrfs/check-integrity.c @@ -667,7 +667,7 @@ static int btrfsic_process_superblock(struct btrfsic_state *state, selected_super = kzalloc(sizeof(*selected_super), GFP_NOFS); if (NULL == selected_super) { printk(KERN_INFO "btrfsic: error, kmalloc failed!\n"); - return -1; + return -ENOMEM; } list_for_each_entry(device, dev_head, dev_list) { @@ -845,8 +845,8 @@ static int btrfsic_process_superblock_dev_mirror( superblock_tmp->never_written = 0; superblock_tmp->mirror_num = 1 + superblock_mirror_num; if (state->print_mask & BTRFSIC_PRINT_MASK_SUPERBLOCK_WRITE) - printk_in_rcu(KERN_INFO "New initial S-block (bdev %p, %s)" - " @%llu (%s/%llu/%d)\n", + btrfs_info_in_rcu(device->dev_root->fs_info, + "new initial S-block (bdev %p, %s) @%llu (%s/%llu/%d)", superblock_bdev, rcu_str_deref(device->name), dev_bytenr, dev_state->name, dev_bytenr, @@ -1660,7 +1660,7 @@ static int btrfsic_read_block(struct btrfsic_state *state, sizeof(*block_ctx->pagev)) * num_pages, GFP_NOFS); if (!block_ctx->mem_to_free) - return -1; + return -ENOMEM; block_ctx->datav = block_ctx->mem_to_free; block_ctx->pagev = (struct page **)(block_ctx->datav + num_pages); for (i = 0; i < num_pages; i++) { diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index 57ee8ca..c473c42 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -482,13 +482,12 @@ static noinline int add_ra_bio_pages(struct inode *inode, goto next; } - page = __page_cache_alloc(mapping_gfp_mask(mapping) & - ~__GFP_FS); + page = __page_cache_alloc(mapping_gfp_constraint(mapping, + ~__GFP_FS)); if (!page) break; - if (add_to_page_cache_lru(page, mapping, pg_index, - GFP_NOFS)) { + if (add_to_page_cache_lru(page, mapping, pg_index, GFP_NOFS)) { page_cache_release(page); goto next; } @@ -745,11 +744,13 @@ out: return ret; } -static struct list_head comp_idle_workspace[BTRFS_COMPRESS_TYPES]; -static spinlock_t comp_workspace_lock[BTRFS_COMPRESS_TYPES]; -static int comp_num_workspace[BTRFS_COMPRESS_TYPES]; -static atomic_t comp_alloc_workspace[BTRFS_COMPRESS_TYPES]; -static wait_queue_head_t comp_workspace_wait[BTRFS_COMPRESS_TYPES]; +static struct { + struct list_head idle_ws; + spinlock_t ws_lock; + int num_ws; + atomic_t alloc_ws; + wait_queue_head_t ws_wait; +} btrfs_comp_ws[BTRFS_COMPRESS_TYPES]; static const struct btrfs_compress_op * const btrfs_compress_op[] = { &btrfs_zlib_compress, @@ -761,10 +762,10 @@ void __init btrfs_init_compress(void) int i; for (i = 0; i < BTRFS_COMPRESS_TYPES; i++) { - INIT_LIST_HEAD(&comp_idle_workspace[i]); - spin_lock_init(&comp_workspace_lock[i]); - atomic_set(&comp_alloc_workspace[i], 0); - init_waitqueue_head(&comp_workspace_wait[i]); + INIT_LIST_HEAD(&btrfs_comp_ws[i].idle_ws); + spin_lock_init(&btrfs_comp_ws[i].ws_lock); + atomic_set(&btrfs_comp_ws[i].alloc_ws, 0); + init_waitqueue_head(&btrfs_comp_ws[i].ws_wait); } } @@ -778,38 +779,38 @@ static struct list_head *find_workspace(int type) int cpus = num_online_cpus(); int idx = type - 1; - struct list_head *idle_workspace = &comp_idle_workspace[idx]; - spinlock_t *workspace_lock = &comp_workspace_lock[idx]; - atomic_t *alloc_workspace = &comp_alloc_workspace[idx]; - wait_queue_head_t *workspace_wait = &comp_workspace_wait[idx]; - int *num_workspace = &comp_num_workspace[idx]; + struct list_head *idle_ws = &btrfs_comp_ws[idx].idle_ws; + spinlock_t *ws_lock = &btrfs_comp_ws[idx].ws_lock; + atomic_t *alloc_ws = &btrfs_comp_ws[idx].alloc_ws; + wait_queue_head_t *ws_wait = &btrfs_comp_ws[idx].ws_wait; + int *num_ws = &btrfs_comp_ws[idx].num_ws; again: - spin_lock(workspace_lock); - if (!list_empty(idle_workspace)) { - workspace = idle_workspace->next; + spin_lock(ws_lock); + if (!list_empty(idle_ws)) { + workspace = idle_ws->next; list_del(workspace); - (*num_workspace)--; - spin_unlock(workspace_lock); + (*num_ws)--; + spin_unlock(ws_lock); return workspace; } - if (atomic_read(alloc_workspace) > cpus) { + if (atomic_read(alloc_ws) > cpus) { DEFINE_WAIT(wait); - spin_unlock(workspace_lock); - prepare_to_wait(workspace_wait, &wait, TASK_UNINTERRUPTIBLE); - if (atomic_read(alloc_workspace) > cpus && !*num_workspace) + spin_unlock(ws_lock); + prepare_to_wait(ws_wait, &wait, TASK_UNINTERRUPTIBLE); + if (atomic_read(alloc_ws) > cpus && !*num_ws) schedule(); - finish_wait(workspace_wait, &wait); + finish_wait(ws_wait, &wait); goto again; } - atomic_inc(alloc_workspace); - spin_unlock(workspace_lock); + atomic_inc(alloc_ws); + spin_unlock(ws_lock); workspace = btrfs_compress_op[idx]->alloc_workspace(); if (IS_ERR(workspace)) { - atomic_dec(alloc_workspace); - wake_up(workspace_wait); + atomic_dec(alloc_ws); + wake_up(ws_wait); } return workspace; } @@ -821,27 +822,30 @@ again: static void free_workspace(int type, struct list_head *workspace) { int idx = type - 1; - struct list_head *idle_workspace = &comp_idle_workspace[idx]; - spinlock_t *workspace_lock = &comp_workspace_lock[idx]; - atomic_t *alloc_workspace = &comp_alloc_workspace[idx]; - wait_queue_head_t *workspace_wait = &comp_workspace_wait[idx]; - int *num_workspace = &comp_num_workspace[idx]; - - spin_lock(workspace_lock); - if (*num_workspace < num_online_cpus()) { - list_add(workspace, idle_workspace); - (*num_workspace)++; - spin_unlock(workspace_lock); + struct list_head *idle_ws = &btrfs_comp_ws[idx].idle_ws; + spinlock_t *ws_lock = &btrfs_comp_ws[idx].ws_lock; + atomic_t *alloc_ws = &btrfs_comp_ws[idx].alloc_ws; + wait_queue_head_t *ws_wait = &btrfs_comp_ws[idx].ws_wait; + int *num_ws = &btrfs_comp_ws[idx].num_ws; + + spin_lock(ws_lock); + if (*num_ws < num_online_cpus()) { + list_add(workspace, idle_ws); + (*num_ws)++; + spin_unlock(ws_lock); goto wake; } - spin_unlock(workspace_lock); + spin_unlock(ws_lock); btrfs_compress_op[idx]->free_workspace(workspace); - atomic_dec(alloc_workspace); + atomic_dec(alloc_ws); wake: + /* + * Make sure counter is updated before we wake up waiters. + */ smp_mb(); - if (waitqueue_active(workspace_wait)) - wake_up(workspace_wait); + if (waitqueue_active(ws_wait)) + wake_up(ws_wait); } /* @@ -853,11 +857,11 @@ static void free_workspaces(void) int i; for (i = 0; i < BTRFS_COMPRESS_TYPES; i++) { - while (!list_empty(&comp_idle_workspace[i])) { - workspace = comp_idle_workspace[i].next; + while (!list_empty(&btrfs_comp_ws[i].idle_ws)) { + workspace = btrfs_comp_ws[i].idle_ws.next; list_del(workspace); btrfs_compress_op[i]->free_workspace(workspace); - atomic_dec(&comp_alloc_workspace[i]); + atomic_dec(&btrfs_comp_ws[i].alloc_ws); } } } diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 5f745ea..5b8e235 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -1011,7 +1011,7 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans, return ret; if (refs == 0) { ret = -EROFS; - btrfs_std_error(root->fs_info, ret); + btrfs_std_error(root->fs_info, ret, NULL); return ret; } } else { @@ -1927,7 +1927,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, child = read_node_slot(root, mid, 0); if (!child) { ret = -EROFS; - btrfs_std_error(root->fs_info, ret); + btrfs_std_error(root->fs_info, ret, NULL); goto enospc; } @@ -2030,7 +2030,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, */ if (!left) { ret = -EROFS; - btrfs_std_error(root->fs_info, ret); + btrfs_std_error(root->fs_info, ret, NULL); goto enospc; } wret = balance_node_right(trans, root, mid, left); @@ -4940,8 +4940,8 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root, { struct extent_buffer *leaf; struct btrfs_item *item; - int last_off; - int dsize = 0; + u32 last_off; + u32 dsize = 0; int ret = 0; int wret; int i; diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 938efe3..8c58191 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -823,8 +823,18 @@ struct btrfs_disk_balance_args { */ __le64 profiles; - /* usage filter */ - __le64 usage; + /* + * usage filter + * BTRFS_BALANCE_ARGS_USAGE with a single value means '0..N' + * BTRFS_BALANCE_ARGS_USAGE_RANGE - range syntax, min..max + */ + union { + __le64 usage; + struct { + __le32 usage_min; + __le32 usage_max; + }; + }; /* devid filter */ __le64 devid; @@ -846,10 +856,27 @@ struct btrfs_disk_balance_args { /* BTRFS_BALANCE_ARGS_* */ __le64 flags; - /* BTRFS_BALANCE_ARGS_LIMIT value */ - __le64 limit; + /* + * BTRFS_BALANCE_ARGS_LIMIT with value 'limit' + * BTRFS_BALANCE_ARGS_LIMIT_RANGE - the extend version can use minimum + * and maximum + */ + union { + __le64 limit; + struct { + __le32 limit_min; + __le32 limit_max; + }; + }; - __le64 unused[7]; + /* + * Process chunks that cross stripes_min..stripes_max devices, + * BTRFS_BALANCE_ARGS_STRIPES_RANGE + */ + __le32 stripes_min; + __le32 stripes_max; + + __le64 unused[6]; } __attribute__ ((__packed__)); /* @@ -1154,6 +1181,10 @@ struct btrfs_space_info { delalloc/allocations */ u64 bytes_readonly; /* total bytes that are read only */ + u64 max_extent_size; /* This will hold the maximum extent size of + the space info if we had an ENOSPC in the + allocator. */ + unsigned int full:1; /* indicates that we cannot allocate any more chunks for this space */ unsigned int chunk_alloc:1; /* set if we are allocating a chunk */ @@ -1228,6 +1259,9 @@ struct btrfs_free_cluster { /* first extent starting offset */ u64 window_start; + /* We did a full search and couldn't create a cluster */ + bool fragmented; + struct btrfs_block_group_cache *block_group; /* * when a cluster is allocated from a block group, we put the @@ -1943,6 +1977,9 @@ struct btrfs_root { int send_in_progress; struct btrfs_subvolume_writers *subv_writers; atomic_t will_be_snapshoted; + + /* For qgroup metadata space reserve */ + atomic_t qgroup_meta_rsv; }; struct btrfs_ioctl_defrag_range_args { @@ -2145,6 +2182,8 @@ struct btrfs_ioctl_defrag_range_args { #define BTRFS_MOUNT_CHECK_INTEGRITY_INCLUDING_EXTENT_DATA (1 << 21) #define BTRFS_MOUNT_PANIC_ON_FATAL_ERROR (1 << 22) #define BTRFS_MOUNT_RESCAN_UUID_TREE (1 << 23) +#define BTRFS_MOUNT_FRAGMENT_DATA (1 << 24) +#define BTRFS_MOUNT_FRAGMENT_METADATA (1 << 25) #define BTRFS_DEFAULT_COMMIT_INTERVAL (30) #define BTRFS_DEFAULT_MAX_INLINE (8192) @@ -2169,6 +2208,18 @@ struct btrfs_ioctl_defrag_range_args { btrfs_clear_opt(root->fs_info->mount_opt, opt); \ } +#ifdef CONFIG_BTRFS_DEBUG +static inline int +btrfs_should_fragment_free_space(struct btrfs_root *root, + struct btrfs_block_group_cache *block_group) +{ + return (btrfs_test_opt(root, FRAGMENT_METADATA) && + block_group->flags & BTRFS_BLOCK_GROUP_METADATA) || + (btrfs_test_opt(root, FRAGMENT_DATA) && + block_group->flags & BTRFS_BLOCK_GROUP_DATA); +} +#endif + /* * Requests for changes that need to be done during transaction commit. * @@ -3316,7 +3367,7 @@ static inline bool btrfs_mixed_space_info(struct btrfs_space_info *space_info) static inline gfp_t btrfs_alloc_write_mask(struct address_space *mapping) { - return mapping_gfp_mask(mapping) & ~__GFP_FS; + return mapping_gfp_constraint(mapping, ~__GFP_FS); } /* extent-tree.c */ @@ -3379,7 +3430,8 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 root_objectid, u64 owner, - u64 offset, struct btrfs_key *ins); + u64 offset, u64 ram_bytes, + struct btrfs_key *ins); int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 root_objectid, u64 owner, u64 offset, @@ -3398,7 +3450,7 @@ int btrfs_set_disk_extent_flags(struct btrfs_trans_handle *trans, int btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 bytenr, u64 num_bytes, u64 parent, u64 root_objectid, - u64 owner, u64 offset, int no_quota); + u64 owner, u64 offset); int btrfs_free_reserved_extent(struct btrfs_root *root, u64 start, u64 len, int delalloc); @@ -3411,7 +3463,7 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans, int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 bytenr, u64 num_bytes, u64 parent, - u64 root_objectid, u64 owner, u64 offset, int no_quota); + u64 root_objectid, u64 owner, u64 offset); int btrfs_start_dirty_block_groups(struct btrfs_trans_handle *trans, struct btrfs_root *root); @@ -3449,8 +3501,11 @@ enum btrfs_reserve_flush_enum { BTRFS_RESERVE_FLUSH_ALL, }; -int btrfs_check_data_free_space(struct inode *inode, u64 bytes, u64 write_bytes); -void btrfs_free_reserved_data_space(struct inode *inode, u64 bytes); +int btrfs_check_data_free_space(struct inode *inode, u64 start, u64 len); +int btrfs_alloc_data_chunk_ondemand(struct inode *inode, u64 bytes); +void btrfs_free_reserved_data_space(struct inode *inode, u64 start, u64 len); +void btrfs_free_reserved_data_space_noquota(struct inode *inode, u64 start, + u64 len); void btrfs_trans_release_metadata(struct btrfs_trans_handle *trans, struct btrfs_root *root); void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans); @@ -3466,8 +3521,8 @@ void btrfs_subvolume_release_metadata(struct btrfs_root *root, u64 qgroup_reserved); int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes); void btrfs_delalloc_release_metadata(struct inode *inode, u64 num_bytes); -int btrfs_delalloc_reserve_space(struct inode *inode, u64 num_bytes); -void btrfs_delalloc_release_space(struct inode *inode, u64 num_bytes); +int btrfs_delalloc_reserve_space(struct inode *inode, u64 start, u64 len); +void btrfs_delalloc_release_space(struct inode *inode, u64 start, u64 len); void btrfs_init_block_rsv(struct btrfs_block_rsv *rsv, unsigned short type); struct btrfs_block_rsv *btrfs_alloc_block_rsv(struct btrfs_root *root, unsigned short type); @@ -4004,8 +4059,8 @@ int btrfs_defrag_leaves(struct btrfs_trans_handle *trans, /* sysfs.c */ int btrfs_init_sysfs(void); void btrfs_exit_sysfs(void); -int btrfs_sysfs_add_one(struct btrfs_fs_info *fs_info); -void btrfs_sysfs_remove_one(struct btrfs_fs_info *fs_info); +int btrfs_sysfs_add_mounted(struct btrfs_fs_info *fs_info); +void btrfs_sysfs_remove_mounted(struct btrfs_fs_info *fs_info); /* xattr.c */ ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size); @@ -4039,14 +4094,102 @@ void btrfs_printk(const struct btrfs_fs_info *fs_info, const char *fmt, ...) #define btrfs_info(fs_info, fmt, args...) \ btrfs_printk(fs_info, KERN_INFO fmt, ##args) +/* + * Wrappers that use printk_in_rcu + */ +#define btrfs_emerg_in_rcu(fs_info, fmt, args...) \ + btrfs_printk_in_rcu(fs_info, KERN_EMERG fmt, ##args) +#define btrfs_alert_in_rcu(fs_info, fmt, args...) \ + btrfs_printk_in_rcu(fs_info, KERN_ALERT fmt, ##args) +#define btrfs_crit_in_rcu(fs_info, fmt, args...) \ + btrfs_printk_in_rcu(fs_info, KERN_CRIT fmt, ##args) +#define btrfs_err_in_rcu(fs_info, fmt, args...) \ + btrfs_printk_in_rcu(fs_info, KERN_ERR fmt, ##args) +#define btrfs_warn_in_rcu(fs_info, fmt, args...) \ + btrfs_printk_in_rcu(fs_info, KERN_WARNING fmt, ##args) +#define btrfs_notice_in_rcu(fs_info, fmt, args...) \ + btrfs_printk_in_rcu(fs_info, KERN_NOTICE fmt, ##args) +#define btrfs_info_in_rcu(fs_info, fmt, args...) \ + btrfs_printk_in_rcu(fs_info, KERN_INFO fmt, ##args) + +/* + * Wrappers that use a ratelimited printk_in_rcu + */ +#define btrfs_emerg_rl_in_rcu(fs_info, fmt, args...) \ + btrfs_printk_rl_in_rcu(fs_info, KERN_EMERG fmt, ##args) +#define btrfs_alert_rl_in_rcu(fs_info, fmt, args...) \ + btrfs_printk_rl_in_rcu(fs_info, KERN_ALERT fmt, ##args) +#define btrfs_crit_rl_in_rcu(fs_info, fmt, args...) \ + btrfs_printk_rl_in_rcu(fs_info, KERN_CRIT fmt, ##args) +#define btrfs_err_rl_in_rcu(fs_info, fmt, args...) \ + btrfs_printk_rl_in_rcu(fs_info, KERN_ERR fmt, ##args) +#define btrfs_warn_rl_in_rcu(fs_info, fmt, args...) \ + btrfs_printk_rl_in_rcu(fs_info, KERN_WARNING fmt, ##args) +#define btrfs_notice_rl_in_rcu(fs_info, fmt, args...) \ + btrfs_printk_rl_in_rcu(fs_info, KERN_NOTICE fmt, ##args) +#define btrfs_info_rl_in_rcu(fs_info, fmt, args...) \ + btrfs_printk_rl_in_rcu(fs_info, KERN_INFO fmt, ##args) + +/* + * Wrappers that use a ratelimited printk + */ +#define btrfs_emerg_rl(fs_info, fmt, args...) \ + btrfs_printk_ratelimited(fs_info, KERN_EMERG fmt, ##args) +#define btrfs_alert_rl(fs_info, fmt, args...) \ + btrfs_printk_ratelimited(fs_info, KERN_ALERT fmt, ##args) +#define btrfs_crit_rl(fs_info, fmt, args...) \ + btrfs_printk_ratelimited(fs_info, KERN_CRIT fmt, ##args) +#define btrfs_err_rl(fs_info, fmt, args...) \ + btrfs_printk_ratelimited(fs_info, KERN_ERR fmt, ##args) +#define btrfs_warn_rl(fs_info, fmt, args...) \ + btrfs_printk_ratelimited(fs_info, KERN_WARNING fmt, ##args) +#define btrfs_notice_rl(fs_info, fmt, args...) \ + btrfs_printk_ratelimited(fs_info, KERN_NOTICE fmt, ##args) +#define btrfs_info_rl(fs_info, fmt, args...) \ + btrfs_printk_ratelimited(fs_info, KERN_INFO fmt, ##args) #ifdef DEBUG #define btrfs_debug(fs_info, fmt, args...) \ btrfs_printk(fs_info, KERN_DEBUG fmt, ##args) +#define btrfs_debug_in_rcu(fs_info, fmt, args...) \ + btrfs_printk_in_rcu(fs_info, KERN_DEBUG fmt, ##args) +#define btrfs_debug_rl_in_rcu(fs_info, fmt, args...) \ + btrfs_printk_rl_in_rcu(fs_info, KERN_DEBUG fmt, ##args) +#define btrfs_debug_rl(fs_info, fmt, args...) \ + btrfs_printk_ratelimited(fs_info, KERN_DEBUG fmt, ##args) #else #define btrfs_debug(fs_info, fmt, args...) \ no_printk(KERN_DEBUG fmt, ##args) +#define btrfs_debug_in_rcu(fs_info, fmt, args...) \ + no_printk(KERN_DEBUG fmt, ##args) +#define btrfs_debug_rl_in_rcu(fs_info, fmt, args...) \ + no_printk(KERN_DEBUG fmt, ##args) +#define btrfs_debug_rl(fs_info, fmt, args...) \ + no_printk(KERN_DEBUG fmt, ##args) #endif +#define btrfs_printk_in_rcu(fs_info, fmt, args...) \ +do { \ + rcu_read_lock(); \ + btrfs_printk(fs_info, fmt, ##args); \ + rcu_read_unlock(); \ +} while (0) + +#define btrfs_printk_ratelimited(fs_info, fmt, args...) \ +do { \ + static DEFINE_RATELIMIT_STATE(_rs, \ + DEFAULT_RATELIMIT_INTERVAL, \ + DEFAULT_RATELIMIT_BURST); \ + if (__ratelimit(&_rs)) \ + btrfs_printk(fs_info, fmt, ##args); \ +} while (0) + +#define btrfs_printk_rl_in_rcu(fs_info, fmt, args...) \ +do { \ + rcu_read_lock(); \ + btrfs_printk_ratelimited(fs_info, fmt, ##args); \ + rcu_read_unlock(); \ +} while (0) + #ifdef CONFIG_BTRFS_ASSERT __cold @@ -4127,14 +4270,7 @@ do { \ __LINE__, (errno)); \ } while (0) -#define btrfs_std_error(fs_info, errno) \ -do { \ - if ((errno)) \ - __btrfs_std_error((fs_info), __func__, \ - __LINE__, (errno), NULL); \ -} while (0) - -#define btrfs_error(fs_info, errno, fmt, args...) \ +#define btrfs_std_error(fs_info, errno, fmt, args...) \ do { \ __btrfs_std_error((fs_info), __func__, __LINE__, \ (errno), fmt, ##args); \ diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index a2ae427..e0941fb 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -463,6 +463,10 @@ static int __btrfs_add_delayed_deletion_item(struct btrfs_delayed_node *node, static void finish_one_item(struct btrfs_delayed_root *delayed_root) { int seq = atomic_inc_return(&delayed_root->items_seq); + + /* + * atomic_dec_return implies a barrier for waitqueue_active + */ if ((atomic_dec_return(&delayed_root->items) < BTRFS_DELAYED_BACKGROUND || seq % BTRFS_DELAYED_BATCH == 0) && waitqueue_active(&delayed_root->wait)) diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c index ac3e81d..e06dd75 100644 --- a/fs/btrfs/delayed-ref.c +++ b/fs/btrfs/delayed-ref.c @@ -197,6 +197,119 @@ static inline void drop_delayed_ref(struct btrfs_trans_handle *trans, trans->delayed_ref_updates--; } +static bool merge_ref(struct btrfs_trans_handle *trans, + struct btrfs_delayed_ref_root *delayed_refs, + struct btrfs_delayed_ref_head *head, + struct btrfs_delayed_ref_node *ref, + u64 seq) +{ + struct btrfs_delayed_ref_node *next; + bool done = false; + + next = list_first_entry(&head->ref_list, struct btrfs_delayed_ref_node, + list); + while (!done && &next->list != &head->ref_list) { + int mod; + struct btrfs_delayed_ref_node *next2; + + next2 = list_next_entry(next, list); + + if (next == ref) + goto next; + + if (seq && next->seq >= seq) + goto next; + + if (next->type != ref->type) + goto next; + + if ((ref->type == BTRFS_TREE_BLOCK_REF_KEY || + ref->type == BTRFS_SHARED_BLOCK_REF_KEY) && + comp_tree_refs(btrfs_delayed_node_to_tree_ref(ref), + btrfs_delayed_node_to_tree_ref(next), + ref->type)) + goto next; + if ((ref->type == BTRFS_EXTENT_DATA_REF_KEY || + ref->type == BTRFS_SHARED_DATA_REF_KEY) && + comp_data_refs(btrfs_delayed_node_to_data_ref(ref), + btrfs_delayed_node_to_data_ref(next))) + goto next; + + if (ref->action == next->action) { + mod = next->ref_mod; + } else { + if (ref->ref_mod < next->ref_mod) { + swap(ref, next); + done = true; + } + mod = -next->ref_mod; + } + + drop_delayed_ref(trans, delayed_refs, head, next); + ref->ref_mod += mod; + if (ref->ref_mod == 0) { + drop_delayed_ref(trans, delayed_refs, head, ref); + done = true; + } else { + /* + * Can't have multiples of the same ref on a tree block. + */ + WARN_ON(ref->type == BTRFS_TREE_BLOCK_REF_KEY || + ref->type == BTRFS_SHARED_BLOCK_REF_KEY); + } +next: + next = next2; + } + + return done; +} + +void btrfs_merge_delayed_refs(struct btrfs_trans_handle *trans, + struct btrfs_fs_info *fs_info, + struct btrfs_delayed_ref_root *delayed_refs, + struct btrfs_delayed_ref_head *head) +{ + struct btrfs_delayed_ref_node *ref; + u64 seq = 0; + + assert_spin_locked(&head->lock); + + if (list_empty(&head->ref_list)) + return; + + /* We don't have too many refs to merge for data. */ + if (head->is_data) + return; + + spin_lock(&fs_info->tree_mod_seq_lock); + if (!list_empty(&fs_info->tree_mod_seq_list)) { + struct seq_list *elem; + + elem = list_first_entry(&fs_info->tree_mod_seq_list, + struct seq_list, list); + seq = elem->seq; + } + spin_unlock(&fs_info->tree_mod_seq_lock); + + ref = list_first_entry(&head->ref_list, struct btrfs_delayed_ref_node, + list); + while (&ref->list != &head->ref_list) { + if (seq && ref->seq >= seq) + goto next; + + if (merge_ref(trans, delayed_refs, head, ref, seq)) { + if (list_empty(&head->ref_list)) + break; + ref = list_first_entry(&head->ref_list, + struct btrfs_delayed_ref_node, + list); + continue; + } +next: + ref = list_next_entry(ref, list); + } +} + int btrfs_check_delayed_seq(struct btrfs_fs_info *fs_info, struct btrfs_delayed_ref_root *delayed_refs, u64 seq) @@ -292,8 +405,7 @@ add_delayed_ref_tail_merge(struct btrfs_trans_handle *trans, exist = list_entry(href->ref_list.prev, struct btrfs_delayed_ref_node, list); /* No need to compare bytenr nor is_head */ - if (exist->type != ref->type || exist->no_quota != ref->no_quota || - exist->seq != ref->seq) + if (exist->type != ref->type || exist->seq != ref->seq) goto add_tail; if ((exist->type == BTRFS_TREE_BLOCK_REF_KEY || @@ -423,7 +535,8 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info, struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_node *ref, struct btrfs_qgroup_extent_record *qrecord, - u64 bytenr, u64 num_bytes, int action, int is_data) + u64 bytenr, u64 num_bytes, u64 ref_root, u64 reserved, + int action, int is_data) { struct btrfs_delayed_ref_head *existing; struct btrfs_delayed_ref_head *head_ref = NULL; @@ -432,6 +545,9 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info, int count_mod = 1; int must_insert_reserved = 0; + /* If reserved is provided, it must be a data extent. */ + BUG_ON(!is_data && reserved); + /* * the head node stores the sum of all the mods, so dropping a ref * should drop the sum in the head node by one. @@ -476,9 +592,16 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info, INIT_LIST_HEAD(&head_ref->ref_list); head_ref->processing = 0; head_ref->total_ref_mod = count_mod; + head_ref->qgroup_reserved = 0; + head_ref->qgroup_ref_root = 0; /* Record qgroup extent info if provided */ if (qrecord) { + if (ref_root && reserved) { + head_ref->qgroup_ref_root = ref_root; + head_ref->qgroup_reserved = reserved; + } + qrecord->bytenr = bytenr; qrecord->num_bytes = num_bytes; qrecord->old_roots = NULL; @@ -497,6 +620,8 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info, existing = htree_insert(&delayed_refs->href_root, &head_ref->href_node); if (existing) { + WARN_ON(ref_root && reserved && existing->qgroup_ref_root + && existing->qgroup_reserved); update_existing_head_ref(delayed_refs, &existing->node, ref); /* * we've updated the existing ref, free the newly @@ -524,7 +649,7 @@ add_delayed_tree_ref(struct btrfs_fs_info *fs_info, struct btrfs_delayed_ref_head *head_ref, struct btrfs_delayed_ref_node *ref, u64 bytenr, u64 num_bytes, u64 parent, u64 ref_root, int level, - int action, int no_quota) + int action) { struct btrfs_delayed_tree_ref *full_ref; struct btrfs_delayed_ref_root *delayed_refs; @@ -546,7 +671,6 @@ add_delayed_tree_ref(struct btrfs_fs_info *fs_info, ref->action = action; ref->is_head = 0; ref->in_tree = 1; - ref->no_quota = no_quota; ref->seq = seq; full_ref = btrfs_delayed_node_to_tree_ref(ref); @@ -579,7 +703,7 @@ add_delayed_data_ref(struct btrfs_fs_info *fs_info, struct btrfs_delayed_ref_head *head_ref, struct btrfs_delayed_ref_node *ref, u64 bytenr, u64 num_bytes, u64 parent, u64 ref_root, u64 owner, - u64 offset, int action, int no_quota) + u64 offset, int action) { struct btrfs_delayed_data_ref *full_ref; struct btrfs_delayed_ref_root *delayed_refs; @@ -602,7 +726,6 @@ add_delayed_data_ref(struct btrfs_fs_info *fs_info, ref->action = action; ref->is_head = 0; ref->in_tree = 1; - ref->no_quota = no_quota; ref->seq = seq; full_ref = btrfs_delayed_node_to_data_ref(ref); @@ -633,17 +756,13 @@ int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info, struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, u64 parent, u64 ref_root, int level, int action, - struct btrfs_delayed_extent_op *extent_op, - int no_quota) + struct btrfs_delayed_extent_op *extent_op) { struct btrfs_delayed_tree_ref *ref; struct btrfs_delayed_ref_head *head_ref; struct btrfs_delayed_ref_root *delayed_refs; struct btrfs_qgroup_extent_record *record = NULL; - if (!is_fstree(ref_root) || !fs_info->quota_enabled) - no_quota = 0; - BUG_ON(extent_op && extent_op->is_data); ref = kmem_cache_alloc(btrfs_delayed_tree_ref_cachep, GFP_NOFS); if (!ref) @@ -669,11 +788,10 @@ int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info, * the spin lock */ head_ref = add_delayed_ref_head(fs_info, trans, &head_ref->node, record, - bytenr, num_bytes, action, 0); + bytenr, num_bytes, 0, 0, action, 0); add_delayed_tree_ref(fs_info, trans, head_ref, &ref->node, bytenr, - num_bytes, parent, ref_root, level, action, - no_quota); + num_bytes, parent, ref_root, level, action); spin_unlock(&delayed_refs->lock); return 0; @@ -693,18 +811,14 @@ int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info, struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, u64 parent, u64 ref_root, - u64 owner, u64 offset, int action, - struct btrfs_delayed_extent_op *extent_op, - int no_quota) + u64 owner, u64 offset, u64 reserved, int action, + struct btrfs_delayed_extent_op *extent_op) { struct btrfs_delayed_data_ref *ref; struct btrfs_delayed_ref_head *head_ref; struct btrfs_delayed_ref_root *delayed_refs; struct btrfs_qgroup_extent_record *record = NULL; - if (!is_fstree(ref_root) || !fs_info->quota_enabled) - no_quota = 0; - BUG_ON(extent_op && !extent_op->is_data); ref = kmem_cache_alloc(btrfs_delayed_data_ref_cachep, GFP_NOFS); if (!ref) @@ -736,16 +850,44 @@ int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info, * the spin lock */ head_ref = add_delayed_ref_head(fs_info, trans, &head_ref->node, record, - bytenr, num_bytes, action, 1); + bytenr, num_bytes, ref_root, reserved, + action, 1); add_delayed_data_ref(fs_info, trans, head_ref, &ref->node, bytenr, num_bytes, parent, ref_root, owner, offset, - action, no_quota); + action); spin_unlock(&delayed_refs->lock); return 0; } +int btrfs_add_delayed_qgroup_reserve(struct btrfs_fs_info *fs_info, + struct btrfs_trans_handle *trans, + u64 ref_root, u64 bytenr, u64 num_bytes) +{ + struct btrfs_delayed_ref_root *delayed_refs; + struct btrfs_delayed_ref_head *ref_head; + int ret = 0; + + if (!fs_info->quota_enabled || !is_fstree(ref_root)) + return 0; + + delayed_refs = &trans->transaction->delayed_refs; + + spin_lock(&delayed_refs->lock); + ref_head = find_ref_head(&delayed_refs->href_root, bytenr, 0); + if (!ref_head) { + ret = -ENOENT; + goto out; + } + WARN_ON(ref_head->qgroup_reserved || ref_head->qgroup_ref_root); + ref_head->qgroup_ref_root = ref_root; + ref_head->qgroup_reserved = num_bytes; +out: + spin_unlock(&delayed_refs->lock); + return ret; +} + int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info, struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, @@ -764,7 +906,7 @@ int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info, spin_lock(&delayed_refs->lock); add_delayed_ref_head(fs_info, trans, &head_ref->node, NULL, bytenr, - num_bytes, BTRFS_UPDATE_DELAYED_HEAD, + num_bytes, 0, 0, BTRFS_UPDATE_DELAYED_HEAD, extent_op->is_data); spin_unlock(&delayed_refs->lock); diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h index 13fb5e6..00ed02c 100644 --- a/fs/btrfs/delayed-ref.h +++ b/fs/btrfs/delayed-ref.h @@ -68,7 +68,6 @@ struct btrfs_delayed_ref_node { unsigned int action:8; unsigned int type:8; - unsigned int no_quota:1; /* is this node still in the rbtree? */ unsigned int is_head:1; unsigned int in_tree:1; @@ -113,6 +112,17 @@ struct btrfs_delayed_ref_head { int total_ref_mod; /* + * For qgroup reserved space freeing. + * + * ref_root and reserved will be recorded after + * BTRFS_ADD_DELAYED_EXTENT is called. + * And will be used to free reserved qgroup space at + * run_delayed_refs() time. + */ + u64 qgroup_ref_root; + u64 qgroup_reserved; + + /* * when a new extent is allocated, it is just reserved in memory * The actual extent isn't inserted into the extent allocation tree * until the delayed ref is processed. must_insert_reserved is @@ -233,15 +243,16 @@ int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info, struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, u64 parent, u64 ref_root, int level, int action, - struct btrfs_delayed_extent_op *extent_op, - int no_quota); + struct btrfs_delayed_extent_op *extent_op); int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info, struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, u64 parent, u64 ref_root, - u64 owner, u64 offset, int action, - struct btrfs_delayed_extent_op *extent_op, - int no_quota); + u64 owner, u64 offset, u64 reserved, int action, + struct btrfs_delayed_extent_op *extent_op); +int btrfs_add_delayed_qgroup_reserve(struct btrfs_fs_info *fs_info, + struct btrfs_trans_handle *trans, + u64 ref_root, u64 bytenr, u64 num_bytes); int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info, struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index e54dd59..1e668fb 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -327,19 +327,6 @@ int btrfs_dev_replace_start(struct btrfs_root *root, args->start.tgtdev_name[0] == '\0') return -EINVAL; - /* - * Here we commit the transaction to make sure commit_total_bytes - * of all the devices are updated. - */ - trans = btrfs_attach_transaction(root); - if (!IS_ERR(trans)) { - ret = btrfs_commit_transaction(trans, root); - if (ret) - return ret; - } else if (PTR_ERR(trans) != -ENOENT) { - return PTR_ERR(trans); - } - /* the disk copy procedure reuses the scrub code */ mutex_lock(&fs_info->volume_mutex); ret = btrfs_dev_replace_find_srcdev(root, args->start.srcdevid, @@ -356,6 +343,19 @@ int btrfs_dev_replace_start(struct btrfs_root *root, if (ret) return ret; + /* + * Here we commit the transaction to make sure commit_total_bytes + * of all the devices are updated. + */ + trans = btrfs_attach_transaction(root); + if (!IS_ERR(trans)) { + ret = btrfs_commit_transaction(trans, root); + if (ret) + return ret; + } else if (PTR_ERR(trans) != -ENOENT) { + return PTR_ERR(trans); + } + btrfs_dev_replace_lock(dev_replace); switch (dev_replace->replace_state) { case BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED: @@ -375,12 +375,8 @@ int btrfs_dev_replace_start(struct btrfs_root *root, WARN_ON(!tgt_device); dev_replace->tgtdev = tgt_device; - ret = btrfs_kobj_add_device(tgt_device->fs_devices, tgt_device); - if (ret) - btrfs_err(root->fs_info, "kobj add dev failed %d\n", ret); - - printk_in_rcu(KERN_INFO - "BTRFS: dev_replace from %s (devid %llu) to %s started\n", + btrfs_info_in_rcu(root->fs_info, + "dev_replace from %s (devid %llu) to %s started", src_device->missing ? "<missing disk>" : rcu_str_deref(src_device->name), src_device->devid, @@ -401,6 +397,10 @@ int btrfs_dev_replace_start(struct btrfs_root *root, args->result = BTRFS_IOCTL_DEV_REPLACE_RESULT_NO_ERROR; btrfs_dev_replace_unlock(dev_replace); + ret = btrfs_sysfs_add_device_link(tgt_device->fs_devices, tgt_device); + if (ret) + btrfs_err(root->fs_info, "kobj add dev failed %d\n", ret); + btrfs_wait_ordered_roots(root->fs_info, -1); /* force writing the updated state information to disk */ @@ -454,8 +454,7 @@ static void btrfs_rm_dev_replace_blocked(struct btrfs_fs_info *fs_info) static void btrfs_rm_dev_replace_unblocked(struct btrfs_fs_info *fs_info) { clear_bit(BTRFS_FS_STATE_DEV_REPLACING, &fs_info->fs_state); - if (waitqueue_active(&fs_info->replace_wait)) - wake_up(&fs_info->replace_wait); + wake_up(&fs_info->replace_wait); } static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, @@ -523,8 +522,8 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, src_device, tgt_device); } else { - printk_in_rcu(KERN_ERR - "BTRFS: btrfs_scrub_dev(%s, %llu, %s) failed %d\n", + btrfs_err_in_rcu(root->fs_info, + "btrfs_scrub_dev(%s, %llu, %s) failed %d", src_device->missing ? "<missing disk>" : rcu_str_deref(src_device->name), src_device->devid, @@ -540,8 +539,8 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, return scrub_ret; } - printk_in_rcu(KERN_INFO - "BTRFS: dev_replace from %s (devid %llu) to %s finished\n", + btrfs_info_in_rcu(root->fs_info, + "dev_replace from %s (devid %llu) to %s finished", src_device->missing ? "<missing disk>" : rcu_str_deref(src_device->name), src_device->devid, @@ -586,7 +585,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, mutex_unlock(&uuid_mutex); /* replace the sysfs entry */ - btrfs_kobj_rm_device(fs_info->fs_devices, src_device); + btrfs_sysfs_rm_device_link(fs_info->fs_devices, src_device); btrfs_rm_dev_replace_free_srcdev(fs_info, src_device); /* write back the superblocks */ @@ -809,8 +808,8 @@ static int btrfs_dev_replace_kthread(void *data) progress = status_args->status.progress_1000; kfree(status_args); progress = div_u64(progress, 10); - printk_in_rcu(KERN_INFO - "BTRFS: continuing dev_replace from %s (devid %llu) to %s @%u%%\n", + btrfs_info_in_rcu(fs_info, + "continuing dev_replace from %s (devid %llu) to %s @%u%%", dev_replace->srcdev->missing ? "<missing disk>" : rcu_str_deref(dev_replace->srcdev->name), dev_replace->srcdev->devid, diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 0d98aee..640598c 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -319,9 +319,9 @@ static int csum_tree_block(struct btrfs_fs_info *fs_info, memcpy(&found, result, csum_size); read_extent_buffer(buf, &val, 0, csum_size); - printk_ratelimited(KERN_WARNING - "BTRFS: %s checksum verify failed on %llu wanted %X found %X " - "level %d\n", + btrfs_warn_rl(fs_info, + "%s checksum verify failed on %llu wanted %X found %X " + "level %d", fs_info->sb->s_id, buf->start, val, found, btrfs_header_level(buf)); if (result != (char *)&inline_result) @@ -368,9 +368,9 @@ static int verify_parent_transid(struct extent_io_tree *io_tree, ret = 0; goto out; } - printk_ratelimited(KERN_ERR - "BTRFS (device %s): parent transid verify failed on %llu wanted %llu found %llu\n", - eb->fs_info->sb->s_id, eb->start, + btrfs_err_rl(eb->fs_info, + "parent transid verify failed on %llu wanted %llu found %llu", + eb->start, parent_transid, btrfs_header_generation(eb)); ret = 1; @@ -629,15 +629,14 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio, found_start = btrfs_header_bytenr(eb); if (found_start != eb->start) { - printk_ratelimited(KERN_ERR "BTRFS (device %s): bad tree block start " - "%llu %llu\n", - eb->fs_info->sb->s_id, found_start, eb->start); + btrfs_err_rl(eb->fs_info, "bad tree block start %llu %llu", + found_start, eb->start); ret = -EIO; goto err; } if (check_tree_block_fsid(root->fs_info, eb)) { - printk_ratelimited(KERN_ERR "BTRFS (device %s): bad fsid on block %llu\n", - eb->fs_info->sb->s_id, eb->start); + btrfs_err_rl(eb->fs_info, "bad fsid on block %llu", + eb->start); ret = -EIO; goto err; } @@ -802,6 +801,9 @@ static void run_one_async_done(struct btrfs_work *work) limit = btrfs_async_submit_limit(fs_info); limit = limit * 2 / 3; + /* + * atomic_dec_return implies a barrier for waitqueue_active + */ if (atomic_dec_return(&fs_info->nr_async_submits) < limit && waitqueue_active(&fs_info->async_submit_wait)) wake_up(&fs_info->async_submit_wait); @@ -1265,6 +1267,7 @@ static void __setup_root(u32 nodesize, u32 sectorsize, u32 stripesize, atomic_set(&root->orphan_inodes, 0); atomic_set(&root->refs, 1); atomic_set(&root->will_be_snapshoted, 0); + atomic_set(&root->qgroup_meta_rsv, 0); root->log_transid = 0; root->log_transid_committed = -1; root->last_log_commit = 0; @@ -1759,6 +1762,7 @@ static int cleaner_kthread(void *arg) int again; struct btrfs_trans_handle *trans; + set_freezable(); do { again = 0; @@ -2348,8 +2352,7 @@ static int btrfs_replay_log(struct btrfs_fs_info *fs_info, u64 bytenr = btrfs_super_log_root(disk_super); if (fs_devices->rw_devices == 0) { - printk(KERN_WARNING "BTRFS: log replay required " - "on RO media\n"); + btrfs_warn(fs_info, "log replay required on RO media"); return -EIO; } @@ -2364,12 +2367,12 @@ static int btrfs_replay_log(struct btrfs_fs_info *fs_info, log_tree_root->node = read_tree_block(tree_root, bytenr, fs_info->generation + 1); if (IS_ERR(log_tree_root->node)) { - printk(KERN_ERR "BTRFS: failed to read log tree\n"); + btrfs_warn(fs_info, "failed to read log tree"); ret = PTR_ERR(log_tree_root->node); kfree(log_tree_root); return ret; } else if (!extent_buffer_uptodate(log_tree_root->node)) { - printk(KERN_ERR "BTRFS: failed to read log tree\n"); + btrfs_err(fs_info, "failed to read log tree"); free_extent_buffer(log_tree_root->node); kfree(log_tree_root); return -EIO; @@ -2377,7 +2380,7 @@ static int btrfs_replay_log(struct btrfs_fs_info *fs_info, /* returns with log_tree_root freed on success */ ret = btrfs_recover_log_trees(log_tree_root); if (ret) { - btrfs_error(tree_root->fs_info, ret, + btrfs_std_error(tree_root->fs_info, ret, "Failed to recover log tree"); free_extent_buffer(log_tree_root->node); kfree(log_tree_root); @@ -2572,7 +2575,7 @@ int open_ctree(struct super_block *sb, fs_info->commit_interval = BTRFS_DEFAULT_COMMIT_INTERVAL; fs_info->avg_delayed_ref_runtime = NSEC_PER_SEC >> 6; /* div by 64 */ /* readahead state */ - INIT_RADIX_TREE(&fs_info->reada_tree, GFP_NOFS & ~__GFP_WAIT); + INIT_RADIX_TREE(&fs_info->reada_tree, GFP_NOFS & ~__GFP_DIRECT_RECLAIM); spin_lock_init(&fs_info->reada_lock); fs_info->thread_pool_size = min_t(unsigned long, @@ -2653,8 +2656,8 @@ int open_ctree(struct super_block *sb, * Read super block and check the signature bytes only */ bh = btrfs_read_dev_super(fs_devices->latest_bdev); - if (!bh) { - err = -EINVAL; + if (IS_ERR(bh)) { + err = PTR_ERR(bh); goto fail_alloc; } @@ -2847,6 +2850,8 @@ int open_ctree(struct super_block *sb, !extent_buffer_uptodate(chunk_root->node)) { printk(KERN_ERR "BTRFS: failed to read chunk root on %s\n", sb->s_id); + if (!IS_ERR(chunk_root->node)) + free_extent_buffer(chunk_root->node); chunk_root->node = NULL; goto fail_tree_roots; } @@ -2885,6 +2890,8 @@ retry_root_backup: !extent_buffer_uptodate(tree_root->node)) { printk(KERN_WARNING "BTRFS: failed to read tree root on %s\n", sb->s_id); + if (!IS_ERR(tree_root->node)) + free_extent_buffer(tree_root->node); tree_root->node = NULL; goto recovery_tree_root; } @@ -2933,7 +2940,7 @@ retry_root_backup: goto fail_fsdev_sysfs; } - ret = btrfs_sysfs_add_one(fs_info); + ret = btrfs_sysfs_add_mounted(fs_info); if (ret) { pr_err("BTRFS: failed to init sysfs interface: %d\n", ret); goto fail_fsdev_sysfs; @@ -3113,7 +3120,7 @@ fail_cleaner: filemap_write_and_wait(fs_info->btree_inode->i_mapping); fail_sysfs: - btrfs_sysfs_remove_one(fs_info); + btrfs_sysfs_remove_mounted(fs_info); fail_fsdev_sysfs: btrfs_sysfs_remove_fsid(fs_info->fs_devices); @@ -3175,8 +3182,8 @@ static void btrfs_end_buffer_write_sync(struct buffer_head *bh, int uptodate) struct btrfs_device *device = (struct btrfs_device *) bh->b_private; - printk_ratelimited_in_rcu(KERN_WARNING "BTRFS: lost page write due to " - "I/O error on %s\n", + btrfs_warn_rl_in_rcu(device->dev_root->fs_info, + "lost page write due to IO error on %s", rcu_str_deref(device->name)); /* note, we dont' set_buffer_write_io_error because we have * our own ways of dealing with the IO errors @@ -3188,6 +3195,37 @@ static void btrfs_end_buffer_write_sync(struct buffer_head *bh, int uptodate) put_bh(bh); } +int btrfs_read_dev_one_super(struct block_device *bdev, int copy_num, + struct buffer_head **bh_ret) +{ + struct buffer_head *bh; + struct btrfs_super_block *super; + u64 bytenr; + + bytenr = btrfs_sb_offset(copy_num); + if (bytenr + BTRFS_SUPER_INFO_SIZE >= i_size_read(bdev->bd_inode)) + return -EINVAL; + + bh = __bread(bdev, bytenr / 4096, BTRFS_SUPER_INFO_SIZE); + /* + * If we fail to read from the underlying devices, as of now + * the best option we have is to mark it EIO. + */ + if (!bh) + return -EIO; + + super = (struct btrfs_super_block *)bh->b_data; + if (btrfs_super_bytenr(super) != bytenr || + btrfs_super_magic(super) != BTRFS_MAGIC) { + brelse(bh); + return -EINVAL; + } + + *bh_ret = bh; + return 0; +} + + struct buffer_head *btrfs_read_dev_super(struct block_device *bdev) { struct buffer_head *bh; @@ -3195,7 +3233,7 @@ struct buffer_head *btrfs_read_dev_super(struct block_device *bdev) struct btrfs_super_block *super; int i; u64 transid = 0; - u64 bytenr; + int ret = -EINVAL; /* we would like to check all the supers, but that would make * a btrfs mount succeed after a mkfs from a different FS. @@ -3203,21 +3241,11 @@ struct buffer_head *btrfs_read_dev_super(struct block_device *bdev) * later supers, using BTRFS_SUPER_MIRROR_MAX instead */ for (i = 0; i < 1; i++) { - bytenr = btrfs_sb_offset(i); - if (bytenr + BTRFS_SUPER_INFO_SIZE >= - i_size_read(bdev->bd_inode)) - break; - bh = __bread(bdev, bytenr / 4096, - BTRFS_SUPER_INFO_SIZE); - if (!bh) + ret = btrfs_read_dev_one_super(bdev, i, &bh); + if (ret) continue; super = (struct btrfs_super_block *)bh->b_data; - if (btrfs_super_bytenr(super) != bytenr || - btrfs_super_magic(super) != BTRFS_MAGIC) { - brelse(bh); - continue; - } if (!latest || btrfs_super_generation(super) > transid) { brelse(latest); @@ -3227,6 +3255,10 @@ struct buffer_head *btrfs_read_dev_super(struct block_device *bdev) brelse(bh); } } + + if (!latest) + return ERR_PTR(ret); + return latest; } @@ -3295,8 +3327,9 @@ static int write_dev_supers(struct btrfs_device *device, bh = __getblk(device->bdev, bytenr / 4096, BTRFS_SUPER_INFO_SIZE); if (!bh) { - printk(KERN_ERR "BTRFS: couldn't get super " - "buffer head for bytenr %Lu\n", bytenr); + btrfs_err(device->dev_root->fs_info, + "couldn't get super buffer head for bytenr %llu", + bytenr); errors++; continue; } @@ -3445,22 +3478,31 @@ static int barrier_all_devices(struct btrfs_fs_info *info) int btrfs_get_num_tolerated_disk_barrier_failures(u64 flags) { - if ((flags & (BTRFS_BLOCK_GROUP_DUP | - BTRFS_BLOCK_GROUP_RAID0 | - BTRFS_AVAIL_ALLOC_BIT_SINGLE)) || - ((flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) == 0)) - return 0; + int raid_type; + int min_tolerated = INT_MAX; - if (flags & (BTRFS_BLOCK_GROUP_RAID1 | - BTRFS_BLOCK_GROUP_RAID5 | - BTRFS_BLOCK_GROUP_RAID10)) - return 1; + if ((flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) == 0 || + (flags & BTRFS_AVAIL_ALLOC_BIT_SINGLE)) + min_tolerated = min(min_tolerated, + btrfs_raid_array[BTRFS_RAID_SINGLE]. + tolerated_failures); - if (flags & BTRFS_BLOCK_GROUP_RAID6) - return 2; + for (raid_type = 0; raid_type < BTRFS_NR_RAID_TYPES; raid_type++) { + if (raid_type == BTRFS_RAID_SINGLE) + continue; + if (!(flags & btrfs_raid_group[raid_type])) + continue; + min_tolerated = min(min_tolerated, + btrfs_raid_array[raid_type]. + tolerated_failures); + } - pr_warn("BTRFS: unknown raid type: %llu\n", flags); - return 0; + if (min_tolerated == INT_MAX) { + pr_warn("BTRFS: unknown raid flag: %llu\n", flags); + min_tolerated = 0; + } + + return min_tolerated; } int btrfs_calc_num_tolerated_disk_barrier_failures( @@ -3544,7 +3586,7 @@ static int write_all_supers(struct btrfs_root *root, int max_mirrors) if (ret) { mutex_unlock( &root->fs_info->fs_devices->device_list_mutex); - btrfs_error(root->fs_info, ret, + btrfs_std_error(root->fs_info, ret, "errors while submitting device barriers."); return ret; } @@ -3584,7 +3626,7 @@ static int write_all_supers(struct btrfs_root *root, int max_mirrors) mutex_unlock(&root->fs_info->fs_devices->device_list_mutex); /* FUA is masked off if unsupported and can't be the reason */ - btrfs_error(root->fs_info, -EIO, + btrfs_std_error(root->fs_info, -EIO, "%d errors while writing supers", total_errors); return -EIO; } @@ -3602,7 +3644,7 @@ static int write_all_supers(struct btrfs_root *root, int max_mirrors) } mutex_unlock(&root->fs_info->fs_devices->device_list_mutex); if (total_errors > max_errors) { - btrfs_error(root->fs_info, -EIO, + btrfs_std_error(root->fs_info, -EIO, "%d errors while writing supers", total_errors); return -EIO; } @@ -3765,9 +3807,7 @@ void close_ctree(struct btrfs_root *root) * block groups queued for removal, the deletion will be * skipped when we quit the cleaner thread. */ - mutex_lock(&root->fs_info->cleaner_mutex); btrfs_delete_unused_bgs(root->fs_info); - mutex_unlock(&root->fs_info->cleaner_mutex); ret = btrfs_commit_super(root); if (ret) @@ -3790,7 +3830,7 @@ void close_ctree(struct btrfs_root *root) percpu_counter_sum(&fs_info->delalloc_bytes)); } - btrfs_sysfs_remove_one(fs_info); + btrfs_sysfs_remove_mounted(fs_info); btrfs_sysfs_remove_fsid(fs_info->fs_devices); btrfs_free_fs_roots(fs_info); @@ -4288,25 +4328,6 @@ again: return 0; } -static void btrfs_free_pending_ordered(struct btrfs_transaction *cur_trans, - struct btrfs_fs_info *fs_info) -{ - struct btrfs_ordered_extent *ordered; - - spin_lock(&fs_info->trans_lock); - while (!list_empty(&cur_trans->pending_ordered)) { - ordered = list_first_entry(&cur_trans->pending_ordered, - struct btrfs_ordered_extent, - trans_list); - list_del_init(&ordered->trans_list); - spin_unlock(&fs_info->trans_lock); - - btrfs_put_ordered_extent(ordered); - spin_lock(&fs_info->trans_lock); - } - spin_unlock(&fs_info->trans_lock); -} - void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans, struct btrfs_root *root) { @@ -4318,7 +4339,6 @@ void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans, cur_trans->state = TRANS_STATE_UNBLOCKED; wake_up(&root->fs_info->transaction_wait); - btrfs_free_pending_ordered(cur_trans, root->fs_info); btrfs_destroy_delayed_inodes(root); btrfs_assert_delayed_root_empty(root); diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index bdfb479..adeb318 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -60,6 +60,8 @@ void close_ctree(struct btrfs_root *root); int write_ctree_super(struct btrfs_trans_handle *trans, struct btrfs_root *root, int max_mirrors); struct buffer_head *btrfs_read_dev_super(struct block_device *bdev); +int btrfs_read_dev_one_super(struct block_device *bdev, int copy_num, + struct buffer_head **bh_ret); int btrfs_commit_super(struct btrfs_root *root); struct extent_buffer *btrfs_find_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr); diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c index 8d05220..2513a7f 100644 --- a/fs/btrfs/export.c +++ b/fs/btrfs/export.c @@ -112,11 +112,11 @@ static struct dentry *btrfs_fh_to_parent(struct super_block *sb, struct fid *fh, u32 generation; if (fh_type == FILEID_BTRFS_WITH_PARENT) { - if (fh_len != BTRFS_FID_SIZE_CONNECTABLE) + if (fh_len < BTRFS_FID_SIZE_CONNECTABLE) return NULL; root_objectid = fid->root_objectid; } else if (fh_type == FILEID_BTRFS_WITH_PARENT_ROOT) { - if (fh_len != BTRFS_FID_SIZE_CONNECTABLE_ROOT) + if (fh_len < BTRFS_FID_SIZE_CONNECTABLE_ROOT) return NULL; root_objectid = fid->parent_root_objectid; } else @@ -136,11 +136,11 @@ static struct dentry *btrfs_fh_to_dentry(struct super_block *sb, struct fid *fh, u32 generation; if ((fh_type != FILEID_BTRFS_WITH_PARENT || - fh_len != BTRFS_FID_SIZE_CONNECTABLE) && + fh_len < BTRFS_FID_SIZE_CONNECTABLE) && (fh_type != FILEID_BTRFS_WITH_PARENT_ROOT || - fh_len != BTRFS_FID_SIZE_CONNECTABLE_ROOT) && + fh_len < BTRFS_FID_SIZE_CONNECTABLE_ROOT) && (fh_type != FILEID_BTRFS_WITHOUT_PARENT || - fh_len != BTRFS_FID_SIZE_NON_CONNECTABLE)) + fh_len < BTRFS_FID_SIZE_NON_CONNECTABLE)) return NULL; objectid = fid->objectid; diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 5411f0a..99a8e57 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -95,8 +95,7 @@ static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 parent, u64 root_objectid, u64 flags, struct btrfs_disk_key *key, - int level, struct btrfs_key *ins, - int no_quota); + int level, struct btrfs_key *ins); static int do_chunk_alloc(struct btrfs_trans_handle *trans, struct btrfs_root *extent_root, u64 flags, int force); @@ -332,6 +331,27 @@ static void put_caching_control(struct btrfs_caching_control *ctl) kfree(ctl); } +#ifdef CONFIG_BTRFS_DEBUG +static void fragment_free_space(struct btrfs_root *root, + struct btrfs_block_group_cache *block_group) +{ + u64 start = block_group->key.objectid; + u64 len = block_group->key.offset; + u64 chunk = block_group->flags & BTRFS_BLOCK_GROUP_METADATA ? + root->nodesize : root->sectorsize; + u64 step = chunk << 1; + + while (len > chunk) { + btrfs_remove_free_space(block_group, start, chunk); + start += step; + if (len < step) + len = 0; + else + len -= step; + } +} +#endif + /* * this is only called by cache_block_group, since we could have freed extents * we need to check the pinned_extents for any extents that can't be used yet @@ -388,6 +408,7 @@ static noinline void caching_thread(struct btrfs_work *work) u64 last = 0; u32 nritems; int ret = -ENOMEM; + bool wakeup = true; caching_ctl = container_of(work, struct btrfs_caching_control, work); block_group = caching_ctl->block_group; @@ -400,6 +421,15 @@ static noinline void caching_thread(struct btrfs_work *work) last = max_t(u64, block_group->key.objectid, BTRFS_SUPER_INFO_OFFSET); +#ifdef CONFIG_BTRFS_DEBUG + /* + * If we're fragmenting we don't want to make anybody think we can + * allocate from this block group until we've had a chance to fragment + * the free space. + */ + if (btrfs_should_fragment_free_space(extent_root, block_group)) + wakeup = false; +#endif /* * We don't want to deadlock with somebody trying to allocate a new * extent for the extent root while also trying to search the extent @@ -441,7 +471,8 @@ next: if (need_resched() || rwsem_is_contended(&fs_info->commit_root_sem)) { - caching_ctl->progress = last; + if (wakeup) + caching_ctl->progress = last; btrfs_release_path(path); up_read(&fs_info->commit_root_sem); mutex_unlock(&caching_ctl->mutex); @@ -464,7 +495,8 @@ next: key.offset = 0; key.type = BTRFS_EXTENT_ITEM_KEY; - caching_ctl->progress = last; + if (wakeup) + caching_ctl->progress = last; btrfs_release_path(path); goto next; } @@ -491,7 +523,8 @@ next: if (total_found > (1024 * 1024 * 2)) { total_found = 0; - wake_up(&caching_ctl->wait); + if (wakeup) + wake_up(&caching_ctl->wait); } } path->slots[0]++; @@ -501,13 +534,27 @@ next: total_found += add_new_free_space(block_group, fs_info, last, block_group->key.objectid + block_group->key.offset); - caching_ctl->progress = (u64)-1; - spin_lock(&block_group->lock); block_group->caching_ctl = NULL; block_group->cached = BTRFS_CACHE_FINISHED; spin_unlock(&block_group->lock); +#ifdef CONFIG_BTRFS_DEBUG + if (btrfs_should_fragment_free_space(extent_root, block_group)) { + u64 bytes_used; + + spin_lock(&block_group->space_info->lock); + spin_lock(&block_group->lock); + bytes_used = block_group->key.offset - + btrfs_block_group_used(&block_group->item); + block_group->space_info->bytes_used += bytes_used >> 1; + spin_unlock(&block_group->lock); + spin_unlock(&block_group->space_info->lock); + fragment_free_space(extent_root, block_group); + } +#endif + + caching_ctl->progress = (u64)-1; err: btrfs_free_path(path); up_read(&fs_info->commit_root_sem); @@ -607,6 +654,22 @@ static int cache_block_group(struct btrfs_block_group_cache *cache, } } spin_unlock(&cache->lock); +#ifdef CONFIG_BTRFS_DEBUG + if (ret == 1 && + btrfs_should_fragment_free_space(fs_info->extent_root, + cache)) { + u64 bytes_used; + + spin_lock(&cache->space_info->lock); + spin_lock(&cache->lock); + bytes_used = cache->key.offset - + btrfs_block_group_used(&cache->item); + cache->space_info->bytes_used += bytes_used >> 1; + spin_unlock(&cache->lock); + spin_unlock(&cache->space_info->lock); + fragment_free_space(fs_info->extent_root, cache); + } +#endif mutex_unlock(&caching_ctl->mutex); wake_up(&caching_ctl->wait); @@ -2009,8 +2072,7 @@ int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr, int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 bytenr, u64 num_bytes, u64 parent, - u64 root_objectid, u64 owner, u64 offset, - int no_quota) + u64 root_objectid, u64 owner, u64 offset) { int ret; struct btrfs_fs_info *fs_info = root->fs_info; @@ -2022,12 +2084,12 @@ int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, ret = btrfs_add_delayed_tree_ref(fs_info, trans, bytenr, num_bytes, parent, root_objectid, (int)owner, - BTRFS_ADD_DELAYED_REF, NULL, no_quota); + BTRFS_ADD_DELAYED_REF, NULL); } else { ret = btrfs_add_delayed_data_ref(fs_info, trans, bytenr, - num_bytes, - parent, root_objectid, owner, offset, - BTRFS_ADD_DELAYED_REF, NULL, no_quota); + num_bytes, parent, root_objectid, + owner, offset, 0, + BTRFS_ADD_DELAYED_REF, NULL); } return ret; } @@ -2048,15 +2110,11 @@ static int __btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, u64 num_bytes = node->num_bytes; u64 refs; int ret; - int no_quota = node->no_quota; path = btrfs_alloc_path(); if (!path) return -ENOMEM; - if (!is_fstree(root_objectid) || !root->fs_info->quota_enabled) - no_quota = 1; - path->reada = 1; path->leave_spinning = 1; /* this will setup the path even if it fails to insert the back ref */ @@ -2291,8 +2349,7 @@ static int run_delayed_tree_ref(struct btrfs_trans_handle *trans, parent, ref_root, extent_op->flags_to_set, &extent_op->key, - ref->level, &ins, - node->no_quota); + ref->level, &ins); } else if (node->action == BTRFS_ADD_DELAYED_REF) { ret = __btrfs_inc_extent_ref(trans, root, node, parent, ref_root, @@ -2345,6 +2402,11 @@ static int run_one_delayed_ref(struct btrfs_trans_handle *trans, node->num_bytes); } } + + /* Also free its reserved qgroup space */ + btrfs_qgroup_free_delayed_ref(root->fs_info, + head->qgroup_ref_root, + head->qgroup_reserved); return ret; } @@ -2433,7 +2495,21 @@ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans, } } + /* + * We need to try and merge add/drops of the same ref since we + * can run into issues with relocate dropping the implicit ref + * and then it being added back again before the drop can + * finish. If we merged anything we need to re-loop so we can + * get a good ref. + * Or we can get node references of the same type that weren't + * merged when created due to bumps in the tree mod seq, and + * we need to merge them to prevent adding an inline extent + * backref before dropping it (triggering a BUG_ON at + * insert_inline_extent_backref()). + */ spin_lock(&locked_ref->lock); + btrfs_merge_delayed_refs(trans, fs_info, delayed_refs, + locked_ref); /* * locked_ref is the head node, so we have to go one @@ -2828,6 +2904,7 @@ int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_head *head; int ret; int run_all = count == (unsigned long)-1; + bool can_flush_pending_bgs = trans->can_flush_pending_bgs; /* We'll clean this up in btrfs_cleanup_transaction */ if (trans->aborted) @@ -2844,6 +2921,7 @@ again: #ifdef SCRAMBLE_DELAYED_REFS delayed_refs->run_delayed_start = find_middle(&delayed_refs->root); #endif + trans->can_flush_pending_bgs = false; ret = __btrfs_run_delayed_refs(trans, root, count); if (ret < 0) { btrfs_abort_transaction(trans, root, ret); @@ -2893,6 +2971,7 @@ again: } out: assert_qgroups_uptodate(trans); + trans->can_flush_pending_bgs = can_flush_pending_bgs; return 0; } @@ -3106,7 +3185,7 @@ static int __btrfs_mod_ref(struct btrfs_trans_handle *trans, int level; int ret = 0; int (*process_func)(struct btrfs_trans_handle *, struct btrfs_root *, - u64, u64, u64, u64, u64, u64, int); + u64, u64, u64, u64, u64, u64); if (btrfs_test_is_dummy_root(root)) @@ -3147,15 +3226,14 @@ static int __btrfs_mod_ref(struct btrfs_trans_handle *trans, key.offset -= btrfs_file_extent_offset(buf, fi); ret = process_func(trans, root, bytenr, num_bytes, parent, ref_root, key.objectid, - key.offset, 1); + key.offset); if (ret) goto fail; } else { bytenr = btrfs_node_blockptr(buf, i); num_bytes = root->nodesize; ret = process_func(trans, root, bytenr, num_bytes, - parent, ref_root, level - 1, 0, - 1); + parent, ref_root, level - 1, 0); if (ret) goto fail; } @@ -3336,6 +3414,15 @@ again: spin_unlock(&block_group->lock); /* + * We hit an ENOSPC when setting up the cache in this transaction, just + * skip doing the setup, we've already cleared the cache so we're safe. + */ + if (test_bit(BTRFS_TRANS_CACHE_ENOSPC, &trans->transaction->flags)) { + ret = -ENOSPC; + goto out_put; + } + + /* * Try to preallocate enough space based on how big the block group is. * Keep in mind this has to include any pinned space which could end up * taking up quite a bit since it's not folded into the other space @@ -3348,16 +3435,26 @@ again: num_pages *= 16; num_pages *= PAGE_CACHE_SIZE; - ret = btrfs_check_data_free_space(inode, num_pages, num_pages); + ret = btrfs_check_data_free_space(inode, 0, num_pages); if (ret) goto out_put; ret = btrfs_prealloc_file_range_trans(inode, trans, 0, 0, num_pages, num_pages, num_pages, &alloc_hint); + /* + * Our cache requires contiguous chunks so that we don't modify a bunch + * of metadata or split extents when writing the cache out, which means + * we can enospc if we are heavily fragmented in addition to just normal + * out of space conditions. So if we hit this just skip setting up any + * other block groups for this transaction, maybe we'll unpin enough + * space the next time around. + */ if (!ret) dcs = BTRFS_DC_SETUP; - btrfs_free_reserved_data_space(inode, num_pages); + else if (ret == -ENOSPC) + set_bit(BTRFS_TRANS_CACHE_ENOSPC, &trans->transaction->flags); + btrfs_free_reserved_data_space(inode, 0, num_pages); out_put: iput(inode); @@ -3742,10 +3839,8 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags, found->bytes_reserved = 0; found->bytes_readonly = 0; found->bytes_may_use = 0; - if (total_bytes > 0) - found->full = 0; - else - found->full = 1; + found->full = 0; + found->max_extent_size = 0; found->force_alloc = CHUNK_ALLOC_NO_FORCE; found->chunk_alloc = 0; found->flush = 0; @@ -3822,7 +3917,8 @@ static u64 btrfs_reduce_alloc_profile(struct btrfs_root *root, u64 flags) { u64 num_devices = root->fs_info->fs_devices->rw_devices; u64 target; - u64 tmp; + u64 raid_type; + u64 allowed = 0; /* * see if restripe for this chunk_type is in progress, if so @@ -3840,31 +3936,26 @@ static u64 btrfs_reduce_alloc_profile(struct btrfs_root *root, u64 flags) spin_unlock(&root->fs_info->balance_lock); /* First, mask out the RAID levels which aren't possible */ - if (num_devices == 1) - flags &= ~(BTRFS_BLOCK_GROUP_RAID1 | BTRFS_BLOCK_GROUP_RAID0 | - BTRFS_BLOCK_GROUP_RAID5); - if (num_devices < 3) - flags &= ~BTRFS_BLOCK_GROUP_RAID6; - if (num_devices < 4) - flags &= ~BTRFS_BLOCK_GROUP_RAID10; - - tmp = flags & (BTRFS_BLOCK_GROUP_DUP | BTRFS_BLOCK_GROUP_RAID0 | - BTRFS_BLOCK_GROUP_RAID1 | BTRFS_BLOCK_GROUP_RAID5 | - BTRFS_BLOCK_GROUP_RAID6 | BTRFS_BLOCK_GROUP_RAID10); - flags &= ~tmp; - - if (tmp & BTRFS_BLOCK_GROUP_RAID6) - tmp = BTRFS_BLOCK_GROUP_RAID6; - else if (tmp & BTRFS_BLOCK_GROUP_RAID5) - tmp = BTRFS_BLOCK_GROUP_RAID5; - else if (tmp & BTRFS_BLOCK_GROUP_RAID10) - tmp = BTRFS_BLOCK_GROUP_RAID10; - else if (tmp & BTRFS_BLOCK_GROUP_RAID1) - tmp = BTRFS_BLOCK_GROUP_RAID1; - else if (tmp & BTRFS_BLOCK_GROUP_RAID0) - tmp = BTRFS_BLOCK_GROUP_RAID0; - - return extended_to_chunk(flags | tmp); + for (raid_type = 0; raid_type < BTRFS_NR_RAID_TYPES; raid_type++) { + if (num_devices >= btrfs_raid_array[raid_type].devs_min) + allowed |= btrfs_raid_group[raid_type]; + } + allowed &= flags; + + if (allowed & BTRFS_BLOCK_GROUP_RAID6) + allowed = BTRFS_BLOCK_GROUP_RAID6; + else if (allowed & BTRFS_BLOCK_GROUP_RAID5) + allowed = BTRFS_BLOCK_GROUP_RAID5; + else if (allowed & BTRFS_BLOCK_GROUP_RAID10) + allowed = BTRFS_BLOCK_GROUP_RAID10; + else if (allowed & BTRFS_BLOCK_GROUP_RAID1) + allowed = BTRFS_BLOCK_GROUP_RAID1; + else if (allowed & BTRFS_BLOCK_GROUP_RAID0) + allowed = BTRFS_BLOCK_GROUP_RAID0; + + flags &= ~BTRFS_BLOCK_GROUP_PROFILE_MASK; + + return extended_to_chunk(flags | allowed); } static u64 get_alloc_profile(struct btrfs_root *root, u64 orig_flags) @@ -3903,11 +3994,7 @@ u64 btrfs_get_alloc_profile(struct btrfs_root *root, int data) return ret; } -/* - * This will check the space that the inode allocates from to make sure we have - * enough space for bytes. - */ -int btrfs_check_data_free_space(struct inode *inode, u64 bytes, u64 write_bytes) +int btrfs_alloc_data_chunk_ondemand(struct inode *inode, u64 bytes) { struct btrfs_space_info *data_sinfo; struct btrfs_root *root = BTRFS_I(inode)->root; @@ -4006,7 +4093,8 @@ commit_trans: if (IS_ERR(trans)) return PTR_ERR(trans); if (have_pinned_space >= 0 || - trans->transaction->have_free_bgs || + test_bit(BTRFS_TRANS_HAVE_FREE_BGS, + &trans->transaction->flags) || need_commit > 0) { ret = btrfs_commit_transaction(trans, root); if (ret) @@ -4028,38 +4116,86 @@ commit_trans: data_sinfo->flags, bytes, 1); return -ENOSPC; } - ret = btrfs_qgroup_reserve(root, write_bytes); - if (ret) - goto out; data_sinfo->bytes_may_use += bytes; trace_btrfs_space_reservation(root->fs_info, "space_info", data_sinfo->flags, bytes, 1); -out: spin_unlock(&data_sinfo->lock); return ret; } /* - * Called if we need to clear a data reservation for this inode. + * New check_data_free_space() with ability for precious data reservation + * Will replace old btrfs_check_data_free_space(), but for patch split, + * add a new function first and then replace it. */ -void btrfs_free_reserved_data_space(struct inode *inode, u64 bytes) +int btrfs_check_data_free_space(struct inode *inode, u64 start, u64 len) +{ + struct btrfs_root *root = BTRFS_I(inode)->root; + int ret; + + /* align the range */ + len = round_up(start + len, root->sectorsize) - + round_down(start, root->sectorsize); + start = round_down(start, root->sectorsize); + + ret = btrfs_alloc_data_chunk_ondemand(inode, len); + if (ret < 0) + return ret; + + /* + * Use new btrfs_qgroup_reserve_data to reserve precious data space + * + * TODO: Find a good method to avoid reserve data space for NOCOW + * range, but don't impact performance on quota disable case. + */ + ret = btrfs_qgroup_reserve_data(inode, start, len); + return ret; +} + +/* + * Called if we need to clear a data reservation for this inode + * Normally in a error case. + * + * This one will *NOT* use accurate qgroup reserved space API, just for case + * which we can't sleep and is sure it won't affect qgroup reserved space. + * Like clear_bit_hook(). + */ +void btrfs_free_reserved_data_space_noquota(struct inode *inode, u64 start, + u64 len) { struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_space_info *data_sinfo; - /* make sure bytes are sectorsize aligned */ - bytes = ALIGN(bytes, root->sectorsize); + /* Make sure the range is aligned to sectorsize */ + len = round_up(start + len, root->sectorsize) - + round_down(start, root->sectorsize); + start = round_down(start, root->sectorsize); data_sinfo = root->fs_info->data_sinfo; spin_lock(&data_sinfo->lock); - WARN_ON(data_sinfo->bytes_may_use < bytes); - data_sinfo->bytes_may_use -= bytes; + if (WARN_ON(data_sinfo->bytes_may_use < len)) + data_sinfo->bytes_may_use = 0; + else + data_sinfo->bytes_may_use -= len; trace_btrfs_space_reservation(root->fs_info, "space_info", - data_sinfo->flags, bytes, 0); + data_sinfo->flags, len, 0); spin_unlock(&data_sinfo->lock); } +/* + * Called if we need to clear a data reservation for this inode + * Normally in a error case. + * + * This one will handle the per-indoe data rsv map for accurate reserved + * space framework. + */ +void btrfs_free_reserved_data_space(struct inode *inode, u64 start, u64 len) +{ + btrfs_free_reserved_data_space_noquota(inode, start, len); + btrfs_qgroup_free_data(inode, start, len); +} + static void force_metadata_allocation(struct btrfs_fs_info *info) { struct list_head *head = &info->space_info; @@ -4309,7 +4445,8 @@ out: * the block groups that were made dirty during the lifetime of the * transaction. */ - if (trans->chunk_bytes_reserved >= (2 * 1024 * 1024ull)) { + if (trans->can_flush_pending_bgs && + trans->chunk_bytes_reserved >= (2 * 1024 * 1024ull)) { btrfs_create_pending_block_groups(trans, trans->root); btrfs_trans_release_chunk_metadata(trans); } @@ -4890,13 +5027,9 @@ static struct btrfs_block_rsv *get_block_rsv( { struct btrfs_block_rsv *block_rsv = NULL; - if (test_bit(BTRFS_ROOT_REF_COWS, &root->state)) - block_rsv = trans->block_rsv; - - if (root == root->fs_info->csum_root && trans->adding_csums) - block_rsv = trans->block_rsv; - - if (root == root->fs_info->uuid_root) + if (test_bit(BTRFS_ROOT_REF_COWS, &root->state) || + (root == root->fs_info->csum_root && trans->adding_csums) || + (root == root->fs_info->uuid_root)) block_rsv = trans->block_rsv; if (!block_rsv) @@ -5339,7 +5472,7 @@ int btrfs_subvolume_reserve_metadata(struct btrfs_root *root, if (root->fs_info->quota_enabled) { /* One for parent inode, two for dir entries */ num_bytes = 3 * root->nodesize; - ret = btrfs_qgroup_reserve(root, num_bytes); + ret = btrfs_qgroup_reserve_meta(root, num_bytes); if (ret) return ret; } else { @@ -5357,10 +5490,8 @@ int btrfs_subvolume_reserve_metadata(struct btrfs_root *root, if (ret == -ENOSPC && use_global_rsv) ret = btrfs_block_rsv_migrate(global_rsv, rsv, num_bytes); - if (ret) { - if (*qgroup_reserved) - btrfs_qgroup_free(root, *qgroup_reserved); - } + if (ret && *qgroup_reserved) + btrfs_qgroup_free_meta(root, *qgroup_reserved); return ret; } @@ -5521,15 +5652,15 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes) spin_unlock(&BTRFS_I(inode)->lock); if (root->fs_info->quota_enabled) { - ret = btrfs_qgroup_reserve(root, nr_extents * root->nodesize); + ret = btrfs_qgroup_reserve_meta(root, + nr_extents * root->nodesize); if (ret) goto out_fail; } ret = reserve_metadata_bytes(root, block_rsv, to_reserve, flush); if (unlikely(ret)) { - if (root->fs_info->quota_enabled) - btrfs_qgroup_free(root, nr_extents * root->nodesize); + btrfs_qgroup_free_meta(root, nr_extents * root->nodesize); goto out_fail; } @@ -5652,41 +5783,48 @@ void btrfs_delalloc_release_metadata(struct inode *inode, u64 num_bytes) } /** - * btrfs_delalloc_reserve_space - reserve data and metadata space for delalloc + * btrfs_delalloc_reserve_space - reserve data and metadata space for + * delalloc * @inode: inode we're writing to - * @num_bytes: the number of bytes we want to allocate + * @start: start range we are writing to + * @len: how long the range we are writing to + * + * TODO: This function will finally replace old btrfs_delalloc_reserve_space() * * This will do the following things * - * o reserve space in the data space info for num_bytes - * o reserve space in the metadata space info based on number of outstanding + * o reserve space in data space info for num bytes + * and reserve precious corresponding qgroup space + * (Done in check_data_free_space) + * + * o reserve space for metadata space, based on the number of outstanding * extents and how much csums will be needed - * o add to the inodes ->delalloc_bytes + * also reserve metadata space in a per root over-reserve method. + * o add to the inodes->delalloc_bytes * o add it to the fs_info's delalloc inodes list. + * (Above 3 all done in delalloc_reserve_metadata) * - * This will return 0 for success and -ENOSPC if there is no space left. + * Return 0 for success + * Return <0 for error(-ENOSPC or -EQUOT) */ -int btrfs_delalloc_reserve_space(struct inode *inode, u64 num_bytes) +int btrfs_delalloc_reserve_space(struct inode *inode, u64 start, u64 len) { int ret; - ret = btrfs_check_data_free_space(inode, num_bytes, num_bytes); - if (ret) - return ret; - - ret = btrfs_delalloc_reserve_metadata(inode, num_bytes); - if (ret) { - btrfs_free_reserved_data_space(inode, num_bytes); + ret = btrfs_check_data_free_space(inode, start, len); + if (ret < 0) return ret; - } - - return 0; + ret = btrfs_delalloc_reserve_metadata(inode, len); + if (ret < 0) + btrfs_free_reserved_data_space(inode, start, len); + return ret; } /** * btrfs_delalloc_release_space - release data and metadata space for delalloc * @inode: inode we're releasing space for - * @num_bytes: the number of bytes we want to free up + * @start: start position of the space already reserved + * @len: the len of the space already reserved * * This must be matched with a call to btrfs_delalloc_reserve_space. This is * called in the case that we don't need the metadata AND data reservations @@ -5695,11 +5833,12 @@ int btrfs_delalloc_reserve_space(struct inode *inode, u64 num_bytes) * This function will release the metadata space that was not used and will * decrement ->delalloc_bytes and remove it from the fs_info delalloc_inodes * list if there are no delalloc bytes left. + * Also it will handle the qgroup reserved space. */ -void btrfs_delalloc_release_space(struct inode *inode, u64 num_bytes) +void btrfs_delalloc_release_space(struct inode *inode, u64 start, u64 len) { - btrfs_delalloc_release_metadata(inode, num_bytes); - btrfs_free_reserved_data_space(inode, num_bytes); + btrfs_delalloc_release_metadata(inode, len); + btrfs_free_reserved_data_space(inode, start, len); } static int update_block_group(struct btrfs_trans_handle *trans, @@ -6064,6 +6203,34 @@ void btrfs_prepare_extent_commit(struct btrfs_trans_handle *trans, update_global_block_rsv(fs_info); } +/* + * Returns the free cluster for the given space info and sets empty_cluster to + * what it should be based on the mount options. + */ +static struct btrfs_free_cluster * +fetch_cluster_info(struct btrfs_root *root, struct btrfs_space_info *space_info, + u64 *empty_cluster) +{ + struct btrfs_free_cluster *ret = NULL; + bool ssd = btrfs_test_opt(root, SSD); + + *empty_cluster = 0; + if (btrfs_mixed_space_info(space_info)) + return ret; + + if (ssd) + *empty_cluster = 2 * 1024 * 1024; + if (space_info->flags & BTRFS_BLOCK_GROUP_METADATA) { + ret = &root->fs_info->meta_alloc_cluster; + if (!ssd) + *empty_cluster = 64 * 1024; + } else if ((space_info->flags & BTRFS_BLOCK_GROUP_DATA) && ssd) { + ret = &root->fs_info->data_alloc_cluster; + } + + return ret; +} + static int unpin_extent_range(struct btrfs_root *root, u64 start, u64 end, const bool return_free_space) { @@ -6071,7 +6238,10 @@ static int unpin_extent_range(struct btrfs_root *root, u64 start, u64 end, struct btrfs_block_group_cache *cache = NULL; struct btrfs_space_info *space_info; struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv; + struct btrfs_free_cluster *cluster = NULL; u64 len; + u64 total_unpinned = 0; + u64 empty_cluster = 0; bool readonly; while (start <= end) { @@ -6080,8 +6250,14 @@ static int unpin_extent_range(struct btrfs_root *root, u64 start, u64 end, start >= cache->key.objectid + cache->key.offset) { if (cache) btrfs_put_block_group(cache); + total_unpinned = 0; cache = btrfs_lookup_block_group(fs_info, start); BUG_ON(!cache); /* Logic error */ + + cluster = fetch_cluster_info(root, + cache->space_info, + &empty_cluster); + empty_cluster <<= 1; } len = cache->key.objectid + cache->key.offset - start; @@ -6094,12 +6270,27 @@ static int unpin_extent_range(struct btrfs_root *root, u64 start, u64 end, } start += len; + total_unpinned += len; space_info = cache->space_info; + /* + * If this space cluster has been marked as fragmented and we've + * unpinned enough in this block group to potentially allow a + * cluster to be created inside of it go ahead and clear the + * fragmented check. + */ + if (cluster && cluster->fragmented && + total_unpinned > empty_cluster) { + spin_lock(&cluster->lock); + cluster->fragmented = 0; + spin_unlock(&cluster->lock); + } + spin_lock(&space_info->lock); spin_lock(&cache->lock); cache->pinned -= len; space_info->bytes_pinned -= len; + space_info->max_extent_size = 0; percpu_counter_add(&space_info->total_bytes_pinned, -len); if (cache->ro) { space_info->bytes_readonly += len; @@ -6232,7 +6423,6 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, int extent_slot = 0; int found_extent = 0; int num_to_del = 1; - int no_quota = node->no_quota; u32 item_size; u64 refs; u64 bytenr = node->bytenr; @@ -6241,9 +6431,6 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, bool skinny_metadata = btrfs_fs_incompat(root->fs_info, SKINNY_METADATA); - if (!info->quota_enabled || !is_fstree(root_objectid)) - no_quota = 1; - path = btrfs_alloc_path(); if (!path) return -ENOMEM; @@ -6569,7 +6756,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, buf->start, buf->len, parent, root->root_key.objectid, btrfs_header_level(buf), - BTRFS_DROP_DELAYED_REF, NULL, 0); + BTRFS_DROP_DELAYED_REF, NULL); BUG_ON(ret); /* -ENOMEM */ } @@ -6617,7 +6804,7 @@ out: /* Can return -ENOMEM */ int btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 bytenr, u64 num_bytes, u64 parent, u64 root_objectid, - u64 owner, u64 offset, int no_quota) + u64 owner, u64 offset) { int ret; struct btrfs_fs_info *fs_info = root->fs_info; @@ -6640,13 +6827,13 @@ int btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_root *root, ret = btrfs_add_delayed_tree_ref(fs_info, trans, bytenr, num_bytes, parent, root_objectid, (int)owner, - BTRFS_DROP_DELAYED_REF, NULL, no_quota); + BTRFS_DROP_DELAYED_REF, NULL); } else { ret = btrfs_add_delayed_data_ref(fs_info, trans, bytenr, num_bytes, parent, root_objectid, owner, - offset, BTRFS_DROP_DELAYED_REF, - NULL, no_quota); + offset, 0, + BTRFS_DROP_DELAYED_REF, NULL); } return ret; } @@ -6832,7 +7019,7 @@ static noinline int find_free_extent(struct btrfs_root *orig_root, struct btrfs_block_group_cache *block_group = NULL; u64 search_start = 0; u64 max_extent_size = 0; - int empty_cluster = 2 * 1024 * 1024; + u64 empty_cluster = 0; struct btrfs_space_info *space_info; int loop = 0; int index = __get_raid_index(flags); @@ -6842,6 +7029,8 @@ static noinline int find_free_extent(struct btrfs_root *orig_root, bool failed_alloc = false; bool use_cluster = true; bool have_caching_bg = false; + bool orig_have_caching_bg = false; + bool full_search = false; WARN_ON(num_bytes < root->sectorsize); ins->type = BTRFS_EXTENT_ITEM_KEY; @@ -6857,36 +7046,47 @@ static noinline int find_free_extent(struct btrfs_root *orig_root, } /* - * If the space info is for both data and metadata it means we have a - * small filesystem and we can't use the clustering stuff. + * If our free space is heavily fragmented we may not be able to make + * big contiguous allocations, so instead of doing the expensive search + * for free space, simply return ENOSPC with our max_extent_size so we + * can go ahead and search for a more manageable chunk. + * + * If our max_extent_size is large enough for our allocation simply + * disable clustering since we will likely not be able to find enough + * space to create a cluster and induce latency trying. */ - if (btrfs_mixed_space_info(space_info)) - use_cluster = false; - - if (flags & BTRFS_BLOCK_GROUP_METADATA && use_cluster) { - last_ptr = &root->fs_info->meta_alloc_cluster; - if (!btrfs_test_opt(root, SSD)) - empty_cluster = 64 * 1024; - } - - if ((flags & BTRFS_BLOCK_GROUP_DATA) && use_cluster && - btrfs_test_opt(root, SSD)) { - last_ptr = &root->fs_info->data_alloc_cluster; + if (unlikely(space_info->max_extent_size)) { + spin_lock(&space_info->lock); + if (space_info->max_extent_size && + num_bytes > space_info->max_extent_size) { + ins->offset = space_info->max_extent_size; + spin_unlock(&space_info->lock); + return -ENOSPC; + } else if (space_info->max_extent_size) { + use_cluster = false; + } + spin_unlock(&space_info->lock); } + last_ptr = fetch_cluster_info(orig_root, space_info, &empty_cluster); if (last_ptr) { spin_lock(&last_ptr->lock); if (last_ptr->block_group) hint_byte = last_ptr->window_start; + if (last_ptr->fragmented) { + /* + * We still set window_start so we can keep track of the + * last place we found an allocation to try and save + * some time. + */ + hint_byte = last_ptr->window_start; + use_cluster = false; + } spin_unlock(&last_ptr->lock); } search_start = max(search_start, first_logical_byte(root, 0)); search_start = max(search_start, hint_byte); - - if (!last_ptr) - empty_cluster = 0; - if (search_start == hint_byte) { block_group = btrfs_lookup_block_group(root->fs_info, search_start); @@ -6921,6 +7121,8 @@ static noinline int find_free_extent(struct btrfs_root *orig_root, } search: have_caching_bg = false; + if (index == 0 || index == __get_raid_index(flags)) + full_search = true; down_read(&space_info->groups_sem); list_for_each_entry(block_group, &space_info->block_groups[index], list) { @@ -6954,6 +7156,7 @@ search: have_block_group: cached = block_group_cache_done(block_group); if (unlikely(!cached)) { + have_caching_bg = true; ret = cache_block_group(block_group, 0); BUG_ON(ret < 0); ret = 0; @@ -6968,7 +7171,7 @@ have_block_group: * Ok we want to try and use the cluster allocator, so * lets look there */ - if (last_ptr) { + if (last_ptr && use_cluster) { struct btrfs_block_group_cache *used_block_group; unsigned long aligned_cluster; /* @@ -7094,6 +7297,16 @@ refill_cluster: } unclustered_alloc: + /* + * We are doing an unclustered alloc, set the fragmented flag so + * we don't bother trying to setup a cluster again until we get + * more space. + */ + if (unlikely(last_ptr)) { + spin_lock(&last_ptr->lock); + last_ptr->fragmented = 1; + spin_unlock(&last_ptr->lock); + } spin_lock(&block_group->free_space_ctl->tree_lock); if (cached && block_group->free_space_ctl->free_space < @@ -7126,8 +7339,6 @@ unclustered_alloc: failed_alloc = true; goto have_block_group; } else if (!offset) { - if (!cached) - have_caching_bg = true; goto loop; } checks: @@ -7168,6 +7379,10 @@ loop: } up_read(&space_info->groups_sem); + if ((loop == LOOP_CACHING_NOWAIT) && have_caching_bg + && !orig_have_caching_bg) + orig_have_caching_bg = true; + if (!ins->objectid && loop >= LOOP_CACHING_WAIT && have_caching_bg) goto search; @@ -7184,7 +7399,20 @@ loop: */ if (!ins->objectid && loop < LOOP_NO_EMPTY_SIZE) { index = 0; - loop++; + if (loop == LOOP_CACHING_NOWAIT) { + /* + * We want to skip the LOOP_CACHING_WAIT step if we + * don't have any unached bgs and we've alrelady done a + * full search through. + */ + if (orig_have_caching_bg || !full_search) + loop = LOOP_CACHING_WAIT; + else + loop = LOOP_ALLOC_CHUNK; + } else { + loop++; + } + if (loop == LOOP_ALLOC_CHUNK) { struct btrfs_trans_handle *trans; int exist = 0; @@ -7202,6 +7430,15 @@ loop: ret = do_chunk_alloc(trans, root, flags, CHUNK_ALLOC_FORCE); + + /* + * If we can't allocate a new chunk we've already looped + * through at least once, move on to the NO_EMPTY_SIZE + * case. + */ + if (ret == -ENOSPC) + loop = LOOP_NO_EMPTY_SIZE; + /* * Do not bail out on ENOSPC since we * can do more things. @@ -7218,6 +7455,15 @@ loop: } if (loop == LOOP_NO_EMPTY_SIZE) { + /* + * Don't loop again if we already have no empty_size and + * no empty_cluster. + */ + if (empty_size == 0 && + empty_cluster == 0) { + ret = -ENOSPC; + goto out; + } empty_size = 0; empty_cluster = 0; } @@ -7226,11 +7472,20 @@ loop: } else if (!ins->objectid) { ret = -ENOSPC; } else if (ins->objectid) { + if (!use_cluster && last_ptr) { + spin_lock(&last_ptr->lock); + last_ptr->window_start = ins->objectid; + spin_unlock(&last_ptr->lock); + } ret = 0; } out: - if (ret == -ENOSPC) + if (ret == -ENOSPC) { + spin_lock(&space_info->lock); + space_info->max_extent_size = max_extent_size; + spin_unlock(&space_info->lock); ins->offset = max_extent_size; + } return ret; } @@ -7279,7 +7534,7 @@ int btrfs_reserve_extent(struct btrfs_root *root, u64 empty_size, u64 hint_byte, struct btrfs_key *ins, int is_data, int delalloc) { - bool final_tried = false; + bool final_tried = num_bytes == min_alloc_size; u64 flags; int ret; @@ -7428,8 +7683,7 @@ static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 parent, u64 root_objectid, u64 flags, struct btrfs_disk_key *key, - int level, struct btrfs_key *ins, - int no_quota) + int level, struct btrfs_key *ins) { int ret; struct btrfs_fs_info *fs_info = root->fs_info; @@ -7510,7 +7764,8 @@ static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans, int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 root_objectid, u64 owner, - u64 offset, struct btrfs_key *ins) + u64 offset, u64 ram_bytes, + struct btrfs_key *ins) { int ret; @@ -7519,7 +7774,8 @@ int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans, ret = btrfs_add_delayed_data_ref(root->fs_info, trans, ins->objectid, ins->offset, 0, root_objectid, owner, offset, - BTRFS_ADD_DELAYED_EXTENT, NULL, 0); + ram_bytes, BTRFS_ADD_DELAYED_EXTENT, + NULL); return ret; } @@ -7733,7 +7989,7 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans, ins.objectid, ins.offset, parent, root_objectid, level, BTRFS_ADD_DELAYED_EXTENT, - extent_op, 0); + extent_op); if (ret) goto out_free_delayed; } @@ -8274,14 +8530,15 @@ skip: ret = account_shared_subtree(trans, root, next, generation, level - 1); if (ret) { - printk_ratelimited(KERN_ERR "BTRFS: %s Error " + btrfs_err_rl(root->fs_info, + "Error " "%d accounting shared subtree. Quota " - "is out of sync, rescan required.\n", - root->fs_info->sb->s_id, ret); + "is out of sync, rescan required.", + ret); } } ret = btrfs_free_extent(trans, root, bytenr, blocksize, parent, - root->root_key.objectid, level - 1, 0, 0); + root->root_key.objectid, level - 1, 0); BUG_ON(ret); /* -ENOMEM */ } btrfs_tree_unlock(next); @@ -8366,10 +8623,11 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans, BUG_ON(ret); /* -ENOMEM */ ret = account_leaf_items(trans, root, eb); if (ret) { - printk_ratelimited(KERN_ERR "BTRFS: %s Error " + btrfs_err_rl(root->fs_info, + "error " "%d accounting leaf items. Quota " - "is out of sync, rescan required.\n", - root->fs_info->sb->s_id, ret); + "is out of sync, rescan required.", + ret); } } /* make block locked assertion in clean_tree_block happy */ @@ -8668,7 +8926,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root, } if (test_bit(BTRFS_ROOT_IN_RADIX, &root->state)) { - btrfs_drop_and_free_fs_root(tree_root->fs_info, root); + btrfs_add_dropped_root(trans, root); } else { free_extent_buffer(root->node); free_extent_buffer(root->commit_root); @@ -8691,7 +8949,7 @@ out: if (!for_reloc && root_dropped == false) btrfs_add_dead_root(root); if (err && err != -EAGAIN) - btrfs_std_error(root->fs_info, err); + btrfs_std_error(root->fs_info, err, NULL); return err; } @@ -8879,7 +9137,7 @@ again: * back off and let this transaction commit */ mutex_lock(&root->fs_info->ro_block_group_mutex); - if (trans->transaction->dirty_bg_run) { + if (test_bit(BTRFS_TRANS_DIRTY_BG_RUN, &trans->transaction->flags)) { u64 transid = trans->transid; mutex_unlock(&root->fs_info->ro_block_group_mutex); @@ -9563,7 +9821,9 @@ void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans, struct btrfs_block_group_item item; struct btrfs_key key; int ret = 0; + bool can_flush_pending_bgs = trans->can_flush_pending_bgs; + trans->can_flush_pending_bgs = false; list_for_each_entry_safe(block_group, tmp, &trans->new_bgs, bg_list) { if (ret) goto next; @@ -9584,6 +9844,7 @@ void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans, next: list_del_init(&block_group->bg_list); } + trans->can_flush_pending_bgs = can_flush_pending_bgs; } int btrfs_make_block_group(struct btrfs_trans_handle *trans, @@ -9626,6 +9887,14 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, free_excluded_extents(root, cache); +#ifdef CONFIG_BTRFS_DEBUG + if (btrfs_should_fragment_free_space(root, cache)) { + u64 new_bytes_used = size - bytes_used; + + bytes_used += new_bytes_used >> 1; + fragment_free_space(root, cache); + } +#endif /* * Call to ensure the corresponding space_info object is created and * assigned to our block group, but don't update its counters just yet. @@ -10366,8 +10635,7 @@ void btrfs_end_write_no_snapshoting(struct btrfs_root *root) { percpu_counter_dec(&root->subv_writers->counter); /* - * Make sure counter is updated before we wake up - * waiters. + * Make sure counter is updated before we wake up waiters. */ smp_mb(); if (waitqueue_active(&root->subv_writers->wait)) diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index f1018cf..9abe187 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -96,8 +96,8 @@ static inline void __btrfs_debug_check_extent_io_range(const char *caller, inode = tree->mapping->host; isize = i_size_read(inode); if (end >= PAGE_SIZE && (end % 2) == 0 && end != isize - 1) { - printk_ratelimited(KERN_DEBUG - "BTRFS: %s: ino %llu isize %llu odd range [%llu,%llu]\n", + btrfs_debug_rl(BTRFS_I(inode)->root->fs_info, + "%s: ino %llu isize %llu odd range [%llu,%llu]", caller, btrfs_ino(inode), isize, start, end); } } @@ -131,6 +131,25 @@ struct extent_page_data { unsigned int sync_io:1; }; +static void add_extent_changeset(struct extent_state *state, unsigned bits, + struct extent_changeset *changeset, + int set) +{ + int ret; + + if (!changeset) + return; + if (set && (state->state & bits) == bits) + return; + if (!set && (state->state & bits) == 0) + return; + changeset->bytes_changed += state->end - state->start + 1; + ret = ulist_add(changeset->range_changed, state->start, state->end, + GFP_ATOMIC); + /* ENOMEM */ + BUG_ON(ret < 0); +} + static noinline void flush_write_bio(void *data); static inline struct btrfs_fs_info * tree_fs_info(struct extent_io_tree *tree) @@ -410,7 +429,8 @@ static void clear_state_cb(struct extent_io_tree *tree, } static void set_state_bits(struct extent_io_tree *tree, - struct extent_state *state, unsigned *bits); + struct extent_state *state, unsigned *bits, + struct extent_changeset *changeset); /* * insert an extent_state struct into the tree. 'bits' are set on the @@ -426,7 +446,7 @@ static int insert_state(struct extent_io_tree *tree, struct extent_state *state, u64 start, u64 end, struct rb_node ***p, struct rb_node **parent, - unsigned *bits) + unsigned *bits, struct extent_changeset *changeset) { struct rb_node *node; @@ -436,7 +456,7 @@ static int insert_state(struct extent_io_tree *tree, state->start = start; state->end = end; - set_state_bits(tree, state, bits); + set_state_bits(tree, state, bits, changeset); node = tree_insert(&tree->state, NULL, end, &state->rb_node, p, parent); if (node) { @@ -511,7 +531,8 @@ static struct extent_state *next_state(struct extent_state *state) */ static struct extent_state *clear_state_bit(struct extent_io_tree *tree, struct extent_state *state, - unsigned *bits, int wake) + unsigned *bits, int wake, + struct extent_changeset *changeset) { struct extent_state *next; unsigned bits_to_clear = *bits & ~EXTENT_CTLBITS; @@ -522,6 +543,7 @@ static struct extent_state *clear_state_bit(struct extent_io_tree *tree, tree->dirty_bytes -= range; } clear_state_cb(tree, state, bits); + add_extent_changeset(state, bits_to_clear, changeset, 0); state->state &= ~bits_to_clear; if (wake) wake_up(&state->wq); @@ -569,10 +591,10 @@ static void extent_io_tree_panic(struct extent_io_tree *tree, int err) * * This takes the tree lock, and returns 0 on success and < 0 on error. */ -int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, - unsigned bits, int wake, int delete, - struct extent_state **cached_state, - gfp_t mask) +static int __clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, + unsigned bits, int wake, int delete, + struct extent_state **cached_state, + gfp_t mask, struct extent_changeset *changeset) { struct extent_state *state; struct extent_state *cached; @@ -594,7 +616,7 @@ int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, if (bits & (EXTENT_IOBITS | EXTENT_BOUNDARY)) clear = 1; again: - if (!prealloc && (mask & __GFP_WAIT)) { + if (!prealloc && gfpflags_allow_blocking(mask)) { /* * Don't care for allocation failure here because we might end * up not needing the pre-allocated extent state at all, which @@ -671,7 +693,8 @@ hit_next: if (err) goto out; if (state->end <= end) { - state = clear_state_bit(tree, state, &bits, wake); + state = clear_state_bit(tree, state, &bits, wake, + changeset); goto next; } goto search_again; @@ -692,13 +715,13 @@ hit_next: if (wake) wake_up(&state->wq); - clear_state_bit(tree, prealloc, &bits, wake); + clear_state_bit(tree, prealloc, &bits, wake, changeset); prealloc = NULL; goto out; } - state = clear_state_bit(tree, state, &bits, wake); + state = clear_state_bit(tree, state, &bits, wake, changeset); next: if (last_end == (u64)-1) goto out; @@ -718,7 +741,7 @@ search_again: if (start > end) goto out; spin_unlock(&tree->lock); - if (mask & __GFP_WAIT) + if (gfpflags_allow_blocking(mask)) cond_resched(); goto again; } @@ -789,7 +812,7 @@ out: static void set_state_bits(struct extent_io_tree *tree, struct extent_state *state, - unsigned *bits) + unsigned *bits, struct extent_changeset *changeset) { unsigned bits_to_set = *bits & ~EXTENT_CTLBITS; @@ -798,6 +821,7 @@ static void set_state_bits(struct extent_io_tree *tree, u64 range = state->end - state->start + 1; tree->dirty_bytes += range; } + add_extent_changeset(state, bits_to_set, changeset, 1); state->state |= bits_to_set; } @@ -835,7 +859,7 @@ static int __must_check __set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, unsigned bits, unsigned exclusive_bits, u64 *failed_start, struct extent_state **cached_state, - gfp_t mask) + gfp_t mask, struct extent_changeset *changeset) { struct extent_state *state; struct extent_state *prealloc = NULL; @@ -850,7 +874,7 @@ __set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, bits |= EXTENT_FIRST_DELALLOC; again: - if (!prealloc && (mask & __GFP_WAIT)) { + if (!prealloc && gfpflags_allow_blocking(mask)) { prealloc = alloc_extent_state(mask); BUG_ON(!prealloc); } @@ -873,7 +897,7 @@ again: prealloc = alloc_extent_state_atomic(prealloc); BUG_ON(!prealloc); err = insert_state(tree, prealloc, start, end, - &p, &parent, &bits); + &p, &parent, &bits, changeset); if (err) extent_io_tree_panic(tree, err); @@ -899,7 +923,7 @@ hit_next: goto out; } - set_state_bits(tree, state, &bits); + set_state_bits(tree, state, &bits, changeset); cache_state(state, cached_state); merge_state(tree, state); if (last_end == (u64)-1) @@ -945,7 +969,7 @@ hit_next: if (err) goto out; if (state->end <= end) { - set_state_bits(tree, state, &bits); + set_state_bits(tree, state, &bits, changeset); cache_state(state, cached_state); merge_state(tree, state); if (last_end == (u64)-1) @@ -980,7 +1004,7 @@ hit_next: * the later extent. */ err = insert_state(tree, prealloc, start, this_end, - NULL, NULL, &bits); + NULL, NULL, &bits, changeset); if (err) extent_io_tree_panic(tree, err); @@ -1008,7 +1032,7 @@ hit_next: if (err) extent_io_tree_panic(tree, err); - set_state_bits(tree, prealloc, &bits); + set_state_bits(tree, prealloc, &bits, changeset); cache_state(prealloc, cached_state); merge_state(tree, prealloc); prealloc = NULL; @@ -1028,7 +1052,7 @@ search_again: if (start > end) goto out; spin_unlock(&tree->lock); - if (mask & __GFP_WAIT) + if (gfpflags_allow_blocking(mask)) cond_resched(); goto again; } @@ -1038,7 +1062,7 @@ int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, struct extent_state **cached_state, gfp_t mask) { return __set_extent_bit(tree, start, end, bits, 0, failed_start, - cached_state, mask); + cached_state, mask, NULL); } @@ -1076,7 +1100,7 @@ int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, btrfs_debug_check_extent_io_range(tree, start, end); again: - if (!prealloc && (mask & __GFP_WAIT)) { + if (!prealloc && gfpflags_allow_blocking(mask)) { /* * Best effort, don't worry if extent state allocation fails * here for the first iteration. We might have a cached state @@ -1111,7 +1135,7 @@ again: goto out; } err = insert_state(tree, prealloc, start, end, - &p, &parent, &bits); + &p, &parent, &bits, NULL); if (err) extent_io_tree_panic(tree, err); cache_state(prealloc, cached_state); @@ -1130,9 +1154,9 @@ hit_next: * Just lock what we found and keep going */ if (state->start == start && state->end <= end) { - set_state_bits(tree, state, &bits); + set_state_bits(tree, state, &bits, NULL); cache_state(state, cached_state); - state = clear_state_bit(tree, state, &clear_bits, 0); + state = clear_state_bit(tree, state, &clear_bits, 0, NULL); if (last_end == (u64)-1) goto out; start = last_end + 1; @@ -1171,9 +1195,10 @@ hit_next: if (err) goto out; if (state->end <= end) { - set_state_bits(tree, state, &bits); + set_state_bits(tree, state, &bits, NULL); cache_state(state, cached_state); - state = clear_state_bit(tree, state, &clear_bits, 0); + state = clear_state_bit(tree, state, &clear_bits, 0, + NULL); if (last_end == (u64)-1) goto out; start = last_end + 1; @@ -1208,7 +1233,7 @@ hit_next: * the later extent. */ err = insert_state(tree, prealloc, start, this_end, - NULL, NULL, &bits); + NULL, NULL, &bits, NULL); if (err) extent_io_tree_panic(tree, err); cache_state(prealloc, cached_state); @@ -1233,9 +1258,9 @@ hit_next: if (err) extent_io_tree_panic(tree, err); - set_state_bits(tree, prealloc, &bits); + set_state_bits(tree, prealloc, &bits, NULL); cache_state(prealloc, cached_state); - clear_state_bit(tree, prealloc, &clear_bits, 0); + clear_state_bit(tree, prealloc, &clear_bits, 0, NULL); prealloc = NULL; goto out; } @@ -1253,7 +1278,7 @@ search_again: if (start > end) goto out; spin_unlock(&tree->lock); - if (mask & __GFP_WAIT) + if (gfpflags_allow_blocking(mask)) cond_resched(); first_iteration = false; goto again; @@ -1274,6 +1299,30 @@ int set_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, NULL, mask); } +int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, + unsigned bits, gfp_t mask, + struct extent_changeset *changeset) +{ + /* + * We don't support EXTENT_LOCKED yet, as current changeset will + * record any bits changed, so for EXTENT_LOCKED case, it will + * either fail with -EEXIST or changeset will record the whole + * range. + */ + BUG_ON(bits & EXTENT_LOCKED); + + return __set_extent_bit(tree, start, end, bits, 0, NULL, NULL, mask, + changeset); +} + +int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, + unsigned bits, int wake, int delete, + struct extent_state **cached, gfp_t mask) +{ + return __clear_extent_bit(tree, start, end, bits, wake, delete, + cached, mask, NULL); +} + int clear_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, unsigned bits, gfp_t mask) { @@ -1285,6 +1334,20 @@ int clear_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, return clear_extent_bit(tree, start, end, bits, wake, 0, NULL, mask); } +int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, + unsigned bits, gfp_t mask, + struct extent_changeset *changeset) +{ + /* + * Don't support EXTENT_LOCKED case, same reason as + * set_record_extent_bits(). + */ + BUG_ON(bits & EXTENT_LOCKED); + + return __clear_extent_bit(tree, start, end, bits, 0, 0, NULL, mask, + changeset); +} + int set_extent_delalloc(struct extent_io_tree *tree, u64 start, u64 end, struct extent_state **cached_state, gfp_t mask) { @@ -1343,7 +1406,7 @@ int lock_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, while (1) { err = __set_extent_bit(tree, start, end, EXTENT_LOCKED | bits, EXTENT_LOCKED, &failed_start, - cached_state, GFP_NOFS); + cached_state, GFP_NOFS, NULL); if (err == -EEXIST) { wait_extent_bit(tree, failed_start, end, EXTENT_LOCKED); start = failed_start; @@ -1365,7 +1428,7 @@ int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end) u64 failed_start; err = __set_extent_bit(tree, start, end, EXTENT_LOCKED, EXTENT_LOCKED, - &failed_start, NULL, GFP_NOFS); + &failed_start, NULL, GFP_NOFS, NULL); if (err == -EEXIST) { if (failed_start > start) clear_extent_bit(tree, start, failed_start - 1, @@ -2078,8 +2141,8 @@ int repair_io_failure(struct inode *inode, u64 start, u64 length, u64 logical, return -EIO; } - printk_ratelimited_in_rcu(KERN_INFO - "BTRFS: read error corrected: ino %llu off %llu (dev %s sector %llu)\n", + btrfs_info_rl_in_rcu(fs_info, + "read error corrected: ino %llu off %llu (dev %s sector %llu)", btrfs_ino(inode), start, rcu_str_deref(dev->name), sector); bio_put(bio); @@ -2798,7 +2861,8 @@ static int submit_extent_page(int rw, struct extent_io_tree *tree, bio_end_io_t end_io_func, int mirror_num, unsigned long prev_bio_flags, - unsigned long bio_flags) + unsigned long bio_flags, + bool force_bio_submit) { int ret = 0; struct bio *bio; @@ -2814,6 +2878,7 @@ static int submit_extent_page(int rw, struct extent_io_tree *tree, contig = bio_end_sector(bio) == sector; if (prev_bio_flags != bio_flags || !contig || + force_bio_submit || merge_bio(rw, tree, page, offset, page_size, bio, bio_flags) || bio_add_page(bio, page, page_size, offset) < page_size) { ret = submit_one_bio(rw, bio, mirror_num, @@ -2910,7 +2975,8 @@ static int __do_readpage(struct extent_io_tree *tree, get_extent_t *get_extent, struct extent_map **em_cached, struct bio **bio, int mirror_num, - unsigned long *bio_flags, int rw) + unsigned long *bio_flags, int rw, + u64 *prev_em_start) { struct inode *inode = page->mapping->host; u64 start = page_offset(page); @@ -2958,6 +3024,7 @@ static int __do_readpage(struct extent_io_tree *tree, } while (cur <= end) { unsigned long pnr = (last_byte >> PAGE_CACHE_SHIFT) + 1; + bool force_bio_submit = false; if (cur >= last_byte) { char *userpage; @@ -3008,6 +3075,49 @@ static int __do_readpage(struct extent_io_tree *tree, block_start = em->block_start; if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) block_start = EXTENT_MAP_HOLE; + + /* + * If we have a file range that points to a compressed extent + * and it's followed by a consecutive file range that points to + * to the same compressed extent (possibly with a different + * offset and/or length, so it either points to the whole extent + * or only part of it), we must make sure we do not submit a + * single bio to populate the pages for the 2 ranges because + * this makes the compressed extent read zero out the pages + * belonging to the 2nd range. Imagine the following scenario: + * + * File layout + * [0 - 8K] [8K - 24K] + * | | + * | | + * points to extent X, points to extent X, + * offset 4K, length of 8K offset 0, length 16K + * + * [extent X, compressed length = 4K uncompressed length = 16K] + * + * If the bio to read the compressed extent covers both ranges, + * it will decompress extent X into the pages belonging to the + * first range and then it will stop, zeroing out the remaining + * pages that belong to the other range that points to extent X. + * So here we make sure we submit 2 bios, one for the first + * range and another one for the third range. Both will target + * the same physical extent from disk, but we can't currently + * make the compressed bio endio callback populate the pages + * for both ranges because each compressed bio is tightly + * coupled with a single extent map, and each range can have + * an extent map with a different offset value relative to the + * uncompressed data of our extent and different lengths. This + * is a corner case so we prioritize correctness over + * non-optimal behavior (submitting 2 bios for the same extent). + */ + if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags) && + prev_em_start && *prev_em_start != (u64)-1 && + *prev_em_start != em->orig_start) + force_bio_submit = true; + + if (prev_em_start) + *prev_em_start = em->orig_start; + free_extent_map(em); em = NULL; @@ -3023,8 +3133,12 @@ static int __do_readpage(struct extent_io_tree *tree, set_extent_uptodate(tree, cur, cur + iosize - 1, &cached, GFP_NOFS); - unlock_extent_cached(tree, cur, cur + iosize - 1, - &cached, GFP_NOFS); + if (parent_locked) + free_extent_state(cached); + else + unlock_extent_cached(tree, cur, + cur + iosize - 1, + &cached, GFP_NOFS); cur = cur + iosize; pg_offset += iosize; continue; @@ -3057,7 +3171,8 @@ static int __do_readpage(struct extent_io_tree *tree, bdev, bio, pnr, end_bio_extent_readpage, mirror_num, *bio_flags, - this_bio_flag); + this_bio_flag, + force_bio_submit); if (!ret) { nr++; *bio_flags = this_bio_flag; @@ -3084,7 +3199,8 @@ static inline void __do_contiguous_readpages(struct extent_io_tree *tree, get_extent_t *get_extent, struct extent_map **em_cached, struct bio **bio, int mirror_num, - unsigned long *bio_flags, int rw) + unsigned long *bio_flags, int rw, + u64 *prev_em_start) { struct inode *inode; struct btrfs_ordered_extent *ordered; @@ -3104,7 +3220,7 @@ static inline void __do_contiguous_readpages(struct extent_io_tree *tree, for (index = 0; index < nr_pages; index++) { __do_readpage(tree, pages[index], get_extent, em_cached, bio, - mirror_num, bio_flags, rw); + mirror_num, bio_flags, rw, prev_em_start); page_cache_release(pages[index]); } } @@ -3114,7 +3230,8 @@ static void __extent_readpages(struct extent_io_tree *tree, int nr_pages, get_extent_t *get_extent, struct extent_map **em_cached, struct bio **bio, int mirror_num, - unsigned long *bio_flags, int rw) + unsigned long *bio_flags, int rw, + u64 *prev_em_start) { u64 start = 0; u64 end = 0; @@ -3135,7 +3252,7 @@ static void __extent_readpages(struct extent_io_tree *tree, index - first_index, start, end, get_extent, em_cached, bio, mirror_num, bio_flags, - rw); + rw, prev_em_start); start = page_start; end = start + PAGE_CACHE_SIZE - 1; first_index = index; @@ -3146,7 +3263,8 @@ static void __extent_readpages(struct extent_io_tree *tree, __do_contiguous_readpages(tree, &pages[first_index], index - first_index, start, end, get_extent, em_cached, bio, - mirror_num, bio_flags, rw); + mirror_num, bio_flags, rw, + prev_em_start); } static int __extent_read_full_page(struct extent_io_tree *tree, @@ -3172,7 +3290,7 @@ static int __extent_read_full_page(struct extent_io_tree *tree, } ret = __do_readpage(tree, page, get_extent, NULL, bio, mirror_num, - bio_flags, rw); + bio_flags, rw, NULL); return ret; } @@ -3198,7 +3316,7 @@ int extent_read_full_page_nolock(struct extent_io_tree *tree, struct page *page, int ret; ret = __do_readpage(tree, page, get_extent, NULL, &bio, mirror_num, - &bio_flags, READ); + &bio_flags, READ, NULL); if (bio) ret = submit_one_bio(READ, bio, mirror_num, bio_flags); return ret; @@ -3451,7 +3569,7 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode, sector, iosize, pg_offset, bdev, &epd->bio, max_nr, end_bio_extent_writepage, - 0, 0, 0); + 0, 0, 0, false); if (ret) SetPageError(page); } @@ -3754,7 +3872,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb, ret = submit_extent_page(rw, tree, wbc, p, offset >> 9, PAGE_CACHE_SIZE, 0, bdev, &epd->bio, -1, end_bio_extent_buffer_writepage, - 0, epd->bio_flags, bio_flags); + 0, epd->bio_flags, bio_flags, false); epd->bio_flags = bio_flags; if (ret) { set_btree_ioerr(p); @@ -4158,6 +4276,7 @@ int extent_readpages(struct extent_io_tree *tree, struct page *page; struct extent_map *em_cached = NULL; int nr = 0; + u64 prev_em_start = (u64)-1; for (page_idx = 0; page_idx < nr_pages; page_idx++) { page = list_entry(pages->prev, struct page, lru); @@ -4174,12 +4293,12 @@ int extent_readpages(struct extent_io_tree *tree, if (nr < ARRAY_SIZE(pagepool)) continue; __extent_readpages(tree, pagepool, nr, get_extent, &em_cached, - &bio, 0, &bio_flags, READ); + &bio, 0, &bio_flags, READ, &prev_em_start); nr = 0; } if (nr) __extent_readpages(tree, pagepool, nr, get_extent, &em_cached, - &bio, 0, &bio_flags, READ); + &bio, 0, &bio_flags, READ, &prev_em_start); if (em_cached) free_extent_map(em_cached); @@ -4267,7 +4386,7 @@ int try_release_extent_mapping(struct extent_map_tree *map, u64 start = page_offset(page); u64 end = start + PAGE_CACHE_SIZE - 1; - if ((mask & __GFP_WAIT) && + if (gfpflags_allow_blocking(mask) && page->mapping->host->i_size > 16 * 1024 * 1024) { u64 len; while (start <= end) { @@ -5514,13 +5633,15 @@ void memcpy_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset, unsigned long src_i; if (src_offset + len > dst->len) { - printk(KERN_ERR "BTRFS: memmove bogus src_offset %lu move " - "len %lu dst len %lu\n", src_offset, len, dst->len); + btrfs_err(dst->fs_info, + "memmove bogus src_offset %lu move " + "len %lu dst len %lu", src_offset, len, dst->len); BUG_ON(1); } if (dst_offset + len > dst->len) { - printk(KERN_ERR "BTRFS: memmove bogus dst_offset %lu move " - "len %lu dst len %lu\n", dst_offset, len, dst->len); + btrfs_err(dst->fs_info, + "memmove bogus dst_offset %lu move " + "len %lu dst len %lu", dst_offset, len, dst->len); BUG_ON(1); } @@ -5560,13 +5681,13 @@ void memmove_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset, unsigned long src_i; if (src_offset + len > dst->len) { - printk(KERN_ERR "BTRFS: memmove bogus src_offset %lu move " - "len %lu len %lu\n", src_offset, len, dst->len); + btrfs_err(dst->fs_info, "memmove bogus src_offset %lu move " + "len %lu len %lu", src_offset, len, dst->len); BUG_ON(1); } if (dst_offset + len > dst->len) { - printk(KERN_ERR "BTRFS: memmove bogus dst_offset %lu move " - "len %lu len %lu\n", dst_offset, len, dst->len); + btrfs_err(dst->fs_info, "memmove bogus dst_offset %lu move " + "len %lu len %lu", dst_offset, len, dst->len); BUG_ON(1); } if (dst_offset < src_offset) { diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index c668f36..f4c1ae1 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -2,6 +2,7 @@ #define __EXTENTIO__ #include <linux/rbtree.h> +#include "ulist.h" /* bits for the extent state */ #define EXTENT_DIRTY (1U << 0) @@ -18,6 +19,7 @@ #define EXTENT_NEED_WAIT (1U << 13) #define EXTENT_DAMAGED (1U << 14) #define EXTENT_NORESERVE (1U << 15) +#define EXTENT_QGROUP_RESERVED (1U << 16) #define EXTENT_IOBITS (EXTENT_LOCKED | EXTENT_WRITEBACK) #define EXTENT_CTLBITS (EXTENT_DO_ACCOUNTING | EXTENT_FIRST_DELALLOC) @@ -161,6 +163,17 @@ struct extent_buffer { #endif }; +/* + * Structure to record how many bytes and which ranges are set/cleared + */ +struct extent_changeset { + /* How many bytes are set/cleared in this operation */ + u64 bytes_changed; + + /* Changed ranges */ + struct ulist *range_changed; +}; + static inline void extent_set_compress_type(unsigned long *bio_flags, int compress_type) { @@ -210,11 +223,17 @@ int test_range_bit(struct extent_io_tree *tree, u64 start, u64 end, struct extent_state *cached_state); int clear_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, unsigned bits, gfp_t mask); +int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, + unsigned bits, gfp_t mask, + struct extent_changeset *changeset); int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, unsigned bits, int wake, int delete, struct extent_state **cached, gfp_t mask); int set_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, unsigned bits, gfp_t mask); +int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, + unsigned bits, gfp_t mask, + struct extent_changeset *changeset); int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, unsigned bits, u64 *failed_start, struct extent_state **cached_state, gfp_t mask); diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index b823fac..6bd5ce9 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -847,7 +847,7 @@ next_slot: disk_bytenr, num_bytes, 0, root->root_key.objectid, new_key.objectid, - start - extent_offset, 1); + start - extent_offset); BUG_ON(ret); /* -ENOMEM */ } key.offset = start; @@ -925,7 +925,7 @@ delete_extent_item: disk_bytenr, num_bytes, 0, root->root_key.objectid, key.objectid, key.offset - - extent_offset, 0); + extent_offset); BUG_ON(ret); /* -ENOMEM */ inode_sub_bytes(inode, extent_end - key.offset); @@ -1204,7 +1204,7 @@ again: ret = btrfs_inc_extent_ref(trans, root, bytenr, num_bytes, 0, root->root_key.objectid, - ino, orig_offset, 1); + ino, orig_offset); BUG_ON(ret); /* -ENOMEM */ if (split == start) { @@ -1231,7 +1231,7 @@ again: del_nr++; ret = btrfs_free_extent(trans, root, bytenr, num_bytes, 0, root->root_key.objectid, - ino, orig_offset, 0); + ino, orig_offset); BUG_ON(ret); /* -ENOMEM */ } other_start = 0; @@ -1248,7 +1248,7 @@ again: del_nr++; ret = btrfs_free_extent(trans, root, bytenr, num_bytes, 0, root->root_key.objectid, - ino, orig_offset, 0); + ino, orig_offset); BUG_ON(ret); /* -ENOMEM */ } if (del_nr == 0) { @@ -1469,7 +1469,6 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file, u64 release_bytes = 0; u64 lockstart; u64 lockend; - unsigned long first_index; size_t num_written = 0; int nrptrs; int ret = 0; @@ -1485,8 +1484,6 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file, if (!pages) return -ENOMEM; - first_index = pos >> PAGE_CACHE_SHIFT; - while (iov_iter_count(i) > 0) { size_t offset = pos & (PAGE_CACHE_SIZE - 1); size_t write_bytes = min(iov_iter_count(i), @@ -1510,12 +1507,17 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file, } reserve_bytes = num_pages << PAGE_CACHE_SHIFT; - ret = btrfs_check_data_free_space(inode, reserve_bytes, write_bytes); - if (ret == -ENOSPC && - (BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW | - BTRFS_INODE_PREALLOC))) { + + if (BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW | + BTRFS_INODE_PREALLOC)) { ret = check_can_nocow(inode, pos, &write_bytes); + if (ret < 0) + break; if (ret > 0) { + /* + * For nodata cow case, no need to reserve + * data space. + */ only_release_metadata = true; /* * our prealloc extent may be smaller than @@ -1524,20 +1526,19 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file, num_pages = DIV_ROUND_UP(write_bytes + offset, PAGE_CACHE_SIZE); reserve_bytes = num_pages << PAGE_CACHE_SHIFT; - ret = 0; - } else { - ret = -ENOSPC; + goto reserve_metadata; } } - - if (ret) + ret = btrfs_check_data_free_space(inode, pos, write_bytes); + if (ret < 0) break; +reserve_metadata: ret = btrfs_delalloc_reserve_metadata(inode, reserve_bytes); if (ret) { if (!only_release_metadata) - btrfs_free_reserved_data_space(inode, - reserve_bytes); + btrfs_free_reserved_data_space(inode, pos, + write_bytes); else btrfs_end_write_no_snapshoting(root); break; @@ -1603,12 +1604,17 @@ again: BTRFS_I(inode)->outstanding_extents++; spin_unlock(&BTRFS_I(inode)->lock); } - if (only_release_metadata) + if (only_release_metadata) { btrfs_delalloc_release_metadata(inode, release_bytes); - else - btrfs_delalloc_release_space(inode, + } else { + u64 __pos; + + __pos = round_down(pos, root->sectorsize) + + (dirty_pages << PAGE_CACHE_SHIFT); + btrfs_delalloc_release_space(inode, __pos, release_bytes); + } } release_bytes = dirty_pages << PAGE_CACHE_SHIFT; @@ -1660,7 +1666,7 @@ again: btrfs_end_write_no_snapshoting(root); btrfs_delalloc_release_metadata(inode, release_bytes); } else { - btrfs_delalloc_release_space(inode, release_bytes); + btrfs_delalloc_release_space(inode, pos, release_bytes); } } @@ -2266,7 +2272,7 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) u64 drop_end; int ret = 0; int err = 0; - int rsv_count; + unsigned int rsv_count; bool same_page; bool no_holes = btrfs_fs_incompat(root->fs_info, NO_HOLES); u64 ino_size; @@ -2488,6 +2494,19 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) trans->block_rsv = &root->fs_info->trans_block_rsv; /* + * If we are using the NO_HOLES feature we might have had already an + * hole that overlaps a part of the region [lockstart, lockend] and + * ends at (or beyond) lockend. Since we have no file extent items to + * represent holes, drop_end can be less than lockend and so we must + * make sure we have an extent map representing the existing hole (the + * call to __btrfs_drop_extents() might have dropped the existing extent + * map representing the existing hole), otherwise the fast fsync path + * will not record the existence of the hole region + * [existing_hole_start, lockend]. + */ + if (drop_end <= lockend) + drop_end = lockend + 1; + /* * Don't insert file hole extent item if it's for a range beyond eof * (because it's useless) or if it represents a 0 bytes range (when * cur_offset == drop_end). @@ -2541,17 +2560,61 @@ out_only_mutex: return err; } +/* Helper structure to record which range is already reserved */ +struct falloc_range { + struct list_head list; + u64 start; + u64 len; +}; + +/* + * Helper function to add falloc range + * + * Caller should have locked the larger range of extent containing + * [start, len) + */ +static int add_falloc_range(struct list_head *head, u64 start, u64 len) +{ + struct falloc_range *prev = NULL; + struct falloc_range *range = NULL; + + if (list_empty(head)) + goto insert; + + /* + * As fallocate iterate by bytenr order, we only need to check + * the last range. + */ + prev = list_entry(head->prev, struct falloc_range, list); + if (prev->start + prev->len == start) { + prev->len += len; + return 0; + } +insert: + range = kmalloc(sizeof(*range), GFP_NOFS); + if (!range) + return -ENOMEM; + range->start = start; + range->len = len; + list_add_tail(&range->list, head); + return 0; +} + static long btrfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len) { struct inode *inode = file_inode(file); struct extent_state *cached_state = NULL; + struct falloc_range *range; + struct falloc_range *tmp; + struct list_head reserve_list; u64 cur_offset; u64 last_byte; u64 alloc_start; u64 alloc_end; u64 alloc_hint = 0; u64 locked_end; + u64 actual_end = 0; struct extent_map *em; int blocksize = BTRFS_I(inode)->root->sectorsize; int ret; @@ -2567,11 +2630,12 @@ static long btrfs_fallocate(struct file *file, int mode, return btrfs_punch_hole(inode, offset, len); /* - * Make sure we have enough space before we do the - * allocation. + * Only trigger disk allocation, don't trigger qgroup reserve + * + * For qgroup space, it will be checked later. */ - ret = btrfs_check_data_free_space(inode, alloc_end - alloc_start, alloc_end - alloc_start); - if (ret) + ret = btrfs_alloc_data_chunk_ondemand(inode, alloc_end - alloc_start); + if (ret < 0) return ret; mutex_lock(&inode->i_mutex); @@ -2579,12 +2643,19 @@ static long btrfs_fallocate(struct file *file, int mode, if (ret) goto out; + /* + * TODO: Move these two operations after we have checked + * accurate reserved space, or fallocate can still fail but + * with page truncated or size expanded. + * + * But that's a minor problem and won't do much harm BTW. + */ if (alloc_start > inode->i_size) { ret = btrfs_cont_expand(inode, i_size_read(inode), alloc_start); if (ret) goto out; - } else { + } else if (offset + len > inode->i_size) { /* * If we are fallocating from the end of the file onward we * need to zero out the end of the page if i_size lands in the @@ -2637,10 +2708,10 @@ static long btrfs_fallocate(struct file *file, int mode, } } + /* First, check if we exceed the qgroup limit */ + INIT_LIST_HEAD(&reserve_list); cur_offset = alloc_start; while (1) { - u64 actual_end; - em = btrfs_get_extent(inode, NULL, 0, cur_offset, alloc_end - cur_offset, 0); if (IS_ERR_OR_NULL(em)) { @@ -2653,57 +2724,82 @@ static long btrfs_fallocate(struct file *file, int mode, last_byte = min(extent_map_end(em), alloc_end); actual_end = min_t(u64, extent_map_end(em), offset + len); last_byte = ALIGN(last_byte, blocksize); - if (em->block_start == EXTENT_MAP_HOLE || (cur_offset >= inode->i_size && !test_bit(EXTENT_FLAG_PREALLOC, &em->flags))) { - ret = btrfs_prealloc_file_range(inode, mode, cur_offset, - last_byte - cur_offset, - 1 << inode->i_blkbits, - offset + len, - &alloc_hint); - } else if (actual_end > inode->i_size && - !(mode & FALLOC_FL_KEEP_SIZE)) { - struct btrfs_trans_handle *trans; - struct btrfs_root *root = BTRFS_I(inode)->root; - - /* - * We didn't need to allocate any more space, but we - * still extended the size of the file so we need to - * update i_size and the inode item. - */ - trans = btrfs_start_transaction(root, 1); - if (IS_ERR(trans)) { - ret = PTR_ERR(trans); - } else { - inode->i_ctime = CURRENT_TIME; - i_size_write(inode, actual_end); - btrfs_ordered_update_i_size(inode, actual_end, - NULL); - ret = btrfs_update_inode(trans, root, inode); - if (ret) - btrfs_end_transaction(trans, root); - else - ret = btrfs_end_transaction(trans, - root); + ret = add_falloc_range(&reserve_list, cur_offset, + last_byte - cur_offset); + if (ret < 0) { + free_extent_map(em); + break; } + ret = btrfs_qgroup_reserve_data(inode, cur_offset, + last_byte - cur_offset); + if (ret < 0) + break; } free_extent_map(em); - if (ret < 0) - break; - cur_offset = last_byte; - if (cur_offset >= alloc_end) { - ret = 0; + if (cur_offset >= alloc_end) break; + } + + /* + * If ret is still 0, means we're OK to fallocate. + * Or just cleanup the list and exit. + */ + list_for_each_entry_safe(range, tmp, &reserve_list, list) { + if (!ret) + ret = btrfs_prealloc_file_range(inode, mode, + range->start, + range->len, 1 << inode->i_blkbits, + offset + len, &alloc_hint); + list_del(&range->list); + kfree(range); + } + if (ret < 0) + goto out_unlock; + + if (actual_end > inode->i_size && + !(mode & FALLOC_FL_KEEP_SIZE)) { + struct btrfs_trans_handle *trans; + struct btrfs_root *root = BTRFS_I(inode)->root; + + /* + * We didn't need to allocate any more space, but we + * still extended the size of the file so we need to + * update i_size and the inode item. + */ + trans = btrfs_start_transaction(root, 1); + if (IS_ERR(trans)) { + ret = PTR_ERR(trans); + } else { + inode->i_ctime = CURRENT_TIME; + i_size_write(inode, actual_end); + btrfs_ordered_update_i_size(inode, actual_end, NULL); + ret = btrfs_update_inode(trans, root, inode); + if (ret) + btrfs_end_transaction(trans, root); + else + ret = btrfs_end_transaction(trans, root); } } +out_unlock: unlock_extent_cached(&BTRFS_I(inode)->io_tree, alloc_start, locked_end, &cached_state, GFP_NOFS); out: + /* + * As we waited the extent range, the data_rsv_map must be empty + * in the range, as written data range will be released from it. + * And for prealloacted extent, it will also be released when + * its metadata is written. + * So this is completely used as cleanup. + */ + btrfs_qgroup_free_data(inode, alloc_start, alloc_end - alloc_start); mutex_unlock(&inode->i_mutex); /* Let go of our reservation. */ - btrfs_free_reserved_data_space(inode, alloc_end - alloc_start); + btrfs_free_reserved_data_space(inode, alloc_start, + alloc_end - alloc_start); return ret; } diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index abe3a66..85a1f86 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -85,8 +85,8 @@ static struct inode *__lookup_free_space_inode(struct btrfs_root *root, } mapping_set_gfp_mask(inode->i_mapping, - mapping_gfp_mask(inode->i_mapping) & - ~(__GFP_FS | __GFP_HIGHMEM)); + mapping_gfp_constraint(inode->i_mapping, + ~(__GFP_FS | __GFP_HIGHMEM))); return inode; } @@ -450,9 +450,9 @@ static int io_ctl_check_generation(struct btrfs_io_ctl *io_ctl, u64 generation) gen = io_ctl->cur; if (le64_to_cpu(*gen) != generation) { - printk_ratelimited(KERN_ERR "BTRFS: space cache generation " - "(%Lu) does not match inode (%Lu)\n", *gen, - generation); + btrfs_err_rl(io_ctl->root->fs_info, + "space cache generation (%llu) does not match inode (%llu)", + *gen, generation); io_ctl_unmap_page(io_ctl); return -EIO; } @@ -506,8 +506,8 @@ static int io_ctl_check_crc(struct btrfs_io_ctl *io_ctl, int index) PAGE_CACHE_SIZE - offset); btrfs_csum_final(crc, (char *)&crc); if (val != crc) { - printk_ratelimited(KERN_ERR "BTRFS: csum mismatch on free " - "space cache\n"); + btrfs_err_rl(io_ctl->root->fs_info, + "csum mismatch on free space cache"); io_ctl_unmap_page(io_ctl); return -EIO; } @@ -1215,7 +1215,7 @@ out: * @offset - the offset for the key we'll insert * * This function writes out a free space cache struct to disk for quick recovery - * on mount. This will return 0 if it was successfull in writing the cache out, + * on mount. This will return 0 if it was successful in writing the cache out, * or an errno if it was not. */ static int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode, @@ -1730,7 +1730,7 @@ static void bitmap_set_bits(struct btrfs_free_space_ctl *ctl, */ static int search_bitmap(struct btrfs_free_space_ctl *ctl, struct btrfs_free_space *bitmap_info, u64 *offset, - u64 *bytes) + u64 *bytes, bool for_alloc) { unsigned long found_bits = 0; unsigned long max_bits = 0; @@ -1738,11 +1738,26 @@ static int search_bitmap(struct btrfs_free_space_ctl *ctl, unsigned long next_zero; unsigned long extent_bits; + /* + * Skip searching the bitmap if we don't have a contiguous section that + * is large enough for this allocation. + */ + if (for_alloc && + bitmap_info->max_extent_size && + bitmap_info->max_extent_size < *bytes) { + *bytes = bitmap_info->max_extent_size; + return -1; + } + i = offset_to_bit(bitmap_info->offset, ctl->unit, max_t(u64, *offset, bitmap_info->offset)); bits = bytes_to_bits(*bytes, ctl->unit); for_each_set_bit_from(i, bitmap_info->bitmap, BITS_PER_BITMAP) { + if (for_alloc && bits == 1) { + found_bits = 1; + break; + } next_zero = find_next_zero_bit(bitmap_info->bitmap, BITS_PER_BITMAP, i); extent_bits = next_zero - i; @@ -1762,6 +1777,7 @@ static int search_bitmap(struct btrfs_free_space_ctl *ctl, } *bytes = (u64)(max_bits) * ctl->unit; + bitmap_info->max_extent_size = *bytes; return -1; } @@ -1813,7 +1829,7 @@ find_free_space(struct btrfs_free_space_ctl *ctl, u64 *offset, u64 *bytes, if (entry->bitmap) { u64 size = *bytes; - ret = search_bitmap(ctl, entry, &tmp, &size); + ret = search_bitmap(ctl, entry, &tmp, &size, true); if (!ret) { *offset = tmp; *bytes = size; @@ -1874,7 +1890,8 @@ again: search_start = *offset; search_bytes = ctl->unit; search_bytes = min(search_bytes, end - search_start + 1); - ret = search_bitmap(ctl, bitmap_info, &search_start, &search_bytes); + ret = search_bitmap(ctl, bitmap_info, &search_start, &search_bytes, + false); if (ret < 0 || search_start != *offset) return -EINVAL; @@ -1919,7 +1936,7 @@ again: search_start = *offset; search_bytes = ctl->unit; ret = search_bitmap(ctl, bitmap_info, &search_start, - &search_bytes); + &search_bytes, false); if (ret < 0 || search_start != *offset) return -EAGAIN; @@ -1943,6 +1960,12 @@ static u64 add_bytes_to_bitmap(struct btrfs_free_space_ctl *ctl, bitmap_set_bits(ctl, info, offset, bytes_to_set); + /* + * We set some bytes, we have no idea what the max extent size is + * anymore. + */ + info->max_extent_size = 0; + return bytes_to_set; } @@ -1951,12 +1974,19 @@ static bool use_bitmap(struct btrfs_free_space_ctl *ctl, struct btrfs_free_space *info) { struct btrfs_block_group_cache *block_group = ctl->private; + bool forced = false; + +#ifdef CONFIG_BTRFS_DEBUG + if (btrfs_should_fragment_free_space(block_group->fs_info->extent_root, + block_group)) + forced = true; +#endif /* * If we are below the extents threshold then we can add this as an * extent, and don't have to deal with the bitmap */ - if (ctl->free_extents < ctl->extents_thresh) { + if (!forced && ctl->free_extents < ctl->extents_thresh) { /* * If this block group has some small extents we don't want to * use up all of our free slots in the cache with them, we want @@ -2661,7 +2691,7 @@ static u64 btrfs_alloc_from_bitmap(struct btrfs_block_group_cache *block_group, search_start = min_start; search_bytes = bytes; - err = search_bitmap(ctl, entry, &search_start, &search_bytes); + err = search_bitmap(ctl, entry, &search_start, &search_bytes, true); if (err) { if (search_bytes > *max_extent_size) *max_extent_size = search_bytes; @@ -2775,6 +2805,7 @@ static int btrfs_bitmap_cluster(struct btrfs_block_group_cache *block_group, unsigned long want_bits; unsigned long min_bits; unsigned long found_bits; + unsigned long max_bits = 0; unsigned long start = 0; unsigned long total_found = 0; int ret; @@ -2784,6 +2815,13 @@ static int btrfs_bitmap_cluster(struct btrfs_block_group_cache *block_group, want_bits = bytes_to_bits(bytes, ctl->unit); min_bits = bytes_to_bits(min_bytes, ctl->unit); + /* + * Don't bother looking for a cluster in this bitmap if it's heavily + * fragmented. + */ + if (entry->max_extent_size && + entry->max_extent_size < cont1_bytes) + return -ENOSPC; again: found_bits = 0; for_each_set_bit_from(i, entry->bitmap, BITS_PER_BITMAP) { @@ -2791,13 +2829,19 @@ again: BITS_PER_BITMAP, i); if (next_zero - i >= min_bits) { found_bits = next_zero - i; + if (found_bits > max_bits) + max_bits = found_bits; break; } + if (next_zero - i > max_bits) + max_bits = next_zero - i; i = next_zero; } - if (!found_bits) + if (!found_bits) { + entry->max_extent_size = (u64)max_bits * ctl->unit; return -ENOSPC; + } if (!total_found) { start = i; @@ -3056,6 +3100,7 @@ void btrfs_init_free_cluster(struct btrfs_free_cluster *cluster) spin_lock_init(&cluster->refill_lock); cluster->root = RB_ROOT; cluster->max_size = 0; + cluster->fragmented = false; INIT_LIST_HEAD(&cluster->block_group_list); cluster->block_group = NULL; } @@ -3223,7 +3268,7 @@ static int trim_bitmaps(struct btrfs_block_group_cache *block_group, } bytes = minlen; - ret2 = search_bitmap(ctl, entry, &start, &bytes); + ret2 = search_bitmap(ctl, entry, &start, &bytes, false); if (ret2 || start >= end) { spin_unlock(&ctl->tree_lock); mutex_unlock(&ctl->cache_writeout_mutex); @@ -3376,7 +3421,7 @@ u64 btrfs_find_ino_for_alloc(struct btrfs_root *fs_root) u64 count = 1; int ret; - ret = search_bitmap(ctl, entry, &offset, &count); + ret = search_bitmap(ctl, entry, &offset, &count, true); /* Logic error; Should be empty if it can't find anything */ ASSERT(!ret); @@ -3532,6 +3577,7 @@ again: spin_lock(&ctl->tree_lock); info->offset = offset; info->bytes = bytes; + info->max_extent_size = 0; ret = link_free_space(ctl, info); spin_unlock(&ctl->tree_lock); if (ret) @@ -3559,6 +3605,7 @@ again: } bytes_added = add_bytes_to_bitmap(ctl, bitmap_info, offset, bytes); + bytes -= bytes_added; offset += bytes_added; spin_unlock(&ctl->tree_lock); @@ -3602,7 +3649,7 @@ have_info: bit_off = offset; bit_bytes = ctl->unit; - ret = search_bitmap(ctl, info, &bit_off, &bit_bytes); + ret = search_bitmap(ctl, info, &bit_off, &bit_bytes, false); if (!ret) { if (bit_off == offset) { ret = 1; diff --git a/fs/btrfs/free-space-cache.h b/fs/btrfs/free-space-cache.h index a16a029..f251865 100644 --- a/fs/btrfs/free-space-cache.h +++ b/fs/btrfs/free-space-cache.h @@ -23,6 +23,7 @@ struct btrfs_free_space { struct rb_node offset_index; u64 offset; u64 bytes; + u64 max_extent_size; unsigned long *bitmap; struct list_head list; }; diff --git a/fs/btrfs/inode-item.c b/fs/btrfs/inode-item.c index 265e03c..be4d22a 100644 --- a/fs/btrfs/inode-item.c +++ b/fs/btrfs/inode-item.c @@ -157,7 +157,7 @@ static int btrfs_del_inode_extref(struct btrfs_trans_handle *trans, */ if (!btrfs_find_name_in_ext_backref(path, ref_objectid, name, name_len, &extref)) { - btrfs_std_error(root->fs_info, -ENOENT); + btrfs_std_error(root->fs_info, -ENOENT, NULL); ret = -EROFS; goto out; } diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c index d4a582a..767a605 100644 --- a/fs/btrfs/inode-map.c +++ b/fs/btrfs/inode-map.c @@ -488,17 +488,17 @@ again: /* Just to make sure we have enough space */ prealloc += 8 * PAGE_CACHE_SIZE; - ret = btrfs_delalloc_reserve_space(inode, prealloc); + ret = btrfs_delalloc_reserve_space(inode, 0, prealloc); if (ret) goto out_put; ret = btrfs_prealloc_file_range_trans(inode, trans, 0, 0, prealloc, prealloc, prealloc, &alloc_hint); if (ret) { - btrfs_delalloc_release_space(inode, prealloc); + btrfs_delalloc_release_space(inode, 0, prealloc); goto out_put; } - btrfs_free_reserved_data_space(inode, prealloc); + btrfs_free_reserved_data_space(inode, 0, prealloc); ret = btrfs_write_out_ino_cache(root, trans, path, inode); out_put: diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index a0fa725..0e4f2bf 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -310,6 +310,13 @@ static noinline int cow_file_range_inline(struct btrfs_root *root, btrfs_delalloc_release_metadata(inode, end + 1 - start); btrfs_drop_extent_cache(inode, start, aligned_end - 1, 0); out: + /* + * Don't forget to free the reserved space, as for inlined extent + * it won't count as data extent, free them directly here. + * And at reserve time, it's always aligned to page size, so + * just free one page here. + */ + btrfs_qgroup_free_data(inode, 0, PAGE_CACHE_SIZE); btrfs_free_path(path); btrfs_end_transaction(trans, root); return ret; @@ -1096,6 +1103,9 @@ static noinline void async_cow_submit(struct btrfs_work *work) nr_pages = (async_cow->end - async_cow->start + PAGE_CACHE_SIZE) >> PAGE_CACHE_SHIFT; + /* + * atomic_sub_return implies a barrier for waitqueue_active + */ if (atomic_sub_return(nr_pages, &root->fs_info->async_delalloc_pages) < 5 * 1024 * 1024 && waitqueue_active(&root->fs_info->async_submit_wait)) @@ -1766,7 +1776,8 @@ static void btrfs_clear_bit_hook(struct inode *inode, if (root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID && do_list && !(state->state & EXTENT_NORESERVE)) - btrfs_free_reserved_data_space(inode, len); + btrfs_free_reserved_data_space_noquota(inode, + state->start, len); __percpu_counter_add(&root->fs_info->delalloc_bytes, -len, root->fs_info->delalloc_batch); @@ -1861,15 +1872,15 @@ static int btrfs_submit_bio_hook(struct inode *inode, int rw, struct bio *bio, u64 bio_offset) { struct btrfs_root *root = BTRFS_I(inode)->root; + enum btrfs_wq_endio_type metadata = BTRFS_WQ_ENDIO_DATA; int ret = 0; int skip_sum; - int metadata = 0; int async = !atomic_read(&BTRFS_I(inode)->sync_writers); skip_sum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM; if (btrfs_is_free_space_inode(inode)) - metadata = 2; + metadata = BTRFS_WQ_ENDIO_FREE_SPACE; if (!(rw & REQ_WRITE)) { ret = btrfs_bio_wq_end_io(root->fs_info, bio, metadata); @@ -1989,7 +2000,8 @@ again: goto again; } - ret = btrfs_delalloc_reserve_space(inode, PAGE_CACHE_SIZE); + ret = btrfs_delalloc_reserve_space(inode, page_start, + PAGE_CACHE_SIZE); if (ret) { mapping_set_error(page->mapping, ret); end_extent_writepage(page, ret, page_start, page_end); @@ -2115,7 +2127,13 @@ static int insert_reserved_file_extent(struct btrfs_trans_handle *trans, ins.type = BTRFS_EXTENT_ITEM_KEY; ret = btrfs_alloc_reserved_file_extent(trans, root, root->root_key.objectid, - btrfs_ino(inode), file_pos, &ins); + btrfs_ino(inode), file_pos, + ram_bytes, &ins); + /* + * Release the reserved range from inode dirty range map, as it is + * already moved into delayed_ref_head + */ + btrfs_qgroup_release_data(inode, file_pos, ram_bytes); out: btrfs_free_path(path); @@ -2573,7 +2591,7 @@ again: ret = btrfs_inc_extent_ref(trans, root, new->bytenr, new->disk_len, 0, backref->root_id, backref->inum, - new->file_pos, 0); /* start - extent_offset */ + new->file_pos); /* start - extent_offset */ if (ret) { btrfs_abort_transaction(trans, root, ret); goto out_free_path; @@ -2599,7 +2617,6 @@ static void free_sa_defrag_extent(struct new_sa_defrag_extent *new) return; list_for_each_entry_safe(old, tmp, &new->head, list) { - list_del(&old->list); kfree(old); } kfree(new); @@ -2824,6 +2841,14 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent) if (test_bit(BTRFS_ORDERED_NOCOW, &ordered_extent->flags)) { BUG_ON(!list_empty(&ordered_extent->list)); /* Logic error */ + + /* + * For mwrite(mmap + memset to write) case, we still reserve + * space for NOCOW range. + * As NOCOW won't cause a new delayed ref, just free the space + */ + btrfs_qgroup_free_data(inode, ordered_extent->file_offset, + ordered_extent->len); btrfs_ordered_update_i_size(inode, 0, ordered_extent); if (nolock) trans = btrfs_join_transaction_nolock(root); @@ -3018,8 +3043,6 @@ static int __readpage_endio_check(struct inode *inode, char *kaddr; u32 csum_expected; u32 csum = ~(u32)0; - static DEFINE_RATELIMIT_STATE(_rs, DEFAULT_RATELIMIT_INTERVAL, - DEFAULT_RATELIMIT_BURST); csum_expected = *(((u32 *)io_bio->csum) + icsum); @@ -3032,9 +3055,8 @@ static int __readpage_endio_check(struct inode *inode, kunmap_atomic(kaddr); return 0; zeroit: - if (__ratelimit(&_rs)) - btrfs_warn(BTRFS_I(inode)->root->fs_info, - "csum failed ino %llu off %llu csum %u expected csum %u", + btrfs_warn_rl(BTRFS_I(inode)->root->fs_info, + "csum failed ino %llu off %llu csum %u expected csum %u", btrfs_ino(inode), start, csum, csum_expected); memset(kaddr + pgoff, 1, len); flush_dcache_page(page); @@ -4217,6 +4239,47 @@ static int truncate_space_check(struct btrfs_trans_handle *trans, } +static int truncate_inline_extent(struct inode *inode, + struct btrfs_path *path, + struct btrfs_key *found_key, + const u64 item_end, + const u64 new_size) +{ + struct extent_buffer *leaf = path->nodes[0]; + int slot = path->slots[0]; + struct btrfs_file_extent_item *fi; + u32 size = (u32)(new_size - found_key->offset); + struct btrfs_root *root = BTRFS_I(inode)->root; + + fi = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item); + + if (btrfs_file_extent_compression(leaf, fi) != BTRFS_COMPRESS_NONE) { + loff_t offset = new_size; + loff_t page_end = ALIGN(offset, PAGE_CACHE_SIZE); + + /* + * Zero out the remaining of the last page of our inline extent, + * instead of directly truncating our inline extent here - that + * would be much more complex (decompressing all the data, then + * compressing the truncated data, which might be bigger than + * the size of the inline extent, resize the extent, etc). + * We release the path because to get the page we might need to + * read the extent item from disk (data not in the page cache). + */ + btrfs_release_path(path); + return btrfs_truncate_page(inode, offset, page_end - offset, 0); + } + + btrfs_set_file_extent_ram_bytes(leaf, fi, size); + size = btrfs_file_extent_calc_inline_size(size); + btrfs_truncate_item(root, path, size, 1); + + if (test_bit(BTRFS_ROOT_REF_COWS, &root->state)) + inode_sub_bytes(inode, item_end + 1 - new_size); + + return 0; +} + /* * this can truncate away extent items, csum items and directory items. * It starts at a high offset and removes keys until it can't find @@ -4411,27 +4474,40 @@ search_again: * special encodings */ if (!del_item && - btrfs_file_extent_compression(leaf, fi) == 0 && btrfs_file_extent_encryption(leaf, fi) == 0 && btrfs_file_extent_other_encoding(leaf, fi) == 0) { - u32 size = new_size - found_key.offset; - - if (test_bit(BTRFS_ROOT_REF_COWS, &root->state)) - inode_sub_bytes(inode, item_end + 1 - - new_size); /* - * update the ram bytes to properly reflect - * the new size of our item + * Need to release path in order to truncate a + * compressed extent. So delete any accumulated + * extent items so far. */ - btrfs_set_file_extent_ram_bytes(leaf, fi, size); - size = - btrfs_file_extent_calc_inline_size(size); - btrfs_truncate_item(root, path, size, 1); + if (btrfs_file_extent_compression(leaf, fi) != + BTRFS_COMPRESS_NONE && pending_del_nr) { + err = btrfs_del_items(trans, root, path, + pending_del_slot, + pending_del_nr); + if (err) { + btrfs_abort_transaction(trans, + root, + err); + goto error; + } + pending_del_nr = 0; + } + + err = truncate_inline_extent(inode, path, + &found_key, + item_end, + new_size); + if (err) { + btrfs_abort_transaction(trans, + root, err); + goto error; + } } else if (test_bit(BTRFS_ROOT_REF_COWS, &root->state)) { - inode_sub_bytes(inode, item_end + 1 - - found_key.offset); + inode_sub_bytes(inode, item_end + 1 - new_size); } } delete: @@ -4461,7 +4537,7 @@ delete: ret = btrfs_free_extent(trans, root, extent_start, extent_num_bytes, 0, btrfs_header_owner(leaf), - ino, extent_offset, 0); + ino, extent_offset); BUG_ON(ret); if (btrfs_should_throttle_delayed_refs(trans, root)) btrfs_async_run_delayed_refs(root, @@ -4575,14 +4651,17 @@ int btrfs_truncate_page(struct inode *inode, loff_t from, loff_t len, if ((offset & (blocksize - 1)) == 0 && (!len || ((len & (blocksize - 1)) == 0))) goto out; - ret = btrfs_delalloc_reserve_space(inode, PAGE_CACHE_SIZE); + ret = btrfs_delalloc_reserve_space(inode, + round_down(from, PAGE_CACHE_SIZE), PAGE_CACHE_SIZE); if (ret) goto out; again: page = find_or_create_page(mapping, index, mask); if (!page) { - btrfs_delalloc_release_space(inode, PAGE_CACHE_SIZE); + btrfs_delalloc_release_space(inode, + round_down(from, PAGE_CACHE_SIZE), + PAGE_CACHE_SIZE); ret = -ENOMEM; goto out; } @@ -4650,7 +4729,8 @@ again: out_unlock: if (ret) - btrfs_delalloc_release_space(inode, PAGE_CACHE_SIZE); + btrfs_delalloc_release_space(inode, page_start, + PAGE_CACHE_SIZE); unlock_page(page); page_cache_release(page); out: @@ -5048,6 +5128,18 @@ static void evict_inode_truncate_pages(struct inode *inode) spin_unlock(&io_tree->lock); lock_extent_bits(io_tree, start, end, 0, &cached_state); + + /* + * If still has DELALLOC flag, the extent didn't reach disk, + * and its reserved space won't be freed by delayed_ref. + * So we need to free its reserved space here. + * (Refer to comment in btrfs_invalidatepage, case 2) + * + * Note, end is the bytenr of last byte, so we need + 1 here. + */ + if (state->state & EXTENT_DELALLOC) + btrfs_qgroup_free_data(inode, start, end - start + 1); + clear_extent_bit(io_tree, start, end, EXTENT_LOCKED | EXTENT_DIRTY | EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING | @@ -5084,7 +5176,8 @@ void btrfs_evict_inode(struct inode *inode) goto no_delete; } /* do we really want it for ->i_nlink > 0 and zero btrfs_root_refs? */ - btrfs_wait_ordered_range(inode, 0, (u64)-1); + if (!special_file(inode->i_mode)) + btrfs_wait_ordered_range(inode, 0, (u64)-1); btrfs_free_io_failure_record(inode, 0, (u64)-1); @@ -6267,9 +6360,6 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry, u64 objectid; u64 index = 0; - if (!new_valid_dev(rdev)) - return -EINVAL; - /* * 2 for inode item and ref * 2 for dir items @@ -7408,6 +7498,10 @@ static struct extent_map *create_pinned_em(struct inode *inode, u64 start, return em; } +struct btrfs_dio_data { + u64 outstanding_extents; + u64 reserve; +}; static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) @@ -7415,10 +7509,10 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, struct extent_map *em; struct btrfs_root *root = BTRFS_I(inode)->root; struct extent_state *cached_state = NULL; + struct btrfs_dio_data *dio_data = NULL; u64 start = iblock << inode->i_blkbits; u64 lockstart, lockend; u64 len = bh_result->b_size; - u64 *outstanding_extents = NULL; int unlock_bits = EXTENT_LOCKED; int ret = 0; @@ -7436,7 +7530,7 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, * that anything that needs to check if there's a transction doesn't get * confused. */ - outstanding_extents = current->journal_info; + dio_data = current->journal_info; current->journal_info = NULL; } @@ -7568,17 +7662,18 @@ unlock: * within our reservation, otherwise we need to adjust our inode * counter appropriately. */ - if (*outstanding_extents) { - (*outstanding_extents)--; + if (dio_data->outstanding_extents) { + (dio_data->outstanding_extents)--; } else { spin_lock(&BTRFS_I(inode)->lock); BTRFS_I(inode)->outstanding_extents++; spin_unlock(&BTRFS_I(inode)->lock); } - current->journal_info = outstanding_extents; - btrfs_free_reserved_data_space(inode, len); - set_bit(BTRFS_INODE_DIO_READY, &BTRFS_I(inode)->runtime_flags); + btrfs_free_reserved_data_space(inode, start, len); + WARN_ON(dio_data->reserve < len); + dio_data->reserve -= len; + current->journal_info = dio_data; } /* @@ -7601,8 +7696,8 @@ unlock: unlock_err: clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, lockend, unlock_bits, 1, 0, &cached_state, GFP_NOFS); - if (outstanding_extents) - current->journal_info = outstanding_extents; + if (dio_data) + current->journal_info = dio_data; return ret; } @@ -8329,7 +8424,8 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; - u64 outstanding_extents = 0; + struct btrfs_root *root = BTRFS_I(inode)->root; + struct btrfs_dio_data dio_data = { 0 }; size_t count = 0; int flags = 0; bool wakeup = true; @@ -8364,10 +8460,10 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, mutex_unlock(&inode->i_mutex); relock = true; } - ret = btrfs_delalloc_reserve_space(inode, count); + ret = btrfs_delalloc_reserve_space(inode, offset, count); if (ret) goto out; - outstanding_extents = div64_u64(count + + dio_data.outstanding_extents = div64_u64(count + BTRFS_MAX_EXTENT_SIZE - 1, BTRFS_MAX_EXTENT_SIZE); @@ -8376,7 +8472,8 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, * do the accounting properly if we go over the number we * originally calculated. Abuse current->journal_info for this. */ - current->journal_info = &outstanding_extents; + dio_data.reserve = round_up(count, root->sectorsize); + current->journal_info = &dio_data; } else if (test_bit(BTRFS_INODE_READDIO_NEED_LOCK, &BTRFS_I(inode)->runtime_flags)) { inode_dio_end(inode); @@ -8391,18 +8488,11 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, if (iov_iter_rw(iter) == WRITE) { current->journal_info = NULL; if (ret < 0 && ret != -EIOCBQUEUED) { - /* - * If the error comes from submitting stage, - * btrfs_get_blocsk_direct() has free'd data space, - * and metadata space will be handled by - * finish_ordered_fn, don't do that again to make - * sure bytes_may_use is correct. - */ - if (!test_and_clear_bit(BTRFS_INODE_DIO_READY, - &BTRFS_I(inode)->runtime_flags)) - btrfs_delalloc_release_space(inode, count); + if (dio_data.reserve) + btrfs_delalloc_release_space(inode, offset, + dio_data.reserve); } else if (ret >= 0 && (size_t)ret < count) - btrfs_delalloc_release_space(inode, + btrfs_delalloc_release_space(inode, offset, count - (size_t)ret); } out: @@ -8561,6 +8651,18 @@ static void btrfs_invalidatepage(struct page *page, unsigned int offset, } } + /* + * Qgroup reserved space handler + * Page here will be either + * 1) Already written to disk + * In this case, its reserved space is released from data rsv map + * and will be freed by delayed_ref handler finally. + * So even we call qgroup_free_data(), it won't decrease reserved + * space. + * 2) Not written to disk + * This means the reserved space should be freed here. + */ + btrfs_qgroup_free_data(inode, page_start, PAGE_CACHE_SIZE); if (!inode_evicting) { clear_extent_bit(tree, page_start, page_end, EXTENT_LOCKED | EXTENT_DIRTY | @@ -8611,7 +8713,11 @@ int btrfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) u64 page_end; sb_start_pagefault(inode->i_sb); - ret = btrfs_delalloc_reserve_space(inode, PAGE_CACHE_SIZE); + page_start = page_offset(page); + page_end = page_start + PAGE_CACHE_SIZE - 1; + + ret = btrfs_delalloc_reserve_space(inode, page_start, + PAGE_CACHE_SIZE); if (!ret) { ret = file_update_time(vma->vm_file); reserved = 1; @@ -8630,8 +8736,6 @@ int btrfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) again: lock_page(page); size = i_size_read(inode); - page_start = page_offset(page); - page_end = page_start + PAGE_CACHE_SIZE - 1; if ((page->mapping != inode->i_mapping) || (page_start >= size)) { @@ -8708,7 +8812,7 @@ out_unlock: } unlock_page(page); out: - btrfs_delalloc_release_space(inode, PAGE_CACHE_SIZE); + btrfs_delalloc_release_space(inode, page_start, PAGE_CACHE_SIZE); out_noreserve: sb_end_pagefault(inode->i_sb); return ret; @@ -8997,6 +9101,7 @@ void btrfs_destroy_inode(struct inode *inode) btrfs_put_ordered_extent(ordered); } } + btrfs_qgroup_check_reserved_leak(inode); inode_tree_del(inode); btrfs_drop_extent_cache(inode, 0, (u64)-1, 0); free: @@ -9633,6 +9738,7 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode, u64 cur_offset = start; u64 i_size; u64 cur_bytes; + u64 last_alloc = (u64)-1; int ret = 0; bool own_trans = true; @@ -9649,6 +9755,13 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode, cur_bytes = min(num_bytes, 256ULL * 1024 * 1024); cur_bytes = max(cur_bytes, min_size); + /* + * If we are severely fragmented we could end up with really + * small allocations, so if the allocator is returning small + * chunks lets make its job easier by only searching for those + * sized chunks. + */ + cur_bytes = min(cur_bytes, last_alloc); ret = btrfs_reserve_extent(root, cur_bytes, min_size, 0, *alloc_hint, &ins, 1, 0); if (ret) { @@ -9657,6 +9770,7 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode, break; } + last_alloc = ins.offset; ret = insert_reserved_file_extent(trans, inode, cur_offset, ins.objectid, ins.offset, ins.offset, diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 0adf542..da94138 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1120,7 +1120,8 @@ static int cluster_pages_for_defrag(struct inode *inode, page_cnt = min_t(u64, (u64)num_pages, (u64)file_end - start_index + 1); ret = btrfs_delalloc_reserve_space(inode, - page_cnt << PAGE_CACHE_SHIFT); + start_index << PAGE_CACHE_SHIFT, + page_cnt << PAGE_CACHE_SHIFT); if (ret) return ret; i_done = 0; @@ -1210,7 +1211,8 @@ again: BTRFS_I(inode)->outstanding_extents++; spin_unlock(&BTRFS_I(inode)->lock); btrfs_delalloc_release_space(inode, - (page_cnt - i_done) << PAGE_CACHE_SHIFT); + start_index << PAGE_CACHE_SHIFT, + (page_cnt - i_done) << PAGE_CACHE_SHIFT); } @@ -1235,7 +1237,9 @@ out: unlock_page(pages[i]); page_cache_release(pages[i]); } - btrfs_delalloc_release_space(inode, page_cnt << PAGE_CACHE_SHIFT); + btrfs_delalloc_release_space(inode, + start_index << PAGE_CACHE_SHIFT, + page_cnt << PAGE_CACHE_SHIFT); return ret; } @@ -1342,7 +1346,7 @@ int btrfs_defrag_file(struct inode *inode, struct file *file, break; if (btrfs_defrag_cancelled(root->fs_info)) { - printk(KERN_DEBUG "BTRFS: defrag_file cancelled\n"); + btrfs_debug(root->fs_info, "defrag_file cancelled"); ret = -EAGAIN; break; } @@ -1579,7 +1583,7 @@ static noinline int btrfs_ioctl_resize(struct file *file, new_size = div_u64(new_size, root->sectorsize); new_size *= root->sectorsize; - printk_in_rcu(KERN_INFO "BTRFS: new size for %s is %llu\n", + btrfs_info_in_rcu(root->fs_info, "new size for %s is %llu", rcu_str_deref(device->name), new_size); if (new_size > old_size) { @@ -2081,7 +2085,7 @@ static noinline int search_ioctl(struct inode *inode, key.offset = (u64)-1; root = btrfs_read_fs_root_no_name(info, &key); if (IS_ERR(root)) { - printk(KERN_ERR "BTRFS: could not find root %llu\n", + btrfs_err(info, "could not find root %llu", sk->tree_id); btrfs_free_path(path); return -ENOENT; @@ -2221,7 +2225,7 @@ static noinline int btrfs_search_path_in_tree(struct btrfs_fs_info *info, key.offset = (u64)-1; root = btrfs_read_fs_root_no_name(info, &key); if (IS_ERR(root)) { - printk(KERN_ERR "BTRFS: could not find root %llu\n", tree_id); + btrfs_err(info, "could not find root %llu", tree_id); ret = -ENOENT; goto out; } @@ -2699,7 +2703,6 @@ static long btrfs_ioctl_fs_info(struct btrfs_root *root, void __user *arg) { struct btrfs_ioctl_fs_info_args *fi_args; struct btrfs_device *device; - struct btrfs_device *next; struct btrfs_fs_devices *fs_devices = root->fs_info->fs_devices; int ret = 0; @@ -2711,7 +2714,7 @@ static long btrfs_ioctl_fs_info(struct btrfs_root *root, void __user *arg) fi_args->num_devices = fs_devices->num_devices; memcpy(&fi_args->fsid, root->fs_info->fsid, sizeof(fi_args->fsid)); - list_for_each_entry_safe(device, next, &fs_devices->devices, dev_list) { + list_for_each_entry(device, &fs_devices->devices, dev_list) { if (device->devid > fi_args->max_id) fi_args->max_id = device->devid; } @@ -3203,41 +3206,6 @@ out: return ret; } -/* Helper to check and see if this root currently has a ref on the given disk - * bytenr. If it does then we need to update the quota for this root. This - * doesn't do anything if quotas aren't enabled. - */ -static int check_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, - u64 disko) -{ - struct seq_list tree_mod_seq_elem = SEQ_LIST_INIT(tree_mod_seq_elem); - struct ulist *roots; - struct ulist_iterator uiter; - struct ulist_node *root_node = NULL; - int ret; - - if (!root->fs_info->quota_enabled) - return 1; - - btrfs_get_tree_mod_seq(root->fs_info, &tree_mod_seq_elem); - ret = btrfs_find_all_roots(trans, root->fs_info, disko, - tree_mod_seq_elem.seq, &roots); - if (ret < 0) - goto out; - ret = 0; - ULIST_ITER_INIT(&uiter); - while ((root_node = ulist_next(roots, &uiter))) { - if (root_node->val == root->objectid) { - ret = 1; - break; - } - } - ulist_free(roots); -out: - btrfs_put_tree_mod_seq(root->fs_info, &tree_mod_seq_elem); - return ret; -} - static int clone_finish_inode_update(struct btrfs_trans_handle *trans, struct inode *inode, u64 endoff, @@ -3328,6 +3296,150 @@ static void clone_update_extent_map(struct inode *inode, &BTRFS_I(inode)->runtime_flags); } +/* + * Make sure we do not end up inserting an inline extent into a file that has + * already other (non-inline) extents. If a file has an inline extent it can + * not have any other extents and the (single) inline extent must start at the + * file offset 0. Failing to respect these rules will lead to file corruption, + * resulting in EIO errors on read/write operations, hitting BUG_ON's in mm, etc + * + * We can have extents that have been already written to disk or we can have + * dirty ranges still in delalloc, in which case the extent maps and items are + * created only when we run delalloc, and the delalloc ranges might fall outside + * the range we are currently locking in the inode's io tree. So we check the + * inode's i_size because of that (i_size updates are done while holding the + * i_mutex, which we are holding here). + * We also check to see if the inode has a size not greater than "datal" but has + * extents beyond it, due to an fallocate with FALLOC_FL_KEEP_SIZE (and we are + * protected against such concurrent fallocate calls by the i_mutex). + * + * If the file has no extents but a size greater than datal, do not allow the + * copy because we would need turn the inline extent into a non-inline one (even + * with NO_HOLES enabled). If we find our destination inode only has one inline + * extent, just overwrite it with the source inline extent if its size is less + * than the source extent's size, or we could copy the source inline extent's + * data into the destination inode's inline extent if the later is greater then + * the former. + */ +static int clone_copy_inline_extent(struct inode *src, + struct inode *dst, + struct btrfs_trans_handle *trans, + struct btrfs_path *path, + struct btrfs_key *new_key, + const u64 drop_start, + const u64 datal, + const u64 skip, + const u64 size, + char *inline_data) +{ + struct btrfs_root *root = BTRFS_I(dst)->root; + const u64 aligned_end = ALIGN(new_key->offset + datal, + root->sectorsize); + int ret; + struct btrfs_key key; + + if (new_key->offset > 0) + return -EOPNOTSUPP; + + key.objectid = btrfs_ino(dst); + key.type = BTRFS_EXTENT_DATA_KEY; + key.offset = 0; + ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); + if (ret < 0) { + return ret; + } else if (ret > 0) { + if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) { + ret = btrfs_next_leaf(root, path); + if (ret < 0) + return ret; + else if (ret > 0) + goto copy_inline_extent; + } + btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); + if (key.objectid == btrfs_ino(dst) && + key.type == BTRFS_EXTENT_DATA_KEY) { + ASSERT(key.offset > 0); + return -EOPNOTSUPP; + } + } else if (i_size_read(dst) <= datal) { + struct btrfs_file_extent_item *ei; + u64 ext_len; + + /* + * If the file size is <= datal, make sure there are no other + * extents following (can happen do to an fallocate call with + * the flag FALLOC_FL_KEEP_SIZE). + */ + ei = btrfs_item_ptr(path->nodes[0], path->slots[0], + struct btrfs_file_extent_item); + /* + * If it's an inline extent, it can not have other extents + * following it. + */ + if (btrfs_file_extent_type(path->nodes[0], ei) == + BTRFS_FILE_EXTENT_INLINE) + goto copy_inline_extent; + + ext_len = btrfs_file_extent_num_bytes(path->nodes[0], ei); + if (ext_len > aligned_end) + return -EOPNOTSUPP; + + ret = btrfs_next_item(root, path); + if (ret < 0) { + return ret; + } else if (ret == 0) { + btrfs_item_key_to_cpu(path->nodes[0], &key, + path->slots[0]); + if (key.objectid == btrfs_ino(dst) && + key.type == BTRFS_EXTENT_DATA_KEY) + return -EOPNOTSUPP; + } + } + +copy_inline_extent: + /* + * We have no extent items, or we have an extent at offset 0 which may + * or may not be inlined. All these cases are dealt the same way. + */ + if (i_size_read(dst) > datal) { + /* + * If the destination inode has an inline extent... + * This would require copying the data from the source inline + * extent into the beginning of the destination's inline extent. + * But this is really complex, both extents can be compressed + * or just one of them, which would require decompressing and + * re-compressing data (which could increase the new compressed + * size, not allowing the compressed data to fit anymore in an + * inline extent). + * So just don't support this case for now (it should be rare, + * we are not really saving space when cloning inline extents). + */ + return -EOPNOTSUPP; + } + + btrfs_release_path(path); + ret = btrfs_drop_extents(trans, root, dst, drop_start, aligned_end, 1); + if (ret) + return ret; + ret = btrfs_insert_empty_item(trans, root, path, new_key, size); + if (ret) + return ret; + + if (skip) { + const u32 start = btrfs_file_extent_calc_inline_size(0); + + memmove(inline_data + start, inline_data + start + skip, datal); + } + + write_extent_buffer(path->nodes[0], inline_data, + btrfs_item_ptr_offset(path->nodes[0], + path->slots[0]), + size); + inode_add_bytes(dst, datal); + + return 0; +} + /** * btrfs_clone() - clone a range from inode file to another * @@ -3352,9 +3464,7 @@ static int btrfs_clone(struct inode *src, struct inode *inode, u32 nritems; int slot; int ret; - int no_quota; const u64 len = olen_aligned; - u64 last_disko = 0; u64 last_dest_end = destoff; ret = -ENOMEM; @@ -3400,7 +3510,6 @@ static int btrfs_clone(struct inode *src, struct inode *inode, nritems = btrfs_header_nritems(path->nodes[0]); process_slot: - no_quota = 1; if (path->slots[0] >= nritems) { ret = btrfs_next_leaf(BTRFS_I(src)->root, path); if (ret < 0) @@ -3552,35 +3661,13 @@ process_slot: btrfs_set_file_extent_num_bytes(leaf, extent, datal); - /* - * We need to look up the roots that point at - * this bytenr and see if the new root does. If - * it does not we need to make sure we update - * quotas appropriately. - */ - if (disko && root != BTRFS_I(src)->root && - disko != last_disko) { - no_quota = check_ref(trans, root, - disko); - if (no_quota < 0) { - btrfs_abort_transaction(trans, - root, - ret); - btrfs_end_transaction(trans, - root); - ret = no_quota; - goto out; - } - } - if (disko) { inode_add_bytes(inode, datal); ret = btrfs_inc_extent_ref(trans, root, disko, diskl, 0, root->root_key.objectid, btrfs_ino(inode), - new_key.offset - datao, - no_quota); + new_key.offset - datao); if (ret) { btrfs_abort_transaction(trans, root, @@ -3594,21 +3681,6 @@ process_slot: } else if (type == BTRFS_FILE_EXTENT_INLINE) { u64 skip = 0; u64 trim = 0; - u64 aligned_end = 0; - - /* - * Don't copy an inline extent into an offset - * greater than zero. Having an inline extent - * at such an offset results in chaos as btrfs - * isn't prepared for such cases. Just skip - * this case for the same reasons as commented - * at btrfs_ioctl_clone(). - */ - if (last_dest_end > 0) { - ret = -EOPNOTSUPP; - btrfs_end_transaction(trans, root); - goto out; - } if (off > key.offset) { skip = off - key.offset; @@ -3626,42 +3698,22 @@ process_slot: size -= skip + trim; datal -= skip + trim; - aligned_end = ALIGN(new_key.offset + datal, - root->sectorsize); - ret = btrfs_drop_extents(trans, root, inode, - drop_start, - aligned_end, - 1); + ret = clone_copy_inline_extent(src, inode, + trans, path, + &new_key, + drop_start, + datal, + skip, size, buf); if (ret) { if (ret != -EOPNOTSUPP) btrfs_abort_transaction(trans, - root, ret); - btrfs_end_transaction(trans, root); - goto out; - } - - ret = btrfs_insert_empty_item(trans, root, path, - &new_key, size); - if (ret) { - btrfs_abort_transaction(trans, root, - ret); + root, + ret); btrfs_end_transaction(trans, root); goto out; } - - if (skip) { - u32 start = - btrfs_file_extent_calc_inline_size(0); - memmove(buf+start, buf+start+skip, - datal); - } - leaf = path->nodes[0]; slot = path->slots[0]; - write_extent_buffer(leaf, buf, - btrfs_item_ptr_offset(leaf, slot), - size); - inode_add_bytes(inode, datal); } /* If we have an implicit hole (NO_HOLES feature). */ @@ -4639,6 +4691,11 @@ locked: bctl->flags |= BTRFS_BALANCE_TYPE_MASK; } + if (bctl->flags & ~(BTRFS_BALANCE_ARGS_MASK | BTRFS_BALANCE_TYPE_MASK)) { + ret = -EINVAL; + goto out_bctl; + } + do_balance: /* * Ownership of bctl and mutually_exclusive_operation_running @@ -4650,12 +4707,15 @@ do_balance: need_unlock = false; ret = btrfs_balance(bctl, bargs); + bctl = NULL; if (arg) { if (copy_to_user(arg, bargs, sizeof(*bargs))) ret = -EFAULT; } +out_bctl: + kfree(bctl); out_bargs: kfree(bargs); out_unlock: @@ -4806,7 +4866,7 @@ static long btrfs_ioctl_qgroup_assign(struct file *file, void __user *arg) /* update qgroup status and info */ err = btrfs_run_qgroups(trans, root->fs_info); if (err < 0) - btrfs_error(root->fs_info, ret, + btrfs_std_error(root->fs_info, ret, "failed to update qgroup status and info\n"); err = btrfs_end_transaction(trans, root); if (err && !ret) diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c index d7e6baf..8077461 100644 --- a/fs/btrfs/locking.c +++ b/fs/btrfs/locking.c @@ -79,6 +79,9 @@ void btrfs_clear_lock_blocking_rw(struct extent_buffer *eb, int rw) write_lock(&eb->lock); WARN_ON(atomic_read(&eb->spinning_writers)); atomic_inc(&eb->spinning_writers); + /* + * atomic_dec_and_test implies a barrier for waitqueue_active + */ if (atomic_dec_and_test(&eb->blocking_writers) && waitqueue_active(&eb->write_lock_wq)) wake_up(&eb->write_lock_wq); @@ -86,6 +89,9 @@ void btrfs_clear_lock_blocking_rw(struct extent_buffer *eb, int rw) BUG_ON(atomic_read(&eb->blocking_readers) == 0); read_lock(&eb->lock); atomic_inc(&eb->spinning_readers); + /* + * atomic_dec_and_test implies a barrier for waitqueue_active + */ if (atomic_dec_and_test(&eb->blocking_readers) && waitqueue_active(&eb->read_lock_wq)) wake_up(&eb->read_lock_wq); @@ -229,6 +235,9 @@ void btrfs_tree_read_unlock_blocking(struct extent_buffer *eb) } btrfs_assert_tree_read_locked(eb); WARN_ON(atomic_read(&eb->blocking_readers) == 0); + /* + * atomic_dec_and_test implies a barrier for waitqueue_active + */ if (atomic_dec_and_test(&eb->blocking_readers) && waitqueue_active(&eb->read_lock_wq)) wake_up(&eb->read_lock_wq); @@ -280,6 +289,9 @@ void btrfs_tree_unlock(struct extent_buffer *eb) if (blockers) { WARN_ON(atomic_read(&eb->spinning_writers)); atomic_dec(&eb->blocking_writers); + /* + * Make sure counter is updated before we wake up waiters. + */ smp_mb(); if (waitqueue_active(&eb->write_lock_wq)) wake_up(&eb->write_lock_wq); diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index 52170cf..8c27292 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -345,6 +345,9 @@ int btrfs_dec_test_first_ordered_pending(struct inode *inode, if (entry->bytes_left == 0) { ret = test_and_set_bit(BTRFS_ORDERED_IO_DONE, &entry->flags); + /* + * Implicit memory barrier after test_and_set_bit + */ if (waitqueue_active(&entry->wait)) wake_up(&entry->wait); } else { @@ -409,6 +412,9 @@ have_entry: if (entry->bytes_left == 0) { ret = test_and_set_bit(BTRFS_ORDERED_IO_DONE, &entry->flags); + /* + * Implicit memory barrier after test_and_set_bit + */ if (waitqueue_active(&entry->wait)) wake_up(&entry->wait); } else { @@ -484,15 +490,16 @@ void btrfs_wait_logged_extents(struct btrfs_trans_handle *trans, spin_lock_irq(&log->log_extents_lock[index]); while (!list_empty(&log->logged_list[index])) { + struct inode *inode; ordered = list_first_entry(&log->logged_list[index], struct btrfs_ordered_extent, log_list); list_del_init(&ordered->log_list); + inode = ordered->inode; spin_unlock_irq(&log->log_extents_lock[index]); if (!test_bit(BTRFS_ORDERED_IO_DONE, &ordered->flags) && !test_bit(BTRFS_ORDERED_DIRECT, &ordered->flags)) { - struct inode *inode = ordered->inode; u64 start = ordered->file_offset; u64 end = ordered->file_offset + ordered->len - 1; @@ -503,20 +510,25 @@ void btrfs_wait_logged_extents(struct btrfs_trans_handle *trans, &ordered->flags)); /* - * If our ordered extent completed it means it updated the - * fs/subvol and csum trees already, so no need to make the - * current transaction's commit wait for it, as we end up - * holding memory unnecessarily and delaying the inode's iput - * until the transaction commit (we schedule an iput for the - * inode when the ordered extent's refcount drops to 0), which - * prevents it from being evictable until the transaction - * commits. + * In order to keep us from losing our ordered extent + * information when committing the transaction we have to make + * sure that any logged extents are completed when we go to + * commit the transaction. To do this we simply increase the + * current transactions pending_ordered counter and decrement it + * when the ordered extent completes. */ - if (test_bit(BTRFS_ORDERED_COMPLETE, &ordered->flags)) - btrfs_put_ordered_extent(ordered); - else - list_add_tail(&ordered->trans_list, &trans->ordered); - + if (!test_bit(BTRFS_ORDERED_COMPLETE, &ordered->flags)) { + struct btrfs_ordered_inode_tree *tree; + + tree = &BTRFS_I(inode)->ordered_tree; + spin_lock_irq(&tree->lock); + if (!test_bit(BTRFS_ORDERED_COMPLETE, &ordered->flags)) { + set_bit(BTRFS_ORDERED_PENDING, &ordered->flags); + atomic_inc(&trans->transaction->pending_ordered); + } + spin_unlock_irq(&tree->lock); + } + btrfs_put_ordered_extent(ordered); spin_lock_irq(&log->log_extents_lock[index]); } spin_unlock_irq(&log->log_extents_lock[index]); @@ -578,6 +590,7 @@ void btrfs_remove_ordered_extent(struct inode *inode, struct btrfs_ordered_inode_tree *tree; struct btrfs_root *root = BTRFS_I(inode)->root; struct rb_node *node; + bool dec_pending_ordered = false; tree = &BTRFS_I(inode)->ordered_tree; spin_lock_irq(&tree->lock); @@ -587,8 +600,37 @@ void btrfs_remove_ordered_extent(struct inode *inode, if (tree->last == node) tree->last = NULL; set_bit(BTRFS_ORDERED_COMPLETE, &entry->flags); + if (test_and_clear_bit(BTRFS_ORDERED_PENDING, &entry->flags)) + dec_pending_ordered = true; spin_unlock_irq(&tree->lock); + /* + * The current running transaction is waiting on us, we need to let it + * know that we're complete and wake it up. + */ + if (dec_pending_ordered) { + struct btrfs_transaction *trans; + + /* + * The checks for trans are just a formality, it should be set, + * but if it isn't we don't want to deref/assert under the spin + * lock, so be nice and check if trans is set, but ASSERT() so + * if it isn't set a developer will notice. + */ + spin_lock(&root->fs_info->trans_lock); + trans = root->fs_info->running_transaction; + if (trans) + atomic_inc(&trans->use_count); + spin_unlock(&root->fs_info->trans_lock); + + ASSERT(trans); + if (trans) { + if (atomic_dec_and_test(&trans->pending_ordered)) + wake_up(&trans->pending_wait); + btrfs_put_transaction(trans); + } + } + spin_lock(&root->ordered_extent_lock); list_del_init(&entry->root_extent_list); root->nr_ordered_extents--; diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h index 7176cc0..23c9605 100644 --- a/fs/btrfs/ordered-data.h +++ b/fs/btrfs/ordered-data.h @@ -73,6 +73,8 @@ struct btrfs_ordered_sum { #define BTRFS_ORDERED_LOGGED 10 /* Set when we've waited on this ordered extent * in the logging code. */ +#define BTRFS_ORDERED_PENDING 11 /* We are waiting for this ordered extent to + * complete in the current transaction. */ struct btrfs_ordered_extent { /* logical offset in the file */ u64 file_offset; diff --git a/fs/btrfs/props.c b/fs/btrfs/props.c index dca137b..f9e6023 100644 --- a/fs/btrfs/props.c +++ b/fs/btrfs/props.c @@ -49,18 +49,16 @@ static struct prop_handler prop_handlers[] = { .extract = prop_compression_extract, .inheritable = 1 }, - { - .xattr_name = NULL - } }; void __init btrfs_props_init(void) { - struct prop_handler *p; + int i; hash_init(prop_handlers_ht); - for (p = &prop_handlers[0]; p->xattr_name; p++) { + for (i = 0; i < ARRAY_SIZE(prop_handlers); i++) { + struct prop_handler *p = &prop_handlers[i]; u64 h = btrfs_name_hash(p->xattr_name, strlen(p->xattr_name)); hash_add(prop_handlers_ht, &p->node, h); @@ -301,15 +299,16 @@ static int inherit_props(struct btrfs_trans_handle *trans, struct inode *inode, struct inode *parent) { - const struct prop_handler *h; struct btrfs_root *root = BTRFS_I(inode)->root; int ret; + int i; if (!test_bit(BTRFS_INODE_HAS_PROPS, &BTRFS_I(parent)->runtime_flags)) return 0; - for (h = &prop_handlers[0]; h->xattr_name; h++) { + for (i = 0; i < ARRAY_SIZE(prop_handlers); i++) { + const struct prop_handler *h = &prop_handlers[i]; const char *value; u64 num_bytes; diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index d904ee1..46476c2 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1652,10 +1652,6 @@ static int qgroup_update_counters(struct btrfs_fs_info *fs_info, } } - /* For exclusive extent, free its reserved bytes too */ - if (nr_old_roots == 0 && nr_new_roots == 1 && - cur_new_count == nr_new_roots) - qg->reserved -= num_bytes; if (dirty) qgroup_dirty(fs_info, qg); } @@ -2035,7 +2031,7 @@ out: return ret; } -int btrfs_qgroup_reserve(struct btrfs_root *root, u64 num_bytes) +static int qgroup_reserve(struct btrfs_root *root, u64 num_bytes) { struct btrfs_root *quota_root; struct btrfs_qgroup *qgroup; @@ -2116,14 +2112,13 @@ out: return ret; } -void btrfs_qgroup_free(struct btrfs_root *root, u64 num_bytes) +void btrfs_qgroup_free_refroot(struct btrfs_fs_info *fs_info, + u64 ref_root, u64 num_bytes) { struct btrfs_root *quota_root; struct btrfs_qgroup *qgroup; - struct btrfs_fs_info *fs_info = root->fs_info; struct ulist_node *unode; struct ulist_iterator uiter; - u64 ref_root = root->root_key.objectid; int ret = 0; if (!is_fstree(ref_root)) @@ -2169,6 +2164,11 @@ out: spin_unlock(&fs_info->qgroup_lock); } +static inline void qgroup_free(struct btrfs_root *root, u64 num_bytes) +{ + return btrfs_qgroup_free_refroot(root->fs_info, root->objectid, + num_bytes); +} void assert_qgroups_uptodate(struct btrfs_trans_handle *trans) { if (list_empty(&trans->qgroup_ref_list) && !trans->delayed_ref_elem.seq) @@ -2188,10 +2188,10 @@ void assert_qgroups_uptodate(struct btrfs_trans_handle *trans) */ static int qgroup_rescan_leaf(struct btrfs_fs_info *fs_info, struct btrfs_path *path, - struct btrfs_trans_handle *trans, - struct extent_buffer *scratch_leaf) + struct btrfs_trans_handle *trans) { struct btrfs_key found; + struct extent_buffer *scratch_leaf = NULL; struct ulist *roots = NULL; struct seq_list tree_mod_seq_elem = SEQ_LIST_INIT(tree_mod_seq_elem); u64 num_bytes; @@ -2229,7 +2229,15 @@ qgroup_rescan_leaf(struct btrfs_fs_info *fs_info, struct btrfs_path *path, fs_info->qgroup_rescan_progress.objectid = found.objectid + 1; btrfs_get_tree_mod_seq(fs_info, &tree_mod_seq_elem); - memcpy(scratch_leaf, path->nodes[0], sizeof(*scratch_leaf)); + scratch_leaf = btrfs_clone_extent_buffer(path->nodes[0]); + if (!scratch_leaf) { + ret = -ENOMEM; + mutex_unlock(&fs_info->qgroup_rescan_lock); + goto out; + } + extent_buffer_get(scratch_leaf); + btrfs_tree_read_lock(scratch_leaf); + btrfs_set_lock_blocking_rw(scratch_leaf, BTRFS_READ_LOCK); slot = path->slots[0]; btrfs_release_path(path); mutex_unlock(&fs_info->qgroup_rescan_lock); @@ -2255,6 +2263,10 @@ qgroup_rescan_leaf(struct btrfs_fs_info *fs_info, struct btrfs_path *path, goto out; } out: + if (scratch_leaf) { + btrfs_tree_read_unlock_blocking(scratch_leaf); + free_extent_buffer(scratch_leaf); + } btrfs_put_tree_mod_seq(fs_info, &tree_mod_seq_elem); return ret; @@ -2266,16 +2278,12 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work) qgroup_rescan_work); struct btrfs_path *path; struct btrfs_trans_handle *trans = NULL; - struct extent_buffer *scratch_leaf = NULL; int err = -ENOMEM; int ret = 0; path = btrfs_alloc_path(); if (!path) goto out; - scratch_leaf = kmalloc(sizeof(*scratch_leaf), GFP_NOFS); - if (!scratch_leaf) - goto out; err = 0; while (!err) { @@ -2287,8 +2295,7 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work) if (!fs_info->quota_enabled) { err = -EINTR; } else { - err = qgroup_rescan_leaf(fs_info, path, trans, - scratch_leaf); + err = qgroup_rescan_leaf(fs_info, path, trans); } if (err > 0) btrfs_commit_transaction(trans, fs_info->fs_root); @@ -2297,7 +2304,6 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work) } out: - kfree(scratch_leaf); btrfs_free_path(path); mutex_lock(&fs_info->qgroup_rescan_lock); @@ -2486,3 +2492,190 @@ btrfs_qgroup_rescan_resume(struct btrfs_fs_info *fs_info) btrfs_queue_work(fs_info->qgroup_rescan_workers, &fs_info->qgroup_rescan_work); } + +/* + * Reserve qgroup space for range [start, start + len). + * + * This function will either reserve space from related qgroups or doing + * nothing if the range is already reserved. + * + * Return 0 for successful reserve + * Return <0 for error (including -EQUOT) + * + * NOTE: this function may sleep for memory allocation. + */ +int btrfs_qgroup_reserve_data(struct inode *inode, u64 start, u64 len) +{ + struct btrfs_root *root = BTRFS_I(inode)->root; + struct extent_changeset changeset; + struct ulist_node *unode; + struct ulist_iterator uiter; + int ret; + + if (!root->fs_info->quota_enabled || !is_fstree(root->objectid) || + len == 0) + return 0; + + changeset.bytes_changed = 0; + changeset.range_changed = ulist_alloc(GFP_NOFS); + ret = set_record_extent_bits(&BTRFS_I(inode)->io_tree, start, + start + len -1, EXTENT_QGROUP_RESERVED, GFP_NOFS, + &changeset); + trace_btrfs_qgroup_reserve_data(inode, start, len, + changeset.bytes_changed, + QGROUP_RESERVE); + if (ret < 0) + goto cleanup; + ret = qgroup_reserve(root, changeset.bytes_changed); + if (ret < 0) + goto cleanup; + + ulist_free(changeset.range_changed); + return ret; + +cleanup: + /* cleanup already reserved ranges */ + ULIST_ITER_INIT(&uiter); + while ((unode = ulist_next(changeset.range_changed, &uiter))) + clear_extent_bit(&BTRFS_I(inode)->io_tree, unode->val, + unode->aux, EXTENT_QGROUP_RESERVED, 0, 0, NULL, + GFP_NOFS); + ulist_free(changeset.range_changed); + return ret; +} + +static int __btrfs_qgroup_release_data(struct inode *inode, u64 start, u64 len, + int free) +{ + struct extent_changeset changeset; + int trace_op = QGROUP_RELEASE; + int ret; + + changeset.bytes_changed = 0; + changeset.range_changed = ulist_alloc(GFP_NOFS); + if (!changeset.range_changed) + return -ENOMEM; + + ret = clear_record_extent_bits(&BTRFS_I(inode)->io_tree, start, + start + len -1, EXTENT_QGROUP_RESERVED, GFP_NOFS, + &changeset); + if (ret < 0) + goto out; + + if (free) { + qgroup_free(BTRFS_I(inode)->root, changeset.bytes_changed); + trace_op = QGROUP_FREE; + } + trace_btrfs_qgroup_release_data(inode, start, len, + changeset.bytes_changed, trace_op); +out: + ulist_free(changeset.range_changed); + return ret; +} + +/* + * Free a reserved space range from io_tree and related qgroups + * + * Should be called when a range of pages get invalidated before reaching disk. + * Or for error cleanup case. + * + * For data written to disk, use btrfs_qgroup_release_data(). + * + * NOTE: This function may sleep for memory allocation. + */ +int btrfs_qgroup_free_data(struct inode *inode, u64 start, u64 len) +{ + return __btrfs_qgroup_release_data(inode, start, len, 1); +} + +/* + * Release a reserved space range from io_tree only. + * + * Should be called when a range of pages get written to disk and corresponding + * FILE_EXTENT is inserted into corresponding root. + * + * Since new qgroup accounting framework will only update qgroup numbers at + * commit_transaction() time, its reserved space shouldn't be freed from + * related qgroups. + * + * But we should release the range from io_tree, to allow further write to be + * COWed. + * + * NOTE: This function may sleep for memory allocation. + */ +int btrfs_qgroup_release_data(struct inode *inode, u64 start, u64 len) +{ + return __btrfs_qgroup_release_data(inode, start, len, 0); +} + +int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes) +{ + int ret; + + if (!root->fs_info->quota_enabled || !is_fstree(root->objectid) || + num_bytes == 0) + return 0; + + BUG_ON(num_bytes != round_down(num_bytes, root->nodesize)); + ret = qgroup_reserve(root, num_bytes); + if (ret < 0) + return ret; + atomic_add(num_bytes, &root->qgroup_meta_rsv); + return ret; +} + +void btrfs_qgroup_free_meta_all(struct btrfs_root *root) +{ + int reserved; + + if (!root->fs_info->quota_enabled || !is_fstree(root->objectid)) + return; + + reserved = atomic_xchg(&root->qgroup_meta_rsv, 0); + if (reserved == 0) + return; + qgroup_free(root, reserved); +} + +void btrfs_qgroup_free_meta(struct btrfs_root *root, int num_bytes) +{ + if (!root->fs_info->quota_enabled || !is_fstree(root->objectid)) + return; + + BUG_ON(num_bytes != round_down(num_bytes, root->nodesize)); + WARN_ON(atomic_read(&root->qgroup_meta_rsv) < num_bytes); + atomic_sub(num_bytes, &root->qgroup_meta_rsv); + qgroup_free(root, num_bytes); +} + +/* + * Check qgroup reserved space leaking, normally at destory inode + * time + */ +void btrfs_qgroup_check_reserved_leak(struct inode *inode) +{ + struct extent_changeset changeset; + struct ulist_node *unode; + struct ulist_iterator iter; + int ret; + + changeset.bytes_changed = 0; + changeset.range_changed = ulist_alloc(GFP_NOFS); + if (WARN_ON(!changeset.range_changed)) + return; + + ret = clear_record_extent_bits(&BTRFS_I(inode)->io_tree, 0, (u64)-1, + EXTENT_QGROUP_RESERVED, GFP_NOFS, &changeset); + + WARN_ON(ret < 0); + if (WARN_ON(changeset.bytes_changed)) { + ULIST_ITER_INIT(&iter); + while ((unode = ulist_next(changeset.range_changed, &iter))) { + btrfs_warn(BTRFS_I(inode)->root->fs_info, + "leaking qgroup reserved space, ino: %lu, start: %llu, end: %llu", + inode->i_ino, unode->val, unode->aux); + } + qgroup_free(BTRFS_I(inode)->root, changeset.bytes_changed); + } + ulist_free(changeset.range_changed); +} diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h index 6387dcf..ecb2c14 100644 --- a/fs/btrfs/qgroup.h +++ b/fs/btrfs/qgroup.h @@ -33,6 +33,13 @@ struct btrfs_qgroup_extent_record { struct ulist *old_roots; }; +/* + * For qgroup event trace points only + */ +#define QGROUP_RESERVE (1<<0) +#define QGROUP_RELEASE (1<<1) +#define QGROUP_FREE (1<<2) + int btrfs_quota_enable(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info); int btrfs_quota_disable(struct btrfs_trans_handle *trans, @@ -71,9 +78,18 @@ int btrfs_run_qgroups(struct btrfs_trans_handle *trans, int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, u64 srcid, u64 objectid, struct btrfs_qgroup_inherit *inherit); -int btrfs_qgroup_reserve(struct btrfs_root *root, u64 num_bytes); -void btrfs_qgroup_free(struct btrfs_root *root, u64 num_bytes); - +void btrfs_qgroup_free_refroot(struct btrfs_fs_info *fs_info, + u64 ref_root, u64 num_bytes); +/* + * TODO: Add proper trace point for it, as btrfs_qgroup_free() is + * called by everywhere, can't provide good trace for delayed ref case. + */ +static inline void btrfs_qgroup_free_delayed_ref(struct btrfs_fs_info *fs_info, + u64 ref_root, u64 num_bytes) +{ + btrfs_qgroup_free_refroot(fs_info, ref_root, num_bytes); + trace_btrfs_qgroup_free_delayed_ref(ref_root, num_bytes); +} void assert_qgroups_uptodate(struct btrfs_trans_handle *trans); #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS @@ -81,4 +97,13 @@ int btrfs_verify_qgroup_counts(struct btrfs_fs_info *fs_info, u64 qgroupid, u64 rfer, u64 excl); #endif +/* New io_tree based accurate qgroup reserve API */ +int btrfs_qgroup_reserve_data(struct inode *inode, u64 start, u64 len); +int btrfs_qgroup_release_data(struct inode *inode, u64 start, u64 len); +int btrfs_qgroup_free_data(struct inode *inode, u64 start, u64 len); + +int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes); +void btrfs_qgroup_free_meta_all(struct btrfs_root *root); +void btrfs_qgroup_free_meta(struct btrfs_root *root, int num_bytes); +void btrfs_qgroup_check_reserved_leak(struct inode *inode); #endif /* __BTRFS_QGROUP__ */ diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index fcf7265..1a33d3e 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -810,7 +810,11 @@ static noinline void unlock_stripe(struct btrfs_raid_bio *rbio) } goto done_nolock; - } else if (waitqueue_active(&h->wait)) { + /* + * The barrier for this waitqueue_active is not needed, + * we're protected by h->lock and can't miss a wakeup. + */ + } else if (waitqueue_active(&h->wait)) { spin_unlock(&rbio->bio_list_lock); spin_unlock_irqrestore(&h->lock, flags); wake_up(&h->wait); diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c index 4645cd1..619f929 100644 --- a/fs/btrfs/reada.c +++ b/fs/btrfs/reada.c @@ -569,7 +569,7 @@ static int reada_add_block(struct reada_control *rc, u64 logical, rec = kzalloc(sizeof(*rec), GFP_NOFS); if (!rec) { reada_extent_put(root->fs_info, re); - return -1; + return -ENOMEM; } rec->rc = rc; @@ -918,6 +918,7 @@ struct reada_control *btrfs_reada_add(struct btrfs_root *root, u64 start; u64 generation; int level; + int ret; struct extent_buffer *node; static struct btrfs_key max_key = { .objectid = (u64)-1, @@ -943,9 +944,10 @@ struct reada_control *btrfs_reada_add(struct btrfs_root *root, generation = btrfs_header_generation(node); free_extent_buffer(node); - if (reada_add_block(rc, start, &max_key, level, generation)) { + ret = reada_add_block(rc, start, &max_key, level, generation); + if (ret) { kfree(rc); - return ERR_PTR(-ENOMEM); + return ERR_PTR(ret); } reada_start_machine(root->fs_info); diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 303babe..b4ca545 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -1716,7 +1716,7 @@ int replace_file_extents(struct btrfs_trans_handle *trans, ret = btrfs_inc_extent_ref(trans, root, new_bytenr, num_bytes, parent, btrfs_header_owner(leaf), - key.objectid, key.offset, 1); + key.objectid, key.offset); if (ret) { btrfs_abort_transaction(trans, root, ret); break; @@ -1724,7 +1724,7 @@ int replace_file_extents(struct btrfs_trans_handle *trans, ret = btrfs_free_extent(trans, root, bytenr, num_bytes, parent, btrfs_header_owner(leaf), - key.objectid, key.offset, 1); + key.objectid, key.offset); if (ret) { btrfs_abort_transaction(trans, root, ret); break; @@ -1900,23 +1900,21 @@ again: ret = btrfs_inc_extent_ref(trans, src, old_bytenr, blocksize, path->nodes[level]->start, - src->root_key.objectid, level - 1, 0, - 1); + src->root_key.objectid, level - 1, 0); BUG_ON(ret); ret = btrfs_inc_extent_ref(trans, dest, new_bytenr, blocksize, 0, dest->root_key.objectid, level - 1, - 0, 1); + 0); BUG_ON(ret); ret = btrfs_free_extent(trans, src, new_bytenr, blocksize, path->nodes[level]->start, - src->root_key.objectid, level - 1, 0, - 1); + src->root_key.objectid, level - 1, 0); BUG_ON(ret); ret = btrfs_free_extent(trans, dest, old_bytenr, blocksize, 0, dest->root_key.objectid, level - 1, - 0, 1); + 0); BUG_ON(ret); btrfs_unlock_up_safe(path, 0); @@ -2418,7 +2416,7 @@ again: } out: if (ret) { - btrfs_std_error(root->fs_info, ret); + btrfs_std_error(root->fs_info, ret, NULL); if (!list_empty(&reloc_roots)) free_reloc_roots(&reloc_roots); @@ -2745,7 +2743,7 @@ static int do_relocation(struct btrfs_trans_handle *trans, node->eb->start, blocksize, upper->eb->start, btrfs_header_owner(upper->eb), - node->level, 0, 1); + node->level, 0); BUG_ON(ret); ret = btrfs_drop_subtree(trans, root, eb, upper->eb); @@ -3034,8 +3032,8 @@ int prealloc_file_extent_cluster(struct inode *inode, BUG_ON(cluster->start != cluster->boundary[0]); mutex_lock(&inode->i_mutex); - ret = btrfs_check_data_free_space(inode, cluster->end + - 1 - cluster->start, 0); + ret = btrfs_check_data_free_space(inode, cluster->start, + cluster->end + 1 - cluster->start); if (ret) goto out; @@ -3056,8 +3054,8 @@ int prealloc_file_extent_cluster(struct inode *inode, break; nr++; } - btrfs_free_reserved_data_space(inode, cluster->end + - 1 - cluster->start); + btrfs_free_reserved_data_space(inode, cluster->start, + cluster->end + 1 - cluster->start); out: mutex_unlock(&inode->i_mutex); return ret; diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c index 360a728..7cf8509 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -45,12 +45,13 @@ static void btrfs_read_root_item(struct extent_buffer *eb, int slot, if (!need_reset && btrfs_root_generation(item) != btrfs_root_generation_v2(item)) { if (btrfs_root_generation_v2(item) != 0) { - printk(KERN_WARNING "BTRFS: mismatching " + btrfs_warn(eb->fs_info, + "mismatching " "generation and generation_v2 " "found in root item. This root " "was probably mounted with an " "older kernel. Resetting all " - "new fields.\n"); + "new fields."); } need_reset = 1; } @@ -141,7 +142,7 @@ int btrfs_update_root(struct btrfs_trans_handle *trans, struct btrfs_root int ret; int slot; unsigned long ptr; - int old_len; + u32 old_len; path = btrfs_alloc_path(); if (!path) @@ -283,7 +284,7 @@ int btrfs_find_orphan_roots(struct btrfs_root *tree_root) trans = btrfs_join_transaction(tree_root); if (IS_ERR(trans)) { err = PTR_ERR(trans); - btrfs_error(tree_root->fs_info, err, + btrfs_std_error(tree_root->fs_info, err, "Failed to start trans to delete " "orphan item"); break; @@ -292,7 +293,7 @@ int btrfs_find_orphan_roots(struct btrfs_root *tree_root) root_key.objectid); btrfs_end_transaction(trans, tree_root); if (err) { - btrfs_error(tree_root->fs_info, err, + btrfs_std_error(tree_root->fs_info, err, "Failed to delete root orphan " "item"); break; diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index a39f5d1..550de89 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -580,9 +580,9 @@ static int scrub_print_warning_inode(u64 inum, u64 offset, u64 root, * hold all of the paths here */ for (i = 0; i < ipath->fspath->elem_cnt; ++i) - printk_in_rcu(KERN_WARNING "BTRFS: %s at logical %llu on dev " + btrfs_warn_in_rcu(fs_info, "%s at logical %llu on dev " "%s, sector %llu, root %llu, inode %llu, offset %llu, " - "length %llu, links %u (path: %s)\n", swarn->errstr, + "length %llu, links %u (path: %s)", swarn->errstr, swarn->logical, rcu_str_deref(swarn->dev->name), (unsigned long long)swarn->sector, root, inum, offset, min(isize - offset, (u64)PAGE_SIZE), nlink, @@ -592,9 +592,9 @@ static int scrub_print_warning_inode(u64 inum, u64 offset, u64 root, return 0; err: - printk_in_rcu(KERN_WARNING "BTRFS: %s at logical %llu on dev " + btrfs_warn_in_rcu(fs_info, "%s at logical %llu on dev " "%s, sector %llu, root %llu, inode %llu, offset %llu: path " - "resolving failed with ret=%d\n", swarn->errstr, + "resolving failed with ret=%d", swarn->errstr, swarn->logical, rcu_str_deref(swarn->dev->name), (unsigned long long)swarn->sector, root, inum, offset, ret); @@ -649,10 +649,10 @@ static void scrub_print_warning(const char *errstr, struct scrub_block *sblock) ret = tree_backref_for_extent(&ptr, eb, &found_key, ei, item_size, &ref_root, &ref_level); - printk_in_rcu(KERN_WARNING - "BTRFS: %s at logical %llu on dev %s, " + btrfs_warn_in_rcu(fs_info, + "%s at logical %llu on dev %s, " "sector %llu: metadata %s (level %d) in tree " - "%llu\n", errstr, swarn.logical, + "%llu", errstr, swarn.logical, rcu_str_deref(dev->name), (unsigned long long)swarn.sector, ref_level ? "node" : "leaf", @@ -850,8 +850,8 @@ out: btrfs_dev_replace_stats_inc( &sctx->dev_root->fs_info->dev_replace. num_uncorrectable_read_errors); - printk_ratelimited_in_rcu(KERN_ERR "BTRFS: " - "unable to fixup (nodatasum) error at logical %llu on dev %s\n", + btrfs_err_rl_in_rcu(sctx->dev_root->fs_info, + "unable to fixup (nodatasum) error at logical %llu on dev %s", fixup->logical, rcu_str_deref(fixup->dev->name)); } @@ -1230,8 +1230,8 @@ corrected_error: sctx->stat.corrected_errors++; sblock_to_check->data_corrected = 1; spin_unlock(&sctx->stat_lock); - printk_ratelimited_in_rcu(KERN_ERR - "BTRFS: fixed up error at logical %llu on dev %s\n", + btrfs_err_rl_in_rcu(fs_info, + "fixed up error at logical %llu on dev %s", logical, rcu_str_deref(dev->name)); } } else { @@ -1239,8 +1239,8 @@ did_not_correct_error: spin_lock(&sctx->stat_lock); sctx->stat.uncorrectable_errors++; spin_unlock(&sctx->stat_lock); - printk_ratelimited_in_rcu(KERN_ERR - "BTRFS: unable to fixup (regular) error at logical %llu on dev %s\n", + btrfs_err_rl_in_rcu(fs_info, + "unable to fixup (regular) error at logical %llu on dev %s", logical, rcu_str_deref(dev->name)); } @@ -1626,9 +1626,9 @@ static int scrub_repair_page_from_good_copy(struct scrub_block *sblock_bad, int ret; if (!page_bad->dev->bdev) { - printk_ratelimited(KERN_WARNING "BTRFS: " + btrfs_warn_rl(sblock_bad->sctx->dev_root->fs_info, "scrub_repair_page_from_good_copy(bdev == NULL) " - "is unexpected!\n"); + "is unexpected"); return -EIO; } @@ -2201,15 +2201,15 @@ static void scrub_missing_raid56_worker(struct btrfs_work *work) spin_lock(&sctx->stat_lock); sctx->stat.read_errors++; spin_unlock(&sctx->stat_lock); - printk_ratelimited_in_rcu(KERN_ERR - "BTRFS: I/O error rebulding logical %llu for dev %s\n", + btrfs_err_rl_in_rcu(fs_info, + "IO error rebuilding logical %llu for dev %s", logical, rcu_str_deref(dev->name)); } else if (sblock->header_error || sblock->checksum_error) { spin_lock(&sctx->stat_lock); sctx->stat.uncorrectable_errors++; spin_unlock(&sctx->stat_lock); - printk_ratelimited_in_rcu(KERN_ERR - "BTRFS: failed to rebuild valid logical %llu for dev %s\n", + btrfs_err_rl_in_rcu(fs_info, + "failed to rebuild valid logical %llu for dev %s", logical, rcu_str_deref(dev->name)); } else { scrub_write_block_to_dev_replace(sblock); @@ -4375,8 +4375,8 @@ static int write_page_nocow(struct scrub_ctx *sctx, if (!dev) return -EIO; if (!dev->bdev) { - printk_ratelimited(KERN_WARNING - "BTRFS: scrub write_page_nocow(bdev == NULL) is unexpected!\n"); + btrfs_warn_rl(dev->dev_root->fs_info, + "scrub write_page_nocow(bdev == NULL) is unexpected"); return -EIO; } bio = btrfs_io_bio_alloc(GFP_NOFS, 1); diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index aa72bfd..355a458 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -1434,16 +1434,6 @@ verbose_printk(KERN_DEBUG "btrfs: find_extent_clone: data_offset=%llu, " } if (cur_clone_root) { - if (compressed != BTRFS_COMPRESS_NONE) { - /* - * Offsets given by iterate_extent_inodes() are relative - * to the start of the extent, we need to add logical - * offset from the file extent item. - * (See why at backref.c:check_extent_in_eb()) - */ - cur_clone_root->offset += btrfs_file_extent_offset(eb, - fi); - } *found = cur_clone_root; ret = 0; } else { @@ -1920,10 +1910,12 @@ static int did_overwrite_ref(struct send_ctx *sctx, /* * We know that it is or will be overwritten. Check this now. * The current inode being processed might have been the one that caused - * inode 'ino' to be orphanized, therefore ow_inode can actually be the - * same as sctx->send_progress. + * inode 'ino' to be orphanized, therefore check if ow_inode matches + * the current inode being processed. */ - if (ow_inode <= sctx->send_progress) + if ((ow_inode < sctx->send_progress) || + (ino != sctx->cur_ino && ow_inode == sctx->cur_ino && + gen == sctx->cur_inode_gen)) ret = 1; else ret = 0; @@ -2351,8 +2343,14 @@ static int send_subvol_begin(struct send_ctx *sctx) } TLV_PUT_STRING(sctx, BTRFS_SEND_A_PATH, name, namelen); - TLV_PUT_UUID(sctx, BTRFS_SEND_A_UUID, - sctx->send_root->root_item.uuid); + + if (!btrfs_is_empty_uuid(sctx->send_root->root_item.received_uuid)) + TLV_PUT_UUID(sctx, BTRFS_SEND_A_UUID, + sctx->send_root->root_item.received_uuid); + else + TLV_PUT_UUID(sctx, BTRFS_SEND_A_UUID, + sctx->send_root->root_item.uuid); + TLV_PUT_U64(sctx, BTRFS_SEND_A_CTRANSID, le64_to_cpu(sctx->send_root->root_item.ctransid)); if (parent_root) { @@ -2562,7 +2560,7 @@ verbose_printk("btrfs: send_create_inode %llu\n", ino); } else if (S_ISSOCK(mode)) { cmd = BTRFS_SEND_C_MKSOCK; } else { - printk(KERN_WARNING "btrfs: unexpected inode type %o", + btrfs_warn(sctx->send_root->fs_info, "unexpected inode type %o", (int)(mode & S_IFMT)); ret = -ENOTSUPP; goto out; @@ -4685,6 +4683,171 @@ tlv_put_failure: return ret; } +static int send_extent_data(struct send_ctx *sctx, + const u64 offset, + const u64 len) +{ + u64 sent = 0; + + if (sctx->flags & BTRFS_SEND_FLAG_NO_FILE_DATA) + return send_update_extent(sctx, offset, len); + + while (sent < len) { + u64 size = len - sent; + int ret; + + if (size > BTRFS_SEND_READ_SIZE) + size = BTRFS_SEND_READ_SIZE; + ret = send_write(sctx, offset + sent, size); + if (ret < 0) + return ret; + if (!ret) + break; + sent += ret; + } + return 0; +} + +static int clone_range(struct send_ctx *sctx, + struct clone_root *clone_root, + const u64 disk_byte, + u64 data_offset, + u64 offset, + u64 len) +{ + struct btrfs_path *path; + struct btrfs_key key; + int ret; + + path = alloc_path_for_send(); + if (!path) + return -ENOMEM; + + /* + * We can't send a clone operation for the entire range if we find + * extent items in the respective range in the source file that + * refer to different extents or if we find holes. + * So check for that and do a mix of clone and regular write/copy + * operations if needed. + * + * Example: + * + * mkfs.btrfs -f /dev/sda + * mount /dev/sda /mnt + * xfs_io -f -c "pwrite -S 0xaa 0K 100K" /mnt/foo + * cp --reflink=always /mnt/foo /mnt/bar + * xfs_io -c "pwrite -S 0xbb 50K 50K" /mnt/foo + * btrfs subvolume snapshot -r /mnt /mnt/snap + * + * If when we send the snapshot and we are processing file bar (which + * has a higher inode number than foo) we blindly send a clone operation + * for the [0, 100K[ range from foo to bar, the receiver ends up getting + * a file bar that matches the content of file foo - iow, doesn't match + * the content from bar in the original filesystem. + */ + key.objectid = clone_root->ino; + key.type = BTRFS_EXTENT_DATA_KEY; + key.offset = clone_root->offset; + ret = btrfs_search_slot(NULL, clone_root->root, &key, path, 0, 0); + if (ret < 0) + goto out; + if (ret > 0 && path->slots[0] > 0) { + btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0] - 1); + if (key.objectid == clone_root->ino && + key.type == BTRFS_EXTENT_DATA_KEY) + path->slots[0]--; + } + + while (true) { + struct extent_buffer *leaf = path->nodes[0]; + int slot = path->slots[0]; + struct btrfs_file_extent_item *ei; + u8 type; + u64 ext_len; + u64 clone_len; + + if (slot >= btrfs_header_nritems(leaf)) { + ret = btrfs_next_leaf(clone_root->root, path); + if (ret < 0) + goto out; + else if (ret > 0) + break; + continue; + } + + btrfs_item_key_to_cpu(leaf, &key, slot); + + /* + * We might have an implicit trailing hole (NO_HOLES feature + * enabled). We deal with it after leaving this loop. + */ + if (key.objectid != clone_root->ino || + key.type != BTRFS_EXTENT_DATA_KEY) + break; + + ei = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item); + type = btrfs_file_extent_type(leaf, ei); + if (type == BTRFS_FILE_EXTENT_INLINE) { + ext_len = btrfs_file_extent_inline_len(leaf, slot, ei); + ext_len = PAGE_CACHE_ALIGN(ext_len); + } else { + ext_len = btrfs_file_extent_num_bytes(leaf, ei); + } + + if (key.offset + ext_len <= clone_root->offset) + goto next; + + if (key.offset > clone_root->offset) { + /* Implicit hole, NO_HOLES feature enabled. */ + u64 hole_len = key.offset - clone_root->offset; + + if (hole_len > len) + hole_len = len; + ret = send_extent_data(sctx, offset, hole_len); + if (ret < 0) + goto out; + + len -= hole_len; + if (len == 0) + break; + offset += hole_len; + clone_root->offset += hole_len; + data_offset += hole_len; + } + + if (key.offset >= clone_root->offset + len) + break; + + clone_len = min_t(u64, ext_len, len); + + if (btrfs_file_extent_disk_bytenr(leaf, ei) == disk_byte && + btrfs_file_extent_offset(leaf, ei) == data_offset) + ret = send_clone(sctx, offset, clone_len, clone_root); + else + ret = send_extent_data(sctx, offset, clone_len); + + if (ret < 0) + goto out; + + len -= clone_len; + if (len == 0) + break; + offset += clone_len; + clone_root->offset += clone_len; + data_offset += clone_len; +next: + path->slots[0]++; + } + + if (len > 0) + ret = send_extent_data(sctx, offset, len); + else + ret = 0; +out: + btrfs_free_path(path); + return ret; +} + static int send_write_or_clone(struct send_ctx *sctx, struct btrfs_path *path, struct btrfs_key *key, @@ -4693,9 +4856,7 @@ static int send_write_or_clone(struct send_ctx *sctx, int ret = 0; struct btrfs_file_extent_item *ei; u64 offset = key->offset; - u64 pos = 0; u64 len; - u32 l; u8 type; u64 bs = sctx->send_root->fs_info->sb->s_blocksize; @@ -4723,22 +4884,15 @@ static int send_write_or_clone(struct send_ctx *sctx, } if (clone_root && IS_ALIGNED(offset + len, bs)) { - ret = send_clone(sctx, offset, len, clone_root); - } else if (sctx->flags & BTRFS_SEND_FLAG_NO_FILE_DATA) { - ret = send_update_extent(sctx, offset, len); + u64 disk_byte; + u64 data_offset; + + disk_byte = btrfs_file_extent_disk_bytenr(path->nodes[0], ei); + data_offset = btrfs_file_extent_offset(path->nodes[0], ei); + ret = clone_range(sctx, clone_root, disk_byte, data_offset, + offset, len); } else { - while (pos < len) { - l = len - pos; - if (l > BTRFS_SEND_READ_SIZE) - l = BTRFS_SEND_READ_SIZE; - ret = send_write(sctx, pos + offset, l); - if (ret < 0) - goto out; - if (!ret) - break; - pos += ret; - } - ret = 0; + ret = send_extent_data(sctx, offset, len); } out: return ret; diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 2b07b35..24154e4 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -130,7 +130,6 @@ static void btrfs_handle_error(struct btrfs_fs_info *fs_info) } } -#ifdef CONFIG_PRINTK /* * __btrfs_std_error decodes expected errors from the caller and * invokes the approciate error response. @@ -140,7 +139,9 @@ void __btrfs_std_error(struct btrfs_fs_info *fs_info, const char *function, unsigned int line, int errno, const char *fmt, ...) { struct super_block *sb = fs_info->sb; +#ifdef CONFIG_PRINTK const char *errstr; +#endif /* * Special case: if the error is EROFS, and we're already @@ -149,6 +150,7 @@ void __btrfs_std_error(struct btrfs_fs_info *fs_info, const char *function, if (errno == -EROFS && (sb->s_flags & MS_RDONLY)) return; +#ifdef CONFIG_PRINTK errstr = btrfs_decode_error(errno); if (fmt) { struct va_format vaf; @@ -166,6 +168,7 @@ void __btrfs_std_error(struct btrfs_fs_info *fs_info, const char *function, printk(KERN_CRIT "BTRFS: error (device %s) in %s:%d: errno=%d %s\n", sb->s_id, function, line, errno, errstr); } +#endif /* Don't go through full error handling during mount */ save_error_info(fs_info); @@ -173,6 +176,7 @@ void __btrfs_std_error(struct btrfs_fs_info *fs_info, const char *function, btrfs_handle_error(fs_info); } +#ifdef CONFIG_PRINTK static const char * const logtypes[] = { "emergency", "alert", @@ -212,27 +216,6 @@ void btrfs_printk(const struct btrfs_fs_info *fs_info, const char *fmt, ...) va_end(args); } - -#else - -void __btrfs_std_error(struct btrfs_fs_info *fs_info, const char *function, - unsigned int line, int errno, const char *fmt, ...) -{ - struct super_block *sb = fs_info->sb; - - /* - * Special case: if the error is EROFS, and we're already - * under MS_RDONLY, then it is safe here. - */ - if (errno == -EROFS && (sb->s_flags & MS_RDONLY)) - return; - - /* Don't go through full error handling during mount */ - if (sb->s_flags & MS_BORN) { - save_error_info(fs_info); - btrfs_handle_error(fs_info); - } -} #endif /* @@ -320,6 +303,9 @@ enum { Opt_commit_interval, Opt_barrier, Opt_nodefrag, Opt_nodiscard, Opt_noenospc_debug, Opt_noflushoncommit, Opt_acl, Opt_datacow, Opt_datasum, Opt_treelog, Opt_noinode_cache, +#ifdef CONFIG_BTRFS_DEBUG + Opt_fragment_data, Opt_fragment_metadata, Opt_fragment_all, +#endif Opt_err, }; @@ -372,6 +358,11 @@ static match_table_t tokens = { {Opt_rescan_uuid_tree, "rescan_uuid_tree"}, {Opt_fatal_errors, "fatal_errors=%s"}, {Opt_commit_interval, "commit=%d"}, +#ifdef CONFIG_BTRFS_DEBUG + {Opt_fragment_data, "fragment=data"}, + {Opt_fragment_metadata, "fragment=metadata"}, + {Opt_fragment_all, "fragment=all"}, +#endif {Opt_err, NULL}, }; @@ -738,6 +729,22 @@ int btrfs_parse_options(struct btrfs_root *root, char *options) info->commit_interval = BTRFS_DEFAULT_COMMIT_INTERVAL; } break; +#ifdef CONFIG_BTRFS_DEBUG + case Opt_fragment_all: + btrfs_info(root->fs_info, "fragmenting all space"); + btrfs_set_opt(info->mount_opt, FRAGMENT_DATA); + btrfs_set_opt(info->mount_opt, FRAGMENT_METADATA); + break; + case Opt_fragment_metadata: + btrfs_info(root->fs_info, "fragmenting metadata"); + btrfs_set_opt(info->mount_opt, + FRAGMENT_METADATA); + break; + case Opt_fragment_data: + btrfs_info(root->fs_info, "fragmenting data"); + btrfs_set_opt(info->mount_opt, FRAGMENT_DATA); + break; +#endif case Opt_err: btrfs_info(root->fs_info, "unrecognized mount option '%s'", p); ret = -EINVAL; @@ -1189,6 +1196,12 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry) seq_puts(seq, ",fatal_errors=panic"); if (info->commit_interval != BTRFS_DEFAULT_COMMIT_INTERVAL) seq_printf(seq, ",commit=%d", info->commit_interval); +#ifdef CONFIG_BTRFS_DEBUG + if (btrfs_test_opt(root, FRAGMENT_DATA)) + seq_puts(seq, ",fragment=data"); + if (btrfs_test_opt(root, FRAGMENT_METADATA)) + seq_puts(seq, ",fragment=metadata"); +#endif seq_printf(seq, ",subvolid=%llu", BTRFS_I(d_inode(dentry))->root->root_key.objectid); seq_puts(seq, ",subvol="); @@ -1658,9 +1671,7 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) * groups on disk until we're mounted read-write again * unless we clean them up here. */ - mutex_lock(&root->fs_info->cleaner_mutex); btrfs_delete_unused_bgs(fs_info); - mutex_unlock(&root->fs_info->cleaner_mutex); btrfs_dev_replace_suspend_for_unmount(fs_info); btrfs_scrub_cancel(fs_info); diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index 603b0cc..e0ac859 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -437,24 +437,24 @@ static const struct attribute *btrfs_attrs[] = { NULL, }; -static void btrfs_release_super_kobj(struct kobject *kobj) +static void btrfs_release_fsid_kobj(struct kobject *kobj) { struct btrfs_fs_devices *fs_devs = to_fs_devs(kobj); - memset(&fs_devs->super_kobj, 0, sizeof(struct kobject)); + memset(&fs_devs->fsid_kobj, 0, sizeof(struct kobject)); complete(&fs_devs->kobj_unregister); } static struct kobj_type btrfs_ktype = { .sysfs_ops = &kobj_sysfs_ops, - .release = btrfs_release_super_kobj, + .release = btrfs_release_fsid_kobj, }; static inline struct btrfs_fs_devices *to_fs_devs(struct kobject *kobj) { if (kobj->ktype != &btrfs_ktype) return NULL; - return container_of(kobj, struct btrfs_fs_devices, super_kobj); + return container_of(kobj, struct btrfs_fs_devices, fsid_kobj); } static inline struct btrfs_fs_info *to_fs_info(struct kobject *kobj) @@ -502,12 +502,12 @@ static int addrm_unknown_feature_attrs(struct btrfs_fs_info *fs_info, bool add) attrs[0] = &fa->kobj_attr.attr; if (add) { int ret; - ret = sysfs_merge_group(&fs_info->fs_devices->super_kobj, + ret = sysfs_merge_group(&fs_info->fs_devices->fsid_kobj, &agroup); if (ret) return ret; } else - sysfs_unmerge_group(&fs_info->fs_devices->super_kobj, + sysfs_unmerge_group(&fs_info->fs_devices->fsid_kobj, &agroup); } @@ -523,9 +523,9 @@ static void __btrfs_sysfs_remove_fsid(struct btrfs_fs_devices *fs_devs) fs_devs->device_dir_kobj = NULL; } - if (fs_devs->super_kobj.state_initialized) { - kobject_del(&fs_devs->super_kobj); - kobject_put(&fs_devs->super_kobj); + if (fs_devs->fsid_kobj.state_initialized) { + kobject_del(&fs_devs->fsid_kobj); + kobject_put(&fs_devs->fsid_kobj); wait_for_completion(&fs_devs->kobj_unregister); } } @@ -545,7 +545,7 @@ void btrfs_sysfs_remove_fsid(struct btrfs_fs_devices *fs_devs) } } -void btrfs_sysfs_remove_one(struct btrfs_fs_info *fs_info) +void btrfs_sysfs_remove_mounted(struct btrfs_fs_info *fs_info) { btrfs_reset_fs_info_ptr(fs_info); @@ -555,9 +555,9 @@ void btrfs_sysfs_remove_one(struct btrfs_fs_info *fs_info) kobject_put(fs_info->space_info_kobj); } addrm_unknown_feature_attrs(fs_info, false); - sysfs_remove_group(&fs_info->fs_devices->super_kobj, &btrfs_feature_attr_group); - sysfs_remove_files(&fs_info->fs_devices->super_kobj, btrfs_attrs); - btrfs_kobj_rm_device(fs_info->fs_devices, NULL); + sysfs_remove_group(&fs_info->fs_devices->fsid_kobj, &btrfs_feature_attr_group); + sysfs_remove_files(&fs_info->fs_devices->fsid_kobj, btrfs_attrs); + btrfs_sysfs_rm_device_link(fs_info->fs_devices, NULL); } const char * const btrfs_feature_set_names[3] = { @@ -637,7 +637,7 @@ static void init_feature_attrs(void) /* when one_device is NULL, it removes all device links */ -int btrfs_kobj_rm_device(struct btrfs_fs_devices *fs_devices, +int btrfs_sysfs_rm_device_link(struct btrfs_fs_devices *fs_devices, struct btrfs_device *one_device) { struct hd_struct *disk; @@ -675,7 +675,7 @@ int btrfs_sysfs_add_device(struct btrfs_fs_devices *fs_devs) { if (!fs_devs->device_dir_kobj) fs_devs->device_dir_kobj = kobject_create_and_add("devices", - &fs_devs->super_kobj); + &fs_devs->fsid_kobj); if (!fs_devs->device_dir_kobj) return -ENOMEM; @@ -683,7 +683,7 @@ int btrfs_sysfs_add_device(struct btrfs_fs_devices *fs_devs) return 0; } -int btrfs_kobj_add_device(struct btrfs_fs_devices *fs_devices, +int btrfs_sysfs_add_device_link(struct btrfs_fs_devices *fs_devices, struct btrfs_device *one_device) { int error = 0; @@ -730,31 +730,31 @@ int btrfs_sysfs_add_fsid(struct btrfs_fs_devices *fs_devs, int error; init_completion(&fs_devs->kobj_unregister); - fs_devs->super_kobj.kset = btrfs_kset; - error = kobject_init_and_add(&fs_devs->super_kobj, + fs_devs->fsid_kobj.kset = btrfs_kset; + error = kobject_init_and_add(&fs_devs->fsid_kobj, &btrfs_ktype, parent, "%pU", fs_devs->fsid); return error; } -int btrfs_sysfs_add_one(struct btrfs_fs_info *fs_info) +int btrfs_sysfs_add_mounted(struct btrfs_fs_info *fs_info) { int error; struct btrfs_fs_devices *fs_devs = fs_info->fs_devices; - struct kobject *super_kobj = &fs_devs->super_kobj; + struct kobject *fsid_kobj = &fs_devs->fsid_kobj; btrfs_set_fs_info_ptr(fs_info); - error = btrfs_kobj_add_device(fs_devs, NULL); + error = btrfs_sysfs_add_device_link(fs_devs, NULL); if (error) return error; - error = sysfs_create_files(super_kobj, btrfs_attrs); + error = sysfs_create_files(fsid_kobj, btrfs_attrs); if (error) { - btrfs_kobj_rm_device(fs_devs, NULL); + btrfs_sysfs_rm_device_link(fs_devs, NULL); return error; } - error = sysfs_create_group(super_kobj, + error = sysfs_create_group(fsid_kobj, &btrfs_feature_attr_group); if (error) goto failure; @@ -764,7 +764,7 @@ int btrfs_sysfs_add_one(struct btrfs_fs_info *fs_info) goto failure; fs_info->space_info_kobj = kobject_create_and_add("allocation", - super_kobj); + fsid_kobj); if (!fs_info->space_info_kobj) { error = -ENOMEM; goto failure; @@ -776,7 +776,7 @@ int btrfs_sysfs_add_one(struct btrfs_fs_info *fs_info) return 0; failure: - btrfs_sysfs_remove_one(fs_info); + btrfs_sysfs_remove_mounted(fs_info); return error; } diff --git a/fs/btrfs/sysfs.h b/fs/btrfs/sysfs.h index 6392527..9c09522 100644 --- a/fs/btrfs/sysfs.h +++ b/fs/btrfs/sysfs.h @@ -82,9 +82,9 @@ char *btrfs_printable_features(enum btrfs_feature_set set, u64 flags); extern const char * const btrfs_feature_set_names[3]; extern struct kobj_type space_info_ktype; extern struct kobj_type btrfs_raid_ktype; -int btrfs_kobj_add_device(struct btrfs_fs_devices *fs_devices, +int btrfs_sysfs_add_device_link(struct btrfs_fs_devices *fs_devices, struct btrfs_device *one_device); -int btrfs_kobj_rm_device(struct btrfs_fs_devices *fs_devices, +int btrfs_sysfs_rm_device_link(struct btrfs_fs_devices *fs_devices, struct btrfs_device *one_device); int btrfs_sysfs_add_fsid(struct btrfs_fs_devices *fs_devs, struct kobject *parent); diff --git a/fs/btrfs/tests/free-space-tests.c b/fs/btrfs/tests/free-space-tests.c index 2299bfd..c8c3d70 100644 --- a/fs/btrfs/tests/free-space-tests.c +++ b/fs/btrfs/tests/free-space-tests.c @@ -19,6 +19,7 @@ #include <linux/slab.h> #include "btrfs-tests.h" #include "../ctree.h" +#include "../disk-io.h" #include "../free-space-cache.h" #define BITS_PER_BITMAP (PAGE_CACHE_SIZE * 8) @@ -35,6 +36,12 @@ static struct btrfs_block_group_cache *init_test_block_group(void) kfree(cache); return NULL; } + cache->fs_info = btrfs_alloc_dummy_fs_info(); + if (!cache->fs_info) { + kfree(cache->free_space_ctl); + kfree(cache); + return NULL; + } cache->key.objectid = 0; cache->key.offset = 1024 * 1024 * 1024; @@ -879,7 +886,8 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache) int btrfs_test_free_space_cache(void) { struct btrfs_block_group_cache *cache; - int ret; + struct btrfs_root *root = NULL; + int ret = -ENOMEM; test_msg("Running btrfs free space cache tests\n"); @@ -889,6 +897,17 @@ int btrfs_test_free_space_cache(void) return 0; } + root = btrfs_alloc_dummy_root(); + if (!root) + goto out; + + root->fs_info = btrfs_alloc_dummy_fs_info(); + if (!root->fs_info) + goto out; + + root->fs_info->extent_root = root; + cache->fs_info = root->fs_info; + ret = test_extents(cache); if (ret) goto out; @@ -904,6 +923,7 @@ out: __btrfs_remove_free_space_cache(cache->free_space_ctl); kfree(cache->free_space_ctl); kfree(cache); + btrfs_free_dummy_root(root); test_msg("Free space cache tests finished\n"); return ret; } diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 8f259b3..418c6a2 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -82,6 +82,12 @@ void btrfs_put_transaction(struct btrfs_transaction *transaction) static void clear_btree_io_tree(struct extent_io_tree *tree) { spin_lock(&tree->lock); + /* + * Do a single barrier for the waitqueue_active check here, the state + * of the waitqueue should not change once clear_btree_io_tree is + * called. + */ + smp_mb(); while (!RB_EMPTY_ROOT(&tree->state)) { struct rb_node *node; struct extent_state *state; @@ -117,6 +123,18 @@ static noinline void switch_commit_roots(struct btrfs_transaction *trans, btrfs_unpin_free_ino(root); clear_btree_io_tree(&root->dirty_log_pages); } + + /* We can free old roots now. */ + spin_lock(&trans->dropped_roots_lock); + while (!list_empty(&trans->dropped_roots)) { + root = list_first_entry(&trans->dropped_roots, + struct btrfs_root, root_list); + list_del_init(&root->root_list); + spin_unlock(&trans->dropped_roots_lock); + btrfs_drop_and_free_fs_root(fs_info, root); + spin_lock(&trans->dropped_roots_lock); + } + spin_unlock(&trans->dropped_roots_lock); up_write(&fs_info->commit_root_sem); } @@ -214,25 +232,22 @@ loop: extwriter_counter_init(cur_trans, type); init_waitqueue_head(&cur_trans->writer_wait); init_waitqueue_head(&cur_trans->commit_wait); + init_waitqueue_head(&cur_trans->pending_wait); cur_trans->state = TRANS_STATE_RUNNING; /* * One for this trans handle, one so it will live on until we * commit the transaction. */ atomic_set(&cur_trans->use_count, 2); - cur_trans->have_free_bgs = 0; + atomic_set(&cur_trans->pending_ordered, 0); + cur_trans->flags = 0; cur_trans->start_time = get_seconds(); - cur_trans->dirty_bg_run = 0; + + memset(&cur_trans->delayed_refs, 0, sizeof(cur_trans->delayed_refs)); cur_trans->delayed_refs.href_root = RB_ROOT; cur_trans->delayed_refs.dirty_extent_root = RB_ROOT; atomic_set(&cur_trans->delayed_refs.num_entries, 0); - cur_trans->delayed_refs.num_heads_ready = 0; - cur_trans->delayed_refs.pending_csums = 0; - cur_trans->delayed_refs.num_heads = 0; - cur_trans->delayed_refs.flushing = 0; - cur_trans->delayed_refs.run_delayed_start = 0; - cur_trans->delayed_refs.qgroup_to_skip = 0; /* * although the tree mod log is per file system and not per transaction, @@ -252,14 +267,15 @@ loop: INIT_LIST_HEAD(&cur_trans->pending_snapshots); INIT_LIST_HEAD(&cur_trans->pending_chunks); INIT_LIST_HEAD(&cur_trans->switch_commits); - INIT_LIST_HEAD(&cur_trans->pending_ordered); INIT_LIST_HEAD(&cur_trans->dirty_bgs); INIT_LIST_HEAD(&cur_trans->io_bgs); + INIT_LIST_HEAD(&cur_trans->dropped_roots); mutex_init(&cur_trans->cache_write_mutex); cur_trans->num_dirty_bgs = 0; spin_lock_init(&cur_trans->dirty_bgs_lock); INIT_LIST_HEAD(&cur_trans->deleted_bgs); spin_lock_init(&cur_trans->deleted_bgs_lock); + spin_lock_init(&cur_trans->dropped_roots_lock); list_add_tail(&cur_trans->list, &fs_info->trans_list); extent_io_tree_init(&cur_trans->dirty_pages, fs_info->btree_inode->i_mapping); @@ -336,6 +352,24 @@ static int record_root_in_trans(struct btrfs_trans_handle *trans, } +void btrfs_add_dropped_root(struct btrfs_trans_handle *trans, + struct btrfs_root *root) +{ + struct btrfs_transaction *cur_trans = trans->transaction; + + /* Add ourselves to the transaction dropped list */ + spin_lock(&cur_trans->dropped_roots_lock); + list_add_tail(&root->root_list, &cur_trans->dropped_roots); + spin_unlock(&cur_trans->dropped_roots_lock); + + /* Make sure we don't try to update the root at commit time */ + spin_lock(&root->fs_info->fs_roots_radix_lock); + radix_tree_tag_clear(&root->fs_info->fs_roots_radix, + (unsigned long)root->root_key.objectid, + BTRFS_ROOT_TRANS_TAG); + spin_unlock(&root->fs_info->fs_roots_radix_lock); +} + int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans, struct btrfs_root *root) { @@ -415,8 +449,8 @@ static inline bool need_reserve_reloc_root(struct btrfs_root *root) } static struct btrfs_trans_handle * -start_transaction(struct btrfs_root *root, u64 num_items, unsigned int type, - enum btrfs_reserve_flush_enum flush) +start_transaction(struct btrfs_root *root, unsigned int num_items, + unsigned int type, enum btrfs_reserve_flush_enum flush) { struct btrfs_trans_handle *h; struct btrfs_transaction *cur_trans; @@ -446,13 +480,10 @@ start_transaction(struct btrfs_root *root, u64 num_items, unsigned int type, * the appropriate flushing if need be. */ if (num_items > 0 && root != root->fs_info->chunk_root) { - if (root->fs_info->quota_enabled && - is_fstree(root->root_key.objectid)) { - qgroup_reserved = num_items * root->nodesize; - ret = btrfs_qgroup_reserve(root, qgroup_reserved); - if (ret) - return ERR_PTR(ret); - } + qgroup_reserved = num_items * root->nodesize; + ret = btrfs_qgroup_reserve_meta(root, qgroup_reserved); + if (ret) + return ERR_PTR(ret); num_bytes = btrfs_calc_trans_metadata_size(root, num_items); /* @@ -470,7 +501,7 @@ start_transaction(struct btrfs_root *root, u64 num_items, unsigned int type, goto reserve_fail; } again: - h = kmem_cache_alloc(btrfs_trans_handle_cachep, GFP_NOFS); + h = kmem_cache_zalloc(btrfs_trans_handle_cachep, GFP_NOFS); if (!h) { ret = -ENOMEM; goto alloc_fail; @@ -511,25 +542,13 @@ again: h->transid = cur_trans->transid; h->transaction = cur_trans; - h->blocks_used = 0; - h->bytes_reserved = 0; - h->chunk_bytes_reserved = 0; h->root = root; - h->delayed_ref_updates = 0; h->use_count = 1; - h->adding_csums = 0; - h->block_rsv = NULL; - h->orig_rsv = NULL; - h->aborted = 0; - h->qgroup_reserved = 0; - h->delayed_ref_elem.seq = 0; + h->type = type; - h->allocating_chunk = false; - h->reloc_reserved = false; - h->sync = false; + h->can_flush_pending_bgs = true; INIT_LIST_HEAD(&h->qgroup_ref_list); INIT_LIST_HEAD(&h->new_bgs); - INIT_LIST_HEAD(&h->ordered); smp_mb(); if (cur_trans->state >= TRANS_STATE_BLOCKED && @@ -546,7 +565,6 @@ again: h->bytes_reserved = num_bytes; h->reloc_reserved = reloc_reserved; } - h->qgroup_reserved = qgroup_reserved; got_it: btrfs_record_root_in_trans(h, root); @@ -564,20 +582,20 @@ alloc_fail: btrfs_block_rsv_release(root, &root->fs_info->trans_block_rsv, num_bytes); reserve_fail: - if (qgroup_reserved) - btrfs_qgroup_free(root, qgroup_reserved); + btrfs_qgroup_free_meta(root, qgroup_reserved); return ERR_PTR(ret); } struct btrfs_trans_handle *btrfs_start_transaction(struct btrfs_root *root, - int num_items) + unsigned int num_items) { return start_transaction(root, num_items, TRANS_START, BTRFS_RESERVE_FLUSH_ALL); } struct btrfs_trans_handle *btrfs_start_transaction_lflush( - struct btrfs_root *root, int num_items) + struct btrfs_root *root, + unsigned int num_items) { return start_transaction(root, num_items, TRANS_START, BTRFS_RESERVE_FLUSH_LIMIT); @@ -761,12 +779,6 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans, if (!list_empty(&trans->new_bgs)) btrfs_create_pending_block_groups(trans, root); - if (!list_empty(&trans->ordered)) { - spin_lock(&info->trans_lock); - list_splice_init(&trans->ordered, &cur_trans->pending_ordered); - spin_unlock(&info->trans_lock); - } - trans->delayed_ref_updates = 0; if (!trans->sync) { must_run_delayed_refs = @@ -782,15 +794,6 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans, must_run_delayed_refs = 2; } - if (trans->qgroup_reserved) { - /* - * the same root has to be passed here between start_transaction - * and end_transaction. Subvolume quota depends on this. - */ - btrfs_qgroup_free(trans->root, trans->qgroup_reserved); - trans->qgroup_reserved = 0; - } - btrfs_trans_release_metadata(trans, root); trans->block_rsv = NULL; @@ -823,6 +826,9 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans, atomic_dec(&cur_trans->num_writers); extwriter_counter_dec(cur_trans, trans->type); + /* + * Make sure counter is updated before we wake up waiters. + */ smp_mb(); if (waitqueue_active(&cur_trans->writer_wait)) wake_up(&cur_trans->writer_wait); @@ -1205,6 +1211,7 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans, spin_lock(&fs_info->fs_roots_radix_lock); if (err) break; + btrfs_qgroup_free_meta_all(root); } } spin_unlock(&fs_info->fs_roots_radix_lock); @@ -1762,25 +1769,10 @@ static inline void btrfs_wait_delalloc_flush(struct btrfs_fs_info *fs_info) } static inline void -btrfs_wait_pending_ordered(struct btrfs_transaction *cur_trans, - struct btrfs_fs_info *fs_info) +btrfs_wait_pending_ordered(struct btrfs_transaction *cur_trans) { - struct btrfs_ordered_extent *ordered; - - spin_lock(&fs_info->trans_lock); - while (!list_empty(&cur_trans->pending_ordered)) { - ordered = list_first_entry(&cur_trans->pending_ordered, - struct btrfs_ordered_extent, - trans_list); - list_del_init(&ordered->trans_list); - spin_unlock(&fs_info->trans_lock); - - wait_event(ordered->wait, test_bit(BTRFS_ORDERED_COMPLETE, - &ordered->flags)); - btrfs_put_ordered_extent(ordered); - spin_lock(&fs_info->trans_lock); - } - spin_unlock(&fs_info->trans_lock); + wait_event(cur_trans->pending_wait, + atomic_read(&cur_trans->pending_ordered) == 0); } int btrfs_commit_transaction(struct btrfs_trans_handle *trans, @@ -1809,10 +1801,6 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, btrfs_trans_release_metadata(trans, root); trans->block_rsv = NULL; - if (trans->qgroup_reserved) { - btrfs_qgroup_free(root, trans->qgroup_reserved); - trans->qgroup_reserved = 0; - } cur_trans = trans->transaction; @@ -1832,7 +1820,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, return ret; } - if (!cur_trans->dirty_bg_run) { + if (!test_bit(BTRFS_TRANS_DIRTY_BG_RUN, &cur_trans->flags)) { int run_it = 0; /* this mutex is also taken before trying to set @@ -1841,18 +1829,17 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, * after a extents from that block group have been * allocated for cache files. btrfs_set_block_group_ro * will wait for the transaction to commit if it - * finds dirty_bg_run = 1 + * finds BTRFS_TRANS_DIRTY_BG_RUN set. * - * The dirty_bg_run flag is also used to make sure only - * one process starts all the block group IO. It wouldn't + * The BTRFS_TRANS_DIRTY_BG_RUN flag is also used to make sure + * only one process starts all the block group IO. It wouldn't * hurt to have more than one go through, but there's no * real advantage to it either. */ mutex_lock(&root->fs_info->ro_block_group_mutex); - if (!cur_trans->dirty_bg_run) { + if (!test_and_set_bit(BTRFS_TRANS_DIRTY_BG_RUN, + &cur_trans->flags)) run_it = 1; - cur_trans->dirty_bg_run = 1; - } mutex_unlock(&root->fs_info->ro_block_group_mutex); if (run_it) @@ -1864,7 +1851,6 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, } spin_lock(&root->fs_info->trans_lock); - list_splice_init(&trans->ordered, &cur_trans->pending_ordered); if (cur_trans->state >= TRANS_STATE_COMMIT_START) { spin_unlock(&root->fs_info->trans_lock); atomic_inc(&cur_trans->use_count); @@ -1923,7 +1909,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, btrfs_wait_delalloc_flush(root->fs_info); - btrfs_wait_pending_ordered(cur_trans, root->fs_info); + btrfs_wait_pending_ordered(cur_trans); btrfs_scrub_pause(root); /* @@ -2103,7 +2089,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, ret = btrfs_write_and_wait_transaction(trans, root); if (ret) { - btrfs_error(root->fs_info, ret, + btrfs_std_error(root->fs_info, ret, "Error while writing out transaction"); mutex_unlock(&root->fs_info->tree_log_mutex); goto scrub_continue; @@ -2123,7 +2109,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, btrfs_finish_extent_commit(trans, root); - if (cur_trans->have_free_bgs) + if (test_bit(BTRFS_TRANS_HAVE_FREE_BGS, &cur_trans->flags)) btrfs_clear_space_info_full(root->fs_info); root->fs_info->last_trans_committed = cur_trans->transid; @@ -2165,10 +2151,6 @@ cleanup_transaction: btrfs_trans_release_metadata(trans, root); btrfs_trans_release_chunk_metadata(trans); trans->block_rsv = NULL; - if (trans->qgroup_reserved) { - btrfs_qgroup_free(root, trans->qgroup_reserved); - trans->qgroup_reserved = 0; - } btrfs_warn(root->fs_info, "Skipping commit of aborted transaction."); if (current->journal_info == trans) current->journal_info = NULL; diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index edc2fbc..b05b2f6 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -32,6 +32,10 @@ enum btrfs_trans_state { TRANS_STATE_MAX = 6, }; +#define BTRFS_TRANS_HAVE_FREE_BGS 0 +#define BTRFS_TRANS_DIRTY_BG_RUN 1 +#define BTRFS_TRANS_CACHE_ENOSPC 2 + struct btrfs_transaction { u64 transid; /* @@ -46,11 +50,9 @@ struct btrfs_transaction { */ atomic_t num_writers; atomic_t use_count; + atomic_t pending_ordered; - /* - * true if there is free bgs operations in this transaction - */ - int have_free_bgs; + unsigned long flags; /* Be protected by fs_info->trans_lock when we want to change it. */ enum btrfs_trans_state state; @@ -59,12 +61,13 @@ struct btrfs_transaction { unsigned long start_time; wait_queue_head_t writer_wait; wait_queue_head_t commit_wait; + wait_queue_head_t pending_wait; struct list_head pending_snapshots; struct list_head pending_chunks; - struct list_head pending_ordered; struct list_head switch_commits; struct list_head dirty_bgs; struct list_head io_bgs; + struct list_head dropped_roots; u64 num_dirty_bgs; /* @@ -76,9 +79,9 @@ struct btrfs_transaction { spinlock_t dirty_bgs_lock; struct list_head deleted_bgs; spinlock_t deleted_bgs_lock; + spinlock_t dropped_roots_lock; struct btrfs_delayed_ref_root delayed_refs; int aborted; - int dirty_bg_run; }; #define __TRANS_FREEZABLE (1U << 0) @@ -105,7 +108,6 @@ struct btrfs_trans_handle { u64 transid; u64 bytes_reserved; u64 chunk_bytes_reserved; - u64 qgroup_reserved; unsigned long use_count; unsigned long blocks_reserved; unsigned long blocks_used; @@ -116,6 +118,7 @@ struct btrfs_trans_handle { short aborted; short adding_csums; bool allocating_chunk; + bool can_flush_pending_bgs; bool reloc_reserved; bool sync; unsigned int type; @@ -126,7 +129,6 @@ struct btrfs_trans_handle { */ struct btrfs_root *root; struct seq_list delayed_ref_elem; - struct list_head ordered; struct list_head qgroup_ref_list; struct list_head new_bgs; }; @@ -182,9 +184,10 @@ static inline void btrfs_clear_skip_qgroup(struct btrfs_trans_handle *trans) int btrfs_end_transaction(struct btrfs_trans_handle *trans, struct btrfs_root *root); struct btrfs_trans_handle *btrfs_start_transaction(struct btrfs_root *root, - int num_items); + unsigned int num_items); struct btrfs_trans_handle *btrfs_start_transaction_lflush( - struct btrfs_root *root, int num_items); + struct btrfs_root *root, + unsigned int num_items); struct btrfs_trans_handle *btrfs_join_transaction(struct btrfs_root *root); struct btrfs_trans_handle *btrfs_join_transaction_nolock(struct btrfs_root *root); struct btrfs_trans_handle *btrfs_attach_transaction(struct btrfs_root *root); @@ -216,5 +219,6 @@ int btrfs_transaction_blocked(struct btrfs_fs_info *info); int btrfs_transaction_in_commit(struct btrfs_fs_info *info); void btrfs_put_transaction(struct btrfs_transaction *transaction); void btrfs_apply_pending_changes(struct btrfs_fs_info *fs_info); - +void btrfs_add_dropped_root(struct btrfs_trans_handle *trans, + struct btrfs_root *root); #endif diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 1bbaace..323e12c 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -229,7 +229,9 @@ int btrfs_pin_log_trans(struct btrfs_root *root) void btrfs_end_log_trans(struct btrfs_root *root) { if (atomic_dec_and_test(&root->log_writers)) { - smp_mb(); + /* + * Implicit memory barrier after atomic_dec_and_test + */ if (waitqueue_active(&root->log_writer_wait)) wake_up(&root->log_writer_wait); } @@ -691,7 +693,7 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans, ret = btrfs_inc_extent_ref(trans, root, ins.objectid, ins.offset, 0, root->root_key.objectid, - key->objectid, offset, 0); + key->objectid, offset); if (ret) goto out; } else { @@ -2820,7 +2822,9 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, mutex_lock(&log_root_tree->log_mutex); if (atomic_dec_and_test(&log_root_tree->log_writers)) { - smp_mb(); + /* + * Implicit memory barrier after atomic_dec_and_test + */ if (waitqueue_active(&log_root_tree->log_writer_wait)) wake_up(&log_root_tree->log_writer_wait); } @@ -2950,6 +2954,9 @@ out_wake_log_root: atomic_set(&log_root_tree->log_commit[index2], 0); mutex_unlock(&log_root_tree->log_mutex); + /* + * The barrier before waitqueue_active is implied by mutex_unlock + */ if (waitqueue_active(&log_root_tree->log_commit_wait[index2])) wake_up(&log_root_tree->log_commit_wait[index2]); out: @@ -2961,6 +2968,9 @@ out: atomic_set(&root->log_commit[index1], 0); mutex_unlock(&root->log_mutex); + /* + * The barrier before waitqueue_active is implied by mutex_unlock + */ if (waitqueue_active(&root->log_commit_wait[index1])) wake_up(&root->log_commit_wait[index1]); return ret; @@ -5314,7 +5324,7 @@ int btrfs_recover_log_trees(struct btrfs_root *log_root_tree) ret = walk_log_tree(trans, log_root_tree, &wc); if (ret) { - btrfs_error(fs_info, ret, "Failed to pin buffers while " + btrfs_std_error(fs_info, ret, "Failed to pin buffers while " "recovering log root tree."); goto error; } @@ -5328,7 +5338,7 @@ again: ret = btrfs_search_slot(NULL, log_root_tree, &key, path, 0, 0); if (ret < 0) { - btrfs_error(fs_info, ret, + btrfs_std_error(fs_info, ret, "Couldn't find tree log root."); goto error; } @@ -5346,7 +5356,7 @@ again: log = btrfs_read_fs_root(log_root_tree, &found_key); if (IS_ERR(log)) { ret = PTR_ERR(log); - btrfs_error(fs_info, ret, + btrfs_std_error(fs_info, ret, "Couldn't read tree log root."); goto error; } @@ -5361,7 +5371,7 @@ again: free_extent_buffer(log->node); free_extent_buffer(log->commit_root); kfree(log); - btrfs_error(fs_info, ret, "Couldn't read target root " + btrfs_std_error(fs_info, ret, "Couldn't read target root " "for tree log recovery."); goto error; } diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 6fc73586..9b2dafa 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -42,6 +42,82 @@ #include "dev-replace.h" #include "sysfs.h" +const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = { + [BTRFS_RAID_RAID10] = { + .sub_stripes = 2, + .dev_stripes = 1, + .devs_max = 0, /* 0 == as many as possible */ + .devs_min = 4, + .tolerated_failures = 1, + .devs_increment = 2, + .ncopies = 2, + }, + [BTRFS_RAID_RAID1] = { + .sub_stripes = 1, + .dev_stripes = 1, + .devs_max = 2, + .devs_min = 2, + .tolerated_failures = 1, + .devs_increment = 2, + .ncopies = 2, + }, + [BTRFS_RAID_DUP] = { + .sub_stripes = 1, + .dev_stripes = 2, + .devs_max = 1, + .devs_min = 1, + .tolerated_failures = 0, + .devs_increment = 1, + .ncopies = 2, + }, + [BTRFS_RAID_RAID0] = { + .sub_stripes = 1, + .dev_stripes = 1, + .devs_max = 0, + .devs_min = 2, + .tolerated_failures = 0, + .devs_increment = 1, + .ncopies = 1, + }, + [BTRFS_RAID_SINGLE] = { + .sub_stripes = 1, + .dev_stripes = 1, + .devs_max = 1, + .devs_min = 1, + .tolerated_failures = 0, + .devs_increment = 1, + .ncopies = 1, + }, + [BTRFS_RAID_RAID5] = { + .sub_stripes = 1, + .dev_stripes = 1, + .devs_max = 0, + .devs_min = 2, + .tolerated_failures = 1, + .devs_increment = 1, + .ncopies = 2, + }, + [BTRFS_RAID_RAID6] = { + .sub_stripes = 1, + .dev_stripes = 1, + .devs_max = 0, + .devs_min = 3, + .tolerated_failures = 2, + .devs_increment = 1, + .ncopies = 3, + }, +}; + +const u64 const btrfs_raid_group[BTRFS_NR_RAID_TYPES] = { + [BTRFS_RAID_RAID10] = BTRFS_BLOCK_GROUP_RAID10, + [BTRFS_RAID_RAID1] = BTRFS_BLOCK_GROUP_RAID1, + [BTRFS_RAID_DUP] = BTRFS_BLOCK_GROUP_DUP, + [BTRFS_RAID_RAID0] = BTRFS_BLOCK_GROUP_RAID0, + [BTRFS_RAID_SINGLE] = 0, + [BTRFS_RAID_RAID5] = BTRFS_BLOCK_GROUP_RAID5, + [BTRFS_RAID_RAID6] = BTRFS_BLOCK_GROUP_RAID6, +}; + static int init_first_rw_device(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_device *device); @@ -156,8 +232,8 @@ static struct btrfs_device *__alloc_device(void) spin_lock_init(&dev->reada_lock); atomic_set(&dev->reada_in_flight, 0); atomic_set(&dev->dev_stats_ccnt, 0); - INIT_RADIX_TREE(&dev->reada_zones, GFP_NOFS & ~__GFP_WAIT); - INIT_RADIX_TREE(&dev->reada_extents, GFP_NOFS & ~__GFP_WAIT); + INIT_RADIX_TREE(&dev->reada_zones, GFP_NOFS & ~__GFP_DIRECT_RECLAIM); + INIT_RADIX_TREE(&dev->reada_extents, GFP_NOFS & ~__GFP_DIRECT_RECLAIM); return dev; } @@ -198,7 +274,6 @@ btrfs_get_bdev_and_sb(const char *device_path, fmode_t flags, void *holder, if (IS_ERR(*bdev)) { ret = PTR_ERR(*bdev); - printk(KERN_INFO "BTRFS: open %s failed\n", device_path); goto error; } @@ -211,8 +286,8 @@ btrfs_get_bdev_and_sb(const char *device_path, fmode_t flags, void *holder, } invalidate_bdev(*bdev); *bh = btrfs_read_dev_super(*bdev); - if (!*bh) { - ret = -EINVAL; + if (IS_ERR(*bh)) { + ret = PTR_ERR(*bh); blkdev_put(*bdev, flags); goto error; } @@ -345,6 +420,9 @@ loop_lock: pending = pending->bi_next; cur->bi_next = NULL; + /* + * atomic_dec_return implies a barrier for waitqueue_active + */ if (atomic_dec_return(&fs_info->nr_async_bios) < limit && waitqueue_active(&fs_info->async_submit_wait)) wake_up(&fs_info->async_submit_wait); @@ -765,36 +843,7 @@ static int __btrfs_close_devices(struct btrfs_fs_devices *fs_devices) mutex_lock(&fs_devices->device_list_mutex); list_for_each_entry_safe(device, tmp, &fs_devices->devices, dev_list) { - struct btrfs_device *new_device; - struct rcu_string *name; - - if (device->bdev) - fs_devices->open_devices--; - - if (device->writeable && - device->devid != BTRFS_DEV_REPLACE_DEVID) { - list_del_init(&device->dev_alloc_list); - fs_devices->rw_devices--; - } - - if (device->missing) - fs_devices->missing_devices--; - - new_device = btrfs_alloc_device(NULL, &device->devid, - device->uuid); - BUG_ON(IS_ERR(new_device)); /* -ENOMEM */ - - /* Safe because we are under uuid_mutex */ - if (device->name) { - name = rcu_string_strdup(device->name->str, GFP_NOFS); - BUG_ON(!name); /* -ENOMEM */ - rcu_assign_pointer(new_device->name, name); - } - - list_replace_rcu(&device->dev_list, &new_device->dev_list); - new_device->fs_devices = device->fs_devices; - - call_rcu(&device->rcu, free_device); + btrfs_close_one_device(device); } mutex_unlock(&fs_devices->device_list_mutex); @@ -1402,7 +1451,7 @@ again: extent = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_dev_extent); } else { - btrfs_error(root->fs_info, ret, "Slot search failed"); + btrfs_std_error(root->fs_info, ret, "Slot search failed"); goto out; } @@ -1410,10 +1459,10 @@ again: ret = btrfs_del_item(trans, root, path); if (ret) { - btrfs_error(root->fs_info, ret, + btrfs_std_error(root->fs_info, ret, "Failed to remove dev extent item"); } else { - trans->transaction->have_free_bgs = 1; + set_bit(BTRFS_TRANS_HAVE_FREE_BGS, &trans->transaction->flags); } out: btrfs_free_path(path); @@ -1801,7 +1850,7 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path) if (device->bdev) { device->fs_devices->open_devices--; /* remove sysfs entry */ - btrfs_kobj_rm_device(root->fs_info->fs_devices, device); + btrfs_sysfs_rm_device_link(root->fs_info->fs_devices, device); } call_rcu(&device->rcu, free_device); @@ -1924,7 +1973,8 @@ void btrfs_rm_dev_replace_remove_srcdev(struct btrfs_fs_info *fs_info, if (srcdev->writeable) { fs_devices->rw_devices--; /* zero out the old super if it is writable */ - btrfs_scratch_superblock(srcdev); + btrfs_scratch_superblocks(srcdev->bdev, + rcu_str_deref(srcdev->name)); } if (srcdev->bdev) @@ -1971,10 +2021,11 @@ void btrfs_destroy_dev_replace_tgtdev(struct btrfs_fs_info *fs_info, WARN_ON(!tgtdev); mutex_lock(&fs_info->fs_devices->device_list_mutex); - btrfs_kobj_rm_device(fs_info->fs_devices, tgtdev); + btrfs_sysfs_rm_device_link(fs_info->fs_devices, tgtdev); if (tgtdev->bdev) { - btrfs_scratch_superblock(tgtdev); + btrfs_scratch_superblocks(tgtdev->bdev, + rcu_str_deref(tgtdev->name)); fs_info->fs_devices->open_devices--; } fs_info->fs_devices->num_devices--; @@ -2041,10 +2092,8 @@ int btrfs_find_device_missing_or_by_path(struct btrfs_root *root, } } - if (!*device) { - btrfs_err(root->fs_info, "no missing device found"); - return -ENOENT; - } + if (!*device) + return BTRFS_ERROR_DEV_MISSING_NOT_FOUND; return 0; } else { @@ -2309,7 +2358,7 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path) tmp + 1); /* add sysfs device entry */ - btrfs_kobj_add_device(root->fs_info->fs_devices, device); + btrfs_sysfs_add_device_link(root->fs_info->fs_devices, device); /* * we've got more storage, clear any full flags on the space @@ -2350,9 +2399,10 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path) */ snprintf(fsid_buf, BTRFS_UUID_UNPARSED_SIZE, "%pU", root->fs_info->fsid); - if (kobject_rename(&root->fs_info->fs_devices->super_kobj, + if (kobject_rename(&root->fs_info->fs_devices->fsid_kobj, fsid_buf)) - pr_warn("BTRFS: sysfs: failed to create fsid for sprout\n"); + btrfs_warn(root->fs_info, + "sysfs: failed to create fsid for sprout"); } root->fs_info->num_tolerated_disk_barrier_failures = @@ -2368,7 +2418,7 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path) ret = btrfs_relocate_sys_chunks(root); if (ret < 0) - btrfs_error(root->fs_info, ret, + btrfs_std_error(root->fs_info, ret, "Failed to relocate sys chunks after " "device initialization. This can be fixed " "using the \"btrfs balance\" command."); @@ -2388,7 +2438,7 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path) error_trans: btrfs_end_transaction(trans, root); rcu_string_free(device->name); - btrfs_kobj_rm_device(root->fs_info->fs_devices, device); + btrfs_sysfs_rm_device_link(root->fs_info->fs_devices, device); kfree(device); error: blkdev_put(bdev, FMODE_EXCL); @@ -2613,7 +2663,7 @@ static int btrfs_free_chunk(struct btrfs_trans_handle *trans, if (ret < 0) goto out; else if (ret > 0) { /* Logic error or corruption */ - btrfs_error(root->fs_info, -ENOENT, + btrfs_std_error(root->fs_info, -ENOENT, "Failed lookup while freeing chunk."); ret = -ENOENT; goto out; @@ -2621,7 +2671,7 @@ static int btrfs_free_chunk(struct btrfs_trans_handle *trans, ret = btrfs_del_item(trans, root, path); if (ret < 0) - btrfs_error(root->fs_info, ret, + btrfs_std_error(root->fs_info, ret, "Failed to delete chunk item."); out: btrfs_free_path(path); @@ -2806,7 +2856,7 @@ static int btrfs_relocate_chunk(struct btrfs_root *root, u64 chunk_offset) trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) { ret = PTR_ERR(trans); - btrfs_std_error(root->fs_info, ret); + btrfs_std_error(root->fs_info, ret, NULL); return ret; } @@ -3009,16 +3059,19 @@ static void update_balance_args(struct btrfs_balance_control *bctl) * (albeit full) chunks. */ if (!(bctl->data.flags & BTRFS_BALANCE_ARGS_USAGE) && + !(bctl->data.flags & BTRFS_BALANCE_ARGS_USAGE_RANGE) && !(bctl->data.flags & BTRFS_BALANCE_ARGS_CONVERT)) { bctl->data.flags |= BTRFS_BALANCE_ARGS_USAGE; bctl->data.usage = 90; } if (!(bctl->sys.flags & BTRFS_BALANCE_ARGS_USAGE) && + !(bctl->sys.flags & BTRFS_BALANCE_ARGS_USAGE_RANGE) && !(bctl->sys.flags & BTRFS_BALANCE_ARGS_CONVERT)) { bctl->sys.flags |= BTRFS_BALANCE_ARGS_USAGE; bctl->sys.usage = 90; } if (!(bctl->meta.flags & BTRFS_BALANCE_ARGS_USAGE) && + !(bctl->meta.flags & BTRFS_BALANCE_ARGS_USAGE_RANGE) && !(bctl->meta.flags & BTRFS_BALANCE_ARGS_CONVERT)) { bctl->meta.flags |= BTRFS_BALANCE_ARGS_USAGE; bctl->meta.usage = 90; @@ -3074,13 +3127,46 @@ static int chunk_usage_filter(struct btrfs_fs_info *fs_info, u64 chunk_offset, struct btrfs_balance_args *bargs) { struct btrfs_block_group_cache *cache; + u64 chunk_used; + u64 user_thresh_min; + u64 user_thresh_max; + int ret = 1; + + cache = btrfs_lookup_block_group(fs_info, chunk_offset); + chunk_used = btrfs_block_group_used(&cache->item); + + if (bargs->usage_min == 0) + user_thresh_min = 0; + else + user_thresh_min = div_factor_fine(cache->key.offset, + bargs->usage_min); + + if (bargs->usage_max == 0) + user_thresh_max = 1; + else if (bargs->usage_max > 100) + user_thresh_max = cache->key.offset; + else + user_thresh_max = div_factor_fine(cache->key.offset, + bargs->usage_max); + + if (user_thresh_min <= chunk_used && chunk_used < user_thresh_max) + ret = 0; + + btrfs_put_block_group(cache); + return ret; +} + +static int chunk_usage_range_filter(struct btrfs_fs_info *fs_info, + u64 chunk_offset, struct btrfs_balance_args *bargs) +{ + struct btrfs_block_group_cache *cache; u64 chunk_used, user_thresh; int ret = 1; cache = btrfs_lookup_block_group(fs_info, chunk_offset); chunk_used = btrfs_block_group_used(&cache->item); - if (bargs->usage == 0) + if (bargs->usage_min == 0) user_thresh = 1; else if (bargs->usage > 100) user_thresh = cache->key.offset; @@ -3170,6 +3256,19 @@ static int chunk_vrange_filter(struct extent_buffer *leaf, return 1; } +static int chunk_stripes_range_filter(struct extent_buffer *leaf, + struct btrfs_chunk *chunk, + struct btrfs_balance_args *bargs) +{ + int num_stripes = btrfs_chunk_num_stripes(leaf, chunk); + + if (bargs->stripes_min <= num_stripes + && num_stripes <= bargs->stripes_max) + return 0; + + return 1; +} + static int chunk_soft_convert_filter(u64 chunk_type, struct btrfs_balance_args *bargs) { @@ -3216,6 +3315,9 @@ static int should_balance_chunk(struct btrfs_root *root, if ((bargs->flags & BTRFS_BALANCE_ARGS_USAGE) && chunk_usage_filter(bctl->fs_info, chunk_offset, bargs)) { return 0; + } else if ((bargs->flags & BTRFS_BALANCE_ARGS_USAGE_RANGE) && + chunk_usage_range_filter(bctl->fs_info, chunk_offset, bargs)) { + return 0; } /* devid filter */ @@ -3236,6 +3338,12 @@ static int should_balance_chunk(struct btrfs_root *root, return 0; } + /* stripes filter */ + if ((bargs->flags & BTRFS_BALANCE_ARGS_STRIPES_RANGE) && + chunk_stripes_range_filter(leaf, chunk, bargs)) { + return 0; + } + /* soft profile changing mode */ if ((bargs->flags & BTRFS_BALANCE_ARGS_SOFT) && chunk_soft_convert_filter(chunk_type, bargs)) { @@ -3250,6 +3358,16 @@ static int should_balance_chunk(struct btrfs_root *root, return 0; else bargs->limit--; + } else if ((bargs->flags & BTRFS_BALANCE_ARGS_LIMIT_RANGE)) { + /* + * Same logic as the 'limit' filter; the minimum cannot be + * determined here because we do not have the global informatoin + * about the count of all chunks that satisfy the filters. + */ + if (bargs->limit_max == 0) + return 0; + else + bargs->limit_max--; } return 1; @@ -3264,6 +3382,7 @@ static int __btrfs_balance(struct btrfs_fs_info *fs_info) struct btrfs_device *device; u64 old_size; u64 size_to_free; + u64 chunk_type; struct btrfs_chunk *chunk; struct btrfs_path *path; struct btrfs_key key; @@ -3274,9 +3393,13 @@ static int __btrfs_balance(struct btrfs_fs_info *fs_info) int ret; int enospc_errors = 0; bool counting = true; + /* The single value limit and min/max limits use the same bytes in the */ u64 limit_data = bctl->data.limit; u64 limit_meta = bctl->meta.limit; u64 limit_sys = bctl->sys.limit; + u32 count_data = 0; + u32 count_meta = 0; + u32 count_sys = 0; /* step one make some room on all the devices */ devices = &fs_info->fs_devices->devices; @@ -3317,6 +3440,10 @@ static int __btrfs_balance(struct btrfs_fs_info *fs_info) spin_unlock(&fs_info->balance_lock); again: if (!counting) { + /* + * The single value limit and min/max limits use the same bytes + * in the + */ bctl->data.limit = limit_data; bctl->meta.limit = limit_meta; bctl->sys.limit = limit_sys; @@ -3364,6 +3491,7 @@ again: } chunk = btrfs_item_ptr(leaf, slot, struct btrfs_chunk); + chunk_type = btrfs_chunk_type(leaf, chunk); if (!counting) { spin_lock(&fs_info->balance_lock); @@ -3384,6 +3512,28 @@ again: spin_lock(&fs_info->balance_lock); bctl->stat.expected++; spin_unlock(&fs_info->balance_lock); + + if (chunk_type & BTRFS_BLOCK_GROUP_DATA) + count_data++; + else if (chunk_type & BTRFS_BLOCK_GROUP_SYSTEM) + count_sys++; + else if (chunk_type & BTRFS_BLOCK_GROUP_METADATA) + count_meta++; + + goto loop; + } + + /* + * Apply limit_min filter, no need to check if the LIMITS + * filter is used, limit_min is 0 by default + */ + if (((chunk_type & BTRFS_BLOCK_GROUP_DATA) && + count_data < bctl->data.limit_min) + || ((chunk_type & BTRFS_BLOCK_GROUP_METADATA) && + count_meta < bctl->meta.limit_min) + || ((chunk_type & BTRFS_BLOCK_GROUP_SYSTEM) && + count_sys < bctl->sys.limit_min)) { + mutex_unlock(&fs_info->delete_unused_bgs_mutex); goto loop; } @@ -3461,11 +3611,20 @@ static void __cancel_balance(struct btrfs_fs_info *fs_info) unset_balance_control(fs_info); ret = del_balance_item(fs_info->tree_root); if (ret) - btrfs_std_error(fs_info, ret); + btrfs_std_error(fs_info, ret, NULL); atomic_set(&fs_info->mutually_exclusive_operation_running, 0); } +/* Non-zero return value signifies invalidity */ +static inline int validate_convert_profile(struct btrfs_balance_args *bctl_arg, + u64 allowed) +{ + return ((bctl_arg->flags & BTRFS_BALANCE_ARGS_CONVERT) && + (!alloc_profile_is_valid(bctl_arg->target, 1) || + (bctl_arg->target & ~allowed))); +} + /* * Should be called with both balance and volume mutexes held */ @@ -3523,27 +3682,21 @@ int btrfs_balance(struct btrfs_balance_control *bctl, if (num_devices > 3) allowed |= (BTRFS_BLOCK_GROUP_RAID10 | BTRFS_BLOCK_GROUP_RAID6); - if ((bctl->data.flags & BTRFS_BALANCE_ARGS_CONVERT) && - (!alloc_profile_is_valid(bctl->data.target, 1) || - (bctl->data.target & ~allowed))) { + if (validate_convert_profile(&bctl->data, allowed)) { btrfs_err(fs_info, "unable to start balance with target " "data profile %llu", bctl->data.target); ret = -EINVAL; goto out; } - if ((bctl->meta.flags & BTRFS_BALANCE_ARGS_CONVERT) && - (!alloc_profile_is_valid(bctl->meta.target, 1) || - (bctl->meta.target & ~allowed))) { + if (validate_convert_profile(&bctl->meta, allowed)) { btrfs_err(fs_info, "unable to start balance with target metadata profile %llu", bctl->meta.target); ret = -EINVAL; goto out; } - if ((bctl->sys.flags & BTRFS_BALANCE_ARGS_CONVERT) && - (!alloc_profile_is_valid(bctl->sys.target, 1) || - (bctl->sys.target & ~allowed))) { + if (validate_convert_profile(&bctl->sys, allowed)) { btrfs_err(fs_info, "unable to start balance with target system profile %llu", bctl->sys.target); @@ -4285,65 +4438,6 @@ static int btrfs_cmp_device_info(const void *a, const void *b) return 0; } -static const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = { - [BTRFS_RAID_RAID10] = { - .sub_stripes = 2, - .dev_stripes = 1, - .devs_max = 0, /* 0 == as many as possible */ - .devs_min = 4, - .devs_increment = 2, - .ncopies = 2, - }, - [BTRFS_RAID_RAID1] = { - .sub_stripes = 1, - .dev_stripes = 1, - .devs_max = 2, - .devs_min = 2, - .devs_increment = 2, - .ncopies = 2, - }, - [BTRFS_RAID_DUP] = { - .sub_stripes = 1, - .dev_stripes = 2, - .devs_max = 1, - .devs_min = 1, - .devs_increment = 1, - .ncopies = 2, - }, - [BTRFS_RAID_RAID0] = { - .sub_stripes = 1, - .dev_stripes = 1, - .devs_max = 0, - .devs_min = 2, - .devs_increment = 1, - .ncopies = 1, - }, - [BTRFS_RAID_SINGLE] = { - .sub_stripes = 1, - .dev_stripes = 1, - .devs_max = 1, - .devs_min = 1, - .devs_increment = 1, - .ncopies = 1, - }, - [BTRFS_RAID_RAID5] = { - .sub_stripes = 1, - .dev_stripes = 1, - .devs_max = 0, - .devs_min = 2, - .devs_increment = 1, - .ncopies = 2, - }, - [BTRFS_RAID_RAID6] = { - .sub_stripes = 1, - .dev_stripes = 1, - .devs_max = 0, - .devs_min = 3, - .devs_increment = 1, - .ncopies = 3, - }, -}; - static u32 find_raid56_stripe_len(u32 data_devices, u32 dev_stripe_target) { /* TODO allow them to set a preferred stripe size */ @@ -6594,8 +6688,8 @@ static int update_dev_stat_item(struct btrfs_trans_handle *trans, BUG_ON(!path); ret = btrfs_search_slot(trans, dev_root, &key, path, -1, 1); if (ret < 0) { - printk_in_rcu(KERN_WARNING "BTRFS: " - "error %d while searching for dev_stats item for device %s!\n", + btrfs_warn_in_rcu(dev_root->fs_info, + "error %d while searching for dev_stats item for device %s", ret, rcu_str_deref(device->name)); goto out; } @@ -6605,8 +6699,8 @@ static int update_dev_stat_item(struct btrfs_trans_handle *trans, /* need to delete old one and insert a new one */ ret = btrfs_del_item(trans, dev_root, path); if (ret != 0) { - printk_in_rcu(KERN_WARNING "BTRFS: " - "delete too small dev_stats item for device %s failed %d!\n", + btrfs_warn_in_rcu(dev_root->fs_info, + "delete too small dev_stats item for device %s failed %d", rcu_str_deref(device->name), ret); goto out; } @@ -6619,9 +6713,9 @@ static int update_dev_stat_item(struct btrfs_trans_handle *trans, ret = btrfs_insert_empty_item(trans, dev_root, path, &key, sizeof(*ptr)); if (ret < 0) { - printk_in_rcu(KERN_WARNING "BTRFS: " - "insert dev_stats item for device %s failed %d!\n", - rcu_str_deref(device->name), ret); + btrfs_warn_in_rcu(dev_root->fs_info, + "insert dev_stats item for device %s failed %d", + rcu_str_deref(device->name), ret); goto out; } } @@ -6675,8 +6769,8 @@ static void btrfs_dev_stat_print_on_error(struct btrfs_device *dev) { if (!dev->dev_stats_valid) return; - printk_ratelimited_in_rcu(KERN_ERR "BTRFS: " - "bdev %s errs: wr %u, rd %u, flush %u, corrupt %u, gen %u\n", + btrfs_err_rl_in_rcu(dev->dev_root->fs_info, + "bdev %s errs: wr %u, rd %u, flush %u, corrupt %u, gen %u", rcu_str_deref(dev->name), btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_WRITE_ERRS), btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_READ_ERRS), @@ -6695,8 +6789,8 @@ static void btrfs_dev_stat_print_on_load(struct btrfs_device *dev) if (i == BTRFS_DEV_STAT_VALUES_MAX) return; /* all values == 0, suppress message */ - printk_in_rcu(KERN_INFO "BTRFS: " - "bdev %s errs: wr %u, rd %u, flush %u, corrupt %u, gen %u\n", + btrfs_info_in_rcu(dev->dev_root->fs_info, + "bdev %s errs: wr %u, rd %u, flush %u, corrupt %u, gen %u", rcu_str_deref(dev->name), btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_WRITE_ERRS), btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_READ_ERRS), @@ -6740,22 +6834,34 @@ int btrfs_get_dev_stats(struct btrfs_root *root, return 0; } -int btrfs_scratch_superblock(struct btrfs_device *device) +void btrfs_scratch_superblocks(struct block_device *bdev, char *device_path) { struct buffer_head *bh; struct btrfs_super_block *disk_super; + int copy_num; - bh = btrfs_read_dev_super(device->bdev); - if (!bh) - return -EINVAL; - disk_super = (struct btrfs_super_block *)bh->b_data; + if (!bdev) + return; - memset(&disk_super->magic, 0, sizeof(disk_super->magic)); - set_buffer_dirty(bh); - sync_dirty_buffer(bh); - brelse(bh); + for (copy_num = 0; copy_num < BTRFS_SUPER_MIRROR_MAX; + copy_num++) { - return 0; + if (btrfs_read_dev_one_super(bdev, copy_num, &bh)) + continue; + + disk_super = (struct btrfs_super_block *)bh->b_data; + + memset(&disk_super->magic, 0, sizeof(disk_super->magic)); + set_buffer_dirty(bh); + sync_dirty_buffer(bh); + brelse(bh); + } + + /* Notify udev that device has changed */ + btrfs_kobject_uevent(bdev, KOBJ_CHANGE); + + /* Update ctime/mtime for device path for libblkid */ + update_dev_time(device_path); } /* @@ -6823,3 +6929,38 @@ void btrfs_reset_fs_info_ptr(struct btrfs_fs_info *fs_info) fs_devices = fs_devices->seed; } } + +void btrfs_close_one_device(struct btrfs_device *device) +{ + struct btrfs_fs_devices *fs_devices = device->fs_devices; + struct btrfs_device *new_device; + struct rcu_string *name; + + if (device->bdev) + fs_devices->open_devices--; + + if (device->writeable && + device->devid != BTRFS_DEV_REPLACE_DEVID) { + list_del_init(&device->dev_alloc_list); + fs_devices->rw_devices--; + } + + if (device->missing) + fs_devices->missing_devices--; + + new_device = btrfs_alloc_device(NULL, &device->devid, + device->uuid); + BUG_ON(IS_ERR(new_device)); /* -ENOMEM */ + + /* Safe because we are under uuid_mutex */ + if (device->name) { + name = rcu_string_strdup(device->name->str, GFP_NOFS); + BUG_ON(!name); /* -ENOMEM */ + rcu_assign_pointer(new_device->name, name); + } + + list_replace_rcu(&device->dev_list, &new_device->dev_list); + new_device->fs_devices = device->fs_devices; + + call_rcu(&device->rcu, free_device); +} diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 2ca784a..ec57123 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -256,7 +256,7 @@ struct btrfs_fs_devices { struct btrfs_fs_info *fs_info; /* sysfs kobjects */ - struct kobject super_kobj; + struct kobject fsid_kobj; struct kobject *device_dir_kobj; struct completion kobj_unregister; }; @@ -334,10 +334,15 @@ struct btrfs_raid_attr { int dev_stripes; /* stripes per dev */ int devs_max; /* max devs to use */ int devs_min; /* min devs needed */ + int tolerated_failures; /* max tolerated fail devs */ int devs_increment; /* ndevs has to be a multiple of this */ int ncopies; /* how many copies to data has */ }; +extern const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES]; + +extern const u64 btrfs_raid_group[BTRFS_NR_RAID_TYPES]; + struct map_lookup { u64 type; int io_align; @@ -375,6 +380,20 @@ struct map_lookup { #define BTRFS_BALANCE_ARGS_DRANGE (1ULL << 3) #define BTRFS_BALANCE_ARGS_VRANGE (1ULL << 4) #define BTRFS_BALANCE_ARGS_LIMIT (1ULL << 5) +#define BTRFS_BALANCE_ARGS_LIMIT_RANGE (1ULL << 6) +#define BTRFS_BALANCE_ARGS_STRIPES_RANGE (1ULL << 7) +#define BTRFS_BALANCE_ARGS_USAGE_RANGE (1ULL << 8) + +#define BTRFS_BALANCE_ARGS_MASK \ + (BTRFS_BALANCE_ARGS_PROFILES | \ + BTRFS_BALANCE_ARGS_USAGE | \ + BTRFS_BALANCE_ARGS_DEVID | \ + BTRFS_BALANCE_ARGS_DRANGE | \ + BTRFS_BALANCE_ARGS_VRANGE | \ + BTRFS_BALANCE_ARGS_LIMIT | \ + BTRFS_BALANCE_ARGS_LIMIT_RANGE | \ + BTRFS_BALANCE_ARGS_STRIPES_RANGE | \ + BTRFS_BALANCE_ARGS_USAGE_RANGE) /* * Profile changing flags. When SOFT is set we won't relocate chunk if @@ -474,7 +493,7 @@ void btrfs_destroy_dev_replace_tgtdev(struct btrfs_fs_info *fs_info, struct btrfs_device *tgtdev); void btrfs_init_dev_replace_tgtdev_for_resume(struct btrfs_fs_info *fs_info, struct btrfs_device *tgtdev); -int btrfs_scratch_superblock(struct btrfs_device *device); +void btrfs_scratch_superblocks(struct block_device *bdev, char *device_path); int btrfs_is_parity_mirror(struct btrfs_mapping_tree *map_tree, u64 logical, u64 len, int mirror_num); unsigned long btrfs_full_stripe_len(struct btrfs_root *root, @@ -547,5 +566,6 @@ static inline void unlock_chunks(struct btrfs_root *root) struct list_head *btrfs_get_fs_uuids(void); void btrfs_set_fs_info_ptr(struct btrfs_fs_info *fs_info); void btrfs_reset_fs_info_ptr(struct btrfs_fs_info *fs_info); +void btrfs_close_one_device(struct btrfs_device *device); #endif diff --git a/fs/buffer.c b/fs/buffer.c index 82283ab..4f4cd95 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -999,7 +999,7 @@ grow_dev_page(struct block_device *bdev, sector_t block, int ret = 0; /* Will call free_more_memory() */ gfp_t gfp_mask; - gfp_mask = (mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS) | gfp; + gfp_mask = mapping_gfp_constraint(inode->i_mapping, ~__GFP_FS) | gfp; /* * XXX: __getblk_slow() can not really deal with failure and @@ -2420,9 +2420,9 @@ EXPORT_SYMBOL(block_commit_write); * unlock the page. * * Direct callers of this function should protect against filesystem freezing - * using sb_start_write() - sb_end_write() functions. + * using sb_start_pagefault() - sb_end_pagefault() functions. */ -int __block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, +int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, get_block_t get_block) { struct page *page = vmf->page; @@ -2459,26 +2459,6 @@ out_unlock: unlock_page(page); return ret; } -EXPORT_SYMBOL(__block_page_mkwrite); - -int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, - get_block_t get_block) -{ - int ret; - struct super_block *sb = file_inode(vma->vm_file)->i_sb; - - sb_start_pagefault(sb); - - /* - * Update file times before taking page lock. We may end up failing the - * fault so this update may be superfluous but who really cares... - */ - file_update_time(vma->vm_file); - - ret = __block_page_mkwrite(vma, vmf, get_block); - sb_end_pagefault(sb); - return block_page_mkwrite_return(ret); -} EXPORT_SYMBOL(block_page_mkwrite); /* diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h index aecd085..9c4b737 100644 --- a/fs/cachefiles/internal.h +++ b/fs/cachefiles/internal.h @@ -30,7 +30,7 @@ extern unsigned cachefiles_debug; #define CACHEFILES_DEBUG_KLEAVE 2 #define CACHEFILES_DEBUG_KDEBUG 4 -#define cachefiles_gfp (__GFP_WAIT | __GFP_NORETRY | __GFP_NOMEMALLOC) +#define cachefiles_gfp (__GFP_RECLAIM | __GFP_NORETRY | __GFP_NOMEMALLOC) /* * node records diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c index fc1056f..c4b8934 100644 --- a/fs/cachefiles/namei.c +++ b/fs/cachefiles/namei.c @@ -655,6 +655,8 @@ lookup_again: aops = d_backing_inode(object->dentry)->i_mapping->a_ops; if (!aops->bmap) goto check_error; + if (object->dentry->d_sb->s_blocksize > PAGE_SIZE) + goto check_error; object->backer = object->dentry; } else { diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c index 3cbb0e8..7a6b02f 100644 --- a/fs/cachefiles/rdwr.c +++ b/fs/cachefiles/rdwr.c @@ -414,9 +414,6 @@ int cachefiles_read_or_alloc_page(struct fscache_retrieval *op, ASSERT(inode->i_mapping->a_ops->readpages); /* calculate the shift required to use bmap */ - if (inode->i_sb->s_blocksize > PAGE_SIZE) - goto enobufs; - shift = PAGE_SHIFT - inode->i_sb->s_blocksize_bits; op->op.flags &= FSCACHE_OP_KEEP_FLAGS; @@ -711,9 +708,6 @@ int cachefiles_read_or_alloc_pages(struct fscache_retrieval *op, ASSERT(inode->i_mapping->a_ops->readpages); /* calculate the shift required to use bmap */ - if (inode->i_sb->s_blocksize > PAGE_SIZE) - goto all_enobufs; - shift = PAGE_SHIFT - inode->i_sb->s_blocksize_bits; pagevec_init(&pagevec, 0); @@ -905,6 +899,15 @@ int cachefiles_write_page(struct fscache_storage *op, struct page *page) cache = container_of(object->fscache.cache, struct cachefiles_cache, cache); + pos = (loff_t)page->index << PAGE_SHIFT; + + /* We mustn't write more data than we have, so we have to beware of a + * partial page at EOF. + */ + eof = object->fscache.store_limit_l; + if (pos >= eof) + goto error; + /* write the page to the backing filesystem and let it store it in its * own time */ path.mnt = cache->mnt; @@ -912,40 +915,38 @@ int cachefiles_write_page(struct fscache_storage *op, struct page *page) file = dentry_open(&path, O_RDWR | O_LARGEFILE, cache->cache_cred); if (IS_ERR(file)) { ret = PTR_ERR(file); - } else { - pos = (loff_t) page->index << PAGE_SHIFT; - - /* we mustn't write more data than we have, so we have - * to beware of a partial page at EOF */ - eof = object->fscache.store_limit_l; - len = PAGE_SIZE; - if (eof & ~PAGE_MASK) { - ASSERTCMP(pos, <, eof); - if (eof - pos < PAGE_SIZE) { - _debug("cut short %llx to %llx", - pos, eof); - len = eof - pos; - ASSERTCMP(pos + len, ==, eof); - } - } - - data = kmap(page); - ret = __kernel_write(file, data, len, &pos); - kunmap(page); - if (ret != len) - ret = -EIO; - fput(file); + goto error_2; } - if (ret < 0) { - if (ret == -EIO) - cachefiles_io_error_obj( - object, "Write page to backing file failed"); - ret = -ENOBUFS; + len = PAGE_SIZE; + if (eof & ~PAGE_MASK) { + if (eof - pos < PAGE_SIZE) { + _debug("cut short %llx to %llx", + pos, eof); + len = eof - pos; + ASSERTCMP(pos + len, ==, eof); + } } - _leave(" = %d", ret); - return ret; + data = kmap(page); + ret = __kernel_write(file, data, len, &pos); + kunmap(page); + fput(file); + if (ret != len) + goto error_eio; + + _leave(" = 0"); + return 0; + +error_eio: + ret = -EIO; +error_2: + if (ret == -EIO) + cachefiles_io_error_obj(object, + "Write page to backing file failed"); +error: + _leave(" = -ENOBUFS [%d]", ret); + return -ENOBUFS; } /* diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 9d23e78..b7d218a 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -1283,8 +1283,8 @@ static int ceph_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) int ret1; struct address_space *mapping = inode->i_mapping; struct page *page = find_or_create_page(mapping, 0, - mapping_gfp_mask(mapping) & - ~__GFP_FS); + mapping_gfp_constraint(mapping, + ~__GFP_FS)); if (!page) { ret = VM_FAULT_OOM; goto out; @@ -1428,7 +1428,8 @@ void ceph_fill_inline_data(struct inode *inode, struct page *locked_page, if (i_size_read(inode) == 0) return; page = find_or_create_page(mapping, 0, - mapping_gfp_mask(mapping) & ~__GFP_FS); + mapping_gfp_constraint(mapping, + ~__GFP_FS)); if (!page) return; if (PageUptodate(page)) { diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c index 6706bde..a2cb0c2 100644 --- a/fs/ceph/locks.c +++ b/fs/ceph/locks.c @@ -228,12 +228,12 @@ int ceph_flock(struct file *file, int cmd, struct file_lock *fl) err = ceph_lock_message(CEPH_LOCK_FLOCK, CEPH_MDS_OP_SETFILELOCK, file, lock_cmd, wait, fl); if (!err) { - err = flock_lock_file_wait(file, fl); + err = locks_lock_file_wait(file, fl); if (err) { ceph_lock_message(CEPH_LOCK_FLOCK, CEPH_MDS_OP_SETFILELOCK, file, CEPH_LOCK_UNLOCK, 0, fl); - dout("got %d on flock_lock_file_wait, undid lock", err); + dout("got %d on locks_lock_file_wait, undid lock", err); } } return err; diff --git a/fs/cifs/cifs_spnego.c b/fs/cifs/cifs_spnego.c index f4cf200..6908080 100644 --- a/fs/cifs/cifs_spnego.c +++ b/fs/cifs/cifs_spnego.c @@ -42,7 +42,7 @@ cifs_spnego_key_instantiate(struct key *key, struct key_preparsed_payload *prep) goto error; /* attach the data */ - key->payload.data = payload; + key->payload.data[0] = payload; ret = 0; error: @@ -52,7 +52,7 @@ error: static void cifs_spnego_key_destroy(struct key *key) { - kfree(key->payload.data); + kfree(key->payload.data[0]); } @@ -167,7 +167,7 @@ cifs_get_spnego_key(struct cifs_ses *sesInfo) #ifdef CONFIG_CIFS_DEBUG2 if (cifsFYI && !IS_ERR(spnego_key)) { - struct cifs_spnego_msg *msg = spnego_key->payload.data; + struct cifs_spnego_msg *msg = spnego_key->payload.data[0]; cifs_dump_mem("SPNEGO reply blob:", msg->data, min(1024U, msg->secblob_len + msg->sesskey_len)); } diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c index 1ea780b..3f93125 100644 --- a/fs/cifs/cifsacl.c +++ b/fs/cifs/cifsacl.c @@ -58,16 +58,15 @@ cifs_idmap_key_instantiate(struct key *key, struct key_preparsed_payload *prep) * dereference payload.data! */ if (prep->datalen <= sizeof(key->payload)) { - key->payload.value = 0; - memcpy(&key->payload.value, prep->data, prep->datalen); - key->datalen = prep->datalen; - return 0; + key->payload.data[0] = NULL; + memcpy(&key->payload, prep->data, prep->datalen); + } else { + payload = kmemdup(prep->data, prep->datalen, GFP_KERNEL); + if (!payload) + return -ENOMEM; + key->payload.data[0] = payload; } - payload = kmemdup(prep->data, prep->datalen, GFP_KERNEL); - if (!payload) - return -ENOMEM; - key->payload.data = payload; key->datalen = prep->datalen; return 0; } @@ -76,7 +75,7 @@ static inline void cifs_idmap_key_destroy(struct key *key) { if (key->datalen > sizeof(key->payload)) - kfree(key->payload.data); + kfree(key->payload.data[0]); } static struct key_type cifs_idmap_key_type = { @@ -233,8 +232,8 @@ id_to_sid(unsigned int cid, uint sidtype, struct cifs_sid *ssid) * it could be. */ ksid = sidkey->datalen <= sizeof(sidkey->payload) ? - (struct cifs_sid *)&sidkey->payload.value : - (struct cifs_sid *)sidkey->payload.data; + (struct cifs_sid *)&sidkey->payload : + (struct cifs_sid *)sidkey->payload.data[0]; ksid_size = CIFS_SID_BASE_SIZE + (ksid->num_subauth * sizeof(__le32)); if (ksid_size > sidkey->datalen) { @@ -307,14 +306,14 @@ sid_to_id(struct cifs_sb_info *cifs_sb, struct cifs_sid *psid, if (sidtype == SIDOWNER) { kuid_t uid; uid_t id; - memcpy(&id, &sidkey->payload.value, sizeof(uid_t)); + memcpy(&id, &sidkey->payload.data[0], sizeof(uid_t)); uid = make_kuid(&init_user_ns, id); if (uid_valid(uid)) fuid = uid; } else { kgid_t gid; gid_t id; - memcpy(&id, &sidkey->payload.value, sizeof(gid_t)); + memcpy(&id, &sidkey->payload.data[0], sizeof(gid_t)); gid = make_kgid(&init_user_ns, id); if (gid_valid(gid)) fgid = gid; diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c index aa0dc25..afa09fc 100644 --- a/fs/cifs/cifsencrypt.c +++ b/fs/cifs/cifsencrypt.c @@ -444,6 +444,48 @@ find_domain_name(struct cifs_ses *ses, const struct nls_table *nls_cp) return 0; } +/* Server has provided av pairs/target info in the type 2 challenge + * packet and we have plucked it and stored within smb session. + * We parse that blob here to find the server given timestamp + * as part of ntlmv2 authentication (or local current time as + * default in case of failure) + */ +static __le64 +find_timestamp(struct cifs_ses *ses) +{ + unsigned int attrsize; + unsigned int type; + unsigned int onesize = sizeof(struct ntlmssp2_name); + unsigned char *blobptr; + unsigned char *blobend; + struct ntlmssp2_name *attrptr; + + if (!ses->auth_key.len || !ses->auth_key.response) + return 0; + + blobptr = ses->auth_key.response; + blobend = blobptr + ses->auth_key.len; + + while (blobptr + onesize < blobend) { + attrptr = (struct ntlmssp2_name *) blobptr; + type = le16_to_cpu(attrptr->type); + if (type == NTLMSSP_AV_EOL) + break; + blobptr += 2; /* advance attr type */ + attrsize = le16_to_cpu(attrptr->length); + blobptr += 2; /* advance attr size */ + if (blobptr + attrsize > blobend) + break; + if (type == NTLMSSP_AV_TIMESTAMP) { + if (attrsize == sizeof(u64)) + return *((__le64 *)blobptr); + } + blobptr += attrsize; /* advance attr value */ + } + + return cpu_to_le64(cifs_UnixTimeToNT(CURRENT_TIME)); +} + static int calc_ntlmv2_hash(struct cifs_ses *ses, char *ntlmv2_hash, const struct nls_table *nls_cp) { @@ -641,6 +683,7 @@ setup_ntlmv2_rsp(struct cifs_ses *ses, const struct nls_table *nls_cp) struct ntlmv2_resp *ntlmv2; char ntlmv2_hash[16]; unsigned char *tiblob = NULL; /* target info blob */ + __le64 rsp_timestamp; if (ses->server->negflavor == CIFS_NEGFLAVOR_EXTENDED) { if (!ses->domainName) { @@ -659,6 +702,12 @@ setup_ntlmv2_rsp(struct cifs_ses *ses, const struct nls_table *nls_cp) } } + /* Must be within 5 minutes of the server (or in range +/-2h + * in case of Mac OS X), so simply carry over server timestamp + * (as Windows 7 does) + */ + rsp_timestamp = find_timestamp(ses); + baselen = CIFS_SESS_KEY_SIZE + sizeof(struct ntlmv2_resp); tilen = ses->auth_key.len; tiblob = ses->auth_key.response; @@ -675,8 +724,8 @@ setup_ntlmv2_rsp(struct cifs_ses *ses, const struct nls_table *nls_cp) (ses->auth_key.response + CIFS_SESS_KEY_SIZE); ntlmv2->blob_signature = cpu_to_le32(0x00000101); ntlmv2->reserved = 0; - /* Must be within 5 minutes of the server */ - ntlmv2->time = cpu_to_le64(cifs_UnixTimeToNT(CURRENT_TIME)); + ntlmv2->time = rsp_timestamp; + get_random_bytes(&ntlmv2->client_chal, sizeof(ntlmv2->client_chal)); ntlmv2->reserved2 = 0; diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index 27aea11..c3cc160 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -136,5 +136,5 @@ extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg); extern const struct export_operations cifs_export_ops; #endif /* CONFIG_CIFS_NFSD_EXPORT */ -#define CIFS_VERSION "2.07" +#define CIFS_VERSION "2.08" #endif /* _CIFSFS_H */ diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 773f4dc..3f22285 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -2325,13 +2325,14 @@ static int cifs_set_cifscreds(struct smb_vol *vol, struct cifs_ses *ses) { int rc = 0; - char *desc, *delim, *payload; + const char *delim, *payload; + char *desc; ssize_t len; struct key *key; struct TCP_Server_Info *server = ses->server; struct sockaddr_in *sa; struct sockaddr_in6 *sa6; - struct user_key_payload *upayload; + const struct user_key_payload *upayload; desc = kmalloc(CIFSCREDS_DESC_SIZE, GFP_KERNEL); if (!desc) @@ -2374,14 +2375,14 @@ cifs_set_cifscreds(struct smb_vol *vol, struct cifs_ses *ses) } down_read(&key->sem); - upayload = key->payload.data; + upayload = user_key_payload(key); if (IS_ERR_OR_NULL(upayload)) { rc = upayload ? PTR_ERR(upayload) : -EINVAL; goto out_key_put; } /* find first : in payload */ - payload = (char *)upayload->data; + payload = upayload->data; delim = strnchr(payload, upayload->datalen, ':'); cifs_dbg(FYI, "payload=%s\n", payload); if (!delim) { diff --git a/fs/cifs/file.c b/fs/cifs/file.c index e2a6af1..0068e82 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -1553,7 +1553,7 @@ cifs_setlk(struct file *file, struct file_lock *flock, __u32 type, out: if (flock->fl_flags & FL_POSIX && !rc) - rc = posix_lock_file_wait(file, flock); + rc = locks_lock_file_wait(file, flock); return rc; } @@ -3380,6 +3380,7 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list, struct page *page, *tpage; unsigned int expected_index; int rc; + gfp_t gfp = mapping_gfp_constraint(mapping, GFP_KERNEL); INIT_LIST_HEAD(tmplist); @@ -3392,7 +3393,7 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list, */ __set_page_locked(page); rc = add_to_page_cache_locked(page, mapping, - page->index, GFP_KERNEL); + page->index, gfp); /* give up if we can't stick it in the cache */ if (rc) { @@ -3418,8 +3419,7 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list, break; __set_page_locked(page); - if (add_to_page_cache_locked(page, mapping, page->index, - GFP_KERNEL)) { + if (add_to_page_cache_locked(page, mapping, page->index, gfp)) { __clear_page_locked(page); break; } diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index f621b44..6b66dd5 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -2034,7 +2034,6 @@ cifs_set_file_size(struct inode *inode, struct iattr *attrs, struct tcon_link *tlink = NULL; struct cifs_tcon *tcon = NULL; struct TCP_Server_Info *server; - struct cifs_io_parms io_parms; /* * To avoid spurious oplock breaks from server, in the case of @@ -2056,18 +2055,6 @@ cifs_set_file_size(struct inode *inode, struct iattr *attrs, rc = -ENOSYS; cifsFileInfo_put(open_file); cifs_dbg(FYI, "SetFSize for attrs rc = %d\n", rc); - if ((rc == -EINVAL) || (rc == -EOPNOTSUPP)) { - unsigned int bytes_written; - - io_parms.netfid = open_file->fid.netfid; - io_parms.pid = open_file->pid; - io_parms.tcon = tcon; - io_parms.offset = 0; - io_parms.length = attrs->ia_size; - rc = CIFSSMBWrite(xid, &io_parms, &bytes_written, - NULL, NULL, 1); - cifs_dbg(FYI, "Wrt seteof rc %d\n", rc); - } } else rc = -EINVAL; @@ -2093,28 +2080,7 @@ cifs_set_file_size(struct inode *inode, struct iattr *attrs, else rc = -ENOSYS; cifs_dbg(FYI, "SetEOF by path (setattrs) rc = %d\n", rc); - if ((rc == -EINVAL) || (rc == -EOPNOTSUPP)) { - __u16 netfid; - int oplock = 0; - rc = SMBLegacyOpen(xid, tcon, full_path, FILE_OPEN, - GENERIC_WRITE, CREATE_NOT_DIR, &netfid, - &oplock, NULL, cifs_sb->local_nls, - cifs_remap(cifs_sb)); - if (rc == 0) { - unsigned int bytes_written; - - io_parms.netfid = netfid; - io_parms.pid = current->tgid; - io_parms.tcon = tcon; - io_parms.offset = 0; - io_parms.length = attrs->ia_size; - rc = CIFSSMBWrite(xid, &io_parms, &bytes_written, NULL, - NULL, 1); - cifs_dbg(FYI, "wrt seteof rc %d\n", rc); - CIFSSMBClose(xid, tcon, netfid); - } - } if (tlink) cifs_put_tlink(tlink); diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index b1eede3..0557c45 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -84,7 +84,7 @@ cifs_prime_dcache(struct dentry *parent, struct qstr *name, cifs_dbg(FYI, "%s: for %s\n", __func__, name->name); dentry = d_hash_and_lookup(parent, name); - if (unlikely(IS_ERR(dentry))) + if (IS_ERR(dentry)) return; if (dentry) { diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c index bce6fdc..59727e3 100644 --- a/fs/cifs/sess.c +++ b/fs/cifs/sess.c @@ -988,7 +988,7 @@ sess_auth_kerberos(struct sess_data *sess_data) goto out; } - msg = spnego_key->payload.data; + msg = spnego_key->payload.data[0]; /* * check version field to make sure that cifs.upcall is * sending us a response in an expected form diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index df91bcf..18da19f 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -50,9 +50,13 @@ change_conf(struct TCP_Server_Info *server) break; default: server->echoes = true; - server->oplocks = true; + if (enable_oplocks) { + server->oplocks = true; + server->oplock_credits = 1; + } else + server->oplocks = false; + server->echo_credits = 1; - server->oplock_credits = 1; } server->credits -= server->echo_credits + server->oplock_credits; return 0; diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 070fb2a..6127692 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -46,6 +46,7 @@ #include "smb2status.h" #include "smb2glob.h" #include "cifspdu.h" +#include "cifs_spnego.h" /* * The following table defines the expected "StructureSize" of SMB2 requests @@ -486,19 +487,15 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses) cifs_dbg(FYI, "missing security blob on negprot\n"); rc = cifs_enable_signing(server, ses->sign); -#ifdef CONFIG_SMB2_ASN1 /* BB REMOVEME when updated asn1.c ready */ if (rc) goto neg_exit; - if (blob_length) + if (blob_length) { rc = decode_negTokenInit(security_blob, blob_length, server); - if (rc == 1) - rc = 0; - else if (rc == 0) { - rc = -EIO; - goto neg_exit; + if (rc == 1) + rc = 0; + else if (rc == 0) + rc = -EIO; } -#endif - neg_exit: free_rsp_buf(resp_buftype, rsp); return rc; @@ -592,7 +589,8 @@ SMB2_sess_setup(const unsigned int xid, struct cifs_ses *ses, __le32 phase = NtLmNegotiate; /* NTLMSSP, if needed, is multistage */ struct TCP_Server_Info *server = ses->server; u16 blob_length = 0; - char *security_blob; + struct key *spnego_key = NULL; + char *security_blob = NULL; char *ntlmssp_blob = NULL; bool use_spnego = false; /* else use raw ntlmssp */ @@ -620,7 +618,8 @@ SMB2_sess_setup(const unsigned int xid, struct cifs_ses *ses, ses->ntlmssp->sesskey_per_smbsess = true; /* FIXME: allow for other auth types besides NTLMSSP (e.g. krb5) */ - ses->sectype = RawNTLMSSP; + if (ses->sectype != Kerberos && ses->sectype != RawNTLMSSP) + ses->sectype = RawNTLMSSP; ssetup_ntlmssp_authenticate: if (phase == NtLmChallenge) @@ -649,7 +648,48 @@ ssetup_ntlmssp_authenticate: iov[0].iov_base = (char *)req; /* 4 for rfc1002 length field and 1 for pad */ iov[0].iov_len = get_rfc1002_length(req) + 4 - 1; - if (phase == NtLmNegotiate) { + + if (ses->sectype == Kerberos) { +#ifdef CONFIG_CIFS_UPCALL + struct cifs_spnego_msg *msg; + + spnego_key = cifs_get_spnego_key(ses); + if (IS_ERR(spnego_key)) { + rc = PTR_ERR(spnego_key); + spnego_key = NULL; + goto ssetup_exit; + } + + msg = spnego_key->payload.data[0]; + /* + * check version field to make sure that cifs.upcall is + * sending us a response in an expected form + */ + if (msg->version != CIFS_SPNEGO_UPCALL_VERSION) { + cifs_dbg(VFS, + "bad cifs.upcall version. Expected %d got %d", + CIFS_SPNEGO_UPCALL_VERSION, msg->version); + rc = -EKEYREJECTED; + goto ssetup_exit; + } + ses->auth_key.response = kmemdup(msg->data, msg->sesskey_len, + GFP_KERNEL); + if (!ses->auth_key.response) { + cifs_dbg(VFS, + "Kerberos can't allocate (%u bytes) memory", + msg->sesskey_len); + rc = -ENOMEM; + goto ssetup_exit; + } + ses->auth_key.len = msg->sesskey_len; + blob_length = msg->secblob_len; + iov[1].iov_base = msg->data + msg->sesskey_len; + iov[1].iov_len = blob_length; +#else + rc = -EOPNOTSUPP; + goto ssetup_exit; +#endif /* CONFIG_CIFS_UPCALL */ + } else if (phase == NtLmNegotiate) { /* if not krb5 must be ntlmssp */ ntlmssp_blob = kmalloc(sizeof(struct _NEGOTIATE_MESSAGE), GFP_KERNEL); if (ntlmssp_blob == NULL) { @@ -672,6 +712,8 @@ ssetup_ntlmssp_authenticate: /* with raw NTLMSSP we don't encapsulate in SPNEGO */ security_blob = ntlmssp_blob; } + iov[1].iov_base = security_blob; + iov[1].iov_len = blob_length; } else if (phase == NtLmAuthenticate) { req->hdr.SessionId = ses->Suid; ntlmssp_blob = kzalloc(sizeof(struct _NEGOTIATE_MESSAGE) + 500, @@ -699,6 +741,8 @@ ssetup_ntlmssp_authenticate: } else { security_blob = ntlmssp_blob; } + iov[1].iov_base = security_blob; + iov[1].iov_len = blob_length; } else { cifs_dbg(VFS, "illegal ntlmssp phase\n"); rc = -EIO; @@ -710,8 +754,6 @@ ssetup_ntlmssp_authenticate: cpu_to_le16(sizeof(struct smb2_sess_setup_req) - 1 /* pad */ - 4 /* rfc1001 len */); req->SecurityBufferLength = cpu_to_le16(blob_length); - iov[1].iov_base = security_blob; - iov[1].iov_len = blob_length; inc_rfc1001_len(req, blob_length - 1 /* pad */); @@ -722,6 +764,7 @@ ssetup_ntlmssp_authenticate: kfree(security_blob); rsp = (struct smb2_sess_setup_rsp *)iov[0].iov_base; + ses->Suid = rsp->hdr.SessionId; if (resp_buftype != CIFS_NO_BUFFER && rsp->hdr.Status == STATUS_MORE_PROCESSING_REQUIRED) { if (phase != NtLmNegotiate) { @@ -739,7 +782,6 @@ ssetup_ntlmssp_authenticate: /* NTLMSSP Negotiate sent now processing challenge (response) */ phase = NtLmChallenge; /* process ntlmssp challenge */ rc = 0; /* MORE_PROCESSING is not an error here but expected */ - ses->Suid = rsp->hdr.SessionId; rc = decode_ntlmssp_challenge(rsp->Buffer, le16_to_cpu(rsp->SecurityBufferLength), ses); } @@ -796,6 +838,10 @@ keygen_exit: kfree(ses->auth_key.response); ses->auth_key.response = NULL; } + if (spnego_key) { + key_invalidate(spnego_key); + key_put(spnego_key); + } kfree(ses->ntlmssp); return rc; @@ -876,6 +922,12 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree, if (tcon && tcon->bad_network_name) return -ENOENT; + if ((tcon && tcon->seal) && + ((ses->server->capabilities & SMB2_GLOBAL_CAP_ENCRYPTION) == 0)) { + cifs_dbg(VFS, "encryption requested but no server support"); + return -EOPNOTSUPP; + } + unc_path = kmalloc(MAX_SHARENAME_LENGTH * 2, GFP_KERNEL); if (unc_path == NULL) return -ENOMEM; @@ -955,6 +1007,8 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree, ((tcon->share_flags & SHI1005_FLAGS_DFS) == 0)) cifs_dbg(VFS, "DFS capability contradicts DFS flag\n"); init_copy_chunk_defaults(tcon); + if (tcon->share_flags & SHI1005_FLAGS_ENCRYPT_DATA) + cifs_dbg(VFS, "Encrypted shares not supported"); if (tcon->ses->server->ops->validate_negotiate) rc = tcon->ses->server->ops->validate_negotiate(xid, tcon); tcon_exit: diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c index 48851f6..dcf2653 100644 --- a/fs/compat_ioctl.c +++ b/fs/compat_ioctl.c @@ -686,7 +686,7 @@ static int do_i2c_rdwr_ioctl(unsigned int fd, unsigned int cmd, if (get_user(nmsgs, &udata->nmsgs)) return -EFAULT; - if (nmsgs > I2C_RDRW_IOCTL_MAX_MSGS) + if (nmsgs > I2C_RDWR_IOCTL_MAX_MSGS) return -EINVAL; if (get_user(datap, &udata->msgs)) diff --git a/fs/coredump.c b/fs/coredump.c index a8f7564..1777331 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -280,23 +280,24 @@ out: return ispipe; } -static int zap_process(struct task_struct *start, int exit_code) +static int zap_process(struct task_struct *start, int exit_code, int flags) { struct task_struct *t; int nr = 0; + /* ignore all signals except SIGKILL, see prepare_signal() */ + start->signal->flags = SIGNAL_GROUP_COREDUMP | flags; start->signal->group_exit_code = exit_code; start->signal->group_stop_count = 0; - t = start; - do { + for_each_thread(start, t) { task_clear_jobctl_pending(t, JOBCTL_PENDING_MASK); if (t != current && t->mm) { sigaddset(&t->pending.signal, SIGKILL); signal_wake_up(t, 1); nr++; } - } while_each_thread(start, t); + } return nr; } @@ -311,10 +312,8 @@ static int zap_threads(struct task_struct *tsk, struct mm_struct *mm, spin_lock_irq(&tsk->sighand->siglock); if (!signal_group_exit(tsk->signal)) { mm->core_state = core_state; - nr = zap_process(tsk, exit_code); tsk->signal->group_exit_task = tsk; - /* ignore all signals except SIGKILL, see prepare_signal() */ - tsk->signal->flags = SIGNAL_GROUP_COREDUMP; + nr = zap_process(tsk, exit_code, 0); clear_tsk_thread_flag(tsk, TIF_SIGPENDING); } spin_unlock_irq(&tsk->sighand->siglock); @@ -360,18 +359,18 @@ static int zap_threads(struct task_struct *tsk, struct mm_struct *mm, continue; if (g->flags & PF_KTHREAD) continue; - p = g; - do { - if (p->mm) { - if (unlikely(p->mm == mm)) { - lock_task_sighand(p, &flags); - nr += zap_process(p, exit_code); - p->signal->flags = SIGNAL_GROUP_EXIT; - unlock_task_sighand(p, &flags); - } - break; + + for_each_thread(g, p) { + if (unlikely(!p->mm)) + continue; + if (unlikely(p->mm == mm)) { + lock_task_sighand(p, &flags); + nr += zap_process(p, exit_code, + SIGNAL_GROUP_EXIT); + unlock_task_sighand(p, &flags); } - } while_each_thread(g, p); + break; + } } rcu_read_unlock(); done: @@ -290,6 +290,7 @@ static int copy_user_bh(struct page *to, struct buffer_head *bh, static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh, struct vm_area_struct *vma, struct vm_fault *vmf) { + struct address_space *mapping = inode->i_mapping; sector_t sector = bh->b_blocknr << (inode->i_blkbits - 9); unsigned long vaddr = (unsigned long)vmf->virtual_address; void __pmem *addr; @@ -297,6 +298,8 @@ static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh, pgoff_t size; int error; + i_mmap_lock_read(mapping); + /* * Check truncate didn't happen while we were allocating a block. * If it did, this block may or may not be still allocated to the @@ -326,6 +329,8 @@ static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh, error = vm_insert_mixed(vma, vaddr, pfn); out: + i_mmap_unlock_read(mapping); + return error; } @@ -387,17 +392,15 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, * from a read fault and we've raced with a truncate */ error = -EIO; - goto unlock; + goto unlock_page; } - } else { - i_mmap_lock_write(mapping); } error = get_block(inode, block, &bh, 0); if (!error && (bh.b_size < PAGE_SIZE)) error = -EIO; /* fs corruption? */ if (error) - goto unlock; + goto unlock_page; if (!buffer_mapped(&bh) && !buffer_unwritten(&bh) && !vmf->cow_page) { if (vmf->flags & FAULT_FLAG_WRITE) { @@ -408,9 +411,8 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, if (!error && (bh.b_size < PAGE_SIZE)) error = -EIO; if (error) - goto unlock; + goto unlock_page; } else { - i_mmap_unlock_write(mapping); return dax_load_hole(mapping, page, vmf); } } @@ -422,15 +424,17 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, else clear_user_highpage(new_page, vaddr); if (error) - goto unlock; + goto unlock_page; vmf->page = page; if (!page) { + i_mmap_lock_read(mapping); /* Check we didn't race with truncate */ size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT; if (vmf->pgoff >= size) { + i_mmap_unlock_read(mapping); error = -EIO; - goto unlock; + goto out; } } return VM_FAULT_LOCKED; @@ -466,8 +470,6 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, WARN_ON_ONCE(!(vmf->flags & FAULT_FLAG_WRITE)); } - if (!page) - i_mmap_unlock_write(mapping); out: if (error == -ENOMEM) return VM_FAULT_OOM | major; @@ -476,14 +478,11 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, return VM_FAULT_SIGBUS | major; return VM_FAULT_NOPAGE | major; - unlock: + unlock_page: if (page) { unlock_page(page); page_cache_release(page); - } else { - i_mmap_unlock_write(mapping); } - goto out; } EXPORT_SYMBOL(__dax_fault); @@ -561,10 +560,10 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address, block = (sector_t)pgoff << (PAGE_SHIFT - blkbits); bh.b_size = PMD_SIZE; - i_mmap_lock_write(mapping); length = get_block(inode, block, &bh, write); if (length) return VM_FAULT_SIGBUS; + i_mmap_lock_read(mapping); /* * If the filesystem isn't willing to tell us the length of a hole, @@ -574,24 +573,14 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address, if (!buffer_size_valid(&bh) || bh.b_size < PMD_SIZE) goto fallback; - if (buffer_unwritten(&bh) || buffer_new(&bh)) { - int i; - for (i = 0; i < PTRS_PER_PMD; i++) - clear_pmem(kaddr + i * PAGE_SIZE, PAGE_SIZE); - wmb_pmem(); - count_vm_event(PGMAJFAULT); - mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT); - result |= VM_FAULT_MAJOR; - } - /* * If we allocated new storage, make sure no process has any * zero pages covering this hole */ if (buffer_new(&bh)) { - i_mmap_unlock_write(mapping); + i_mmap_unlock_read(mapping); unmap_mapping_range(mapping, pgoff << PAGE_SHIFT, PMD_SIZE, 0); - i_mmap_lock_write(mapping); + i_mmap_lock_read(mapping); } /* @@ -638,15 +627,25 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address, if ((length < PMD_SIZE) || (pfn & PG_PMD_COLOUR)) goto fallback; + if (buffer_unwritten(&bh) || buffer_new(&bh)) { + int i; + for (i = 0; i < PTRS_PER_PMD; i++) + clear_pmem(kaddr + i * PAGE_SIZE, PAGE_SIZE); + wmb_pmem(); + count_vm_event(PGMAJFAULT); + mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT); + result |= VM_FAULT_MAJOR; + } + result |= vmf_insert_pfn_pmd(vma, address, pmd, pfn, write); } out: + i_mmap_unlock_read(mapping); + if (buffer_unwritten(&bh)) complete_unwritten(&bh, !(result & VM_FAULT_ERROR)); - i_mmap_unlock_write(mapping); - return result; fallback: diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index 6c55ade..d2ba12e 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -42,6 +42,22 @@ const struct file_operations debugfs_file_operations = { .llseek = noop_llseek, }; +static struct dentry *debugfs_create_mode(const char *name, umode_t mode, + struct dentry *parent, void *value, + const struct file_operations *fops, + const struct file_operations *fops_ro, + const struct file_operations *fops_wo) +{ + /* if there are no write bits set, make read only */ + if (!(mode & S_IWUGO)) + return debugfs_create_file(name, mode, parent, value, fops_ro); + /* if there are no read bits set, make write only */ + if (!(mode & S_IRUGO)) + return debugfs_create_file(name, mode, parent, value, fops_wo); + + return debugfs_create_file(name, mode, parent, value, fops); +} + static int debugfs_u8_set(void *data, u64 val) { *(u8 *)data = val; @@ -83,14 +99,8 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_u8_wo, NULL, debugfs_u8_set, "%llu\n"); struct dentry *debugfs_create_u8(const char *name, umode_t mode, struct dentry *parent, u8 *value) { - /* if there are no write bits set, make read only */ - if (!(mode & S_IWUGO)) - return debugfs_create_file(name, mode, parent, value, &fops_u8_ro); - /* if there are no read bits set, make write only */ - if (!(mode & S_IRUGO)) - return debugfs_create_file(name, mode, parent, value, &fops_u8_wo); - - return debugfs_create_file(name, mode, parent, value, &fops_u8); + return debugfs_create_mode(name, mode, parent, value, &fops_u8, + &fops_u8_ro, &fops_u8_wo); } EXPORT_SYMBOL_GPL(debugfs_create_u8); @@ -135,14 +145,8 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_u16_wo, NULL, debugfs_u16_set, "%llu\n"); struct dentry *debugfs_create_u16(const char *name, umode_t mode, struct dentry *parent, u16 *value) { - /* if there are no write bits set, make read only */ - if (!(mode & S_IWUGO)) - return debugfs_create_file(name, mode, parent, value, &fops_u16_ro); - /* if there are no read bits set, make write only */ - if (!(mode & S_IRUGO)) - return debugfs_create_file(name, mode, parent, value, &fops_u16_wo); - - return debugfs_create_file(name, mode, parent, value, &fops_u16); + return debugfs_create_mode(name, mode, parent, value, &fops_u16, + &fops_u16_ro, &fops_u16_wo); } EXPORT_SYMBOL_GPL(debugfs_create_u16); @@ -187,14 +191,8 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_u32_wo, NULL, debugfs_u32_set, "%llu\n"); struct dentry *debugfs_create_u32(const char *name, umode_t mode, struct dentry *parent, u32 *value) { - /* if there are no write bits set, make read only */ - if (!(mode & S_IWUGO)) - return debugfs_create_file(name, mode, parent, value, &fops_u32_ro); - /* if there are no read bits set, make write only */ - if (!(mode & S_IRUGO)) - return debugfs_create_file(name, mode, parent, value, &fops_u32_wo); - - return debugfs_create_file(name, mode, parent, value, &fops_u32); + return debugfs_create_mode(name, mode, parent, value, &fops_u32, + &fops_u32_ro, &fops_u32_wo); } EXPORT_SYMBOL_GPL(debugfs_create_u32); @@ -240,17 +238,59 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_u64_wo, NULL, debugfs_u64_set, "%llu\n"); struct dentry *debugfs_create_u64(const char *name, umode_t mode, struct dentry *parent, u64 *value) { - /* if there are no write bits set, make read only */ - if (!(mode & S_IWUGO)) - return debugfs_create_file(name, mode, parent, value, &fops_u64_ro); - /* if there are no read bits set, make write only */ - if (!(mode & S_IRUGO)) - return debugfs_create_file(name, mode, parent, value, &fops_u64_wo); - - return debugfs_create_file(name, mode, parent, value, &fops_u64); + return debugfs_create_mode(name, mode, parent, value, &fops_u64, + &fops_u64_ro, &fops_u64_wo); } EXPORT_SYMBOL_GPL(debugfs_create_u64); +static int debugfs_ulong_set(void *data, u64 val) +{ + *(unsigned long *)data = val; + return 0; +} + +static int debugfs_ulong_get(void *data, u64 *val) +{ + *val = *(unsigned long *)data; + return 0; +} +DEFINE_SIMPLE_ATTRIBUTE(fops_ulong, debugfs_ulong_get, debugfs_ulong_set, "%llu\n"); +DEFINE_SIMPLE_ATTRIBUTE(fops_ulong_ro, debugfs_ulong_get, NULL, "%llu\n"); +DEFINE_SIMPLE_ATTRIBUTE(fops_ulong_wo, NULL, debugfs_ulong_set, "%llu\n"); + +/** + * debugfs_create_ulong - create a debugfs file that is used to read and write + * an unsigned long value. + * @name: a pointer to a string containing the name of the file to create. + * @mode: the permission that the file should have + * @parent: a pointer to the parent dentry for this file. This should be a + * directory dentry if set. If this parameter is %NULL, then the + * file will be created in the root of the debugfs filesystem. + * @value: a pointer to the variable that the file should read to and write + * from. + * + * This function creates a file in debugfs with the given name that + * contains the value of the variable @value. If the @mode variable is so + * set, it can be read from, and written to. + * + * This function will return a pointer to a dentry if it succeeds. This + * pointer must be passed to the debugfs_remove() function when the file is + * to be removed (no automatic cleanup happens if your module is unloaded, + * you are responsible here.) If an error occurs, %NULL will be returned. + * + * If debugfs is not enabled in the kernel, the value -%ENODEV will be + * returned. It is not wise to check for this value, but rather, check for + * %NULL or !%NULL instead as to eliminate the need for #ifdef in the calling + * code. + */ +struct dentry *debugfs_create_ulong(const char *name, umode_t mode, + struct dentry *parent, unsigned long *value) +{ + return debugfs_create_mode(name, mode, parent, value, &fops_ulong, + &fops_ulong_ro, &fops_ulong_wo); +} +EXPORT_SYMBOL_GPL(debugfs_create_ulong); + DEFINE_SIMPLE_ATTRIBUTE(fops_x8, debugfs_u8_get, debugfs_u8_set, "0x%02llx\n"); DEFINE_SIMPLE_ATTRIBUTE(fops_x8_ro, debugfs_u8_get, NULL, "0x%02llx\n"); DEFINE_SIMPLE_ATTRIBUTE(fops_x8_wo, NULL, debugfs_u8_set, "0x%02llx\n"); @@ -264,6 +304,8 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_x32_ro, debugfs_u32_get, NULL, "0x%08llx\n"); DEFINE_SIMPLE_ATTRIBUTE(fops_x32_wo, NULL, debugfs_u32_set, "0x%08llx\n"); DEFINE_SIMPLE_ATTRIBUTE(fops_x64, debugfs_u64_get, debugfs_u64_set, "0x%016llx\n"); +DEFINE_SIMPLE_ATTRIBUTE(fops_x64_ro, debugfs_u64_get, NULL, "0x%016llx\n"); +DEFINE_SIMPLE_ATTRIBUTE(fops_x64_wo, NULL, debugfs_u64_set, "0x%016llx\n"); /* * debugfs_create_x{8,16,32,64} - create a debugfs file that is used to read and write an unsigned {8,16,32,64}-bit value @@ -286,14 +328,8 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_x64, debugfs_u64_get, debugfs_u64_set, "0x%016llx\n struct dentry *debugfs_create_x8(const char *name, umode_t mode, struct dentry *parent, u8 *value) { - /* if there are no write bits set, make read only */ - if (!(mode & S_IWUGO)) - return debugfs_create_file(name, mode, parent, value, &fops_x8_ro); - /* if there are no read bits set, make write only */ - if (!(mode & S_IRUGO)) - return debugfs_create_file(name, mode, parent, value, &fops_x8_wo); - - return debugfs_create_file(name, mode, parent, value, &fops_x8); + return debugfs_create_mode(name, mode, parent, value, &fops_x8, + &fops_x8_ro, &fops_x8_wo); } EXPORT_SYMBOL_GPL(debugfs_create_x8); @@ -310,14 +346,8 @@ EXPORT_SYMBOL_GPL(debugfs_create_x8); struct dentry *debugfs_create_x16(const char *name, umode_t mode, struct dentry *parent, u16 *value) { - /* if there are no write bits set, make read only */ - if (!(mode & S_IWUGO)) - return debugfs_create_file(name, mode, parent, value, &fops_x16_ro); - /* if there are no read bits set, make write only */ - if (!(mode & S_IRUGO)) - return debugfs_create_file(name, mode, parent, value, &fops_x16_wo); - - return debugfs_create_file(name, mode, parent, value, &fops_x16); + return debugfs_create_mode(name, mode, parent, value, &fops_x16, + &fops_x16_ro, &fops_x16_wo); } EXPORT_SYMBOL_GPL(debugfs_create_x16); @@ -334,14 +364,8 @@ EXPORT_SYMBOL_GPL(debugfs_create_x16); struct dentry *debugfs_create_x32(const char *name, umode_t mode, struct dentry *parent, u32 *value) { - /* if there are no write bits set, make read only */ - if (!(mode & S_IWUGO)) - return debugfs_create_file(name, mode, parent, value, &fops_x32_ro); - /* if there are no read bits set, make write only */ - if (!(mode & S_IRUGO)) - return debugfs_create_file(name, mode, parent, value, &fops_x32_wo); - - return debugfs_create_file(name, mode, parent, value, &fops_x32); + return debugfs_create_mode(name, mode, parent, value, &fops_x32, + &fops_x32_ro, &fops_x32_wo); } EXPORT_SYMBOL_GPL(debugfs_create_x32); @@ -358,7 +382,8 @@ EXPORT_SYMBOL_GPL(debugfs_create_x32); struct dentry *debugfs_create_x64(const char *name, umode_t mode, struct dentry *parent, u64 *value) { - return debugfs_create_file(name, mode, parent, value, &fops_x64); + return debugfs_create_mode(name, mode, parent, value, &fops_x64, + &fops_x64_ro, &fops_x64_wo); } EXPORT_SYMBOL_GPL(debugfs_create_x64); @@ -375,6 +400,8 @@ static int debugfs_size_t_get(void *data, u64 *val) } DEFINE_SIMPLE_ATTRIBUTE(fops_size_t, debugfs_size_t_get, debugfs_size_t_set, "%llu\n"); /* %llu and %zu are more or less the same */ +DEFINE_SIMPLE_ATTRIBUTE(fops_size_t_ro, debugfs_size_t_get, NULL, "%llu\n"); +DEFINE_SIMPLE_ATTRIBUTE(fops_size_t_wo, NULL, debugfs_size_t_set, "%llu\n"); /** * debugfs_create_size_t - create a debugfs file that is used to read and write an size_t value @@ -389,7 +416,8 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_size_t, debugfs_size_t_get, debugfs_size_t_set, struct dentry *debugfs_create_size_t(const char *name, umode_t mode, struct dentry *parent, size_t *value) { - return debugfs_create_file(name, mode, parent, value, &fops_size_t); + return debugfs_create_mode(name, mode, parent, value, &fops_size_t, + &fops_size_t_ro, &fops_size_t_wo); } EXPORT_SYMBOL_GPL(debugfs_create_size_t); @@ -422,16 +450,8 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_atomic_t_wo, NULL, debugfs_atomic_t_set, "%lld\n"); struct dentry *debugfs_create_atomic_t(const char *name, umode_t mode, struct dentry *parent, atomic_t *value) { - /* if there are no write bits set, make read only */ - if (!(mode & S_IWUGO)) - return debugfs_create_file(name, mode, parent, value, - &fops_atomic_t_ro); - /* if there are no read bits set, make write only */ - if (!(mode & S_IRUGO)) - return debugfs_create_file(name, mode, parent, value, - &fops_atomic_t_wo); - - return debugfs_create_file(name, mode, parent, value, &fops_atomic_t); + return debugfs_create_mode(name, mode, parent, value, &fops_atomic_t, + &fops_atomic_t_ro, &fops_atomic_t_wo); } EXPORT_SYMBOL_GPL(debugfs_create_atomic_t); @@ -439,7 +459,7 @@ ssize_t debugfs_read_file_bool(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { char buf[3]; - u32 *val = file->private_data; + bool *val = file->private_data; if (*val) buf[0] = 'Y'; @@ -457,7 +477,7 @@ ssize_t debugfs_write_file_bool(struct file *file, const char __user *user_buf, char buf[32]; size_t buf_size; bool bv; - u32 *val = file->private_data; + bool *val = file->private_data; buf_size = min(count, (sizeof(buf)-1)); if (copy_from_user(buf, user_buf, buf_size)) @@ -478,6 +498,18 @@ static const struct file_operations fops_bool = { .llseek = default_llseek, }; +static const struct file_operations fops_bool_ro = { + .read = debugfs_read_file_bool, + .open = simple_open, + .llseek = default_llseek, +}; + +static const struct file_operations fops_bool_wo = { + .write = debugfs_write_file_bool, + .open = simple_open, + .llseek = default_llseek, +}; + /** * debugfs_create_bool - create a debugfs file that is used to read and write a boolean value * @name: a pointer to a string containing the name of the file to create. @@ -503,9 +535,10 @@ static const struct file_operations fops_bool = { * code. */ struct dentry *debugfs_create_bool(const char *name, umode_t mode, - struct dentry *parent, u32 *value) + struct dentry *parent, bool *value) { - return debugfs_create_file(name, mode, parent, value, &fops_bool); + return debugfs_create_mode(name, mode, parent, value, &fops_bool, + &fops_bool_ro, &fops_bool_wo); } EXPORT_SYMBOL_GPL(debugfs_create_bool); diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index c711be8..b7fcc0d 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -271,8 +271,12 @@ static struct dentry *start_creating(const char *name, struct dentry *parent) dput(dentry); dentry = ERR_PTR(-EEXIST); } - if (IS_ERR(dentry)) + + if (IS_ERR(dentry)) { mutex_unlock(&d_inode(parent)->i_mutex); + simple_release_fs(&debugfs_mount, &debugfs_mount_count); + } + return dentry; } @@ -533,7 +537,8 @@ static int __debugfs_remove(struct dentry *dentry, struct dentry *parent) /** * debugfs_remove - removes a file or directory from the debugfs filesystem * @dentry: a pointer to a the dentry of the file or directory to be - * removed. + * removed. If this parameter is NULL or an error value, nothing + * will be done. * * This function removes a file or directory in debugfs that was previously * created with a call to another debugfs function (like @@ -565,7 +570,8 @@ EXPORT_SYMBOL_GPL(debugfs_remove); /** * debugfs_remove_recursive - recursively removes a directory - * @dentry: a pointer to a the dentry of the directory to be removed. + * @dentry: a pointer to a the dentry of the directory to be removed. If this + * parameter is NULL or an error value, nothing will be done. * * This function recursively removes a directory tree in debugfs that * was previously created with a call to another debugfs function diff --git a/fs/direct-io.c b/fs/direct-io.c index 1125629..cb5337d 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -109,6 +109,8 @@ struct dio_submit { struct dio { int flags; /* doesn't change */ int rw; + blk_qc_t bio_cookie; + struct block_device *bio_bdev; struct inode *inode; loff_t i_size; /* i_size when submitted */ dio_iodone_t *end_io; /* IO completion function */ @@ -120,6 +122,7 @@ struct dio { int page_errors; /* errno from get_user_pages() */ int is_async; /* is IO async ? */ bool defer_completion; /* defer AIO completion to workqueue? */ + bool should_dirty; /* if pages should be dirtied */ int io_error; /* IO error in completion path */ unsigned long refcount; /* direct_io_worker() and bios */ struct bio *bio_list; /* singly linked via bi_private */ @@ -360,7 +363,7 @@ dio_bio_alloc(struct dio *dio, struct dio_submit *sdio, /* * bio_alloc() is guaranteed to return a bio when called with - * __GFP_WAIT and we request a valid number of vectors. + * __GFP_RECLAIM and we request a valid number of vectors. */ bio = bio_alloc(GFP_KERNEL, nr_vecs); @@ -393,14 +396,17 @@ static inline void dio_bio_submit(struct dio *dio, struct dio_submit *sdio) dio->refcount++; spin_unlock_irqrestore(&dio->bio_lock, flags); - if (dio->is_async && dio->rw == READ) + if (dio->is_async && dio->rw == READ && dio->should_dirty) bio_set_pages_dirty(bio); - if (sdio->submit_io) + dio->bio_bdev = bio->bi_bdev; + + if (sdio->submit_io) { sdio->submit_io(dio->rw, bio, dio->inode, sdio->logical_offset_in_bio); - else - submit_bio(dio->rw, bio); + dio->bio_cookie = BLK_QC_T_NONE; + } else + dio->bio_cookie = submit_bio(dio->rw, bio); sdio->bio = NULL; sdio->boundary = 0; @@ -439,7 +445,8 @@ static struct bio *dio_await_one(struct dio *dio) __set_current_state(TASK_UNINTERRUPTIBLE); dio->waiter = current; spin_unlock_irqrestore(&dio->bio_lock, flags); - io_schedule(); + if (!blk_poll(bdev_get_queue(dio->bio_bdev), dio->bio_cookie)) + io_schedule(); /* wake up sets us TASK_RUNNING */ spin_lock_irqsave(&dio->bio_lock, flags); dio->waiter = NULL; @@ -464,14 +471,15 @@ static int dio_bio_complete(struct dio *dio, struct bio *bio) if (bio->bi_error) dio->io_error = -EIO; - if (dio->is_async && dio->rw == READ) { + if (dio->is_async && dio->rw == READ && dio->should_dirty) { bio_check_pages_dirty(bio); /* transfers ownership */ err = bio->bi_error; } else { bio_for_each_segment_all(bvec, bio, i) { struct page *page = bvec->bv_page; - if (dio->rw == READ && !PageCompound(page)) + if (dio->rw == READ && !PageCompound(page) && + dio->should_dirty) set_page_dirty_lock(page); page_cache_release(page); } @@ -1219,6 +1227,7 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, spin_lock_init(&dio->bio_lock); dio->refcount = 1; + dio->should_dirty = (iter->type == ITER_IOVEC); sdio.iter = iter; sdio.final_block_in_request = (offset + iov_iter_count(iter)) >> blkbits; diff --git a/fs/dlm/plock.c b/fs/dlm/plock.c index 5532f09..d401425 100644 --- a/fs/dlm/plock.c +++ b/fs/dlm/plock.c @@ -145,7 +145,7 @@ int dlm_posix_lock(dlm_lockspace_t *lockspace, u64 number, struct file *file, send_op(op); if (xop->callback == NULL) { - rv = wait_event_killable(recv_wq, (op->done != 0)); + rv = wait_event_interruptible(recv_wq, (op->done != 0)); if (rv == -ERESTARTSYS) { log_debug(ls, "dlm_posix_lock: wait killed %llx", (unsigned long long)number); @@ -172,7 +172,7 @@ int dlm_posix_lock(dlm_lockspace_t *lockspace, u64 number, struct file *file, rv = op->info.rv; if (!rv) { - if (posix_lock_file_wait(file, fl) < 0) + if (locks_lock_file_wait(file, fl) < 0) log_error(ls, "dlm_posix_lock: vfs lock error %llx", (unsigned long long)number); } @@ -262,7 +262,7 @@ int dlm_posix_unlock(dlm_lockspace_t *lockspace, u64 number, struct file *file, /* cause the vfs unlock to return ENOENT if lock is not found */ fl->fl_flags |= FL_EXISTS; - rv = posix_lock_file_wait(file, fl); + rv = locks_lock_file_wait(file, fl); if (rv == -ENOENT) { rv = 0; goto out_free; diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h index 5ba029e..7b39260 100644 --- a/fs/ecryptfs/ecryptfs_kernel.h +++ b/fs/ecryptfs/ecryptfs_kernel.h @@ -86,7 +86,7 @@ ecryptfs_get_encrypted_key_payload_data(struct key *key) { if (key->type == &key_type_encrypted) return (struct ecryptfs_auth_tok *) - (&((struct encrypted_key_payload *)key->payload.data)->payload_data); + (&((struct encrypted_key_payload *)key->payload.data[0])->payload_data); else return NULL; } @@ -117,8 +117,7 @@ ecryptfs_get_key_payload_data(struct key *key) auth_tok = ecryptfs_get_encrypted_key_payload_data(key); if (!auth_tok) - return (struct ecryptfs_auth_tok *) - (((struct user_key_payload *)key->payload.data)->data); + return (struct ecryptfs_auth_tok *)user_key_payload(key)->data; else return auth_tok; } diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index 3c4db11..e2e47ba 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -270,7 +270,7 @@ ecryptfs_create(struct inode *directory_inode, struct dentry *ecryptfs_dentry, ecryptfs_inode = ecryptfs_do_create(directory_inode, ecryptfs_dentry, mode); - if (unlikely(IS_ERR(ecryptfs_inode))) { + if (IS_ERR(ecryptfs_inode)) { ecryptfs_printk(KERN_WARNING, "Failed to create file in" "lower filesystem\n"); rc = PTR_ERR(ecryptfs_inode); diff --git a/fs/exofs/namei.c b/fs/exofs/namei.c index 09a6bb1..994e078 100644 --- a/fs/exofs/namei.c +++ b/fs/exofs/namei.c @@ -80,9 +80,6 @@ static int exofs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, struct inode *inode; int err; - if (!new_valid_dev(rdev)) - return -EINVAL; - inode = exofs_new_inode(dir, mode); err = PTR_ERR(inode); if (!IS_ERR(inode)) { diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h index 8d15feb..4c69c94 100644 --- a/fs/ext2/ext2.h +++ b/fs/ext2/ext2.h @@ -684,6 +684,9 @@ struct ext2_inode_info { struct rw_semaphore xattr_sem; #endif rwlock_t i_meta_lock; +#ifdef CONFIG_FS_DAX + struct rw_semaphore dax_sem; +#endif /* * truncate_mutex is for serialising ext2_truncate() against @@ -699,6 +702,14 @@ struct ext2_inode_info { #endif }; +#ifdef CONFIG_FS_DAX +#define dax_sem_down_write(ext2_inode) down_write(&(ext2_inode)->dax_sem) +#define dax_sem_up_write(ext2_inode) up_write(&(ext2_inode)->dax_sem) +#else +#define dax_sem_down_write(ext2_inode) +#define dax_sem_up_write(ext2_inode) +#endif + /* * Inode dynamic state flags */ diff --git a/fs/ext2/file.c b/fs/ext2/file.c index 1982c3f..11a42c5 100644 --- a/fs/ext2/file.c +++ b/fs/ext2/file.c @@ -27,27 +27,103 @@ #include "acl.h" #ifdef CONFIG_FS_DAX +/* + * The lock ordering for ext2 DAX fault paths is: + * + * mmap_sem (MM) + * sb_start_pagefault (vfs, freeze) + * ext2_inode_info->dax_sem + * address_space->i_mmap_rwsem or page_lock (mutually exclusive in DAX) + * ext2_inode_info->truncate_mutex + * + * The default page_lock and i_size verification done by non-DAX fault paths + * is sufficient because ext2 doesn't support hole punching. + */ static int ext2_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf) { - return dax_fault(vma, vmf, ext2_get_block, NULL); + struct inode *inode = file_inode(vma->vm_file); + struct ext2_inode_info *ei = EXT2_I(inode); + int ret; + + if (vmf->flags & FAULT_FLAG_WRITE) { + sb_start_pagefault(inode->i_sb); + file_update_time(vma->vm_file); + } + down_read(&ei->dax_sem); + + ret = __dax_fault(vma, vmf, ext2_get_block, NULL); + + up_read(&ei->dax_sem); + if (vmf->flags & FAULT_FLAG_WRITE) + sb_end_pagefault(inode->i_sb); + return ret; } static int ext2_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, unsigned int flags) { - return dax_pmd_fault(vma, addr, pmd, flags, ext2_get_block, NULL); + struct inode *inode = file_inode(vma->vm_file); + struct ext2_inode_info *ei = EXT2_I(inode); + int ret; + + if (flags & FAULT_FLAG_WRITE) { + sb_start_pagefault(inode->i_sb); + file_update_time(vma->vm_file); + } + down_read(&ei->dax_sem); + + ret = __dax_pmd_fault(vma, addr, pmd, flags, ext2_get_block, NULL); + + up_read(&ei->dax_sem); + if (flags & FAULT_FLAG_WRITE) + sb_end_pagefault(inode->i_sb); + return ret; } static int ext2_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) { - return dax_mkwrite(vma, vmf, ext2_get_block, NULL); + struct inode *inode = file_inode(vma->vm_file); + struct ext2_inode_info *ei = EXT2_I(inode); + int ret; + + sb_start_pagefault(inode->i_sb); + file_update_time(vma->vm_file); + down_read(&ei->dax_sem); + + ret = __dax_mkwrite(vma, vmf, ext2_get_block, NULL); + + up_read(&ei->dax_sem); + sb_end_pagefault(inode->i_sb); + return ret; +} + +static int ext2_dax_pfn_mkwrite(struct vm_area_struct *vma, + struct vm_fault *vmf) +{ + struct inode *inode = file_inode(vma->vm_file); + struct ext2_inode_info *ei = EXT2_I(inode); + int ret = VM_FAULT_NOPAGE; + loff_t size; + + sb_start_pagefault(inode->i_sb); + file_update_time(vma->vm_file); + down_read(&ei->dax_sem); + + /* check that the faulting page hasn't raced with truncate */ + size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT; + if (vmf->pgoff >= size) + ret = VM_FAULT_SIGBUS; + + up_read(&ei->dax_sem); + sb_end_pagefault(inode->i_sb); + return ret; } static const struct vm_operations_struct ext2_dax_vm_ops = { .fault = ext2_dax_fault, .pmd_fault = ext2_dax_pmd_fault, .page_mkwrite = ext2_dax_mkwrite, - .pfn_mkwrite = dax_pfn_mkwrite, + .pfn_mkwrite = ext2_dax_pfn_mkwrite, }; static int ext2_file_mmap(struct file *file, struct vm_area_struct *vma) diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index c60a248..0aa9bf6 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -1085,6 +1085,7 @@ static void ext2_free_branches(struct inode *inode, __le32 *p, __le32 *q, int de ext2_free_data(inode, p, q); } +/* dax_sem must be held when calling this function */ static void __ext2_truncate_blocks(struct inode *inode, loff_t offset) { __le32 *i_data = EXT2_I(inode)->i_data; @@ -1100,6 +1101,10 @@ static void __ext2_truncate_blocks(struct inode *inode, loff_t offset) blocksize = inode->i_sb->s_blocksize; iblock = (offset + blocksize-1) >> EXT2_BLOCK_SIZE_BITS(inode->i_sb); +#ifdef CONFIG_FS_DAX + WARN_ON(!rwsem_is_locked(&ei->dax_sem)); +#endif + n = ext2_block_to_path(inode, iblock, offsets, NULL); if (n == 0) return; @@ -1185,7 +1190,10 @@ static void ext2_truncate_blocks(struct inode *inode, loff_t offset) return; if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) return; + + dax_sem_down_write(EXT2_I(inode)); __ext2_truncate_blocks(inode, offset); + dax_sem_up_write(EXT2_I(inode)); } static int ext2_setsize(struct inode *inode, loff_t newsize) @@ -1213,8 +1221,10 @@ static int ext2_setsize(struct inode *inode, loff_t newsize) if (error) return error; + dax_sem_down_write(EXT2_I(inode)); truncate_setsize(inode, newsize); __ext2_truncate_blocks(inode, newsize); + dax_sem_up_write(EXT2_I(inode)); inode->i_mtime = inode->i_ctime = CURRENT_TIME_SEC; if (inode_needs_sync(inode)) { diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c index b4841e3..3267a80 100644 --- a/fs/ext2/namei.c +++ b/fs/ext2/namei.c @@ -143,9 +143,6 @@ static int ext2_mknod (struct inode * dir, struct dentry *dentry, umode_t mode, struct inode * inode; int err; - if (!new_valid_dev(rdev)) - return -EINVAL; - err = dquot_initialize(dir); if (err) return err; diff --git a/fs/ext2/super.c b/fs/ext2/super.c index 900e19c..3a71cea 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -192,6 +192,9 @@ static void init_once(void *foo) init_rwsem(&ei->xattr_sem); #endif mutex_init(&ei->truncate_mutex); +#ifdef CONFIG_FS_DAX + init_rwsem(&ei->dax_sem); +#endif inode_init_once(&ei->vfs_inode); } diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig index 47728da..b46e9fc 100644 --- a/fs/ext4/Kconfig +++ b/fs/ext4/Kconfig @@ -63,7 +63,7 @@ config EXT4_FS If unsure, say N. config EXT4_USE_FOR_EXT2 - bool "Use ext4 for ext2/ext3 file systems" + bool "Use ext4 for ext2 file systems" depends on EXT4_FS depends on EXT2_FS=n default y diff --git a/fs/ext4/Makefile b/fs/ext4/Makefile index 75285ea..f52cf54 100644 --- a/fs/ext4/Makefile +++ b/fs/ext4/Makefile @@ -8,7 +8,7 @@ ext4-y := balloc.o bitmap.o dir.o file.o fsync.o ialloc.o inode.o page-io.o \ ioctl.o namei.o super.o symlink.o hash.o resize.o extents.o \ ext4_jbd2.o migrate.o mballoc.o block_validity.o move_extent.o \ mmp.o indirect.o extents_status.o xattr.o xattr_user.o \ - xattr_trusted.o inline.o readpage.o + xattr_trusted.o inline.o readpage.o sysfs.o ext4-$(CONFIG_EXT4_FS_POSIX_ACL) += acl.o ext4-$(CONFIG_EXT4_FS_SECURITY) += xattr_security.o diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index cd6ea29..ec0668a 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -191,6 +191,7 @@ static int ext4_init_block_bitmap(struct super_block *sb, /* If checksum is bad mark all blocks used to prevent allocation * essentially implementing a per-group read-only flag. */ if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) { + ext4_error(sb, "Checksum bad for group %u", block_group); grp = ext4_get_group_info(sb, block_group); if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp)) percpu_counter_sub(&sbi->s_freeclusters_counter, @@ -203,7 +204,7 @@ static int ext4_init_block_bitmap(struct super_block *sb, count); } set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &grp->bb_state); - return -EIO; + return -EFSBADCRC; } memset(bh->b_data, 0, sb->s_blocksize); @@ -213,7 +214,7 @@ static int ext4_init_block_bitmap(struct super_block *sb, start = ext4_group_first_block_no(sb, block_group); - if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) + if (ext4_has_feature_flex_bg(sb)) flex_bg = 1; /* Set bits for block and inode bitmaps, and inode table */ @@ -322,7 +323,7 @@ static ext4_fsblk_t ext4_valid_block_bitmap(struct super_block *sb, ext4_fsblk_t blk; ext4_fsblk_t group_first_block; - if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) { + if (ext4_has_feature_flex_bg(sb)) { /* with FLEX_BG, the inode/block bitmaps and itable * blocks may not be in the group at all * so the bitmap validation will be skipped for those groups @@ -360,42 +361,45 @@ static ext4_fsblk_t ext4_valid_block_bitmap(struct super_block *sb, return 0; } -static void ext4_validate_block_bitmap(struct super_block *sb, - struct ext4_group_desc *desc, - ext4_group_t block_group, - struct buffer_head *bh) +static int ext4_validate_block_bitmap(struct super_block *sb, + struct ext4_group_desc *desc, + ext4_group_t block_group, + struct buffer_head *bh) { ext4_fsblk_t blk; struct ext4_group_info *grp = ext4_get_group_info(sb, block_group); struct ext4_sb_info *sbi = EXT4_SB(sb); - if (buffer_verified(bh) || EXT4_MB_GRP_BBITMAP_CORRUPT(grp)) - return; + if (buffer_verified(bh)) + return 0; + if (EXT4_MB_GRP_BBITMAP_CORRUPT(grp)) + return -EFSCORRUPTED; ext4_lock_group(sb, block_group); - blk = ext4_valid_block_bitmap(sb, desc, block_group, bh); - if (unlikely(blk != 0)) { + if (unlikely(!ext4_block_bitmap_csum_verify(sb, block_group, + desc, bh))) { ext4_unlock_group(sb, block_group); - ext4_error(sb, "bg %u: block %llu: invalid block bitmap", - block_group, blk); + ext4_error(sb, "bg %u: bad block bitmap checksum", block_group); if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp)) percpu_counter_sub(&sbi->s_freeclusters_counter, grp->bb_free); set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state); - return; + return -EFSBADCRC; } - if (unlikely(!ext4_block_bitmap_csum_verify(sb, block_group, - desc, bh))) { + blk = ext4_valid_block_bitmap(sb, desc, block_group, bh); + if (unlikely(blk != 0)) { ext4_unlock_group(sb, block_group); - ext4_error(sb, "bg %u: bad block bitmap checksum", block_group); + ext4_error(sb, "bg %u: block %llu: invalid block bitmap", + block_group, blk); if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp)) percpu_counter_sub(&sbi->s_freeclusters_counter, grp->bb_free); set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state); - return; + return -EFSCORRUPTED; } set_buffer_verified(bh); ext4_unlock_group(sb, block_group); + return 0; } /** @@ -414,17 +418,18 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group) struct ext4_group_desc *desc; struct buffer_head *bh; ext4_fsblk_t bitmap_blk; + int err; desc = ext4_get_group_desc(sb, block_group, NULL); if (!desc) - return NULL; + return ERR_PTR(-EFSCORRUPTED); bitmap_blk = ext4_block_bitmap(sb, desc); bh = sb_getblk(sb, bitmap_blk); if (unlikely(!bh)) { ext4_error(sb, "Cannot get buffer for block bitmap - " "block_group = %u, block_bitmap = %llu", block_group, bitmap_blk); - return NULL; + return ERR_PTR(-ENOMEM); } if (bitmap_uptodate(bh)) @@ -437,7 +442,6 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group) } ext4_lock_group(sb, block_group); if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) { - int err; err = ext4_init_block_bitmap(sb, bh, block_group, desc); set_bitmap_uptodate(bh); @@ -445,7 +449,7 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group) ext4_unlock_group(sb, block_group); unlock_buffer(bh); if (err) - ext4_error(sb, "Checksum bad for grp %u", block_group); + goto out; goto verify; } ext4_unlock_group(sb, block_group); @@ -468,11 +472,13 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group) submit_bh(READ | REQ_META | REQ_PRIO, bh); return bh; verify: - ext4_validate_block_bitmap(sb, desc, block_group, bh); - if (buffer_verified(bh)) - return bh; + err = ext4_validate_block_bitmap(sb, desc, block_group, bh); + if (err) + goto out; + return bh; +out: put_bh(bh); - return NULL; + return ERR_PTR(err); } /* Returns 0 on success, 1 on error */ @@ -485,32 +491,32 @@ int ext4_wait_block_bitmap(struct super_block *sb, ext4_group_t block_group, return 0; desc = ext4_get_group_desc(sb, block_group, NULL); if (!desc) - return 1; + return -EFSCORRUPTED; wait_on_buffer(bh); if (!buffer_uptodate(bh)) { ext4_error(sb, "Cannot read block bitmap - " "block_group = %u, block_bitmap = %llu", block_group, (unsigned long long) bh->b_blocknr); - return 1; + return -EIO; } clear_buffer_new(bh); /* Panic or remount fs read-only if block bitmap is invalid */ - ext4_validate_block_bitmap(sb, desc, block_group, bh); - /* ...but check for error just in case errors=continue. */ - return !buffer_verified(bh); + return ext4_validate_block_bitmap(sb, desc, block_group, bh); } struct buffer_head * ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group) { struct buffer_head *bh; + int err; bh = ext4_read_block_bitmap_nowait(sb, block_group); - if (!bh) - return NULL; - if (ext4_wait_block_bitmap(sb, block_group, bh)) { + if (IS_ERR(bh)) + return bh; + err = ext4_wait_block_bitmap(sb, block_group, bh); + if (err) { put_bh(bh); - return NULL; + return ERR_PTR(err); } return bh; } @@ -681,8 +687,10 @@ ext4_fsblk_t ext4_count_free_clusters(struct super_block *sb) desc_count += ext4_free_group_clusters(sb, gdp); brelse(bitmap_bh); bitmap_bh = ext4_read_block_bitmap(sb, i); - if (bitmap_bh == NULL) + if (IS_ERR(bitmap_bh)) { + bitmap_bh = NULL; continue; + } x = ext4_count_free(bitmap_bh->b_data, EXT4_CLUSTERS_PER_GROUP(sb) / 8); @@ -740,14 +748,13 @@ int ext4_bg_has_super(struct super_block *sb, ext4_group_t group) if (group == 0) return 1; - if (EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_SPARSE_SUPER2)) { + if (ext4_has_feature_sparse_super2(sb)) { if (group == le32_to_cpu(es->s_backup_bgs[0]) || group == le32_to_cpu(es->s_backup_bgs[1])) return 1; return 0; } - if ((group <= 1) || !EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER)) + if ((group <= 1) || !ext4_has_feature_sparse_super(sb)) return 1; if (!(group & 1)) return 0; @@ -776,7 +783,7 @@ static unsigned long ext4_bg_num_gdb_nometa(struct super_block *sb, if (!ext4_bg_has_super(sb, group)) return 0; - if (EXT4_HAS_INCOMPAT_FEATURE(sb,EXT4_FEATURE_INCOMPAT_META_BG)) + if (ext4_has_feature_meta_bg(sb)) return le32_to_cpu(EXT4_SB(sb)->s_es->s_first_meta_bg); else return EXT4_SB(sb)->s_gdb_count; @@ -797,8 +804,7 @@ unsigned long ext4_bg_num_gdb(struct super_block *sb, ext4_group_t group) le32_to_cpu(EXT4_SB(sb)->s_es->s_first_meta_bg); unsigned long metagroup = group / EXT4_DESC_PER_BLOCK(sb); - if (!EXT4_HAS_INCOMPAT_FEATURE(sb,EXT4_FEATURE_INCOMPAT_META_BG) || - metagroup < first_meta_bg) + if (!ext4_has_feature_meta_bg(sb) || metagroup < first_meta_bg) return ext4_bg_num_gdb_nometa(sb, group); return ext4_bg_num_gdb_meta(sb,group); @@ -818,7 +824,7 @@ static unsigned ext4_num_base_meta_clusters(struct super_block *sb, /* Check for superblock and gdt backups in this group */ num = ext4_bg_has_super(sb, block_group); - if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_META_BG) || + if (!ext4_has_feature_meta_bg(sb) || block_group < le32_to_cpu(sbi->s_es->s_first_meta_bg) * sbi->s_desc_per_block) { if (num) { diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c index 3522340..02ddec6 100644 --- a/fs/ext4/block_validity.c +++ b/fs/ext4/block_validity.c @@ -234,7 +234,7 @@ int ext4_check_blockref(const char *function, unsigned int line, es->s_last_error_block = cpu_to_le64(blk); ext4_error_inode(inode, function, line, blk, "invalid block"); - return -EIO; + return -EFSCORRUPTED; } } return 0; diff --git a/fs/ext4/crypto.c b/fs/ext4/crypto.c index 4573155..af06830 100644 --- a/fs/ext4/crypto.c +++ b/fs/ext4/crypto.c @@ -253,8 +253,7 @@ typedef enum { EXT4_ENCRYPT, } ext4_direction_t; -static int ext4_page_crypto(struct ext4_crypto_ctx *ctx, - struct inode *inode, +static int ext4_page_crypto(struct inode *inode, ext4_direction_t rw, pgoff_t index, struct page *src_page, @@ -296,7 +295,6 @@ static int ext4_page_crypto(struct ext4_crypto_ctx *ctx, else res = crypto_ablkcipher_encrypt(req); if (res == -EINPROGRESS || res == -EBUSY) { - BUG_ON(req->base.data != &ecr); wait_for_completion(&ecr.completion); res = ecr.res; } @@ -353,7 +351,7 @@ struct page *ext4_encrypt(struct inode *inode, if (IS_ERR(ciphertext_page)) goto errout; ctx->w.control_page = plaintext_page; - err = ext4_page_crypto(ctx, inode, EXT4_ENCRYPT, plaintext_page->index, + err = ext4_page_crypto(inode, EXT4_ENCRYPT, plaintext_page->index, plaintext_page, ciphertext_page); if (err) { ciphertext_page = ERR_PTR(err); @@ -378,31 +376,14 @@ struct page *ext4_encrypt(struct inode *inode, * * Return: Zero on success, non-zero otherwise. */ -int ext4_decrypt(struct ext4_crypto_ctx *ctx, struct page *page) +int ext4_decrypt(struct page *page) { BUG_ON(!PageLocked(page)); - return ext4_page_crypto(ctx, page->mapping->host, + return ext4_page_crypto(page->mapping->host, EXT4_DECRYPT, page->index, page, page); } -/* - * Convenience function which takes care of allocating and - * deallocating the encryption context - */ -int ext4_decrypt_one(struct inode *inode, struct page *page) -{ - int ret; - - struct ext4_crypto_ctx *ctx = ext4_get_crypto_ctx(inode); - - if (IS_ERR(ctx)) - return PTR_ERR(ctx); - ret = ext4_decrypt(ctx, page); - ext4_release_crypto_ctx(ctx); - return ret; -} - int ext4_encrypted_zeroout(struct inode *inode, struct ext4_extent *ex) { struct ext4_crypto_ctx *ctx; @@ -411,7 +392,13 @@ int ext4_encrypted_zeroout(struct inode *inode, struct ext4_extent *ex) ext4_lblk_t lblk = ex->ee_block; ext4_fsblk_t pblk = ext4_ext_pblock(ex); unsigned int len = ext4_ext_get_actual_len(ex); - int err = 0; + int ret, err = 0; + +#if 0 + ext4_msg(inode->i_sb, KERN_CRIT, + "ext4_encrypted_zeroout ino %lu lblk %u len %u", + (unsigned long) inode->i_ino, lblk, len); +#endif BUG_ON(inode->i_sb->s_blocksize != PAGE_CACHE_SIZE); @@ -426,7 +413,7 @@ int ext4_encrypted_zeroout(struct inode *inode, struct ext4_extent *ex) } while (len--) { - err = ext4_page_crypto(ctx, inode, EXT4_ENCRYPT, lblk, + err = ext4_page_crypto(inode, EXT4_ENCRYPT, lblk, ZERO_PAGE(0), ciphertext_page); if (err) goto errout; @@ -437,17 +424,26 @@ int ext4_encrypted_zeroout(struct inode *inode, struct ext4_extent *ex) goto errout; } bio->bi_bdev = inode->i_sb->s_bdev; - bio->bi_iter.bi_sector = pblk; - err = bio_add_page(bio, ciphertext_page, + bio->bi_iter.bi_sector = + pblk << (inode->i_sb->s_blocksize_bits - 9); + ret = bio_add_page(bio, ciphertext_page, inode->i_sb->s_blocksize, 0); - if (err) { + if (ret != inode->i_sb->s_blocksize) { + /* should never happen! */ + ext4_msg(inode->i_sb, KERN_ERR, + "bio_add_page failed: %d", ret); + WARN_ON(1); bio_put(bio); + err = -EIO; goto errout; } err = submit_bio_wait(WRITE, bio); + if ((err == 0) && bio->bi_error) + err = -EIO; bio_put(bio); if (err) goto errout; + lblk++; pblk++; } err = 0; errout: diff --git a/fs/ext4/crypto_fname.c b/fs/ext4/crypto_fname.c index 847f919..2fbef8a 100644 --- a/fs/ext4/crypto_fname.c +++ b/fs/ext4/crypto_fname.c @@ -120,7 +120,6 @@ static int ext4_fname_encrypt(struct inode *inode, ablkcipher_request_set_crypt(req, &src_sg, &dst_sg, ciphertext_len, iv); res = crypto_ablkcipher_encrypt(req); if (res == -EINPROGRESS || res == -EBUSY) { - BUG_ON(req->base.data != &ecr); wait_for_completion(&ecr.completion); res = ecr.res; } @@ -182,7 +181,6 @@ static int ext4_fname_decrypt(struct inode *inode, ablkcipher_request_set_crypt(req, &src_sg, &dst_sg, iname->len, iv); res = crypto_ablkcipher_decrypt(req); if (res == -EINPROGRESS || res == -EBUSY) { - BUG_ON(req->base.data != &ecr); wait_for_completion(&ecr.completion); res = ecr.res; } diff --git a/fs/ext4/crypto_key.c b/fs/ext4/crypto_key.c index 1d510c1..c5882b3 100644 --- a/fs/ext4/crypto_key.c +++ b/fs/ext4/crypto_key.c @@ -71,7 +71,6 @@ static int ext4_derive_key_aes(char deriving_key[EXT4_AES_128_ECB_KEY_SIZE], EXT4_AES_256_XTS_KEY_SIZE, NULL); res = crypto_ablkcipher_encrypt(req); if (res == -EINPROGRESS || res == -EBUSY) { - BUG_ON(req->base.data != &ecr); wait_for_completion(&ecr.completion); res = ecr.res; } @@ -121,7 +120,7 @@ int _ext4_get_encryption_info(struct inode *inode) struct key *keyring_key = NULL; struct ext4_encryption_key *master_key; struct ext4_encryption_context ctx; - struct user_key_payload *ukp; + const struct user_key_payload *ukp; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct crypto_ablkcipher *ctfm; const char *cipher_str; @@ -208,8 +207,13 @@ retry: goto out; } crypt_info->ci_keyring_key = keyring_key; - BUG_ON(keyring_key->type != &key_type_logon); - ukp = ((struct user_key_payload *)keyring_key->payload.data); + if (keyring_key->type != &key_type_logon) { + printk_once(KERN_WARNING + "ext4: key type must be logon\n"); + res = -ENOKEY; + goto out; + } + ukp = user_key_payload(keyring_key); if (ukp->datalen != sizeof(struct ext4_encryption_key)) { res = -EINVAL; goto out; @@ -217,7 +221,13 @@ retry: master_key = (struct ext4_encryption_key *)ukp->data; BUILD_BUG_ON(EXT4_AES_128_ECB_KEY_SIZE != EXT4_KEY_DERIVATION_NONCE_SIZE); - BUG_ON(master_key->size != EXT4_AES_256_XTS_KEY_SIZE); + if (master_key->size != EXT4_AES_256_XTS_KEY_SIZE) { + printk_once(KERN_WARNING + "ext4: key size incorrect: %d\n", + master_key->size); + res = -ENOKEY; + goto out; + } res = ext4_derive_key_aes(ctx.nonce, master_key->raw, raw_key); if (res) diff --git a/fs/ext4/crypto_policy.c b/fs/ext4/crypto_policy.c index a640ec2..ad05069 100644 --- a/fs/ext4/crypto_policy.c +++ b/fs/ext4/crypto_policy.c @@ -150,7 +150,8 @@ int ext4_is_child_context_consistent_with_parent(struct inode *parent, if ((parent == NULL) || (child == NULL)) { pr_err("parent %p child %p\n", parent, child); - BUG_ON(1); + WARN_ON(1); /* Should never happen */ + return 0; } /* no restrictions if the parent directory is not encrypted */ if (!ext4_encrypted_inode(parent)) diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index f9e1491..1d1bca7 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -40,8 +40,7 @@ static int is_dx_dir(struct inode *inode) { struct super_block *sb = inode->i_sb; - if (EXT4_HAS_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_COMPAT_DIR_INDEX) && + if (ext4_has_feature_dir_index(inode->i_sb) && ((ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) || ((inode->i_size >> sb->s_blocksize_bits) == 1) || ext4_has_inline_data(inode))) @@ -621,14 +620,14 @@ int ext4_check_all_de(struct inode *dir, struct buffer_head *bh, void *buf, while ((char *) de < top) { if (ext4_check_dir_entry(dir, NULL, de, bh, buf, buf_size, offset)) - return -EIO; + return -EFSCORRUPTED; nlen = EXT4_DIR_REC_LEN(de->name_len); rlen = ext4_rec_len_from_disk(de->rec_len, buf_size); de = (struct ext4_dir_entry_2 *)((char *)de + rlen); offset += rlen; } if ((char *) de > top) - return -EIO; + return -EFSCORRUPTED; return 0; } diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index fd1f28b..750063f 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -374,6 +374,7 @@ struct flex_groups { #define EXT4_EA_INODE_FL 0x00200000 /* Inode used for large EA */ #define EXT4_EOFBLOCKS_FL 0x00400000 /* Blocks allocated beyond EOF */ #define EXT4_INLINE_DATA_FL 0x10000000 /* Inode has inline data. */ +#define EXT4_PROJINHERIT_FL 0x20000000 /* Create with parents projid */ #define EXT4_RESERVED_FL 0x80000000 /* reserved for ext4 lib */ #define EXT4_FL_USER_VISIBLE 0x004BDFFF /* User visible flags */ @@ -431,6 +432,7 @@ enum { EXT4_INODE_EA_INODE = 21, /* Inode used for large EA */ EXT4_INODE_EOFBLOCKS = 22, /* Blocks allocated beyond EOF */ EXT4_INODE_INLINE_DATA = 28, /* Data in inode. */ + EXT4_INODE_PROJINHERIT = 29, /* Create with parents projid */ EXT4_INODE_RESERVED = 31, /* reserved for ext4 lib */ }; @@ -475,6 +477,7 @@ static inline void ext4_check_flag_values(void) CHECK_FLAG_VALUE(EA_INODE); CHECK_FLAG_VALUE(EOFBLOCKS); CHECK_FLAG_VALUE(INLINE_DATA); + CHECK_FLAG_VALUE(PROJINHERIT); CHECK_FLAG_VALUE(RESERVED); } @@ -692,6 +695,7 @@ struct ext4_inode { __le32 i_crtime; /* File Creation time */ __le32 i_crtime_extra; /* extra FileCreationtime (nsec << 2 | epoch) */ __le32 i_version_hi; /* high 32 bits for 64-bit version */ + __le32 i_projid; /* Project ID */ }; struct move_extent { @@ -1019,6 +1023,9 @@ struct ext4_inode_info { #define EXT4_MOUNT2_HURD_COMPAT 0x00000004 /* Support HURD-castrated file systems */ +#define EXT4_MOUNT2_EXPLICIT_JOURNAL_CHECKSUM 0x00000008 /* User explicitly + specified journal checksum */ + #define clear_opt(sb, opt) EXT4_SB(sb)->s_mount_opt &= \ ~EXT4_MOUNT_##opt #define set_opt(sb, opt) EXT4_SB(sb)->s_mount_opt |= \ @@ -1179,7 +1186,9 @@ struct ext4_super_block { __u8 s_encrypt_algos[4]; /* Encryption algorithms in use */ __u8 s_encrypt_pw_salt[16]; /* Salt used for string2key algorithm */ __le32 s_lpf_ino; /* Location of the lost+found inode */ - __le32 s_reserved[100]; /* Padding to the end of the block */ + __le32 s_prj_quota_inum; /* inode for tracking project quota */ + __le32 s_checksum_seed; /* crc32c(uuid) if csum_seed set */ + __le32 s_reserved[98]; /* Padding to the end of the block */ __le32 s_checksum; /* crc32c(superblock) */ }; @@ -1522,6 +1531,7 @@ static inline int ext4_encrypted_inode(struct inode *inode) * Feature set definitions */ +/* Use the ext4_{has,set,clear}_feature_* helpers; these will be removed */ #define EXT4_HAS_COMPAT_FEATURE(sb,mask) \ ((EXT4_SB(sb)->s_es->s_feature_compat & cpu_to_le32(mask)) != 0) #define EXT4_HAS_RO_COMPAT_FEATURE(sb,mask) \ @@ -1566,6 +1576,7 @@ static inline int ext4_encrypted_inode(struct inode *inode) */ #define EXT4_FEATURE_RO_COMPAT_METADATA_CSUM 0x0400 #define EXT4_FEATURE_RO_COMPAT_READONLY 0x1000 +#define EXT4_FEATURE_RO_COMPAT_PROJECT 0x2000 #define EXT4_FEATURE_INCOMPAT_COMPRESSION 0x0001 #define EXT4_FEATURE_INCOMPAT_FILETYPE 0x0002 @@ -1578,11 +1589,99 @@ static inline int ext4_encrypted_inode(struct inode *inode) #define EXT4_FEATURE_INCOMPAT_FLEX_BG 0x0200 #define EXT4_FEATURE_INCOMPAT_EA_INODE 0x0400 /* EA in inode */ #define EXT4_FEATURE_INCOMPAT_DIRDATA 0x1000 /* data in dirent */ -#define EXT4_FEATURE_INCOMPAT_BG_USE_META_CSUM 0x2000 /* use crc32c for bg */ +#define EXT4_FEATURE_INCOMPAT_CSUM_SEED 0x2000 #define EXT4_FEATURE_INCOMPAT_LARGEDIR 0x4000 /* >2GB or 3-lvl htree */ #define EXT4_FEATURE_INCOMPAT_INLINE_DATA 0x8000 /* data in inode */ #define EXT4_FEATURE_INCOMPAT_ENCRYPT 0x10000 +#define EXT4_FEATURE_COMPAT_FUNCS(name, flagname) \ +static inline bool ext4_has_feature_##name(struct super_block *sb) \ +{ \ + return ((EXT4_SB(sb)->s_es->s_feature_compat & \ + cpu_to_le32(EXT4_FEATURE_COMPAT_##flagname)) != 0); \ +} \ +static inline void ext4_set_feature_##name(struct super_block *sb) \ +{ \ + EXT4_SB(sb)->s_es->s_feature_compat |= \ + cpu_to_le32(EXT4_FEATURE_COMPAT_##flagname); \ +} \ +static inline void ext4_clear_feature_##name(struct super_block *sb) \ +{ \ + EXT4_SB(sb)->s_es->s_feature_compat &= \ + ~cpu_to_le32(EXT4_FEATURE_COMPAT_##flagname); \ +} + +#define EXT4_FEATURE_RO_COMPAT_FUNCS(name, flagname) \ +static inline bool ext4_has_feature_##name(struct super_block *sb) \ +{ \ + return ((EXT4_SB(sb)->s_es->s_feature_ro_compat & \ + cpu_to_le32(EXT4_FEATURE_RO_COMPAT_##flagname)) != 0); \ +} \ +static inline void ext4_set_feature_##name(struct super_block *sb) \ +{ \ + EXT4_SB(sb)->s_es->s_feature_ro_compat |= \ + cpu_to_le32(EXT4_FEATURE_RO_COMPAT_##flagname); \ +} \ +static inline void ext4_clear_feature_##name(struct super_block *sb) \ +{ \ + EXT4_SB(sb)->s_es->s_feature_ro_compat &= \ + ~cpu_to_le32(EXT4_FEATURE_RO_COMPAT_##flagname); \ +} + +#define EXT4_FEATURE_INCOMPAT_FUNCS(name, flagname) \ +static inline bool ext4_has_feature_##name(struct super_block *sb) \ +{ \ + return ((EXT4_SB(sb)->s_es->s_feature_incompat & \ + cpu_to_le32(EXT4_FEATURE_INCOMPAT_##flagname)) != 0); \ +} \ +static inline void ext4_set_feature_##name(struct super_block *sb) \ +{ \ + EXT4_SB(sb)->s_es->s_feature_incompat |= \ + cpu_to_le32(EXT4_FEATURE_INCOMPAT_##flagname); \ +} \ +static inline void ext4_clear_feature_##name(struct super_block *sb) \ +{ \ + EXT4_SB(sb)->s_es->s_feature_incompat &= \ + ~cpu_to_le32(EXT4_FEATURE_INCOMPAT_##flagname); \ +} + +EXT4_FEATURE_COMPAT_FUNCS(dir_prealloc, DIR_PREALLOC) +EXT4_FEATURE_COMPAT_FUNCS(imagic_inodes, IMAGIC_INODES) +EXT4_FEATURE_COMPAT_FUNCS(journal, HAS_JOURNAL) +EXT4_FEATURE_COMPAT_FUNCS(xattr, EXT_ATTR) +EXT4_FEATURE_COMPAT_FUNCS(resize_inode, RESIZE_INODE) +EXT4_FEATURE_COMPAT_FUNCS(dir_index, DIR_INDEX) +EXT4_FEATURE_COMPAT_FUNCS(sparse_super2, SPARSE_SUPER2) + +EXT4_FEATURE_RO_COMPAT_FUNCS(sparse_super, SPARSE_SUPER) +EXT4_FEATURE_RO_COMPAT_FUNCS(large_file, LARGE_FILE) +EXT4_FEATURE_RO_COMPAT_FUNCS(btree_dir, BTREE_DIR) +EXT4_FEATURE_RO_COMPAT_FUNCS(huge_file, HUGE_FILE) +EXT4_FEATURE_RO_COMPAT_FUNCS(gdt_csum, GDT_CSUM) +EXT4_FEATURE_RO_COMPAT_FUNCS(dir_nlink, DIR_NLINK) +EXT4_FEATURE_RO_COMPAT_FUNCS(extra_isize, EXTRA_ISIZE) +EXT4_FEATURE_RO_COMPAT_FUNCS(quota, QUOTA) +EXT4_FEATURE_RO_COMPAT_FUNCS(bigalloc, BIGALLOC) +EXT4_FEATURE_RO_COMPAT_FUNCS(metadata_csum, METADATA_CSUM) +EXT4_FEATURE_RO_COMPAT_FUNCS(readonly, READONLY) +EXT4_FEATURE_RO_COMPAT_FUNCS(project, PROJECT) + +EXT4_FEATURE_INCOMPAT_FUNCS(compression, COMPRESSION) +EXT4_FEATURE_INCOMPAT_FUNCS(filetype, FILETYPE) +EXT4_FEATURE_INCOMPAT_FUNCS(journal_needs_recovery, RECOVER) +EXT4_FEATURE_INCOMPAT_FUNCS(journal_dev, JOURNAL_DEV) +EXT4_FEATURE_INCOMPAT_FUNCS(meta_bg, META_BG) +EXT4_FEATURE_INCOMPAT_FUNCS(extents, EXTENTS) +EXT4_FEATURE_INCOMPAT_FUNCS(64bit, 64BIT) +EXT4_FEATURE_INCOMPAT_FUNCS(mmp, MMP) +EXT4_FEATURE_INCOMPAT_FUNCS(flex_bg, FLEX_BG) +EXT4_FEATURE_INCOMPAT_FUNCS(ea_inode, EA_INODE) +EXT4_FEATURE_INCOMPAT_FUNCS(dirdata, DIRDATA) +EXT4_FEATURE_INCOMPAT_FUNCS(csum_seed, CSUM_SEED) +EXT4_FEATURE_INCOMPAT_FUNCS(largedir, LARGEDIR) +EXT4_FEATURE_INCOMPAT_FUNCS(inline_data, INLINE_DATA) +EXT4_FEATURE_INCOMPAT_FUNCS(encrypt, ENCRYPT) + #define EXT2_FEATURE_COMPAT_SUPP EXT4_FEATURE_COMPAT_EXT_ATTR #define EXT2_FEATURE_INCOMPAT_SUPP (EXT4_FEATURE_INCOMPAT_FILETYPE| \ EXT4_FEATURE_INCOMPAT_META_BG) @@ -1598,7 +1697,7 @@ static inline int ext4_encrypted_inode(struct inode *inode) EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \ EXT4_FEATURE_RO_COMPAT_BTREE_DIR) -#define EXT4_FEATURE_COMPAT_SUPP EXT2_FEATURE_COMPAT_EXT_ATTR +#define EXT4_FEATURE_COMPAT_SUPP EXT4_FEATURE_COMPAT_EXT_ATTR #define EXT4_FEATURE_INCOMPAT_SUPP (EXT4_FEATURE_INCOMPAT_FILETYPE| \ EXT4_FEATURE_INCOMPAT_RECOVER| \ EXT4_FEATURE_INCOMPAT_META_BG| \ @@ -1607,7 +1706,8 @@ static inline int ext4_encrypted_inode(struct inode *inode) EXT4_FEATURE_INCOMPAT_FLEX_BG| \ EXT4_FEATURE_INCOMPAT_MMP | \ EXT4_FEATURE_INCOMPAT_INLINE_DATA | \ - EXT4_FEATURE_INCOMPAT_ENCRYPT) + EXT4_FEATURE_INCOMPAT_ENCRYPT | \ + EXT4_FEATURE_INCOMPAT_CSUM_SEED) #define EXT4_FEATURE_RO_COMPAT_SUPP (EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \ EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \ EXT4_FEATURE_RO_COMPAT_GDT_CSUM| \ @@ -1619,6 +1719,40 @@ static inline int ext4_encrypted_inode(struct inode *inode) EXT4_FEATURE_RO_COMPAT_METADATA_CSUM|\ EXT4_FEATURE_RO_COMPAT_QUOTA) +#define EXTN_FEATURE_FUNCS(ver) \ +static inline bool ext4_has_unknown_ext##ver##_compat_features(struct super_block *sb) \ +{ \ + return ((EXT4_SB(sb)->s_es->s_feature_compat & \ + cpu_to_le32(~EXT##ver##_FEATURE_COMPAT_SUPP)) != 0); \ +} \ +static inline bool ext4_has_unknown_ext##ver##_ro_compat_features(struct super_block *sb) \ +{ \ + return ((EXT4_SB(sb)->s_es->s_feature_ro_compat & \ + cpu_to_le32(~EXT##ver##_FEATURE_RO_COMPAT_SUPP)) != 0); \ +} \ +static inline bool ext4_has_unknown_ext##ver##_incompat_features(struct super_block *sb) \ +{ \ + return ((EXT4_SB(sb)->s_es->s_feature_incompat & \ + cpu_to_le32(~EXT##ver##_FEATURE_INCOMPAT_SUPP)) != 0); \ +} + +EXTN_FEATURE_FUNCS(2) +EXTN_FEATURE_FUNCS(3) +EXTN_FEATURE_FUNCS(4) + +static inline bool ext4_has_compat_features(struct super_block *sb) +{ + return (EXT4_SB(sb)->s_es->s_feature_compat != 0); +} +static inline bool ext4_has_ro_compat_features(struct super_block *sb) +{ + return (EXT4_SB(sb)->s_es->s_feature_ro_compat != 0); +} +static inline bool ext4_has_incompat_features(struct super_block *sb) +{ + return (EXT4_SB(sb)->s_es->s_feature_incompat != 0); +} + /* * Default values for user and/or group using reserved blocks */ @@ -1769,8 +1903,7 @@ static inline __le16 ext4_rec_len_to_disk(unsigned len, unsigned blocksize) * (c) Daniel Phillips, 2001 */ -#define is_dx(dir) (EXT4_HAS_COMPAT_FEATURE(dir->i_sb, \ - EXT4_FEATURE_COMPAT_DIR_INDEX) && \ +#define is_dx(dir) (ext4_has_feature_dir_index((dir)->i_sb) && \ ext4_test_inode_flag((dir), EXT4_INODE_INDEX)) #define EXT4_DIR_LINK_MAX(dir) (!is_dx(dir) && (dir)->i_nlink >= EXT4_LINK_MAX) #define EXT4_DIR_LINK_EMPTY(dir) ((dir)->i_nlink == 2 || (dir)->i_nlink == 1) @@ -2063,8 +2196,7 @@ void ext4_release_crypto_ctx(struct ext4_crypto_ctx *ctx); void ext4_restore_control_page(struct page *data_page); struct page *ext4_encrypt(struct inode *inode, struct page *plaintext_page); -int ext4_decrypt(struct ext4_crypto_ctx *ctx, struct page *page); -int ext4_decrypt_one(struct inode *inode, struct page *page); +int ext4_decrypt(struct page *page); int ext4_encrypted_zeroout(struct inode *inode, struct ext4_extent *ex); #ifdef CONFIG_EXT4_FS_ENCRYPTION @@ -2072,7 +2204,7 @@ int ext4_init_crypto(void); void ext4_exit_crypto(void); static inline int ext4_sb_has_crypto(struct super_block *sb) { - return EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_ENCRYPT); + return ext4_has_feature_encrypt(sb); } #else static inline int ext4_init_crypto(void) { return 0; } @@ -2193,8 +2325,7 @@ int ext4_insert_dentry(struct inode *dir, struct ext4_filename *fname); static inline void ext4_update_dx_flag(struct inode *inode) { - if (!EXT4_HAS_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_COMPAT_DIR_INDEX)) + if (!ext4_has_feature_dir_index(inode->i_sb)) ext4_clear_inode_flag(inode, EXT4_INODE_INDEX); } static unsigned char ext4_filetype_table[] = { @@ -2203,8 +2334,7 @@ static unsigned char ext4_filetype_table[] = { static inline unsigned char get_dtype(struct super_block *sb, int filetype) { - if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FILETYPE) || - (filetype >= EXT4_FT_MAX)) + if (!ext4_has_feature_filetype(sb) || filetype >= EXT4_FT_MAX) return DT_UNKNOWN; return ext4_filetype_table[filetype]; @@ -2245,6 +2375,7 @@ extern int ext4_init_inode_table(struct super_block *sb, extern void ext4_end_bitmap_read(struct buffer_head *bh, int uptodate); /* mballoc.c */ +extern const struct file_operations ext4_seq_mb_groups_fops; extern long ext4_mb_stats; extern long ext4_mb_max_to_scan; extern int ext4_mb_init(struct super_block *); @@ -2372,6 +2503,7 @@ extern int ext4_group_extend(struct super_block *sb, extern int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count); /* super.c */ +extern int ext4_seq_options_show(struct seq_file *seq, void *offset); extern int ext4_calculate_overhead(struct super_block *sb); extern void ext4_superblock_csum_set(struct super_block *sb); extern void *ext4_kvmalloc(size_t size, gfp_t flags); @@ -2534,15 +2666,13 @@ extern int ext4_register_li_request(struct super_block *sb, static inline int ext4_has_group_desc_csum(struct super_block *sb) { - return EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_GDT_CSUM) || - (EXT4_SB(sb)->s_chksum_driver != NULL); + return ext4_has_feature_gdt_csum(sb) || + EXT4_SB(sb)->s_chksum_driver != NULL; } static inline int ext4_has_metadata_csum(struct super_block *sb) { - WARN_ON_ONCE(EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM) && + WARN_ON_ONCE(ext4_has_feature_metadata_csum(sb) && !EXT4_SB(sb)->s_chksum_driver); return (EXT4_SB(sb)->s_chksum_driver != NULL); @@ -2889,7 +3019,7 @@ static unsigned char ext4_type_by_mode[S_IFMT >> S_SHIFT] = { static inline void ext4_set_de_type(struct super_block *sb, struct ext4_dir_entry_2 *de, umode_t mode) { - if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FILETYPE)) + if (ext4_has_feature_filetype(sb)) de->file_type = ext4_type_by_mode[(mode & S_IFMT)>>S_SHIFT]; } @@ -2903,6 +3033,12 @@ extern const struct inode_operations ext4_encrypted_symlink_inode_operations; extern const struct inode_operations ext4_symlink_inode_operations; extern const struct inode_operations ext4_fast_symlink_inode_operations; +/* sysfs.c */ +extern int ext4_register_sysfs(struct super_block *sb); +extern void ext4_unregister_sysfs(struct super_block *sb); +extern int __init ext4_init_sysfs(void); +extern void ext4_exit_sysfs(void); + /* block_validity */ extern void ext4_release_system_zone(struct super_block *sb); extern int ext4_setup_system_zone(struct super_block *sb); @@ -3049,4 +3185,7 @@ extern void ext4_resize_end(struct super_block *sb); #endif /* __KERNEL__ */ +#define EFSBADCRC EBADMSG /* Bad CRC detected */ +#define EFSCORRUPTED EUCLEAN /* Filesystem is corrupted */ + #endif /* _EXT4_H */ diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c index d418431..e770c1ee 100644 --- a/fs/ext4/ext4_jbd2.c +++ b/fs/ext4/ext4_jbd2.c @@ -88,13 +88,13 @@ int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle) return 0; } + err = handle->h_err; if (!handle->h_transaction) { - err = jbd2_journal_stop(handle); - return handle->h_err ? handle->h_err : err; + rc = jbd2_journal_stop(handle); + return err ? err : rc; } sb = handle->h_transaction->t_journal->j_private; - err = handle->h_err; rc = jbd2_journal_stop(handle); if (!err) diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h index 9c5b49f..5f58462 100644 --- a/fs/ext4/ext4_jbd2.h +++ b/fs/ext4/ext4_jbd2.h @@ -34,8 +34,7 @@ */ #define EXT4_SINGLEDATA_TRANS_BLOCKS(sb) \ - (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS) \ - ? 20U : 8U) + (ext4_has_feature_extents(sb) ? 20U : 8U) /* Extended attribute operations touch at most two data buffers, * two bitmap buffers, and two group summaries, in addition to the inode @@ -84,17 +83,16 @@ /* Amount of blocks needed for quota update - we know that the structure was * allocated so we need to update only data block */ #define EXT4_QUOTA_TRANS_BLOCKS(sb) ((test_opt(sb, QUOTA) ||\ - EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) ?\ - 1 : 0) + ext4_has_feature_quota(sb)) ? 1 : 0) /* Amount of blocks needed for quota insert/delete - we do some block writes * but inode, sb and group updates are done only once */ #define EXT4_QUOTA_INIT_BLOCKS(sb) ((test_opt(sb, QUOTA) ||\ - EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) ?\ + ext4_has_feature_quota(sb)) ?\ (DQUOT_INIT_ALLOC*(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)\ +3+DQUOT_INIT_REWRITE) : 0) #define EXT4_QUOTA_DEL_BLOCKS(sb) ((test_opt(sb, QUOTA) ||\ - EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) ?\ + ext4_has_feature_quota(sb)) ?\ (DQUOT_DEL_ALLOC*(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)\ +3+DQUOT_DEL_REWRITE) : 0) #else diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 2553aa8..551353b 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -442,7 +442,7 @@ static int __ext4_ext_check(const char *function, unsigned int line, int depth, ext4_fsblk_t pblk) { const char *error_msg; - int max = 0; + int max = 0, err = -EFSCORRUPTED; if (unlikely(eh->eh_magic != EXT4_EXT_MAGIC)) { error_msg = "invalid magic"; @@ -473,6 +473,7 @@ static int __ext4_ext_check(const char *function, unsigned int line, if (ext_depth(inode) != depth && !ext4_extent_block_csum_verify(inode, eh)) { error_msg = "extent tree corrupted"; + err = -EFSBADCRC; goto corrupted; } return 0; @@ -485,7 +486,7 @@ corrupted: le16_to_cpu(eh->eh_magic), le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max), max, le16_to_cpu(eh->eh_depth), depth); - return -EIO; + return err; } #define ext4_ext_check(inode, eh, depth, pblk) \ @@ -899,7 +900,7 @@ ext4_find_extent(struct inode *inode, ext4_lblk_t block, bh = read_extent_tree_block(inode, path[ppos].p_block, --i, flags); - if (unlikely(IS_ERR(bh))) { + if (IS_ERR(bh)) { ret = PTR_ERR(bh); goto err; } @@ -910,7 +911,7 @@ ext4_find_extent(struct inode *inode, ext4_lblk_t block, put_bh(bh); EXT4_ERROR_INODE(inode, "ppos %d > depth %d", ppos, depth); - ret = -EIO; + ret = -EFSCORRUPTED; goto err; } path[ppos].p_bh = bh; @@ -959,7 +960,7 @@ static int ext4_ext_insert_index(handle_t *handle, struct inode *inode, EXT4_ERROR_INODE(inode, "logical %d == ei_block %d!", logical, le32_to_cpu(curp->p_idx->ei_block)); - return -EIO; + return -EFSCORRUPTED; } if (unlikely(le16_to_cpu(curp->p_hdr->eh_entries) @@ -968,7 +969,7 @@ static int ext4_ext_insert_index(handle_t *handle, struct inode *inode, "eh_entries %d >= eh_max %d!", le16_to_cpu(curp->p_hdr->eh_entries), le16_to_cpu(curp->p_hdr->eh_max)); - return -EIO; + return -EFSCORRUPTED; } if (logical > le32_to_cpu(curp->p_idx->ei_block)) { @@ -992,7 +993,7 @@ static int ext4_ext_insert_index(handle_t *handle, struct inode *inode, if (unlikely(ix > EXT_MAX_INDEX(curp->p_hdr))) { EXT4_ERROR_INODE(inode, "ix > EXT_MAX_INDEX!"); - return -EIO; + return -EFSCORRUPTED; } ix->ei_block = cpu_to_le32(logical); @@ -1001,7 +1002,7 @@ static int ext4_ext_insert_index(handle_t *handle, struct inode *inode, if (unlikely(ix > EXT_LAST_INDEX(curp->p_hdr))) { EXT4_ERROR_INODE(inode, "ix > EXT_LAST_INDEX!"); - return -EIO; + return -EFSCORRUPTED; } err = ext4_ext_dirty(handle, inode, curp); @@ -1042,7 +1043,7 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, * border from split point */ if (unlikely(path[depth].p_ext > EXT_MAX_EXTENT(path[depth].p_hdr))) { EXT4_ERROR_INODE(inode, "p_ext > EXT_MAX_EXTENT!"); - return -EIO; + return -EFSCORRUPTED; } if (path[depth].p_ext != EXT_MAX_EXTENT(path[depth].p_hdr)) { border = path[depth].p_ext[1].ee_block; @@ -1086,7 +1087,7 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, newblock = ablocks[--a]; if (unlikely(newblock == 0)) { EXT4_ERROR_INODE(inode, "newblock == 0!"); - err = -EIO; + err = -EFSCORRUPTED; goto cleanup; } bh = sb_getblk_gfp(inode->i_sb, newblock, __GFP_MOVABLE | GFP_NOFS); @@ -1112,7 +1113,7 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, EXT4_ERROR_INODE(inode, "eh_entries %d != eh_max %d!", path[depth].p_hdr->eh_entries, path[depth].p_hdr->eh_max); - err = -EIO; + err = -EFSCORRUPTED; goto cleanup; } /* start copy from next extent */ @@ -1151,7 +1152,7 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, k = depth - at - 1; if (unlikely(k < 0)) { EXT4_ERROR_INODE(inode, "k %d < 0!", k); - err = -EIO; + err = -EFSCORRUPTED; goto cleanup; } if (k) @@ -1191,7 +1192,7 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, EXT4_ERROR_INODE(inode, "EXT_MAX_INDEX != EXT_LAST_INDEX ee_block %d!", le32_to_cpu(path[i].p_ext->ee_block)); - err = -EIO; + err = -EFSCORRUPTED; goto cleanup; } /* start copy indexes */ @@ -1425,7 +1426,7 @@ static int ext4_ext_search_left(struct inode *inode, if (unlikely(path == NULL)) { EXT4_ERROR_INODE(inode, "path == NULL *logical %d!", *logical); - return -EIO; + return -EFSCORRUPTED; } depth = path->p_depth; *phys = 0; @@ -1444,7 +1445,7 @@ static int ext4_ext_search_left(struct inode *inode, EXT4_ERROR_INODE(inode, "EXT_FIRST_EXTENT != ex *logical %d ee_block %d!", *logical, le32_to_cpu(ex->ee_block)); - return -EIO; + return -EFSCORRUPTED; } while (--depth >= 0) { ix = path[depth].p_idx; @@ -1455,7 +1456,7 @@ static int ext4_ext_search_left(struct inode *inode, EXT_FIRST_INDEX(path[depth].p_hdr) != NULL ? le32_to_cpu(EXT_FIRST_INDEX(path[depth].p_hdr)->ei_block) : 0, depth); - return -EIO; + return -EFSCORRUPTED; } } return 0; @@ -1465,7 +1466,7 @@ static int ext4_ext_search_left(struct inode *inode, EXT4_ERROR_INODE(inode, "logical %d < ee_block %d + ee_len %d!", *logical, le32_to_cpu(ex->ee_block), ee_len); - return -EIO; + return -EFSCORRUPTED; } *logical = le32_to_cpu(ex->ee_block) + ee_len - 1; @@ -1495,7 +1496,7 @@ static int ext4_ext_search_right(struct inode *inode, if (unlikely(path == NULL)) { EXT4_ERROR_INODE(inode, "path == NULL *logical %d!", *logical); - return -EIO; + return -EFSCORRUPTED; } depth = path->p_depth; *phys = 0; @@ -1514,7 +1515,7 @@ static int ext4_ext_search_right(struct inode *inode, EXT4_ERROR_INODE(inode, "first_extent(path[%d].p_hdr) != ex", depth); - return -EIO; + return -EFSCORRUPTED; } while (--depth >= 0) { ix = path[depth].p_idx; @@ -1522,7 +1523,7 @@ static int ext4_ext_search_right(struct inode *inode, EXT4_ERROR_INODE(inode, "ix != EXT_FIRST_INDEX *logical %d!", *logical); - return -EIO; + return -EFSCORRUPTED; } } goto found_extent; @@ -1532,7 +1533,7 @@ static int ext4_ext_search_right(struct inode *inode, EXT4_ERROR_INODE(inode, "logical %d < ee_block %d + ee_len %d!", *logical, le32_to_cpu(ex->ee_block), ee_len); - return -EIO; + return -EFSCORRUPTED; } if (ex != EXT_LAST_EXTENT(path[depth].p_hdr)) { @@ -1670,7 +1671,7 @@ static int ext4_ext_correct_indexes(handle_t *handle, struct inode *inode, if (unlikely(ex == NULL || eh == NULL)) { EXT4_ERROR_INODE(inode, "ex %p == NULL or eh %p == NULL", ex, eh); - return -EIO; + return -EFSCORRUPTED; } if (depth == 0) { @@ -1938,14 +1939,14 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode, mb_flags |= EXT4_MB_DELALLOC_RESERVED; if (unlikely(ext4_ext_get_actual_len(newext) == 0)) { EXT4_ERROR_INODE(inode, "ext4_ext_get_actual_len(newext) == 0"); - return -EIO; + return -EFSCORRUPTED; } depth = ext_depth(inode); ex = path[depth].p_ext; eh = path[depth].p_hdr; if (unlikely(path[depth].p_hdr == NULL)) { EXT4_ERROR_INODE(inode, "path[%d].p_hdr == NULL", depth); - return -EIO; + return -EFSCORRUPTED; } /* try to insert block into found extent and return */ @@ -2172,7 +2173,7 @@ static int ext4_fill_fiemap_extents(struct inode *inode, if (unlikely(path[depth].p_hdr == NULL)) { up_read(&EXT4_I(inode)->i_data_sem); EXT4_ERROR_INODE(inode, "path[%d].p_hdr == NULL", depth); - err = -EIO; + err = -EFSCORRUPTED; break; } ex = path[depth].p_ext; @@ -2241,7 +2242,7 @@ static int ext4_fill_fiemap_extents(struct inode *inode, if (unlikely(es.es_len == 0)) { EXT4_ERROR_INODE(inode, "es.es_len == 0"); - err = -EIO; + err = -EFSCORRUPTED; break; } @@ -2264,7 +2265,7 @@ static int ext4_fill_fiemap_extents(struct inode *inode, "next extent == %u, next " "delalloc extent = %u", next, next_del); - err = -EIO; + err = -EFSCORRUPTED; break; } } @@ -2363,7 +2364,7 @@ static int ext4_ext_rm_idx(handle_t *handle, struct inode *inode, leaf = ext4_idx_pblock(path->p_idx); if (unlikely(path->p_hdr->eh_entries == 0)) { EXT4_ERROR_INODE(inode, "path->p_hdr->eh_entries == 0"); - return -EIO; + return -EFSCORRUPTED; } err = ext4_ext_get_access(handle, inode, path); if (err) @@ -2612,7 +2613,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, eh = path[depth].p_hdr; if (unlikely(path[depth].p_hdr == NULL)) { EXT4_ERROR_INODE(inode, "path[%d].p_hdr == NULL", depth); - return -EIO; + return -EFSCORRUPTED; } /* find where to start removing */ ex = path[depth].p_ext; @@ -2666,7 +2667,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, "on extent %u:%u", start, end, ex_ee_block, ex_ee_block + ex_ee_len - 1); - err = -EIO; + err = -EFSCORRUPTED; goto out; } else if (a != ex_ee_block) { /* remove tail of the extent */ @@ -2841,7 +2842,7 @@ again: EXT4_ERROR_INODE(inode, "path[%d].p_hdr == NULL", depth); - err = -EIO; + err = -EFSCORRUPTED; } goto out; } @@ -2920,7 +2921,7 @@ again: i = 0; if (ext4_ext_check(inode, path[0].p_hdr, depth, 0)) { - err = -EIO; + err = -EFSCORRUPTED; goto out; } } @@ -2978,7 +2979,7 @@ again: * Should be a no-op if we did IO above. */ cond_resched(); if (WARN_ON(i + 1 > depth)) { - err = -EIO; + err = -EFSCORRUPTED; break; } path[i + 1].p_bh = bh; @@ -3054,7 +3055,7 @@ void ext4_ext_init(struct super_block *sb) * possible initialization would be here */ - if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) { + if (ext4_has_feature_extents(sb)) { #if defined(AGGRESSIVE_TEST) || defined(CHECK_BINSEARCH) || defined(EXTENTS_STATS) printk(KERN_INFO "EXT4-fs: file extents enabled" #ifdef AGGRESSIVE_TEST @@ -3081,7 +3082,7 @@ void ext4_ext_init(struct super_block *sb) */ void ext4_ext_release(struct super_block *sb) { - if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) + if (!ext4_has_feature_extents(sb)) return; #ifdef EXTENTS_STATS @@ -3345,7 +3346,7 @@ static int ext4_split_extent(handle_t *handle, if (!ex) { EXT4_ERROR_INODE(inode, "unexpected hole at %lu", (unsigned long) map->m_lblk); - return -EIO; + return -EFSCORRUPTED; } unwritten = ext4_ext_is_unwritten(ex); split_flag1 = 0; @@ -3558,6 +3559,9 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, max_zeroout = sbi->s_extent_max_zeroout_kb >> (inode->i_sb->s_blocksize_bits - 10); + if (ext4_encrypted_inode(inode)) + max_zeroout = 0; + /* If extent is less than s_max_zeroout_kb, zeroout directly */ if (max_zeroout && (ee_len <= max_zeroout)) { err = ext4_ext_zeroout(inode, ex); @@ -3970,7 +3974,7 @@ convert_initialized_extent(handle_t *handle, struct inode *inode, if (!ex) { EXT4_ERROR_INODE(inode, "unexpected hole at %lu", (unsigned long) map->m_lblk); - return -EIO; + return -EFSCORRUPTED; } } @@ -4308,7 +4312,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, "lblock: %lu, depth: %d pblock %lld", (unsigned long) map->m_lblk, depth, path[depth].p_block); - err = -EIO; + err = -EFSCORRUPTED; goto out2; } @@ -5271,7 +5275,7 @@ ext4_ext_shift_path_extents(struct ext4_ext_path *path, ext4_lblk_t shift, if (depth == path->p_depth) { ex_start = path[depth].p_ext; if (!ex_start) - return -EIO; + return -EFSCORRUPTED; ex_last = EXT_LAST_EXTENT(path[depth].p_hdr); @@ -5411,7 +5415,7 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle, if (!extent) { EXT4_ERROR_INODE(inode, "unexpected hole at %lu", (unsigned long) *iterator); - return -EIO; + return -EFSCORRUPTED; } if (SHIFT == SHIFT_LEFT && *iterator > le32_to_cpu(extent->ee_block)) { @@ -5792,7 +5796,7 @@ ext4_swap_extents(handle_t *handle, struct inode *inode1, int split = 0; path1 = ext4_find_extent(inode1, lblk1, NULL, EXT4_EX_NOCACHE); - if (unlikely(IS_ERR(path1))) { + if (IS_ERR(path1)) { *erp = PTR_ERR(path1); path1 = NULL; finish: @@ -5800,7 +5804,7 @@ ext4_swap_extents(handle_t *handle, struct inode *inode1, goto repeat; } path2 = ext4_find_extent(inode2, lblk2, NULL, EXT4_EX_NOCACHE); - if (unlikely(IS_ERR(path2))) { + if (IS_ERR(path2)) { *erp = PTR_ERR(path2); path2 = NULL; goto finish; diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c index 26724ae..ac748b3 100644 --- a/fs/ext4/extents_status.c +++ b/fs/ext4/extents_status.c @@ -1089,20 +1089,9 @@ static unsigned long ext4_es_scan(struct shrinker *shrink, return nr_shrunk; } -static void *ext4_es_seq_shrinker_info_start(struct seq_file *seq, loff_t *pos) +int ext4_seq_es_shrinker_info_show(struct seq_file *seq, void *v) { - return *pos ? NULL : SEQ_START_TOKEN; -} - -static void * -ext4_es_seq_shrinker_info_next(struct seq_file *seq, void *v, loff_t *pos) -{ - return NULL; -} - -static int ext4_es_seq_shrinker_info_show(struct seq_file *seq, void *v) -{ - struct ext4_sb_info *sbi = seq->private; + struct ext4_sb_info *sbi = EXT4_SB((struct super_block *) seq->private); struct ext4_es_stats *es_stats = &sbi->s_es_stats; struct ext4_inode_info *ei, *max = NULL; unsigned int inode_cnt = 0; @@ -1143,45 +1132,6 @@ static int ext4_es_seq_shrinker_info_show(struct seq_file *seq, void *v) return 0; } -static void ext4_es_seq_shrinker_info_stop(struct seq_file *seq, void *v) -{ -} - -static const struct seq_operations ext4_es_seq_shrinker_info_ops = { - .start = ext4_es_seq_shrinker_info_start, - .next = ext4_es_seq_shrinker_info_next, - .stop = ext4_es_seq_shrinker_info_stop, - .show = ext4_es_seq_shrinker_info_show, -}; - -static int -ext4_es_seq_shrinker_info_open(struct inode *inode, struct file *file) -{ - int ret; - - ret = seq_open(file, &ext4_es_seq_shrinker_info_ops); - if (!ret) { - struct seq_file *m = file->private_data; - m->private = PDE_DATA(inode); - } - - return ret; -} - -static int -ext4_es_seq_shrinker_info_release(struct inode *inode, struct file *file) -{ - return seq_release(inode, file); -} - -static const struct file_operations ext4_es_seq_shrinker_info_fops = { - .owner = THIS_MODULE, - .open = ext4_es_seq_shrinker_info_open, - .read = seq_read, - .llseek = seq_lseek, - .release = ext4_es_seq_shrinker_info_release, -}; - int ext4_es_register_shrinker(struct ext4_sb_info *sbi) { int err; @@ -1210,10 +1160,6 @@ int ext4_es_register_shrinker(struct ext4_sb_info *sbi) if (err) goto err2; - if (sbi->s_proc) - proc_create_data("es_shrinker_info", S_IRUGO, sbi->s_proc, - &ext4_es_seq_shrinker_info_fops, sbi); - return 0; err2: @@ -1225,8 +1171,6 @@ err1: void ext4_es_unregister_shrinker(struct ext4_sb_info *sbi) { - if (sbi->s_proc) - remove_proc_entry("es_shrinker_info", sbi->s_proc); percpu_counter_destroy(&sbi->s_es_stats.es_stats_all_cnt); percpu_counter_destroy(&sbi->s_es_stats.es_stats_shk_cnt); unregister_shrinker(&sbi->s_es_shrinker); diff --git a/fs/ext4/extents_status.h b/fs/ext4/extents_status.h index 691b526..f7aa24f 100644 --- a/fs/ext4/extents_status.h +++ b/fs/ext4/extents_status.h @@ -172,4 +172,6 @@ static inline void ext4_es_store_pblock_status(struct extent_status *es, extern int ext4_es_register_shrinker(struct ext4_sb_info *sbi); extern void ext4_es_unregister_shrinker(struct ext4_sb_info *sbi); +extern int ext4_seq_es_shrinker_info_show(struct seq_file *seq, void *v); + #endif /* _EXT4_EXTENTS_STATUS_H */ diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 619bfc1..1b8024d 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -64,7 +64,7 @@ void ext4_mark_bitmap_end(int start_bit, int end_bit, char *bitmap) } /* Initializes an uninitialized inode bitmap */ -static unsigned ext4_init_inode_bitmap(struct super_block *sb, +static int ext4_init_inode_bitmap(struct super_block *sb, struct buffer_head *bh, ext4_group_t block_group, struct ext4_group_desc *gdp) @@ -89,7 +89,7 @@ static unsigned ext4_init_inode_bitmap(struct super_block *sb, count); } set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &grp->bb_state); - return 0; + return -EFSBADCRC; } memset(bh->b_data, 0, (EXT4_INODES_PER_GROUP(sb) + 7) / 8); @@ -99,7 +99,7 @@ static unsigned ext4_init_inode_bitmap(struct super_block *sb, EXT4_INODES_PER_GROUP(sb) / 8); ext4_group_desc_csum_set(sb, block_group, gdp); - return EXT4_INODES_PER_GROUP(sb); + return 0; } void ext4_end_bitmap_read(struct buffer_head *bh, int uptodate) @@ -112,6 +112,42 @@ void ext4_end_bitmap_read(struct buffer_head *bh, int uptodate) put_bh(bh); } +static int ext4_validate_inode_bitmap(struct super_block *sb, + struct ext4_group_desc *desc, + ext4_group_t block_group, + struct buffer_head *bh) +{ + ext4_fsblk_t blk; + struct ext4_group_info *grp = ext4_get_group_info(sb, block_group); + struct ext4_sb_info *sbi = EXT4_SB(sb); + + if (buffer_verified(bh)) + return 0; + if (EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) + return -EFSCORRUPTED; + + ext4_lock_group(sb, block_group); + blk = ext4_inode_bitmap(sb, desc); + if (!ext4_inode_bitmap_csum_verify(sb, block_group, desc, bh, + EXT4_INODES_PER_GROUP(sb) / 8)) { + ext4_unlock_group(sb, block_group); + ext4_error(sb, "Corrupt inode bitmap - block_group = %u, " + "inode_bitmap = %llu", block_group, blk); + grp = ext4_get_group_info(sb, block_group); + if (!EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) { + int count; + count = ext4_free_inodes_count(sb, desc); + percpu_counter_sub(&sbi->s_freeinodes_counter, + count); + } + set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &grp->bb_state); + return -EFSBADCRC; + } + set_buffer_verified(bh); + ext4_unlock_group(sb, block_group); + return 0; +} + /* * Read the inode allocation bitmap for a given block_group, reading * into the specified slot in the superblock's bitmap cache. @@ -124,12 +160,11 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group) struct ext4_group_desc *desc; struct buffer_head *bh = NULL; ext4_fsblk_t bitmap_blk; - struct ext4_group_info *grp; - struct ext4_sb_info *sbi = EXT4_SB(sb); + int err; desc = ext4_get_group_desc(sb, block_group, NULL); if (!desc) - return NULL; + return ERR_PTR(-EFSCORRUPTED); bitmap_blk = ext4_inode_bitmap(sb, desc); bh = sb_getblk(sb, bitmap_blk); @@ -137,7 +172,7 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group) ext4_error(sb, "Cannot read inode bitmap - " "block_group = %u, inode_bitmap = %llu", block_group, bitmap_blk); - return NULL; + return ERR_PTR(-EIO); } if (bitmap_uptodate(bh)) goto verify; @@ -150,12 +185,14 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group) ext4_lock_group(sb, block_group); if (desc->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) { - ext4_init_inode_bitmap(sb, bh, block_group, desc); + err = ext4_init_inode_bitmap(sb, bh, block_group, desc); set_bitmap_uptodate(bh); set_buffer_uptodate(bh); set_buffer_verified(bh); ext4_unlock_group(sb, block_group); unlock_buffer(bh); + if (err) + goto out; return bh; } ext4_unlock_group(sb, block_group); @@ -182,31 +219,17 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group) ext4_error(sb, "Cannot read inode bitmap - " "block_group = %u, inode_bitmap = %llu", block_group, bitmap_blk); - return NULL; + return ERR_PTR(-EIO); } verify: - ext4_lock_group(sb, block_group); - if (!buffer_verified(bh) && - !ext4_inode_bitmap_csum_verify(sb, block_group, desc, bh, - EXT4_INODES_PER_GROUP(sb) / 8)) { - ext4_unlock_group(sb, block_group); - put_bh(bh); - ext4_error(sb, "Corrupt inode bitmap - block_group = %u, " - "inode_bitmap = %llu", block_group, bitmap_blk); - grp = ext4_get_group_info(sb, block_group); - if (!EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) { - int count; - count = ext4_free_inodes_count(sb, desc); - percpu_counter_sub(&sbi->s_freeinodes_counter, - count); - } - set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &grp->bb_state); - return NULL; - } - ext4_unlock_group(sb, block_group); - set_buffer_verified(bh); + err = ext4_validate_inode_bitmap(sb, desc, block_group, bh); + if (err) + goto out; return bh; +out: + put_bh(bh); + return ERR_PTR(err); } /* @@ -286,8 +309,15 @@ void ext4_free_inode(handle_t *handle, struct inode *inode) bitmap_bh = ext4_read_inode_bitmap(sb, block_group); /* Don't bother if the inode bitmap is corrupt. */ grp = ext4_get_group_info(sb, block_group); - if (unlikely(EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) || !bitmap_bh) + if (IS_ERR(bitmap_bh)) { + fatal = PTR_ERR(bitmap_bh); + bitmap_bh = NULL; + goto error_return; + } + if (unlikely(EXT4_MB_GRP_IBITMAP_CORRUPT(grp))) { + fatal = -EFSCORRUPTED; goto error_return; + } BUFFER_TRACE(bitmap_bh, "get_write_access"); fatal = ext4_journal_get_write_access(handle, bitmap_bh); @@ -826,7 +856,9 @@ got_group: brelse(inode_bitmap_bh); inode_bitmap_bh = ext4_read_inode_bitmap(sb, group); /* Skip groups with suspicious inode tables */ - if (EXT4_MB_GRP_IBITMAP_CORRUPT(grp) || !inode_bitmap_bh) { + if (EXT4_MB_GRP_IBITMAP_CORRUPT(grp) || + IS_ERR(inode_bitmap_bh)) { + inode_bitmap_bh = NULL; if (++group == ngroups) group = 0; continue; @@ -902,8 +934,8 @@ got: struct buffer_head *block_bitmap_bh; block_bitmap_bh = ext4_read_block_bitmap(sb, group); - if (!block_bitmap_bh) { - err = -EIO; + if (IS_ERR(block_bitmap_bh)) { + err = PTR_ERR(block_bitmap_bh); goto out; } BUFFER_TRACE(block_bitmap_bh, "get block bitmap access"); @@ -1045,7 +1077,7 @@ got: ei->i_extra_isize = EXT4_SB(sb)->s_want_extra_isize; ei->i_inline_off = 0; - if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_INLINE_DATA)) + if (ext4_has_feature_inline_data(sb)) ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); ret = inode; err = dquot_alloc_inode(inode); @@ -1060,7 +1092,7 @@ got: if (err) goto fail_free_drop; - if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) { + if (ext4_has_feature_extents(sb)) { /* set extent flag only for directory, file and normal symlink*/ if (S_ISDIR(mode) || S_ISREG(mode) || S_ISLNK(mode)) { ext4_set_inode_flag(inode, EXT4_INODE_EXTENTS); @@ -1116,14 +1148,17 @@ struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino) /* Error cases - e2fsck has already cleaned up for us */ if (ino > max_ino) { ext4_warning(sb, "bad orphan ino %lu! e2fsck was run?", ino); + err = -EFSCORRUPTED; goto error; } block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb); bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb); bitmap_bh = ext4_read_inode_bitmap(sb, block_group); - if (!bitmap_bh) { - ext4_warning(sb, "inode bitmap error for orphan %lu", ino); + if (IS_ERR(bitmap_bh)) { + err = PTR_ERR(bitmap_bh); + ext4_warning(sb, "inode bitmap error %ld for orphan %lu", + ino, err); goto error; } @@ -1198,8 +1233,10 @@ unsigned long ext4_count_free_inodes(struct super_block *sb) desc_count += ext4_free_inodes_count(sb, gdp); brelse(bitmap_bh); bitmap_bh = ext4_read_inode_bitmap(sb, i); - if (!bitmap_bh) + if (IS_ERR(bitmap_bh)) { + bitmap_bh = NULL; continue; + } x = ext4_count_free(bitmap_bh->b_data, EXT4_INODES_PER_GROUP(sb) / 8); diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index 2468261..355ef9c 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -562,11 +562,10 @@ int ext4_ind_map_blocks(handle_t *handle, struct inode *inode, /* * Okay, we need to do block allocation. */ - if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_BIGALLOC)) { + if (ext4_has_feature_bigalloc(inode->i_sb)) { EXT4_ERROR_INODE(inode, "Can't allocate blocks for " "non-extent mapped inodes with bigalloc"); - return -EUCLEAN; + return -EFSCORRUPTED; } /* Set up for the direct block allocation */ diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index cd944a7..d884989 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -434,8 +434,7 @@ static int ext4_destroy_inline_data_nolock(handle_t *handle, memset((void *)ext4_raw_inode(&is.iloc)->i_block, 0, EXT4_MIN_INLINE_DATA_SIZE); - if (EXT4_HAS_INCOMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_INCOMPAT_EXTENTS)) { + if (ext4_has_feature_extents(inode->i_sb)) { if (S_ISDIR(inode->i_mode) || S_ISREG(inode->i_mode) || S_ISLNK(inode->i_mode)) { ext4_set_inode_flag(inode, EXT4_INODE_EXTENTS); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 612fbcf..ea433a7 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -378,7 +378,7 @@ static int __check_block_validity(struct inode *inode, const char *func, "lblock %lu mapped to illegal pblock " "(length %d)", (unsigned long) map->m_lblk, map->m_len); - return -EIO; + return -EFSCORRUPTED; } return 0; } @@ -480,7 +480,7 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode, /* We can handle the block number less than EXT_MAX_BLOCKS */ if (unlikely(map->m_lblk >= EXT_MAX_BLOCKS)) - return -EIO; + return -EFSCORRUPTED; /* Lookup extent status tree firstly */ if (ext4_es_lookup_extent(inode, map->m_lblk, &es)) { @@ -965,7 +965,7 @@ static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len, if (unlikely(err)) page_zero_new_buffers(page, from, to); else if (decrypt) - err = ext4_decrypt_one(inode, page); + err = ext4_decrypt(page); return err; } #endif @@ -1181,6 +1181,38 @@ errout: return ret ? ret : copied; } +/* + * 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); +} + static int ext4_journalled_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, @@ -1207,7 +1239,7 @@ static int ext4_journalled_write_end(struct file *file, if (copied < len) { if (!PageUptodate(page)) copied = 0; - page_zero_new_buffers(page, from+copied, to); + zero_new_buffers(page, from+copied, to); } ret = ext4_walk_page_buffers(handle, page_buffers(page), from, @@ -1815,11 +1847,22 @@ static int ext4_writepage(struct page *page, * 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) { + if ((current->flags & PF_MEMALLOC) || + (inode->i_sb->s_blocksize == PAGE_CACHE_SIZE)) { /* * For memory cleaning there's no point in writing only * some buffers. So just bail out. Warn if we came here @@ -2599,8 +2642,7 @@ static int ext4_nonda_switch(struct super_block *sb) /* 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_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_LARGE_FILE))) + if (likely(ext4_has_feature_large_file(inode->i_sb))) return 1; if (pos + len <= 0x7fffffffULL) @@ -3344,7 +3386,7 @@ static int __ext4_block_zero_page_range(handle_t *handle, int err = 0; page = find_or_create_page(mapping, from >> PAGE_CACHE_SHIFT, - mapping_gfp_mask(mapping) & ~__GFP_FS); + mapping_gfp_constraint(mapping, ~__GFP_FS)); if (!page) return -ENOMEM; @@ -3393,7 +3435,7 @@ static int __ext4_block_zero_page_range(handle_t *handle, /* We expect the key to be set. */ BUG_ON(!ext4_has_encryption_key(inode)); BUG_ON(blocksize != PAGE_CACHE_SIZE); - WARN_ON_ONCE(ext4_decrypt_one(inode, page)); + WARN_ON_ONCE(ext4_decrypt(page)); } } if (ext4_should_journal_data(inode)) { @@ -3820,7 +3862,7 @@ static int __ext4_get_inode_loc(struct inode *inode, iloc->bh = NULL; if (!ext4_valid_inum(sb, inode->i_ino)) - return -EIO; + return -EFSCORRUPTED; iloc->block_group = (inode->i_ino - 1) / EXT4_INODES_PER_GROUP(sb); gdp = ext4_get_group_desc(sb, iloc->block_group, NULL); @@ -4006,8 +4048,7 @@ static blkcnt_t ext4_inode_blocks(struct ext4_inode *raw_inode, struct inode *inode = &(ei->vfs_inode); struct super_block *sb = inode->i_sb; - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_HUGE_FILE)) { + 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); @@ -4068,7 +4109,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) EXT4_ERROR_INODE(inode, "bad extra_isize (%u != %u)", EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize, EXT4_INODE_SIZE(inode->i_sb)); - ret = -EIO; + ret = -EFSCORRUPTED; goto bad_inode; } } else @@ -4088,7 +4129,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) if (!ext4_inode_csum_verify(inode, raw_inode, ei)) { EXT4_ERROR_INODE(inode, "checksum invalid"); - ret = -EIO; + ret = -EFSBADCRC; goto bad_inode; } @@ -4130,7 +4171,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) 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_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_64BIT)) + 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); @@ -4203,7 +4244,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) !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 = -EIO; + ret = -EFSCORRUPTED; goto bad_inode; } else if (!ext4_has_inline_data(inode)) { if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { @@ -4254,7 +4295,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) } else if (ino == EXT4_BOOT_LOADER_INO) { make_bad_inode(inode); } else { - ret = -EIO; + ret = -EFSCORRUPTED; EXT4_ERROR_INODE(inode, "bogus i_mode (%o)", inode->i_mode); goto bad_inode; } @@ -4272,7 +4313,7 @@ bad_inode: 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(-EIO); + return ERR_PTR(-EFSCORRUPTED); return ext4_iget(sb, ino); } @@ -4294,7 +4335,7 @@ static int ext4_inode_blocks_set(handle_t *handle, ext4_clear_inode_flag(inode, EXT4_INODE_HUGE_FILE); return 0; } - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_HUGE_FILE)) + if (!ext4_has_feature_huge_file(sb)) return -EFBIG; if (i_blocks <= 0xffffffffffffULL) { @@ -4455,8 +4496,7 @@ static int ext4_do_update_inode(handle_t *handle, need_datasync = 1; } if (ei->i_disksize > 0x7fffffffULL) { - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_LARGE_FILE) || + 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; @@ -4505,8 +4545,7 @@ static int ext4_do_update_inode(handle_t *handle, if (err) goto out_brelse; ext4_update_dynamic_rev(sb); - EXT4_SET_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_LARGE_FILE); + ext4_set_feature_large_file(sb); ext4_handle_sync(handle); err = ext4_handle_dirty_super(handle, sb); } @@ -5244,7 +5283,7 @@ int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) !ext4_should_journal_data(inode) && !ext4_nonda_switch(inode->i_sb)) { do { - ret = __block_page_mkwrite(vma, vmf, + ret = block_page_mkwrite(vma, vmf, ext4_da_get_block_prep); } while (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)); @@ -5291,7 +5330,7 @@ retry_alloc: ret = VM_FAULT_SIGBUS; goto out; } - ret = __block_page_mkwrite(vma, vmf, get_block); + 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_CACHE_SIZE, NULL, do_journal_get_write_access)) { diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 1346cfa..5e872fd 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -145,8 +145,7 @@ static long swap_inode_boot_loader(struct super_block *sb, inode_bl->i_version = 1; i_size_write(inode_bl, 0); inode_bl->i_mode = S_IFREG; - if (EXT4_HAS_INCOMPAT_FEATURE(sb, - EXT4_FEATURE_INCOMPAT_EXTENTS)) { + if (ext4_has_feature_extents(sb)) { ext4_set_inode_flag(inode_bl, EXT4_INODE_EXTENTS); ext4_ext_tree_init(handle, inode_bl); } else @@ -383,8 +382,7 @@ setversion_out: goto group_extend_out; } - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_BIGALLOC)) { + if (ext4_has_feature_bigalloc(sb)) { ext4_msg(sb, KERN_ERR, "Online resizing not supported with bigalloc"); err = -EOPNOTSUPP; @@ -432,8 +430,7 @@ group_extend_out: goto mext_out; } - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_BIGALLOC)) { + if (ext4_has_feature_bigalloc(sb)) { ext4_msg(sb, KERN_ERR, "Online defrag not supported with bigalloc"); err = -EOPNOTSUPP; @@ -470,8 +467,7 @@ mext_out: goto group_add_out; } - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_BIGALLOC)) { + if (ext4_has_feature_bigalloc(sb)) { ext4_msg(sb, KERN_ERR, "Online resizing not supported with bigalloc"); err = -EOPNOTSUPP; @@ -553,8 +549,7 @@ group_add_out: int err = 0, err2 = 0; ext4_group_t o_group = EXT4_SB(sb)->s_groups_count; - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_BIGALLOC)) { + if (ext4_has_feature_bigalloc(sb)) { ext4_msg(sb, KERN_ERR, "Online resizing not (yet) supported with bigalloc"); return -EOPNOTSUPP; diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 34b610e..61eaf74 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -874,8 +874,10 @@ static int ext4_mb_init_cache(struct page *page, char *incore) bh[i] = NULL; continue; } - if (!(bh[i] = ext4_read_block_bitmap_nowait(sb, group))) { - err = -ENOMEM; + bh[i] = ext4_read_block_bitmap_nowait(sb, group); + if (IS_ERR(bh[i])) { + err = PTR_ERR(bh[i]); + bh[i] = NULL; goto out; } mb_debug(1, "read bitmap for group %u\n", group); @@ -883,8 +885,13 @@ static int ext4_mb_init_cache(struct page *page, char *incore) /* wait for I/O completion */ for (i = 0, group = first_group; i < groups_per_page; i++, group++) { - if (bh[i] && ext4_wait_block_bitmap(sb, group, bh[i])) - err = -EIO; + int err2; + + if (!bh[i]) + continue; + err2 = ext4_wait_block_bitmap(sb, group, bh[i]); + if (!err) + err = err2; } first_block = page->index * blocks_per_page; @@ -2333,7 +2340,7 @@ static int ext4_mb_seq_groups_open(struct inode *inode, struct file *file) } -static const struct file_operations ext4_mb_seq_groups_fops = { +const struct file_operations ext4_seq_mb_groups_fops = { .owner = THIS_MODULE, .open = ext4_mb_seq_groups_open, .read = seq_read, @@ -2447,7 +2454,7 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group, kmalloc(sb->s_blocksize, GFP_NOFS); BUG_ON(meta_group_info[i]->bb_bitmap == NULL); bh = ext4_read_block_bitmap(sb, group); - BUG_ON(bh == NULL); + BUG_ON(IS_ERR_OR_NULL(bh)); memcpy(meta_group_info[i]->bb_bitmap, bh->b_data, sb->s_blocksize); put_bh(bh); @@ -2661,10 +2668,6 @@ int ext4_mb_init(struct super_block *sb) if (ret != 0) goto out_free_locality_groups; - if (sbi->s_proc) - proc_create_data("mb_groups", S_IRUGO, sbi->s_proc, - &ext4_mb_seq_groups_fops, sb); - return 0; out_free_locality_groups: @@ -2705,9 +2708,6 @@ int ext4_mb_release(struct super_block *sb) struct ext4_sb_info *sbi = EXT4_SB(sb); struct kmem_cache *cachep = get_groupinfo_cache(sb->s_blocksize_bits); - if (sbi->s_proc) - remove_proc_entry("mb_groups", sbi->s_proc); - if (sbi->s_group_info) { for (i = 0; i < ngroups; i++) { grinfo = ext4_get_group_info(sb, i); @@ -2896,10 +2896,12 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, sb = ac->ac_sb; sbi = EXT4_SB(sb); - err = -EIO; bitmap_bh = ext4_read_block_bitmap(sb, ac->ac_b_ex.fe_group); - if (!bitmap_bh) + if (IS_ERR(bitmap_bh)) { + err = PTR_ERR(bitmap_bh); + bitmap_bh = NULL; goto out_err; + } BUFFER_TRACE(bitmap_bh, "getting write access"); err = ext4_journal_get_write_access(handle, bitmap_bh); @@ -3843,8 +3845,10 @@ ext4_mb_discard_group_preallocations(struct super_block *sb, return 0; bitmap_bh = ext4_read_block_bitmap(sb, group); - if (bitmap_bh == NULL) { - ext4_error(sb, "Error reading block bitmap for %u", group); + if (IS_ERR(bitmap_bh)) { + err = PTR_ERR(bitmap_bh); + ext4_error(sb, "Error %d reading block bitmap for %u", + err, group); return 0; } @@ -4015,9 +4019,10 @@ repeat: } bitmap_bh = ext4_read_block_bitmap(sb, group); - if (bitmap_bh == NULL) { - ext4_error(sb, "Error reading block bitmap for %u", - group); + if (IS_ERR(bitmap_bh)) { + err = PTR_ERR(bitmap_bh); + ext4_error(sb, "Error %d reading block bitmap for %u", + err, group); ext4_mb_unload_buddy(&e4b); continue; } @@ -4682,22 +4687,11 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode, ext4_debug("freeing block %llu\n", block); trace_ext4_free_blocks(inode, block, count, flags); - if (flags & EXT4_FREE_BLOCKS_FORGET) { - struct buffer_head *tbh = bh; - int i; - - BUG_ON(bh && (count > 1)); + if (bh && (flags & EXT4_FREE_BLOCKS_FORGET)) { + BUG_ON(count > 1); - for (i = 0; i < count; i++) { - cond_resched(); - if (!bh) - tbh = sb_find_get_block(inode->i_sb, - block + i); - if (!tbh) - continue; - ext4_forget(handle, flags & EXT4_FREE_BLOCKS_METADATA, - inode, tbh, block + i); - } + ext4_forget(handle, flags & EXT4_FREE_BLOCKS_METADATA, + inode, bh, block); } /* @@ -4742,6 +4736,19 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode, count += sbi->s_cluster_ratio - overflow; } + if (!bh && (flags & EXT4_FREE_BLOCKS_FORGET)) { + int i; + + for (i = 0; i < count; i++) { + cond_resched(); + bh = sb_find_get_block(inode->i_sb, block + i); + if (!bh) + continue; + ext4_forget(handle, flags & EXT4_FREE_BLOCKS_METADATA, + inode, bh, block + i); + } + } + do_more: overflow = 0; ext4_get_group_no_and_offset(sb, block, &block_group, &bit); @@ -4761,8 +4768,9 @@ do_more: } count_clusters = EXT4_NUM_B2C(sbi, count); bitmap_bh = ext4_read_block_bitmap(sb, block_group); - if (!bitmap_bh) { - err = -EIO; + if (IS_ERR(bitmap_bh)) { + err = PTR_ERR(bitmap_bh); + bitmap_bh = NULL; goto error_return; } gdp = ext4_get_group_desc(sb, block_group, &gd_bh); @@ -4931,8 +4939,9 @@ int ext4_group_add_blocks(handle_t *handle, struct super_block *sb, } bitmap_bh = ext4_read_block_bitmap(sb, block_group); - if (!bitmap_bh) { - err = -EIO; + if (IS_ERR(bitmap_bh)) { + err = PTR_ERR(bitmap_bh); + bitmap_bh = NULL; goto error_return; } diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c index 6163ad2..a465189 100644 --- a/fs/ext4/migrate.c +++ b/fs/ext4/migrate.c @@ -448,8 +448,7 @@ int ext4_ext_migrate(struct inode *inode) * If the filesystem does not support extents, or the inode * already is extent-based, error out. */ - if (!EXT4_HAS_INCOMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_INCOMPAT_EXTENTS) || + if (!ext4_has_feature_extents(inode->i_sb) || (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) return -EINVAL; @@ -625,13 +624,11 @@ int ext4_ind_migrate(struct inode *inode) handle_t *handle; int ret; - if (!EXT4_HAS_INCOMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_INCOMPAT_EXTENTS) || + if (!ext4_has_feature_extents(inode->i_sb) || (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) return -EINVAL; - if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_BIGALLOC)) + if (ext4_has_feature_bigalloc(inode->i_sb)) return -EOPNOTSUPP; /* diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c index 6eb1a61..0a512aa 100644 --- a/fs/ext4/mmp.c +++ b/fs/ext4/mmp.c @@ -98,10 +98,12 @@ static int read_mmp_block(struct super_block *sb, struct buffer_head **bh, } mmp = (struct mmp_struct *)((*bh)->b_data); - if (le32_to_cpu(mmp->mmp_magic) == EXT4_MMP_MAGIC && - ext4_mmp_csum_verify(sb, mmp)) + if (le32_to_cpu(mmp->mmp_magic) != EXT4_MMP_MAGIC) + ret = -EFSCORRUPTED; + else if (!ext4_mmp_csum_verify(sb, mmp)) + ret = -EFSBADCRC; + else return 0; - ret = -EINVAL; warn_exit: ext4_warning(sb, "Error %d while reading MMP block %llu", diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 9f61e76..a969ab3 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -109,7 +109,7 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode, if (!bh) { ext4_error_inode(inode, func, line, block, "Directory hole found"); - return ERR_PTR(-EIO); + return ERR_PTR(-EFSCORRUPTED); } dirent = (struct ext4_dir_entry *) bh->b_data; /* Determine whether or not we have an index block */ @@ -124,7 +124,7 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode, if (!is_dx_block && type == INDEX) { ext4_error_inode(inode, func, line, block, "directory leaf block found instead of index block"); - return ERR_PTR(-EIO); + return ERR_PTR(-EFSCORRUPTED); } if (!ext4_has_metadata_csum(inode->i_sb) || buffer_verified(bh)) @@ -142,7 +142,7 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode, ext4_error_inode(inode, func, line, block, "Directory index failed checksum"); brelse(bh); - return ERR_PTR(-EIO); + return ERR_PTR(-EFSBADCRC); } } if (!is_dx_block) { @@ -152,7 +152,7 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode, ext4_error_inode(inode, func, line, block, "Directory block failed checksum"); brelse(bh); - return ERR_PTR(-EIO); + return ERR_PTR(-EFSBADCRC); } } return bh; @@ -1429,7 +1429,7 @@ restart: } num++; bh = ext4_getblk(NULL, dir, b++, 0); - if (unlikely(IS_ERR(bh))) { + if (IS_ERR(bh)) { if (ra_max == 0) { ret = bh; goto cleanup_and_exit; @@ -1570,19 +1570,19 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi brelse(bh); if (!ext4_valid_inum(dir->i_sb, ino)) { EXT4_ERROR_INODE(dir, "bad inode number: %u", ino); - return ERR_PTR(-EIO); + return ERR_PTR(-EFSCORRUPTED); } if (unlikely(ino == dir->i_ino)) { EXT4_ERROR_INODE(dir, "'%pd' linked to parent dir", dentry); - return ERR_PTR(-EIO); + return ERR_PTR(-EFSCORRUPTED); } inode = ext4_iget_normal(dir->i_sb, ino); if (inode == ERR_PTR(-ESTALE)) { EXT4_ERROR_INODE(dir, "deleted inode referenced: %u", ino); - return ERR_PTR(-EIO); + return ERR_PTR(-EFSCORRUPTED); } if (!IS_ERR(inode) && ext4_encrypted_inode(dir) && (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || @@ -1619,7 +1619,7 @@ struct dentry *ext4_get_parent(struct dentry *child) if (!ext4_valid_inum(d_inode(child)->i_sb, ino)) { EXT4_ERROR_INODE(d_inode(child), "bad parent inode number: %u", ino); - return ERR_PTR(-EIO); + return ERR_PTR(-EFSCORRUPTED); } return d_obtain_alias(ext4_iget_normal(d_inode(child)->i_sb, ino)); @@ -1807,7 +1807,7 @@ int ext4_find_dest_de(struct inode *dir, struct inode *inode, while ((char *) de <= top) { if (ext4_check_dir_entry(dir, NULL, de, bh, buf, buf_size, offset)) { - res = -EIO; + res = -EFSCORRUPTED; goto return_result; } /* Provide crypto context and crypto buffer to ext4 match */ @@ -1967,7 +1967,7 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname, if ((char *) de >= (((char *) root) + blocksize)) { EXT4_ERROR_INODE(dir, "invalid rec_len for '..'"); brelse(bh); - return -EIO; + return -EFSCORRUPTED; } len = ((char *) root) + (blocksize - csum_size) - (char *) de; @@ -2118,7 +2118,7 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, goto out; if (blocks == 1 && !dx_fallback && - EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_DIR_INDEX)) { + ext4_has_feature_dir_index(sb)) { retval = make_indexed_dir(handle, &fname, dentry, inode, bh); bh = NULL; /* make_indexed_dir releases bh */ @@ -2315,7 +2315,7 @@ int ext4_generic_delete_entry(handle_t *handle, while (i < buf_size - csum_size) { if (ext4_check_dir_entry(dir, NULL, de, bh, bh->b_data, bh->b_size, i)) - return -EIO; + return -EFSCORRUPTED; if (de == de_del) { if (pde) pde->rec_len = ext4_rec_len_to_disk( @@ -2388,8 +2388,7 @@ static void ext4_inc_count(handle_t *handle, struct inode *inode) /* limit is 16-bit i_links_count */ if (inode->i_nlink >= EXT4_LINK_MAX || inode->i_nlink == 2) { set_nlink(inode, 1); - EXT4_SET_RO_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_RO_COMPAT_DIR_NLINK); + ext4_set_feature_dir_nlink(inode->i_sb); } } } @@ -2469,9 +2468,6 @@ static int ext4_mknod(struct inode *dir, struct dentry *dentry, struct inode *inode; int err, credits, retries = 0; - if (!new_valid_dev(rdev)) - return -EINVAL; - err = dquot_initialize(dir); if (err) return err; @@ -2934,7 +2930,7 @@ static int ext4_rmdir(struct inode *dir, struct dentry *dentry) inode = d_inode(dentry); - retval = -EIO; + retval = -EFSCORRUPTED; if (le32_to_cpu(de->inode) != inode->i_ino) goto end_rmdir; @@ -3008,7 +3004,7 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry) inode = d_inode(dentry); - retval = -EIO; + retval = -EFSCORRUPTED; if (le32_to_cpu(de->inode) != inode->i_ino) goto end_unlink; @@ -3310,7 +3306,7 @@ static int ext4_rename_dir_prepare(handle_t *handle, struct ext4_renament *ent) if (!ent->dir_bh) return retval; if (le32_to_cpu(ent->parent_de->inode) != ent->dir->i_ino) - return -EIO; + return -EFSCORRUPTED; BUFFER_TRACE(ent->dir_bh, "get_write_access"); return ext4_journal_get_write_access(handle, ent->dir_bh); } @@ -3352,8 +3348,7 @@ static int ext4_setent(handle_t *handle, struct ext4_renament *ent, if (retval) return retval; ent->de->inode = cpu_to_le32(ino); - if (EXT4_HAS_INCOMPAT_FEATURE(ent->dir->i_sb, - EXT4_FEATURE_INCOMPAT_FILETYPE)) + if (ext4_has_feature_filetype(ent->dir->i_sb)) ent->de->file_type = file_type; ent->dir->i_version++; ent->dir->i_ctime = ent->dir->i_mtime = diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 84ba4d2..17fbe38 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -425,6 +425,7 @@ int ext4_bio_write_page(struct ext4_io_submit *io, struct buffer_head *bh, *head; int ret = 0; int nr_submitted = 0; + int nr_to_submit = 0; blocksize = 1 << inode->i_blkbits; @@ -477,11 +478,13 @@ int ext4_bio_write_page(struct ext4_io_submit *io, unmap_underlying_metadata(bh->b_bdev, bh->b_blocknr); } set_buffer_async_write(bh); + nr_to_submit++; } while ((bh = bh->b_this_page) != head); bh = head = page_buffers(page); - if (ext4_encrypted_inode(inode) && S_ISREG(inode->i_mode)) { + if (ext4_encrypted_inode(inode) && S_ISREG(inode->i_mode) && + nr_to_submit) { data_page = ext4_encrypt(inode, page); if (IS_ERR(data_page)) { ret = PTR_ERR(data_page); diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c index e26803f..5dc5e95 100644 --- a/fs/ext4/readpage.c +++ b/fs/ext4/readpage.c @@ -62,7 +62,7 @@ static void completion_pages(struct work_struct *work) bio_for_each_segment_all(bv, bio, i) { struct page *page = bv->bv_page; - int ret = ext4_decrypt(ctx, page); + int ret = ext4_decrypt(page); if (ret) { WARN_ON_ONCE(1); SetPageError(page); @@ -165,8 +165,8 @@ int ext4_mpage_readpages(struct address_space *mapping, if (pages) { page = list_entry(pages->prev, struct page, lru); list_del(&page->lru); - if (add_to_page_cache_lru(page, mapping, - page->index, GFP_KERNEL)) + if (add_to_page_cache_lru(page, mapping, page->index, + mapping_gfp_constraint(mapping, GFP_KERNEL))) goto next_page; } diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index cf0c472..ad62d7a 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -490,7 +490,7 @@ static int setup_new_flex_group_blocks(struct super_block *sb, group_data[0].group != sbi->s_groups_count); reserved_gdb = le16_to_cpu(es->s_reserved_gdt_blocks); - meta_bg = EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_META_BG); + meta_bg = ext4_has_feature_meta_bg(sb); /* This transaction may be extended/restarted along the way */ handle = ext4_journal_start_sb(sb, EXT4_HT_RESIZE, EXT4_MAX_TRANS_DATA); @@ -680,8 +680,7 @@ static unsigned ext4_list_backups(struct super_block *sb, unsigned *three, int mult = 3; unsigned ret; - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER)) { + if (!ext4_has_feature_sparse_super(sb)) { ret = *min; *min += 1; return ret; @@ -1040,7 +1039,7 @@ exit_free: * do not copy the full number of backups at this time. The resize * which changed s_groups_count will backup again. */ -static void update_backups(struct super_block *sb, int blk_off, char *data, +static void update_backups(struct super_block *sb, sector_t blk_off, char *data, int size, int meta_bg) { struct ext4_sb_info *sbi = EXT4_SB(sb); @@ -1065,7 +1064,7 @@ static void update_backups(struct super_block *sb, int blk_off, char *data, group = ext4_list_backups(sb, &three, &five, &seven); last = sbi->s_groups_count; } else { - group = ext4_meta_bg_first_group(sb, group) + 1; + group = ext4_get_group_number(sb, blk_off) + 1; last = (ext4_group_t)(group + EXT4_DESC_PER_BLOCK(sb) - 2); } @@ -1158,7 +1157,7 @@ static int ext4_add_new_descs(handle_t *handle, struct super_block *sb, int i, gdb_off, gdb_num, err = 0; int meta_bg; - meta_bg = EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_META_BG); + meta_bg = ext4_has_feature_meta_bg(sb); for (i = 0; i < count; i++, group++) { int reserved_gdb = ext4_bg_has_super(sb, group) ? le16_to_cpu(es->s_reserved_gdt_blocks) : 0; @@ -1381,9 +1380,7 @@ static void ext4_update_super(struct super_block *sb, ext4_debug("free blocks count %llu", percpu_counter_read(&sbi->s_freeclusters_counter)); - if (EXT4_HAS_INCOMPAT_FEATURE(sb, - EXT4_FEATURE_INCOMPAT_FLEX_BG) && - sbi->s_log_groups_per_flex) { + if (ext4_has_feature_flex_bg(sb) && sbi->s_log_groups_per_flex) { ext4_group_t flex_group; flex_group = ext4_flex_group(sbi, group_data[0].group); atomic64_add(EXT4_NUM_B2C(sbi, free_blocks), @@ -1476,8 +1473,7 @@ exit_journal: int gdb_num = group / EXT4_DESC_PER_BLOCK(sb); int gdb_num_end = ((group + flex_gd->count - 1) / EXT4_DESC_PER_BLOCK(sb)); - int meta_bg = EXT4_HAS_INCOMPAT_FEATURE(sb, - EXT4_FEATURE_INCOMPAT_META_BG); + int meta_bg = ext4_has_feature_meta_bg(sb); sector_t old_gdb = 0; update_backups(sb, sbi->s_sbh->b_blocknr, (char *)es, @@ -1585,8 +1581,7 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input) gdb_off = input->group % EXT4_DESC_PER_BLOCK(sb); - if (gdb_off == 0 && !EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER)) { + if (gdb_off == 0 && !ext4_has_feature_sparse_super(sb)) { ext4_warning(sb, "Can't resize non-sparse filesystem further"); return -EPERM; } @@ -1604,9 +1599,8 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input) } if (reserved_gdb || gdb_off == 0) { - if (!EXT4_HAS_COMPAT_FEATURE(sb, - EXT4_FEATURE_COMPAT_RESIZE_INODE) - || !le16_to_cpu(es->s_reserved_gdt_blocks)) { + if (ext4_has_feature_resize_inode(sb) || + !le16_to_cpu(es->s_reserved_gdt_blocks)) { ext4_warning(sb, "No reserved GDT blocks, can't resize"); return -EPERM; @@ -1825,8 +1819,8 @@ static int ext4_convert_meta_bg(struct super_block *sb, struct inode *inode) if (err) goto errout; - EXT4_CLEAR_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_RESIZE_INODE); - EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_META_BG); + ext4_clear_feature_resize_inode(sb); + ext4_set_feature_meta_bg(sb); sbi->s_es->s_first_meta_bg = cpu_to_le32(num_desc_blocks(sb, sbi->s_groups_count)); @@ -1918,9 +1912,9 @@ retry: n_desc_blocks = num_desc_blocks(sb, n_group + 1); o_desc_blocks = num_desc_blocks(sb, sbi->s_groups_count); - meta_bg = EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_META_BG); + meta_bg = ext4_has_feature_meta_bg(sb); - if (EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_RESIZE_INODE)) { + if (ext4_has_feature_resize_inode(sb)) { if (meta_bg) { ext4_error(sb, "resize_inode and meta_bg enabled " "simultaneously"); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index a63c7b0..753f4e6 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -34,7 +34,6 @@ #include <linux/namei.h> #include <linux/quotaops.h> #include <linux/seq_file.h> -#include <linux/proc_fs.h> #include <linux/ctype.h> #include <linux/log2.h> #include <linux/crc16.h> @@ -54,11 +53,8 @@ #define CREATE_TRACE_POINTS #include <trace/events/ext4.h> -static struct proc_dir_entry *ext4_proc_root; -static struct kset *ext4_kset; static struct ext4_lazy_init *ext4_li_info; static struct mutex ext4_li_mtx; -static struct ext4_features *ext4_feat; static int ext4_mballoc_ready; static struct ratelimit_state ext4_mount_msg_ratelimit; @@ -83,7 +79,6 @@ static int ext4_feature_set_ok(struct super_block *sb, int readonly); static void ext4_destroy_lazyinit_thread(void); static void ext4_unregister_li_request(struct super_block *sb); static void ext4_clear_request_list(void); -static int ext4_reserve_clusters(struct ext4_sb_info *, ext4_fsblk_t); #if !defined(CONFIG_EXT2_FS) && !defined(CONFIG_EXT2_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT2) static struct file_system_type ext2_fs_type = { @@ -115,8 +110,7 @@ MODULE_ALIAS("ext3"); static int ext4_verify_csum_type(struct super_block *sb, struct ext4_super_block *es) { - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + if (!ext4_has_feature_metadata_csum(sb)) return 1; return es->s_checksum_type == EXT4_CRC32C_CHKSUM; @@ -394,9 +388,13 @@ static void ext4_handle_error(struct super_block *sb) smp_wmb(); sb->s_flags |= MS_RDONLY; } - if (test_opt(sb, ERRORS_PANIC)) + if (test_opt(sb, ERRORS_PANIC)) { + if (EXT4_SB(sb)->s_journal && + !(EXT4_SB(sb)->s_journal->j_flags & JBD2_REC_ERR)) + return; panic("EXT4-fs (device %s): panic forced after error\n", sb->s_id); + } } #define ext4_error_ratelimit(sb) \ @@ -495,6 +493,12 @@ const char *ext4_decode_error(struct super_block *sb, int errno, char *errstr = NULL; switch (errno) { + case -EFSCORRUPTED: + errstr = "Corrupt filesystem"; + break; + case -EFSBADCRC: + errstr = "Filesystem failed CRC"; + break; case -EIO: errstr = "IO failure"; break; @@ -585,8 +589,12 @@ void __ext4_abort(struct super_block *sb, const char *function, jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO); save_error_info(sb, function, line); } - if (test_opt(sb, ERRORS_PANIC)) + if (test_opt(sb, ERRORS_PANIC)) { + if (EXT4_SB(sb)->s_journal && + !(EXT4_SB(sb)->s_journal->j_flags & JBD2_REC_ERR)) + return; panic("EXT4-fs panic from previous error\n"); + } } void __ext4_msg(struct super_block *sb, @@ -800,6 +808,7 @@ static void ext4_put_super(struct super_block *sb) ext4_abort(sb, "Couldn't clean up the journal"); } + ext4_unregister_sysfs(sb); ext4_es_unregister_shrinker(sbi); del_timer_sync(&sbi->s_err_report); ext4_release_system_zone(sb); @@ -808,18 +817,12 @@ static void ext4_put_super(struct super_block *sb) ext4_xattr_put_super(sb); if (!(sb->s_flags & MS_RDONLY)) { - EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); + ext4_clear_feature_journal_needs_recovery(sb); es->s_state = cpu_to_le16(sbi->s_mount_state); } if (!(sb->s_flags & MS_RDONLY)) ext4_commit_super(sb, 1); - if (sbi->s_proc) { - remove_proc_entry("options", sbi->s_proc); - remove_proc_entry(sb->s_id, ext4_proc_root); - } - kobject_del(&sbi->s_kobj); - for (i = 0; i < sbi->s_gdb_count; i++) brelse(sbi->s_group_desc[i]); kvfree(sbi->s_group_desc); @@ -1058,7 +1061,7 @@ static int bdev_try_to_free_page(struct super_block *sb, struct page *page, return 0; if (journal) return jbd2_journal_try_to_free_buffers(journal, page, - wait & ~__GFP_WAIT); + wait & ~__GFP_DIRECT_RECLAIM); return try_to_free_buffers(page); } @@ -1288,7 +1291,7 @@ static int set_qf_name(struct super_block *sb, int qtype, substring_t *args) "quota options when quota turned on"); return -1; } - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) { + if (ext4_has_feature_quota(sb)) { ext4_msg(sb, KERN_ERR, "Cannot set journaled quota options " "when QUOTA feature is enabled"); return -1; @@ -1381,10 +1384,10 @@ static const struct mount_opts { {Opt_nojournal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM, MOPT_EXT4_ONLY | MOPT_CLEAR}, {Opt_journal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM, - MOPT_EXT4_ONLY | MOPT_SET}, + MOPT_EXT4_ONLY | MOPT_SET | MOPT_EXPLICIT}, {Opt_journal_async_commit, (EXT4_MOUNT_JOURNAL_ASYNC_COMMIT | EXT4_MOUNT_JOURNAL_CHECKSUM), - MOPT_EXT4_ONLY | MOPT_SET}, + MOPT_EXT4_ONLY | MOPT_SET | MOPT_EXPLICIT}, {Opt_noload, EXT4_MOUNT_NOLOAD, MOPT_NO_EXT2 | MOPT_SET}, {Opt_err_panic, EXT4_MOUNT_ERRORS_PANIC, MOPT_SET | MOPT_CLEAR_ERR}, {Opt_err_ro, EXT4_MOUNT_ERRORS_RO, MOPT_SET | MOPT_CLEAR_ERR}, @@ -1513,8 +1516,14 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token, return -1; if (args->from && (m->flags & MOPT_GTE0) && (arg < 0)) return -1; - if (m->flags & MOPT_EXPLICIT) - set_opt2(sb, EXPLICIT_DELALLOC); + if (m->flags & MOPT_EXPLICIT) { + if (m->mount_opt & EXT4_MOUNT_DELALLOC) { + set_opt2(sb, EXPLICIT_DELALLOC); + } else if (m->mount_opt & EXT4_MOUNT_JOURNAL_CHECKSUM) { + set_opt2(sb, EXPLICIT_JOURNAL_CHECKSUM); + } else + return -1; + } if (m->flags & MOPT_CLEAR_ERR) clear_opt(sb, ERRORS_MASK); if (token == Opt_noquota && sb_any_quota_loaded(sb)) { @@ -1647,8 +1656,7 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token, "quota options when quota turned on"); return -1; } - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_QUOTA)) { + if (ext4_has_feature_quota(sb)) { ext4_msg(sb, KERN_ERR, "Cannot set journaled quota options " "when QUOTA feature is enabled"); @@ -1707,7 +1715,7 @@ static int parse_options(char *options, struct super_block *sb, return 0; } #ifdef CONFIG_QUOTA - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA) && + if (ext4_has_feature_quota(sb) && (test_opt(sb, USRQUOTA) || test_opt(sb, GRPQUOTA))) { ext4_msg(sb, KERN_ERR, "Cannot set quota options when QUOTA " "feature is enabled"); @@ -1880,7 +1888,7 @@ static int ext4_show_options(struct seq_file *seq, struct dentry *root) return _ext4_show_options(seq, root->d_sb, 0); } -static int options_seq_show(struct seq_file *seq, void *offset) +int ext4_seq_options_show(struct seq_file *seq, void *offset) { struct super_block *sb = seq->private; int rc; @@ -1891,19 +1899,6 @@ static int options_seq_show(struct seq_file *seq, void *offset) return rc; } -static int options_open_fs(struct inode *inode, struct file *file) -{ - return single_open(file, options_seq_show, PDE_DATA(inode)); -} - -static const struct file_operations ext4_seq_options_fops = { - .owner = THIS_MODULE, - .open = options_open_fs, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es, int read_only) { @@ -1944,7 +1939,7 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es, es->s_mtime = cpu_to_le32(get_seconds()); ext4_update_dynamic_rev(sb); if (sbi->s_journal) - EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); + ext4_set_feature_journal_needs_recovery(sb); ext4_commit_super(sb, 1); done: @@ -2027,12 +2022,13 @@ failed: return 0; } -static __le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 block_group, +static __le16 ext4_group_desc_csum(struct super_block *sb, __u32 block_group, struct ext4_group_desc *gdp) { int offset; __u16 crc = 0; __le32 le_group = cpu_to_le32(block_group); + struct ext4_sb_info *sbi = EXT4_SB(sb); if (ext4_has_metadata_csum(sbi->s_sb)) { /* Use new metadata_csum algorithm */ @@ -2052,8 +2048,7 @@ static __le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 block_group, } /* old crc16 code */ - if (!(sbi->s_es->s_feature_ro_compat & - cpu_to_le32(EXT4_FEATURE_RO_COMPAT_GDT_CSUM))) + if (!ext4_has_feature_gdt_csum(sb)) return 0; offset = offsetof(struct ext4_group_desc, bg_checksum); @@ -2063,8 +2058,7 @@ static __le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 block_group, crc = crc16(crc, (__u8 *)gdp, offset); offset += sizeof(gdp->bg_checksum); /* skip checksum */ /* for checksum of struct ext4_group_desc do the rest...*/ - if ((sbi->s_es->s_feature_incompat & - cpu_to_le32(EXT4_FEATURE_INCOMPAT_64BIT)) && + if (ext4_has_feature_64bit(sb) && offset < le16_to_cpu(sbi->s_es->s_desc_size)) crc = crc16(crc, (__u8 *)gdp + offset, le16_to_cpu(sbi->s_es->s_desc_size) - @@ -2078,8 +2072,7 @@ int ext4_group_desc_csum_verify(struct super_block *sb, __u32 block_group, struct ext4_group_desc *gdp) { if (ext4_has_group_desc_csum(sb) && - (gdp->bg_checksum != ext4_group_desc_csum(EXT4_SB(sb), - block_group, gdp))) + (gdp->bg_checksum != ext4_group_desc_csum(sb, block_group, gdp))) return 0; return 1; @@ -2090,7 +2083,7 @@ void ext4_group_desc_csum_set(struct super_block *sb, __u32 block_group, { if (!ext4_has_group_desc_csum(sb)) return; - gdp->bg_checksum = ext4_group_desc_csum(EXT4_SB(sb), block_group, gdp); + gdp->bg_checksum = ext4_group_desc_csum(sb, block_group, gdp); } /* Called at mount-time, super-block is locked */ @@ -2106,7 +2099,7 @@ static int ext4_check_descriptors(struct super_block *sb, int flexbg_flag = 0; ext4_group_t i, grp = sbi->s_groups_count; - if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) + if (ext4_has_feature_flex_bg(sb)) flexbg_flag = 1; ext4_debug("Checking group descriptors"); @@ -2150,7 +2143,7 @@ static int ext4_check_descriptors(struct super_block *sb, if (!ext4_group_desc_csum_verify(sb, i, gdp)) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Checksum for group %u failed (%u!=%u)", - i, le16_to_cpu(ext4_group_desc_csum(sbi, i, + i, le16_to_cpu(ext4_group_desc_csum(sb, i, gdp)), le16_to_cpu(gdp->bg_checksum)); if (!(sb->s_flags & MS_RDONLY)) { ext4_unlock_group(sb, i); @@ -2413,8 +2406,7 @@ static ext4_fsblk_t descriptor_loc(struct super_block *sb, first_meta_bg = le32_to_cpu(sbi->s_es->s_first_meta_bg); - if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_META_BG) || - nr < first_meta_bg) + if (!ext4_has_feature_meta_bg(sb) || nr < first_meta_bg) return logical_sb_block + nr + 1; bg = sbi->s_desc_per_block * nr; if (ext4_bg_has_super(sb, bg)) @@ -2470,335 +2462,6 @@ static unsigned long ext4_get_stripe_size(struct ext4_sb_info *sbi) return ret; } -/* sysfs supprt */ - -struct ext4_attr { - struct attribute attr; - ssize_t (*show)(struct ext4_attr *, struct ext4_sb_info *, char *); - ssize_t (*store)(struct ext4_attr *, struct ext4_sb_info *, - const char *, size_t); - union { - int offset; - int deprecated_val; - } u; -}; - -static int parse_strtoull(const char *buf, - unsigned long long max, unsigned long long *value) -{ - int ret; - - ret = kstrtoull(skip_spaces(buf), 0, value); - if (!ret && *value > max) - ret = -EINVAL; - return ret; -} - -static ssize_t delayed_allocation_blocks_show(struct ext4_attr *a, - struct ext4_sb_info *sbi, - char *buf) -{ - return snprintf(buf, PAGE_SIZE, "%llu\n", - (s64) EXT4_C2B(sbi, - percpu_counter_sum(&sbi->s_dirtyclusters_counter))); -} - -static ssize_t session_write_kbytes_show(struct ext4_attr *a, - struct ext4_sb_info *sbi, char *buf) -{ - struct super_block *sb = sbi->s_buddy_cache->i_sb; - - if (!sb->s_bdev->bd_part) - return snprintf(buf, PAGE_SIZE, "0\n"); - return snprintf(buf, PAGE_SIZE, "%lu\n", - (part_stat_read(sb->s_bdev->bd_part, sectors[1]) - - sbi->s_sectors_written_start) >> 1); -} - -static ssize_t lifetime_write_kbytes_show(struct ext4_attr *a, - struct ext4_sb_info *sbi, char *buf) -{ - struct super_block *sb = sbi->s_buddy_cache->i_sb; - - if (!sb->s_bdev->bd_part) - return snprintf(buf, PAGE_SIZE, "0\n"); - return snprintf(buf, PAGE_SIZE, "%llu\n", - (unsigned long long)(sbi->s_kbytes_written + - ((part_stat_read(sb->s_bdev->bd_part, sectors[1]) - - EXT4_SB(sb)->s_sectors_written_start) >> 1))); -} - -static ssize_t inode_readahead_blks_store(struct ext4_attr *a, - struct ext4_sb_info *sbi, - const char *buf, size_t count) -{ - unsigned long t; - int ret; - - ret = kstrtoul(skip_spaces(buf), 0, &t); - if (ret) - return ret; - - if (t && (!is_power_of_2(t) || t > 0x40000000)) - return -EINVAL; - - sbi->s_inode_readahead_blks = t; - return count; -} - -static ssize_t sbi_ui_show(struct ext4_attr *a, - struct ext4_sb_info *sbi, char *buf) -{ - unsigned int *ui = (unsigned int *) (((char *) sbi) + a->u.offset); - - return snprintf(buf, PAGE_SIZE, "%u\n", *ui); -} - -static ssize_t sbi_ui_store(struct ext4_attr *a, - struct ext4_sb_info *sbi, - const char *buf, size_t count) -{ - unsigned int *ui = (unsigned int *) (((char *) sbi) + a->u.offset); - unsigned long t; - int ret; - - ret = kstrtoul(skip_spaces(buf), 0, &t); - if (ret) - return ret; - *ui = t; - return count; -} - -static ssize_t es_ui_show(struct ext4_attr *a, - struct ext4_sb_info *sbi, char *buf) -{ - - unsigned int *ui = (unsigned int *) (((char *) sbi->s_es) + - a->u.offset); - - return snprintf(buf, PAGE_SIZE, "%u\n", *ui); -} - -static ssize_t reserved_clusters_show(struct ext4_attr *a, - struct ext4_sb_info *sbi, char *buf) -{ - return snprintf(buf, PAGE_SIZE, "%llu\n", - (unsigned long long) atomic64_read(&sbi->s_resv_clusters)); -} - -static ssize_t reserved_clusters_store(struct ext4_attr *a, - struct ext4_sb_info *sbi, - const char *buf, size_t count) -{ - unsigned long long val; - int ret; - - if (parse_strtoull(buf, -1ULL, &val)) - return -EINVAL; - ret = ext4_reserve_clusters(sbi, val); - - return ret ? ret : count; -} - -static ssize_t trigger_test_error(struct ext4_attr *a, - struct ext4_sb_info *sbi, - const char *buf, size_t count) -{ - int len = count; - - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; - - if (len && buf[len-1] == '\n') - len--; - - if (len) - ext4_error(sbi->s_sb, "%.*s", len, buf); - return count; -} - -static ssize_t sbi_deprecated_show(struct ext4_attr *a, - struct ext4_sb_info *sbi, char *buf) -{ - return snprintf(buf, PAGE_SIZE, "%d\n", a->u.deprecated_val); -} - -#define EXT4_ATTR_OFFSET(_name,_mode,_show,_store,_elname) \ -static struct ext4_attr ext4_attr_##_name = { \ - .attr = {.name = __stringify(_name), .mode = _mode }, \ - .show = _show, \ - .store = _store, \ - .u = { \ - .offset = offsetof(struct ext4_sb_info, _elname),\ - }, \ -} - -#define EXT4_ATTR_OFFSET_ES(_name,_mode,_show,_store,_elname) \ -static struct ext4_attr ext4_attr_##_name = { \ - .attr = {.name = __stringify(_name), .mode = _mode }, \ - .show = _show, \ - .store = _store, \ - .u = { \ - .offset = offsetof(struct ext4_super_block, _elname), \ - }, \ -} - -#define EXT4_ATTR(name, mode, show, store) \ -static struct ext4_attr ext4_attr_##name = __ATTR(name, mode, show, store) - -#define EXT4_INFO_ATTR(name) EXT4_ATTR(name, 0444, NULL, NULL) -#define EXT4_RO_ATTR(name) EXT4_ATTR(name, 0444, name##_show, NULL) -#define EXT4_RW_ATTR(name) EXT4_ATTR(name, 0644, name##_show, name##_store) - -#define EXT4_RO_ATTR_ES_UI(name, elname) \ - EXT4_ATTR_OFFSET_ES(name, 0444, es_ui_show, NULL, elname) -#define EXT4_RW_ATTR_SBI_UI(name, elname) \ - EXT4_ATTR_OFFSET(name, 0644, sbi_ui_show, sbi_ui_store, elname) - -#define ATTR_LIST(name) &ext4_attr_##name.attr -#define EXT4_DEPRECATED_ATTR(_name, _val) \ -static struct ext4_attr ext4_attr_##_name = { \ - .attr = {.name = __stringify(_name), .mode = 0444 }, \ - .show = sbi_deprecated_show, \ - .u = { \ - .deprecated_val = _val, \ - }, \ -} - -EXT4_RO_ATTR(delayed_allocation_blocks); -EXT4_RO_ATTR(session_write_kbytes); -EXT4_RO_ATTR(lifetime_write_kbytes); -EXT4_RW_ATTR(reserved_clusters); -EXT4_ATTR_OFFSET(inode_readahead_blks, 0644, sbi_ui_show, - inode_readahead_blks_store, s_inode_readahead_blks); -EXT4_RW_ATTR_SBI_UI(inode_goal, s_inode_goal); -EXT4_RW_ATTR_SBI_UI(mb_stats, s_mb_stats); -EXT4_RW_ATTR_SBI_UI(mb_max_to_scan, s_mb_max_to_scan); -EXT4_RW_ATTR_SBI_UI(mb_min_to_scan, s_mb_min_to_scan); -EXT4_RW_ATTR_SBI_UI(mb_order2_req, s_mb_order2_reqs); -EXT4_RW_ATTR_SBI_UI(mb_stream_req, s_mb_stream_request); -EXT4_RW_ATTR_SBI_UI(mb_group_prealloc, s_mb_group_prealloc); -EXT4_DEPRECATED_ATTR(max_writeback_mb_bump, 128); -EXT4_RW_ATTR_SBI_UI(extent_max_zeroout_kb, s_extent_max_zeroout_kb); -EXT4_ATTR(trigger_fs_error, 0200, NULL, trigger_test_error); -EXT4_RW_ATTR_SBI_UI(err_ratelimit_interval_ms, s_err_ratelimit_state.interval); -EXT4_RW_ATTR_SBI_UI(err_ratelimit_burst, s_err_ratelimit_state.burst); -EXT4_RW_ATTR_SBI_UI(warning_ratelimit_interval_ms, s_warning_ratelimit_state.interval); -EXT4_RW_ATTR_SBI_UI(warning_ratelimit_burst, s_warning_ratelimit_state.burst); -EXT4_RW_ATTR_SBI_UI(msg_ratelimit_interval_ms, s_msg_ratelimit_state.interval); -EXT4_RW_ATTR_SBI_UI(msg_ratelimit_burst, s_msg_ratelimit_state.burst); -EXT4_RO_ATTR_ES_UI(errors_count, s_error_count); -EXT4_RO_ATTR_ES_UI(first_error_time, s_first_error_time); -EXT4_RO_ATTR_ES_UI(last_error_time, s_last_error_time); - -static struct attribute *ext4_attrs[] = { - ATTR_LIST(delayed_allocation_blocks), - ATTR_LIST(session_write_kbytes), - ATTR_LIST(lifetime_write_kbytes), - ATTR_LIST(reserved_clusters), - ATTR_LIST(inode_readahead_blks), - ATTR_LIST(inode_goal), - ATTR_LIST(mb_stats), - ATTR_LIST(mb_max_to_scan), - ATTR_LIST(mb_min_to_scan), - ATTR_LIST(mb_order2_req), - ATTR_LIST(mb_stream_req), - ATTR_LIST(mb_group_prealloc), - ATTR_LIST(max_writeback_mb_bump), - ATTR_LIST(extent_max_zeroout_kb), - ATTR_LIST(trigger_fs_error), - ATTR_LIST(err_ratelimit_interval_ms), - ATTR_LIST(err_ratelimit_burst), - ATTR_LIST(warning_ratelimit_interval_ms), - ATTR_LIST(warning_ratelimit_burst), - ATTR_LIST(msg_ratelimit_interval_ms), - ATTR_LIST(msg_ratelimit_burst), - ATTR_LIST(errors_count), - ATTR_LIST(first_error_time), - ATTR_LIST(last_error_time), - NULL, -}; - -/* Features this copy of ext4 supports */ -EXT4_INFO_ATTR(lazy_itable_init); -EXT4_INFO_ATTR(batched_discard); -EXT4_INFO_ATTR(meta_bg_resize); -EXT4_INFO_ATTR(encryption); - -static struct attribute *ext4_feat_attrs[] = { - ATTR_LIST(lazy_itable_init), - ATTR_LIST(batched_discard), - ATTR_LIST(meta_bg_resize), - ATTR_LIST(encryption), - NULL, -}; - -static ssize_t ext4_attr_show(struct kobject *kobj, - struct attribute *attr, char *buf) -{ - struct ext4_sb_info *sbi = container_of(kobj, struct ext4_sb_info, - s_kobj); - struct ext4_attr *a = container_of(attr, struct ext4_attr, attr); - - return a->show ? a->show(a, sbi, buf) : 0; -} - -static ssize_t ext4_attr_store(struct kobject *kobj, - struct attribute *attr, - const char *buf, size_t len) -{ - struct ext4_sb_info *sbi = container_of(kobj, struct ext4_sb_info, - s_kobj); - struct ext4_attr *a = container_of(attr, struct ext4_attr, attr); - - return a->store ? a->store(a, sbi, buf, len) : 0; -} - -static void ext4_sb_release(struct kobject *kobj) -{ - struct ext4_sb_info *sbi = container_of(kobj, struct ext4_sb_info, - s_kobj); - complete(&sbi->s_kobj_unregister); -} - -static const struct sysfs_ops ext4_attr_ops = { - .show = ext4_attr_show, - .store = ext4_attr_store, -}; - -static struct kobj_type ext4_ktype = { - .default_attrs = ext4_attrs, - .sysfs_ops = &ext4_attr_ops, - .release = ext4_sb_release, -}; - -static void ext4_feat_release(struct kobject *kobj) -{ - complete(&ext4_feat->f_kobj_unregister); -} - -static ssize_t ext4_feat_show(struct kobject *kobj, - struct attribute *attr, char *buf) -{ - return snprintf(buf, PAGE_SIZE, "supported\n"); -} - -/* - * We can not use ext4_attr_show/store because it relies on the kobject - * being embedded in the ext4_sb_info structure which is definitely not - * true in this case. - */ -static const struct sysfs_ops ext4_feat_ops = { - .show = ext4_feat_show, - .store = NULL, -}; - -static struct kobj_type ext4_feat_ktype = { - .default_attrs = ext4_feat_attrs, - .sysfs_ops = &ext4_feat_ops, - .release = ext4_feat_release, -}; - /* * Check whether this filesystem can be mounted based on * the features present and the RDONLY/RDWR mount requested. @@ -2807,7 +2470,7 @@ static struct kobj_type ext4_feat_ktype = { */ static int ext4_feature_set_ok(struct super_block *sb, int readonly) { - if (EXT4_HAS_INCOMPAT_FEATURE(sb, ~EXT4_FEATURE_INCOMPAT_SUPP)) { + if (ext4_has_unknown_ext4_incompat_features(sb)) { ext4_msg(sb, KERN_ERR, "Couldn't mount because of " "unsupported optional features (%x)", @@ -2819,14 +2482,14 @@ static int ext4_feature_set_ok(struct super_block *sb, int readonly) if (readonly) return 1; - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_READONLY)) { + if (ext4_has_feature_readonly(sb)) { ext4_msg(sb, KERN_INFO, "filesystem is read-only"); sb->s_flags |= MS_RDONLY; return 1; } /* Check that feature set is OK for a read-write mount */ - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, ~EXT4_FEATURE_RO_COMPAT_SUPP)) { + if (ext4_has_unknown_ext4_ro_compat_features(sb)) { ext4_msg(sb, KERN_ERR, "couldn't mount RDWR because of " "unsupported optional features (%x)", (le32_to_cpu(EXT4_SB(sb)->s_es->s_feature_ro_compat) & @@ -2837,7 +2500,7 @@ static int ext4_feature_set_ok(struct super_block *sb, int readonly) * Large file size enabled file system can only be mounted * read-write on 32-bit systems if kernel is built with CONFIG_LBDAF */ - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_HUGE_FILE)) { + if (ext4_has_feature_huge_file(sb)) { if (sizeof(blkcnt_t) < sizeof(u64)) { ext4_msg(sb, KERN_ERR, "Filesystem with huge files " "cannot be mounted RDWR without " @@ -2845,8 +2508,7 @@ static int ext4_feature_set_ok(struct super_block *sb, int readonly) return 0; } } - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_BIGALLOC) && - !EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) { + if (ext4_has_feature_bigalloc(sb) && !ext4_has_feature_extents(sb)) { ext4_msg(sb, KERN_ERR, "Can't support bigalloc feature without " "extents feature\n"); @@ -2854,8 +2516,7 @@ static int ext4_feature_set_ok(struct super_block *sb, int readonly) } #ifndef CONFIG_QUOTA - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA) && - !readonly) { + if (ext4_has_feature_quota(sb) && !readonly) { ext4_msg(sb, KERN_ERR, "Filesystem with quota feature cannot be mounted RDWR " "without CONFIG_QUOTA"); @@ -3312,7 +2973,7 @@ static int count_overhead(struct super_block *sb, ext4_group_t grp, ext4_group_t i, ngroups = ext4_get_groups_count(sb); int s, j, count = 0; - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_BIGALLOC)) + if (!ext4_has_feature_bigalloc(sb)) return (ext4_bg_has_super(sb, grp) + ext4_bg_num_gdb(sb, grp) + sbi->s_itb_per_group + 2); @@ -3403,10 +3064,10 @@ int ext4_calculate_overhead(struct super_block *sb) return 0; } - -static ext4_fsblk_t ext4_calculate_resv_clusters(struct super_block *sb) +static void ext4_set_resv_clusters(struct super_block *sb) { ext4_fsblk_t resv_clusters; + struct ext4_sb_info *sbi = EXT4_SB(sb); /* * There's no need to reserve anything when we aren't using extents. @@ -3414,8 +3075,8 @@ static ext4_fsblk_t ext4_calculate_resv_clusters(struct super_block *sb) * hole punching doesn't need new metadata... This is needed especially * to keep ext2/3 backward compatibility. */ - if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) - return 0; + if (!ext4_has_feature_extents(sb)) + return; /* * By default we reserve 2% or 4096 clusters, whichever is smaller. * This should cover the situations where we can not afford to run @@ -3424,26 +3085,13 @@ static ext4_fsblk_t ext4_calculate_resv_clusters(struct super_block *sb) * allocation would require 1, or 2 blocks, higher numbers are * very rare. */ - resv_clusters = ext4_blocks_count(EXT4_SB(sb)->s_es) >> - EXT4_SB(sb)->s_cluster_bits; + resv_clusters = (ext4_blocks_count(sbi->s_es) >> + sbi->s_cluster_bits); do_div(resv_clusters, 50); resv_clusters = min_t(ext4_fsblk_t, resv_clusters, 4096); - return resv_clusters; -} - - -static int ext4_reserve_clusters(struct ext4_sb_info *sbi, ext4_fsblk_t count) -{ - ext4_fsblk_t clusters = ext4_blocks_count(sbi->s_es) >> - sbi->s_cluster_bits; - - if (count >= clusters) - return -EINVAL; - - atomic64_set(&sbi->s_resv_clusters, count); - return 0; + atomic64_set(&sbi->s_resv_clusters, resv_clusters); } static int ext4_fill_super(struct super_block *sb, void *data, int silent) @@ -3526,9 +3174,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_kbytes_written = le64_to_cpu(es->s_kbytes_written); /* Warn if metadata_csum and gdt_csum are both set. */ - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM) && - EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_GDT_CSUM)) + if (ext4_has_feature_metadata_csum(sb) && + ext4_has_feature_gdt_csum(sb)) ext4_warning(sb, "metadata_csum and uninit_bg are " "redundant flags; please run fsck."); @@ -3541,8 +3188,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } /* Load the checksum driver */ - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) { + if (ext4_has_feature_metadata_csum(sb)) { sbi->s_chksum_driver = crypto_alloc_shash("crc32c", 0, 0); if (IS_ERR(sbi->s_chksum_driver)) { ext4_msg(sb, KERN_ERR, "Cannot load crc32c driver."); @@ -3557,11 +3203,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) ext4_msg(sb, KERN_ERR, "VFS: Found ext4 filesystem with " "invalid superblock checksum. Run e2fsck?"); silent = 1; + ret = -EFSBADCRC; goto cantfind_ext4; } /* Precompute checksum seed for all metadata */ - if (ext4_has_metadata_csum(sb)) + if (ext4_has_feature_csum_seed(sb)) + sbi->s_csum_seed = le32_to_cpu(es->s_checksum_seed); + else if (ext4_has_metadata_csum(sb)) sbi->s_csum_seed = ext4_chksum(sbi, ~0, es->s_uuid, sizeof(es->s_uuid)); @@ -3664,17 +3313,16 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) (test_opt(sb, POSIX_ACL) ? MS_POSIXACL : 0); if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV && - (EXT4_HAS_COMPAT_FEATURE(sb, ~0U) || - EXT4_HAS_RO_COMPAT_FEATURE(sb, ~0U) || - EXT4_HAS_INCOMPAT_FEATURE(sb, ~0U))) + (ext4_has_compat_features(sb) || + ext4_has_ro_compat_features(sb) || + ext4_has_incompat_features(sb))) ext4_msg(sb, KERN_WARNING, "feature flags set on rev 0 fs, " "running e2fsck is recommended"); if (es->s_creator_os == cpu_to_le32(EXT4_OS_HURD)) { set_opt2(sb, HURD_COMPAT); - if (EXT4_HAS_INCOMPAT_FEATURE(sb, - EXT4_FEATURE_INCOMPAT_64BIT)) { + if (ext4_has_feature_64bit(sb)) { ext4_msg(sb, KERN_ERR, "The Hurd can't support 64-bit file systems"); goto failed_mount; @@ -3732,8 +3380,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } } - if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_ENCRYPT) && - es->s_encryption_level) { + if (ext4_has_feature_encrypt(sb) && es->s_encryption_level) { ext4_msg(sb, KERN_ERR, "Unsupported encryption level %d", es->s_encryption_level); goto failed_mount; @@ -3765,8 +3412,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } } - has_huge_files = EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_HUGE_FILE); + has_huge_files = ext4_has_feature_huge_file(sb); sbi->s_bitmap_maxbytes = ext4_max_bitmap_size(sb->s_blocksize_bits, has_huge_files); sb->s_maxbytes = ext4_max_size(sb->s_blocksize_bits, has_huge_files); @@ -3790,7 +3436,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } sbi->s_desc_size = le16_to_cpu(es->s_desc_size); - if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_64BIT)) { + if (ext4_has_feature_64bit(sb)) { if (sbi->s_desc_size < EXT4_MIN_DESC_SIZE_64BIT || sbi->s_desc_size > EXT4_MAX_DESC_SIZE || !is_power_of_2(sbi->s_desc_size)) { @@ -3821,7 +3467,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) for (i = 0; i < 4; i++) sbi->s_hash_seed[i] = le32_to_cpu(es->s_hash_seed[i]); sbi->s_def_hash_version = es->s_def_hash_version; - if (EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_DIR_INDEX)) { + if (ext4_has_feature_dir_index(sb)) { i = le32_to_cpu(es->s_flags); if (i & EXT2_FLAGS_UNSIGNED_HASH) sbi->s_hash_unsigned = 3; @@ -3841,8 +3487,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) /* Handle clustersize */ clustersize = BLOCK_SIZE << le32_to_cpu(es->s_log_cluster_size); - has_bigalloc = EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_BIGALLOC); + has_bigalloc = ext4_has_feature_bigalloc(sb); if (has_bigalloc) { if (clustersize < blocksize) { ext4_msg(sb, KERN_ERR, @@ -3961,13 +3606,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount; } - if (ext4_proc_root) - sbi->s_proc = proc_mkdir(sb->s_id, ext4_proc_root); - - if (sbi->s_proc) - proc_create_data("options", S_IRUGO, sbi->s_proc, - &ext4_seq_options_fops, sb); - bgl_lock_init(sbi->s_blockgroup_lock); for (i = 0; i < db_count; i++) { @@ -3982,6 +3620,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } if (!ext4_check_descriptors(sb, &first_not_zeroed)) { ext4_msg(sb, KERN_ERR, "group descriptors corrupted!"); + ret = -EFSCORRUPTED; goto failed_mount2; } @@ -4007,7 +3646,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sb->s_xattr = ext4_xattr_handlers; #ifdef CONFIG_QUOTA sb->dq_op = &ext4_quota_operations; - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) + if (ext4_has_feature_quota(sb)) sb->s_qcop = &dquot_quotactl_sysfile_ops; else sb->s_qcop = &ext4_qctl_operations; @@ -4021,11 +3660,9 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sb->s_root = NULL; needs_recovery = (es->s_last_orphan != 0 || - EXT4_HAS_INCOMPAT_FEATURE(sb, - EXT4_FEATURE_INCOMPAT_RECOVER)); + ext4_has_feature_journal_needs_recovery(sb)); - if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_MMP) && - !(sb->s_flags & MS_RDONLY)) + if (ext4_has_feature_mmp(sb) && !(sb->s_flags & MS_RDONLY)) if (ext4_multi_mount_protect(sb, le64_to_cpu(es->s_mmp_block))) goto failed_mount3a; @@ -4033,23 +3670,47 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) * The first inode we look at is the journal inode. Don't try * root first: it may be modified in the journal! */ - if (!test_opt(sb, NOLOAD) && - EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL)) { + if (!test_opt(sb, NOLOAD) && ext4_has_feature_journal(sb)) { if (ext4_load_journal(sb, es, journal_devnum)) goto failed_mount3a; } else if (test_opt(sb, NOLOAD) && !(sb->s_flags & MS_RDONLY) && - EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER)) { + ext4_has_feature_journal_needs_recovery(sb)) { ext4_msg(sb, KERN_ERR, "required journal recovery " "suppressed and not mounted read-only"); goto failed_mount_wq; } else { + /* Nojournal mode, all journal mount options are illegal */ + if (test_opt2(sb, EXPLICIT_JOURNAL_CHECKSUM)) { + ext4_msg(sb, KERN_ERR, "can't mount with " + "journal_checksum, fs mounted w/o journal"); + goto failed_mount_wq; + } + if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) { + ext4_msg(sb, KERN_ERR, "can't mount with " + "journal_async_commit, fs mounted w/o journal"); + goto failed_mount_wq; + } + if (sbi->s_commit_interval != JBD2_DEFAULT_MAX_COMMIT_AGE*HZ) { + ext4_msg(sb, KERN_ERR, "can't mount with " + "commit=%lu, fs mounted w/o journal", + sbi->s_commit_interval / HZ); + goto failed_mount_wq; + } + if (EXT4_MOUNT_DATA_FLAGS & + (sbi->s_mount_opt ^ sbi->s_def_mount_opt)) { + ext4_msg(sb, KERN_ERR, "can't mount with " + "data=, fs mounted w/o journal"); + goto failed_mount_wq; + } + sbi->s_def_mount_opt &= EXT4_MOUNT_JOURNAL_CHECKSUM; + clear_opt(sb, JOURNAL_CHECKSUM); clear_opt(sb, DATA_FLAGS); sbi->s_journal = NULL; needs_recovery = 0; goto no_journal; } - if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_64BIT) && + if (ext4_has_feature_64bit(sb) && !jbd2_journal_set_features(EXT4_SB(sb)->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_64BIT)) { ext4_msg(sb, KERN_ERR, "Failed to set 64-bit journal feature"); @@ -4101,18 +3762,16 @@ no_journal: } } - if ((DUMMY_ENCRYPTION_ENABLED(sbi) || - EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_ENCRYPT)) && + if ((DUMMY_ENCRYPTION_ENABLED(sbi) || ext4_has_feature_encrypt(sb)) && (blocksize != PAGE_CACHE_SIZE)) { ext4_msg(sb, KERN_ERR, "Unsupported blocksize for fs encryption"); goto failed_mount_wq; } - if (DUMMY_ENCRYPTION_ENABLED(sbi) && - !(sb->s_flags & MS_RDONLY) && - !EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_ENCRYPT)) { - EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_ENCRYPT); + if (DUMMY_ENCRYPTION_ENABLED(sbi) && !(sb->s_flags & MS_RDONLY) && + !ext4_has_feature_encrypt(sb)) { + ext4_set_feature_encrypt(sb); ext4_commit_super(sb, 1); } @@ -4171,8 +3830,7 @@ no_journal: if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE) { sbi->s_want_extra_isize = sizeof(struct ext4_inode) - EXT4_GOOD_OLD_INODE_SIZE; - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE)) { + if (ext4_has_feature_extra_isize(sb)) { if (sbi->s_want_extra_isize < le16_to_cpu(es->s_want_extra_isize)) sbi->s_want_extra_isize = @@ -4192,12 +3850,7 @@ no_journal: "available"); } - err = ext4_reserve_clusters(sbi, ext4_calculate_resv_clusters(sb)); - if (err) { - ext4_msg(sb, KERN_ERR, "failed to reserve %llu clusters for " - "reserved pool", ext4_calculate_resv_clusters(sb)); - goto failed_mount4a; - } + ext4_set_resv_clusters(sb); err = ext4_setup_system_zone(sb); if (err) { @@ -4236,7 +3889,7 @@ no_journal: goto failed_mount6; } - if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) + if (ext4_has_feature_flex_bg(sb)) if (!ext4_fill_flex_info(sb)) { ext4_msg(sb, KERN_ERR, "unable to initialize " @@ -4248,17 +3901,13 @@ no_journal: if (err) goto failed_mount6; - sbi->s_kobj.kset = ext4_kset; - init_completion(&sbi->s_kobj_unregister); - err = kobject_init_and_add(&sbi->s_kobj, &ext4_ktype, NULL, - "%s", sb->s_id); + err = ext4_register_sysfs(sb); if (err) goto failed_mount7; #ifdef CONFIG_QUOTA /* Enable quota usage during mount. */ - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA) && - !(sb->s_flags & MS_RDONLY)) { + if (ext4_has_feature_quota(sb) && !(sb->s_flags & MS_RDONLY)) { err = ext4_enable_quotas(sb); if (err) goto failed_mount8; @@ -4313,7 +3962,7 @@ cantfind_ext4: #ifdef CONFIG_QUOTA failed_mount8: - kobject_del(&sbi->s_kobj); + ext4_unregister_sysfs(sb); #endif failed_mount7: ext4_unregister_li_request(sb); @@ -4353,10 +4002,6 @@ failed_mount2: failed_mount: if (sbi->s_chksum_driver) crypto_free_shash(sbi->s_chksum_driver); - if (sbi->s_proc) { - remove_proc_entry("options", sbi->s_proc); - remove_proc_entry(sb->s_id, ext4_proc_root); - } #ifdef CONFIG_QUOTA for (i = 0; i < EXT4_MAXQUOTAS; i++) kfree(sbi->s_qf_names[i]); @@ -4403,7 +4048,7 @@ static journal_t *ext4_get_journal(struct super_block *sb, struct inode *journal_inode; journal_t *journal; - BUG_ON(!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL)); + BUG_ON(!ext4_has_feature_journal(sb)); /* First, test for the existence of a valid inode on disk. Bad * things happen if we iget() an unused inode, as the subsequent @@ -4453,7 +4098,7 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb, struct ext4_super_block *es; struct block_device *bdev; - BUG_ON(!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL)); + BUG_ON(!ext4_has_feature_journal(sb)); bdev = ext4_blkdev_get(j_dev, sb); if (bdev == NULL) @@ -4545,7 +4190,7 @@ static int ext4_load_journal(struct super_block *sb, int err = 0; int really_read_only; - BUG_ON(!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL)); + BUG_ON(!ext4_has_feature_journal(sb)); if (journal_devnum && journal_devnum != le32_to_cpu(es->s_journal_dev)) { @@ -4562,7 +4207,7 @@ static int ext4_load_journal(struct super_block *sb, * crash? For recovery, we need to check in advance whether we * can get read-write access to the device. */ - if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER)) { + if (ext4_has_feature_journal_needs_recovery(sb)) { if (sb->s_flags & MS_RDONLY) { ext4_msg(sb, KERN_INFO, "INFO: recovery " "required on readonly filesystem"); @@ -4593,7 +4238,7 @@ static int ext4_load_journal(struct super_block *sb, if (!(journal->j_flags & JBD2_BARRIER)) ext4_msg(sb, KERN_INFO, "barriers disabled"); - if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER)) + if (!ext4_has_feature_journal_needs_recovery(sb)) err = jbd2_journal_wipe(journal, !really_read_only); if (!err) { char *save = kmalloc(EXT4_S_ERR_LEN, GFP_KERNEL); @@ -4707,7 +4352,7 @@ static void ext4_mark_recovery_complete(struct super_block *sb, { journal_t *journal = EXT4_SB(sb)->s_journal; - if (!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL)) { + if (!ext4_has_feature_journal(sb)) { BUG_ON(journal != NULL); return; } @@ -4715,9 +4360,9 @@ static void ext4_mark_recovery_complete(struct super_block *sb, if (jbd2_journal_flush(journal) < 0) goto out; - if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER) && + if (ext4_has_feature_journal_needs_recovery(sb) && sb->s_flags & MS_RDONLY) { - EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); + ext4_clear_feature_journal_needs_recovery(sb); ext4_commit_super(sb, 1); } @@ -4737,7 +4382,7 @@ static void ext4_clear_journal_err(struct super_block *sb, int j_errno; const char *errstr; - BUG_ON(!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL)); + BUG_ON(!ext4_has_feature_journal(sb)); journal = EXT4_SB(sb)->s_journal; @@ -4852,7 +4497,7 @@ static int ext4_freeze(struct super_block *sb) goto out; /* Journal blocked and flushed, clear needs_recovery flag. */ - EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); + ext4_clear_feature_journal_needs_recovery(sb); } error = ext4_commit_super(sb, 1); @@ -4874,7 +4519,7 @@ static int ext4_unfreeze(struct super_block *sb) if (EXT4_SB(sb)->s_journal) { /* Reset the needs_recovery flag before the fs is unlocked. */ - EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); + ext4_set_feature_journal_needs_recovery(sb); } ext4_commit_super(sb, 1); @@ -5027,8 +4672,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) ext4_mark_recovery_complete(sb, es); } else { /* Make sure we can mount this feature set readwrite */ - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_READONLY) || + if (ext4_has_feature_readonly(sb) || !ext4_feature_set_ok(sb, 0)) { err = -EROFS; goto restore_opts; @@ -5044,9 +4688,9 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) if (!ext4_group_desc_csum_verify(sb, g, gdp)) { ext4_msg(sb, KERN_ERR, "ext4_remount: Checksum for group %u failed (%u!=%u)", - g, le16_to_cpu(ext4_group_desc_csum(sbi, g, gdp)), + g, le16_to_cpu(ext4_group_desc_csum(sb, g, gdp)), le16_to_cpu(gdp->bg_checksum)); - err = -EINVAL; + err = -EFSBADCRC; goto restore_opts; } } @@ -5076,8 +4720,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) sbi->s_mount_state = le16_to_cpu(es->s_state); if (!ext4_setup_super(sb, es, 0)) sb->s_flags &= ~MS_RDONLY; - if (EXT4_HAS_INCOMPAT_FEATURE(sb, - EXT4_FEATURE_INCOMPAT_MMP)) + if (ext4_has_feature_mmp(sb)) if (ext4_multi_mount_protect(sb, le64_to_cpu(es->s_mmp_block))) { err = -EROFS; @@ -5110,8 +4753,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) if (enable_quota) { if (sb_any_quota_suspended(sb)) dquot_resume(sb, -1); - else if (EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_QUOTA)) { + else if (ext4_has_feature_quota(sb)) { err = ext4_enable_quotas(sb); if (err) goto restore_opts; @@ -5255,7 +4897,7 @@ static int ext4_mark_dquot_dirty(struct dquot *dquot) struct ext4_sb_info *sbi = EXT4_SB(sb); /* Are we journaling quotas? */ - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA) || + if (ext4_has_feature_quota(sb) || sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]) { dquot_mark_dquot_dirty(dquot); return ext4_write_dquot(dquot); @@ -5343,7 +4985,7 @@ static int ext4_quota_enable(struct super_block *sb, int type, int format_id, le32_to_cpu(EXT4_SB(sb)->s_es->s_grp_quota_inum) }; - BUG_ON(!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)); + BUG_ON(!ext4_has_feature_quota(sb)); if (!qf_inums[type]) return -EPERM; @@ -5537,11 +5179,11 @@ static inline void unregister_as_ext2(void) static inline int ext2_feature_set_ok(struct super_block *sb) { - if (EXT4_HAS_INCOMPAT_FEATURE(sb, ~EXT2_FEATURE_INCOMPAT_SUPP)) + if (ext4_has_unknown_ext2_incompat_features(sb)) return 0; if (sb->s_flags & MS_RDONLY) return 1; - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, ~EXT2_FEATURE_RO_COMPAT_SUPP)) + if (ext4_has_unknown_ext2_ro_compat_features(sb)) return 0; return 1; } @@ -5566,13 +5208,13 @@ static inline void unregister_as_ext3(void) static inline int ext3_feature_set_ok(struct super_block *sb) { - if (EXT4_HAS_INCOMPAT_FEATURE(sb, ~EXT3_FEATURE_INCOMPAT_SUPP)) + if (ext4_has_unknown_ext3_incompat_features(sb)) return 0; - if (!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL)) + if (!ext4_has_feature_journal(sb)) return 0; if (sb->s_flags & MS_RDONLY) return 1; - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, ~EXT3_FEATURE_RO_COMPAT_SUPP)) + if (ext4_has_unknown_ext3_ro_compat_features(sb)) return 0; return 1; } @@ -5586,37 +5228,6 @@ static struct file_system_type ext4_fs_type = { }; MODULE_ALIAS_FS("ext4"); -static int __init ext4_init_feat_adverts(void) -{ - struct ext4_features *ef; - int ret = -ENOMEM; - - ef = kzalloc(sizeof(struct ext4_features), GFP_KERNEL); - if (!ef) - goto out; - - ef->f_kobj.kset = ext4_kset; - init_completion(&ef->f_kobj_unregister); - ret = kobject_init_and_add(&ef->f_kobj, &ext4_feat_ktype, NULL, - "features"); - if (ret) { - kfree(ef); - goto out; - } - - ext4_feat = ef; - ret = 0; -out: - return ret; -} - -static void ext4_exit_feat_adverts(void) -{ - kobject_put(&ext4_feat->f_kobj); - wait_for_completion(&ext4_feat->f_kobj_unregister); - kfree(ext4_feat); -} - /* Shared across all ext4 file systems */ wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ]; struct mutex ext4__aio_mutex[EXT4_WQ_HASH_SZ]; @@ -5643,21 +5254,15 @@ static int __init ext4_init_fs(void) err = ext4_init_pageio(); if (err) - goto out7; + goto out5; err = ext4_init_system_zone(); if (err) - goto out6; - ext4_kset = kset_create_and_add("ext4", NULL, fs_kobj); - if (!ext4_kset) { - err = -ENOMEM; - goto out5; - } - ext4_proc_root = proc_mkdir("fs/ext4", NULL); + goto out4; - err = ext4_init_feat_adverts(); + err = ext4_init_sysfs(); if (err) - goto out4; + goto out3; err = ext4_init_mballoc(); if (err) @@ -5682,16 +5287,12 @@ out1: ext4_mballoc_ready = 0; ext4_exit_mballoc(); out2: - ext4_exit_feat_adverts(); -out4: - if (ext4_proc_root) - remove_proc_entry("fs/ext4", NULL); - kset_unregister(ext4_kset); -out5: + ext4_exit_sysfs(); +out3: ext4_exit_system_zone(); -out6: +out4: ext4_exit_pageio(); -out7: +out5: ext4_exit_es(); return err; @@ -5706,9 +5307,7 @@ static void __exit ext4_exit_fs(void) unregister_filesystem(&ext4_fs_type); destroy_inodecache(); ext4_exit_mballoc(); - ext4_exit_feat_adverts(); - remove_proc_entry("fs/ext4", NULL); - kset_unregister(ext4_kset); + ext4_exit_sysfs(); ext4_exit_system_zone(); ext4_exit_pageio(); ext4_exit_es(); diff --git a/fs/ext4/symlink.c b/fs/ext4/symlink.c index c677f2c..abe2401 100644 --- a/fs/ext4/symlink.c +++ b/fs/ext4/symlink.c @@ -57,7 +57,7 @@ static const char *ext4_encrypted_follow_link(struct dentry *dentry, void **cook sizeof(struct ext4_encrypted_symlink_data) - 1) > max_size) { /* Symlink data on the disk is corrupted */ - res = -EIO; + res = -EFSCORRUPTED; goto errout; } plen = (cstr.len < EXT4_FNAME_CRYPTO_DIGEST_SIZE*2) ? diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c new file mode 100644 index 0000000..1b57c72 --- /dev/null +++ b/fs/ext4/sysfs.c @@ -0,0 +1,448 @@ +/* + * linux/fs/ext4/sysfs.c + * + * Copyright (C) 1992, 1993, 1994, 1995 + * Remy Card (card@masi.ibp.fr) + * Theodore Ts'o (tytso@mit.edu) + * + */ + +#include <linux/time.h> +#include <linux/fs.h> +#include <linux/seq_file.h> +#include <linux/proc_fs.h> + +#include "ext4.h" +#include "ext4_jbd2.h" + +typedef enum { + attr_noop, + attr_delayed_allocation_blocks, + attr_session_write_kbytes, + attr_lifetime_write_kbytes, + attr_reserved_clusters, + attr_inode_readahead, + attr_trigger_test_error, + attr_feature, + attr_pointer_ui, + attr_pointer_atomic, +} attr_id_t; + +typedef enum { + ptr_explicit, + ptr_ext4_sb_info_offset, + ptr_ext4_super_block_offset, +} attr_ptr_t; + +static const char *proc_dirname = "fs/ext4"; +static struct proc_dir_entry *ext4_proc_root; + +struct ext4_attr { + struct attribute attr; + short attr_id; + short attr_ptr; + union { + int offset; + void *explicit_ptr; + } u; +}; + +static ssize_t session_write_kbytes_show(struct ext4_attr *a, + struct ext4_sb_info *sbi, char *buf) +{ + struct super_block *sb = sbi->s_buddy_cache->i_sb; + + if (!sb->s_bdev->bd_part) + return snprintf(buf, PAGE_SIZE, "0\n"); + return snprintf(buf, PAGE_SIZE, "%lu\n", + (part_stat_read(sb->s_bdev->bd_part, sectors[1]) - + sbi->s_sectors_written_start) >> 1); +} + +static ssize_t lifetime_write_kbytes_show(struct ext4_attr *a, + struct ext4_sb_info *sbi, char *buf) +{ + struct super_block *sb = sbi->s_buddy_cache->i_sb; + + if (!sb->s_bdev->bd_part) + return snprintf(buf, PAGE_SIZE, "0\n"); + return snprintf(buf, PAGE_SIZE, "%llu\n", + (unsigned long long)(sbi->s_kbytes_written + + ((part_stat_read(sb->s_bdev->bd_part, sectors[1]) - + EXT4_SB(sb)->s_sectors_written_start) >> 1))); +} + +static ssize_t inode_readahead_blks_store(struct ext4_attr *a, + struct ext4_sb_info *sbi, + const char *buf, size_t count) +{ + unsigned long t; + int ret; + + ret = kstrtoul(skip_spaces(buf), 0, &t); + if (ret) + return ret; + + if (t && (!is_power_of_2(t) || t > 0x40000000)) + return -EINVAL; + + sbi->s_inode_readahead_blks = t; + return count; +} + +static ssize_t reserved_clusters_store(struct ext4_attr *a, + struct ext4_sb_info *sbi, + const char *buf, size_t count) +{ + unsigned long long val; + ext4_fsblk_t clusters = (ext4_blocks_count(sbi->s_es) >> + sbi->s_cluster_bits); + int ret; + + ret = kstrtoull(skip_spaces(buf), 0, &val); + if (!ret || val >= clusters) + return -EINVAL; + + atomic64_set(&sbi->s_resv_clusters, val); + return count; +} + +static ssize_t trigger_test_error(struct ext4_attr *a, + struct ext4_sb_info *sbi, + const char *buf, size_t count) +{ + int len = count; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (len && buf[len-1] == '\n') + len--; + + if (len) + ext4_error(sbi->s_sb, "%.*s", len, buf); + return count; +} + +#define EXT4_ATTR(_name,_mode,_id) \ +static struct ext4_attr ext4_attr_##_name = { \ + .attr = {.name = __stringify(_name), .mode = _mode }, \ + .attr_id = attr_##_id, \ +} + +#define EXT4_ATTR_FUNC(_name,_mode) EXT4_ATTR(_name,_mode,_name) + +#define EXT4_ATTR_FEATURE(_name) EXT4_ATTR(_name, 0444, feature) + +#define EXT4_ATTR_OFFSET(_name,_mode,_id,_struct,_elname) \ +static struct ext4_attr ext4_attr_##_name = { \ + .attr = {.name = __stringify(_name), .mode = _mode }, \ + .attr_id = attr_##_id, \ + .attr_ptr = ptr_##_struct##_offset, \ + .u = { \ + .offset = offsetof(struct _struct, _elname),\ + }, \ +} + +#define EXT4_RO_ATTR_ES_UI(_name,_elname) \ + EXT4_ATTR_OFFSET(_name, 0444, pointer_ui, ext4_super_block, _elname) + +#define EXT4_RW_ATTR_SBI_UI(_name,_elname) \ + EXT4_ATTR_OFFSET(_name, 0644, pointer_ui, ext4_sb_info, _elname) + +#define EXT4_ATTR_PTR(_name,_mode,_id,_ptr) \ +static struct ext4_attr ext4_attr_##_name = { \ + .attr = {.name = __stringify(_name), .mode = _mode }, \ + .attr_id = attr_##_id, \ + .attr_ptr = ptr_explicit, \ + .u = { \ + .explicit_ptr = _ptr, \ + }, \ +} + +#define ATTR_LIST(name) &ext4_attr_##name.attr + +EXT4_ATTR_FUNC(delayed_allocation_blocks, 0444); +EXT4_ATTR_FUNC(session_write_kbytes, 0444); +EXT4_ATTR_FUNC(lifetime_write_kbytes, 0444); +EXT4_ATTR_FUNC(reserved_clusters, 0644); + +EXT4_ATTR_OFFSET(inode_readahead_blks, 0644, inode_readahead, + ext4_sb_info, s_inode_readahead_blks); +EXT4_RW_ATTR_SBI_UI(inode_goal, s_inode_goal); +EXT4_RW_ATTR_SBI_UI(mb_stats, s_mb_stats); +EXT4_RW_ATTR_SBI_UI(mb_max_to_scan, s_mb_max_to_scan); +EXT4_RW_ATTR_SBI_UI(mb_min_to_scan, s_mb_min_to_scan); +EXT4_RW_ATTR_SBI_UI(mb_order2_req, s_mb_order2_reqs); +EXT4_RW_ATTR_SBI_UI(mb_stream_req, s_mb_stream_request); +EXT4_RW_ATTR_SBI_UI(mb_group_prealloc, s_mb_group_prealloc); +EXT4_RW_ATTR_SBI_UI(extent_max_zeroout_kb, s_extent_max_zeroout_kb); +EXT4_ATTR(trigger_fs_error, 0200, trigger_test_error); +EXT4_RW_ATTR_SBI_UI(err_ratelimit_interval_ms, s_err_ratelimit_state.interval); +EXT4_RW_ATTR_SBI_UI(err_ratelimit_burst, s_err_ratelimit_state.burst); +EXT4_RW_ATTR_SBI_UI(warning_ratelimit_interval_ms, s_warning_ratelimit_state.interval); +EXT4_RW_ATTR_SBI_UI(warning_ratelimit_burst, s_warning_ratelimit_state.burst); +EXT4_RW_ATTR_SBI_UI(msg_ratelimit_interval_ms, s_msg_ratelimit_state.interval); +EXT4_RW_ATTR_SBI_UI(msg_ratelimit_burst, s_msg_ratelimit_state.burst); +EXT4_RO_ATTR_ES_UI(errors_count, s_error_count); +EXT4_RO_ATTR_ES_UI(first_error_time, s_first_error_time); +EXT4_RO_ATTR_ES_UI(last_error_time, s_last_error_time); + +static unsigned int old_bump_val = 128; +EXT4_ATTR_PTR(max_writeback_mb_bump, 0444, pointer_ui, &old_bump_val); + +static struct attribute *ext4_attrs[] = { + ATTR_LIST(delayed_allocation_blocks), + ATTR_LIST(session_write_kbytes), + ATTR_LIST(lifetime_write_kbytes), + ATTR_LIST(reserved_clusters), + ATTR_LIST(inode_readahead_blks), + ATTR_LIST(inode_goal), + ATTR_LIST(mb_stats), + ATTR_LIST(mb_max_to_scan), + ATTR_LIST(mb_min_to_scan), + ATTR_LIST(mb_order2_req), + ATTR_LIST(mb_stream_req), + ATTR_LIST(mb_group_prealloc), + ATTR_LIST(max_writeback_mb_bump), + ATTR_LIST(extent_max_zeroout_kb), + ATTR_LIST(trigger_fs_error), + ATTR_LIST(err_ratelimit_interval_ms), + ATTR_LIST(err_ratelimit_burst), + ATTR_LIST(warning_ratelimit_interval_ms), + ATTR_LIST(warning_ratelimit_burst), + ATTR_LIST(msg_ratelimit_interval_ms), + ATTR_LIST(msg_ratelimit_burst), + ATTR_LIST(errors_count), + ATTR_LIST(first_error_time), + ATTR_LIST(last_error_time), + NULL, +}; + +/* Features this copy of ext4 supports */ +EXT4_ATTR_FEATURE(lazy_itable_init); +EXT4_ATTR_FEATURE(batched_discard); +EXT4_ATTR_FEATURE(meta_bg_resize); +EXT4_ATTR_FEATURE(encryption); +EXT4_ATTR_FEATURE(metadata_csum_seed); + +static struct attribute *ext4_feat_attrs[] = { + ATTR_LIST(lazy_itable_init), + ATTR_LIST(batched_discard), + ATTR_LIST(meta_bg_resize), + ATTR_LIST(encryption), + ATTR_LIST(metadata_csum_seed), + NULL, +}; + +static void *calc_ptr(struct ext4_attr *a, struct ext4_sb_info *sbi) +{ + switch (a->attr_ptr) { + case ptr_explicit: + return a->u.explicit_ptr; + case ptr_ext4_sb_info_offset: + return (void *) (((char *) sbi) + a->u.offset); + case ptr_ext4_super_block_offset: + return (void *) (((char *) sbi->s_es) + a->u.offset); + } + return NULL; +} + +static ssize_t ext4_attr_show(struct kobject *kobj, + struct attribute *attr, char *buf) +{ + struct ext4_sb_info *sbi = container_of(kobj, struct ext4_sb_info, + s_kobj); + struct ext4_attr *a = container_of(attr, struct ext4_attr, attr); + void *ptr = calc_ptr(a, sbi); + + switch (a->attr_id) { + case attr_delayed_allocation_blocks: + return snprintf(buf, PAGE_SIZE, "%llu\n", + (s64) EXT4_C2B(sbi, + percpu_counter_sum(&sbi->s_dirtyclusters_counter))); + case attr_session_write_kbytes: + return session_write_kbytes_show(a, sbi, buf); + case attr_lifetime_write_kbytes: + return lifetime_write_kbytes_show(a, sbi, buf); + case attr_reserved_clusters: + return snprintf(buf, PAGE_SIZE, "%llu\n", + (unsigned long long) + atomic64_read(&sbi->s_resv_clusters)); + case attr_inode_readahead: + case attr_pointer_ui: + if (!ptr) + return 0; + return snprintf(buf, PAGE_SIZE, "%u\n", + *((unsigned int *) ptr)); + case attr_pointer_atomic: + if (!ptr) + return 0; + return snprintf(buf, PAGE_SIZE, "%d\n", + atomic_read((atomic_t *) ptr)); + case attr_feature: + return snprintf(buf, PAGE_SIZE, "supported\n"); + } + + return 0; +} + +static ssize_t ext4_attr_store(struct kobject *kobj, + struct attribute *attr, + const char *buf, size_t len) +{ + struct ext4_sb_info *sbi = container_of(kobj, struct ext4_sb_info, + s_kobj); + struct ext4_attr *a = container_of(attr, struct ext4_attr, attr); + void *ptr = calc_ptr(a, sbi); + unsigned long t; + int ret; + + switch (a->attr_id) { + case attr_reserved_clusters: + return reserved_clusters_store(a, sbi, buf, len); + case attr_pointer_ui: + if (!ptr) + return 0; + ret = kstrtoul(skip_spaces(buf), 0, &t); + if (ret) + return ret; + *((unsigned int *) ptr) = t; + return len; + case attr_inode_readahead: + return inode_readahead_blks_store(a, sbi, buf, len); + case attr_trigger_test_error: + return trigger_test_error(a, sbi, buf, len); + } + return 0; +} + +static void ext4_sb_release(struct kobject *kobj) +{ + struct ext4_sb_info *sbi = container_of(kobj, struct ext4_sb_info, + s_kobj); + complete(&sbi->s_kobj_unregister); +} + +static const struct sysfs_ops ext4_attr_ops = { + .show = ext4_attr_show, + .store = ext4_attr_store, +}; + +static struct kobj_type ext4_sb_ktype = { + .default_attrs = ext4_attrs, + .sysfs_ops = &ext4_attr_ops, + .release = ext4_sb_release, +}; + +static struct kobj_type ext4_ktype = { + .sysfs_ops = &ext4_attr_ops, +}; + +static struct kset ext4_kset = { + .kobj = {.ktype = &ext4_ktype}, +}; + +static struct kobj_type ext4_feat_ktype = { + .default_attrs = ext4_feat_attrs, + .sysfs_ops = &ext4_attr_ops, +}; + +static struct kobject ext4_feat = { + .kset = &ext4_kset, +}; + +#define PROC_FILE_SHOW_DEFN(name) \ +static int name##_open(struct inode *inode, struct file *file) \ +{ \ + return single_open(file, ext4_seq_##name##_show, PDE_DATA(inode)); \ +} \ +\ +const struct file_operations ext4_seq_##name##_fops = { \ + .owner = THIS_MODULE, \ + .open = name##_open, \ + .read = seq_read, \ + .llseek = seq_lseek, \ + .release = single_release, \ +} + +#define PROC_FILE_LIST(name) \ + { __stringify(name), &ext4_seq_##name##_fops } + +PROC_FILE_SHOW_DEFN(es_shrinker_info); +PROC_FILE_SHOW_DEFN(options); + +static struct ext4_proc_files { + const char *name; + const struct file_operations *fops; +} proc_files[] = { + PROC_FILE_LIST(options), + PROC_FILE_LIST(es_shrinker_info), + PROC_FILE_LIST(mb_groups), + { NULL, NULL }, +}; + +int ext4_register_sysfs(struct super_block *sb) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_proc_files *p; + int err; + + sbi->s_kobj.kset = &ext4_kset; + init_completion(&sbi->s_kobj_unregister); + err = kobject_init_and_add(&sbi->s_kobj, &ext4_sb_ktype, NULL, + "%s", sb->s_id); + if (err) + return err; + + if (ext4_proc_root) + sbi->s_proc = proc_mkdir(sb->s_id, ext4_proc_root); + + if (sbi->s_proc) { + for (p = proc_files; p->name; p++) + proc_create_data(p->name, S_IRUGO, sbi->s_proc, + p->fops, sb); + } + return 0; +} + +void ext4_unregister_sysfs(struct super_block *sb) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_proc_files *p; + + if (sbi->s_proc) { + for (p = proc_files; p->name; p++) + remove_proc_entry(p->name, sbi->s_proc); + remove_proc_entry(sb->s_id, ext4_proc_root); + } + kobject_del(&sbi->s_kobj); +} + +int __init ext4_init_sysfs(void) +{ + int ret; + + kobject_set_name(&ext4_kset.kobj, "ext4"); + ext4_kset.kobj.parent = fs_kobj; + ret = kset_register(&ext4_kset); + if (ret) + return ret; + + ret = kobject_init_and_add(&ext4_feat, &ext4_feat_ktype, + NULL, "features"); + if (ret) + kset_unregister(&ext4_kset); + else + ext4_proc_root = proc_mkdir(proc_dirname, NULL); + return ret; +} + +void ext4_exit_sysfs(void) +{ + kobject_put(&ext4_feat); + kset_unregister(&ext4_kset); + remove_proc_entry(proc_dirname, NULL); + ext4_proc_root = NULL; +} + diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 16e28c0..984448c 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -195,7 +195,7 @@ ext4_xattr_check_names(struct ext4_xattr_entry *entry, void *end, while (!IS_LAST_ENTRY(e)) { struct ext4_xattr_entry *next = EXT4_XATTR_NEXT(e); if ((void *)next >= end) - return -EIO; + return -EFSCORRUPTED; e = next; } @@ -205,7 +205,7 @@ ext4_xattr_check_names(struct ext4_xattr_entry *entry, void *end, (void *)e + sizeof(__u32) || value_start + le16_to_cpu(entry->e_value_offs) + le32_to_cpu(entry->e_value_size) > end)) - return -EIO; + return -EFSCORRUPTED; entry = EXT4_XATTR_NEXT(entry); } @@ -222,9 +222,9 @@ ext4_xattr_check_block(struct inode *inode, struct buffer_head *bh) if (BHDR(bh)->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC) || BHDR(bh)->h_blocks != cpu_to_le32(1)) - return -EIO; + return -EFSCORRUPTED; if (!ext4_xattr_block_csum_verify(inode, bh->b_blocknr, BHDR(bh))) - return -EIO; + return -EFSBADCRC; error = ext4_xattr_check_names(BFIRST(bh), bh->b_data + bh->b_size, bh->b_data); if (!error) @@ -239,7 +239,7 @@ ext4_xattr_check_entry(struct ext4_xattr_entry *entry, size_t size) if (entry->e_value_block != 0 || value_size > size || le16_to_cpu(entry->e_value_offs) + value_size > size) - return -EIO; + return -EFSCORRUPTED; return 0; } @@ -266,7 +266,7 @@ ext4_xattr_find_entry(struct ext4_xattr_entry **pentry, int name_index, } *pentry = entry; if (!cmp && ext4_xattr_check_entry(entry, size)) - return -EIO; + return -EFSCORRUPTED; return cmp ? -ENODATA : 0; } @@ -297,13 +297,13 @@ ext4_xattr_block_get(struct inode *inode, int name_index, const char *name, bad_block: EXT4_ERROR_INODE(inode, "bad block %llu", EXT4_I(inode)->i_file_acl); - error = -EIO; + error = -EFSCORRUPTED; goto cleanup; } ext4_xattr_cache_insert(ext4_mb_cache, bh); entry = BFIRST(bh); error = ext4_xattr_find_entry(&entry, name_index, name, bh->b_size, 1); - if (error == -EIO) + if (error == -EFSCORRUPTED) goto bad_block; if (error) goto cleanup; @@ -445,7 +445,7 @@ ext4_xattr_block_list(struct dentry *dentry, char *buffer, size_t buffer_size) if (ext4_xattr_check_block(inode, bh)) { EXT4_ERROR_INODE(inode, "bad block %llu", EXT4_I(inode)->i_file_acl); - error = -EIO; + error = -EFSCORRUPTED; goto cleanup; } ext4_xattr_cache_insert(ext4_mb_cache, bh); @@ -525,12 +525,12 @@ errout: static void ext4_xattr_update_super_block(handle_t *handle, struct super_block *sb) { - if (EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_EXT_ATTR)) + if (ext4_has_feature_xattr(sb)) return; BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get_write_access"); if (ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh) == 0) { - EXT4_SET_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_EXT_ATTR); + ext4_set_feature_xattr(sb); ext4_handle_dirty_super(handle, sb); } } @@ -751,7 +751,7 @@ ext4_xattr_block_find(struct inode *inode, struct ext4_xattr_info *i, if (ext4_xattr_check_block(inode, bs->bh)) { EXT4_ERROR_INODE(inode, "bad block %llu", EXT4_I(inode)->i_file_acl); - error = -EIO; + error = -EFSCORRUPTED; goto cleanup; } /* Find the named attribute. */ @@ -811,7 +811,7 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode, bs->bh); } unlock_buffer(bs->bh); - if (error == -EIO) + if (error == -EFSCORRUPTED) goto bad_block; if (!error) error = ext4_handle_dirty_xattr_block(handle, @@ -855,7 +855,7 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode, } error = ext4_xattr_set_entry(i, s); - if (error == -EIO) + if (error == -EFSCORRUPTED) goto bad_block; if (error) goto cleanup; @@ -1314,7 +1314,7 @@ retry: if (ext4_xattr_check_block(inode, bh)) { EXT4_ERROR_INODE(inode, "bad block %llu", EXT4_I(inode)->i_file_acl); - error = -EIO; + error = -EFSCORRUPTED; goto cleanup; } base = BHDR(bh); @@ -1579,7 +1579,7 @@ ext4_xattr_cmp(struct ext4_xattr_header *header1, memcmp(entry1->e_name, entry2->e_name, entry1->e_name_len)) return 1; if (entry1->e_value_block != 0 || entry2->e_value_block != 0) - return -EIO; + return -EFSCORRUPTED; if (memcmp((char *)header1 + le16_to_cpu(entry1->e_value_offs), (char *)header2 + le16_to_cpu(entry2->e_value_offs), le32_to_cpu(entry1->e_value_size))) diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index c5a38e3..f661d80 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -47,7 +47,8 @@ repeat: /* * We guarantee no failure on the returned page. */ -struct page *get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index) +static struct page *__get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index, + bool is_meta) { struct address_space *mapping = META_MAPPING(sbi); struct page *page; @@ -58,6 +59,9 @@ struct page *get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index) .blk_addr = index, .encrypted_page = NULL, }; + + if (unlikely(!is_meta)) + fio.rw &= ~REQ_META; repeat: page = grab_cache_page(mapping, index); if (!page) { @@ -91,6 +95,17 @@ out: return page; } +struct page *get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index) +{ + return __get_meta_page(sbi, index, true); +} + +/* for POR only */ +struct page *get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index) +{ + return __get_meta_page(sbi, index, false); +} + bool is_valid_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type) { switch (type) { @@ -125,7 +140,8 @@ bool is_valid_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type) /* * Readahead CP/NAT/SIT/SSA pages */ -int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, int type) +int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, + int type, bool sync) { block_t prev_blk_addr = 0; struct page *page; @@ -133,10 +149,13 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, int type struct f2fs_io_info fio = { .sbi = sbi, .type = META, - .rw = READ_SYNC | REQ_META | REQ_PRIO, + .rw = sync ? (READ_SYNC | REQ_META | REQ_PRIO) : READA, .encrypted_page = NULL, }; + if (unlikely(type == META_POR)) + fio.rw &= ~REQ_META; + for (; nrpages-- > 0; blkno++) { if (!is_valid_blkaddr(sbi, blkno, type)) @@ -196,7 +215,7 @@ void ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index) f2fs_put_page(page, 0); if (readahead) - ra_meta_pages(sbi, index, MAX_BIO_BLOCKS(sbi), META_POR); + ra_meta_pages(sbi, index, MAX_BIO_BLOCKS(sbi), META_POR, true); } static int f2fs_write_meta_page(struct page *page, @@ -257,7 +276,7 @@ long sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type, long nr_to_write) { struct address_space *mapping = META_MAPPING(sbi); - pgoff_t index = 0, end = LONG_MAX; + pgoff_t index = 0, end = LONG_MAX, prev = LONG_MAX; struct pagevec pvec; long nwritten = 0; struct writeback_control wbc = { @@ -277,6 +296,13 @@ long sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type, for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; + if (prev == LONG_MAX) + prev = page->index - 1; + if (nr_to_write != LONG_MAX && page->index != prev + 1) { + pagevec_release(&pvec); + goto stop; + } + lock_page(page); if (unlikely(page->mapping != mapping)) { @@ -297,13 +323,14 @@ continue_unlock: break; } nwritten++; + prev = page->index; if (unlikely(nwritten >= nr_to_write)) break; } pagevec_release(&pvec); cond_resched(); } - +stop: if (nwritten) f2fs_submit_merged_bio(sbi, type, WRITE); @@ -495,7 +522,7 @@ int recover_orphan_inodes(struct f2fs_sb_info *sbi) start_blk = __start_cp_addr(sbi) + 1 + __cp_payload(sbi); orphan_blocks = __start_sum_addr(sbi) - 1 - __cp_payload(sbi); - ra_meta_pages(sbi, start_blk, orphan_blocks, META_CP); + ra_meta_pages(sbi, start_blk, orphan_blocks, META_CP, true); for (i = 0; i < orphan_blocks; i++) { struct page *page = get_meta_page(sbi, start_blk + i); @@ -1000,6 +1027,11 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) start_blk = __start_cp_addr(sbi); + /* need to wait for end_io results */ + wait_on_all_pages_writeback(sbi); + if (unlikely(f2fs_cp_error(sbi))) + return; + /* write out checkpoint buffer at block 0 */ update_meta_page(sbi, ckpt, start_blk++); @@ -1109,6 +1141,9 @@ void write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) if (cpc->reason == CP_RECOVERY) f2fs_msg(sbi->sb, KERN_NOTICE, "checkpoint: version = %llx", ckpt_ver); + + /* do checkpoint periodically */ + sbi->cp_expires = round_jiffies_up(jiffies + HZ * sbi->cp_interval); out: mutex_unlock(&sbi->cp_mutex); trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish checkpoint"); diff --git a/fs/f2fs/crypto_key.c b/fs/f2fs/crypto_key.c index 9f77de2..5de2d86 100644 --- a/fs/f2fs/crypto_key.c +++ b/fs/f2fs/crypto_key.c @@ -122,7 +122,7 @@ int _f2fs_get_encryption_info(struct inode *inode) struct key *keyring_key = NULL; struct f2fs_encryption_key *master_key; struct f2fs_encryption_context ctx; - struct user_key_payload *ukp; + const struct user_key_payload *ukp; struct crypto_ablkcipher *ctfm; const char *cipher_str; char raw_key[F2FS_MAX_KEY_SIZE]; @@ -199,7 +199,7 @@ retry: } crypt_info->ci_keyring_key = keyring_key; BUG_ON(keyring_key->type != &key_type_logon); - ukp = ((struct user_key_payload *)keyring_key->payload.data); + ukp = user_key_payload(keyring_key); if (ukp->datalen != sizeof(struct f2fs_encryption_key)) { res = -EINVAL; goto out; diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index a82abe9..972eab7 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -275,7 +275,8 @@ int f2fs_get_block(struct dnode_of_data *dn, pgoff_t index) return f2fs_reserve_block(dn, index); } -struct page *get_read_data_page(struct inode *inode, pgoff_t index, int rw) +struct page *get_read_data_page(struct inode *inode, pgoff_t index, + int rw, bool for_write) { struct address_space *mapping = inode->i_mapping; struct dnode_of_data dn; @@ -292,7 +293,7 @@ struct page *get_read_data_page(struct inode *inode, pgoff_t index, int rw) if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) return read_mapping_page(mapping, index, NULL); - page = grab_cache_page(mapping, index); + page = f2fs_grab_cache_page(mapping, index, for_write); if (!page) return ERR_PTR(-ENOMEM); @@ -352,7 +353,7 @@ struct page *find_data_page(struct inode *inode, pgoff_t index) return page; f2fs_put_page(page, 0); - page = get_read_data_page(inode, index, READ_SYNC); + page = get_read_data_page(inode, index, READ_SYNC, false); if (IS_ERR(page)) return page; @@ -372,12 +373,13 @@ struct page *find_data_page(struct inode *inode, pgoff_t index) * Because, the callers, functions in dir.c and GC, should be able to know * whether this page exists or not. */ -struct page *get_lock_data_page(struct inode *inode, pgoff_t index) +struct page *get_lock_data_page(struct inode *inode, pgoff_t index, + bool for_write) { struct address_space *mapping = inode->i_mapping; struct page *page; repeat: - page = get_read_data_page(inode, index, READ_SYNC); + page = get_read_data_page(inode, index, READ_SYNC, for_write); if (IS_ERR(page)) return page; @@ -411,7 +413,7 @@ struct page *get_new_data_page(struct inode *inode, struct dnode_of_data dn; int err; repeat: - page = grab_cache_page(mapping, index); + page = f2fs_grab_cache_page(mapping, index, true); if (!page) { /* * before exiting, we should make sure ipage will be released @@ -439,7 +441,7 @@ repeat: } else { f2fs_put_page(page, 1); - page = get_read_data_page(inode, index, READ_SYNC); + page = get_read_data_page(inode, index, READ_SYNC, true); if (IS_ERR(page)) goto repeat; @@ -447,9 +449,9 @@ repeat: lock_page(page); } got_it: - if (new_i_size && - i_size_read(inode) < ((index + 1) << PAGE_CACHE_SHIFT)) { - i_size_write(inode, ((index + 1) << PAGE_CACHE_SHIFT)); + if (new_i_size && i_size_read(inode) < + ((loff_t)(index + 1) << PAGE_CACHE_SHIFT)) { + i_size_write(inode, ((loff_t)(index + 1) << PAGE_CACHE_SHIFT)); /* Only the directory inode sets new_i_size */ set_inode_flag(F2FS_I(inode), FI_UPDATE_DIR); } @@ -489,8 +491,9 @@ alloc: /* update i_size */ fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) + dn->ofs_in_node; - if (i_size_read(dn->inode) < ((fofs + 1) << PAGE_CACHE_SHIFT)) - i_size_write(dn->inode, ((fofs + 1) << PAGE_CACHE_SHIFT)); + if (i_size_read(dn->inode) < ((loff_t)(fofs + 1) << PAGE_CACHE_SHIFT)) + i_size_write(dn->inode, + ((loff_t)(fofs + 1) << PAGE_CACHE_SHIFT)); /* direct IO doesn't use extent cache to maximize the performance */ f2fs_drop_largest_extent(dn->inode, fofs); @@ -523,6 +526,9 @@ static void __allocate_data_blocks(struct inode *inode, loff_t offset, while (dn.ofs_in_node < end_offset && len) { block_t blkaddr; + if (unlikely(f2fs_cp_error(sbi))) + goto sync_out; + blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node); if (blkaddr == NULL_ADDR || blkaddr == NEW_ADDR) { if (__allocate_data_block(&dn)) @@ -565,6 +571,7 @@ static int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map, { unsigned int maxblocks = map->m_len; struct dnode_of_data dn; + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); int mode = create ? ALLOC_NODE : LOOKUP_NODE_RA; pgoff_t pgofs, end_offset; int err = 0, ofs = 1; @@ -595,40 +602,40 @@ static int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map, err = 0; goto unlock_out; } - if (dn.data_blkaddr == NEW_ADDR) { - if (flag == F2FS_GET_BLOCK_BMAP) { - err = -ENOENT; - goto put_out; - } else if (flag == F2FS_GET_BLOCK_READ || - flag == F2FS_GET_BLOCK_DIO) { - goto put_out; + + if (dn.data_blkaddr == NEW_ADDR || dn.data_blkaddr == NULL_ADDR) { + if (create) { + if (unlikely(f2fs_cp_error(sbi))) { + err = -EIO; + goto put_out; + } + err = __allocate_data_block(&dn); + if (err) + goto put_out; + allocated = true; + map->m_flags = F2FS_MAP_NEW; + } else { + if (flag != F2FS_GET_BLOCK_FIEMAP || + dn.data_blkaddr != NEW_ADDR) { + if (flag == F2FS_GET_BLOCK_BMAP) + err = -ENOENT; + goto put_out; + } + + /* + * preallocated unwritten block should be mapped + * for fiemap. + */ + if (dn.data_blkaddr == NEW_ADDR) + map->m_flags = F2FS_MAP_UNWRITTEN; } - /* - * if it is in fiemap call path (flag = F2FS_GET_BLOCK_FIEMAP), - * mark it as mapped and unwritten block. - */ } - if (dn.data_blkaddr != NULL_ADDR) { - map->m_flags = F2FS_MAP_MAPPED; - map->m_pblk = dn.data_blkaddr; - if (dn.data_blkaddr == NEW_ADDR) - map->m_flags |= F2FS_MAP_UNWRITTEN; - } else if (create) { - err = __allocate_data_block(&dn); - if (err) - goto put_out; - allocated = true; - map->m_flags = F2FS_MAP_NEW | F2FS_MAP_MAPPED; - map->m_pblk = dn.data_blkaddr; - } else { - if (flag == F2FS_GET_BLOCK_BMAP) - err = -ENOENT; - goto put_out; - } + map->m_flags |= F2FS_MAP_MAPPED; + map->m_pblk = dn.data_blkaddr; + map->m_len = 1; end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode)); - map->m_len = 1; dn.ofs_in_node++; pgofs++; @@ -647,23 +654,35 @@ get_next: goto unlock_out; } - if (dn.data_blkaddr == NEW_ADDR && - flag != F2FS_GET_BLOCK_FIEMAP) - goto put_out; - end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode)); } if (maxblocks > map->m_len) { block_t blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node); - if (blkaddr == NULL_ADDR && create) { - err = __allocate_data_block(&dn); - if (err) - goto sync_out; - allocated = true; - map->m_flags |= F2FS_MAP_NEW; - blkaddr = dn.data_blkaddr; + + if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR) { + if (create) { + if (unlikely(f2fs_cp_error(sbi))) { + err = -EIO; + goto sync_out; + } + err = __allocate_data_block(&dn); + if (err) + goto sync_out; + allocated = true; + map->m_flags |= F2FS_MAP_NEW; + blkaddr = dn.data_blkaddr; + } else { + /* + * we only merge preallocated unwritten blocks + * for fiemap. + */ + if (flag != F2FS_GET_BLOCK_FIEMAP || + blkaddr != NEW_ADDR) + goto sync_out; + } } + /* Give more consecutive addresses for the readahead */ if ((map->m_pblk != NEW_ADDR && blkaddr == (map->m_pblk + ofs)) || @@ -752,6 +771,12 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, if (ret) return ret; + if (f2fs_has_inline_data(inode)) { + ret = f2fs_inline_data_fiemap(inode, fieinfo, start, len); + if (ret != -EAGAIN) + return ret; + } + mutex_lock(&inode->i_mutex); if (len >= isize) { @@ -903,7 +928,8 @@ static int f2fs_mpage_readpages(struct address_space *mapping, map.m_lblk = block_in_file; map.m_len = last_block - block_in_file; - if (f2fs_map_blocks(inode, &map, 0, false)) + if (f2fs_map_blocks(inode, &map, 0, + F2FS_GET_BLOCK_READ)) goto set_error_page; } got_it: @@ -936,21 +962,14 @@ submit_and_realloc: if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) { - struct page *cpage; ctx = f2fs_get_crypto_ctx(inode); if (IS_ERR(ctx)) goto set_error_page; /* wait the page to be moved by cleaning */ - cpage = find_lock_page( - META_MAPPING(F2FS_I_SB(inode)), - block_nr); - if (cpage) { - f2fs_wait_on_page_writeback(cpage, - DATA); - f2fs_put_page(cpage, 1); - } + f2fs_wait_on_encrypted_page_writeback( + F2FS_I_SB(inode), block_nr); } bio = bio_alloc(GFP_KERNEL, @@ -1012,6 +1031,9 @@ static int f2fs_read_data_pages(struct file *file, struct list_head *pages, unsigned nr_pages) { struct inode *inode = file->f_mapping->host; + struct page *page = list_entry(pages->prev, struct page, lru); + + trace_f2fs_readpages(inode, page, nr_pages); /* If the file has inline data, skip readpages */ if (f2fs_has_inline_data(inode)) @@ -1041,6 +1063,11 @@ int do_write_data_page(struct f2fs_io_info *fio) } if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) { + + /* wait for GCed encrypted page writeback */ + f2fs_wait_on_encrypted_page_writeback(F2FS_I_SB(inode), + fio->blk_addr); + fio->encrypted_page = f2fs_encrypt(inode, fio->page); if (IS_ERR(fio->encrypted_page)) { err = PTR_ERR(fio->encrypted_page); @@ -1429,6 +1456,10 @@ put_next: f2fs_wait_on_page_writeback(page, DATA); + /* wait for GCed encrypted page writeback */ + if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) + f2fs_wait_on_encrypted_page_writeback(sbi, dn.data_blkaddr); + if (len == PAGE_CACHE_SIZE) goto out_update; if (PageUptodate(page)) @@ -1551,10 +1582,16 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, trace_f2fs_direct_IO_enter(inode, offset, count, iov_iter_rw(iter)); - if (iov_iter_rw(iter) == WRITE) + if (iov_iter_rw(iter) == WRITE) { __allocate_data_blocks(inode, offset, count); + if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) { + err = -EIO; + goto out; + } + } err = blockdev_direct_IO(iocb, inode, iter, offset, get_data_block_dio); +out: if (err < 0 && iov_iter_rw(iter) == WRITE) f2fs_write_failed(mapping, offset + count); @@ -1636,12 +1673,13 @@ static sector_t f2fs_bmap(struct address_space *mapping, sector_t block) { struct inode *inode = mapping->host; - /* we don't need to use inline_data strictly */ - if (f2fs_has_inline_data(inode)) { - int err = f2fs_convert_inline_inode(inode); - if (err) - return err; - } + if (f2fs_has_inline_data(inode)) + return 0; + + /* make sure allocating whole blocks */ + if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) + filemap_write_and_wait(mapping); + return generic_block_bmap(mapping, block, get_data_block_bmap); } diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c index d013d84..478e5d5 100644 --- a/fs/f2fs/debug.c +++ b/fs/f2fs/debug.c @@ -33,11 +33,11 @@ static void update_general_status(struct f2fs_sb_info *sbi) int i; /* validation check of the segment numbers */ - si->hit_largest = atomic_read(&sbi->read_hit_largest); - si->hit_cached = atomic_read(&sbi->read_hit_cached); - si->hit_rbtree = atomic_read(&sbi->read_hit_rbtree); + si->hit_largest = atomic64_read(&sbi->read_hit_largest); + si->hit_cached = atomic64_read(&sbi->read_hit_cached); + si->hit_rbtree = atomic64_read(&sbi->read_hit_rbtree); si->hit_total = si->hit_largest + si->hit_cached + si->hit_rbtree; - si->total_ext = atomic_read(&sbi->total_hit_ext); + si->total_ext = atomic64_read(&sbi->total_hit_ext); si->ext_tree = sbi->total_ext_tree; si->ext_node = atomic_read(&sbi->total_ext_node); si->ndirty_node = get_pages(sbi, F2FS_DIRTY_NODES); @@ -118,7 +118,7 @@ static void update_sit_info(struct f2fs_sb_info *sbi) } } dist = div_u64(MAIN_SECS(sbi) * hblks_per_sec * hblks_per_sec, 100); - si->bimodal = div_u64(bimodal, dist); + si->bimodal = div64_u64(bimodal, dist); if (si->dirty_count) si->avg_vblocks = div_u64(total_vblocks, ndirty); else @@ -198,9 +198,9 @@ get_cache: si->page_mem = 0; npages = NODE_MAPPING(sbi)->nrpages; - si->page_mem += npages << PAGE_CACHE_SHIFT; + si->page_mem += (unsigned long long)npages << PAGE_CACHE_SHIFT; npages = META_MAPPING(sbi)->nrpages; - si->page_mem += npages << PAGE_CACHE_SHIFT; + si->page_mem += (unsigned long long)npages << PAGE_CACHE_SHIFT; } static int stat_show(struct seq_file *s, void *v) @@ -283,12 +283,12 @@ static int stat_show(struct seq_file *s, void *v) seq_printf(s, " - node blocks : %d (%d)\n", si->node_blks, si->bg_node_blks); seq_puts(s, "\nExtent Cache:\n"); - seq_printf(s, " - Hit Count: L1-1:%d L1-2:%d L2:%d\n", + seq_printf(s, " - Hit Count: L1-1:%llu L1-2:%llu L2:%llu\n", si->hit_largest, si->hit_cached, si->hit_rbtree); - seq_printf(s, " - Hit Ratio: %d%% (%d / %d)\n", + seq_printf(s, " - Hit Ratio: %llu%% (%llu / %llu)\n", !si->total_ext ? 0 : - (si->hit_total * 100) / si->total_ext, + div64_u64(si->hit_total * 100, si->total_ext), si->hit_total, si->total_ext); seq_printf(s, " - Inner Struct Count: tree: %d, node: %d\n", si->ext_tree, si->ext_node); @@ -333,13 +333,13 @@ static int stat_show(struct seq_file *s, void *v) /* memory footprint */ update_mem_info(si->sbi); - seq_printf(s, "\nMemory: %u KB\n", + seq_printf(s, "\nMemory: %llu KB\n", (si->base_mem + si->cache_mem + si->page_mem) >> 10); - seq_printf(s, " - static: %u KB\n", + seq_printf(s, " - static: %llu KB\n", si->base_mem >> 10); - seq_printf(s, " - cached: %u KB\n", + seq_printf(s, " - cached: %llu KB\n", si->cache_mem >> 10); - seq_printf(s, " - paged : %u KB\n", + seq_printf(s, " - paged : %llu KB\n", si->page_mem >> 10); } mutex_unlock(&f2fs_stat_mutex); @@ -378,10 +378,10 @@ int f2fs_build_stats(struct f2fs_sb_info *sbi) si->sbi = sbi; sbi->stat_info = si; - atomic_set(&sbi->total_hit_ext, 0); - atomic_set(&sbi->read_hit_rbtree, 0); - atomic_set(&sbi->read_hit_largest, 0); - atomic_set(&sbi->read_hit_cached, 0); + atomic64_set(&sbi->total_hit_ext, 0); + atomic64_set(&sbi->read_hit_rbtree, 0); + atomic64_set(&sbi->read_hit_largest, 0); + atomic64_set(&sbi->read_hit_cached, 0); atomic_set(&sbi->inline_xattr, 0); atomic_set(&sbi->inline_inode, 0); diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index 8f15fc1..7c1678b 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -258,7 +258,7 @@ struct f2fs_dir_entry *f2fs_parent_dir(struct inode *dir, struct page **p) if (f2fs_has_inline_dentry(dir)) return f2fs_parent_inline_dir(dir, p); - page = get_lock_data_page(dir, 0); + page = get_lock_data_page(dir, 0, false); if (IS_ERR(page)) return NULL; @@ -740,7 +740,7 @@ bool f2fs_empty_dir(struct inode *dir) return f2fs_empty_inline_dir(dir); for (bidx = 0; bidx < nblock; bidx++) { - dentry_page = get_lock_data_page(dir, bidx); + dentry_page = get_lock_data_page(dir, bidx, false); if (IS_ERR(dentry_page)) { if (PTR_ERR(dentry_page) == -ENOENT) continue; @@ -787,7 +787,6 @@ bool f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d, else d_type = DT_UNKNOWN; - /* encrypted case */ de_name.name = d->filename[bit_pos]; de_name.len = le16_to_cpu(de->name_len); @@ -795,12 +794,20 @@ bool f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d, int save_len = fstr->len; int ret; + de_name.name = kmalloc(de_name.len, GFP_NOFS); + if (!de_name.name) + return false; + + memcpy(de_name.name, d->filename[bit_pos], de_name.len); + ret = f2fs_fname_disk_to_usr(d->inode, &de->hash_code, &de_name, fstr); - de_name = *fstr; - fstr->len = save_len; + kfree(de_name.name); if (ret < 0) return true; + + de_name = *fstr; + fstr->len = save_len; } if (!dir_emit(ctx, de_name.name, de_name.len, @@ -847,7 +854,7 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx) min(npages - n, (pgoff_t)MAX_DIR_RA_PAGES)); for (; n < npages; n++) { - dentry_page = get_lock_data_page(inode, n); + dentry_page = get_lock_data_page(inode, n, false); if (IS_ERR(dentry_page)) continue; diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c index 997ac86..7ddba81 100644 --- a/fs/f2fs/extent_cache.c +++ b/fs/f2fs/extent_cache.c @@ -155,11 +155,12 @@ static unsigned int __free_extent_tree(struct f2fs_sb_info *sbi, return count - et->count; } -static void __drop_largest_extent(struct inode *inode, pgoff_t fofs) +static void __drop_largest_extent(struct inode *inode, + pgoff_t fofs, unsigned int len) { struct extent_info *largest = &F2FS_I(inode)->extent_tree->largest; - if (largest->fofs <= fofs && largest->fofs + largest->len > fofs) + if (fofs < largest->fofs + largest->len && fofs + len > largest->fofs) largest->len = 0; } @@ -168,7 +169,7 @@ void f2fs_drop_largest_extent(struct inode *inode, pgoff_t fofs) if (!f2fs_may_extent_tree(inode)) return; - __drop_largest_extent(inode, fofs); + __drop_largest_extent(inode, fofs, 1); } void f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext) @@ -350,8 +351,7 @@ static struct extent_node *__try_merge_extent_node(struct f2fs_sb_info *sbi, } if (en) { - if (en->ei.len > et->largest.len) - et->largest = en->ei; + __try_update_largest_extent(et, en); et->cached_en = en; } return en; @@ -388,18 +388,17 @@ do_insert: if (!en) return NULL; - if (en->ei.len > et->largest.len) - et->largest = en->ei; + __try_update_largest_extent(et, en); et->cached_en = en; return en; } -unsigned int f2fs_update_extent_tree_range(struct inode *inode, +static unsigned int f2fs_update_extent_tree_range(struct inode *inode, pgoff_t fofs, block_t blkaddr, unsigned int len) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct extent_tree *et = F2FS_I(inode)->extent_tree; - struct extent_node *en = NULL, *en1 = NULL, *en2 = NULL, *en3 = NULL; + struct extent_node *en = NULL, *en1 = NULL; struct extent_node *prev_en = NULL, *next_en = NULL; struct extent_info ei, dei, prev; struct rb_node **insert_p = NULL, *insert_parent = NULL; @@ -409,6 +408,8 @@ unsigned int f2fs_update_extent_tree_range(struct inode *inode, if (!et) return false; + trace_f2fs_update_extent_tree_range(inode, fofs, blkaddr, len); + write_lock(&et->lock); if (is_inode_flag_set(F2FS_I(inode), FI_NO_EXTENT)) { @@ -419,148 +420,99 @@ unsigned int f2fs_update_extent_tree_range(struct inode *inode, prev = et->largest; dei.len = 0; - /* we do not guarantee that the largest extent is cached all the time */ - __drop_largest_extent(inode, fofs); + /* + * drop largest extent before lookup, in case it's already + * been shrunk from extent tree + */ + __drop_largest_extent(inode, fofs, len); /* 1. lookup first extent node in range [fofs, fofs + len - 1] */ en = __lookup_extent_tree_ret(et, fofs, &prev_en, &next_en, &insert_p, &insert_parent); - if (!en) { - if (next_en) { - en = next_en; - f2fs_bug_on(sbi, en->ei.fofs <= pos); - pos = en->ei.fofs; - } else { - /* - * skip searching in the tree since there is no - * larger extent node in the cache. - */ - goto update_extent; - } - } + if (!en) + en = next_en; /* 2. invlidate all extent nodes in range [fofs, fofs + len - 1] */ - while (en) { - struct rb_node *node; + while (en && en->ei.fofs < end) { + unsigned int org_end; + int parts = 0; /* # of parts current extent split into */ - if (pos >= end) - break; + next_en = en1 = NULL; dei = en->ei; - en1 = en2 = NULL; + org_end = dei.fofs + dei.len; + f2fs_bug_on(sbi, pos >= org_end); - node = rb_next(&en->rb_node); + if (pos > dei.fofs && pos - dei.fofs >= F2FS_MIN_EXTENT_LEN) { + en->ei.len = pos - en->ei.fofs; + prev_en = en; + parts = 1; + } - /* - * 2.1 there are four cases when we invalidate blkaddr in extent - * node, |V: valid address, X: will be invalidated| - */ - /* case#1, invalidate right part of extent node |VVVVVXXXXX| */ - if (pos > dei.fofs && end >= dei.fofs + dei.len) { - en->ei.len = pos - dei.fofs; - - if (en->ei.len < F2FS_MIN_EXTENT_LEN) { - __detach_extent_node(sbi, et, en); - insert_p = NULL; - insert_parent = NULL; - goto update; + if (end < org_end && org_end - end >= F2FS_MIN_EXTENT_LEN) { + if (parts) { + set_extent_info(&ei, end, + end - dei.fofs + dei.blk, + org_end - end); + en1 = __insert_extent_tree(sbi, et, &ei, + NULL, NULL); + next_en = en1; + } else { + en->ei.fofs = end; + en->ei.blk += end - dei.fofs; + en->ei.len -= end - dei.fofs; + next_en = en; } - - if (__is_extent_same(&dei, &et->largest)) - et->largest = en->ei; - goto next; + parts++; } - /* case#2, invalidate left part of extent node |XXXXXVVVVV| */ - if (pos <= dei.fofs && end < dei.fofs + dei.len) { - en->ei.fofs = end; - en->ei.blk += end - dei.fofs; - en->ei.len -= end - dei.fofs; - - if (en->ei.len < F2FS_MIN_EXTENT_LEN) { - __detach_extent_node(sbi, et, en); - insert_p = NULL; - insert_parent = NULL; - goto update; - } + if (!next_en) { + struct rb_node *node = rb_next(&en->rb_node); - if (__is_extent_same(&dei, &et->largest)) - et->largest = en->ei; - goto next; + next_en = node ? + rb_entry(node, struct extent_node, rb_node) + : NULL; } - __detach_extent_node(sbi, et, en); + if (parts) + __try_update_largest_extent(et, en); + else + __detach_extent_node(sbi, et, en); /* - * if we remove node in rb-tree, our parent node pointer may - * point the wrong place, discard them. + * if original extent is split into zero or two parts, extent + * tree has been altered by deletion or insertion, therefore + * invalidate pointers regard to tree. */ - insert_p = NULL; - insert_parent = NULL; - - /* case#3, invalidate entire extent node |XXXXXXXXXX| */ - if (pos <= dei.fofs && end >= dei.fofs + dei.len) { - if (__is_extent_same(&dei, &et->largest)) - et->largest.len = 0; - goto update; + if (parts != 1) { + insert_p = NULL; + insert_parent = NULL; } - /* - * case#4, invalidate data in the middle of extent node - * |VVVXXXXVVV| - */ - if (dei.len > F2FS_MIN_EXTENT_LEN) { - unsigned int endofs; - - /* insert left part of split extent into cache */ - if (pos - dei.fofs >= F2FS_MIN_EXTENT_LEN) { - set_extent_info(&ei, dei.fofs, dei.blk, - pos - dei.fofs); - en1 = __insert_extent_tree(sbi, et, &ei, - NULL, NULL); - } - - /* insert right part of split extent into cache */ - endofs = dei.fofs + dei.len; - if (endofs - end >= F2FS_MIN_EXTENT_LEN) { - set_extent_info(&ei, end, - end - dei.fofs + dei.blk, - endofs - end); - en2 = __insert_extent_tree(sbi, et, &ei, - NULL, NULL); - } - } -update: - /* 2.2 update in global extent list */ + /* update in global extent list */ spin_lock(&sbi->extent_lock); - if (en && !list_empty(&en->list)) + if (!parts && !list_empty(&en->list)) list_del(&en->list); if (en1) list_add_tail(&en1->list, &sbi->extent_list); - if (en2) - list_add_tail(&en2->list, &sbi->extent_list); spin_unlock(&sbi->extent_lock); - /* 2.3 release extent node */ - if (en) + /* release extent node */ + if (!parts) kmem_cache_free(extent_node_slab, en); -next: - en = node ? rb_entry(node, struct extent_node, rb_node) : NULL; - next_en = en; - if (en) - pos = en->ei.fofs; + + en = next_en; } -update_extent: /* 3. update extent in extent cache */ if (blkaddr) { struct extent_node *den = NULL; set_extent_info(&ei, fofs, blkaddr, len); - en3 = __try_merge_extent_node(sbi, et, &ei, &den, + en1 = __try_merge_extent_node(sbi, et, &ei, &den, prev_en, next_en); - if (!en3) - en3 = __insert_extent_tree(sbi, et, &ei, + if (!en1) + en1 = __insert_extent_tree(sbi, et, &ei, insert_p, insert_parent); /* give up extent_cache, if split and small updates happen */ @@ -572,11 +524,11 @@ update_extent: } spin_lock(&sbi->extent_lock); - if (en3) { - if (list_empty(&en3->list)) - list_add_tail(&en3->list, &sbi->extent_list); + if (en1) { + if (list_empty(&en1->list)) + list_add_tail(&en1->list, &sbi->extent_list); else - list_move_tail(&en3->list, &sbi->extent_list); + list_move_tail(&en1->list, &sbi->extent_list); } if (den && !list_empty(&den->list)) list_del(&den->list); @@ -650,6 +602,11 @@ unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink) } spin_unlock(&sbi->extent_lock); + /* + * reset ino for searching victims from beginning of global extent tree. + */ + ino = F2FS_ROOT_INO(sbi); + while ((found = radix_tree_gang_lookup(root, (void **)treevec, ino, EXT_TREE_VEC_SIZE))) { unsigned i; @@ -663,7 +620,7 @@ unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink) write_unlock(&et->lock); if (node_cnt + tree_cnt >= nr_shrink) - break; + goto unlock_out; } } unlock_out: diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index f1a90ff..9db5500 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -19,6 +19,7 @@ #include <linux/magic.h> #include <linux/kobject.h> #include <linux/sched.h> +#include <linux/vmalloc.h> #include <linux/bio.h> #ifdef CONFIG_F2FS_CHECK_FS @@ -52,6 +53,7 @@ #define F2FS_MOUNT_NOBARRIER 0x00000800 #define F2FS_MOUNT_FASTBOOT 0x00001000 #define F2FS_MOUNT_EXTENT_CACHE 0x00002000 +#define F2FS_MOUNT_FORCE_FG_GC 0x00004000 #define clear_opt(sbi, option) (sbi->mount_opt.opt &= ~F2FS_MOUNT_##option) #define set_opt(sbi, option) (sbi->mount_opt.opt |= F2FS_MOUNT_##option) @@ -122,6 +124,7 @@ enum { (SM_I(sbi)->trim_sections * (sbi)->segs_per_sec) #define BATCHED_TRIM_BLOCKS(sbi) \ (BATCHED_TRIM_SEGMENTS(sbi) << (sbi)->log_blocks_per_seg) +#define DEF_CP_INTERVAL 60 /* 60 secs */ struct cp_control { int reason; @@ -230,6 +233,7 @@ static inline bool __has_cursum_space(struct f2fs_summary_block *sum, int size, #define F2FS_IOC_RELEASE_VOLATILE_WRITE _IO(F2FS_IOCTL_MAGIC, 4) #define F2FS_IOC_ABORT_VOLATILE_WRITE _IO(F2FS_IOCTL_MAGIC, 5) #define F2FS_IOC_GARBAGE_COLLECT _IO(F2FS_IOCTL_MAGIC, 6) +#define F2FS_IOC_WRITE_CHECKPOINT _IO(F2FS_IOCTL_MAGIC, 7) #define F2FS_IOC_SET_ENCRYPTION_POLICY \ _IOR('f', 19, struct f2fs_encryption_policy) @@ -246,6 +250,7 @@ static inline bool __has_cursum_space(struct f2fs_summary_block *sum, int size, #define F2FS_GOING_DOWN_FULLSYNC 0x0 /* going down with full sync */ #define F2FS_GOING_DOWN_METASYNC 0x1 /* going down with metadata */ #define F2FS_GOING_DOWN_NOSYNC 0x2 /* going down */ +#define F2FS_GOING_DOWN_METAFLUSH 0x3 /* going down with meta flush */ #if defined(__KERNEL__) && defined(CONFIG_COMPAT) /* @@ -492,12 +497,20 @@ static inline bool __is_front_mergeable(struct extent_info *cur, return __is_extent_mergeable(cur, front); } +static inline void __try_update_largest_extent(struct extent_tree *et, + struct extent_node *en) +{ + if (en->ei.len > et->largest.len) + et->largest = en->ei; +} + struct f2fs_nm_info { block_t nat_blkaddr; /* base disk address of NAT */ nid_t max_nid; /* maximum possible node ids */ nid_t available_nids; /* maximum available node ids */ nid_t next_scan_nid; /* the next nid to be scanned */ unsigned int ram_thresh; /* control the memory footprint */ + unsigned int ra_nid_pages; /* # of nid pages to be readaheaded */ /* NAT cache management */ struct radix_tree_root nat_root;/* root of the nat entry cache */ @@ -724,6 +737,7 @@ struct f2fs_sb_info { struct rw_semaphore node_write; /* locking node writes */ struct mutex writepages; /* mutex for writepages() */ wait_queue_head_t cp_wait; + long cp_expires, cp_interval; /* next expected periodic cp */ struct inode_management im[MAX_INO_ENTRY]; /* manage inode cache */ @@ -787,10 +801,10 @@ struct f2fs_sb_info { unsigned int segment_count[2]; /* # of allocated segments */ unsigned int block_count[2]; /* # of allocated blocks */ atomic_t inplace_count; /* # of inplace update */ - atomic_t total_hit_ext; /* # of lookup extent cache */ - atomic_t read_hit_rbtree; /* # of hit rbtree extent node */ - atomic_t read_hit_largest; /* # of hit largest extent node */ - atomic_t read_hit_cached; /* # of hit cached extent node */ + atomic64_t total_hit_ext; /* # of lookup extent cache */ + atomic64_t read_hit_rbtree; /* # of hit rbtree extent node */ + atomic64_t read_hit_largest; /* # of hit largest extent node */ + atomic64_t read_hit_cached; /* # of hit cached extent node */ atomic_t inline_xattr; /* # of inline_xattr inodes */ atomic_t inline_inode; /* # of inline_data inodes */ atomic_t inline_dir; /* # of inline_dentry inodes */ @@ -1220,6 +1234,24 @@ static inline unsigned int valid_inode_count(struct f2fs_sb_info *sbi) return sbi->total_valid_inode_count; } +static inline struct page *f2fs_grab_cache_page(struct address_space *mapping, + pgoff_t index, bool for_write) +{ + if (!for_write) + return grab_cache_page(mapping, index); + return grab_cache_page_write_begin(mapping, index, AOP_FLAG_NOFS); +} + +static inline void f2fs_copy_page(struct page *src, struct page *dst) +{ + char *src_kaddr = kmap(src); + char *dst_kaddr = kmap(dst); + + memcpy(dst_kaddr, src_kaddr, PAGE_SIZE); + kunmap(dst); + kunmap(src); +} + static inline void f2fs_put_page(struct page *page, int unlock) { if (!page) @@ -1579,6 +1611,26 @@ static inline bool f2fs_may_extent_tree(struct inode *inode) return S_ISREG(mode); } +static inline void *f2fs_kvmalloc(size_t size, gfp_t flags) +{ + void *ret; + + ret = kmalloc(size, flags | __GFP_NOWARN); + if (!ret) + ret = __vmalloc(size, flags, PAGE_KERNEL); + return ret; +} + +static inline void *f2fs_kvzalloc(size_t size, gfp_t flags) +{ + void *ret; + + ret = kzalloc(size, flags | __GFP_NOWARN); + if (!ret) + ret = __vmalloc(size, flags | __GFP_ZERO, PAGE_KERNEL); + return ret; +} + #define get_inode_mode(i) \ ((is_inode_flag_set(F2FS_I(i), FI_ACL_MODE)) ? \ (F2FS_I(i)->i_acl_mode) : ((i)->i_mode)) @@ -1721,6 +1773,7 @@ int f2fs_issue_flush(struct f2fs_sb_info *); int create_flush_cmd_control(struct f2fs_sb_info *); void destroy_flush_cmd_control(struct f2fs_sb_info *); void invalidate_blocks(struct f2fs_sb_info *, block_t); +bool is_checkpointed_data(struct f2fs_sb_info *, block_t); void refresh_sit_entry(struct f2fs_sb_info *, block_t, block_t); void clear_prefree_segments(struct f2fs_sb_info *, struct cp_control *); void release_discard_addrs(struct f2fs_sb_info *); @@ -1739,6 +1792,7 @@ void f2fs_replace_block(struct f2fs_sb_info *, struct dnode_of_data *, void allocate_data_block(struct f2fs_sb_info *, struct page *, block_t, block_t *, struct f2fs_summary *, int); void f2fs_wait_on_page_writeback(struct page *, enum page_type); +void f2fs_wait_on_encrypted_page_writeback(struct f2fs_sb_info *, block_t); void write_data_summaries(struct f2fs_sb_info *, block_t); void write_node_summaries(struct f2fs_sb_info *, block_t); int lookup_journal_in_cursum(struct f2fs_summary_block *, @@ -1754,8 +1808,9 @@ void destroy_segment_manager_caches(void); */ struct page *grab_meta_page(struct f2fs_sb_info *, pgoff_t); struct page *get_meta_page(struct f2fs_sb_info *, pgoff_t); +struct page *get_tmp_page(struct f2fs_sb_info *, pgoff_t); bool is_valid_blkaddr(struct f2fs_sb_info *, block_t, int); -int ra_meta_pages(struct f2fs_sb_info *, block_t, int, int); +int ra_meta_pages(struct f2fs_sb_info *, block_t, int, int, bool); void ra_meta_pages_cond(struct f2fs_sb_info *, pgoff_t); long sync_meta_pages(struct f2fs_sb_info *, enum page_type, long); void add_dirty_inode(struct f2fs_sb_info *, nid_t, int type); @@ -1787,9 +1842,9 @@ void set_data_blkaddr(struct dnode_of_data *); int reserve_new_block(struct dnode_of_data *); int f2fs_get_block(struct dnode_of_data *, pgoff_t); int f2fs_reserve_block(struct dnode_of_data *, pgoff_t); -struct page *get_read_data_page(struct inode *, pgoff_t, int); +struct page *get_read_data_page(struct inode *, pgoff_t, int, bool); struct page *find_data_page(struct inode *, pgoff_t); -struct page *get_lock_data_page(struct inode *, pgoff_t); +struct page *get_lock_data_page(struct inode *, pgoff_t, bool); struct page *get_new_data_page(struct inode *, struct page *, pgoff_t, bool); int do_write_data_page(struct f2fs_io_info *); int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *, u64, u64); @@ -1802,7 +1857,7 @@ int f2fs_release_page(struct page *, gfp_t); int start_gc_thread(struct f2fs_sb_info *); void stop_gc_thread(struct f2fs_sb_info *); block_t start_bidx_of_node(unsigned int, struct f2fs_inode_info *); -int f2fs_gc(struct f2fs_sb_info *); +int f2fs_gc(struct f2fs_sb_info *, bool); void build_gc_manager(struct f2fs_sb_info *); /* @@ -1820,7 +1875,8 @@ struct f2fs_stat_info { struct f2fs_sb_info *sbi; int all_area_segs, sit_area_segs, nat_area_segs, ssa_area_segs; int main_area_segs, main_area_sections, main_area_zones; - int hit_largest, hit_cached, hit_rbtree, hit_total, total_ext; + unsigned long long hit_largest, hit_cached, hit_rbtree; + unsigned long long hit_total, total_ext; int ext_tree, ext_node; int ndirty_node, ndirty_dent, ndirty_dirs, ndirty_meta; int nats, dirty_nats, sits, dirty_sits, fnids; @@ -1844,7 +1900,7 @@ struct f2fs_stat_info { unsigned int segment_count[2]; unsigned int block_count[2]; unsigned int inplace_count; - unsigned base_mem, cache_mem, page_mem; + unsigned long long base_mem, cache_mem, page_mem; }; static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi) @@ -1857,10 +1913,10 @@ static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi) #define stat_inc_bggc_count(sbi) ((sbi)->bg_gc++) #define stat_inc_dirty_dir(sbi) ((sbi)->n_dirty_dirs++) #define stat_dec_dirty_dir(sbi) ((sbi)->n_dirty_dirs--) -#define stat_inc_total_hit(sbi) (atomic_inc(&(sbi)->total_hit_ext)) -#define stat_inc_rbtree_node_hit(sbi) (atomic_inc(&(sbi)->read_hit_rbtree)) -#define stat_inc_largest_node_hit(sbi) (atomic_inc(&(sbi)->read_hit_largest)) -#define stat_inc_cached_node_hit(sbi) (atomic_inc(&(sbi)->read_hit_cached)) +#define stat_inc_total_hit(sbi) (atomic64_inc(&(sbi)->total_hit_ext)) +#define stat_inc_rbtree_node_hit(sbi) (atomic64_inc(&(sbi)->read_hit_rbtree)) +#define stat_inc_largest_node_hit(sbi) (atomic64_inc(&(sbi)->read_hit_largest)) +#define stat_inc_cached_node_hit(sbi) (atomic64_inc(&(sbi)->read_hit_cached)) #define stat_inc_inline_xattr(inode) \ do { \ if (f2fs_has_inline_xattr(inode)) \ @@ -1998,6 +2054,8 @@ void f2fs_delete_inline_entry(struct f2fs_dir_entry *, struct page *, bool f2fs_empty_inline_dir(struct inode *); int f2fs_read_inline_dir(struct file *, struct dir_context *, struct f2fs_str *); +int f2fs_inline_data_fiemap(struct inode *, + struct fiemap_extent_info *, __u64, __u64); /* * shrinker.c diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 8120f86..a197215 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -74,7 +74,8 @@ static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma, goto mapped; /* page is wholly or partially inside EOF */ - if (((page->index + 1) << PAGE_CACHE_SHIFT) > i_size_read(inode)) { + if (((loff_t)(page->index + 1) << PAGE_CACHE_SHIFT) > + i_size_read(inode)) { unsigned offset; offset = i_size_read(inode) & ~PAGE_CACHE_MASK; zero_user_segment(page, offset, PAGE_CACHE_SIZE); @@ -86,6 +87,11 @@ static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma, mapped: /* fill the page */ f2fs_wait_on_page_writeback(page, DATA); + + /* wait for GCed encrypted page writeback */ + if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) + f2fs_wait_on_encrypted_page_writeback(sbi, dn.data_blkaddr); + /* if gced page is attached, don't write to cold segment */ clear_cold_data(page); out: @@ -343,7 +349,7 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence) dirty = __get_first_dirty_index(inode->i_mapping, pgofs, whence); - for (; data_ofs < isize; data_ofs = pgofs << PAGE_CACHE_SHIFT) { + for (; data_ofs < isize; data_ofs = (loff_t)pgofs << PAGE_CACHE_SHIFT) { set_new_dnode(&dn, inode, NULL, NULL, 0); err = get_dnode_of_data(&dn, pgofs, LOOKUP_NODE_RA); if (err && err != -ENOENT) { @@ -504,14 +510,14 @@ static int truncate_partial_data_page(struct inode *inode, u64 from, return 0; if (cache_only) { - page = grab_cache_page(mapping, index); + page = f2fs_grab_cache_page(mapping, index, false); if (page && PageUptodate(page)) goto truncate_out; f2fs_put_page(page, 1); return 0; } - page = get_lock_data_page(inode, index); + page = get_lock_data_page(inode, index, true); if (IS_ERR(page)) return 0; truncate_out: @@ -680,6 +686,7 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr) * larger than i_size. */ truncate_setsize(inode, attr->ia_size); + inode->i_mtime = inode->i_ctime = CURRENT_TIME; } } @@ -738,23 +745,31 @@ static int fill_zero(struct inode *inode, pgoff_t index, int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end) { - pgoff_t index; int err; - for (index = pg_start; index < pg_end; index++) { + while (pg_start < pg_end) { struct dnode_of_data dn; + pgoff_t end_offset, count; set_new_dnode(&dn, inode, NULL, NULL, 0); - err = get_dnode_of_data(&dn, index, LOOKUP_NODE); + err = get_dnode_of_data(&dn, pg_start, LOOKUP_NODE); if (err) { - if (err == -ENOENT) + if (err == -ENOENT) { + pg_start++; continue; + } return err; } - if (dn.data_blkaddr != NULL_ADDR) - truncate_data_blocks_range(&dn, 1); + end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode)); + count = min(end_offset - dn.ofs_in_node, pg_end - pg_start); + + f2fs_bug_on(F2FS_I_SB(inode), count == 0 || count > end_offset); + + truncate_data_blocks_range(&dn, count); f2fs_put_dnode(&dn); + + pg_start += count; } return 0; } @@ -765,9 +780,6 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len) loff_t off_start, off_end; int ret = 0; - if (!S_ISREG(inode->i_mode)) - return -EOPNOTSUPP; - if (f2fs_has_inline_data(inode)) { ret = f2fs_convert_inline_inode(inode); if (ret) @@ -805,8 +817,8 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len) f2fs_balance_fs(sbi); - blk_start = pg_start << PAGE_CACHE_SHIFT; - blk_end = pg_end << PAGE_CACHE_SHIFT; + blk_start = (loff_t)pg_start << PAGE_CACHE_SHIFT; + blk_end = (loff_t)pg_end << PAGE_CACHE_SHIFT; truncate_inode_pages_range(mapping, blk_start, blk_end - 1); @@ -819,86 +831,100 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len) return ret; } -static int f2fs_do_collapse(struct inode *inode, pgoff_t start, pgoff_t end) +static int __exchange_data_block(struct inode *inode, pgoff_t src, + pgoff_t dst, bool full) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct dnode_of_data dn; - pgoff_t nrpages = (i_size_read(inode) + PAGE_SIZE - 1) / PAGE_SIZE; - int ret = 0; - - for (; end < nrpages; start++, end++) { - block_t new_addr, old_addr; - - f2fs_lock_op(sbi); + block_t new_addr; + bool do_replace = false; + int ret; - set_new_dnode(&dn, inode, NULL, NULL, 0); - ret = get_dnode_of_data(&dn, end, LOOKUP_NODE_RA); - if (ret && ret != -ENOENT) { - goto out; - } else if (ret == -ENOENT) { - new_addr = NULL_ADDR; - } else { - new_addr = dn.data_blkaddr; - truncate_data_blocks_range(&dn, 1); - f2fs_put_dnode(&dn); + set_new_dnode(&dn, inode, NULL, NULL, 0); + ret = get_dnode_of_data(&dn, src, LOOKUP_NODE_RA); + if (ret && ret != -ENOENT) { + return ret; + } else if (ret == -ENOENT) { + new_addr = NULL_ADDR; + } else { + new_addr = dn.data_blkaddr; + if (!is_checkpointed_data(sbi, new_addr)) { + dn.data_blkaddr = NULL_ADDR; + /* do not invalidate this block address */ + set_data_blkaddr(&dn); + f2fs_update_extent_cache(&dn); + do_replace = true; } + f2fs_put_dnode(&dn); + } - if (new_addr == NULL_ADDR) { - set_new_dnode(&dn, inode, NULL, NULL, 0); - ret = get_dnode_of_data(&dn, start, LOOKUP_NODE_RA); - if (ret && ret != -ENOENT) { - goto out; - } else if (ret == -ENOENT) { - f2fs_unlock_op(sbi); - continue; - } + if (new_addr == NULL_ADDR) + return full ? truncate_hole(inode, dst, dst + 1) : 0; - if (dn.data_blkaddr == NULL_ADDR) { - f2fs_put_dnode(&dn); - f2fs_unlock_op(sbi); - continue; - } else { - truncate_data_blocks_range(&dn, 1); - } + if (do_replace) { + struct page *ipage = get_node_page(sbi, inode->i_ino); + struct node_info ni; - f2fs_put_dnode(&dn); - } else { - struct page *ipage; + if (IS_ERR(ipage)) { + ret = PTR_ERR(ipage); + goto err_out; + } - ipage = get_node_page(sbi, inode->i_ino); - if (IS_ERR(ipage)) { - ret = PTR_ERR(ipage); - goto out; - } + set_new_dnode(&dn, inode, ipage, NULL, 0); + ret = f2fs_reserve_block(&dn, dst); + if (ret) + goto err_out; - set_new_dnode(&dn, inode, ipage, NULL, 0); - ret = f2fs_reserve_block(&dn, start); - if (ret) - goto out; + truncate_data_blocks_range(&dn, 1); - old_addr = dn.data_blkaddr; - if (old_addr != NEW_ADDR && new_addr == NEW_ADDR) { - dn.data_blkaddr = NULL_ADDR; - f2fs_update_extent_cache(&dn); - invalidate_blocks(sbi, old_addr); + get_node_info(sbi, dn.nid, &ni); + f2fs_replace_block(sbi, &dn, dn.data_blkaddr, new_addr, + ni.version, true); + f2fs_put_dnode(&dn); + } else { + struct page *psrc, *pdst; + + psrc = get_lock_data_page(inode, src, true); + if (IS_ERR(psrc)) + return PTR_ERR(psrc); + pdst = get_new_data_page(inode, NULL, dst, false); + if (IS_ERR(pdst)) { + f2fs_put_page(psrc, 1); + return PTR_ERR(pdst); + } + f2fs_copy_page(psrc, pdst); + set_page_dirty(pdst); + f2fs_put_page(pdst, 1); + f2fs_put_page(psrc, 1); - dn.data_blkaddr = new_addr; - set_data_blkaddr(&dn); - } else if (new_addr != NEW_ADDR) { - struct node_info ni; + return truncate_hole(inode, src, src + 1); + } + return 0; - get_node_info(sbi, dn.nid, &ni); - f2fs_replace_block(sbi, &dn, old_addr, new_addr, - ni.version, true); - } +err_out: + if (!get_dnode_of_data(&dn, src, LOOKUP_NODE)) { + dn.data_blkaddr = new_addr; + set_data_blkaddr(&dn); + f2fs_update_extent_cache(&dn); + f2fs_put_dnode(&dn); + } + return ret; +} - f2fs_put_dnode(&dn); - } +static int f2fs_do_collapse(struct inode *inode, pgoff_t start, pgoff_t end) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + pgoff_t nrpages = (i_size_read(inode) + PAGE_SIZE - 1) / PAGE_SIZE; + int ret = 0; + + for (; end < nrpages; start++, end++) { + f2fs_balance_fs(sbi); + f2fs_lock_op(sbi); + ret = __exchange_data_block(inode, end, start, true); f2fs_unlock_op(sbi); + if (ret) + break; } - return 0; -out: - f2fs_unlock_op(sbi); return ret; } @@ -908,9 +934,6 @@ static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len) loff_t new_size; int ret; - if (!S_ISREG(inode->i_mode)) - return -EINVAL; - if (offset + len >= i_size_read(inode)) return -EINVAL; @@ -940,7 +963,12 @@ static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len) if (ret) return ret; + /* write out all moved pages, if possible */ + filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX); + truncate_pagecache(inode, offset); + new_size = i_size_read(inode) - len; + truncate_pagecache(inode, new_size); ret = truncate_blocks(inode, new_size, true); if (!ret) @@ -959,9 +987,6 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len, loff_t off_start, off_end; int ret = 0; - if (!S_ISREG(inode->i_mode)) - return -EINVAL; - ret = inode_newsize_ok(inode, (len + offset)); if (ret) return ret; @@ -1003,7 +1028,7 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len, return ret; new_size = max_t(loff_t, new_size, - pg_start << PAGE_CACHE_SHIFT); + (loff_t)pg_start << PAGE_CACHE_SHIFT); } for (index = pg_start; index < pg_end; index++) { @@ -1039,7 +1064,7 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len, f2fs_unlock_op(sbi); new_size = max_t(loff_t, new_size, - (index + 1) << PAGE_CACHE_SHIFT); + (loff_t)(index + 1) << PAGE_CACHE_SHIFT); } if (off_end) { @@ -1066,10 +1091,7 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len) struct f2fs_sb_info *sbi = F2FS_I_SB(inode); pgoff_t pg_start, pg_end, delta, nrpages, idx; loff_t new_size; - int ret; - - if (!S_ISREG(inode->i_mode)) - return -EINVAL; + int ret = 0; new_size = i_size_read(inode) + len; if (new_size > inode->i_sb->s_maxbytes) @@ -1107,57 +1129,19 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len) nrpages = (i_size_read(inode) + PAGE_SIZE - 1) / PAGE_SIZE; for (idx = nrpages - 1; idx >= pg_start && idx != -1; idx--) { - struct dnode_of_data dn; - struct page *ipage; - block_t new_addr, old_addr; - f2fs_lock_op(sbi); - - set_new_dnode(&dn, inode, NULL, NULL, 0); - ret = get_dnode_of_data(&dn, idx, LOOKUP_NODE_RA); - if (ret && ret != -ENOENT) { - goto out; - } else if (ret == -ENOENT) { - goto next; - } else if (dn.data_blkaddr == NULL_ADDR) { - f2fs_put_dnode(&dn); - goto next; - } else { - new_addr = dn.data_blkaddr; - truncate_data_blocks_range(&dn, 1); - f2fs_put_dnode(&dn); - } - - ipage = get_node_page(sbi, inode->i_ino); - if (IS_ERR(ipage)) { - ret = PTR_ERR(ipage); - goto out; - } - - set_new_dnode(&dn, inode, ipage, NULL, 0); - ret = f2fs_reserve_block(&dn, idx + delta); - if (ret) - goto out; - - old_addr = dn.data_blkaddr; - f2fs_bug_on(sbi, old_addr != NEW_ADDR); - - if (new_addr != NEW_ADDR) { - struct node_info ni; - - get_node_info(sbi, dn.nid, &ni); - f2fs_replace_block(sbi, &dn, old_addr, new_addr, - ni.version, true); - } - f2fs_put_dnode(&dn); -next: + ret = __exchange_data_block(inode, idx, idx + delta, false); f2fs_unlock_op(sbi); + if (ret) + break; } - i_size_write(inode, new_size); - return 0; -out: - f2fs_unlock_op(sbi); + /* write out all moved pages, if possible */ + filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX); + truncate_pagecache(inode, offset); + + if (!ret) + i_size_write(inode, new_size); return ret; } @@ -1204,9 +1188,10 @@ noalloc: if (pg_start == pg_end) new_size = offset + len; else if (index == pg_start && off_start) - new_size = (index + 1) << PAGE_CACHE_SHIFT; + new_size = (loff_t)(index + 1) << PAGE_CACHE_SHIFT; else if (index == pg_end) - new_size = (index << PAGE_CACHE_SHIFT) + off_end; + new_size = ((loff_t)index << PAGE_CACHE_SHIFT) + + off_end; else new_size += PAGE_CACHE_SIZE; } @@ -1228,6 +1213,10 @@ static long f2fs_fallocate(struct file *file, int mode, struct inode *inode = file_inode(file); long ret = 0; + /* f2fs only support ->fallocate for regular file */ + if (!S_ISREG(inode->i_mode)) + return -EINVAL; + if (f2fs_encrypted_inode(inode) && (mode & (FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_INSERT_RANGE))) return -EOPNOTSUPP; @@ -1437,8 +1426,7 @@ static int f2fs_ioc_release_volatile_write(struct file *filp) if (!f2fs_is_first_block_written(inode)) return truncate_partial_data_page(inode, 0, true); - punch_hole(inode, 0, F2FS_BLKSIZE); - return 0; + return punch_hole(inode, 0, F2FS_BLKSIZE); } static int f2fs_ioc_abort_volatile_write(struct file *filp) @@ -1455,13 +1443,9 @@ static int f2fs_ioc_abort_volatile_write(struct file *filp) f2fs_balance_fs(F2FS_I_SB(inode)); - if (f2fs_is_atomic_file(inode)) { - clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE); - commit_inmem_pages(inode, true); - } - - if (f2fs_is_volatile_file(inode)) - clear_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE); + clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE); + clear_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE); + commit_inmem_pages(inode, true); mnt_drop_write_file(filp); return ret; @@ -1496,6 +1480,10 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg) case F2FS_GOING_DOWN_NOSYNC: f2fs_stop_checkpoint(sbi); break; + case F2FS_GOING_DOWN_METAFLUSH: + sync_meta_pages(sbi, META, LONG_MAX); + f2fs_stop_checkpoint(sbi); + break; default: return -EINVAL; } @@ -1616,27 +1604,44 @@ static int f2fs_ioc_gc(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - __u32 i, count; + __u32 sync; if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (get_user(count, (__u32 __user *)arg)) + if (get_user(sync, (__u32 __user *)arg)) return -EFAULT; - if (!count || count > F2FS_BATCH_GC_MAX_NUM) - return -EINVAL; + if (f2fs_readonly(sbi->sb)) + return -EROFS; - for (i = 0; i < count; i++) { + if (!sync) { if (!mutex_trylock(&sbi->gc_mutex)) - break; - - if (f2fs_gc(sbi)) - break; + return -EBUSY; + } else { + mutex_lock(&sbi->gc_mutex); } - if (put_user(i, (__u32 __user *)arg)) - return -EFAULT; + return f2fs_gc(sbi, sync); +} + +static int f2fs_ioc_write_checkpoint(struct file *filp, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct cp_control cpc; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (f2fs_readonly(sbi->sb)) + return -EROFS; + + cpc.reason = __get_cp_reason(sbi); + + mutex_lock(&sbi->gc_mutex); + write_checkpoint(sbi, &cpc); + mutex_unlock(&sbi->gc_mutex); return 0; } @@ -1672,6 +1677,8 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) return f2fs_ioc_get_encryption_pwsalt(filp, arg); case F2FS_IOC_GARBAGE_COLLECT: return f2fs_ioc_gc(filp, arg); + case F2FS_IOC_WRITE_CHECKPOINT: + return f2fs_ioc_write_checkpoint(filp, arg); default: return -ENOTTY; } diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 782b8e7..fedbf67 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -78,9 +78,12 @@ static int gc_thread_func(void *data) stat_inc_bggc_count(sbi); /* if return value is not zero, no victim was selected */ - if (f2fs_gc(sbi)) + if (f2fs_gc(sbi, test_opt(sbi, FORCE_FG_GC))) wait_ms = gc_th->no_gc_sleep_time; + trace_f2fs_background_gc(sbi->sb, wait_ms, + prefree_segments(sbi), free_segments(sbi)); + /* balancing f2fs's metadata periodically */ f2fs_balance_fs_bg(sbi); @@ -257,6 +260,7 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi, struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); struct victim_sel_policy p; unsigned int secno, max_cost; + unsigned int last_segment = MAIN_SEGS(sbi); int nsearched = 0; mutex_lock(&dirty_i->seglist_lock); @@ -267,6 +271,9 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi, p.min_segno = NULL_SEGNO; p.min_cost = max_cost = get_max_cost(sbi, &p); + if (p.max_search == 0) + goto out; + if (p.alloc_mode == LFS && gc_type == FG_GC) { p.min_segno = check_bg_victims(sbi); if (p.min_segno != NULL_SEGNO) @@ -277,9 +284,10 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi, unsigned long cost; unsigned int segno; - segno = find_next_bit(p.dirty_segmap, MAIN_SEGS(sbi), p.offset); - if (segno >= MAIN_SEGS(sbi)) { + segno = find_next_bit(p.dirty_segmap, last_segment, p.offset); + if (segno >= last_segment) { if (sbi->last_victim[p.gc_mode]) { + last_segment = sbi->last_victim[p.gc_mode]; sbi->last_victim[p.gc_mode] = 0; p.offset = 0; continue; @@ -327,6 +335,7 @@ got_it: sbi->cur_victim_sec, prefree_segments(sbi), free_segments(sbi)); } +out: mutex_unlock(&dirty_i->seglist_lock); return (p.min_segno == NULL_SEGNO) ? 0 : 1; @@ -541,7 +550,7 @@ static void move_encrypted_block(struct inode *inode, block_t bidx) int err; /* do not read out */ - page = grab_cache_page(inode->i_mapping, bidx); + page = f2fs_grab_cache_page(inode->i_mapping, bidx, false); if (!page) return; @@ -550,8 +559,16 @@ static void move_encrypted_block(struct inode *inode, block_t bidx) if (err) goto out; - if (unlikely(dn.data_blkaddr == NULL_ADDR)) + if (unlikely(dn.data_blkaddr == NULL_ADDR)) { + ClearPageUptodate(page); goto put_out; + } + + /* + * don't cache encrypted data into meta inode until previous dirty + * data were writebacked to avoid racing between GC and flush. + */ + f2fs_wait_on_page_writeback(page, DATA); get_node_info(fio.sbi, dn.nid, &ni); set_summary(&sum, dn.nid, dn.ofs_in_node, ni.version); @@ -580,7 +597,7 @@ static void move_encrypted_block(struct inode *inode, block_t bidx) goto put_page_out; set_page_dirty(fio.encrypted_page); - f2fs_wait_on_page_writeback(fio.encrypted_page, META); + f2fs_wait_on_page_writeback(fio.encrypted_page, DATA); if (clear_page_dirty_for_io(fio.encrypted_page)) dec_page_count(fio.sbi, F2FS_DIRTY_META); @@ -611,7 +628,7 @@ static void move_data_page(struct inode *inode, block_t bidx, int gc_type) { struct page *page; - page = get_lock_data_page(inode, bidx); + page = get_lock_data_page(inode, bidx, true); if (IS_ERR(page)) return; @@ -705,7 +722,7 @@ next_step: start_bidx = start_bidx_of_node(nofs, F2FS_I(inode)); data_page = get_read_data_page(inode, - start_bidx + ofs_in_node, READA); + start_bidx + ofs_in_node, READA, true); if (IS_ERR(data_page)) { iput(inode); continue; @@ -797,13 +814,12 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi, unsigned int segno, return nfree; } -int f2fs_gc(struct f2fs_sb_info *sbi) +int f2fs_gc(struct f2fs_sb_info *sbi, bool sync) { - unsigned int segno = NULL_SEGNO; - unsigned int i; - int gc_type = BG_GC; - int nfree = 0; - int ret = -1; + unsigned int segno, i; + int gc_type = sync ? FG_GC : BG_GC; + int sec_freed = 0; + int ret = -EINVAL; struct cp_control cpc; struct gc_inode_list gc_list = { .ilist = LIST_HEAD_INIT(gc_list.ilist), @@ -812,12 +828,14 @@ int f2fs_gc(struct f2fs_sb_info *sbi) cpc.reason = __get_cp_reason(sbi); gc_more: + segno = NULL_SEGNO; + if (unlikely(!(sbi->sb->s_flags & MS_ACTIVE))) goto stop; if (unlikely(f2fs_cp_error(sbi))) goto stop; - if (gc_type == BG_GC && has_not_enough_free_secs(sbi, nfree)) { + if (gc_type == BG_GC && has_not_enough_free_secs(sbi, sec_freed)) { gc_type = FG_GC; if (__get_victim(sbi, &segno, gc_type) || prefree_segments(sbi)) write_checkpoint(sbi, &cpc); @@ -830,23 +848,38 @@ gc_more: /* readahead multi ssa blocks those have contiguous address */ if (sbi->segs_per_sec > 1) ra_meta_pages(sbi, GET_SUM_BLOCK(sbi, segno), sbi->segs_per_sec, - META_SSA); + META_SSA, true); - for (i = 0; i < sbi->segs_per_sec; i++) - nfree += do_garbage_collect(sbi, segno + i, &gc_list, gc_type); + for (i = 0; i < sbi->segs_per_sec; i++) { + /* + * for FG_GC case, halt gcing left segments once failed one + * of segments in selected section to avoid long latency. + */ + if (!do_garbage_collect(sbi, segno + i, &gc_list, gc_type) && + gc_type == FG_GC) + break; + } + + if (i == sbi->segs_per_sec && gc_type == FG_GC) + sec_freed++; if (gc_type == FG_GC) sbi->cur_victim_sec = NULL_SEGNO; - if (has_not_enough_free_secs(sbi, nfree)) - goto gc_more; + if (!sync) { + if (has_not_enough_free_secs(sbi, sec_freed)) + goto gc_more; - if (gc_type == FG_GC) - write_checkpoint(sbi, &cpc); + if (gc_type == FG_GC) + write_checkpoint(sbi, &cpc); + } stop: mutex_unlock(&sbi->gc_mutex); put_gc_inode(&gc_list); + + if (sync) + ret = sec_freed ? 0 : -EAGAIN; return ret; } diff --git a/fs/f2fs/gc.h b/fs/f2fs/gc.h index c5a055b..b4a65be 100644 --- a/fs/f2fs/gc.h +++ b/fs/f2fs/gc.h @@ -19,12 +19,6 @@ #define LIMIT_INVALID_BLOCK 40 /* percentage over total user space */ #define LIMIT_FREE_BLOCK 40 /* percentage over invalid + free space */ -/* - * with this macro, we can control the max time we do garbage collection, - * when user triggers batch mode gc by ioctl. - */ -#define F2FS_BATCH_GC_MAX_NUM 16 - /* Search max. number of dirty segments to select a victim segment */ #define DEF_MAX_VICTIM_SEARCH 4096 /* covers 8GB */ diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c index 3d143be..bda7126 100644 --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -12,6 +12,7 @@ #include <linux/f2fs_fs.h> #include "f2fs.h" +#include "node.h" bool f2fs_may_inline_data(struct inode *inode) { @@ -274,12 +275,14 @@ process_inline: if (f2fs_has_inline_data(inode)) { ipage = get_node_page(sbi, inode->i_ino); f2fs_bug_on(sbi, IS_ERR(ipage)); - truncate_inline_inode(ipage, 0); + if (!truncate_inline_inode(ipage, 0)) + return false; f2fs_clear_inline_inode(inode); update_inode(inode, ipage); f2fs_put_page(ipage, 1); } else if (ri && (ri->i_inline & F2FS_INLINE_DATA)) { - truncate_blocks(inode, 0, false); + if (truncate_blocks(inode, 0, false)) + return false; goto process_inline; } return false; @@ -568,3 +571,38 @@ int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx, f2fs_put_page(ipage, 1); return 0; } + +int f2fs_inline_data_fiemap(struct inode *inode, + struct fiemap_extent_info *fieinfo, __u64 start, __u64 len) +{ + __u64 byteaddr, ilen; + __u32 flags = FIEMAP_EXTENT_DATA_INLINE | FIEMAP_EXTENT_NOT_ALIGNED | + FIEMAP_EXTENT_LAST; + struct node_info ni; + struct page *ipage; + int err = 0; + + ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino); + if (IS_ERR(ipage)) + return PTR_ERR(ipage); + + if (!f2fs_has_inline_data(inode)) { + err = -EAGAIN; + goto out; + } + + ilen = min_t(size_t, MAX_INLINE_DATA, i_size_read(inode)); + if (start >= ilen) + goto out; + if (start + len < ilen) + ilen = start + len; + ilen -= start; + + get_node_info(F2FS_I_SB(inode), inode->i_ino, &ni); + byteaddr = (__u64)ni.blk_addr << inode->i_sb->s_blocksize_bits; + byteaddr += (char *)inline_data_addr(ipage) - (char *)F2FS_INODE(ipage); + err = fiemap_fill_next_extent(fieinfo, start, byteaddr, ilen, flags); +out: + f2fs_put_page(ipage, 1); + return err; +} diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 35aae65..97e20de 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -296,16 +296,12 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc) return 0; /* - * We need to lock here to prevent from producing dirty node pages + * We need to balance fs here to prevent from producing dirty node pages * during the urgent cleaning time when runing out of free sections. */ - f2fs_lock_op(sbi); update_inode_page(inode); - f2fs_unlock_op(sbi); - - if (wbc) - f2fs_balance_fs(sbi); + f2fs_balance_fs(sbi); return 0; } diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index a680bf3..2c32110 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -410,11 +410,14 @@ err_out: * If the symlink path is stored into inline_data, there is no * performance regression. */ - if (!err) + if (!err) { filemap_write_and_wait_range(inode->i_mapping, 0, p_len - 1); - if (IS_DIRSYNC(dir)) - f2fs_sync_fs(sbi->sb, 1); + if (IS_DIRSYNC(dir)) + f2fs_sync_fs(sbi->sb, 1); + } else { + f2fs_unlink(dir, dentry); + } kfree(sd); f2fs_fname_crypto_free_buffer(&disk_link); @@ -478,9 +481,6 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry, struct inode *inode; int err = 0; - if (!new_valid_dev(rdev)) - return -EINVAL; - f2fs_balance_fs(sbi); inode = f2fs_new_inode(dir, mode); @@ -947,8 +947,13 @@ static const char *f2fs_encrypted_follow_link(struct dentry *dentry, void **cook /* Symlink is encrypted */ sd = (struct f2fs_encrypted_symlink_data *)caddr; - cstr.name = sd->encrypted_path; cstr.len = le16_to_cpu(sd->len); + cstr.name = kmalloc(cstr.len, GFP_NOFS); + if (!cstr.name) { + res = -ENOMEM; + goto errout; + } + memcpy(cstr.name, sd->encrypted_path, cstr.len); /* this is broken symlink case */ if (cstr.name[0] == 0 && cstr.len == 0) { @@ -970,6 +975,8 @@ static const char *f2fs_encrypted_follow_link(struct dentry *dentry, void **cook if (res < 0) goto errout; + kfree(cstr.name); + paddr = pstr.name; /* Null-terminate the name */ @@ -979,6 +986,7 @@ static const char *f2fs_encrypted_follow_link(struct dentry *dentry, void **cook page_cache_release(cpage); return *cookie = paddr; errout: + kfree(cstr.name); f2fs_fname_crypto_free_buffer(&pstr); kunmap(cpage); page_cache_release(cpage); diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 27d1a74..7bcbc6e 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -1323,23 +1323,24 @@ static int f2fs_write_node_page(struct page *page, nid = nid_of_node(page); f2fs_bug_on(sbi, page->index != nid); + if (wbc->for_reclaim) { + if (!down_read_trylock(&sbi->node_write)) + goto redirty_out; + } else { + down_read(&sbi->node_write); + } + get_node_info(sbi, nid, &ni); /* This page is already truncated */ if (unlikely(ni.blk_addr == NULL_ADDR)) { ClearPageUptodate(page); dec_page_count(sbi, F2FS_DIRTY_NODES); + up_read(&sbi->node_write); unlock_page(page); return 0; } - if (wbc->for_reclaim) { - if (!down_read_trylock(&sbi->node_write)) - goto redirty_out; - } else { - down_read(&sbi->node_write); - } - set_page_writeback(page); fio.blk_addr = ni.blk_addr; write_node_page(nid, &fio); @@ -1528,7 +1529,8 @@ static void build_free_nids(struct f2fs_sb_info *sbi) return; /* readahead nat pages to be scanned */ - ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), FREE_NID_PAGES, META_NAT); + ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), FREE_NID_PAGES, + META_NAT, true); while (1) { struct page *page = get_current_nat_page(sbi, nid); @@ -1558,6 +1560,9 @@ static void build_free_nids(struct f2fs_sb_info *sbi) remove_free_nid(nm_i, nid); } mutex_unlock(&curseg->curseg_mutex); + + ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nm_i->next_scan_nid), + nm_i->ra_nid_pages, META_NAT, false); } /* @@ -1803,10 +1808,10 @@ int restore_node_summary(struct f2fs_sb_info *sbi, nrpages = min(last_offset - i, bio_blocks); /* readahead node pages */ - ra_meta_pages(sbi, addr, nrpages, META_POR); + ra_meta_pages(sbi, addr, nrpages, META_POR, true); for (idx = addr; idx < addr + nrpages; idx++) { - struct page *page = get_meta_page(sbi, idx); + struct page *page = get_tmp_page(sbi, idx); rn = F2FS_NODE(page); sum_entry->nid = rn->footer.nid; @@ -2000,6 +2005,7 @@ static int init_node_manager(struct f2fs_sb_info *sbi) nm_i->fcnt = 0; nm_i->nat_cnt = 0; nm_i->ram_thresh = DEF_RAM_THRESHOLD; + nm_i->ra_nid_pages = DEF_RA_NID_PAGES; INIT_RADIX_TREE(&nm_i->free_nid_root, GFP_ATOMIC); INIT_LIST_HEAD(&nm_i->free_nid_list); diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h index 7427e95..e4fffd2 100644 --- a/fs/f2fs/node.h +++ b/fs/f2fs/node.h @@ -14,9 +14,11 @@ /* node block offset on the NAT area dedicated to the given start node id */ #define NAT_BLOCK_OFFSET(start_nid) (start_nid / NAT_ENTRY_PER_BLOCK) -/* # of pages to perform readahead before building free nids */ +/* # of pages to perform synchronous readahead before building free nids */ #define FREE_NID_PAGES 4 +#define DEF_RA_NID_PAGES 4 /* # of nid pages to be readaheaded */ + /* maximum readahead size for node during getting data blocks */ #define MAX_RA_NODE 128 diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index faec2ca..cbf74f4 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -180,7 +180,7 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head) curseg = CURSEG_I(sbi, CURSEG_WARM_NODE); blkaddr = NEXT_FREE_BLKADDR(sbi, curseg); - ra_meta_pages(sbi, blkaddr, 1, META_POR); + ra_meta_pages(sbi, blkaddr, 1, META_POR, true); while (1) { struct fsync_inode_entry *entry; @@ -188,7 +188,7 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head) if (!is_valid_blkaddr(sbi, blkaddr, META_POR)) return 0; - page = get_meta_page(sbi, blkaddr); + page = get_tmp_page(sbi, blkaddr); if (cp_ver != cpver_of_node(page)) break; @@ -383,15 +383,11 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode, start = start_bidx_of_node(ofs_of_node(page), fi); end = start + ADDRS_PER_PAGE(page, fi); - f2fs_lock_op(sbi); - set_new_dnode(&dn, inode, NULL, NULL, 0); err = get_dnode_of_data(&dn, start, ALLOC_NODE); - if (err) { - f2fs_unlock_op(sbi); + if (err) goto out; - } f2fs_wait_on_page_writeback(dn.node_page, NODE); @@ -456,7 +452,6 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode, set_page_dirty(dn.node_page); err: f2fs_put_dnode(&dn); - f2fs_unlock_op(sbi); out: f2fs_msg(sbi->sb, KERN_NOTICE, "recover_data: ino = %lx, recovered = %d blocks, err = %d", @@ -485,7 +480,7 @@ static int recover_data(struct f2fs_sb_info *sbi, ra_meta_pages_cond(sbi, blkaddr); - page = get_meta_page(sbi, blkaddr); + page = get_tmp_page(sbi, blkaddr); if (cp_ver != cpver_of_node(page)) { f2fs_put_page(page, 1); @@ -570,7 +565,7 @@ out: /* truncate meta pages to be used by the recovery */ truncate_inode_pages_range(META_MAPPING(sbi), - MAIN_BLKADDR(sbi) << PAGE_CACHE_SHIFT, -1); + (loff_t)MAIN_BLKADDR(sbi) << PAGE_CACHE_SHIFT, -1); if (err) { truncate_inode_pages_final(NODE_MAPPING(sbi)); diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 78e6d06..f77b325 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -14,8 +14,8 @@ #include <linux/blkdev.h> #include <linux/prefetch.h> #include <linux/kthread.h> -#include <linux/vmalloc.h> #include <linux/swap.h> +#include <linux/timer.h> #include "f2fs.h" #include "segment.h" @@ -29,6 +29,21 @@ static struct kmem_cache *discard_entry_slab; static struct kmem_cache *sit_entry_set_slab; static struct kmem_cache *inmem_entry_slab; +static unsigned long __reverse_ulong(unsigned char *str) +{ + unsigned long tmp = 0; + int shift = 24, idx = 0; + +#if BITS_PER_LONG == 64 + shift = 56; +#endif + while (shift >= 0) { + tmp |= (unsigned long)str[idx++] << shift; + shift -= BITS_PER_BYTE; + } + return tmp; +} + /* * __reverse_ffs is copied from include/asm-generic/bitops/__ffs.h since * MSB and LSB are reversed in a byte by f2fs_set_bit. @@ -38,27 +53,31 @@ static inline unsigned long __reverse_ffs(unsigned long word) int num = 0; #if BITS_PER_LONG == 64 - if ((word & 0xffffffff) == 0) { + if ((word & 0xffffffff00000000UL) == 0) num += 32; + else word >>= 32; - } #endif - if ((word & 0xffff) == 0) { + if ((word & 0xffff0000) == 0) num += 16; + else word >>= 16; - } - if ((word & 0xff) == 0) { + + if ((word & 0xff00) == 0) num += 8; + else word >>= 8; - } + if ((word & 0xf0) == 0) num += 4; else word >>= 4; + if ((word & 0xc) == 0) num += 2; else word >>= 2; + if ((word & 0x2) == 0) num += 1; return num; @@ -68,26 +87,16 @@ static inline unsigned long __reverse_ffs(unsigned long word) * __find_rev_next(_zero)_bit is copied from lib/find_next_bit.c because * f2fs_set_bit makes MSB and LSB reversed in a byte. * Example: - * LSB <--> MSB - * f2fs_set_bit(0, bitmap) => 0000 0001 - * f2fs_set_bit(7, bitmap) => 1000 0000 + * MSB <--> LSB + * f2fs_set_bit(0, bitmap) => 1000 0000 + * f2fs_set_bit(7, bitmap) => 0000 0001 */ static unsigned long __find_rev_next_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { - while (!f2fs_test_bit(offset, (unsigned char *)addr)) - offset++; - - if (offset > size) - offset = size; - - return offset; -#if 0 const unsigned long *p = addr + BIT_WORD(offset); unsigned long result = offset & ~(BITS_PER_LONG - 1); unsigned long tmp; - unsigned long mask, submask; - unsigned long quot, rest; if (offset >= size) return size; @@ -97,14 +106,9 @@ static unsigned long __find_rev_next_bit(const unsigned long *addr, if (!offset) goto aligned; - tmp = *(p++); - quot = (offset >> 3) << 3; - rest = offset & 0x7; - mask = ~0UL << quot; - submask = (unsigned char)(0xff << rest) >> rest; - submask <<= quot; - mask &= submask; - tmp &= mask; + tmp = __reverse_ulong((unsigned char *)p); + tmp &= ~0UL >> offset; + if (size < BITS_PER_LONG) goto found_first; if (tmp) @@ -112,42 +116,34 @@ static unsigned long __find_rev_next_bit(const unsigned long *addr, size -= BITS_PER_LONG; result += BITS_PER_LONG; + p++; aligned: while (size & ~(BITS_PER_LONG-1)) { - tmp = *(p++); + tmp = __reverse_ulong((unsigned char *)p); if (tmp) goto found_middle; result += BITS_PER_LONG; size -= BITS_PER_LONG; + p++; } if (!size) return result; - tmp = *p; + + tmp = __reverse_ulong((unsigned char *)p); found_first: - tmp &= (~0UL >> (BITS_PER_LONG - size)); - if (tmp == 0UL) /* Are any bits set? */ + tmp &= (~0UL << (BITS_PER_LONG - size)); + if (!tmp) /* Are any bits set? */ return result + size; /* Nope. */ found_middle: return result + __reverse_ffs(tmp); -#endif } static unsigned long __find_rev_next_zero_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { - while (f2fs_test_bit(offset, (unsigned char *)addr)) - offset++; - - if (offset > size) - offset = size; - - return offset; -#if 0 const unsigned long *p = addr + BIT_WORD(offset); unsigned long result = offset & ~(BITS_PER_LONG - 1); unsigned long tmp; - unsigned long mask, submask; - unsigned long quot, rest; if (offset >= size) return size; @@ -157,40 +153,36 @@ static unsigned long __find_rev_next_zero_bit(const unsigned long *addr, if (!offset) goto aligned; - tmp = *(p++); - quot = (offset >> 3) << 3; - rest = offset & 0x7; - mask = ~(~0UL << quot); - submask = (unsigned char)~((unsigned char)(0xff << rest) >> rest); - submask <<= quot; - mask += submask; - tmp |= mask; + tmp = __reverse_ulong((unsigned char *)p); + tmp |= ~((~0UL << offset) >> offset); + if (size < BITS_PER_LONG) goto found_first; - if (~tmp) + if (tmp != ~0UL) goto found_middle; size -= BITS_PER_LONG; result += BITS_PER_LONG; + p++; aligned: while (size & ~(BITS_PER_LONG - 1)) { - tmp = *(p++); - if (~tmp) + tmp = __reverse_ulong((unsigned char *)p); + if (tmp != ~0UL) goto found_middle; result += BITS_PER_LONG; size -= BITS_PER_LONG; + p++; } if (!size) return result; - tmp = *p; + tmp = __reverse_ulong((unsigned char *)p); found_first: - tmp |= ~0UL << size; - if (tmp == ~0UL) /* Are any bits zero? */ + tmp |= ~(~0UL << (BITS_PER_LONG - size)); + if (tmp == ~0UL) /* Are any bits zero? */ return result + size; /* Nope. */ found_middle: return result + __reverse_ffz(tmp); -#endif } void register_inmem_page(struct inode *inode, struct page *page) @@ -257,11 +249,12 @@ int commit_inmem_pages(struct inode *inode, bool abort) trace_f2fs_commit_inmem_page(cur->page, INMEM); fio.page = cur->page; err = do_write_data_page(&fio); - submit_bio = true; if (err) { unlock_page(cur->page); break; } + clear_cold_data(cur->page); + submit_bio = true; } } else { trace_f2fs_commit_inmem_page(cur->page, INMEM_DROP); @@ -296,7 +289,7 @@ void f2fs_balance_fs(struct f2fs_sb_info *sbi) */ if (has_not_enough_free_secs(sbi, 0)) { mutex_lock(&sbi->gc_mutex); - f2fs_gc(sbi); + f2fs_gc(sbi, false); } } @@ -316,7 +309,8 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi) /* checkpoint is the only way to shrink partial cached entries */ if (!available_free_memory(sbi, NAT_ENTRIES) || excess_prefree_segs(sbi) || - !available_free_memory(sbi, INO_ENTRIES)) + !available_free_memory(sbi, INO_ENTRIES) || + jiffies > sbi->cp_expires) f2fs_sync_fs(sbi->sb, true); } @@ -767,6 +761,30 @@ void invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr) mutex_unlock(&sit_i->sentry_lock); } +bool is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr) +{ + struct sit_info *sit_i = SIT_I(sbi); + unsigned int segno, offset; + struct seg_entry *se; + bool is_cp = false; + + if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR) + return true; + + mutex_lock(&sit_i->sentry_lock); + + segno = GET_SEGNO(sbi, blkaddr); + se = get_seg_entry(sbi, segno); + offset = GET_BLKOFF_FROM_SEG0(sbi, blkaddr); + + if (f2fs_test_bit(offset, se->ckpt_valid_map)) + is_cp = true; + + mutex_unlock(&sit_i->sentry_lock); + + return is_cp; +} + /* * This function should be resided under the curseg_mutex lock */ @@ -1292,6 +1310,9 @@ void write_meta_page(struct f2fs_sb_info *sbi, struct page *page) .encrypted_page = NULL, }; + if (unlikely(page->index >= MAIN_BLKADDR(sbi))) + fio.rw &= ~REQ_META; + set_page_writeback(page); f2fs_submit_page_mbio(&fio); } @@ -1369,7 +1390,14 @@ static void __f2fs_replace_block(struct f2fs_sb_info *sbi, curseg->next_blkoff = GET_BLKOFF_FROM_SEG0(sbi, new_blkaddr); __add_sum_entry(sbi, type, sum); - refresh_sit_entry(sbi, old_blkaddr, new_blkaddr); + if (!recover_curseg) + update_sit_entry(sbi, new_blkaddr, 1); + if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO) + update_sit_entry(sbi, old_blkaddr, -1); + + locate_dirty_segment(sbi, GET_SEGNO(sbi, old_blkaddr)); + locate_dirty_segment(sbi, GET_SEGNO(sbi, new_blkaddr)); + locate_dirty_segment(sbi, old_cursegno); if (recover_curseg) { @@ -1449,6 +1477,23 @@ void f2fs_wait_on_page_writeback(struct page *page, } } +void f2fs_wait_on_encrypted_page_writeback(struct f2fs_sb_info *sbi, + block_t blkaddr) +{ + struct page *cpage; + + if (blkaddr == NEW_ADDR) + return; + + f2fs_bug_on(sbi, blkaddr == NULL_ADDR); + + cpage = find_lock_page(META_MAPPING(sbi), blkaddr); + if (cpage) { + f2fs_wait_on_page_writeback(cpage, DATA); + f2fs_put_page(cpage, 1); + } +} + static int read_compacted_summaries(struct f2fs_sb_info *sbi) { struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); @@ -1586,7 +1631,7 @@ static int restore_curseg_summaries(struct f2fs_sb_info *sbi) if (npages >= 2) ra_meta_pages(sbi, start_sum_block(sbi), npages, - META_CP); + META_CP, true); /* restore for compacted data summary */ if (read_compacted_summaries(sbi)) @@ -1596,7 +1641,7 @@ static int restore_curseg_summaries(struct f2fs_sb_info *sbi) if (__exist_node_summaries(sbi)) ra_meta_pages(sbi, sum_blk_addr(sbi, NR_CURSEG_TYPE, type), - NR_CURSEG_TYPE - type, META_CP); + NR_CURSEG_TYPE - type, META_CP, true); for (; type <= CURSEG_COLD_NODE; type++) { err = read_normal_summaries(sbi, type); @@ -1955,12 +2000,13 @@ static int build_sit_info(struct f2fs_sb_info *sbi) SM_I(sbi)->sit_info = sit_i; - sit_i->sentries = vzalloc(MAIN_SEGS(sbi) * sizeof(struct seg_entry)); + sit_i->sentries = f2fs_kvzalloc(MAIN_SEGS(sbi) * + sizeof(struct seg_entry), GFP_KERNEL); if (!sit_i->sentries) return -ENOMEM; bitmap_size = f2fs_bitmap_size(MAIN_SEGS(sbi)); - sit_i->dirty_sentries_bitmap = kzalloc(bitmap_size, GFP_KERNEL); + sit_i->dirty_sentries_bitmap = f2fs_kvzalloc(bitmap_size, GFP_KERNEL); if (!sit_i->dirty_sentries_bitmap) return -ENOMEM; @@ -1982,8 +2028,8 @@ static int build_sit_info(struct f2fs_sb_info *sbi) return -ENOMEM; if (sbi->segs_per_sec > 1) { - sit_i->sec_entries = vzalloc(MAIN_SECS(sbi) * - sizeof(struct sec_entry)); + sit_i->sec_entries = f2fs_kvzalloc(MAIN_SECS(sbi) * + sizeof(struct sec_entry), GFP_KERNEL); if (!sit_i->sec_entries) return -ENOMEM; } @@ -2028,12 +2074,12 @@ static int build_free_segmap(struct f2fs_sb_info *sbi) SM_I(sbi)->free_info = free_i; bitmap_size = f2fs_bitmap_size(MAIN_SEGS(sbi)); - free_i->free_segmap = kmalloc(bitmap_size, GFP_KERNEL); + free_i->free_segmap = f2fs_kvmalloc(bitmap_size, GFP_KERNEL); if (!free_i->free_segmap) return -ENOMEM; sec_bitmap_size = f2fs_bitmap_size(MAIN_SECS(sbi)); - free_i->free_secmap = kmalloc(sec_bitmap_size, GFP_KERNEL); + free_i->free_secmap = f2fs_kvmalloc(sec_bitmap_size, GFP_KERNEL); if (!free_i->free_secmap) return -ENOMEM; @@ -2082,7 +2128,7 @@ static void build_sit_entries(struct f2fs_sb_info *sbi) int nrpages = MAX_BIO_BLOCKS(sbi); do { - readed = ra_meta_pages(sbi, start_blk, nrpages, META_SIT); + readed = ra_meta_pages(sbi, start_blk, nrpages, META_SIT, true); start = start_blk * sit_i->sents_per_block; end = (start_blk + readed) * sit_i->sents_per_block; @@ -2174,7 +2220,7 @@ static int init_victim_secmap(struct f2fs_sb_info *sbi) struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); unsigned int bitmap_size = f2fs_bitmap_size(MAIN_SECS(sbi)); - dirty_i->victim_secmap = kzalloc(bitmap_size, GFP_KERNEL); + dirty_i->victim_secmap = f2fs_kvzalloc(bitmap_size, GFP_KERNEL); if (!dirty_i->victim_secmap) return -ENOMEM; return 0; @@ -2196,7 +2242,7 @@ static int build_dirty_segmap(struct f2fs_sb_info *sbi) bitmap_size = f2fs_bitmap_size(MAIN_SEGS(sbi)); for (i = 0; i < NR_DIRTY_TYPE; i++) { - dirty_i->dirty_segmap[i] = kzalloc(bitmap_size, GFP_KERNEL); + dirty_i->dirty_segmap[i] = f2fs_kvzalloc(bitmap_size, GFP_KERNEL); if (!dirty_i->dirty_segmap[i]) return -ENOMEM; } @@ -2301,7 +2347,7 @@ static void discard_dirty_segmap(struct f2fs_sb_info *sbi, struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); mutex_lock(&dirty_i->seglist_lock); - kfree(dirty_i->dirty_segmap[dirty_type]); + kvfree(dirty_i->dirty_segmap[dirty_type]); dirty_i->nr_dirty[dirty_type] = 0; mutex_unlock(&dirty_i->seglist_lock); } @@ -2309,7 +2355,7 @@ static void discard_dirty_segmap(struct f2fs_sb_info *sbi, static void destroy_victim_secmap(struct f2fs_sb_info *sbi) { struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); - kfree(dirty_i->victim_secmap); + kvfree(dirty_i->victim_secmap); } static void destroy_dirty_segmap(struct f2fs_sb_info *sbi) @@ -2348,8 +2394,8 @@ static void destroy_free_segmap(struct f2fs_sb_info *sbi) if (!free_i) return; SM_I(sbi)->free_info = NULL; - kfree(free_i->free_segmap); - kfree(free_i->free_secmap); + kvfree(free_i->free_segmap); + kvfree(free_i->free_secmap); kfree(free_i); } @@ -2370,9 +2416,9 @@ static void destroy_sit_info(struct f2fs_sb_info *sbi) } kfree(sit_i->tmp_map); - vfree(sit_i->sentries); - vfree(sit_i->sec_entries); - kfree(sit_i->dirty_sentries_bitmap); + kvfree(sit_i->sentries); + kvfree(sit_i->sec_entries); + kvfree(sit_i->dirty_sentries_bitmap); SM_I(sbi)->sit_info = NULL; kfree(sit_i->sit_bitmap); diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h index b6e4ed1..ee44d34 100644 --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -137,10 +137,12 @@ enum { /* * BG_GC means the background cleaning job. * FG_GC means the on-demand cleaning job. + * FORCE_FG_GC means on-demand cleaning job in background. */ enum { BG_GC = 0, - FG_GC + FG_GC, + FORCE_FG_GC, }; /* for a function parameter to select a victim segment */ diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index f794781..3a65e01 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -213,8 +213,10 @@ F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, ipu_policy, ipu_policy); F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_ipu_util, min_ipu_util); F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_fsync_blocks, min_fsync_blocks); F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ram_thresh, ram_thresh); +F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ra_nid_pages, ra_nid_pages); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, max_victim_search, max_victim_search); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, dir_level, dir_level); +F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, cp_interval, cp_interval); #define ATTR_LIST(name) (&f2fs_attr_##name.attr) static struct attribute *f2fs_attrs[] = { @@ -231,6 +233,8 @@ static struct attribute *f2fs_attrs[] = { ATTR_LIST(max_victim_search), ATTR_LIST(dir_level), ATTR_LIST(ram_thresh), + ATTR_LIST(ra_nid_pages), + ATTR_LIST(cp_interval), NULL, }; @@ -292,11 +296,16 @@ static int parse_options(struct super_block *sb, char *options) if (!name) return -ENOMEM; - if (strlen(name) == 2 && !strncmp(name, "on", 2)) + if (strlen(name) == 2 && !strncmp(name, "on", 2)) { set_opt(sbi, BG_GC); - else if (strlen(name) == 3 && !strncmp(name, "off", 3)) + clear_opt(sbi, FORCE_FG_GC); + } else if (strlen(name) == 3 && !strncmp(name, "off", 3)) { clear_opt(sbi, BG_GC); - else { + clear_opt(sbi, FORCE_FG_GC); + } else if (strlen(name) == 4 && !strncmp(name, "sync", 4)) { + set_opt(sbi, BG_GC); + set_opt(sbi, FORCE_FG_GC); + } else { kfree(name); return -EINVAL; } @@ -631,10 +640,14 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) { struct f2fs_sb_info *sbi = F2FS_SB(root->d_sb); - if (!f2fs_readonly(sbi->sb) && test_opt(sbi, BG_GC)) - seq_printf(seq, ",background_gc=%s", "on"); - else + if (!f2fs_readonly(sbi->sb) && test_opt(sbi, BG_GC)) { + if (test_opt(sbi, FORCE_FG_GC)) + seq_printf(seq, ",background_gc=%s", "sync"); + else + seq_printf(seq, ",background_gc=%s", "on"); + } else { seq_printf(seq, ",background_gc=%s", "off"); + } if (test_opt(sbi, DISABLE_ROLL_FORWARD)) seq_puts(seq, ",disable_roll_forward"); if (test_opt(sbi, DISCARD)) @@ -742,6 +755,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) int err, active_logs; bool need_restart_gc = false; bool need_stop_gc = false; + bool no_extent_cache = !test_opt(sbi, EXTENT_CACHE); sync_filesystem(sb); @@ -767,6 +781,14 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) if (f2fs_readonly(sb) && (*flags & MS_RDONLY)) goto skip; + /* disallow enable/disable extent_cache dynamically */ + if (no_extent_cache == !!test_opt(sbi, EXTENT_CACHE)) { + err = -EINVAL; + f2fs_msg(sbi->sb, KERN_WARNING, + "switch extent_cache option is not allowed"); + goto restore_opts; + } + /* * We stop the GC thread if FS is mounted as RO * or if background_gc = off is passed in mount @@ -996,6 +1018,7 @@ static void init_sb_info(struct f2fs_sb_info *sbi) atomic_set(&sbi->nr_pages[i], 0); sbi->dir_level = DEF_DIR_LEVEL; + sbi->cp_interval = DEF_CP_INTERVAL; clear_sbi_flag(sbi, SBI_NEED_FSCK); INIT_LIST_HEAD(&sbi->s_list); @@ -1332,6 +1355,8 @@ try_onemore: f2fs_commit_super(sbi, true); } + sbi->cp_expires = round_jiffies_up(jiffies); + return 0; free_kobj: @@ -56,9 +56,35 @@ static void free_fdtable_rcu(struct rcu_head *rcu) __free_fdtable(container_of(rcu, struct fdtable, rcu)); } +#define BITBIT_NR(nr) BITS_TO_LONGS(BITS_TO_LONGS(nr)) +#define BITBIT_SIZE(nr) (BITBIT_NR(nr) * sizeof(long)) + +/* + * Copy 'count' fd bits from the old table to the new table and clear the extra + * space if any. This does not copy the file pointers. Called with the files + * spinlock held for write. + */ +static void copy_fd_bitmaps(struct fdtable *nfdt, struct fdtable *ofdt, + unsigned int count) +{ + unsigned int cpy, set; + + cpy = count / BITS_PER_BYTE; + set = (nfdt->max_fds - count) / BITS_PER_BYTE; + memcpy(nfdt->open_fds, ofdt->open_fds, cpy); + memset((char *)nfdt->open_fds + cpy, 0, set); + memcpy(nfdt->close_on_exec, ofdt->close_on_exec, cpy); + memset((char *)nfdt->close_on_exec + cpy, 0, set); + + cpy = BITBIT_SIZE(count); + set = BITBIT_SIZE(nfdt->max_fds) - cpy; + memcpy(nfdt->full_fds_bits, ofdt->full_fds_bits, cpy); + memset((char *)nfdt->full_fds_bits + cpy, 0, set); +} + /* - * Expand the fdset in the files_struct. Called with the files spinlock - * held for write. + * Copy all file descriptors from the old table to the new, expanded table and + * clear the extra space. Called with the files spinlock held for write. */ static void copy_fdtable(struct fdtable *nfdt, struct fdtable *ofdt) { @@ -69,14 +95,9 @@ static void copy_fdtable(struct fdtable *nfdt, struct fdtable *ofdt) cpy = ofdt->max_fds * sizeof(struct file *); set = (nfdt->max_fds - ofdt->max_fds) * sizeof(struct file *); memcpy(nfdt->fd, ofdt->fd, cpy); - memset((char *)(nfdt->fd) + cpy, 0, set); + memset((char *)nfdt->fd + cpy, 0, set); - cpy = ofdt->max_fds / BITS_PER_BYTE; - set = (nfdt->max_fds - ofdt->max_fds) / BITS_PER_BYTE; - memcpy(nfdt->open_fds, ofdt->open_fds, cpy); - memset((char *)(nfdt->open_fds) + cpy, 0, set); - memcpy(nfdt->close_on_exec, ofdt->close_on_exec, cpy); - memset((char *)(nfdt->close_on_exec) + cpy, 0, set); + copy_fd_bitmaps(nfdt, ofdt, ofdt->max_fds); } static struct fdtable * alloc_fdtable(unsigned int nr) @@ -115,12 +136,14 @@ static struct fdtable * alloc_fdtable(unsigned int nr) fdt->fd = data; data = alloc_fdmem(max_t(size_t, - 2 * nr / BITS_PER_BYTE, L1_CACHE_BYTES)); + 2 * nr / BITS_PER_BYTE + BITBIT_SIZE(nr), L1_CACHE_BYTES)); if (!data) goto out_arr; fdt->open_fds = data; data += nr / BITS_PER_BYTE; fdt->close_on_exec = data; + data += nr / BITS_PER_BYTE; + fdt->full_fds_bits = data; return fdt; @@ -226,17 +249,22 @@ static inline void __set_close_on_exec(int fd, struct fdtable *fdt) static inline void __clear_close_on_exec(int fd, struct fdtable *fdt) { - __clear_bit(fd, fdt->close_on_exec); + if (test_bit(fd, fdt->close_on_exec)) + __clear_bit(fd, fdt->close_on_exec); } -static inline void __set_open_fd(int fd, struct fdtable *fdt) +static inline void __set_open_fd(unsigned int fd, struct fdtable *fdt) { __set_bit(fd, fdt->open_fds); + fd /= BITS_PER_LONG; + if (!~fdt->open_fds[fd]) + __set_bit(fd, fdt->full_fds_bits); } -static inline void __clear_open_fd(int fd, struct fdtable *fdt) +static inline void __clear_open_fd(unsigned int fd, struct fdtable *fdt) { __clear_bit(fd, fdt->open_fds); + __clear_bit(fd / BITS_PER_LONG, fdt->full_fds_bits); } static int count_open_files(struct fdtable *fdt) @@ -262,7 +290,7 @@ struct files_struct *dup_fd(struct files_struct *oldf, int *errorp) { struct files_struct *newf; struct file **old_fds, **new_fds; - int open_files, size, i; + int open_files, i; struct fdtable *old_fdt, *new_fdt; *errorp = -ENOMEM; @@ -280,6 +308,7 @@ struct files_struct *dup_fd(struct files_struct *oldf, int *errorp) new_fdt->max_fds = NR_OPEN_DEFAULT; new_fdt->close_on_exec = newf->close_on_exec_init; new_fdt->open_fds = newf->open_fds_init; + new_fdt->full_fds_bits = newf->full_fds_bits_init; new_fdt->fd = &newf->fd_array[0]; spin_lock(&oldf->file_lock); @@ -318,12 +347,11 @@ struct files_struct *dup_fd(struct files_struct *oldf, int *errorp) open_files = count_open_files(old_fdt); } + copy_fd_bitmaps(new_fdt, old_fdt, open_files); + old_fds = old_fdt->fd; new_fds = new_fdt->fd; - memcpy(new_fdt->open_fds, old_fdt->open_fds, open_files / 8); - memcpy(new_fdt->close_on_exec, old_fdt->close_on_exec, open_files / 8); - for (i = open_files; i != 0; i--) { struct file *f = *old_fds++; if (f) { @@ -341,19 +369,8 @@ struct files_struct *dup_fd(struct files_struct *oldf, int *errorp) } spin_unlock(&oldf->file_lock); - /* compute the remainder to be cleared */ - size = (new_fdt->max_fds - open_files) * sizeof(struct file *); - - /* This is long word aligned thus could use a optimized version */ - memset(new_fds, 0, size); - - if (new_fdt->max_fds > open_files) { - int left = (new_fdt->max_fds - open_files) / 8; - int start = open_files / BITS_PER_LONG; - - memset(&new_fdt->open_fds[start], 0, left); - memset(&new_fdt->close_on_exec[start], 0, left); - } + /* clear the remainder */ + memset(new_fds, 0, (new_fdt->max_fds - open_files) * sizeof(struct file *)); rcu_assign_pointer(newf->fdt, new_fdt); @@ -454,10 +471,25 @@ struct files_struct init_files = { .fd = &init_files.fd_array[0], .close_on_exec = init_files.close_on_exec_init, .open_fds = init_files.open_fds_init, + .full_fds_bits = init_files.full_fds_bits_init, }, .file_lock = __SPIN_LOCK_UNLOCKED(init_files.file_lock), }; +static unsigned long find_next_fd(struct fdtable *fdt, unsigned long start) +{ + unsigned long maxfd = fdt->max_fds; + unsigned long maxbit = maxfd / BITS_PER_LONG; + unsigned long bitbit = start / BITS_PER_LONG; + + bitbit = find_next_zero_bit(fdt->full_fds_bits, maxbit, bitbit) * BITS_PER_LONG; + if (bitbit > maxfd) + return maxfd; + if (bitbit > start) + start = bitbit; + return find_next_zero_bit(fdt->open_fds, maxfd, start); +} + /* * allocate a file descriptor, mark it busy. */ @@ -476,7 +508,7 @@ repeat: fd = files->next_fd; if (fd < fdt->max_fds) - fd = find_next_zero_bit(fdt->open_fds, fdt->max_fds, fd); + fd = find_next_fd(fdt, fd); /* * N.B. For clone tasks sharing a files structure, this test diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 091a364..023f6a1 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -778,19 +778,24 @@ static void bdi_split_work_to_wbs(struct backing_dev_info *bdi, struct wb_writeback_work *base_work, bool skip_if_busy) { - int next_memcg_id = 0; - struct bdi_writeback *wb; - struct wb_iter iter; + struct bdi_writeback *last_wb = NULL; + struct bdi_writeback *wb = list_entry(&bdi->wb_list, + struct bdi_writeback, bdi_node); might_sleep(); restart: rcu_read_lock(); - bdi_for_each_wb(wb, bdi, &iter, next_memcg_id) { + list_for_each_entry_continue_rcu(wb, &bdi->wb_list, bdi_node) { DEFINE_WB_COMPLETION_ONSTACK(fallback_work_done); struct wb_writeback_work fallback_work; struct wb_writeback_work *work; long nr_pages; + if (last_wb) { + wb_put(last_wb); + last_wb = NULL; + } + /* SYNC_ALL writes out I_DIRTY_TIME too */ if (!wb_has_dirty_io(wb) && (base_work->sync_mode == WB_SYNC_NONE || @@ -819,12 +824,22 @@ restart: wb_queue_work(wb, work); - next_memcg_id = wb->memcg_css->id + 1; + /* + * Pin @wb so that it stays on @bdi->wb_list. This allows + * continuing iteration from @wb after dropping and + * regrabbing rcu read lock. + */ + wb_get(wb); + last_wb = wb; + rcu_read_unlock(); wb_wait_for_completion(bdi, &fallback_work_done); goto restart; } rcu_read_unlock(); + + if (last_wb) + wb_put(last_wb); } #else /* CONFIG_CGROUP_WRITEBACK */ @@ -1857,12 +1872,11 @@ void wakeup_flusher_threads(long nr_pages, enum wb_reason reason) rcu_read_lock(); list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) { struct bdi_writeback *wb; - struct wb_iter iter; if (!bdi_has_dirty_io(bdi)) continue; - bdi_for_each_wb(wb, bdi, &iter, 0) + list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node) wb_start_writeback(wb, wb_split_bdi_pages(wb, nr_pages), false, reason); } @@ -1894,11 +1908,10 @@ static void wakeup_dirtytime_writeback(struct work_struct *w) rcu_read_lock(); list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) { struct bdi_writeback *wb; - struct wb_iter iter; - bdi_for_each_wb(wb, bdi, &iter, 0) - if (!list_empty(&bdi->wb.b_dirty_time)) - wb_wakeup(&bdi->wb); + list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node) + if (!list_empty(&wb->b_dirty_time)) + wb_wakeup(wb); } rcu_read_unlock(); schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ); @@ -1968,9 +1981,9 @@ static noinline void block_dump___mark_inode_dirty(struct inode *inode) * page->mapping->host, so the page-dirtying time is recorded in the internal * blockdev inode. */ -#define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) void __mark_inode_dirty(struct inode *inode, int flags) { +#define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) struct super_block *sb = inode->i_sb; int dirtytime; @@ -2080,6 +2093,7 @@ void __mark_inode_dirty(struct inode *inode, int flags) out_unlock_inode: spin_unlock(&inode->i_lock); +#undef I_DIRTY_INODE } EXPORT_SYMBOL(__mark_inode_dirty); @@ -2136,7 +2150,12 @@ static void wait_sb_inodes(struct super_block *sb) iput(old_inode); old_inode = inode; - filemap_fdatawait(mapping); + /* + * We keep the error status of individual mapping so that + * applications can catch the writeback error using fsync(2). + * See filemap_fdatawait_keep_errors() for details. + */ + filemap_fdatawait_keep_errors(mapping); cond_resched(); diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c index d403c69..43040721 100644 --- a/fs/fscache/cookie.c +++ b/fs/fscache/cookie.c @@ -111,7 +111,7 @@ struct fscache_cookie *__fscache_acquire_cookie( /* radix tree insertion won't use the preallocation pool unless it's * told it may not wait */ - INIT_RADIX_TREE(&cookie->stores, GFP_NOFS & ~__GFP_WAIT); + INIT_RADIX_TREE(&cookie->stores, GFP_NOFS & ~__GFP_DIRECT_RECLAIM); switch (cookie->def->type) { case FSCACHE_COOKIE_TYPE_INDEX: diff --git a/fs/fscache/netfs.c b/fs/fscache/netfs.c index 6d941f5..9b28649 100644 --- a/fs/fscache/netfs.c +++ b/fs/fscache/netfs.c @@ -22,6 +22,7 @@ static LIST_HEAD(fscache_netfs_list); int __fscache_register_netfs(struct fscache_netfs *netfs) { struct fscache_netfs *ptr; + struct fscache_cookie *cookie; int ret; _enter("{%s}", netfs->name); @@ -29,29 +30,25 @@ int __fscache_register_netfs(struct fscache_netfs *netfs) INIT_LIST_HEAD(&netfs->link); /* allocate a cookie for the primary index */ - netfs->primary_index = - kmem_cache_zalloc(fscache_cookie_jar, GFP_KERNEL); + cookie = kmem_cache_zalloc(fscache_cookie_jar, GFP_KERNEL); - if (!netfs->primary_index) { + if (!cookie) { _leave(" = -ENOMEM"); return -ENOMEM; } /* initialise the primary index cookie */ - atomic_set(&netfs->primary_index->usage, 1); - atomic_set(&netfs->primary_index->n_children, 0); - atomic_set(&netfs->primary_index->n_active, 1); + atomic_set(&cookie->usage, 1); + atomic_set(&cookie->n_children, 0); + atomic_set(&cookie->n_active, 1); - netfs->primary_index->def = &fscache_fsdef_netfs_def; - netfs->primary_index->parent = &fscache_fsdef_index; - netfs->primary_index->netfs_data = netfs; - netfs->primary_index->flags = 1 << FSCACHE_COOKIE_ENABLED; + cookie->def = &fscache_fsdef_netfs_def; + cookie->parent = &fscache_fsdef_index; + cookie->netfs_data = netfs; + cookie->flags = 1 << FSCACHE_COOKIE_ENABLED; - atomic_inc(&netfs->primary_index->parent->usage); - atomic_inc(&netfs->primary_index->parent->n_children); - - spin_lock_init(&netfs->primary_index->lock); - INIT_HLIST_HEAD(&netfs->primary_index->backing_objects); + spin_lock_init(&cookie->lock); + INIT_HLIST_HEAD(&cookie->backing_objects); /* check the netfs type is not already present */ down_write(&fscache_addremove_sem); @@ -62,6 +59,10 @@ int __fscache_register_netfs(struct fscache_netfs *netfs) goto already_registered; } + atomic_inc(&cookie->parent->usage); + atomic_inc(&cookie->parent->n_children); + + netfs->primary_index = cookie; list_add(&netfs->link, &fscache_netfs_list); ret = 0; @@ -70,11 +71,8 @@ int __fscache_register_netfs(struct fscache_netfs *netfs) already_registered: up_write(&fscache_addremove_sem); - if (ret < 0) { - netfs->primary_index->parent = NULL; - __fscache_cookie_put(netfs->primary_index); - netfs->primary_index = NULL; - } + if (ret < 0) + kmem_cache_free(fscache_cookie_jar, cookie); _leave(" = %d", ret); return ret; diff --git a/fs/fscache/object-list.c b/fs/fscache/object-list.c index 51dde81..6b028b7 100644 --- a/fs/fscache/object-list.c +++ b/fs/fscache/object-list.c @@ -316,7 +316,7 @@ static const struct seq_operations fscache_objlist_ops = { static void fscache_objlist_config(struct fscache_objlist_data *data) { #ifdef CONFIG_KEYS - struct user_key_payload *confkey; + const struct user_key_payload *confkey; unsigned long config; struct key *key; const char *buf; @@ -329,7 +329,7 @@ static void fscache_objlist_config(struct fscache_objlist_data *data) config = 0; rcu_read_lock(); - confkey = key->payload.data; + confkey = user_key_payload(key); buf = confkey->data; for (len = confkey->datalen - 1; len >= 0; len--) { diff --git a/fs/fscache/page.c b/fs/fscache/page.c index 483bbc6..6b35fc4 100644 --- a/fs/fscache/page.c +++ b/fs/fscache/page.c @@ -58,7 +58,7 @@ bool release_page_wait_timeout(struct fscache_cookie *cookie, struct page *page) /* * decide whether a page can be released, possibly by cancelling a store to it - * - we're allowed to sleep if __GFP_WAIT is flagged + * - we're allowed to sleep if __GFP_DIRECT_RECLAIM is flagged */ bool __fscache_maybe_release_page(struct fscache_cookie *cookie, struct page *page, @@ -122,7 +122,7 @@ page_busy: * allocator as the work threads writing to the cache may all end up * sleeping on memory allocation, so we may need to impose a timeout * too. */ - if (!(gfp & __GFP_WAIT) || !(gfp & __GFP_FS)) { + if (!(gfp & __GFP_DIRECT_RECLAIM) || !(gfp & __GFP_FS)) { fscache_stat(&fscache_n_store_vmscan_busy); return false; } @@ -132,7 +132,7 @@ page_busy: _debug("fscache writeout timeout page: %p{%lx}", page, page->index); - gfp &= ~__GFP_WAIT; + gfp &= ~__GFP_DIRECT_RECLAIM; goto try_again; } EXPORT_SYMBOL(__fscache_maybe_release_page); @@ -816,7 +816,7 @@ static void fscache_write_op(struct fscache_operation *_op) goto superseded; page = results[0]; _debug("gang %d [%lx]", n, page->index); - if (page->index > op->store_limit) { + if (page->index >= op->store_limit) { fscache_stat(&fscache_n_store_pages_over_limit); goto superseded; } diff --git a/fs/fuse/file.c b/fs/fuse/file.c index f523f2f..e0faf8f 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -2189,7 +2189,7 @@ static int fuse_file_flock(struct file *file, int cmd, struct file_lock *fl) int err; if (fc->no_flock) { - err = flock_lock_file_wait(file, fl); + err = locks_lock_file_wait(file, fl); } else { struct fuse_file *ff = file->private_data; diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c index 487527b..ad8a5b7 100644 --- a/fs/gfs2/dir.c +++ b/fs/gfs2/dir.c @@ -388,8 +388,13 @@ static __be64 *gfs2_dir_get_hash_table(struct gfs2_inode *ip) */ void gfs2_dir_hash_inval(struct gfs2_inode *ip) { - __be64 *hc = ip->i_hash_cache; + __be64 *hc; + + spin_lock(&ip->i_inode.i_lock); + hc = ip->i_hash_cache; ip->i_hash_cache = NULL; + spin_unlock(&ip->i_inode.i_lock); + kvfree(hc); } diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index cf4ab89..5e42546 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -897,8 +897,8 @@ static long __gfs2_fallocate(struct file *file, int mode, loff_t offset, loff_t if (!(mode & FALLOC_FL_KEEP_SIZE) && (pos + count) > inode->i_size) { i_size_write(inode, pos + count); - /* Marks the inode as dirty */ file_update_time(file); + mark_inode_dirty(inode); } return generic_write_sync(file, pos, count); @@ -1000,7 +1000,7 @@ static int gfs2_lock(struct file *file, int cmd, struct file_lock *fl) } if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) { if (fl->fl_type == F_UNLCK) - posix_lock_file_wait(file, fl); + locks_lock_file_wait(file, fl); return -EIO; } if (IS_GETLK(cmd)) @@ -1031,7 +1031,7 @@ static int do_flock(struct file *file, int cmd, struct file_lock *fl) if (gl) { if (fl_gh->gh_state == state) goto out; - flock_lock_file_wait(file, + locks_lock_file_wait(file, &(struct file_lock){.fl_type = F_UNLCK}); gfs2_glock_dq(fl_gh); gfs2_holder_reinit(state, flags, fl_gh); @@ -1056,7 +1056,7 @@ static int do_flock(struct file *file, int cmd, struct file_lock *fl) if (error == GLR_TRYFAILED) error = -EAGAIN; } else { - error = flock_lock_file_wait(file, fl); + error = locks_lock_file_wait(file, fl); gfs2_assert_warn(GFS2_SB(&ip->i_inode), !error); } @@ -1071,7 +1071,7 @@ static void do_unflock(struct file *file, struct file_lock *fl) struct gfs2_holder *fl_gh = &fp->f_fl_gh; mutex_lock(&fp->f_fl_mutex); - flock_lock_file_wait(file, fl); + locks_lock_file_wait(file, fl); if (fl_gh->gh_gl) { gfs2_glock_dq(fl_gh); gfs2_holder_uninit(fl_gh); diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 9bd1244..32e7471 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -246,8 +246,8 @@ static inline void do_error(struct gfs2_glock *gl, const int ret) */ static int do_promote(struct gfs2_glock *gl) -__releases(&gl->gl_spin) -__acquires(&gl->gl_spin) +__releases(&gl->gl_lockref.lock) +__acquires(&gl->gl_lockref.lock) { const struct gfs2_glock_operations *glops = gl->gl_ops; struct gfs2_holder *gh, *tmp; @@ -260,10 +260,10 @@ restart: if (may_grant(gl, gh)) { if (gh->gh_list.prev == &gl->gl_holders && glops->go_lock) { - spin_unlock(&gl->gl_spin); + spin_unlock(&gl->gl_lockref.lock); /* FIXME: eliminate this eventually */ ret = glops->go_lock(gh); - spin_lock(&gl->gl_spin); + spin_lock(&gl->gl_lockref.lock); if (ret) { if (ret == 1) return 2; @@ -361,7 +361,7 @@ static void finish_xmote(struct gfs2_glock *gl, unsigned int ret) unsigned state = ret & LM_OUT_ST_MASK; int rv; - spin_lock(&gl->gl_spin); + spin_lock(&gl->gl_lockref.lock); trace_gfs2_glock_state_change(gl, state); state_change(gl, state); gh = find_first_waiter(gl); @@ -405,7 +405,7 @@ retry: pr_err("wanted %u got %u\n", gl->gl_target, state); GLOCK_BUG_ON(gl, 1); } - spin_unlock(&gl->gl_spin); + spin_unlock(&gl->gl_lockref.lock); return; } @@ -414,9 +414,9 @@ retry: gfs2_demote_wake(gl); if (state != LM_ST_UNLOCKED) { if (glops->go_xmote_bh) { - spin_unlock(&gl->gl_spin); + spin_unlock(&gl->gl_lockref.lock); rv = glops->go_xmote_bh(gl, gh); - spin_lock(&gl->gl_spin); + spin_lock(&gl->gl_lockref.lock); if (rv) { do_error(gl, rv); goto out; @@ -429,7 +429,7 @@ retry: out: clear_bit(GLF_LOCK, &gl->gl_flags); out_locked: - spin_unlock(&gl->gl_spin); + spin_unlock(&gl->gl_lockref.lock); } /** @@ -441,8 +441,8 @@ out_locked: */ static void do_xmote(struct gfs2_glock *gl, struct gfs2_holder *gh, unsigned int target) -__releases(&gl->gl_spin) -__acquires(&gl->gl_spin) +__releases(&gl->gl_lockref.lock) +__acquires(&gl->gl_lockref.lock) { const struct gfs2_glock_operations *glops = gl->gl_ops; struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; @@ -464,7 +464,7 @@ __acquires(&gl->gl_spin) (gl->gl_state == LM_ST_EXCLUSIVE) || (lck_flags & (LM_FLAG_TRY|LM_FLAG_TRY_1CB))) clear_bit(GLF_BLOCKING, &gl->gl_flags); - spin_unlock(&gl->gl_spin); + spin_unlock(&gl->gl_lockref.lock); if (glops->go_sync) glops->go_sync(gl); if (test_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags)) @@ -485,7 +485,7 @@ __acquires(&gl->gl_spin) gfs2_glock_put(gl); } - spin_lock(&gl->gl_spin); + spin_lock(&gl->gl_lockref.lock); } /** @@ -513,8 +513,8 @@ static inline struct gfs2_holder *find_first_holder(const struct gfs2_glock *gl) */ static void run_queue(struct gfs2_glock *gl, const int nonblock) -__releases(&gl->gl_spin) -__acquires(&gl->gl_spin) +__releases(&gl->gl_lockref.lock) +__acquires(&gl->gl_lockref.lock) { struct gfs2_holder *gh = NULL; int ret; @@ -596,7 +596,7 @@ static void glock_work_func(struct work_struct *work) finish_xmote(gl, gl->gl_reply); drop_ref = 1; } - spin_lock(&gl->gl_spin); + spin_lock(&gl->gl_lockref.lock); if (test_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) && gl->gl_state != LM_ST_UNLOCKED && gl->gl_demote_state != LM_ST_EXCLUSIVE) { @@ -612,7 +612,7 @@ static void glock_work_func(struct work_struct *work) } } run_queue(gl, 0); - spin_unlock(&gl->gl_spin); + spin_unlock(&gl->gl_lockref.lock); if (!delay) gfs2_glock_put(gl); else { @@ -876,8 +876,8 @@ void gfs2_print_dbg(struct seq_file *seq, const char *fmt, ...) */ static inline void add_to_queue(struct gfs2_holder *gh) -__releases(&gl->gl_spin) -__acquires(&gl->gl_spin) +__releases(&gl->gl_lockref.lock) +__acquires(&gl->gl_lockref.lock) { struct gfs2_glock *gl = gh->gh_gl; struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; @@ -926,10 +926,10 @@ fail: do_cancel: gh = list_entry(gl->gl_holders.next, struct gfs2_holder, gh_list); if (!(gh->gh_flags & LM_FLAG_PRIORITY)) { - spin_unlock(&gl->gl_spin); + spin_unlock(&gl->gl_lockref.lock); if (sdp->sd_lockstruct.ls_ops->lm_cancel) sdp->sd_lockstruct.ls_ops->lm_cancel(gl); - spin_lock(&gl->gl_spin); + spin_lock(&gl->gl_lockref.lock); } return; @@ -967,7 +967,7 @@ int gfs2_glock_nq(struct gfs2_holder *gh) if (test_bit(GLF_LRU, &gl->gl_flags)) gfs2_glock_remove_from_lru(gl); - spin_lock(&gl->gl_spin); + spin_lock(&gl->gl_lockref.lock); add_to_queue(gh); if (unlikely((LM_FLAG_NOEXP & gh->gh_flags) && test_and_clear_bit(GLF_FROZEN, &gl->gl_flags))) { @@ -977,7 +977,7 @@ int gfs2_glock_nq(struct gfs2_holder *gh) gl->gl_lockref.count--; } run_queue(gl, 1); - spin_unlock(&gl->gl_spin); + spin_unlock(&gl->gl_lockref.lock); if (!(gh->gh_flags & GL_ASYNC)) error = gfs2_glock_wait(gh); @@ -1010,7 +1010,7 @@ void gfs2_glock_dq(struct gfs2_holder *gh) unsigned delay = 0; int fast_path = 0; - spin_lock(&gl->gl_spin); + spin_lock(&gl->gl_lockref.lock); if (gh->gh_flags & GL_NOCACHE) handle_callback(gl, LM_ST_UNLOCKED, 0, false); @@ -1018,9 +1018,9 @@ void gfs2_glock_dq(struct gfs2_holder *gh) if (find_first_holder(gl) == NULL) { if (glops->go_unlock) { GLOCK_BUG_ON(gl, test_and_set_bit(GLF_LOCK, &gl->gl_flags)); - spin_unlock(&gl->gl_spin); + spin_unlock(&gl->gl_lockref.lock); glops->go_unlock(gh); - spin_lock(&gl->gl_spin); + spin_lock(&gl->gl_lockref.lock); clear_bit(GLF_LOCK, &gl->gl_flags); } if (list_empty(&gl->gl_holders) && @@ -1033,7 +1033,7 @@ void gfs2_glock_dq(struct gfs2_holder *gh) gfs2_glock_add_to_lru(gl); trace_gfs2_glock_queue(gh, 0); - spin_unlock(&gl->gl_spin); + spin_unlock(&gl->gl_lockref.lock); if (likely(fast_path)) return; @@ -1217,9 +1217,9 @@ void gfs2_glock_cb(struct gfs2_glock *gl, unsigned int state) delay = gl->gl_hold_time; } - spin_lock(&gl->gl_spin); + spin_lock(&gl->gl_lockref.lock); handle_callback(gl, state, delay, true); - spin_unlock(&gl->gl_spin); + spin_unlock(&gl->gl_lockref.lock); if (queue_delayed_work(glock_workqueue, &gl->gl_work, delay) == 0) gfs2_glock_put(gl); } @@ -1259,7 +1259,7 @@ static int gfs2_should_freeze(const struct gfs2_glock *gl) * @gl: Pointer to the glock * @ret: The return value from the dlm * - * The gl_reply field is under the gl_spin lock so that it is ok + * The gl_reply field is under the gl_lockref.lock lock so that it is ok * to use a bitfield shared with other glock state fields. */ @@ -1267,20 +1267,20 @@ void gfs2_glock_complete(struct gfs2_glock *gl, int ret) { struct lm_lockstruct *ls = &gl->gl_name.ln_sbd->sd_lockstruct; - spin_lock(&gl->gl_spin); + spin_lock(&gl->gl_lockref.lock); gl->gl_reply = ret; if (unlikely(test_bit(DFL_BLOCK_LOCKS, &ls->ls_recover_flags))) { if (gfs2_should_freeze(gl)) { set_bit(GLF_FROZEN, &gl->gl_flags); - spin_unlock(&gl->gl_spin); + spin_unlock(&gl->gl_lockref.lock); return; } } gl->gl_lockref.count++; set_bit(GLF_REPLY_PENDING, &gl->gl_flags); - spin_unlock(&gl->gl_spin); + spin_unlock(&gl->gl_lockref.lock); if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0) gfs2_glock_put(gl); @@ -1326,14 +1326,14 @@ __acquires(&lru_lock) while(!list_empty(list)) { gl = list_entry(list->next, struct gfs2_glock, gl_lru); list_del_init(&gl->gl_lru); - if (!spin_trylock(&gl->gl_spin)) { + if (!spin_trylock(&gl->gl_lockref.lock)) { add_back_to_lru: list_add(&gl->gl_lru, &lru_list); atomic_inc(&lru_count); continue; } if (test_and_set_bit(GLF_LOCK, &gl->gl_flags)) { - spin_unlock(&gl->gl_spin); + spin_unlock(&gl->gl_lockref.lock); goto add_back_to_lru; } clear_bit(GLF_LRU, &gl->gl_flags); @@ -1343,7 +1343,7 @@ add_back_to_lru: WARN_ON(!test_and_clear_bit(GLF_LOCK, &gl->gl_flags)); if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0) gl->gl_lockref.count--; - spin_unlock(&gl->gl_spin); + spin_unlock(&gl->gl_lockref.lock); cond_resched_lock(&lru_lock); } } @@ -1461,10 +1461,10 @@ static void clear_glock(struct gfs2_glock *gl) { gfs2_glock_remove_from_lru(gl); - spin_lock(&gl->gl_spin); + spin_lock(&gl->gl_lockref.lock); if (gl->gl_state != LM_ST_UNLOCKED) handle_callback(gl, LM_ST_UNLOCKED, 0, false); - spin_unlock(&gl->gl_spin); + spin_unlock(&gl->gl_lockref.lock); if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0) gfs2_glock_put(gl); } @@ -1482,9 +1482,9 @@ void gfs2_glock_thaw(struct gfs2_sbd *sdp) static void dump_glock(struct seq_file *seq, struct gfs2_glock *gl) { - spin_lock(&gl->gl_spin); + spin_lock(&gl->gl_lockref.lock); gfs2_dump_glock(seq, gl); - spin_unlock(&gl->gl_spin); + spin_unlock(&gl->gl_lockref.lock); } static void dump_glock_func(struct gfs2_glock *gl) @@ -1518,10 +1518,10 @@ void gfs2_glock_finish_truncate(struct gfs2_inode *ip) ret = gfs2_truncatei_resume(ip); gfs2_assert_withdraw(gl->gl_name.ln_sbd, ret == 0); - spin_lock(&gl->gl_spin); + spin_lock(&gl->gl_lockref.lock); clear_bit(GLF_LOCK, &gl->gl_flags); run_queue(gl, 1); - spin_unlock(&gl->gl_spin); + spin_unlock(&gl->gl_lockref.lock); } static const char *state2str(unsigned state) diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h index 32572f7..f7cdaa8 100644 --- a/fs/gfs2/glock.h +++ b/fs/gfs2/glock.h @@ -141,7 +141,7 @@ static inline struct gfs2_holder *gfs2_glock_is_locked_by_me(struct gfs2_glock * struct pid *pid; /* Look in glock's list of holders for one with current task as owner */ - spin_lock(&gl->gl_spin); + spin_lock(&gl->gl_lockref.lock); pid = task_pid(current); list_for_each_entry(gh, &gl->gl_holders, gh_list) { if (!test_bit(HIF_HOLDER, &gh->gh_iflags)) @@ -151,7 +151,7 @@ static inline struct gfs2_holder *gfs2_glock_is_locked_by_me(struct gfs2_glock * } gh = NULL; out: - spin_unlock(&gl->gl_spin); + spin_unlock(&gl->gl_lockref.lock); return gh; } diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index 1f6c9c3..f348cfb 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -146,11 +146,11 @@ static void rgrp_go_sync(struct gfs2_glock *gl) struct gfs2_rgrpd *rgd; int error; - spin_lock(&gl->gl_spin); + spin_lock(&gl->gl_lockref.lock); rgd = gl->gl_object; if (rgd) gfs2_rgrp_brelse(rgd); - spin_unlock(&gl->gl_spin); + spin_unlock(&gl->gl_lockref.lock); if (!test_and_clear_bit(GLF_DIRTY, &gl->gl_flags)) return; @@ -162,11 +162,11 @@ static void rgrp_go_sync(struct gfs2_glock *gl) mapping_set_error(mapping, error); gfs2_ail_empty_gl(gl); - spin_lock(&gl->gl_spin); + spin_lock(&gl->gl_lockref.lock); rgd = gl->gl_object; if (rgd) gfs2_free_clones(rgd); - spin_unlock(&gl->gl_spin); + spin_unlock(&gl->gl_lockref.lock); } /** @@ -542,7 +542,7 @@ static int freeze_go_demote_ok(const struct gfs2_glock *gl) * iopen_go_callback - schedule the dcache entry for the inode to be deleted * @gl: the glock * - * gl_spin lock is held while calling this + * gl_lockref.lock lock is held while calling this */ static void iopen_go_callback(struct gfs2_glock *gl, bool remote) { diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h index 121ed08..de7b4f9 100644 --- a/fs/gfs2/incore.h +++ b/fs/gfs2/incore.h @@ -334,9 +334,8 @@ struct gfs2_glock { struct lm_lockname gl_name; struct lockref gl_lockref; -#define gl_spin gl_lockref.lock - /* State fields protected by gl_spin */ + /* State fields protected by gl_lockref.lock */ unsigned int gl_state:2, /* Current state */ gl_target:2, /* Target state */ gl_demote_state:2, /* State requested by remote node */ diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c index 284c154..8b907c5 100644 --- a/fs/gfs2/lock_dlm.c +++ b/fs/gfs2/lock_dlm.c @@ -50,7 +50,7 @@ static inline void gfs2_update_stats(struct gfs2_lkstats *s, unsigned index, s64 delta = sample - s->stats[index]; s->stats[index] += (delta >> 3); index++; - s->stats[index] += ((abs64(delta) - s->stats[index]) >> 2); + s->stats[index] += ((abs(delta) - s->stats[index]) >> 2); } /** diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c index 241a399..fb2b42c 100644 --- a/fs/gfs2/main.c +++ b/fs/gfs2/main.c @@ -50,7 +50,7 @@ static void gfs2_init_glock_once(void *foo) struct gfs2_glock *gl = foo; INIT_HLIST_BL_NODE(&gl->gl_list); - spin_lock_init(&gl->gl_spin); + spin_lock_init(&gl->gl_lockref.lock); INIT_LIST_HEAD(&gl->gl_holders); INIT_LIST_HEAD(&gl->gl_lru); INIT_LIST_HEAD(&gl->gl_ail_list); diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index 02586e7..baab99b 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -1291,6 +1291,9 @@ static struct dentry *gfs2_mount(struct file_system_type *fs_type, int flags, up_write(&s->s_umount); blkdev_put(bdev, mode); down_write(&s->s_umount); + } else { + /* s_mode must be set before deactivate_locked_super calls */ + s->s_mode = mode; } memset(&args, 0, sizeof(args)); @@ -1314,7 +1317,6 @@ static struct dentry *gfs2_mount(struct file_system_type *fs_type, int flags, } else { char b[BDEVNAME_SIZE]; - s->s_mode = mode; strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id)); sb_set_blocksize(s, block_size(bdev)); error = fill_super(s, &args, flags & MS_SILENT ? 1 : 0); diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index 475985d..c134c04 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -729,9 +729,9 @@ void gfs2_clear_rgrpd(struct gfs2_sbd *sdp) rb_erase(n, &sdp->sd_rindex_tree); if (gl) { - spin_lock(&gl->gl_spin); + spin_lock(&gl->gl_lockref.lock); gl->gl_object = NULL; - spin_unlock(&gl->gl_spin); + spin_unlock(&gl->gl_lockref.lock); gfs2_glock_add_to_lru(gl); gfs2_glock_put(gl); } @@ -933,8 +933,9 @@ static int read_rindex_entry(struct gfs2_inode *ip) goto fail; rgd->rd_gl->gl_object = rgd; - rgd->rd_gl->gl_vm.start = rgd->rd_addr * bsize; - rgd->rd_gl->gl_vm.end = rgd->rd_gl->gl_vm.start + (rgd->rd_length * bsize) - 1; + rgd->rd_gl->gl_vm.start = (rgd->rd_addr * bsize) & PAGE_CACHE_MASK; + rgd->rd_gl->gl_vm.end = PAGE_CACHE_ALIGN((rgd->rd_addr + + rgd->rd_length) * bsize) - 1; rgd->rd_rgl = (struct gfs2_rgrp_lvb *)rgd->rd_gl->gl_lksb.sb_lvbptr; rgd->rd_flags &= ~(GFS2_RDF_UPTODATE | GFS2_RDF_PREFERRED); if (rgd->rd_data > sdp->sd_max_rg_data) diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c index b95d0d6..0c1bde3 100644 --- a/fs/gfs2/trans.c +++ b/fs/gfs2/trans.c @@ -176,6 +176,8 @@ void gfs2_trans_add_data(struct gfs2_glock *gl, struct buffer_head *bh) unlock_buffer(bh); if (bh->b_private == NULL) bd = gfs2_alloc_bufdata(gl, bh, &gfs2_databuf_lops); + else + bd = bh->b_private; lock_buffer(bh); gfs2_log_lock(sdp); } @@ -236,6 +238,8 @@ void gfs2_trans_add_meta(struct gfs2_glock *gl, struct buffer_head *bh) lock_page(bh->b_page); if (bh->b_private == NULL) bd = gfs2_alloc_bufdata(gl, bh, &gfs2_buf_lops); + else + bd = bh->b_private; unlock_page(bh->b_page); lock_buffer(bh); gfs2_log_lock(sdp); diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c index 9e92c9c..ae4d5a1 100644 --- a/fs/hpfs/namei.c +++ b/fs/hpfs/namei.c @@ -227,8 +227,6 @@ static int hpfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, de int err; if ((err = hpfs_chk_name(name, &len))) return err==-ENOENT ? -EINVAL : err; if (hpfs_sb(dir->i_sb)->sb_eas < 2) return -EPERM; - if (!new_valid_dev(rdev)) - return -EINVAL; hpfs_lock(dir->i_sb); err = -ENOSPC; fnode = hpfs_alloc_fnode(dir->i_sb, hpfs_i(dir)->i_dno, &fno, &bh); @@ -1597,6 +1597,7 @@ static int update_time(struct inode *inode, struct timespec *time, int flags) /** * touch_atime - update the access time * @path: the &struct path to update + * @inode: inode to update * * Update the accessed time on an inode and mark it for writeback. * This function automatically handles read only file systems and media, diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index 8c44654..684996c 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -427,7 +427,6 @@ static int journal_clean_one_cp_list(struct journal_head *jh, bool destroy) struct journal_head *last_jh; struct journal_head *next_jh = jh; int ret; - int freed = 0; if (!jh) return 0; @@ -441,10 +440,9 @@ static int journal_clean_one_cp_list(struct journal_head *jh, bool destroy) else ret = __jbd2_journal_remove_checkpoint(jh) + 1; if (!ret) - return freed; + return 0; if (ret == 2) return 1; - freed = 1; /* * This function only frees up some memory * if possible so we dont have an obligation @@ -452,10 +450,10 @@ static int journal_clean_one_cp_list(struct journal_head *jh, bool destroy) * requested: */ if (need_resched()) - return freed; + return 0; } while (jh != last_jh); - return freed; + return 0; } /* diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 362e5f6..36345fe 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -142,8 +142,7 @@ static int journal_submit_commit_record(journal_t *journal, tmp->h_commit_sec = cpu_to_be64(now.tv_sec); tmp->h_commit_nsec = cpu_to_be32(now.tv_nsec); - if (JBD2_HAS_COMPAT_FEATURE(journal, - JBD2_FEATURE_COMPAT_CHECKSUM)) { + if (jbd2_has_feature_checksum(journal)) { tmp->h_chksum_type = JBD2_CRC32_CHKSUM; tmp->h_chksum_size = JBD2_CRC32_CHKSUM_SIZE; tmp->h_chksum[0] = cpu_to_be32(crc32_sum); @@ -157,8 +156,7 @@ static int journal_submit_commit_record(journal_t *journal, bh->b_end_io = journal_end_buffer_io_sync; if (journal->j_flags & JBD2_BARRIER && - !JBD2_HAS_INCOMPAT_FEATURE(journal, - JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) + !jbd2_has_feature_async_commit(journal)) ret = submit_bh(WRITE_SYNC | WRITE_FLUSH_FUA, bh); else ret = submit_bh(WRITE_SYNC, bh); @@ -317,7 +315,7 @@ static void write_tag_block(journal_t *j, journal_block_tag_t *tag, unsigned long long block) { tag->t_blocknr = cpu_to_be32(block & (u32)~0); - if (JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_64BIT)) + if (jbd2_has_feature_64bit(j)) tag->t_blocknr_high = cpu_to_be32((block >> 31) >> 1); } @@ -356,7 +354,7 @@ static void jbd2_block_tag_csum_set(journal_t *j, journal_block_tag_t *tag, bh->b_size); kunmap_atomic(addr); - if (JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V3)) + if (jbd2_has_feature_csum3(j)) tag3->t_checksum = cpu_to_be32(csum32); else tag->t_checksum = cpu_to_be16(csum32); @@ -730,8 +728,7 @@ start_journal_io: /* * Compute checksum. */ - if (JBD2_HAS_COMPAT_FEATURE(journal, - JBD2_FEATURE_COMPAT_CHECKSUM)) { + if (jbd2_has_feature_checksum(journal)) { crc32_sum = jbd2_checksum_data(crc32_sum, bh); } @@ -797,8 +794,7 @@ start_journal_io: blkdev_issue_flush(journal->j_fs_dev, GFP_NOFS, NULL); /* Done it all: now write the commit record asynchronously. */ - if (JBD2_HAS_INCOMPAT_FEATURE(journal, - JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) { + if (jbd2_has_feature_async_commit(journal)) { err = journal_submit_commit_record(journal, commit_transaction, &cbh, crc32_sum); if (err) @@ -889,8 +885,7 @@ start_journal_io: commit_transaction->t_state = T_COMMIT_JFLUSH; write_unlock(&journal->j_state_lock); - if (!JBD2_HAS_INCOMPAT_FEATURE(journal, - JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) { + if (!jbd2_has_feature_async_commit(journal)) { err = journal_submit_commit_record(journal, commit_transaction, &cbh, crc32_sum); if (err) @@ -898,8 +893,7 @@ start_journal_io: } if (cbh) err = journal_wait_on_commit_record(journal, cbh); - if (JBD2_HAS_INCOMPAT_FEATURE(journal, - JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT) && + if (jbd2_has_feature_async_commit(journal) && journal->j_flags & JBD2_BARRIER) { blkdev_issue_flush(journal->j_dev, GFP_NOFS, NULL); } diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 8270fe9..81e6226 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -124,7 +124,7 @@ EXPORT_SYMBOL(__jbd2_debug); /* Checksumming functions */ static int jbd2_verify_csum_type(journal_t *j, journal_superblock_t *sb) { - if (!jbd2_journal_has_csum_v2or3(j)) + if (!jbd2_journal_has_csum_v2or3_feature(j)) return 1; return sb->s_checksum_type == JBD2_CRC32C_CHKSUM; @@ -1523,16 +1523,16 @@ static int journal_get_superblock(journal_t *journal) goto out; } - if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2) && - JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V3)) { + if (jbd2_has_feature_csum2(journal) && + jbd2_has_feature_csum3(journal)) { /* Can't have checksum v2 and v3 at the same time! */ printk(KERN_ERR "JBD2: Can't enable checksumming v2 and v3 " "at the same time!\n"); goto out; } - if (jbd2_journal_has_csum_v2or3(journal) && - JBD2_HAS_COMPAT_FEATURE(journal, JBD2_FEATURE_COMPAT_CHECKSUM)) { + if (jbd2_journal_has_csum_v2or3_feature(journal) && + jbd2_has_feature_checksum(journal)) { /* Can't have checksum v1 and v2 on at the same time! */ printk(KERN_ERR "JBD2: Can't enable checksumming v1 and v2/3 " "at the same time!\n"); @@ -1545,7 +1545,7 @@ static int journal_get_superblock(journal_t *journal) } /* Load the checksum driver */ - if (jbd2_journal_has_csum_v2or3(journal)) { + if (jbd2_journal_has_csum_v2or3_feature(journal)) { journal->j_chksum_driver = crypto_alloc_shash("crc32c", 0, 0); if (IS_ERR(journal->j_chksum_driver)) { printk(KERN_ERR "JBD2: Cannot load crc32c driver.\n"); @@ -1558,6 +1558,7 @@ static int journal_get_superblock(journal_t *journal) /* Check superblock checksum */ if (!jbd2_superblock_csum_verify(journal, sb)) { printk(KERN_ERR "JBD2: journal checksum error\n"); + err = -EFSBADCRC; goto out; } @@ -1649,7 +1650,7 @@ int jbd2_journal_load(journal_t *journal) printk(KERN_ERR "JBD2: journal transaction %u on %s " "is corrupt.\n", journal->j_failed_commit, journal->j_devname); - return -EIO; + return -EFSCORRUPTED; } /* OK, we've finished with the dynamic journal bits: @@ -2071,8 +2072,12 @@ static void __journal_abort_soft (journal_t *journal, int errno) __jbd2_journal_abort_hard(journal); - if (errno) + if (errno) { jbd2_journal_update_sb_errno(journal); + write_lock(&journal->j_state_lock); + journal->j_flags |= JBD2_REC_ERR; + write_unlock(&journal->j_state_lock); + } } /** @@ -2197,15 +2202,15 @@ size_t journal_tag_bytes(journal_t *journal) { size_t sz; - if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V3)) + if (jbd2_has_feature_csum3(journal)) return sizeof(journal_block_tag3_t); sz = sizeof(journal_block_tag_t); - if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + if (jbd2_has_feature_csum2(journal)) sz += sizeof(__u16); - if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT)) + if (jbd2_has_feature_64bit(journal)) return sz; else return sz - sizeof(__u32); diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c index a9079d0..7f277e4 100644 --- a/fs/jbd2/recovery.c +++ b/fs/jbd2/recovery.c @@ -140,7 +140,7 @@ static int jread(struct buffer_head **bhp, journal_t *journal, if (offset >= journal->j_maxlen) { printk(KERN_ERR "JBD2: corrupted journal superblock\n"); - return -EIO; + return -EFSCORRUPTED; } err = jbd2_journal_bmap(journal, offset, &blocknr); @@ -342,7 +342,7 @@ static inline unsigned long long read_tag_block(journal_t *journal, journal_block_tag_t *tag) { unsigned long long block = be32_to_cpu(tag->t_blocknr); - if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT)) + if (jbd2_has_feature_64bit(journal)) block |= (u64)be32_to_cpu(tag->t_blocknr_high) << 32; return block; } @@ -411,7 +411,7 @@ static int jbd2_block_tag_csum_verify(journal_t *j, journal_block_tag_t *tag, csum32 = jbd2_chksum(j, j->j_csum_seed, (__u8 *)&seq, sizeof(seq)); csum32 = jbd2_chksum(j, csum32, buf, j->j_blocksize); - if (JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V3)) + if (jbd2_has_feature_csum3(j)) return tag3->t_checksum == cpu_to_be32(csum32); else return tag->t_checksum == cpu_to_be16(csum32); @@ -527,7 +527,7 @@ static int do_one_pass(journal_t *journal, printk(KERN_ERR "JBD2: Invalid checksum " "recovering block %lu in log\n", next_log_block); - err = -EIO; + err = -EFSBADCRC; brelse(bh); goto failed; } @@ -538,8 +538,7 @@ static int do_one_pass(journal_t *journal, * just skip over the blocks it describes. */ if (pass != PASS_REPLAY) { if (pass == PASS_SCAN && - JBD2_HAS_COMPAT_FEATURE(journal, - JBD2_FEATURE_COMPAT_CHECKSUM) && + jbd2_has_feature_checksum(journal) && !info->end_transaction) { if (calc_chksums(journal, bh, &next_log_block, @@ -602,7 +601,7 @@ static int do_one_pass(journal_t *journal, journal, tag, obh->b_data, be32_to_cpu(tmp->h_sequence))) { brelse(obh); - success = -EIO; + success = -EFSBADCRC; printk(KERN_ERR "JBD2: Invalid " "checksum recovering " "block %llu in log\n", @@ -694,8 +693,7 @@ static int do_one_pass(journal_t *journal, * much to do other than move on to the next sequence * number. */ if (pass == PASS_SCAN && - JBD2_HAS_COMPAT_FEATURE(journal, - JBD2_FEATURE_COMPAT_CHECKSUM)) { + jbd2_has_feature_checksum(journal)) { int chksum_err, chksum_seen; struct commit_header *cbh = (struct commit_header *)bh->b_data; @@ -735,8 +733,7 @@ static int do_one_pass(journal_t *journal, if (chksum_err) { info->end_transaction = next_commit_ID; - if (!JBD2_HAS_INCOMPAT_FEATURE(journal, - JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)){ + if (!jbd2_has_feature_async_commit(journal)) { journal->j_failed_commit = next_commit_ID; brelse(bh); @@ -750,8 +747,7 @@ static int do_one_pass(journal_t *journal, bh->b_data)) { info->end_transaction = next_commit_ID; - if (!JBD2_HAS_INCOMPAT_FEATURE(journal, - JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) { + if (!jbd2_has_feature_async_commit(journal)) { journal->j_failed_commit = next_commit_ID; brelse(bh); @@ -851,7 +847,7 @@ static int scan_revoke_records(journal_t *journal, struct buffer_head *bh, rcount = be32_to_cpu(header->r_count); if (!jbd2_revoke_block_csum_verify(journal, header)) - return -EINVAL; + return -EFSBADCRC; if (jbd2_journal_has_csum_v2or3(journal)) csum_size = sizeof(struct jbd2_journal_revoke_tail); @@ -859,7 +855,7 @@ static int scan_revoke_records(journal_t *journal, struct buffer_head *bh, return -EINVAL; max = rcount; - if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT)) + if (jbd2_has_feature_64bit(journal)) record_len = 8; while (offset + record_len <= max) { diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c index 0abf2e7..705ae57 100644 --- a/fs/jbd2/revoke.c +++ b/fs/jbd2/revoke.c @@ -589,7 +589,7 @@ static void write_one_revoke_record(journal_t *journal, if (jbd2_journal_has_csum_v2or3(journal)) csum_size = sizeof(struct jbd2_journal_revoke_tail); - if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT)) + if (jbd2_has_feature_64bit(journal)) sz = 8; else sz = 4; @@ -619,7 +619,7 @@ static void write_one_revoke_record(journal_t *journal, *descriptorp = descriptor; } - if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT)) + if (jbd2_has_feature_64bit(journal)) * ((__be64 *)(&descriptor->b_data[offset])) = cpu_to_be64(record->blocknr); else diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 6b8338e..89463ee 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -1937,8 +1937,8 @@ out: * @journal: journal for operation * @page: to try and free * @gfp_mask: we use the mask to detect how hard should we try to release - * buffers. If __GFP_WAIT and __GFP_FS is set, we wait for commit code to - * release the buffers. + * buffers. If __GFP_DIRECT_RECLAIM and __GFP_FS is set, we wait for commit + * code to release the buffers. * * * For all the buffers on this page, diff --git a/fs/jffs2/background.c b/fs/jffs2/background.c index bb9cebc..e5c1783 100644 --- a/fs/jffs2/background.c +++ b/fs/jffs2/background.c @@ -80,7 +80,6 @@ static int jffs2_garbage_collect_thread(void *_c) siginitset(&hupmask, sigmask(SIGHUP)); allow_signal(SIGKILL); allow_signal(SIGSTOP); - allow_signal(SIGCONT); allow_signal(SIGHUP); c->gc_task = current; @@ -121,20 +120,18 @@ static int jffs2_garbage_collect_thread(void *_c) /* Put_super will send a SIGKILL and then wait on the sem. */ while (signal_pending(current) || freezing(current)) { - siginfo_t info; unsigned long signr; if (try_to_freeze()) goto again; - signr = dequeue_signal_lock(current, ¤t->blocked, &info); + signr = kernel_dequeue_signal(NULL); switch(signr) { case SIGSTOP: jffs2_dbg(1, "%s(): SIGSTOP received\n", __func__); - set_current_state(TASK_STOPPED); - schedule(); + kernel_signal_stop(); break; case SIGKILL: diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c index 8118002..d211b8e 100644 --- a/fs/jffs2/dir.c +++ b/fs/jffs2/dir.c @@ -621,9 +621,6 @@ static int jffs2_mknod (struct inode *dir_i, struct dentry *dentry, umode_t mode uint32_t alloclen; int ret; - if (!new_valid_dev(rdev)) - return -EINVAL; - ri = jffs2_alloc_raw_inode(); if (!ri) return -ENOMEM; diff --git a/fs/jffs2/malloc.c b/fs/jffs2/malloc.c index b8fd651..ce11897 100644 --- a/fs/jffs2/malloc.c +++ b/fs/jffs2/malloc.c @@ -97,25 +97,16 @@ int __init jffs2_create_slab_caches(void) void jffs2_destroy_slab_caches(void) { - if(full_dnode_slab) - kmem_cache_destroy(full_dnode_slab); - if(raw_dirent_slab) - kmem_cache_destroy(raw_dirent_slab); - if(raw_inode_slab) - kmem_cache_destroy(raw_inode_slab); - if(tmp_dnode_info_slab) - kmem_cache_destroy(tmp_dnode_info_slab); - if(raw_node_ref_slab) - kmem_cache_destroy(raw_node_ref_slab); - if(node_frag_slab) - kmem_cache_destroy(node_frag_slab); - if(inode_cache_slab) - kmem_cache_destroy(inode_cache_slab); + kmem_cache_destroy(full_dnode_slab); + kmem_cache_destroy(raw_dirent_slab); + kmem_cache_destroy(raw_inode_slab); + kmem_cache_destroy(tmp_dnode_info_slab); + kmem_cache_destroy(raw_node_ref_slab); + kmem_cache_destroy(node_frag_slab); + kmem_cache_destroy(inode_cache_slab); #ifdef CONFIG_JFFS2_FS_XATTR - if (xattr_datum_cache) - kmem_cache_destroy(xattr_datum_cache); - if (xattr_ref_cache) - kmem_cache_destroy(xattr_ref_cache); + kmem_cache_destroy(xattr_datum_cache); + kmem_cache_destroy(xattr_ref_cache); #endif } diff --git a/fs/jffs2/readinode.c b/fs/jffs2/readinode.c index 28e0aab..bfebbf1 100644 --- a/fs/jffs2/readinode.c +++ b/fs/jffs2/readinode.c @@ -660,8 +660,12 @@ static inline int read_direntry(struct jffs2_sb_info *c, struct jffs2_raw_node_r err = jffs2_flash_read(c, (ref_offset(ref)) + read, rd->nsize - already, &read, &fd->name[already]); - if (unlikely(read != rd->nsize - already) && likely(!err)) + if (unlikely(read != rd->nsize - already) && likely(!err)) { + jffs2_free_full_dirent(fd); + JFFS2_ERROR("short read: wanted %d bytes, got %zd\n", + rd->nsize - already, read); return -EIO; + } if (unlikely(err)) { JFFS2_ERROR("read remainder of name: error %d\n", err); diff --git a/fs/jffs2/wbuf.c b/fs/jffs2/wbuf.c index 09ed551..f3a4857 100644 --- a/fs/jffs2/wbuf.c +++ b/fs/jffs2/wbuf.c @@ -1264,7 +1264,7 @@ int jffs2_dataflash_setup(struct jffs2_sb_info *c) { if ((c->flash_size % c->sector_size) != 0) { c->flash_size = (c->flash_size / c->sector_size) * c->sector_size; pr_warn("flash size adjusted to %dKiB\n", c->flash_size); - }; + } c->wbuf_ofs = 0xFFFFFFFF; c->wbuf = kmalloc(c->wbuf_pagesize, GFP_KERNEL); @@ -1274,7 +1274,6 @@ int jffs2_dataflash_setup(struct jffs2_sb_info *c) { #ifdef CONFIG_JFFS2_FS_WBUF_VERIFY c->wbuf_verify = kmalloc(c->wbuf_pagesize, GFP_KERNEL); if (!c->wbuf_verify) { - kfree(c->oobbuf); kfree(c->wbuf); return -ENOMEM; } diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c index 35976bd..9d7551f 100644 --- a/fs/jfs/namei.c +++ b/fs/jfs/namei.c @@ -1372,9 +1372,6 @@ static int jfs_mknod(struct inode *dir, struct dentry *dentry, tid_t tid; struct tblock *tblk; - if (!new_valid_dev(rdev)) - return -EINVAL; - jfs_info("jfs_mknod: %pd", dentry); rc = dquot_initialize(dir); diff --git a/fs/jfs/super.c b/fs/jfs/super.c index 4cd9798..8f9176c 100644 --- a/fs/jfs/super.c +++ b/fs/jfs/super.c @@ -496,9 +496,6 @@ static int jfs_fill_super(struct super_block *sb, void *data, int silent) jfs_info("In jfs_read_super: s_flags=0x%lx", sb->s_flags); - if (!new_valid_dev(sb->s_bdev->bd_dev)) - return -EOVERFLOW; - sbi = kzalloc(sizeof(struct jfs_sb_info), GFP_KERNEL); if (!sbi) return -ENOMEM; diff --git a/fs/lockd/clntproc.c b/fs/lockd/clntproc.c index acd3947..1129520 100644 --- a/fs/lockd/clntproc.c +++ b/fs/lockd/clntproc.c @@ -474,18 +474,7 @@ static void nlmclnt_locks_init_private(struct file_lock *fl, struct nlm_host *ho static int do_vfs_lock(struct file_lock *fl) { - int res = 0; - switch (fl->fl_flags & (FL_POSIX|FL_FLOCK)) { - case FL_POSIX: - res = posix_lock_file_wait(fl->fl_file, fl); - break; - case FL_FLOCK: - res = flock_lock_file_wait(fl->fl_file, fl); - break; - default: - BUG(); - } - return res; + return locks_lock_file_wait(fl->fl_file, fl); } /* diff --git a/fs/lockd/host.c b/fs/lockd/host.c index 969d589..d716c99 100644 --- a/fs/lockd/host.c +++ b/fs/lockd/host.c @@ -116,7 +116,7 @@ static struct nlm_host *nlm_alloc_host(struct nlm_lookup_host_info *ni, atomic_inc(&nsm->sm_count); else { host = NULL; - nsm = nsm_get_handle(ni->sap, ni->salen, + nsm = nsm_get_handle(ni->net, ni->sap, ni->salen, ni->hostname, ni->hostname_len); if (unlikely(nsm == NULL)) { dprintk("lockd: %s failed; no nsm handle\n", @@ -161,6 +161,7 @@ static struct nlm_host *nlm_alloc_host(struct nlm_lookup_host_info *ni, host->h_nsmhandle = nsm; host->h_addrbuf = nsm->sm_addrbuf; host->net = ni->net; + strlcpy(host->nodename, utsname()->nodename, sizeof(host->nodename)); out: return host; @@ -534,17 +535,18 @@ static struct nlm_host *next_host_state(struct hlist_head *cache, /** * nlm_host_rebooted - Release all resources held by rebooted host + * @net: network namespace * @info: pointer to decoded results of NLM_SM_NOTIFY call * * We were notified that the specified host has rebooted. Release * all resources held by that peer. */ -void nlm_host_rebooted(const struct nlm_reboot *info) +void nlm_host_rebooted(const struct net *net, const struct nlm_reboot *info) { struct nsm_handle *nsm; struct nlm_host *host; - nsm = nsm_reboot_lookup(info); + nsm = nsm_reboot_lookup(net, info); if (unlikely(nsm == NULL)) return; diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c index 47a32b6..19166d4 100644 --- a/fs/lockd/mon.c +++ b/fs/lockd/mon.c @@ -42,7 +42,7 @@ struct nsm_args { u32 proc; char *mon_name; - char *nodename; + const char *nodename; }; struct nsm_res { @@ -51,7 +51,6 @@ struct nsm_res { }; static const struct rpc_program nsm_program; -static LIST_HEAD(nsm_handles); static DEFINE_SPINLOCK(nsm_lock); /* @@ -87,69 +86,18 @@ static struct rpc_clnt *nsm_create(struct net *net, const char *nodename) return rpc_create(&args); } -static struct rpc_clnt *nsm_client_set(struct lockd_net *ln, - struct rpc_clnt *clnt) -{ - spin_lock(&ln->nsm_clnt_lock); - if (ln->nsm_users == 0) { - if (clnt == NULL) - goto out; - ln->nsm_clnt = clnt; - } - clnt = ln->nsm_clnt; - ln->nsm_users++; -out: - spin_unlock(&ln->nsm_clnt_lock); - return clnt; -} - -static struct rpc_clnt *nsm_client_get(struct net *net, const char *nodename) -{ - struct rpc_clnt *clnt, *new; - struct lockd_net *ln = net_generic(net, lockd_net_id); - - clnt = nsm_client_set(ln, NULL); - if (clnt != NULL) - goto out; - - clnt = new = nsm_create(net, nodename); - if (IS_ERR(clnt)) - goto out; - - clnt = nsm_client_set(ln, new); - if (clnt != new) - rpc_shutdown_client(new); -out: - return clnt; -} - -static void nsm_client_put(struct net *net) -{ - struct lockd_net *ln = net_generic(net, lockd_net_id); - struct rpc_clnt *clnt = NULL; - - spin_lock(&ln->nsm_clnt_lock); - ln->nsm_users--; - if (ln->nsm_users == 0) { - clnt = ln->nsm_clnt; - ln->nsm_clnt = NULL; - } - spin_unlock(&ln->nsm_clnt_lock); - if (clnt != NULL) - rpc_shutdown_client(clnt); -} - static int nsm_mon_unmon(struct nsm_handle *nsm, u32 proc, struct nsm_res *res, - struct rpc_clnt *clnt) + const struct nlm_host *host) { int status; + struct rpc_clnt *clnt; struct nsm_args args = { .priv = &nsm->sm_priv, .prog = NLM_PROGRAM, .vers = 3, .proc = NLMPROC_NSM_NOTIFY, .mon_name = nsm->sm_mon_name, - .nodename = clnt->cl_nodename, + .nodename = host->nodename, }; struct rpc_message msg = { .rpc_argp = &args, @@ -158,6 +106,13 @@ static int nsm_mon_unmon(struct nsm_handle *nsm, u32 proc, struct nsm_res *res, memset(res, 0, sizeof(*res)); + clnt = nsm_create(host->net, host->nodename); + if (IS_ERR(clnt)) { + dprintk("lockd: failed to create NSM upcall transport, " + "status=%ld, net=%p\n", PTR_ERR(clnt), host->net); + return PTR_ERR(clnt); + } + msg.rpc_proc = &clnt->cl_procinfo[proc]; status = rpc_call_sync(clnt, &msg, RPC_TASK_SOFTCONN); if (status == -ECONNREFUSED) { @@ -171,6 +126,8 @@ static int nsm_mon_unmon(struct nsm_handle *nsm, u32 proc, struct nsm_res *res, status); else status = 0; + + rpc_shutdown_client(clnt); return status; } @@ -190,32 +147,19 @@ int nsm_monitor(const struct nlm_host *host) struct nsm_handle *nsm = host->h_nsmhandle; struct nsm_res res; int status; - struct rpc_clnt *clnt; - const char *nodename = NULL; dprintk("lockd: nsm_monitor(%s)\n", nsm->sm_name); if (nsm->sm_monitored) return 0; - if (host->h_rpcclnt) - nodename = host->h_rpcclnt->cl_nodename; - /* * Choose whether to record the caller_name or IP address of * this peer in the local rpc.statd's database. */ nsm->sm_mon_name = nsm_use_hostnames ? nsm->sm_name : nsm->sm_addrbuf; - clnt = nsm_client_get(host->net, nodename); - if (IS_ERR(clnt)) { - status = PTR_ERR(clnt); - dprintk("lockd: failed to create NSM upcall transport, " - "status=%d, net=%p\n", status, host->net); - return status; - } - - status = nsm_mon_unmon(nsm, NSMPROC_MON, &res, clnt); + status = nsm_mon_unmon(nsm, NSMPROC_MON, &res, host); if (unlikely(res.status != 0)) status = -EIO; if (unlikely(status < 0)) { @@ -247,11 +191,9 @@ void nsm_unmonitor(const struct nlm_host *host) if (atomic_read(&nsm->sm_count) == 1 && nsm->sm_monitored && !nsm->sm_sticky) { - struct lockd_net *ln = net_generic(host->net, lockd_net_id); - dprintk("lockd: nsm_unmonitor(%s)\n", nsm->sm_name); - status = nsm_mon_unmon(nsm, NSMPROC_UNMON, &res, ln->nsm_clnt); + status = nsm_mon_unmon(nsm, NSMPROC_UNMON, &res, host); if (res.status != 0) status = -EIO; if (status < 0) @@ -259,38 +201,38 @@ void nsm_unmonitor(const struct nlm_host *host) nsm->sm_name); else nsm->sm_monitored = 0; - - nsm_client_put(host->net); } } -static struct nsm_handle *nsm_lookup_hostname(const char *hostname, - const size_t len) +static struct nsm_handle *nsm_lookup_hostname(const struct list_head *nsm_handles, + const char *hostname, const size_t len) { struct nsm_handle *nsm; - list_for_each_entry(nsm, &nsm_handles, sm_link) + list_for_each_entry(nsm, nsm_handles, sm_link) if (strlen(nsm->sm_name) == len && memcmp(nsm->sm_name, hostname, len) == 0) return nsm; return NULL; } -static struct nsm_handle *nsm_lookup_addr(const struct sockaddr *sap) +static struct nsm_handle *nsm_lookup_addr(const struct list_head *nsm_handles, + const struct sockaddr *sap) { struct nsm_handle *nsm; - list_for_each_entry(nsm, &nsm_handles, sm_link) + list_for_each_entry(nsm, nsm_handles, sm_link) if (rpc_cmp_addr(nsm_addr(nsm), sap)) return nsm; return NULL; } -static struct nsm_handle *nsm_lookup_priv(const struct nsm_private *priv) +static struct nsm_handle *nsm_lookup_priv(const struct list_head *nsm_handles, + const struct nsm_private *priv) { struct nsm_handle *nsm; - list_for_each_entry(nsm, &nsm_handles, sm_link) + list_for_each_entry(nsm, nsm_handles, sm_link) if (memcmp(nsm->sm_priv.data, priv->data, sizeof(priv->data)) == 0) return nsm; @@ -353,6 +295,7 @@ static struct nsm_handle *nsm_create_handle(const struct sockaddr *sap, /** * nsm_get_handle - Find or create a cached nsm_handle + * @net: network namespace * @sap: pointer to socket address of handle to find * @salen: length of socket address * @hostname: pointer to C string containing hostname to find @@ -365,11 +308,13 @@ static struct nsm_handle *nsm_create_handle(const struct sockaddr *sap, * @hostname cannot be found in the handle cache. Returns NULL if * an error occurs. */ -struct nsm_handle *nsm_get_handle(const struct sockaddr *sap, +struct nsm_handle *nsm_get_handle(const struct net *net, + const struct sockaddr *sap, const size_t salen, const char *hostname, const size_t hostname_len) { struct nsm_handle *cached, *new = NULL; + struct lockd_net *ln = net_generic(net, lockd_net_id); if (hostname && memchr(hostname, '/', hostname_len) != NULL) { if (printk_ratelimit()) { @@ -384,9 +329,10 @@ retry: spin_lock(&nsm_lock); if (nsm_use_hostnames && hostname != NULL) - cached = nsm_lookup_hostname(hostname, hostname_len); + cached = nsm_lookup_hostname(&ln->nsm_handles, + hostname, hostname_len); else - cached = nsm_lookup_addr(sap); + cached = nsm_lookup_addr(&ln->nsm_handles, sap); if (cached != NULL) { atomic_inc(&cached->sm_count); @@ -400,7 +346,7 @@ retry: } if (new != NULL) { - list_add(&new->sm_link, &nsm_handles); + list_add(&new->sm_link, &ln->nsm_handles); spin_unlock(&nsm_lock); dprintk("lockd: created nsm_handle for %s (%s)\n", new->sm_name, new->sm_addrbuf); @@ -417,19 +363,22 @@ retry: /** * nsm_reboot_lookup - match NLMPROC_SM_NOTIFY arguments to an nsm_handle + * @net: network namespace * @info: pointer to NLMPROC_SM_NOTIFY arguments * * Returns a matching nsm_handle if found in the nsm cache. The returned * nsm_handle's reference count is bumped. Otherwise returns NULL if some * error occurred. */ -struct nsm_handle *nsm_reboot_lookup(const struct nlm_reboot *info) +struct nsm_handle *nsm_reboot_lookup(const struct net *net, + const struct nlm_reboot *info) { struct nsm_handle *cached; + struct lockd_net *ln = net_generic(net, lockd_net_id); spin_lock(&nsm_lock); - cached = nsm_lookup_priv(&info->priv); + cached = nsm_lookup_priv(&ln->nsm_handles, &info->priv); if (unlikely(cached == NULL)) { spin_unlock(&nsm_lock); dprintk("lockd: never saw rebooted peer '%.*s' before\n", diff --git a/fs/lockd/netns.h b/fs/lockd/netns.h index 097bfa3..5426189 100644 --- a/fs/lockd/netns.h +++ b/fs/lockd/netns.h @@ -12,9 +12,7 @@ struct lockd_net { struct delayed_work grace_period_end; struct lock_manager lockd_manager; - spinlock_t nsm_clnt_lock; - unsigned int nsm_users; - struct rpc_clnt *nsm_clnt; + struct list_head nsm_handles; }; extern int lockd_net_id; diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index d678bcc..5f31ebd 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -592,7 +592,7 @@ static int lockd_init_net(struct net *net) INIT_DELAYED_WORK(&ln->grace_period_end, grace_ender); INIT_LIST_HEAD(&ln->lockd_manager.list); ln->lockd_manager.block_opens = false; - spin_lock_init(&ln->nsm_clnt_lock); + INIT_LIST_HEAD(&ln->nsm_handles); return 0; } diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c index b147d1a..09c576f 100644 --- a/fs/lockd/svc4proc.c +++ b/fs/lockd/svc4proc.c @@ -421,7 +421,7 @@ nlm4svc_proc_sm_notify(struct svc_rqst *rqstp, struct nlm_reboot *argp, return rpc_system_err; } - nlm_host_rebooted(argp); + nlm_host_rebooted(SVC_NET(rqstp), argp); return rpc_success; } diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c index 21171f0..fb26b9f 100644 --- a/fs/lockd/svcproc.c +++ b/fs/lockd/svcproc.c @@ -464,7 +464,7 @@ nlmsvc_proc_sm_notify(struct svc_rqst *rqstp, struct nlm_reboot *argp, return rpc_system_err; } - nlm_host_rebooted(argp); + nlm_host_rebooted(SVC_NET(rqstp), argp); return rpc_success; } @@ -205,28 +205,32 @@ static struct kmem_cache *filelock_cache __read_mostly; static struct file_lock_context * locks_get_lock_context(struct inode *inode, int type) { - struct file_lock_context *new; + struct file_lock_context *ctx; - if (likely(inode->i_flctx) || type == F_UNLCK) + /* paired with cmpxchg() below */ + ctx = smp_load_acquire(&inode->i_flctx); + if (likely(ctx) || type == F_UNLCK) goto out; - new = kmem_cache_alloc(flctx_cache, GFP_KERNEL); - if (!new) + ctx = kmem_cache_alloc(flctx_cache, GFP_KERNEL); + if (!ctx) goto out; - spin_lock_init(&new->flc_lock); - INIT_LIST_HEAD(&new->flc_flock); - INIT_LIST_HEAD(&new->flc_posix); - INIT_LIST_HEAD(&new->flc_lease); + spin_lock_init(&ctx->flc_lock); + INIT_LIST_HEAD(&ctx->flc_flock); + INIT_LIST_HEAD(&ctx->flc_posix); + INIT_LIST_HEAD(&ctx->flc_lease); /* * Assign the pointer if it's not already assigned. If it is, then * free the context we just allocated. */ - if (cmpxchg(&inode->i_flctx, NULL, new)) - kmem_cache_free(flctx_cache, new); + if (cmpxchg(&inode->i_flctx, NULL, ctx)) { + kmem_cache_free(flctx_cache, ctx); + ctx = smp_load_acquire(&inode->i_flctx); + } out: - return inode->i_flctx; + return ctx; } void @@ -762,7 +766,7 @@ posix_test_lock(struct file *filp, struct file_lock *fl) struct file_lock_context *ctx; struct inode *inode = file_inode(filp); - ctx = inode->i_flctx; + ctx = smp_load_acquire(&inode->i_flctx); if (!ctx || list_empty_careful(&ctx->flc_posix)) { fl->fl_type = F_UNLCK; return; @@ -1167,10 +1171,9 @@ EXPORT_SYMBOL(posix_lock_file); * @inode: inode of file to which lock request should be applied * @fl: The lock to be applied * - * Variant of posix_lock_file_wait that does not take a filp, and so can be - * used after the filp has already been torn down. + * Apply a POSIX style lock request to an inode. */ -int posix_lock_inode_wait(struct inode *inode, struct file_lock *fl) +static int posix_lock_inode_wait(struct inode *inode, struct file_lock *fl) { int error; might_sleep (); @@ -1187,7 +1190,6 @@ int posix_lock_inode_wait(struct inode *inode, struct file_lock *fl) } return error; } -EXPORT_SYMBOL(posix_lock_inode_wait); /** * locks_mandatory_locked - Check for an active lock @@ -1203,7 +1205,7 @@ int locks_mandatory_locked(struct file *file) struct file_lock_context *ctx; struct file_lock *fl; - ctx = inode->i_flctx; + ctx = smp_load_acquire(&inode->i_flctx); if (!ctx || list_empty_careful(&ctx->flc_posix)) return 0; @@ -1388,7 +1390,7 @@ any_leases_conflict(struct inode *inode, struct file_lock *breaker) int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) { int error = 0; - struct file_lock_context *ctx = inode->i_flctx; + struct file_lock_context *ctx; struct file_lock *new_fl, *fl, *tmp; unsigned long break_time; int want_write = (mode & O_ACCMODE) != O_RDONLY; @@ -1400,6 +1402,7 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) new_fl->fl_flags = type; /* typically we will check that ctx is non-NULL before calling */ + ctx = smp_load_acquire(&inode->i_flctx); if (!ctx) { WARN_ON_ONCE(1); return error; @@ -1494,9 +1497,10 @@ EXPORT_SYMBOL(__break_lease); void lease_get_mtime(struct inode *inode, struct timespec *time) { bool has_lease = false; - struct file_lock_context *ctx = inode->i_flctx; + struct file_lock_context *ctx; struct file_lock *fl; + ctx = smp_load_acquire(&inode->i_flctx); if (ctx && !list_empty_careful(&ctx->flc_lease)) { spin_lock(&ctx->flc_lock); if (!list_empty(&ctx->flc_lease)) { @@ -1543,10 +1547,11 @@ int fcntl_getlease(struct file *filp) { struct file_lock *fl; struct inode *inode = file_inode(filp); - struct file_lock_context *ctx = inode->i_flctx; + struct file_lock_context *ctx; int type = F_UNLCK; LIST_HEAD(dispose); + ctx = smp_load_acquire(&inode->i_flctx); if (ctx && !list_empty_careful(&ctx->flc_lease)) { spin_lock(&ctx->flc_lock); time_out_leases(file_inode(filp), &dispose); @@ -1711,11 +1716,11 @@ static int generic_delete_lease(struct file *filp, void *owner) { int error = -EAGAIN; struct file_lock *fl, *victim = NULL; - struct dentry *dentry = filp->f_path.dentry; - struct inode *inode = dentry->d_inode; - struct file_lock_context *ctx = inode->i_flctx; + struct inode *inode = file_inode(filp); + struct file_lock_context *ctx; LIST_HEAD(dispose); + ctx = smp_load_acquire(&inode->i_flctx); if (!ctx) { trace_generic_delete_lease(inode, NULL); return error; @@ -1751,8 +1756,7 @@ static int generic_delete_lease(struct file *filp, void *owner) int generic_setlease(struct file *filp, long arg, struct file_lock **flp, void **priv) { - struct dentry *dentry = filp->f_path.dentry; - struct inode *inode = dentry->d_inode; + struct inode *inode = file_inode(filp); int error; if ((!uid_eq(current_fsuid(), inode->i_uid)) && !capable(CAP_LEASE)) @@ -1856,7 +1860,7 @@ int fcntl_setlease(unsigned int fd, struct file *filp, long arg) * * Apply a FLOCK style lock request to an inode. */ -int flock_lock_inode_wait(struct inode *inode, struct file_lock *fl) +static int flock_lock_inode_wait(struct inode *inode, struct file_lock *fl) { int error; might_sleep(); @@ -1873,7 +1877,30 @@ int flock_lock_inode_wait(struct inode *inode, struct file_lock *fl) } return error; } -EXPORT_SYMBOL(flock_lock_inode_wait); + +/** + * locks_lock_inode_wait - Apply a lock to an inode + * @inode: inode of the file to apply to + * @fl: The lock to be applied + * + * Apply a POSIX or FLOCK style lock request to an inode. + */ +int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl) +{ + int res = 0; + switch (fl->fl_flags & (FL_POSIX|FL_FLOCK)) { + case FL_POSIX: + res = posix_lock_inode_wait(inode, fl); + break; + case FL_FLOCK: + res = flock_lock_inode_wait(inode, fl); + break; + default: + BUG(); + } + return res; +} +EXPORT_SYMBOL(locks_lock_inode_wait); /** * sys_flock: - flock() system call. @@ -1931,7 +1958,7 @@ SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd) (can_sleep) ? F_SETLKW : F_SETLK, lock); else - error = flock_lock_file_wait(f.file, lock); + error = locks_lock_file_wait(f.file, lock); out_free: locks_free_lock(lock); @@ -2107,7 +2134,7 @@ static int do_lock_file_wait(struct file *filp, unsigned int cmd, return error; } -/* Ensure that fl->fl_filp has compatible f_mode for F_SETLK calls */ +/* Ensure that fl->fl_file has compatible f_mode for F_SETLK calls */ static int check_fmode_for_setlk(struct file_lock *fl) { @@ -2359,13 +2386,14 @@ out: void locks_remove_posix(struct file *filp, fl_owner_t owner) { struct file_lock lock; - struct file_lock_context *ctx = file_inode(filp)->i_flctx; + struct file_lock_context *ctx; /* * If there are no locks held on this file, we don't need to call * posix_lock_file(). Another process could be setting a lock on this * file at the same time, but we wouldn't remove that lock anyway. */ + ctx = smp_load_acquire(&file_inode(filp)->i_flctx); if (!ctx || list_empty(&ctx->flc_posix)) return; @@ -2389,7 +2417,7 @@ EXPORT_SYMBOL(locks_remove_posix); /* The i_flctx must be valid when calling into here */ static void -locks_remove_flock(struct file *filp) +locks_remove_flock(struct file *filp, struct file_lock_context *flctx) { struct file_lock fl = { .fl_owner = filp, @@ -2400,7 +2428,6 @@ locks_remove_flock(struct file *filp) .fl_end = OFFSET_MAX, }; struct inode *inode = file_inode(filp); - struct file_lock_context *flctx = inode->i_flctx; if (list_empty(&flctx->flc_flock)) return; @@ -2416,10 +2443,8 @@ locks_remove_flock(struct file *filp) /* The i_flctx must be valid when calling into here */ static void -locks_remove_lease(struct file *filp) +locks_remove_lease(struct file *filp, struct file_lock_context *ctx) { - struct inode *inode = file_inode(filp); - struct file_lock_context *ctx = inode->i_flctx; struct file_lock *fl, *tmp; LIST_HEAD(dispose); @@ -2439,17 +2464,20 @@ locks_remove_lease(struct file *filp) */ void locks_remove_file(struct file *filp) { - if (!file_inode(filp)->i_flctx) + struct file_lock_context *ctx; + + ctx = smp_load_acquire(&file_inode(filp)->i_flctx); + if (!ctx) return; /* remove any OFD locks */ locks_remove_posix(filp, filp); /* remove flock locks */ - locks_remove_flock(filp); + locks_remove_flock(filp, ctx); /* remove any leases */ - locks_remove_lease(filp); + locks_remove_lease(filp, ctx); } /** @@ -2616,7 +2644,7 @@ void show_fd_locks(struct seq_file *f, struct file_lock_context *ctx; int id = 0; - ctx = inode->i_flctx; + ctx = smp_load_acquire(&inode->i_flctx); if (!ctx) return; diff --git a/fs/logfs/dev_bdev.c b/fs/logfs/dev_bdev.c index a7fdbd8..a709d80 100644 --- a/fs/logfs/dev_bdev.c +++ b/fs/logfs/dev_bdev.c @@ -81,7 +81,7 @@ static int __bdev_writeseg(struct super_block *sb, u64 ofs, pgoff_t index, unsigned int max_pages; int i; - max_pages = min(nr_pages, BIO_MAX_PAGES); + max_pages = min_t(size_t, nr_pages, BIO_MAX_PAGES); bio = bio_alloc(GFP_NOFS, max_pages); BUG_ON(!bio); @@ -171,7 +171,7 @@ static int do_erase(struct super_block *sb, u64 ofs, pgoff_t index, unsigned int max_pages; int i; - max_pages = min(nr_pages, BIO_MAX_PAGES); + max_pages = min_t(size_t, nr_pages, BIO_MAX_PAGES); bio = bio_alloc(GFP_NOFS, max_pages); BUG_ON(!bio); diff --git a/fs/logfs/segment.c b/fs/logfs/segment.c index 7f9b096..6de0fbf 100644 --- a/fs/logfs/segment.c +++ b/fs/logfs/segment.c @@ -57,7 +57,7 @@ static struct page *get_mapping_page(struct super_block *sb, pgoff_t index, filler_t *filler = super->s_devops->readpage; struct page *page; - BUG_ON(mapping_gfp_mask(mapping) & __GFP_FS); + BUG_ON(mapping_gfp_constraint(mapping, __GFP_FS)); if (use_filler) page = read_cache_page(mapping, index, filler, sb); else { @@ -139,7 +139,8 @@ map_buffer_to_page(struct page *page, struct buffer_head *bh, int page_block) static struct bio * do_mpage_readpage(struct bio *bio, struct page *page, unsigned nr_pages, sector_t *last_block_in_bio, struct buffer_head *map_bh, - unsigned long *first_logical_block, get_block_t get_block) + unsigned long *first_logical_block, get_block_t get_block, + gfp_t gfp) { struct inode *inode = page->mapping->host; const unsigned blkbits = inode->i_blkbits; @@ -277,8 +278,7 @@ alloc_new: goto out; } bio = mpage_alloc(bdev, blocks[0] << (blkbits - 9), - min_t(int, nr_pages, BIO_MAX_PAGES), - GFP_KERNEL); + min_t(int, nr_pages, BIO_MAX_PAGES), gfp); if (bio == NULL) goto confused; } @@ -361,6 +361,7 @@ mpage_readpages(struct address_space *mapping, struct list_head *pages, sector_t last_block_in_bio = 0; struct buffer_head map_bh; unsigned long first_logical_block = 0; + gfp_t gfp = mapping_gfp_constraint(mapping, GFP_KERNEL); map_bh.b_state = 0; map_bh.b_size = 0; @@ -370,12 +371,13 @@ mpage_readpages(struct address_space *mapping, struct list_head *pages, prefetchw(&page->flags); list_del(&page->lru); if (!add_to_page_cache_lru(page, mapping, - page->index, GFP_KERNEL)) { + page->index, + gfp)) { bio = do_mpage_readpage(bio, page, nr_pages - page_idx, &last_block_in_bio, &map_bh, &first_logical_block, - get_block); + get_block, gfp); } page_cache_release(page); } @@ -395,11 +397,12 @@ int mpage_readpage(struct page *page, get_block_t get_block) sector_t last_block_in_bio = 0; struct buffer_head map_bh; unsigned long first_logical_block = 0; + gfp_t gfp = mapping_gfp_constraint(page->mapping, GFP_KERNEL); map_bh.b_state = 0; map_bh.b_size = 0; bio = do_mpage_readpage(bio, page, 1, &last_block_in_bio, - &map_bh, &first_logical_block, get_block); + &map_bh, &first_logical_block, get_block, gfp); if (bio) mpage_bio_submit(READ, bio); return 0; @@ -482,6 +485,7 @@ static int __mpage_writepage(struct page *page, struct writeback_control *wbc, struct buffer_head map_bh; loff_t i_size = i_size_read(inode); int ret = 0; + int wr = (wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : WRITE); if (page_has_buffers(page)) { struct buffer_head *head = page_buffers(page); @@ -590,7 +594,7 @@ page_is_mapped: * This page will go to BIO. Do we need to send this BIO off first? */ if (bio && mpd->last_block_in_bio != blocks[0] - 1) - bio = mpage_bio_submit(WRITE, bio); + bio = mpage_bio_submit(wr, bio); alloc_new: if (bio == NULL) { @@ -617,7 +621,7 @@ alloc_new: wbc_account_io(wbc, page, PAGE_SIZE); length = first_unmapped << blkbits; if (bio_add_page(bio, page, length, 0) < length) { - bio = mpage_bio_submit(WRITE, bio); + bio = mpage_bio_submit(wr, bio); goto alloc_new; } @@ -627,7 +631,7 @@ alloc_new: set_page_writeback(page); unlock_page(page); if (boundary || (first_unmapped != blocks_per_page)) { - bio = mpage_bio_submit(WRITE, bio); + bio = mpage_bio_submit(wr, bio); if (boundary_block) { write_boundary_block(boundary_bdev, boundary_block, 1 << blkbits); @@ -639,7 +643,7 @@ alloc_new: confused: if (bio) - bio = mpage_bio_submit(WRITE, bio); + bio = mpage_bio_submit(wr, bio); if (mpd->use_writepage) { ret = mapping->a_ops->writepage(page, wbc); @@ -695,8 +699,11 @@ mpage_writepages(struct address_space *mapping, }; ret = write_cache_pages(mapping, wbc, __mpage_writepage, &mpd); - if (mpd.bio) - mpage_bio_submit(WRITE, mpd.bio); + if (mpd.bio) { + int wr = (wbc->sync_mode == WB_SYNC_ALL ? + WRITE_SYNC : WRITE); + mpage_bio_submit(wr, mpd.bio); + } } blk_finish_plug(&plug); return ret; @@ -713,8 +720,11 @@ int mpage_writepage(struct page *page, get_block_t get_block, .use_writepage = 0, }; int ret = __mpage_writepage(page, wbc, &mpd); - if (mpd.bio) - mpage_bio_submit(WRITE, mpd.bio); + if (mpd.bio) { + int wr = (wbc->sync_mode == WB_SYNC_ALL ? + WRITE_SYNC : WRITE); + mpage_bio_submit(wr, mpd.bio); + } return ret; } EXPORT_SYMBOL(mpage_writepage); @@ -955,26 +955,23 @@ static bool safe_hardlink_source(struct inode *inode) * - sysctl_protected_hardlinks enabled * - fsuid does not match inode * - hardlink source is unsafe (see safe_hardlink_source() above) - * - not CAP_FOWNER + * - not CAP_FOWNER in a namespace with the inode owner uid mapped * * Returns 0 if successful, -ve on error. */ static int may_linkat(struct path *link) { - const struct cred *cred; struct inode *inode; if (!sysctl_protected_hardlinks) return 0; - cred = current_cred(); inode = link->dentry->d_inode; /* Source inode owner (or CAP_FOWNER) can hardlink all they like, * otherwise, it must be a safe source. */ - if (uid_eq(cred->fsuid, inode->i_uid) || safe_hardlink_source(inode) || - capable(CAP_FOWNER)) + if (inode_owner_or_capable(inode) || safe_hardlink_source(inode)) return 0; audit_log_link_denied("linkat", link); @@ -1558,8 +1555,6 @@ static int lookup_fast(struct nameidata *nd, negative = d_is_negative(dentry); if (read_seqcount_retry(&dentry->d_seq, seq)) return -ECHILD; - if (negative) - return -ENOENT; /* * This sequence count validates that the parent had no @@ -1580,6 +1575,12 @@ static int lookup_fast(struct nameidata *nd, goto unlazy; } } + /* + * Note: do negative dentry check after revalidation in + * case that drops it. + */ + if (negative) + return -ENOENT; path->mnt = mnt; path->dentry = dentry; if (likely(__follow_mount_rcu(nd, path, inode, seqp))) @@ -1965,7 +1966,7 @@ OK: if (err) { const char *s = get_link(nd); - if (unlikely(IS_ERR(s))) + if (IS_ERR(s)) return PTR_ERR(s); err = 0; if (unlikely(!s)) { @@ -3379,7 +3380,7 @@ struct file *do_file_open_root(struct dentry *dentry, struct vfsmount *mnt, return ERR_PTR(-ELOOP); filename = getname_kernel(name); - if (unlikely(IS_ERR(filename))) + if (IS_ERR(filename)) return ERR_CAST(filename); set_nameidata(&nd, -1, filename); @@ -4603,7 +4604,7 @@ EXPORT_SYMBOL(__page_symlink); int page_symlink(struct inode *inode, const char *symname, int len) { return __page_symlink(inode, symname, len, - !(mapping_gfp_mask(inode->i_mapping) & __GFP_FS)); + !mapping_gfp_constraint(inode->i_mapping, __GFP_FS)); } EXPORT_SYMBOL(page_symlink); diff --git a/fs/ncpfs/dir.c b/fs/ncpfs/dir.c index 93575e9..f0e3e9e 100644 --- a/fs/ncpfs/dir.c +++ b/fs/ncpfs/dir.c @@ -597,7 +597,7 @@ ncp_fill_cache(struct file *file, struct dir_context *ctx, qname.name = __name; newdent = d_hash_and_lookup(dentry, &qname); - if (unlikely(IS_ERR(newdent))) + if (IS_ERR(newdent)) goto end_advance; if (!newdent) { newdent = d_alloc(dentry, &qname); @@ -1165,8 +1165,6 @@ out: static int ncp_mknod(struct inode * dir, struct dentry *dentry, umode_t mode, dev_t rdev) { - if (!new_valid_dev(rdev)) - return -EINVAL; if (ncp_is_nfs_extras(NCP_SERVER(dir), NCP_FINFO(dir)->volNumber)) { ncp_dbg(1, "mode = 0%ho\n", mode); return ncp_create_new(dir, dentry, mode, rdev, 0); diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c index 9cd4eb3..ddd0138 100644 --- a/fs/nfs/blocklayout/blocklayout.c +++ b/fs/nfs/blocklayout/blocklayout.c @@ -229,7 +229,7 @@ bl_read_pagelist(struct nfs_pgio_header *header) struct parallel_io *par; loff_t f_offset = header->args.offset; size_t bytes_left = header->args.count; - unsigned int pg_offset, pg_len; + unsigned int pg_offset = header->args.pgbase, pg_len; struct page **pages = header->args.pages; int pg_index = header->args.pgbase >> PAGE_CACHE_SHIFT; const bool is_dio = (header->dreq != NULL); @@ -262,7 +262,6 @@ bl_read_pagelist(struct nfs_pgio_header *header) extent_length = be.be_length - (isect - be.be_f_offset); } - pg_offset = f_offset & ~PAGE_CACHE_MASK; if (is_dio) { if (pg_offset + bytes_left > PAGE_CACHE_SIZE) pg_len = PAGE_CACHE_SIZE - pg_offset; @@ -273,9 +272,6 @@ bl_read_pagelist(struct nfs_pgio_header *header) pg_len = PAGE_CACHE_SIZE; } - isect += (pg_offset >> SECTOR_SHIFT); - extent_length -= (pg_offset >> SECTOR_SHIFT); - if (is_hole(&be)) { bio = bl_submit_bio(READ, bio); /* Fill hole w/ zeroes w/o accessing device */ @@ -301,6 +297,7 @@ bl_read_pagelist(struct nfs_pgio_header *header) extent_length -= (pg_len >> SECTOR_SHIFT); f_offset += pg_len; bytes_left -= pg_len; + pg_offset = 0; } if ((isect << SECTOR_SHIFT) >= header->inode->i_size) { header->res.eof = 1; diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index 75f7c0a..a7f2e6e 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -99,17 +99,6 @@ nfs4_callback_up(struct svc_serv *serv) } #if defined(CONFIG_NFS_V4_1) -static int nfs41_callback_up_net(struct svc_serv *serv, struct net *net) -{ - /* - * Create an svc_sock for the back channel service that shares the - * fore channel connection. - * Returns the input port (0) and sets the svc_serv bc_xprt on success - */ - return svc_create_xprt(serv, "tcp-bc", net, PF_INET, 0, - SVC_SOCK_ANONYMOUS); -} - /* * The callback service for NFSv4.1 callbacks */ @@ -184,11 +173,6 @@ static inline void nfs_callback_bc_serv(u32 minorversion, struct rpc_xprt *xprt, xprt->bc_serv = serv; } #else -static int nfs41_callback_up_net(struct svc_serv *serv, struct net *net) -{ - return 0; -} - static void nfs_minorversion_callback_svc_setup(struct svc_serv *serv, struct svc_rqst **rqstpp, int (**callback_svc)(void *vrqstp)) { @@ -259,7 +243,8 @@ static void nfs_callback_down_net(u32 minorversion, struct svc_serv *serv, struc svc_shutdown_net(serv, net); } -static int nfs_callback_up_net(int minorversion, struct svc_serv *serv, struct net *net) +static int nfs_callback_up_net(int minorversion, struct svc_serv *serv, + struct net *net, struct rpc_xprt *xprt) { struct nfs_net *nn = net_generic(net, nfs_net_id); int ret; @@ -275,20 +260,11 @@ static int nfs_callback_up_net(int minorversion, struct svc_serv *serv, struct n goto err_bind; } - switch (minorversion) { - case 0: - ret = nfs4_callback_up_net(serv, net); - break; - case 1: - case 2: - ret = nfs41_callback_up_net(serv, net); - break; - default: - printk(KERN_ERR "NFS: unknown callback version: %d\n", - minorversion); - ret = -EINVAL; - break; - } + ret = -EPROTONOSUPPORT; + if (minorversion == 0) + ret = nfs4_callback_up_net(serv, net); + else if (xprt->ops->bc_up) + ret = xprt->ops->bc_up(serv, net); if (ret < 0) { printk(KERN_ERR "NFS: callback service start failed\n"); @@ -364,7 +340,7 @@ int nfs_callback_up(u32 minorversion, struct rpc_xprt *xprt) goto err_create; } - ret = nfs_callback_up_net(minorversion, serv, net); + ret = nfs_callback_up_net(minorversion, serv, net, xprt); if (ret < 0) goto err_net; diff --git a/fs/nfs/callback.h b/fs/nfs/callback.h index 84326e9..ff8195b 100644 --- a/fs/nfs/callback.h +++ b/fs/nfs/callback.h @@ -61,7 +61,6 @@ struct cb_compound_hdr_res { }; struct cb_getattrargs { - struct sockaddr *addr; struct nfs_fh fh; uint32_t bitmap[2]; }; @@ -76,7 +75,6 @@ struct cb_getattrres { }; struct cb_recallargs { - struct sockaddr *addr; struct nfs_fh fh; nfs4_stateid stateid; uint32_t truncate; @@ -119,9 +117,6 @@ extern __be32 nfs4_callback_sequence(struct cb_sequenceargs *args, struct cb_sequenceres *res, struct cb_process_state *cps); -extern int nfs41_validate_delegation_stateid(struct nfs_delegation *delegation, - const nfs4_stateid *stateid); - #define RCA4_TYPE_MASK_RDATA_DLG 0 #define RCA4_TYPE_MASK_WDATA_DLG 1 #define RCA4_TYPE_MASK_DIR_DLG 2 @@ -134,7 +129,6 @@ extern int nfs41_validate_delegation_stateid(struct nfs_delegation *delegation, #define RCA4_TYPE_MASK_ALL 0xf31f struct cb_recallanyargs { - struct sockaddr *craa_addr; uint32_t craa_objs_to_keep; uint32_t craa_type_mask; }; @@ -144,7 +138,6 @@ extern __be32 nfs4_callback_recallany(struct cb_recallanyargs *args, struct cb_process_state *cps); struct cb_recallslotargs { - struct sockaddr *crsa_addr; uint32_t crsa_target_highest_slotid; }; extern __be32 nfs4_callback_recallslot(struct cb_recallslotargs *args, @@ -152,7 +145,6 @@ extern __be32 nfs4_callback_recallslot(struct cb_recallslotargs *args, struct cb_process_state *cps); struct cb_layoutrecallargs { - struct sockaddr *cbl_addr; uint32_t cbl_recall_type; uint32_t cbl_layout_type; uint32_t cbl_layoutchanged; @@ -196,9 +188,6 @@ extern __be32 nfs4_callback_recall(struct cb_recallargs *args, void *dummy, #if IS_ENABLED(CONFIG_NFS_V4) extern int nfs_callback_up(u32 minorversion, struct rpc_xprt *xprt); extern void nfs_callback_down(int minorversion, struct net *net); -extern int nfs4_validate_delegation_stateid(struct nfs_delegation *delegation, - const nfs4_stateid *stateid); -extern int nfs4_set_callback_sessionid(struct nfs_client *clp); #endif /* CONFIG_NFS_V4 */ /* * nfs41: Callbacks are expected to not cause substantial latency, @@ -209,6 +198,5 @@ extern int nfs4_set_callback_sessionid(struct nfs_client *clp); #define NFS41_BC_MAX_CALLBACKS 1 extern unsigned int nfs_callback_set_tcpport; -extern unsigned short nfs_callback_tcpport; #endif /* __LINUX_FS_NFS_CALLBACK_H */ diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c index b85cf7a..807eb6e 100644 --- a/fs/nfs/callback_proc.c +++ b/fs/nfs/callback_proc.c @@ -17,9 +17,7 @@ #include "nfs4session.h" #include "nfs4trace.h" -#ifdef NFS_DEBUG #define NFSDBG_FACILITY NFSDBG_CALLBACK -#endif __be32 nfs4_callback_getattr(struct cb_getattrargs *args, struct cb_getattrres *res, diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index 6b1697a..646cdac 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -18,19 +18,21 @@ #include "internal.h" #include "nfs4session.h" -#define CB_OP_TAGLEN_MAXSZ (512) -#define CB_OP_HDR_RES_MAXSZ (2 + CB_OP_TAGLEN_MAXSZ) -#define CB_OP_GETATTR_BITMAP_MAXSZ (4) -#define CB_OP_GETATTR_RES_MAXSZ (CB_OP_HDR_RES_MAXSZ + \ - CB_OP_GETATTR_BITMAP_MAXSZ + \ - 2 + 2 + 3 + 3) -#define CB_OP_RECALL_RES_MAXSZ (CB_OP_HDR_RES_MAXSZ) +#define CB_OP_TAGLEN_MAXSZ (512) +#define CB_OP_HDR_RES_MAXSZ (2 * 4) // opcode, status +#define CB_OP_GETATTR_BITMAP_MAXSZ (4 * 4) // bitmap length, 3 bitmaps +#define CB_OP_GETATTR_RES_MAXSZ (CB_OP_HDR_RES_MAXSZ + \ + CB_OP_GETATTR_BITMAP_MAXSZ + \ + /* change, size, ctime, mtime */\ + (2 + 2 + 3 + 3) * 4) +#define CB_OP_RECALL_RES_MAXSZ (CB_OP_HDR_RES_MAXSZ) #if defined(CONFIG_NFS_V4_1) #define CB_OP_LAYOUTRECALL_RES_MAXSZ (CB_OP_HDR_RES_MAXSZ) #define CB_OP_DEVICENOTIFY_RES_MAXSZ (CB_OP_HDR_RES_MAXSZ) #define CB_OP_SEQUENCE_RES_MAXSZ (CB_OP_HDR_RES_MAXSZ + \ - 4 + 1 + 3) + NFS4_MAX_SESSIONID_LEN + \ + (1 + 3) * 4) // seqid, 3 slotids #define CB_OP_RECALLANY_RES_MAXSZ (CB_OP_HDR_RES_MAXSZ) #define CB_OP_RECALLSLOT_RES_MAXSZ (CB_OP_HDR_RES_MAXSZ) #endif /* CONFIG_NFS_V4_1 */ @@ -157,7 +159,7 @@ static __be32 decode_compound_hdr_arg(struct xdr_stream *xdr, struct cb_compound if (unlikely(status != 0)) return status; /* We do not like overly long tags! */ - if (hdr->taglen > CB_OP_TAGLEN_MAXSZ - 12) { + if (hdr->taglen > CB_OP_TAGLEN_MAXSZ) { printk("NFS: NFSv4 CALLBACK %s: client sent tag of length %u\n", __func__, hdr->taglen); return htonl(NFS4ERR_RESOURCE); @@ -198,7 +200,6 @@ static __be32 decode_getattr_args(struct svc_rqst *rqstp, struct xdr_stream *xdr status = decode_fh(xdr, &args->fh); if (unlikely(status != 0)) goto out; - args->addr = svc_addr(rqstp); status = decode_bitmap(xdr, args->bitmap); out: dprintk("%s: exit with status = %d\n", __func__, ntohl(status)); @@ -210,7 +211,6 @@ static __be32 decode_recall_args(struct svc_rqst *rqstp, struct xdr_stream *xdr, __be32 *p; __be32 status; - args->addr = svc_addr(rqstp); status = decode_stateid(xdr, &args->stateid); if (unlikely(status != 0)) goto out; @@ -236,7 +236,6 @@ static __be32 decode_layoutrecall_args(struct svc_rqst *rqstp, __be32 status = 0; uint32_t iomode; - args->cbl_addr = svc_addr(rqstp); p = read_buf(xdr, 4 * sizeof(uint32_t)); if (unlikely(p == NULL)) { status = htonl(NFS4ERR_BADXDR); @@ -383,13 +382,12 @@ static __be32 decode_sessionid(struct xdr_stream *xdr, struct nfs4_sessionid *sid) { __be32 *p; - int len = NFS4_MAX_SESSIONID_LEN; - p = read_buf(xdr, len); + p = read_buf(xdr, NFS4_MAX_SESSIONID_LEN); if (unlikely(p == NULL)) return htonl(NFS4ERR_RESOURCE); - memcpy(sid->data, p, len); + memcpy(sid->data, p, NFS4_MAX_SESSIONID_LEN); return 0; } @@ -500,7 +498,6 @@ static __be32 decode_recallany_args(struct svc_rqst *rqstp, uint32_t bitmap[2]; __be32 *p, status; - args->craa_addr = svc_addr(rqstp); p = read_buf(xdr, 4); if (unlikely(p == NULL)) return htonl(NFS4ERR_BADXDR); @@ -519,7 +516,6 @@ static __be32 decode_recallslot_args(struct svc_rqst *rqstp, { __be32 *p; - args->crsa_addr = svc_addr(rqstp); p = read_buf(xdr, 4); if (unlikely(p == NULL)) return htonl(NFS4ERR_BADXDR); @@ -684,13 +680,12 @@ static __be32 encode_sessionid(struct xdr_stream *xdr, const struct nfs4_sessionid *sid) { __be32 *p; - int len = NFS4_MAX_SESSIONID_LEN; - p = xdr_reserve_space(xdr, len); + p = xdr_reserve_space(xdr, NFS4_MAX_SESSIONID_LEN); if (unlikely(p == NULL)) return htonl(NFS4ERR_RESOURCE); - memcpy(p, sid, len); + memcpy(p, sid, NFS4_MAX_SESSIONID_LEN); return 0; } @@ -704,7 +699,9 @@ static __be32 encode_cb_sequence_res(struct svc_rqst *rqstp, if (unlikely(status != 0)) goto out; - encode_sessionid(xdr, &res->csr_sessionid); + status = encode_sessionid(xdr, &res->csr_sessionid); + if (status) + goto out; p = xdr_reserve_space(xdr, 4 * sizeof(uint32_t)); if (unlikely(p == NULL)) diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 57c5a02..d6d5d2a 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -764,6 +764,7 @@ static void nfs_server_set_fsinfo(struct nfs_server *server, server->time_delta = fsinfo->time_delta; + server->clone_blksize = fsinfo->clone_blksize; /* We're airborne Set socket buffersize */ rpc_setbufsize(server->client, server->wsize + 100, server->rsize + 100); } diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index 2714ef8..5166adc 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -113,7 +113,8 @@ out: return status; } -static int nfs_delegation_claim_opens(struct inode *inode, const nfs4_stateid *stateid) +static int nfs_delegation_claim_opens(struct inode *inode, + const nfs4_stateid *stateid, fmode_t type) { struct nfs_inode *nfsi = NFS_I(inode); struct nfs_open_context *ctx; @@ -140,7 +141,7 @@ again: /* Block nfs4_proc_unlck */ mutex_lock(&sp->so_delegreturn_mutex); seq = raw_seqcount_begin(&sp->so_reclaim_seqcount); - err = nfs4_open_delegation_recall(ctx, state, stateid); + err = nfs4_open_delegation_recall(ctx, state, stateid, type); if (!err) err = nfs_delegation_claim_locks(ctx, state, stateid); if (!err && read_seqcount_retry(&sp->so_reclaim_seqcount, seq)) @@ -411,7 +412,8 @@ static int nfs_end_delegation_return(struct inode *inode, struct nfs_delegation do { if (test_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) break; - err = nfs_delegation_claim_opens(inode, &delegation->stateid); + err = nfs_delegation_claim_opens(inode, &delegation->stateid, + delegation->type); if (!issync || err != -EAGAIN) break; /* @@ -719,14 +721,12 @@ int nfs_async_inode_return_delegation(struct inode *inode, struct nfs_client *clp = server->nfs_client; struct nfs_delegation *delegation; - filemap_flush(inode->i_mapping); - rcu_read_lock(); delegation = rcu_dereference(NFS_I(inode)->delegation); if (delegation == NULL) goto out_enoent; - - if (!clp->cl_mvops->match_stateid(&delegation->stateid, stateid)) + if (stateid != NULL && + !clp->cl_mvops->match_stateid(&delegation->stateid, stateid)) goto out_enoent; nfs_mark_return_delegation(server, delegation); rcu_read_unlock(); diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h index a448291..333063e 100644 --- a/fs/nfs/delegation.h +++ b/fs/nfs/delegation.h @@ -54,7 +54,7 @@ void nfs_delegation_reap_unclaimed(struct nfs_client *clp); /* NFSv4 delegation-related procedures */ int nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, const nfs4_stateid *stateid, int issync); -int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state *state, const nfs4_stateid *stateid); +int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state *state, const nfs4_stateid *stateid, fmode_t type); int nfs4_lock_delegation_recall(struct file_lock *fl, struct nfs4_state *state, const nfs4_stateid *stateid); bool nfs4_copy_delegation_stateid(nfs4_stateid *dst, struct inode *inode, fmode_t flags); diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 3d8e4ff..ce5a218 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1714,9 +1714,6 @@ nfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) dfprintk(VFS, "NFS: mknod(%s/%lu), %pd\n", dir->i_sb->s_id, dir->i_ino, dentry); - if (!new_valid_dev(rdev)) - return -EINVAL; - attr.ia_mode = mode; attr.ia_valid = ATTR_MODE; diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 38678d9..4b1d08f 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -166,8 +166,11 @@ nfs_direct_select_verf(struct nfs_direct_req *dreq, struct nfs_writeverf *verfp = &dreq->verf; #ifdef CONFIG_NFS_V4_1 - if (ds_clp) { - /* pNFS is in use, use the DS verf */ + /* + * pNFS is in use, use the DS verf except commit_through_mds is set + * for layout segment where nbuckets is zero. + */ + if (ds_clp && dreq->ds_cinfo.nbuckets > 0) { if (commit_idx >= 0 && commit_idx < dreq->ds_cinfo.nbuckets) verfp = &dreq->ds_cinfo.buckets[commit_idx].direct_verf; else diff --git a/fs/nfs/file.c b/fs/nfs/file.c index c0f9b1e..93e2364 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -473,8 +473,8 @@ static int nfs_release_page(struct page *page, gfp_t gfp) dfprintk(PAGECACHE, "NFS: release_page(%p)\n", page); /* Always try to initiate a 'commit' if relevant, but only - * wait for it if __GFP_WAIT is set. Even then, only wait 1 - * second and only if the 'bdi' is not congested. + * wait for it if the caller allows blocking. Even then, + * only wait 1 second and only if the 'bdi' is not congested. * Waiting indefinitely can cause deadlocks when the NFS * server is on this machine, when a new TCP connection is * needed and in other rare cases. There is no particular @@ -484,7 +484,7 @@ static int nfs_release_page(struct page *page, gfp_t gfp) if (mapping) { struct nfs_server *nfss = NFS_SERVER(mapping->host); nfs_commit_inode(mapping->host, 0); - if ((gfp & __GFP_WAIT) && + if (gfpflags_allow_blocking(gfp) && !bdi_write_congested(&nfss->backing_dev_info)) { wait_on_page_bit_killable_timeout(page, PG_private, HZ); @@ -738,18 +738,7 @@ out_noconflict: static int do_vfs_lock(struct file *file, struct file_lock *fl) { - int res = 0; - switch (fl->fl_flags & (FL_POSIX|FL_FLOCK)) { - case FL_POSIX: - res = posix_lock_file_wait(file, fl); - break; - case FL_FLOCK: - res = flock_lock_file_wait(file, fl); - break; - default: - BUG(); - } - return res; + return locks_lock_file_wait(file, fl); } static int diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index b34f2e2..02ec079 100644 --- a/fs/nfs/filelayout/filelayout.c +++ b/fs/nfs/filelayout/filelayout.c @@ -629,23 +629,18 @@ out_put: goto out; } -static void filelayout_free_fh_array(struct nfs4_filelayout_segment *fl) +static void _filelayout_free_lseg(struct nfs4_filelayout_segment *fl) { int i; - for (i = 0; i < fl->num_fh; i++) { - if (!fl->fh_array[i]) - break; - kfree(fl->fh_array[i]); + if (fl->fh_array) { + for (i = 0; i < fl->num_fh; i++) { + if (!fl->fh_array[i]) + break; + kfree(fl->fh_array[i]); + } + kfree(fl->fh_array); } - kfree(fl->fh_array); - fl->fh_array = NULL; -} - -static void -_filelayout_free_lseg(struct nfs4_filelayout_segment *fl) -{ - filelayout_free_fh_array(fl); kfree(fl); } @@ -716,21 +711,21 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo, /* Do we want to use a mempool here? */ fl->fh_array[i] = kmalloc(sizeof(struct nfs_fh), gfp_flags); if (!fl->fh_array[i]) - goto out_err_free; + goto out_err; p = xdr_inline_decode(&stream, 4); if (unlikely(!p)) - goto out_err_free; + goto out_err; fl->fh_array[i]->size = be32_to_cpup(p++); if (sizeof(struct nfs_fh) < fl->fh_array[i]->size) { printk(KERN_ERR "NFS: Too big fh %d received %d\n", i, fl->fh_array[i]->size); - goto out_err_free; + goto out_err; } p = xdr_inline_decode(&stream, fl->fh_array[i]->size); if (unlikely(!p)) - goto out_err_free; + goto out_err; memcpy(fl->fh_array[i]->data, p, fl->fh_array[i]->size); dprintk("DEBUG: %s: fh len %d\n", __func__, fl->fh_array[i]->size); @@ -739,8 +734,6 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo, __free_page(scratch); return 0; -out_err_free: - filelayout_free_fh_array(fl); out_err: __free_page(scratch); return -EIO; diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index fbc5a56..03516c8 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -339,6 +339,19 @@ static void ff_layout_sort_mirrors(struct nfs4_ff_layout_segment *fls) } } +static void ff_layout_mark_devices_valid(struct nfs4_ff_layout_segment *fls) +{ + struct nfs4_deviceid_node *node; + int i; + + if (!(fls->flags & FF_FLAGS_NO_IO_THRU_MDS)) + return; + for (i = 0; i < fls->mirror_array_cnt; i++) { + node = &fls->mirror_array[i]->mirror_ds->id_node; + clear_bit(NFS_DEVICEID_UNAVAILABLE, &node->flags); + } +} + static struct pnfs_layout_segment * ff_layout_alloc_lseg(struct pnfs_layout_hdr *lh, struct nfs4_layoutget_res *lgr, @@ -499,6 +512,7 @@ ff_layout_alloc_lseg(struct pnfs_layout_hdr *lh, rc = ff_layout_check_layout(lgr); if (rc) goto out_err_free; + ff_layout_mark_devices_valid(fls); ret = &fls->generic_hdr; dprintk("<-- %s (success)\n", __func__); @@ -741,17 +755,17 @@ ff_layout_alloc_commit_info(struct pnfs_layout_segment *lseg, } static struct nfs4_pnfs_ds * -ff_layout_choose_best_ds_for_read(struct nfs_pageio_descriptor *pgio, +ff_layout_choose_best_ds_for_read(struct pnfs_layout_segment *lseg, + int start_idx, int *best_idx) { - struct nfs4_ff_layout_segment *fls; + struct nfs4_ff_layout_segment *fls = FF_LAYOUT_LSEG(lseg); struct nfs4_pnfs_ds *ds; int idx; - fls = FF_LAYOUT_LSEG(pgio->pg_lseg); /* mirrors are sorted by efficiency */ - for (idx = 0; idx < fls->mirror_array_cnt; idx++) { - ds = nfs4_ff_layout_prepare_ds(pgio->pg_lseg, idx, false); + for (idx = start_idx; idx < fls->mirror_array_cnt; idx++) { + ds = nfs4_ff_layout_prepare_ds(lseg, idx, false); if (ds) { *best_idx = idx; return ds; @@ -782,7 +796,7 @@ ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio, if (pgio->pg_lseg == NULL) goto out_mds; - ds = ff_layout_choose_best_ds_for_read(pgio, &ds_idx); + ds = ff_layout_choose_best_ds_for_read(pgio->pg_lseg, 0, &ds_idx); if (!ds) goto out_mds; mirror = FF_LAYOUT_COMP(pgio->pg_lseg, ds_idx); @@ -1035,7 +1049,8 @@ static int ff_layout_async_handle_error_v4(struct rpc_task *task, rpc_wake_up(&tbl->slot_tbl_waitq); /* fall through */ default: - if (ff_layout_has_available_ds(lseg)) + if (ff_layout_no_fallback_to_mds(lseg) || + ff_layout_has_available_ds(lseg)) return -NFS4ERR_RESET_TO_PNFS; reset: dprintk("%s Retry through MDS. Error %d\n", __func__, @@ -1153,7 +1168,6 @@ static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg, } /* NFS_PROTO call done callback routines */ - static int ff_layout_read_done_cb(struct rpc_task *task, struct nfs_pgio_header *hdr) { @@ -1171,6 +1185,10 @@ static int ff_layout_read_done_cb(struct rpc_task *task, switch (err) { case -NFS4ERR_RESET_TO_PNFS: + if (ff_layout_choose_best_ds_for_read(hdr->lseg, + hdr->pgio_mirror_idx + 1, + &hdr->pgio_mirror_idx)) + goto out_eagain; set_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, &hdr->lseg->pls_layout->plh_flags); pnfs_read_resend_pnfs(hdr); @@ -1179,11 +1197,13 @@ static int ff_layout_read_done_cb(struct rpc_task *task, ff_layout_reset_read(hdr); return task->tk_status; case -EAGAIN: - rpc_restart_call_prepare(task); - return -EAGAIN; + goto out_eagain; } return 0; +out_eagain: + rpc_restart_call_prepare(task); + return -EAGAIN; } static bool diff --git a/fs/nfs/flexfilelayout/flexfilelayout.h b/fs/nfs/flexfilelayout/flexfilelayout.h index 68cc0d9..2bb08bc 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.h +++ b/fs/nfs/flexfilelayout/flexfilelayout.h @@ -10,6 +10,7 @@ #define FS_NFS_NFS4FLEXFILELAYOUT_H #define FF_FLAGS_NO_LAYOUTCOMMIT 1 +#define FF_FLAGS_NO_IO_THRU_MDS 2 #include "../pnfs.h" @@ -146,6 +147,12 @@ FF_LAYOUT_MIRROR_COUNT(struct pnfs_layout_segment *lseg) } static inline bool +ff_layout_no_fallback_to_mds(struct pnfs_layout_segment *lseg) +{ + return FF_LAYOUT_LSEG(lseg)->flags & FF_FLAGS_NO_IO_THRU_MDS; +} + +static inline bool ff_layout_test_devid_unavailable(struct nfs4_deviceid_node *node) { return nfs4_test_deviceid_unavailable(node); diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c index 99a4528..09b1900 100644 --- a/fs/nfs/mount_clnt.c +++ b/fs/nfs/mount_clnt.c @@ -16,9 +16,7 @@ #include <linux/nfs_fs.h> #include "internal.h" -#ifdef NFS_DEBUG -# define NFSDBG_FACILITY NFSDBG_MOUNT -#endif +#define NFSDBG_FACILITY NFSDBG_MOUNT /* * Defined by RFC 1094, section A.3; and RFC 1813, section 5.1.4 diff --git a/fs/nfs/nfs42.h b/fs/nfs/nfs42.h index 814c125..b587ccd 100644 --- a/fs/nfs/nfs42.h +++ b/fs/nfs/nfs42.h @@ -17,5 +17,6 @@ int nfs42_proc_deallocate(struct file *, loff_t, loff_t); loff_t nfs42_proc_llseek(struct file *, loff_t, int); int nfs42_proc_layoutstats_generic(struct nfs_server *, struct nfs42_layoutstat_data *); +int nfs42_proc_clone(struct file *, struct file *, loff_t, loff_t, loff_t); #endif /* __LINUX_FS_NFS_NFS4_2_H */ diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index d731bbf..3e92a3c 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -175,10 +175,12 @@ loff_t nfs42_proc_llseek(struct file *filep, loff_t offset, int whence) { struct nfs_server *server = NFS_SERVER(file_inode(filep)); struct nfs4_exception exception = { }; - int err; + loff_t err; do { err = _nfs42_proc_llseek(filep, offset, whence); + if (err >= 0) + break; if (err == -ENOTSUPP) return -EOPNOTSUPP; err = nfs4_handle_exception(server, err, &exception); @@ -269,3 +271,74 @@ int nfs42_proc_layoutstats_generic(struct nfs_server *server, return PTR_ERR(task); return 0; } + +static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f, + struct file *dst_f, loff_t src_offset, + loff_t dst_offset, loff_t count) +{ + struct inode *src_inode = file_inode(src_f); + struct inode *dst_inode = file_inode(dst_f); + struct nfs_server *server = NFS_SERVER(dst_inode); + struct nfs42_clone_args args = { + .src_fh = NFS_FH(src_inode), + .dst_fh = NFS_FH(dst_inode), + .src_offset = src_offset, + .dst_offset = dst_offset, + .dst_bitmask = server->cache_consistency_bitmask, + }; + struct nfs42_clone_res res = { + .server = server, + }; + int status; + + msg->rpc_argp = &args; + msg->rpc_resp = &res; + + status = nfs42_set_rw_stateid(&args.src_stateid, src_f, FMODE_READ); + if (status) + return status; + + status = nfs42_set_rw_stateid(&args.dst_stateid, dst_f, FMODE_WRITE); + if (status) + return status; + + res.dst_fattr = nfs_alloc_fattr(); + if (!res.dst_fattr) + return -ENOMEM; + + status = nfs4_call_sync(server->client, server, msg, + &args.seq_args, &res.seq_res, 0); + if (status == 0) + status = nfs_post_op_update_inode(dst_inode, res.dst_fattr); + + kfree(res.dst_fattr); + return status; +} + +int nfs42_proc_clone(struct file *src_f, struct file *dst_f, + loff_t src_offset, loff_t dst_offset, loff_t count) +{ + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_CLONE], + }; + struct inode *inode = file_inode(src_f); + struct nfs_server *server = NFS_SERVER(file_inode(src_f)); + struct nfs4_exception exception = { }; + int err; + + if (!nfs_server_capable(inode, NFS_CAP_CLONE)) + return -EOPNOTSUPP; + + do { + err = _nfs42_proc_clone(&msg, src_f, dst_f, src_offset, + dst_offset, count); + if (err == -ENOTSUPP || err == -EOPNOTSUPP) { + NFS_SERVER(inode)->caps &= ~NFS_CAP_CLONE; + return -EOPNOTSUPP; + } + err = nfs4_handle_exception(server, err, &exception); + } while (exception.retry); + + return err; + +} diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c index 0eb29e1..0ca482a 100644 --- a/fs/nfs/nfs42xdr.c +++ b/fs/nfs/nfs42xdr.c @@ -34,6 +34,12 @@ 1 /* opaque devaddr4 length */ + \ XDR_QUADLEN(PNFS_LAYOUTSTATS_MAXSIZE)) #define decode_layoutstats_maxsz (op_decode_hdr_maxsz) +#define encode_clone_maxsz (encode_stateid_maxsz + \ + encode_stateid_maxsz + \ + 2 /* src offset */ + \ + 2 /* dst offset */ + \ + 2 /* count */) +#define decode_clone_maxsz (op_decode_hdr_maxsz) #define NFS4_enc_allocate_sz (compound_encode_hdr_maxsz + \ encode_putfh_maxsz + \ @@ -65,7 +71,20 @@ decode_sequence_maxsz + \ decode_putfh_maxsz + \ PNFS_LAYOUTSTATS_MAXDEV * decode_layoutstats_maxsz) - +#define NFS4_enc_clone_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putfh_maxsz + \ + encode_savefh_maxsz + \ + encode_putfh_maxsz + \ + encode_clone_maxsz + \ + encode_getattr_maxsz) +#define NFS4_dec_clone_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_savefh_maxsz + \ + decode_putfh_maxsz + \ + decode_clone_maxsz + \ + decode_getattr_maxsz) static void encode_fallocate(struct xdr_stream *xdr, struct nfs42_falloc_args *args) @@ -128,6 +147,21 @@ static void encode_layoutstats(struct xdr_stream *xdr, encode_uint32(xdr, 0); } +static void encode_clone(struct xdr_stream *xdr, + struct nfs42_clone_args *args, + struct compound_hdr *hdr) +{ + __be32 *p; + + encode_op_hdr(xdr, OP_CLONE, decode_clone_maxsz, hdr); + encode_nfs4_stateid(xdr, &args->src_stateid); + encode_nfs4_stateid(xdr, &args->dst_stateid); + p = reserve_space(xdr, 3*8); + p = xdr_encode_hyper(p, args->src_offset); + p = xdr_encode_hyper(p, args->dst_offset); + xdr_encode_hyper(p, args->count); +} + /* * Encode ALLOCATE request */ @@ -206,6 +240,27 @@ static void nfs4_xdr_enc_layoutstats(struct rpc_rqst *req, encode_nops(&hdr); } +/* + * Encode CLONE request + */ +static void nfs4_xdr_enc_clone(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs42_clone_args *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->src_fh, &hdr); + encode_savefh(xdr, &hdr); + encode_putfh(xdr, args->dst_fh, &hdr); + encode_clone(xdr, args, &hdr); + encode_getfattr(xdr, args->dst_bitmask, &hdr); + encode_nops(&hdr); +} + static int decode_allocate(struct xdr_stream *xdr, struct nfs42_falloc_res *res) { return decode_op_hdr(xdr, OP_ALLOCATE); @@ -243,6 +298,11 @@ static int decode_layoutstats(struct xdr_stream *xdr) return decode_op_hdr(xdr, OP_LAYOUTSTATS); } +static int decode_clone(struct xdr_stream *xdr) +{ + return decode_op_hdr(xdr, OP_CLONE); +} + /* * Decode ALLOCATE request */ @@ -351,4 +411,39 @@ out: return status; } +/* + * Decode CLONE request + */ +static int nfs4_xdr_dec_clone(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + struct nfs42_clone_res *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_savefh(xdr); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_clone(xdr); + if (status) + goto out; + status = decode_getfattr(xdr, res->dst_fattr, res->server); + +out: + res->rpc_status = status; + return status; +} + #endif /* __LINUX_FS_NFS_NFS4_2XDR_H */ diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 50cfc4c..4afdee4 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -183,10 +183,12 @@ struct nfs4_state { struct nfs4_exception { - long timeout; - int retry; struct nfs4_state *state; struct inode *inode; + long timeout; + unsigned char delay : 1, + recovering : 1, + retry : 1; }; struct nfs4_state_recovery_ops { diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index b0dbe0a..4aa5719 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -4,6 +4,7 @@ * Copyright (C) 1992 Rick Sladkey */ #include <linux/fs.h> +#include <linux/file.h> #include <linux/falloc.h> #include <linux/nfs_fs.h> #include "delegation.h" @@ -192,8 +193,138 @@ static long nfs42_fallocate(struct file *filep, int mode, loff_t offset, loff_t return nfs42_proc_deallocate(filep, offset, len); return nfs42_proc_allocate(filep, offset, len); } + +static noinline long +nfs42_ioctl_clone(struct file *dst_file, unsigned long srcfd, + u64 src_off, u64 dst_off, u64 count) +{ + struct inode *dst_inode = file_inode(dst_file); + struct nfs_server *server = NFS_SERVER(dst_inode); + struct fd src_file; + struct inode *src_inode; + unsigned int bs = server->clone_blksize; + int ret; + + /* dst file must be opened for writing */ + if (!(dst_file->f_mode & FMODE_WRITE)) + return -EINVAL; + + ret = mnt_want_write_file(dst_file); + if (ret) + return ret; + + src_file = fdget(srcfd); + if (!src_file.file) { + ret = -EBADF; + goto out_drop_write; + } + + src_inode = file_inode(src_file.file); + + /* src and dst must be different files */ + ret = -EINVAL; + if (src_inode == dst_inode) + goto out_fput; + + /* src file must be opened for reading */ + if (!(src_file.file->f_mode & FMODE_READ)) + goto out_fput; + + /* src and dst must be regular files */ + ret = -EISDIR; + if (!S_ISREG(src_inode->i_mode) || !S_ISREG(dst_inode->i_mode)) + goto out_fput; + + ret = -EXDEV; + if (src_file.file->f_path.mnt != dst_file->f_path.mnt || + src_inode->i_sb != dst_inode->i_sb) + goto out_fput; + + /* check alignment w.r.t. clone_blksize */ + ret = -EINVAL; + if (bs) { + if (!IS_ALIGNED(src_off, bs) || !IS_ALIGNED(dst_off, bs)) + goto out_fput; + if (!IS_ALIGNED(count, bs) && i_size_read(src_inode) != (src_off + count)) + goto out_fput; + } + + /* XXX: do we lock at all? what if server needs CB_RECALL_LAYOUT? */ + if (dst_inode < src_inode) { + mutex_lock_nested(&dst_inode->i_mutex, I_MUTEX_PARENT); + mutex_lock_nested(&src_inode->i_mutex, I_MUTEX_CHILD); + } else { + mutex_lock_nested(&src_inode->i_mutex, I_MUTEX_PARENT); + mutex_lock_nested(&dst_inode->i_mutex, I_MUTEX_CHILD); + } + + /* flush all pending writes on both src and dst so that server + * has the latest data */ + ret = nfs_sync_inode(src_inode); + if (ret) + goto out_unlock; + ret = nfs_sync_inode(dst_inode); + if (ret) + goto out_unlock; + + ret = nfs42_proc_clone(src_file.file, dst_file, src_off, dst_off, count); + + /* truncate inode page cache of the dst range so that future reads can fetch + * new data from server */ + if (!ret) + truncate_inode_pages_range(&dst_inode->i_data, dst_off, dst_off + count - 1); + +out_unlock: + if (dst_inode < src_inode) { + mutex_unlock(&src_inode->i_mutex); + mutex_unlock(&dst_inode->i_mutex); + } else { + mutex_unlock(&dst_inode->i_mutex); + mutex_unlock(&src_inode->i_mutex); + } +out_fput: + fdput(src_file); +out_drop_write: + mnt_drop_write_file(dst_file); + return ret; +} + +static long nfs42_ioctl_clone_range(struct file *dst_file, void __user *argp) +{ + struct nfs_ioctl_clone_range_args args; + + if (copy_from_user(&args, argp, sizeof(args))) + return -EFAULT; + + return nfs42_ioctl_clone(dst_file, args.src_fd, args.src_off, args.dst_off, args.count); +} +#else +static long nfs42_ioctl_clone(struct file *dst_file, unsigned long srcfd, + u64 src_off, u64 dst_off, u64 count) +{ + return -ENOTTY; +} + +static long nfs42_ioctl_clone_range(struct file *dst_file, void __user *argp) +{ + return -ENOTTY; +} #endif /* CONFIG_NFS_V4_2 */ +long nfs4_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + void __user *argp = (void __user *)arg; + + switch (cmd) { + case NFS_IOC_CLONE: + return nfs42_ioctl_clone(file, arg, 0, 0, 0); + case NFS_IOC_CLONE_RANGE: + return nfs42_ioctl_clone_range(file, argp); + } + + return -ENOTTY; +} + const struct file_operations nfs4_file_operations = { #ifdef CONFIG_NFS_V4_2 .llseek = nfs4_file_llseek, @@ -216,4 +347,9 @@ const struct file_operations nfs4_file_operations = { #endif /* CONFIG_NFS_V4_2 */ .check_flags = nfs_check_flags, .setlease = simple_nosetlease, +#ifdef CONFIG_COMPAT + .unlocked_ioctl = nfs4_ioctl, +#else + .compat_ioctl = nfs4_ioctl, +#endif /* CONFIG_COMPAT */ }; diff --git a/fs/nfs/nfs4idmap.c b/fs/nfs/nfs4idmap.c index 2e49022..5ba22c6 100644 --- a/fs/nfs/nfs4idmap.c +++ b/fs/nfs/nfs4idmap.c @@ -297,7 +297,7 @@ static ssize_t nfs_idmap_get_key(const char *name, size_t namelen, { const struct cred *saved_cred; struct key *rkey; - struct user_key_payload *payload; + const struct user_key_payload *payload; ssize_t ret; saved_cred = override_creds(id_resolver_cache); @@ -316,7 +316,7 @@ static ssize_t nfs_idmap_get_key(const char *name, size_t namelen, if (ret < 0) goto out_up; - payload = rcu_dereference(rkey->payload.rcudata); + payload = user_key_payload(rkey); if (IS_ERR_OR_NULL(payload)) { ret = PTR_ERR(payload); goto out_up; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 693b903..ff5bddc 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -78,7 +78,6 @@ struct nfs4_opendata; static int _nfs4_proc_open(struct nfs4_opendata *data); static int _nfs4_recover_proc_open(struct nfs4_opendata *data); static int nfs4_do_fsinfo(struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *); -static int nfs4_async_handle_error(struct rpc_task *, const struct nfs_server *, struct nfs4_state *, long *); static void nfs_fixup_referral_attributes(struct nfs_fattr *fattr); static int nfs4_proc_getattr(struct nfs_server *, struct nfs_fh *, struct nfs_fattr *, struct nfs4_label *label); static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fattr *fattr, struct nfs4_label *label); @@ -239,6 +238,7 @@ const u32 nfs4_fsinfo_bitmap[3] = { FATTR4_WORD0_MAXFILESIZE FATTR4_WORD1_TIME_DELTA | FATTR4_WORD1_FS_LAYOUT_TYPES, FATTR4_WORD2_LAYOUT_BLKSIZE + | FATTR4_WORD2_CLONE_BLKSIZE }; const u32 nfs4_fs_locations_bitmap[3] = { @@ -344,13 +344,16 @@ static int nfs4_delay(struct rpc_clnt *clnt, long *timeout) /* This is the error handling routine for processes that are allowed * to sleep. */ -int nfs4_handle_exception(struct nfs_server *server, int errorcode, struct nfs4_exception *exception) +static int nfs4_do_handle_exception(struct nfs_server *server, + int errorcode, struct nfs4_exception *exception) { struct nfs_client *clp = server->nfs_client; struct nfs4_state *state = exception->state; struct inode *inode = exception->inode; int ret = errorcode; + exception->delay = 0; + exception->recovering = 0; exception->retry = 0; switch(errorcode) { case 0: @@ -359,11 +362,9 @@ int nfs4_handle_exception(struct nfs_server *server, int errorcode, struct nfs4_ case -NFS4ERR_DELEG_REVOKED: case -NFS4ERR_ADMIN_REVOKED: case -NFS4ERR_BAD_STATEID: - if (inode && nfs4_have_delegation(inode, FMODE_READ)) { - nfs4_inode_return_delegation(inode); - exception->retry = 1; - return 0; - } + if (inode && nfs_async_inode_return_delegation(inode, + NULL) == 0) + goto wait_on_recovery; if (state == NULL) break; ret = nfs4_schedule_stateid_recovery(server, state); @@ -409,11 +410,12 @@ int nfs4_handle_exception(struct nfs_server *server, int errorcode, struct nfs4_ ret = -EBUSY; break; } - case -NFS4ERR_GRACE: case -NFS4ERR_DELAY: - ret = nfs4_delay(server->client, &exception->timeout); - if (ret != 0) - break; + nfs_inc_server_stats(server, NFSIOS_DELAY); + case -NFS4ERR_GRACE: + exception->delay = 1; + return 0; + case -NFS4ERR_RETRY_UNCACHED_REP: case -NFS4ERR_OLD_STATEID: exception->retry = 1; @@ -434,14 +436,85 @@ int nfs4_handle_exception(struct nfs_server *server, int errorcode, struct nfs4_ /* We failed to handle the error */ return nfs4_map_errors(ret); wait_on_recovery: - ret = nfs4_wait_clnt_recover(clp); + exception->recovering = 1; + return 0; +} + +/* This is the error handling routine for processes that are allowed + * to sleep. + */ +int nfs4_handle_exception(struct nfs_server *server, int errorcode, struct nfs4_exception *exception) +{ + struct nfs_client *clp = server->nfs_client; + int ret; + + ret = nfs4_do_handle_exception(server, errorcode, exception); + if (exception->delay) { + ret = nfs4_delay(server->client, &exception->timeout); + goto out_retry; + } + if (exception->recovering) { + ret = nfs4_wait_clnt_recover(clp); + if (test_bit(NFS_MIG_FAILED, &server->mig_status)) + return -EIO; + goto out_retry; + } + return ret; +out_retry: + if (ret == 0) + exception->retry = 1; + return ret; +} + +static int +nfs4_async_handle_exception(struct rpc_task *task, struct nfs_server *server, + int errorcode, struct nfs4_exception *exception) +{ + struct nfs_client *clp = server->nfs_client; + int ret; + + ret = nfs4_do_handle_exception(server, errorcode, exception); + if (exception->delay) { + rpc_delay(task, nfs4_update_delay(&exception->timeout)); + goto out_retry; + } + if (exception->recovering) { + rpc_sleep_on(&clp->cl_rpcwaitq, task, NULL); + if (test_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) == 0) + rpc_wake_up_queued_task(&clp->cl_rpcwaitq, task); + goto out_retry; + } if (test_bit(NFS_MIG_FAILED, &server->mig_status)) - return -EIO; + ret = -EIO; + return ret; +out_retry: if (ret == 0) exception->retry = 1; return ret; } +static int +nfs4_async_handle_error(struct rpc_task *task, struct nfs_server *server, + struct nfs4_state *state, long *timeout) +{ + struct nfs4_exception exception = { + .state = state, + }; + + if (task->tk_status >= 0) + return 0; + if (timeout) + exception.timeout = *timeout; + task->tk_status = nfs4_async_handle_exception(task, server, + task->tk_status, + &exception); + if (exception.delay && timeout) + *timeout = exception.timeout; + if (exception.retry) + return -EAGAIN; + return 0; +} + /* * Return 'true' if 'clp' is using an rpc_client that is integrity protected * or 'false' otherwise. @@ -1127,6 +1200,21 @@ static int nfs4_wait_for_completion_rpc_task(struct rpc_task *task) return ret; } +static bool nfs4_mode_match_open_stateid(struct nfs4_state *state, + fmode_t fmode) +{ + switch(fmode & (FMODE_READ|FMODE_WRITE)) { + case FMODE_READ|FMODE_WRITE: + return state->n_rdwr != 0; + case FMODE_WRITE: + return state->n_wronly != 0; + case FMODE_READ: + return state->n_rdonly != 0; + } + WARN_ON_ONCE(1); + return false; +} + static int can_open_cached(struct nfs4_state *state, fmode_t mode, int open_mode) { int ret = 0; @@ -1443,12 +1531,18 @@ nfs4_opendata_check_deleg(struct nfs4_opendata *data, struct nfs4_state *state) if (delegation) delegation_flags = delegation->flags; rcu_read_unlock(); - if (data->o_arg.claim == NFS4_OPEN_CLAIM_DELEGATE_CUR) { + switch (data->o_arg.claim) { + default: + break; + case NFS4_OPEN_CLAIM_DELEGATE_CUR: + case NFS4_OPEN_CLAIM_DELEG_CUR_FH: pr_err_ratelimited("NFS: Broken NFSv4 server %s is " "returning a delegation for " "OPEN(CLAIM_DELEGATE_CUR)\n", clp->cl_hostname); - } else if ((delegation_flags & 1UL<<NFS_DELEGATION_NEED_RECLAIM) == 0) + return; + } + if ((delegation_flags & 1UL<<NFS_DELEGATION_NEED_RECLAIM) == 0) nfs_inode_set_delegation(state->inode, data->owner->so_cred, &data->o_res); @@ -1571,17 +1665,13 @@ static struct nfs4_opendata *nfs4_open_recoverdata_alloc(struct nfs_open_context return opendata; } -static int nfs4_open_recover_helper(struct nfs4_opendata *opendata, fmode_t fmode, struct nfs4_state **res) +static int nfs4_open_recover_helper(struct nfs4_opendata *opendata, + fmode_t fmode) { struct nfs4_state *newstate; int ret; - if ((opendata->o_arg.claim == NFS4_OPEN_CLAIM_DELEGATE_CUR || - opendata->o_arg.claim == NFS4_OPEN_CLAIM_DELEG_CUR_FH) && - (opendata->o_arg.u.delegation_type & fmode) != fmode) - /* This mode can't have been delegated, so we must have - * a valid open_stateid to cover it - not need to reclaim. - */ + if (!nfs4_mode_match_open_stateid(opendata->state, fmode)) return 0; opendata->o_arg.open_flags = 0; opendata->o_arg.fmode = fmode; @@ -1597,14 +1687,14 @@ static int nfs4_open_recover_helper(struct nfs4_opendata *opendata, fmode_t fmod newstate = nfs4_opendata_to_nfs4_state(opendata); if (IS_ERR(newstate)) return PTR_ERR(newstate); + if (newstate != opendata->state) + ret = -ESTALE; nfs4_close_state(newstate, fmode); - *res = newstate; - return 0; + return ret; } static int nfs4_open_recover(struct nfs4_opendata *opendata, struct nfs4_state *state) { - struct nfs4_state *newstate; int ret; /* Don't trigger recovery in nfs_test_and_clear_all_open_stateid */ @@ -1615,27 +1705,15 @@ static int nfs4_open_recover(struct nfs4_opendata *opendata, struct nfs4_state * clear_bit(NFS_DELEGATED_STATE, &state->flags); clear_bit(NFS_OPEN_STATE, &state->flags); smp_rmb(); - if (state->n_rdwr != 0) { - ret = nfs4_open_recover_helper(opendata, FMODE_READ|FMODE_WRITE, &newstate); - if (ret != 0) - return ret; - if (newstate != state) - return -ESTALE; - } - if (state->n_wronly != 0) { - ret = nfs4_open_recover_helper(opendata, FMODE_WRITE, &newstate); - if (ret != 0) - return ret; - if (newstate != state) - return -ESTALE; - } - if (state->n_rdonly != 0) { - ret = nfs4_open_recover_helper(opendata, FMODE_READ, &newstate); - if (ret != 0) - return ret; - if (newstate != state) - return -ESTALE; - } + ret = nfs4_open_recover_helper(opendata, FMODE_READ|FMODE_WRITE); + if (ret != 0) + return ret; + ret = nfs4_open_recover_helper(opendata, FMODE_WRITE); + if (ret != 0) + return ret; + ret = nfs4_open_recover_helper(opendata, FMODE_READ); + if (ret != 0) + return ret; /* * We may have performed cached opens for all three recoveries. * Check if we need to update the current stateid. @@ -1759,18 +1837,35 @@ static int nfs4_handle_delegation_recall_error(struct nfs_server *server, struct return err; } -int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state *state, const nfs4_stateid *stateid) +int nfs4_open_delegation_recall(struct nfs_open_context *ctx, + struct nfs4_state *state, const nfs4_stateid *stateid, + fmode_t type) { struct nfs_server *server = NFS_SERVER(state->inode); struct nfs4_opendata *opendata; - int err; + int err = 0; opendata = nfs4_open_recoverdata_alloc(ctx, state, NFS4_OPEN_CLAIM_DELEG_CUR_FH); if (IS_ERR(opendata)) return PTR_ERR(opendata); nfs4_stateid_copy(&opendata->o_arg.u.delegation, stateid); - err = nfs4_open_recover(opendata, state); + write_seqlock(&state->seqlock); + nfs4_stateid_copy(&state->stateid, &state->open_stateid); + write_sequnlock(&state->seqlock); + clear_bit(NFS_DELEGATED_STATE, &state->flags); + switch (type & (FMODE_READ|FMODE_WRITE)) { + case FMODE_READ|FMODE_WRITE: + case FMODE_WRITE: + err = nfs4_open_recover_helper(opendata, FMODE_READ|FMODE_WRITE); + if (err) + break; + err = nfs4_open_recover_helper(opendata, FMODE_WRITE); + if (err) + break; + case FMODE_READ: + err = nfs4_open_recover_helper(opendata, FMODE_READ); + } nfs4_opendata_put(opendata); return nfs4_handle_delegation_recall_error(server, state, stateid, err); } @@ -1850,6 +1945,8 @@ static int _nfs4_proc_open_confirm(struct nfs4_opendata *data) data->rpc_done = 0; data->rpc_status = 0; data->timestamp = jiffies; + if (data->is_recover) + nfs4_set_sequence_privileged(&data->c_arg.seq_args); task = rpc_run_task(&task_setup_data); if (IS_ERR(task)) return PTR_ERR(task); @@ -2645,6 +2742,15 @@ out: return err; } +static bool +nfs4_wait_on_layoutreturn(struct inode *inode, struct rpc_task *task) +{ + if (inode == NULL || !nfs_have_layout(inode)) + return false; + + return pnfs_wait_on_layoutreturn(inode, task); +} + struct nfs4_closedata { struct inode *inode; struct nfs4_state *state; @@ -2763,6 +2869,11 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data) goto out_no_action; } + if (nfs4_wait_on_layoutreturn(inode, task)) { + nfs_release_seqid(calldata->arg.seqid); + goto out_wait; + } + if (calldata->arg.fmode == 0) task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_CLOSE]; if (calldata->roc) @@ -4492,7 +4603,7 @@ static inline int nfs4_server_supports_acls(struct nfs_server *server) #define NFS4ACL_MAXPAGES DIV_ROUND_UP(XATTR_SIZE_MAX, PAGE_SIZE) static int buf_to_pages_noslab(const void *buf, size_t buflen, - struct page **pages, unsigned int *pgbase) + struct page **pages) { struct page *newpage, **spages; int rc = 0; @@ -4636,7 +4747,6 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu goto out_free; args.acl_len = npages * PAGE_SIZE; - args.acl_pgbase = 0; dprintk("%s buf %p buflen %zu npages %d args.acl_len %zu\n", __func__, buf, buflen, npages, args.acl_len); @@ -4728,7 +4838,7 @@ static int __nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t bufl return -EOPNOTSUPP; if (npages > ARRAY_SIZE(pages)) return -ERANGE; - i = buf_to_pages_noslab(buf, buflen, arg.acl_pages, &arg.acl_pgbase); + i = buf_to_pages_noslab(buf, buflen, arg.acl_pages); if (i < 0) return i; nfs4_inode_return_delegation(inode); @@ -4917,79 +5027,6 @@ out: #endif /* CONFIG_NFS_V4_SECURITY_LABEL */ -static int -nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server, - struct nfs4_state *state, long *timeout) -{ - struct nfs_client *clp = server->nfs_client; - - if (task->tk_status >= 0) - return 0; - switch(task->tk_status) { - case -NFS4ERR_DELEG_REVOKED: - case -NFS4ERR_ADMIN_REVOKED: - case -NFS4ERR_BAD_STATEID: - case -NFS4ERR_OPENMODE: - if (state == NULL) - break; - if (nfs4_schedule_stateid_recovery(server, state) < 0) - goto recovery_failed; - goto wait_on_recovery; - case -NFS4ERR_EXPIRED: - if (state != NULL) { - if (nfs4_schedule_stateid_recovery(server, state) < 0) - goto recovery_failed; - } - case -NFS4ERR_STALE_STATEID: - case -NFS4ERR_STALE_CLIENTID: - nfs4_schedule_lease_recovery(clp); - goto wait_on_recovery; - case -NFS4ERR_MOVED: - if (nfs4_schedule_migration_recovery(server) < 0) - goto recovery_failed; - goto wait_on_recovery; - case -NFS4ERR_LEASE_MOVED: - nfs4_schedule_lease_moved_recovery(clp); - goto wait_on_recovery; -#if defined(CONFIG_NFS_V4_1) - case -NFS4ERR_BADSESSION: - case -NFS4ERR_BADSLOT: - case -NFS4ERR_BAD_HIGH_SLOT: - case -NFS4ERR_DEADSESSION: - case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION: - case -NFS4ERR_SEQ_FALSE_RETRY: - case -NFS4ERR_SEQ_MISORDERED: - dprintk("%s ERROR %d, Reset session\n", __func__, - task->tk_status); - nfs4_schedule_session_recovery(clp->cl_session, task->tk_status); - goto wait_on_recovery; -#endif /* CONFIG_NFS_V4_1 */ - case -NFS4ERR_DELAY: - nfs_inc_server_stats(server, NFSIOS_DELAY); - rpc_delay(task, nfs4_update_delay(timeout)); - goto restart_call; - case -NFS4ERR_GRACE: - rpc_delay(task, NFS4_POLL_RETRY_MAX); - case -NFS4ERR_RETRY_UNCACHED_REP: - case -NFS4ERR_OLD_STATEID: - goto restart_call; - } - task->tk_status = nfs4_map_errors(task->tk_status); - return 0; -recovery_failed: - task->tk_status = -EIO; - return 0; -wait_on_recovery: - rpc_sleep_on(&clp->cl_rpcwaitq, task, NULL); - if (test_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) == 0) - rpc_wake_up_queued_task(&clp->cl_rpcwaitq, task); - if (test_bit(NFS_MIG_FAILED, &server->mig_status)) - goto recovery_failed; -restart_call: - task->tk_status = 0; - return -EAGAIN; -} - static void nfs4_init_boot_verifier(const struct nfs_client *clp, nfs4_verifier *bootverf) { @@ -5308,6 +5345,9 @@ static void nfs4_delegreturn_prepare(struct rpc_task *task, void *data) d_data = (struct nfs4_delegreturndata *)data; + if (nfs4_wait_on_layoutreturn(d_data->inode, task)) + return; + if (d_data->roc) pnfs_roc_get_barrier(d_data->inode, &d_data->roc_barrier); @@ -5472,18 +5512,7 @@ static int nfs4_proc_getlk(struct nfs4_state *state, int cmd, struct file_lock * static int do_vfs_lock(struct inode *inode, struct file_lock *fl) { - int res = 0; - switch (fl->fl_flags & (FL_POSIX|FL_FLOCK)) { - case FL_POSIX: - res = posix_lock_inode_wait(inode, fl); - break; - case FL_FLOCK: - res = flock_lock_inode_wait(inode, fl); - break; - default: - BUG(); - } - return res; + return locks_lock_inode_wait(inode, fl); } struct nfs4_unlockdata { @@ -5492,7 +5521,7 @@ struct nfs4_unlockdata { struct nfs4_lock_state *lsp; struct nfs_open_context *ctx; struct file_lock fl; - const struct nfs_server *server; + struct nfs_server *server; unsigned long timestamp; }; @@ -7800,39 +7829,46 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata) dprintk("%s: NFS4ERR_RECALLCONFLICT waiting %lu\n", __func__, delay); rpc_delay(task, delay); - task->tk_status = 0; - rpc_restart_call_prepare(task); - goto out; /* Do not call nfs4_async_handle_error() */ + /* Do not call nfs4_async_handle_error() */ + goto out_restart; } break; case -NFS4ERR_EXPIRED: case -NFS4ERR_BAD_STATEID: spin_lock(&inode->i_lock); - lo = NFS_I(inode)->layout; - if (!lo || list_empty(&lo->plh_segs)) { + if (nfs4_stateid_match(&lgp->args.stateid, + &lgp->args.ctx->state->stateid)) { spin_unlock(&inode->i_lock); /* If the open stateid was bad, then recover it. */ state = lgp->args.ctx->state; - } else { + break; + } + lo = NFS_I(inode)->layout; + if (lo && nfs4_stateid_match(&lgp->args.stateid, + &lo->plh_stateid)) { LIST_HEAD(head); /* * Mark the bad layout state as invalid, then retry * with the current stateid. */ + set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags); pnfs_mark_matching_lsegs_invalid(lo, &head, NULL); spin_unlock(&inode->i_lock); pnfs_free_lseg_list(&head); - - task->tk_status = 0; - rpc_restart_call_prepare(task); - } + } else + spin_unlock(&inode->i_lock); + goto out_restart; } if (nfs4_async_handle_error(task, server, state, NULL) == -EAGAIN) - rpc_restart_call_prepare(task); + goto out_restart; out: dprintk("<-- %s\n", __func__); return; +out_restart: + task->tk_status = 0; + rpc_restart_call_prepare(task); + return; out_overflow: task->tk_status = -EOVERFLOW; goto out; @@ -8681,7 +8717,8 @@ static const struct nfs4_minor_version_ops nfs_v4_2_minor_ops = { | NFS_CAP_ALLOCATE | NFS_CAP_DEALLOCATE | NFS_CAP_SEEK - | NFS_CAP_LAYOUTSTATS, + | NFS_CAP_LAYOUTSTATS + | NFS_CAP_CLONE, .init_client = nfs41_init_client, .shutdown_client = nfs41_shutdown_client, .match_stateid = nfs41_match_stateid, diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index da73bc4..d854693 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1481,7 +1481,7 @@ restart: spin_unlock(&state->state_lock); } nfs4_put_open_state(state); - clear_bit(NFS4CLNT_RECLAIM_NOGRACE, + clear_bit(NFS_STATE_RECLAIM_NOGRACE, &state->flags); spin_lock(&sp->so_lock); goto restart; @@ -1725,7 +1725,8 @@ restart: if (!test_and_clear_bit(ops->owner_flag_bit, &sp->so_flags)) continue; - atomic_inc(&sp->so_count); + if (!atomic_inc_not_zero(&sp->so_count)) + continue; spin_unlock(&clp->cl_lock); rcu_read_unlock(); diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h index 28df12e..671cf68 100644 --- a/fs/nfs/nfs4trace.h +++ b/fs/nfs/nfs4trace.h @@ -409,7 +409,7 @@ DECLARE_EVENT_CLASS(nfs4_open_event, __entry->flags = flags; __entry->fmode = (__force unsigned int)ctx->mode; __entry->dev = ctx->dentry->d_sb->s_dev; - if (!IS_ERR(state)) + if (!IS_ERR_OR_NULL(state)) inode = state->inode; if (inode != NULL) { __entry->fileid = NFS_FILEID(inode); diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 788adf3..dfed4f5 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -1659,7 +1659,7 @@ encode_setacl(struct xdr_stream *xdr, struct nfs_setaclargs *arg, struct compoun *p = cpu_to_be32(FATTR4_WORD0_ACL); p = reserve_space(xdr, 4); *p = cpu_to_be32(arg->acl_len); - xdr_write_pages(xdr, arg->acl_pages, arg->acl_pgbase, arg->acl_len); + xdr_write_pages(xdr, arg->acl_pages, 0, arg->acl_len); } static void @@ -2491,7 +2491,7 @@ static void nfs4_xdr_enc_getacl(struct rpc_rqst *req, struct xdr_stream *xdr, encode_getattr_two(xdr, FATTR4_WORD0_ACL, 0, &hdr); xdr_inline_pages(&req->rq_rcv_buf, replen << 2, - args->acl_pages, args->acl_pgbase, args->acl_len); + args->acl_pages, 0, args->acl_len); encode_nops(&hdr); } @@ -4375,6 +4375,11 @@ static int decode_statfs(struct xdr_stream *xdr, struct nfs_fsstat *fsstat) goto xdr_error; if ((status = decode_attr_files_total(xdr, bitmap, &fsstat->tfiles)) != 0) goto xdr_error; + + status = -EIO; + if (unlikely(bitmap[0])) + goto xdr_error; + if ((status = decode_attr_space_avail(xdr, bitmap, &fsstat->abytes)) != 0) goto xdr_error; if ((status = decode_attr_space_free(xdr, bitmap, &fsstat->fbytes)) != 0) @@ -4574,6 +4579,10 @@ static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap, goto xdr_error; fattr->valid |= status; + status = -EIO; + if (unlikely(bitmap[0])) + goto xdr_error; + status = decode_attr_mode(xdr, bitmap, &fmode); if (status < 0) goto xdr_error; @@ -4627,6 +4636,10 @@ static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap, goto xdr_error; fattr->valid |= status; + status = -EIO; + if (unlikely(bitmap[1])) + goto xdr_error; + status = decode_attr_mdsthreshold(xdr, bitmap, fattr->mdsthreshold); if (status < 0) goto xdr_error; @@ -4764,6 +4777,28 @@ static int decode_attr_layout_blksize(struct xdr_stream *xdr, uint32_t *bitmap, return 0; } +/* + * The granularity of a CLONE operation. + */ +static int decode_attr_clone_blksize(struct xdr_stream *xdr, uint32_t *bitmap, + uint32_t *res) +{ + __be32 *p; + + dprintk("%s: bitmap is %x\n", __func__, bitmap[2]); + *res = 0; + if (bitmap[2] & FATTR4_WORD2_CLONE_BLKSIZE) { + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) { + print_overflow_msg(__func__, xdr); + return -EIO; + } + *res = be32_to_cpup(p); + bitmap[2] &= ~FATTR4_WORD2_CLONE_BLKSIZE; + } + return 0; +} + static int decode_fsinfo(struct xdr_stream *xdr, struct nfs_fsinfo *fsinfo) { unsigned int savep; @@ -4789,15 +4824,28 @@ static int decode_fsinfo(struct xdr_stream *xdr, struct nfs_fsinfo *fsinfo) if ((status = decode_attr_maxwrite(xdr, bitmap, &fsinfo->wtmax)) != 0) goto xdr_error; fsinfo->wtpref = fsinfo->wtmax; + + status = -EIO; + if (unlikely(bitmap[0])) + goto xdr_error; + status = decode_attr_time_delta(xdr, bitmap, &fsinfo->time_delta); if (status != 0) goto xdr_error; status = decode_attr_pnfstype(xdr, bitmap, &fsinfo->layouttype); if (status != 0) goto xdr_error; + + status = -EIO; + if (unlikely(bitmap[1])) + goto xdr_error; + status = decode_attr_layout_blksize(xdr, bitmap, &fsinfo->blksize); if (status) goto xdr_error; + status = decode_attr_clone_blksize(xdr, bitmap, &fsinfo->clone_blksize); + if (status) + goto xdr_error; status = verify_attr_len(xdr, savep, attrlen); xdr_error: @@ -7465,6 +7513,7 @@ struct rpc_procinfo nfs4_procedures[] = { PROC(ALLOCATE, enc_allocate, dec_allocate), PROC(DEALLOCATE, enc_deallocate, dec_deallocate), PROC(LAYOUTSTATS, enc_layoutstats, dec_layoutstats), + PROC(CLONE, enc_clone, dec_clone), #endif /* CONFIG_NFS_V4_2 */ }; diff --git a/fs/nfs/nfsroot.c b/fs/nfs/nfsroot.c index 9bc9f04..89a15db 100644 --- a/fs/nfs/nfsroot.c +++ b/fs/nfs/nfsroot.c @@ -90,7 +90,7 @@ #define NFS_DEF_OPTIONS "vers=2,udp,rsize=4096,wsize=4096" /* Parameters passed from the kernel command line */ -static char nfs_root_parms[256] __initdata = ""; +static char nfs_root_parms[NFS_MAXPATHLEN + 1] __initdata = ""; /* Text-based mount options passed to super.c */ static char nfs_root_options[256] __initdata = NFS_DEF_OPTIONS; diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c index 5aaed36..5c0c6b5 100644 --- a/fs/nfs/objlayout/objio_osd.c +++ b/fs/nfs/objlayout/objio_osd.c @@ -124,7 +124,7 @@ objio_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev, retry_lookup: od = osduld_info_lookup(&odi); - if (unlikely(IS_ERR(od))) { + if (IS_ERR(od)) { err = PTR_ERR(od); dprintk("%s: osduld_info_lookup => %d\n", __func__, err); if (err == -ENODEV && retry_flag) { diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 7c5718b..fe3ddd2 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -508,7 +508,7 @@ size_t nfs_generic_pg_test(struct nfs_pageio_descriptor *desc, * for it without upsetting the slab allocator. */ if (((mirror->pg_count + req->wb_bytes) >> PAGE_SHIFT) * - sizeof(struct page) > PAGE_SIZE) + sizeof(struct page *) > PAGE_SIZE) return 0; return min(mirror->pg_bsize - mirror->pg_count, (size_t)req->wb_bytes); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index ba12464..93496c0 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1104,20 +1104,15 @@ bool pnfs_roc(struct inode *ino) mark_lseg_invalid(lseg, &tmp_list); found = true; } - /* pnfs_prepare_layoutreturn() grabs lo ref and it will be put - * in pnfs_roc_release(). We don't really send a layoutreturn but - * still want others to view us like we are sending one! - * - * If pnfs_prepare_layoutreturn() fails, it means someone else is doing - * LAYOUTRETURN, so we proceed like there are no layouts to return. - * - * ROC in three conditions: + /* ROC in two conditions: * 1. there are ROC lsegs * 2. we don't send layoutreturn - * 3. no others are sending layoutreturn */ - if (found && !layoutreturn && pnfs_prepare_layoutreturn(lo)) + if (found && !layoutreturn) { + /* lo ref dropped in pnfs_roc_release() */ + pnfs_get_layout_hdr(lo); roc = true; + } out_noroc: spin_unlock(&ino->i_lock); @@ -1172,6 +1167,26 @@ void pnfs_roc_get_barrier(struct inode *ino, u32 *barrier) spin_unlock(&ino->i_lock); } +bool pnfs_wait_on_layoutreturn(struct inode *ino, struct rpc_task *task) +{ + struct nfs_inode *nfsi = NFS_I(ino); + struct pnfs_layout_hdr *lo; + bool sleep = false; + + /* we might not have grabbed lo reference. so need to check under + * i_lock */ + spin_lock(&ino->i_lock); + lo = nfsi->layout; + if (lo && test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags)) + sleep = true; + spin_unlock(&ino->i_lock); + + if (sleep) + rpc_sleep_on(&NFS_SERVER(ino)->roc_rpcwaitq, task, NULL); + + return sleep; +} + /* * Compare two layout segments for sorting into layout cache. * We want to preferentially return RW over RO layouts, so ensure those @@ -1897,12 +1912,13 @@ static void pnfs_ld_handle_write_error(struct nfs_pgio_header *hdr) */ void pnfs_ld_write_done(struct nfs_pgio_header *hdr) { - trace_nfs4_pnfs_write(hdr, hdr->pnfs_error); - if (!hdr->pnfs_error) { + if (likely(!hdr->pnfs_error)) { pnfs_set_layoutcommit(hdr->inode, hdr->lseg, hdr->mds_offset + hdr->res.count); hdr->mds_ops->rpc_call_done(&hdr->task, hdr); - } else + } + trace_nfs4_pnfs_write(hdr, hdr->pnfs_error); + if (unlikely(hdr->pnfs_error)) pnfs_ld_handle_write_error(hdr); hdr->mds_ops->rpc_release(hdr); } @@ -2013,11 +2029,12 @@ static void pnfs_ld_handle_read_error(struct nfs_pgio_header *hdr) */ void pnfs_ld_read_done(struct nfs_pgio_header *hdr) { - trace_nfs4_pnfs_read(hdr, hdr->pnfs_error); if (likely(!hdr->pnfs_error)) { __nfs4_read_done_cb(hdr); hdr->mds_ops->rpc_call_done(&hdr->task, hdr); - } else + } + trace_nfs4_pnfs_read(hdr, hdr->pnfs_error); + if (unlikely(hdr->pnfs_error)) pnfs_ld_handle_read_error(hdr); hdr->mds_ops->rpc_release(hdr); } diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 78c9351..d1990e9 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -270,6 +270,7 @@ bool pnfs_roc(struct inode *ino); void pnfs_roc_release(struct inode *ino); void pnfs_roc_set_barrier(struct inode *ino, u32 barrier); void pnfs_roc_get_barrier(struct inode *ino, u32 *barrier); +bool pnfs_wait_on_layoutreturn(struct inode *ino, struct rpc_task *task); void pnfs_set_layoutcommit(struct inode *, struct pnfs_layout_segment *, loff_t); void pnfs_cleanup_layoutcommit(struct nfs4_layoutcommit_data *data); int pnfs_layoutcommit_inode(struct inode *inode, bool sync); @@ -639,6 +640,12 @@ pnfs_roc_get_barrier(struct inode *ino, u32 *barrier) { } +static inline bool +pnfs_wait_on_layoutreturn(struct inode *ino, struct rpc_task *task) +{ + return false; +} + static inline void set_pnfs_layoutdriver(struct nfs_server *s, const struct nfs_fh *mntfh, u32 id) { diff --git a/fs/nfs/read.c b/fs/nfs/read.c index ae0ff7a..0a5e33f 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -72,6 +72,9 @@ void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio) { struct nfs_pgio_mirror *mirror; + if (pgio->pg_ops && pgio->pg_ops->pg_cleanup) + pgio->pg_ops->pg_cleanup(pgio); + pgio->pg_ops = &nfs_pgio_rw_ops; /* read path should never have more than one mirror */ @@ -243,6 +246,13 @@ static void nfs_readpage_retry(struct rpc_task *task, nfs_set_pgio_error(hdr, -EIO, argp->offset); return; } + + /* For non rpc-based layout drivers, retry-through-MDS */ + if (!task->tk_ops) { + hdr->pnfs_error = -EAGAIN; + return; + } + /* Yes, so retry the read at the end of the hdr */ hdr->mds_offset += resp->count; argp->offset += resp->count; @@ -265,7 +275,7 @@ static void nfs_readpage_result(struct rpc_task *task, hdr->good_bytes = bound - hdr->io_start; } spin_unlock(&hdr->lock); - } else if (hdr->res.count != hdr->args.count) + } else if (hdr->res.count < hdr->args.count) nfs_readpage_retry(task, hdr); } diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 383a027..f126828 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -2816,7 +2816,6 @@ out_invalid_transport_udp: * NFS client for backwards compatibility */ unsigned int nfs_callback_set_tcpport; -unsigned short nfs_callback_tcpport; /* Default cache timeout is 10 minutes */ unsigned int nfs_idmap_cache_timeout = 600; /* Turn off NFSv4 uid/gid mapping when using AUTH_SYS */ @@ -2827,7 +2826,6 @@ char nfs4_client_id_uniquifier[NFS4_CLIENT_ID_UNIQ_LEN] = ""; bool recover_lost_locks = false; EXPORT_SYMBOL_GPL(nfs_callback_set_tcpport); -EXPORT_SYMBOL_GPL(nfs_callback_tcpport); EXPORT_SYMBOL_GPL(nfs_idmap_cache_timeout); EXPORT_SYMBOL_GPL(nfs4_disable_idmapping); EXPORT_SYMBOL_GPL(max_session_slots); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 388f480..7b93164 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -569,19 +569,17 @@ static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio, if (!nfs_pageio_add_request(pgio, req)) { nfs_redirty_request(req); ret = pgio->pg_error; - } + } else + nfs_add_stats(page_file_mapping(page)->host, + NFSIOS_WRITEPAGES, 1); out: return ret; } static int nfs_do_writepage(struct page *page, struct writeback_control *wbc, struct nfs_pageio_descriptor *pgio) { - struct inode *inode = page_file_mapping(page)->host; int ret; - nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGE); - nfs_add_stats(inode, NFSIOS_WRITEPAGES, 1); - nfs_pageio_cond_complete(pgio, page_file_index(page)); ret = nfs_page_async_flush(pgio, page, wbc->sync_mode == WB_SYNC_NONE); if (ret == -EAGAIN) { @@ -597,9 +595,11 @@ static int nfs_do_writepage(struct page *page, struct writeback_control *wbc, st static int nfs_writepage_locked(struct page *page, struct writeback_control *wbc) { struct nfs_pageio_descriptor pgio; + struct inode *inode = page_file_mapping(page)->host; int err; - nfs_pageio_init_write(&pgio, page->mapping->host, wb_priority(wbc), + nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGE); + nfs_pageio_init_write(&pgio, inode, wb_priority(wbc), false, &nfs_async_write_completion_ops); err = nfs_do_writepage(page, wbc, &pgio); nfs_pageio_complete(&pgio); @@ -1223,7 +1223,7 @@ static int nfs_can_extend_write(struct file *file, struct page *page, struct ino return 1; if (!flctx || (list_empty_careful(&flctx->flc_flock) && list_empty_careful(&flctx->flc_posix))) - return 0; + return 1; /* Check to see if there are whole file write locks */ ret = 0; @@ -1351,6 +1351,9 @@ void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio) { struct nfs_pgio_mirror *mirror; + if (pgio->pg_ops && pgio->pg_ops->pg_cleanup) + pgio->pg_ops->pg_cleanup(pgio); + pgio->pg_ops = &nfs_pgio_rw_ops; nfs_pageio_stop_mirroring(pgio); @@ -1502,6 +1505,13 @@ static void nfs_writeback_result(struct rpc_task *task, task->tk_status = -EIO; return; } + + /* For non rpc-based layout drivers, retry-through-MDS */ + if (!task->tk_ops) { + hdr->pnfs_error = -EAGAIN; + return; + } + /* Was this an NFSv2 write or an NFSv3 stable write? */ if (resp->verf->committed != NFS_UNSTABLE) { /* Resend from where the server left off */ diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c index cdefaa3..c29d942 100644 --- a/fs/nfsd/blocklayout.c +++ b/fs/nfsd/blocklayout.c @@ -56,14 +56,6 @@ nfsd4_block_proc_layoutget(struct inode *inode, const struct svc_fh *fhp, u32 device_generation = 0; int error; - /* - * We do not attempt to support I/O smaller than the fs block size, - * or not aligned to it. - */ - if (args->lg_minlength < block_size) { - dprintk("pnfsd: I/O too small\n"); - goto out_layoutunavailable; - } if (seg->offset & (block_size - 1)) { dprintk("pnfsd: I/O misaligned\n"); goto out_layoutunavailable; diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index f6e7cba..00575d7 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -262,11 +262,11 @@ void fill_post_wcc(struct svc_fh *fhp) err = fh_getattr(fhp, &fhp->fh_post_attr); fhp->fh_post_change = d_inode(fhp->fh_dentry)->i_version; if (err) { - fhp->fh_post_saved = 0; + fhp->fh_post_saved = false; /* Grab the ctime anyway - set_change_info might use it */ fhp->fh_post_attr.ctime = d_inode(fhp->fh_dentry)->i_ctime; } else - fhp->fh_post_saved = 1; + fhp->fh_post_saved = true; } /* diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c index ebf90e4..9ffef06 100644 --- a/fs/nfsd/nfs4layouts.c +++ b/fs/nfsd/nfs4layouts.c @@ -201,6 +201,7 @@ nfsd4_alloc_layout_stateid(struct nfsd4_compound_state *cstate, INIT_LIST_HEAD(&ls->ls_perfile); spin_lock_init(&ls->ls_lock); INIT_LIST_HEAD(&ls->ls_layouts); + mutex_init(&ls->ls_mutex); ls->ls_layout_type = layout_type; nfsd4_init_cb(&ls->ls_recall, clp, &nfsd4_cb_layout_ops, NFSPROC4_CLNT_CB_LAYOUT); @@ -262,19 +263,23 @@ nfsd4_preprocess_layout_stateid(struct svc_rqst *rqstp, status = nfserr_jukebox; if (!ls) goto out; + mutex_lock(&ls->ls_mutex); } else { ls = container_of(stid, struct nfs4_layout_stateid, ls_stid); status = nfserr_bad_stateid; + mutex_lock(&ls->ls_mutex); if (stateid->si_generation > stid->sc_stateid.si_generation) - goto out_put_stid; + goto out_unlock_stid; if (layout_type != ls->ls_layout_type) - goto out_put_stid; + goto out_unlock_stid; } *lsp = ls; return 0; +out_unlock_stid: + mutex_unlock(&ls->ls_mutex); out_put_stid: nfs4_put_stid(stid); out: @@ -296,8 +301,6 @@ nfsd4_recall_file_layout(struct nfs4_layout_stateid *ls) trace_layout_recall(&ls->ls_stid.sc_stateid); atomic_inc(&ls->ls_stid.sc_count); - update_stateid(&ls->ls_stid.sc_stateid); - memcpy(&ls->ls_recall_sid, &ls->ls_stid.sc_stateid, sizeof(stateid_t)); nfsd4_run_cb(&ls->ls_recall); out_unlock: @@ -406,8 +409,7 @@ nfsd4_insert_layout(struct nfsd4_layoutget *lgp, struct nfs4_layout_stateid *ls) list_add_tail(&new->lo_perstate, &ls->ls_layouts); new = NULL; done: - update_stateid(&ls->ls_stid.sc_stateid); - memcpy(&lgp->lg_sid, &ls->ls_stid.sc_stateid, sizeof(stateid_t)); + nfs4_inc_and_copy_stateid(&lgp->lg_sid, &ls->ls_stid); spin_unlock(&ls->ls_lock); out: spin_unlock(&fp->fi_lock); @@ -481,11 +483,8 @@ nfsd4_return_file_layouts(struct svc_rqst *rqstp, } } if (!list_empty(&ls->ls_layouts)) { - if (found) { - update_stateid(&ls->ls_stid.sc_stateid); - memcpy(&lrp->lr_sid, &ls->ls_stid.sc_stateid, - sizeof(stateid_t)); - } + if (found) + nfs4_inc_and_copy_stateid(&lrp->lr_sid, &ls->ls_stid); lrp->lrs_present = 1; } else { trace_layoutstate_unhash(&ls->ls_stid.sc_stateid); @@ -494,6 +493,7 @@ nfsd4_return_file_layouts(struct svc_rqst *rqstp, } spin_unlock(&ls->ls_lock); + mutex_unlock(&ls->ls_mutex); nfs4_put_stid(&ls->ls_stid); nfsd4_free_layouts(&reaplist); return nfs_ok; @@ -608,6 +608,16 @@ nfsd4_cb_layout_fail(struct nfs4_layout_stateid *ls) } } +static void +nfsd4_cb_layout_prepare(struct nfsd4_callback *cb) +{ + struct nfs4_layout_stateid *ls = + container_of(cb, struct nfs4_layout_stateid, ls_recall); + + mutex_lock(&ls->ls_mutex); + nfs4_inc_and_copy_stateid(&ls->ls_recall_sid, &ls->ls_stid); +} + static int nfsd4_cb_layout_done(struct nfsd4_callback *cb, struct rpc_task *task) { @@ -649,12 +659,14 @@ nfsd4_cb_layout_release(struct nfsd4_callback *cb) trace_layout_recall_release(&ls->ls_stid.sc_stateid); + mutex_unlock(&ls->ls_mutex); nfsd4_return_all_layouts(ls, &reaplist); nfsd4_free_layouts(&reaplist); nfs4_put_stid(&ls->ls_stid); } static struct nfsd4_callback_ops nfsd4_cb_layout_ops = { + .prepare = nfsd4_cb_layout_prepare, .done = nfsd4_cb_layout_done, .release = nfsd4_cb_layout_release, }; diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 4ce6b97..a9f096c 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1309,6 +1309,7 @@ nfsd4_layoutget(struct svc_rqst *rqstp, nfserr = nfsd4_insert_layout(lgp, ls); out_put_stid: + mutex_unlock(&ls->ls_mutex); nfs4_put_stid(&ls->ls_stid); out: return nfserr; @@ -1362,6 +1363,9 @@ nfsd4_layoutcommit(struct svc_rqst *rqstp, goto out; } + /* LAYOUTCOMMIT does not require any serialization */ + mutex_unlock(&ls->ls_mutex); + if (new_size > i_size_read(inode)) { lcp->lc_size_chg = 1; lcp->lc_newsize = new_size; diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 0f1d569..6b800b5b 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -575,6 +575,7 @@ struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, stid->sc_stateid.si_opaque.so_clid = cl->cl_clientid; /* Will be incremented before return to client: */ atomic_set(&stid->sc_count, 1); + spin_lock_init(&stid->sc_lock); /* * It shouldn't be a problem to reuse an opaque stateid value. @@ -745,6 +746,18 @@ nfs4_put_stid(struct nfs4_stid *s) put_nfs4_file(fp); } +void +nfs4_inc_and_copy_stateid(stateid_t *dst, struct nfs4_stid *stid) +{ + stateid_t *src = &stid->sc_stateid; + + spin_lock(&stid->sc_lock); + if (unlikely(++src->si_generation == 0)) + src->si_generation = 1; + memcpy(dst, src, sizeof(*dst)); + spin_unlock(&stid->sc_lock); +} + static void nfs4_put_deleg_lease(struct nfs4_file *fp) { struct file *filp = NULL; @@ -765,16 +778,68 @@ void nfs4_unhash_stid(struct nfs4_stid *s) s->sc_type = 0; } -static void +/** + * nfs4_get_existing_delegation - Discover if this delegation already exists + * @clp: a pointer to the nfs4_client we're granting a delegation to + * @fp: a pointer to the nfs4_file we're granting a delegation on + * + * Return: + * On success: NULL if an existing delegation was not found. + * + * On error: -EAGAIN if one was previously granted to this nfs4_client + * for this nfs4_file. + * + */ + +static int +nfs4_get_existing_delegation(struct nfs4_client *clp, struct nfs4_file *fp) +{ + struct nfs4_delegation *searchdp = NULL; + struct nfs4_client *searchclp = NULL; + + lockdep_assert_held(&state_lock); + lockdep_assert_held(&fp->fi_lock); + + list_for_each_entry(searchdp, &fp->fi_delegations, dl_perfile) { + searchclp = searchdp->dl_stid.sc_client; + if (clp == searchclp) { + return -EAGAIN; + } + } + return 0; +} + +/** + * hash_delegation_locked - Add a delegation to the appropriate lists + * @dp: a pointer to the nfs4_delegation we are adding. + * @fp: a pointer to the nfs4_file we're granting a delegation on + * + * Return: + * On success: NULL if the delegation was successfully hashed. + * + * On error: -EAGAIN if one was previously granted to this + * nfs4_client for this nfs4_file. Delegation is not hashed. + * + */ + +static int hash_delegation_locked(struct nfs4_delegation *dp, struct nfs4_file *fp) { + int status; + struct nfs4_client *clp = dp->dl_stid.sc_client; + lockdep_assert_held(&state_lock); lockdep_assert_held(&fp->fi_lock); + status = nfs4_get_existing_delegation(clp, fp); + if (status) + return status; + ++fp->fi_delegees; atomic_inc(&dp->dl_stid.sc_count); dp->dl_stid.sc_type = NFS4_DELEG_STID; list_add(&dp->dl_perfile, &fp->fi_delegations); - list_add(&dp->dl_perclnt, &dp->dl_stid.sc_client->cl_delegations); + list_add(&dp->dl_perclnt, &clp->cl_delegations); + return 0; } static bool @@ -2256,15 +2321,20 @@ nfsd4_set_ex_flags(struct nfs4_client *new, struct nfsd4_exchange_id *clid) clid->flags = new->cl_exchange_flags; } +static bool client_has_openowners(struct nfs4_client *clp) +{ + struct nfs4_openowner *oo; + + list_for_each_entry(oo, &clp->cl_openowners, oo_perclient) { + if (!list_empty(&oo->oo_owner.so_stateids)) + return true; + } + return false; +} + static bool client_has_state(struct nfs4_client *clp) { - /* - * Note clp->cl_openowners check isn't quite right: there's no - * need to count owners without stateid's. - * - * Also note we should probably be using this in 4.0 case too. - */ - return !list_empty(&clp->cl_openowners) + return client_has_openowners(clp) #ifdef CONFIG_NFSD_PNFS || !list_empty(&clp->cl_lo_states) #endif @@ -3049,7 +3119,7 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, /* Cases below refer to rfc 3530 section 14.2.33: */ spin_lock(&nn->client_lock); conf = find_confirmed_client_by_name(&clname, nn); - if (conf) { + if (conf && client_has_state(conf)) { /* case 0: */ status = nfserr_clid_inuse; if (clp_used_exchangeid(conf)) @@ -3136,6 +3206,11 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp, } else { /* case 3: normal case; new or rebooted client */ old = find_confirmed_client_by_name(&unconf->cl_name, nn); if (old) { + status = nfserr_clid_inuse; + if (client_has_state(old) + && !same_creds(&unconf->cl_cred, + &old->cl_cred)) + goto out; status = mark_client_expired_locked(old); if (status) { old = NULL; @@ -3317,6 +3392,27 @@ static const struct nfs4_stateowner_operations openowner_ops = { .so_free = nfs4_free_openowner, }; +static struct nfs4_ol_stateid * +nfsd4_find_existing_open(struct nfs4_file *fp, struct nfsd4_open *open) +{ + struct nfs4_ol_stateid *local, *ret = NULL; + struct nfs4_openowner *oo = open->op_openowner; + + lockdep_assert_held(&fp->fi_lock); + + list_for_each_entry(local, &fp->fi_stateids, st_perfile) { + /* ignore lock owners */ + if (local->st_stateowner->so_is_open_owner == 0) + continue; + if (local->st_stateowner == &oo->oo_owner) { + ret = local; + atomic_inc(&ret->st_stid.sc_count); + break; + } + } + return ret; +} + static struct nfs4_openowner * alloc_init_open_stateowner(unsigned int strhashval, struct nfsd4_open *open, struct nfsd4_compound_state *cstate) @@ -3348,9 +3444,20 @@ alloc_init_open_stateowner(unsigned int strhashval, struct nfsd4_open *open, return ret; } -static void init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp, struct nfsd4_open *open) { +static struct nfs4_ol_stateid * +init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp, + struct nfsd4_open *open) +{ + struct nfs4_openowner *oo = open->op_openowner; + struct nfs4_ol_stateid *retstp = NULL; + spin_lock(&oo->oo_owner.so_client->cl_lock); + spin_lock(&fp->fi_lock); + + retstp = nfsd4_find_existing_open(fp, open); + if (retstp) + goto out_unlock; atomic_inc(&stp->st_stid.sc_count); stp->st_stid.sc_type = NFS4_OPEN_STID; INIT_LIST_HEAD(&stp->st_locks); @@ -3360,12 +3467,14 @@ static void init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp, stp->st_access_bmap = 0; stp->st_deny_bmap = 0; stp->st_openstp = NULL; - spin_lock(&oo->oo_owner.so_client->cl_lock); + init_rwsem(&stp->st_rwsem); list_add(&stp->st_perstateowner, &oo->oo_owner.so_stateids); - spin_lock(&fp->fi_lock); list_add(&stp->st_perfile, &fp->fi_stateids); + +out_unlock: spin_unlock(&fp->fi_lock); spin_unlock(&oo->oo_owner.so_client->cl_lock); + return retstp; } /* @@ -3776,27 +3885,6 @@ out: return nfs_ok; } -static struct nfs4_ol_stateid * -nfsd4_find_existing_open(struct nfs4_file *fp, struct nfsd4_open *open) -{ - struct nfs4_ol_stateid *local, *ret = NULL; - struct nfs4_openowner *oo = open->op_openowner; - - spin_lock(&fp->fi_lock); - list_for_each_entry(local, &fp->fi_stateids, st_perfile) { - /* ignore lock owners */ - if (local->st_stateowner->so_is_open_owner == 0) - continue; - if (local->st_stateowner == &oo->oo_owner) { - ret = local; - atomic_inc(&ret->st_stid.sc_count); - break; - } - } - spin_unlock(&fp->fi_lock); - return ret; -} - static inline int nfs4_access_to_access(u32 nfs4_access) { int flags = 0; @@ -3945,6 +4033,18 @@ static struct file_lock *nfs4_alloc_init_lease(struct nfs4_file *fp, int flag) return fl; } +/** + * nfs4_setlease - Obtain a delegation by requesting lease from vfs layer + * @dp: a pointer to the nfs4_delegation we're adding. + * + * Return: + * On success: Return code will be 0 on success. + * + * On error: -EAGAIN if there was an existing delegation. + * nonzero if there is an error in other cases. + * + */ + static int nfs4_setlease(struct nfs4_delegation *dp) { struct nfs4_file *fp = dp->dl_stid.sc_file; @@ -3976,16 +4076,19 @@ static int nfs4_setlease(struct nfs4_delegation *dp) goto out_unlock; /* Race breaker */ if (fp->fi_deleg_file) { - status = 0; - ++fp->fi_delegees; - hash_delegation_locked(dp, fp); + status = hash_delegation_locked(dp, fp); goto out_unlock; } fp->fi_deleg_file = filp; - fp->fi_delegees = 1; - hash_delegation_locked(dp, fp); + fp->fi_delegees = 0; + status = hash_delegation_locked(dp, fp); spin_unlock(&fp->fi_lock); spin_unlock(&state_lock); + if (status) { + /* Should never happen, this is a new fi_deleg_file */ + WARN_ON_ONCE(1); + goto out_fput; + } return 0; out_unlock: spin_unlock(&fp->fi_lock); @@ -4005,6 +4108,15 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh, if (fp->fi_had_conflict) return ERR_PTR(-EAGAIN); + spin_lock(&state_lock); + spin_lock(&fp->fi_lock); + status = nfs4_get_existing_delegation(clp, fp); + spin_unlock(&fp->fi_lock); + spin_unlock(&state_lock); + + if (status) + return ERR_PTR(status); + dp = alloc_init_deleg(clp, fh, odstate); if (!dp) return ERR_PTR(-ENOMEM); @@ -4023,9 +4135,7 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh, status = -EAGAIN; goto out_unlock; } - ++fp->fi_delegees; - hash_delegation_locked(dp, fp); - status = 0; + status = hash_delegation_locked(dp, fp); out_unlock: spin_unlock(&fp->fi_lock); spin_unlock(&state_lock); @@ -4160,6 +4270,7 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf struct nfs4_client *cl = open->op_openowner->oo_owner.so_client; struct nfs4_file *fp = NULL; struct nfs4_ol_stateid *stp = NULL; + struct nfs4_ol_stateid *swapstp = NULL; struct nfs4_delegation *dp = NULL; __be32 status; @@ -4173,7 +4284,9 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf status = nfs4_check_deleg(cl, open, &dp); if (status) goto out; + spin_lock(&fp->fi_lock); stp = nfsd4_find_existing_open(fp, open); + spin_unlock(&fp->fi_lock); } else { open->op_file = NULL; status = nfserr_bad_stateid; @@ -4187,15 +4300,32 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf */ if (stp) { /* Stateid was found, this is an OPEN upgrade */ + down_read(&stp->st_rwsem); status = nfs4_upgrade_open(rqstp, fp, current_fh, stp, open); - if (status) + if (status) { + up_read(&stp->st_rwsem); goto out; + } } else { stp = open->op_stp; open->op_stp = NULL; - init_open_stateid(stp, fp, open); + swapstp = init_open_stateid(stp, fp, open); + if (swapstp) { + nfs4_put_stid(&stp->st_stid); + stp = swapstp; + down_read(&stp->st_rwsem); + status = nfs4_upgrade_open(rqstp, fp, current_fh, + stp, open); + if (status) { + up_read(&stp->st_rwsem); + goto out; + } + goto upgrade_out; + } + down_read(&stp->st_rwsem); status = nfs4_get_vfs_file(rqstp, fp, current_fh, stp, open); if (status) { + up_read(&stp->st_rwsem); release_open_stateid(stp); goto out; } @@ -4205,8 +4335,9 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf if (stp->st_clnt_odstate == open->op_odstate) open->op_odstate = NULL; } - update_stateid(&stp->st_stid.sc_stateid); - memcpy(&open->op_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t)); +upgrade_out: + nfs4_inc_and_copy_stateid(&open->op_stateid, &stp->st_stid); + up_read(&stp->st_rwsem); if (nfsd4_has_session(&resp->cstate)) { if (open->op_deleg_want & NFS4_SHARE_WANT_NO_DELEG) { @@ -4819,10 +4950,13 @@ static __be32 nfs4_seqid_op_checks(struct nfsd4_compound_state *cstate, stateid_ * revoked delegations are kept only for free_stateid. */ return nfserr_bad_stateid; + down_write(&stp->st_rwsem); status = check_stateid_generation(stateid, &stp->st_stid.sc_stateid, nfsd4_has_session(cstate)); - if (status) - return status; - return nfs4_check_fh(current_fh, &stp->st_stid); + if (status == nfs_ok) + status = nfs4_check_fh(current_fh, &stp->st_stid); + if (status != nfs_ok) + up_write(&stp->st_rwsem); + return status; } /* @@ -4869,6 +5003,7 @@ static __be32 nfs4_preprocess_confirmed_seqid_op(struct nfsd4_compound_state *cs return status; oo = openowner(stp->st_stateowner); if (!(oo->oo_flags & NFS4_OO_CONFIRMED)) { + up_write(&stp->st_rwsem); nfs4_put_stid(&stp->st_stid); return nfserr_bad_stateid; } @@ -4899,11 +5034,13 @@ nfsd4_open_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; oo = openowner(stp->st_stateowner); status = nfserr_bad_stateid; - if (oo->oo_flags & NFS4_OO_CONFIRMED) + if (oo->oo_flags & NFS4_OO_CONFIRMED) { + up_write(&stp->st_rwsem); goto put_stateid; + } oo->oo_flags |= NFS4_OO_CONFIRMED; - update_stateid(&stp->st_stid.sc_stateid); - memcpy(&oc->oc_resp_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t)); + nfs4_inc_and_copy_stateid(&oc->oc_resp_stateid, &stp->st_stid); + up_write(&stp->st_rwsem); dprintk("NFSD: %s: success, seqid=%d stateid=" STATEID_FMT "\n", __func__, oc->oc_seqid, STATEID_VAL(&stp->st_stid.sc_stateid)); @@ -4975,13 +5112,11 @@ nfsd4_open_downgrade(struct svc_rqst *rqstp, goto put_stateid; } nfs4_stateid_downgrade(stp, od->od_share_access); - reset_union_bmap_deny(od->od_share_deny, stp); - - update_stateid(&stp->st_stid.sc_stateid); - memcpy(&od->od_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t)); + nfs4_inc_and_copy_stateid(&od->od_stateid, &stp->st_stid); status = nfs_ok; put_stateid: + up_write(&stp->st_rwsem); nfs4_put_stid(&stp->st_stid); out: nfsd4_bump_seqid(cstate, status); @@ -5033,8 +5168,8 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, nfsd4_bump_seqid(cstate, status); if (status) goto out; - update_stateid(&stp->st_stid.sc_stateid); - memcpy(&close->cl_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t)); + nfs4_inc_and_copy_stateid(&close->cl_stateid, &stp->st_stid); + up_write(&stp->st_rwsem); nfsd4_close_open_stateid(stp); @@ -5260,6 +5395,7 @@ init_lock_stateid(struct nfs4_ol_stateid *stp, struct nfs4_lockowner *lo, stp->st_access_bmap = 0; stp->st_deny_bmap = open_stp->st_deny_bmap; stp->st_openstp = open_stp; + init_rwsem(&stp->st_rwsem); list_add(&stp->st_locks, &open_stp->st_locks); list_add(&stp->st_perstateowner, &lo->lo_owner.so_stateids); spin_lock(&fp->fi_lock); @@ -5428,6 +5564,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, &open_stp, nn); if (status) goto out; + up_write(&open_stp->st_rwsem); open_sop = openowner(open_stp->st_stateowner); status = nfserr_bad_stateid; if (!same_clid(&open_sop->oo_owner.so_client->cl_clientid, @@ -5435,6 +5572,8 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; status = lookup_or_create_lock_state(cstate, open_stp, lock, &lock_stp, &new); + if (status == nfs_ok) + down_write(&lock_stp->st_rwsem); } else { status = nfs4_preprocess_seqid_op(cstate, lock->lk_old_lock_seqid, @@ -5512,9 +5651,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, err = vfs_lock_file(filp, F_SETLK, file_lock, conflock); switch (-err) { case 0: /* success! */ - update_stateid(&lock_stp->st_stid.sc_stateid); - memcpy(&lock->lk_resp_stateid, &lock_stp->st_stid.sc_stateid, - sizeof(stateid_t)); + nfs4_inc_and_copy_stateid(&lock->lk_resp_stateid, &lock_stp->st_stid); status = 0; break; case (EAGAIN): /* conflock holds conflicting lock */ @@ -5540,6 +5677,8 @@ out: seqid_mutating_err(ntohl(status))) lock_sop->lo_owner.so_seqid++; + up_write(&lock_stp->st_rwsem); + /* * If this is a new, never-before-used stateid, and we are * returning an error, then just go ahead and release it. @@ -5704,11 +5843,11 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, dprintk("NFSD: nfs4_locku: vfs_lock_file failed!\n"); goto out_nfserr; } - update_stateid(&stp->st_stid.sc_stateid); - memcpy(&locku->lu_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t)); + nfs4_inc_and_copy_stateid(&locku->lu_stateid, &stp->st_stid); fput: fput(filp); put_stateid: + up_write(&stp->st_rwsem); nfs4_put_stid(&stp->st_stid); out: nfsd4_bump_seqid(cstate, status); diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c index 46ec934..54cde9a 100644 --- a/fs/nfsd/nfscache.c +++ b/fs/nfsd/nfscache.c @@ -63,7 +63,6 @@ static unsigned int longest_chain; static unsigned int longest_chain_cachesize; static int nfsd_cache_append(struct svc_rqst *rqstp, struct kvec *vec); -static void cache_cleaner_func(struct work_struct *unused); static unsigned long nfsd_reply_cache_count(struct shrinker *shrink, struct shrink_control *sc); static unsigned long nfsd_reply_cache_scan(struct shrinker *shrink, @@ -76,13 +75,6 @@ static struct shrinker nfsd_reply_cache_shrinker = { }; /* - * locking for the reply cache: - * A cache entry is "single use" if c_state == RC_INPROG - * Otherwise, it when accessing _prev or _next, the lock must be held. - */ -static DECLARE_DELAYED_WORK(cache_cleaner, cache_cleaner_func); - -/* * Put a cap on the size of the DRC based on the amount of available * low memory in the machine. * @@ -203,7 +195,6 @@ void nfsd_reply_cache_shutdown(void) unsigned int i; unregister_shrinker(&nfsd_reply_cache_shrinker); - cancel_delayed_work_sync(&cache_cleaner); for (i = 0; i < drc_hashsize; i++) { struct list_head *head = &drc_hashtbl[i].lru_head; @@ -217,10 +208,8 @@ void nfsd_reply_cache_shutdown(void) drc_hashtbl = NULL; drc_hashsize = 0; - if (drc_slab) { - kmem_cache_destroy(drc_slab); - drc_slab = NULL; - } + kmem_cache_destroy(drc_slab); + drc_slab = NULL; } /* @@ -232,7 +221,6 @@ lru_put_end(struct nfsd_drc_bucket *b, struct svc_cacherep *rp) { rp->c_timestamp = jiffies; list_move_tail(&rp->c_lru, &b->lru_head); - schedule_delayed_work(&cache_cleaner, RC_EXPIRE); } static long @@ -266,7 +254,6 @@ prune_cache_entries(void) { unsigned int i; long freed = 0; - bool cancel = true; for (i = 0; i < drc_hashsize; i++) { struct nfsd_drc_bucket *b = &drc_hashtbl[i]; @@ -275,26 +262,11 @@ prune_cache_entries(void) continue; spin_lock(&b->cache_lock); freed += prune_bucket(b); - if (!list_empty(&b->lru_head)) - cancel = false; spin_unlock(&b->cache_lock); } - - /* - * Conditionally rearm the job to run in RC_EXPIRE since we just - * ran the pruner. - */ - if (!cancel) - mod_delayed_work(system_wq, &cache_cleaner, RC_EXPIRE); return freed; } -static void -cache_cleaner_func(struct work_struct *unused) -{ - prune_cache_entries(); -} - static unsigned long nfsd_reply_cache_count(struct shrinker *shrink, struct shrink_control *sc) { diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index 350041a..c1681ce 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -631,10 +631,7 @@ fh_put(struct svc_fh *fhp) fh_unlock(fhp); fhp->fh_dentry = NULL; dput(dentry); -#ifdef CONFIG_NFSD_V3 - fhp->fh_pre_saved = 0; - fhp->fh_post_saved = 0; -#endif + fh_clear_wcc(fhp); } fh_drop_write(fhp); if (exp) { diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h index 1e90dad..2087bae 100644 --- a/fs/nfsd/nfsfh.h +++ b/fs/nfsd/nfsfh.h @@ -26,16 +26,16 @@ static inline ino_t u32_to_ino_t(__u32 uino) */ typedef struct svc_fh { struct knfsd_fh fh_handle; /* FH data */ + int fh_maxsize; /* max size for fh_handle */ struct dentry * fh_dentry; /* validated dentry */ struct svc_export * fh_export; /* export pointer */ - int fh_maxsize; /* max size for fh_handle */ - unsigned char fh_locked; /* inode locked by us */ - unsigned char fh_want_write; /* remount protection taken */ + bool fh_locked; /* inode locked by us */ + bool fh_want_write; /* remount protection taken */ #ifdef CONFIG_NFSD_V3 - unsigned char fh_post_saved; /* post-op attrs saved */ - unsigned char fh_pre_saved; /* pre-op attrs saved */ + bool fh_post_saved; /* post-op attrs saved */ + bool fh_pre_saved; /* pre-op attrs saved */ /* Pre-op attributes saved during fh_lock */ __u64 fh_pre_size; /* size before operation */ @@ -213,8 +213,8 @@ static inline bool fh_fsid_match(struct knfsd_fh *fh1, struct knfsd_fh *fh2) static inline void fh_clear_wcc(struct svc_fh *fhp) { - fhp->fh_post_saved = 0; - fhp->fh_pre_saved = 0; + fhp->fh_post_saved = false; + fhp->fh_pre_saved = false; } /* @@ -231,7 +231,7 @@ fill_pre_wcc(struct svc_fh *fhp) fhp->fh_pre_ctime = inode->i_ctime; fhp->fh_pre_size = inode->i_size; fhp->fh_pre_change = inode->i_version; - fhp->fh_pre_saved = 1; + fhp->fh_pre_saved = true; } } @@ -267,7 +267,7 @@ fh_lock_nested(struct svc_fh *fhp, unsigned int subclass) inode = d_inode(dentry); mutex_lock_nested(&inode->i_mutex, subclass); fill_pre_wcc(fhp); - fhp->fh_locked = 1; + fhp->fh_locked = true; } static inline void @@ -285,7 +285,7 @@ fh_unlock(struct svc_fh *fhp) if (fhp->fh_locked) { fill_post_wcc(fhp); mutex_unlock(&d_inode(fhp->fh_dentry)->i_mutex); - fhp->fh_locked = 0; + fhp->fh_locked = false; } } diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 583ffc1..77fdf4d 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -84,7 +84,7 @@ struct nfsd4_callback_ops { * fields that are of general use to any stateid. */ struct nfs4_stid { - atomic_t sc_count; + atomic_t sc_count; #define NFS4_OPEN_STID 1 #define NFS4_LOCK_STID 2 #define NFS4_DELEG_STID 4 @@ -94,11 +94,12 @@ struct nfs4_stid { #define NFS4_REVOKED_DELEG_STID 16 #define NFS4_CLOSED_DELEG_STID 32 #define NFS4_LAYOUT_STID 64 - unsigned char sc_type; - stateid_t sc_stateid; - struct nfs4_client *sc_client; - struct nfs4_file *sc_file; - void (*sc_free)(struct nfs4_stid *); + unsigned char sc_type; + stateid_t sc_stateid; + spinlock_t sc_lock; + struct nfs4_client *sc_client; + struct nfs4_file *sc_file; + void (*sc_free)(struct nfs4_stid *); }; /* @@ -364,15 +365,6 @@ struct nfs4_client_reclaim { char cr_recdir[HEXDIR_LEN]; /* recover dir */ }; -static inline void -update_stateid(stateid_t *stateid) -{ - stateid->si_generation++; - /* Wraparound recommendation from 3530bis-13 9.1.3.2: */ - if (stateid->si_generation == 0) - stateid->si_generation = 1; -} - /* A reasonable value for REPLAY_ISIZE was estimated as follows: * The OPEN response, typically the largest, requires * 4(status) + 8(stateid) + 20(changeinfo) + 4(rflags) + 8(verifier) + @@ -534,15 +526,16 @@ struct nfs4_file { * Better suggestions welcome. */ struct nfs4_ol_stateid { - struct nfs4_stid st_stid; /* must be first field */ - struct list_head st_perfile; - struct list_head st_perstateowner; - struct list_head st_locks; - struct nfs4_stateowner * st_stateowner; - struct nfs4_clnt_odstate * st_clnt_odstate; - unsigned char st_access_bmap; - unsigned char st_deny_bmap; - struct nfs4_ol_stateid * st_openstp; + struct nfs4_stid st_stid; + struct list_head st_perfile; + struct list_head st_perstateowner; + struct list_head st_locks; + struct nfs4_stateowner *st_stateowner; + struct nfs4_clnt_odstate *st_clnt_odstate; + unsigned char st_access_bmap; + unsigned char st_deny_bmap; + struct nfs4_ol_stateid *st_openstp; + struct rw_semaphore st_rwsem; }; static inline struct nfs4_ol_stateid *openlockstateid(struct nfs4_stid *s) @@ -561,6 +554,7 @@ struct nfs4_layout_stateid { struct nfsd4_callback ls_recall; stateid_t ls_recall_sid; bool ls_recalled; + struct mutex ls_mutex; }; static inline struct nfs4_layout_stateid *layoutstateid(struct nfs4_stid *s) @@ -593,6 +587,7 @@ struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct kmem_cache *slab); void nfs4_unhash_stid(struct nfs4_stid *s); void nfs4_put_stid(struct nfs4_stid *s); +void nfs4_inc_and_copy_stateid(stateid_t *dst, struct nfs4_stid *stid); void nfs4_remove_reclaim_record(struct nfs4_client_reclaim *, struct nfsd_net *); extern void nfs4_release_reclaim(struct nfsd_net *); extern struct nfs4_client_reclaim *nfsd4_find_reclaim_client(const char *recdir, diff --git a/fs/nfsd/trace.c b/fs/nfsd/trace.c index 82f8907..9096746 100644 --- a/fs/nfsd/trace.c +++ b/fs/nfsd/trace.c @@ -1,5 +1,3 @@ -#include "state.h" - #define CREATE_TRACE_POINTS #include "trace.h" diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h index c668520..0befe76 100644 --- a/fs/nfsd/trace.h +++ b/fs/nfsd/trace.h @@ -9,6 +9,8 @@ #include <linux/tracepoint.h> +#include "state.h" + DECLARE_EVENT_CLASS(nfsd_stateid_class, TP_PROTO(stateid_t *stp), TP_ARGS(stp), diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 45c0497..994d66f 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -1631,7 +1631,7 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen, /* cannot use fh_lock as we need deadlock protective ordering * so do it by hand */ trap = lock_rename(tdentry, fdentry); - ffhp->fh_locked = tfhp->fh_locked = 1; + ffhp->fh_locked = tfhp->fh_locked = true; fill_pre_wcc(ffhp); fill_pre_wcc(tfhp); @@ -1681,7 +1681,7 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen, fill_post_wcc(ffhp); fill_post_wcc(tfhp); unlock_rename(tdentry, fdentry); - ffhp->fh_locked = tfhp->fh_locked = 0; + ffhp->fh_locked = tfhp->fh_locked = false; fh_drop_write(ffhp); out: diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h index fee2451..fcfc48c 100644 --- a/fs/nfsd/vfs.h +++ b/fs/nfsd/vfs.h @@ -112,14 +112,14 @@ static inline int fh_want_write(struct svc_fh *fh) int ret = mnt_want_write(fh->fh_export->ex_path.mnt); if (!ret) - fh->fh_want_write = 1; + fh->fh_want_write = true; return ret; } static inline void fh_drop_write(struct svc_fh *fh) { if (fh->fh_want_write) { - fh->fh_want_write = 0; + fh->fh_want_write = false; mnt_drop_write(fh->fh_export->ex_path.mnt); } } diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index 9f99100..ce7362c 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -632,7 +632,7 @@ static inline void set_change_info(struct nfsd4_change_info *cinfo, struct svc_fh *fhp) { BUG_ON(!fhp->fh_pre_saved); - cinfo->atomic = fhp->fh_post_saved; + cinfo->atomic = (u32)fhp->fh_post_saved; cinfo->change_supported = IS_I_VERSION(d_inode(fhp->fh_dentry)); cinfo->before_change = fhp->fh_pre_change; diff --git a/fs/nilfs2/alloc.c b/fs/nilfs2/alloc.c index 8df0f3b..2ccbf55 100644 --- a/fs/nilfs2/alloc.c +++ b/fs/nilfs2/alloc.c @@ -133,38 +133,38 @@ nilfs_palloc_bitmap_blkoff(const struct inode *inode, unsigned long group) /** * nilfs_palloc_group_desc_nfrees - get the number of free entries in a group - * @inode: inode of metadata file using this allocator - * @group: group number * @desc: pointer to descriptor structure for the group + * @lock: spin lock protecting @desc */ static unsigned long -nilfs_palloc_group_desc_nfrees(struct inode *inode, unsigned long group, - const struct nilfs_palloc_group_desc *desc) +nilfs_palloc_group_desc_nfrees(const struct nilfs_palloc_group_desc *desc, + spinlock_t *lock) { unsigned long nfree; - spin_lock(nilfs_mdt_bgl_lock(inode, group)); + spin_lock(lock); nfree = le32_to_cpu(desc->pg_nfrees); - spin_unlock(nilfs_mdt_bgl_lock(inode, group)); + spin_unlock(lock); return nfree; } /** * nilfs_palloc_group_desc_add_entries - adjust count of free entries - * @inode: inode of metadata file using this allocator - * @group: group number * @desc: pointer to descriptor structure for the group + * @lock: spin lock protecting @desc * @n: delta to be added */ -static void -nilfs_palloc_group_desc_add_entries(struct inode *inode, - unsigned long group, - struct nilfs_palloc_group_desc *desc, - u32 n) +static u32 +nilfs_palloc_group_desc_add_entries(struct nilfs_palloc_group_desc *desc, + spinlock_t *lock, u32 n) { - spin_lock(nilfs_mdt_bgl_lock(inode, group)); + u32 nfree; + + spin_lock(lock); le32_add_cpu(&desc->pg_nfrees, n); - spin_unlock(nilfs_mdt_bgl_lock(inode, group)); + nfree = le32_to_cpu(desc->pg_nfrees); + spin_unlock(lock); + return nfree; } /** @@ -240,6 +240,26 @@ static int nilfs_palloc_get_block(struct inode *inode, unsigned long blkoff, } /** + * nilfs_palloc_delete_block - delete a block on the persistent allocator file + * @inode: inode of metadata file using this allocator + * @blkoff: block offset + * @prev: nilfs_bh_assoc struct of the last used buffer + * @lock: spin lock protecting @prev + */ +static int nilfs_palloc_delete_block(struct inode *inode, unsigned long blkoff, + struct nilfs_bh_assoc *prev, + spinlock_t *lock) +{ + spin_lock(lock); + if (prev->bh && blkoff == prev->blkoff) { + brelse(prev->bh); + prev->bh = NULL; + } + spin_unlock(lock); + return nilfs_mdt_delete_block(inode, blkoff); +} + +/** * nilfs_palloc_get_desc_block - get buffer head of a group descriptor block * @inode: inode of metadata file using this allocator * @group: group number @@ -278,6 +298,22 @@ static int nilfs_palloc_get_bitmap_block(struct inode *inode, } /** + * nilfs_palloc_delete_bitmap_block - delete a bitmap block + * @inode: inode of metadata file using this allocator + * @group: group number + */ +static int nilfs_palloc_delete_bitmap_block(struct inode *inode, + unsigned long group) +{ + struct nilfs_palloc_cache *cache = NILFS_MDT(inode)->mi_palloc_cache; + + return nilfs_palloc_delete_block(inode, + nilfs_palloc_bitmap_blkoff(inode, + group), + &cache->prev_bitmap, &cache->lock); +} + +/** * nilfs_palloc_get_entry_block - get buffer head of an entry block * @inode: inode of metadata file using this allocator * @nr: serial number of the entry (e.g. inode number) @@ -296,6 +332,20 @@ int nilfs_palloc_get_entry_block(struct inode *inode, __u64 nr, } /** + * nilfs_palloc_delete_entry_block - delete an entry block + * @inode: inode of metadata file using this allocator + * @nr: serial number of the entry + */ +static int nilfs_palloc_delete_entry_block(struct inode *inode, __u64 nr) +{ + struct nilfs_palloc_cache *cache = NILFS_MDT(inode)->mi_palloc_cache; + + return nilfs_palloc_delete_block(inode, + nilfs_palloc_entry_blkoff(inode, nr), + &cache->prev_entry, &cache->lock); +} + +/** * nilfs_palloc_block_get_group_desc - get kernel address of a group descriptor * @inode: inode of metadata file using this allocator * @group: group number @@ -332,51 +382,40 @@ void *nilfs_palloc_block_get_entry(const struct inode *inode, __u64 nr, /** * nilfs_palloc_find_available_slot - find available slot in a group - * @inode: inode of metadata file using this allocator - * @group: group number - * @target: offset number of an entry in the group (start point) * @bitmap: bitmap of the group + * @target: offset number of an entry in the group (start point) * @bsize: size in bits + * @lock: spin lock protecting @bitmap */ -static int nilfs_palloc_find_available_slot(struct inode *inode, - unsigned long group, +static int nilfs_palloc_find_available_slot(unsigned char *bitmap, unsigned long target, - unsigned char *bitmap, - int bsize) -{ - int curr, pos, end, i; - - if (target > 0) { - end = (target + BITS_PER_LONG - 1) & ~(BITS_PER_LONG - 1); - if (end > bsize) - end = bsize; - pos = nilfs_find_next_zero_bit(bitmap, end, target); - if (pos < end && - !nilfs_set_bit_atomic( - nilfs_mdt_bgl_lock(inode, group), pos, bitmap)) - return pos; - } else - end = 0; - - for (i = 0, curr = end; - i < bsize; - i += BITS_PER_LONG, curr += BITS_PER_LONG) { - /* wrap around */ - if (curr >= bsize) - curr = 0; - while (*((unsigned long *)bitmap + curr / BITS_PER_LONG) - != ~0UL) { - end = curr + BITS_PER_LONG; - if (end > bsize) - end = bsize; - pos = nilfs_find_next_zero_bit(bitmap, end, curr); - if ((pos < end) && - !nilfs_set_bit_atomic( - nilfs_mdt_bgl_lock(inode, group), pos, - bitmap)) + unsigned bsize, + spinlock_t *lock) +{ + int pos, end = bsize; + + if (likely(target < bsize)) { + pos = target; + do { + pos = nilfs_find_next_zero_bit(bitmap, end, pos); + if (pos >= end) + break; + if (!nilfs_set_bit_atomic(lock, pos, bitmap)) return pos; - } + } while (++pos < end); + + end = target; + } + + /* wrap around */ + for (pos = 0; pos < end; pos++) { + pos = nilfs_find_next_zero_bit(bitmap, end, pos); + if (pos >= end) + break; + if (!nilfs_set_bit_atomic(lock, pos, bitmap)) + return pos; } + return -ENOSPC; } @@ -475,15 +514,15 @@ int nilfs_palloc_prepare_alloc_entry(struct inode *inode, void *desc_kaddr, *bitmap_kaddr; unsigned long group, maxgroup, ngroups; unsigned long group_offset, maxgroup_offset; - unsigned long n, entries_per_group, groups_per_desc_block; + unsigned long n, entries_per_group; unsigned long i, j; + spinlock_t *lock; int pos, ret; ngroups = nilfs_palloc_groups_count(inode); maxgroup = ngroups - 1; group = nilfs_palloc_group(inode, req->pr_entry_nr, &group_offset); entries_per_group = nilfs_palloc_entries_per_group(inode); - groups_per_desc_block = nilfs_palloc_groups_per_desc_block(inode); for (i = 0; i < ngroups; i += n) { if (group >= ngroups) { @@ -501,8 +540,8 @@ int nilfs_palloc_prepare_alloc_entry(struct inode *inode, n = nilfs_palloc_rest_groups_in_desc_block(inode, group, maxgroup); for (j = 0; j < n; j++, desc++, group++) { - if (nilfs_palloc_group_desc_nfrees(inode, group, desc) - > 0) { + lock = nilfs_mdt_bgl_lock(inode, group); + if (nilfs_palloc_group_desc_nfrees(desc, lock) > 0) { ret = nilfs_palloc_get_bitmap_block( inode, group, 1, &bitmap_bh); if (ret < 0) @@ -510,12 +549,12 @@ int nilfs_palloc_prepare_alloc_entry(struct inode *inode, bitmap_kaddr = kmap(bitmap_bh->b_page); bitmap = bitmap_kaddr + bh_offset(bitmap_bh); pos = nilfs_palloc_find_available_slot( - inode, group, group_offset, bitmap, - entries_per_group); + bitmap, group_offset, + entries_per_group, lock); if (pos >= 0) { /* found a free entry */ nilfs_palloc_group_desc_add_entries( - inode, group, desc, -1); + desc, lock, -1); req->pr_entry_nr = entries_per_group * group + pos; kunmap(desc_bh->b_page); @@ -573,6 +612,7 @@ void nilfs_palloc_commit_free_entry(struct inode *inode, unsigned long group, group_offset; unsigned char *bitmap; void *desc_kaddr, *bitmap_kaddr; + spinlock_t *lock; group = nilfs_palloc_group(inode, req->pr_entry_nr, &group_offset); desc_kaddr = kmap(req->pr_desc_bh->b_page); @@ -580,13 +620,15 @@ void nilfs_palloc_commit_free_entry(struct inode *inode, req->pr_desc_bh, desc_kaddr); bitmap_kaddr = kmap(req->pr_bitmap_bh->b_page); bitmap = bitmap_kaddr + bh_offset(req->pr_bitmap_bh); + lock = nilfs_mdt_bgl_lock(inode, group); - if (!nilfs_clear_bit_atomic(nilfs_mdt_bgl_lock(inode, group), - group_offset, bitmap)) - printk(KERN_WARNING "%s: entry number %llu already freed\n", - __func__, (unsigned long long)req->pr_entry_nr); + if (!nilfs_clear_bit_atomic(lock, group_offset, bitmap)) + nilfs_warning(inode->i_sb, __func__, + "entry number %llu already freed: ino=%lu\n", + (unsigned long long)req->pr_entry_nr, + (unsigned long)inode->i_ino); else - nilfs_palloc_group_desc_add_entries(inode, group, desc, 1); + nilfs_palloc_group_desc_add_entries(desc, lock, 1); kunmap(req->pr_bitmap_bh->b_page); kunmap(req->pr_desc_bh->b_page); @@ -611,6 +653,7 @@ void nilfs_palloc_abort_alloc_entry(struct inode *inode, void *desc_kaddr, *bitmap_kaddr; unsigned char *bitmap; unsigned long group, group_offset; + spinlock_t *lock; group = nilfs_palloc_group(inode, req->pr_entry_nr, &group_offset); desc_kaddr = kmap(req->pr_desc_bh->b_page); @@ -618,12 +661,15 @@ void nilfs_palloc_abort_alloc_entry(struct inode *inode, req->pr_desc_bh, desc_kaddr); bitmap_kaddr = kmap(req->pr_bitmap_bh->b_page); bitmap = bitmap_kaddr + bh_offset(req->pr_bitmap_bh); - if (!nilfs_clear_bit_atomic(nilfs_mdt_bgl_lock(inode, group), - group_offset, bitmap)) - printk(KERN_WARNING "%s: entry number %llu already freed\n", - __func__, (unsigned long long)req->pr_entry_nr); + lock = nilfs_mdt_bgl_lock(inode, group); + + if (!nilfs_clear_bit_atomic(lock, group_offset, bitmap)) + nilfs_warning(inode->i_sb, __func__, + "entry number %llu already freed: ino=%lu\n", + (unsigned long long)req->pr_entry_nr, + (unsigned long)inode->i_ino); else - nilfs_palloc_group_desc_add_entries(inode, group, desc, 1); + nilfs_palloc_group_desc_add_entries(desc, lock, 1); kunmap(req->pr_bitmap_bh->b_page); kunmap(req->pr_desc_bh->b_page); @@ -680,22 +726,6 @@ void nilfs_palloc_abort_free_entry(struct inode *inode, } /** - * nilfs_palloc_group_is_in - judge if an entry is in a group - * @inode: inode of metadata file using this allocator - * @group: group number - * @nr: serial number of the entry (e.g. inode number) - */ -static int -nilfs_palloc_group_is_in(struct inode *inode, unsigned long group, __u64 nr) -{ - __u64 first, last; - - first = group * nilfs_palloc_entries_per_group(inode); - last = first + nilfs_palloc_entries_per_group(inode) - 1; - return (nr >= first) && (nr <= last); -} - -/** * nilfs_palloc_freev - deallocate a set of persistent objects * @inode: inode of metadata file using this allocator * @entry_nrs: array of entry numbers to be deallocated @@ -708,9 +738,18 @@ int nilfs_palloc_freev(struct inode *inode, __u64 *entry_nrs, size_t nitems) unsigned char *bitmap; void *desc_kaddr, *bitmap_kaddr; unsigned long group, group_offset; - int i, j, n, ret; + __u64 group_min_nr, last_nrs[8]; + const unsigned long epg = nilfs_palloc_entries_per_group(inode); + const unsigned epb = NILFS_MDT(inode)->mi_entries_per_block; + unsigned entry_start, end, pos; + spinlock_t *lock; + int i, j, k, ret; + u32 nfree; for (i = 0; i < nitems; i = j) { + int change_group = false; + int nempties = 0, n = 0; + group = nilfs_palloc_group(inode, entry_nrs[i], &group_offset); ret = nilfs_palloc_get_desc_block(inode, group, 0, &desc_bh); if (ret < 0) @@ -721,38 +760,89 @@ int nilfs_palloc_freev(struct inode *inode, __u64 *entry_nrs, size_t nitems) brelse(desc_bh); return ret; } - desc_kaddr = kmap(desc_bh->b_page); - desc = nilfs_palloc_block_get_group_desc( - inode, group, desc_bh, desc_kaddr); + + /* Get the first entry number of the group */ + group_min_nr = (__u64)group * epg; + bitmap_kaddr = kmap(bitmap_bh->b_page); bitmap = bitmap_kaddr + bh_offset(bitmap_bh); - for (j = i, n = 0; - (j < nitems) && nilfs_palloc_group_is_in(inode, group, - entry_nrs[j]); - j++) { - nilfs_palloc_group(inode, entry_nrs[j], &group_offset); - if (!nilfs_clear_bit_atomic( - nilfs_mdt_bgl_lock(inode, group), - group_offset, bitmap)) { - printk(KERN_WARNING - "%s: entry number %llu already freed\n", - __func__, - (unsigned long long)entry_nrs[j]); + lock = nilfs_mdt_bgl_lock(inode, group); + + j = i; + entry_start = rounddown(group_offset, epb); + do { + if (!nilfs_clear_bit_atomic(lock, group_offset, + bitmap)) { + nilfs_warning(inode->i_sb, __func__, + "entry number %llu already freed: ino=%lu\n", + (unsigned long long)entry_nrs[j], + (unsigned long)inode->i_ino); } else { n++; } - } - nilfs_palloc_group_desc_add_entries(inode, group, desc, n); + + j++; + if (j >= nitems || entry_nrs[j] < group_min_nr || + entry_nrs[j] >= group_min_nr + epg) { + change_group = true; + } else { + group_offset = entry_nrs[j] - group_min_nr; + if (group_offset >= entry_start && + group_offset < entry_start + epb) { + /* This entry is in the same block */ + continue; + } + } + + /* Test if the entry block is empty or not */ + end = entry_start + epb; + pos = nilfs_find_next_bit(bitmap, end, entry_start); + if (pos >= end) { + last_nrs[nempties++] = entry_nrs[j - 1]; + if (nempties >= ARRAY_SIZE(last_nrs)) + break; + } + + if (change_group) + break; + + /* Go on to the next entry block */ + entry_start = rounddown(group_offset, epb); + } while (true); kunmap(bitmap_bh->b_page); - kunmap(desc_bh->b_page); + mark_buffer_dirty(bitmap_bh); + brelse(bitmap_bh); + for (k = 0; k < nempties; k++) { + ret = nilfs_palloc_delete_entry_block(inode, + last_nrs[k]); + if (ret && ret != -ENOENT) { + nilfs_warning(inode->i_sb, __func__, + "failed to delete block of entry %llu: ino=%lu, err=%d\n", + (unsigned long long)last_nrs[k], + (unsigned long)inode->i_ino, ret); + } + } + + desc_kaddr = kmap_atomic(desc_bh->b_page); + desc = nilfs_palloc_block_get_group_desc( + inode, group, desc_bh, desc_kaddr); + nfree = nilfs_palloc_group_desc_add_entries(desc, lock, n); + kunmap_atomic(desc_kaddr); mark_buffer_dirty(desc_bh); - mark_buffer_dirty(bitmap_bh); nilfs_mdt_mark_dirty(inode); - - brelse(bitmap_bh); brelse(desc_bh); + + if (nfree == nilfs_palloc_entries_per_group(inode)) { + ret = nilfs_palloc_delete_bitmap_block(inode, group); + if (ret && ret != -ENOENT) { + nilfs_warning(inode->i_sb, __func__, + "failed to delete bitmap block of group %lu: ino=%lu, err=%d\n", + group, + (unsigned long)inode->i_ino, ret); + } + } } return 0; } diff --git a/fs/nilfs2/alloc.h b/fs/nilfs2/alloc.h index 4bd6451..6e6f49a 100644 --- a/fs/nilfs2/alloc.h +++ b/fs/nilfs2/alloc.h @@ -77,6 +77,7 @@ int nilfs_palloc_freev(struct inode *, __u64 *, size_t); #define nilfs_set_bit_atomic ext2_set_bit_atomic #define nilfs_clear_bit_atomic ext2_clear_bit_atomic #define nilfs_find_next_zero_bit find_next_zero_bit_le +#define nilfs_find_next_bit find_next_bit_le /** * struct nilfs_bh_assoc - block offset and buffer head association diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c index 919fd5b..3a3821b 100644 --- a/fs/nilfs2/btree.c +++ b/fs/nilfs2/btree.c @@ -919,8 +919,6 @@ static void nilfs_btree_split(struct nilfs_bmap *btree, int level, __u64 *keyp, __u64 *ptrp) { struct nilfs_btree_node *node, *right; - __u64 newkey; - __u64 newptr; int nchildren, n, move, ncblk; node = nilfs_btree_get_nonroot_node(path, level); @@ -942,9 +940,6 @@ static void nilfs_btree_split(struct nilfs_bmap *btree, if (!buffer_dirty(path[level].bp_sib_bh)) mark_buffer_dirty(path[level].bp_sib_bh); - newkey = nilfs_btree_node_get_key(right, 0); - newptr = path[level].bp_newreq.bpr_ptr; - if (move) { path[level].bp_index -= nilfs_btree_node_get_nchildren(node); nilfs_btree_node_insert(right, path[level].bp_index, @@ -1856,7 +1851,7 @@ int nilfs_btree_convert_and_insert(struct nilfs_bmap *btree, __u64 key, __u64 ptr, const __u64 *keys, const __u64 *ptrs, int n) { - struct buffer_head *bh; + struct buffer_head *bh = NULL; union nilfs_bmap_ptr_req dreq, nreq, *di, *ni; struct nilfs_bmap_stats stats; int ret; diff --git a/fs/nilfs2/dat.c b/fs/nilfs2/dat.c index 0d5fada..7dc23f1 100644 --- a/fs/nilfs2/dat.c +++ b/fs/nilfs2/dat.c @@ -155,7 +155,6 @@ void nilfs_dat_commit_start(struct inode *dat, struct nilfs_palloc_req *req, int nilfs_dat_prepare_end(struct inode *dat, struct nilfs_palloc_req *req) { struct nilfs_dat_entry *entry; - __u64 start; sector_t blocknr; void *kaddr; int ret; @@ -169,7 +168,6 @@ int nilfs_dat_prepare_end(struct inode *dat, struct nilfs_palloc_req *req) kaddr = kmap_atomic(req->pr_entry_bh->b_page); entry = nilfs_palloc_block_get_entry(dat, req->pr_entry_nr, req->pr_entry_bh, kaddr); - start = le64_to_cpu(entry->de_start); blocknr = le64_to_cpu(entry->de_blocknr); kunmap_atomic(kaddr); diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c index 54575e3..088ba00 100644 --- a/fs/nilfs2/file.c +++ b/fs/nilfs2/file.c @@ -109,7 +109,7 @@ static int nilfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) goto out; file_update_time(vma->vm_file); - ret = __block_page_mkwrite(vma, vmf, nilfs_get_block); + ret = block_page_mkwrite(vma, vmf, nilfs_get_block); if (ret) { nilfs_transaction_abort(inode->i_sb); goto out; diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 4a73d6d..ac2f649 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -356,7 +356,7 @@ struct inode *nilfs_new_inode(struct inode *dir, umode_t mode) goto failed; mapping_set_gfp_mask(inode->i_mapping, - mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS); + mapping_gfp_constraint(inode->i_mapping, ~__GFP_FS)); root = NILFS_I(dir)->i_root; ii = NILFS_I(inode); @@ -522,7 +522,7 @@ static int __nilfs_read_inode(struct super_block *sb, up_read(&NILFS_MDT(nilfs->ns_dat)->mi_sem); nilfs_set_inode_flags(inode); mapping_set_gfp_mask(inode->i_mapping, - mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS); + mapping_gfp_constraint(inode->i_mapping, ~__GFP_FS)); return 0; failed_unmap: diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c index dee34d9..1125f40 100644 --- a/fs/nilfs2/mdt.c +++ b/fs/nilfs2/mdt.c @@ -33,6 +33,7 @@ #include "page.h" #include "mdt.h" +#include <trace/events/nilfs2.h> #define NILFS_MDT_MAX_RA_BLOCKS (16 - 1) @@ -68,6 +69,9 @@ nilfs_mdt_insert_new_block(struct inode *inode, unsigned long block, set_buffer_uptodate(bh); mark_buffer_dirty(bh); nilfs_mdt_mark_dirty(inode); + + trace_nilfs2_mdt_insert_new_block(inode, inode->i_ino, block); + return 0; } @@ -158,6 +162,8 @@ nilfs_mdt_submit_block(struct inode *inode, unsigned long blkoff, get_bh(bh); submit_bh(mode, bh); ret = 0; + + trace_nilfs2_mdt_submit_block(inode, inode->i_ino, blkoff, mode); out: get_bh(bh); *out_bh = bh; diff --git a/fs/nilfs2/mdt.h b/fs/nilfs2/mdt.h index fe529a8..03246ca 100644 --- a/fs/nilfs2/mdt.h +++ b/fs/nilfs2/mdt.h @@ -72,7 +72,7 @@ static inline struct nilfs_mdt_info *NILFS_MDT(const struct inode *inode) } /* Default GFP flags using highmem */ -#define NILFS_MDT_GFP (__GFP_WAIT | __GFP_IO | __GFP_HIGHMEM) +#define NILFS_MDT_GFP (__GFP_RECLAIM | __GFP_IO | __GFP_HIGHMEM) int nilfs_mdt_get_block(struct inode *, unsigned long, int, void (*init_block)(struct inode *, diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c index 37dd6b0..c9a1a49 100644 --- a/fs/nilfs2/namei.c +++ b/fs/nilfs2/namei.c @@ -120,9 +120,6 @@ nilfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) struct nilfs_transaction_info ti; int err; - if (!new_valid_dev(rdev)) - return -EINVAL; - err = nilfs_transaction_begin(dir->i_sb, &ti, 1); if (err) return err; diff --git a/fs/nilfs2/recovery.c b/fs/nilfs2/recovery.c index ff00a0b..9b4f205 100644 --- a/fs/nilfs2/recovery.c +++ b/fs/nilfs2/recovery.c @@ -582,7 +582,7 @@ static int nilfs_do_roll_forward(struct the_nilfs *nilfs, struct nilfs_recovery_info *ri) { struct buffer_head *bh_sum = NULL; - struct nilfs_segment_summary *sum; + struct nilfs_segment_summary *sum = NULL; sector_t pseg_start; sector_t seg_start, seg_end; /* Starting/ending DBN of full segment */ unsigned long nsalvaged_blocks = 0; @@ -814,7 +814,7 @@ int nilfs_search_super_root(struct the_nilfs *nilfs, struct nilfs_recovery_info *ri) { struct buffer_head *bh_sum = NULL; - struct nilfs_segment_summary *sum; + struct nilfs_segment_summary *sum = NULL; sector_t pseg_start, pseg_end, sr_pseg_start = 0; sector_t seg_start, seg_end; /* range of full segment (block number) */ sector_t b, end; diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index c6abbad9..3b65ada 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -77,6 +77,36 @@ enum { NILFS_ST_DONE, }; +#define CREATE_TRACE_POINTS +#include <trace/events/nilfs2.h> + +/* + * nilfs_sc_cstage_inc(), nilfs_sc_cstage_set(), nilfs_sc_cstage_get() are + * wrapper functions of stage count (nilfs_sc_info->sc_stage.scnt). Users of + * the variable must use them because transition of stage count must involve + * trace events (trace_nilfs2_collection_stage_transition). + * + * nilfs_sc_cstage_get() isn't required for the above purpose because it doesn't + * produce tracepoint events. It is provided just for making the intention + * clear. + */ +static inline void nilfs_sc_cstage_inc(struct nilfs_sc_info *sci) +{ + sci->sc_stage.scnt++; + trace_nilfs2_collection_stage_transition(sci); +} + +static inline void nilfs_sc_cstage_set(struct nilfs_sc_info *sci, int next_scnt) +{ + sci->sc_stage.scnt = next_scnt; + trace_nilfs2_collection_stage_transition(sci); +} + +static inline int nilfs_sc_cstage_get(struct nilfs_sc_info *sci) +{ + return sci->sc_stage.scnt; +} + /* State flags of collection */ #define NILFS_CF_NODE 0x0001 /* Collecting node blocks */ #define NILFS_CF_IFILE_STARTED 0x0002 /* IFILE stage has started */ @@ -184,11 +214,18 @@ int nilfs_transaction_begin(struct super_block *sb, { struct the_nilfs *nilfs; int ret = nilfs_prepare_segment_lock(ti); + struct nilfs_transaction_info *trace_ti; if (unlikely(ret < 0)) return ret; - if (ret > 0) + if (ret > 0) { + trace_ti = current->journal_info; + + trace_nilfs2_transaction_transition(sb, trace_ti, + trace_ti->ti_count, trace_ti->ti_flags, + TRACE_NILFS2_TRANSACTION_BEGIN); return 0; + } sb_start_intwrite(sb); @@ -199,6 +236,11 @@ int nilfs_transaction_begin(struct super_block *sb, ret = -ENOSPC; goto failed; } + + trace_ti = current->journal_info; + trace_nilfs2_transaction_transition(sb, trace_ti, trace_ti->ti_count, + trace_ti->ti_flags, + TRACE_NILFS2_TRANSACTION_BEGIN); return 0; failed: @@ -231,6 +273,8 @@ int nilfs_transaction_commit(struct super_block *sb) ti->ti_flags |= NILFS_TI_COMMIT; if (ti->ti_count > 0) { ti->ti_count--; + trace_nilfs2_transaction_transition(sb, ti, ti->ti_count, + ti->ti_flags, TRACE_NILFS2_TRANSACTION_COMMIT); return 0; } if (nilfs->ns_writer) { @@ -242,6 +286,9 @@ int nilfs_transaction_commit(struct super_block *sb) nilfs_segctor_do_flush(sci, 0); } up_read(&nilfs->ns_segctor_sem); + trace_nilfs2_transaction_transition(sb, ti, ti->ti_count, + ti->ti_flags, TRACE_NILFS2_TRANSACTION_COMMIT); + current->journal_info = ti->ti_save; if (ti->ti_flags & NILFS_TI_SYNC) @@ -260,10 +307,15 @@ void nilfs_transaction_abort(struct super_block *sb) BUG_ON(ti == NULL || ti->ti_magic != NILFS_TI_MAGIC); if (ti->ti_count > 0) { ti->ti_count--; + trace_nilfs2_transaction_transition(sb, ti, ti->ti_count, + ti->ti_flags, TRACE_NILFS2_TRANSACTION_ABORT); return; } up_read(&nilfs->ns_segctor_sem); + trace_nilfs2_transaction_transition(sb, ti, ti->ti_count, + ti->ti_flags, TRACE_NILFS2_TRANSACTION_ABORT); + current->journal_info = ti->ti_save; if (ti->ti_flags & NILFS_TI_DYNAMIC_ALLOC) kmem_cache_free(nilfs_transaction_cachep, ti); @@ -309,6 +361,9 @@ static void nilfs_transaction_lock(struct super_block *sb, current->journal_info = ti; for (;;) { + trace_nilfs2_transaction_transition(sb, ti, ti->ti_count, + ti->ti_flags, TRACE_NILFS2_TRANSACTION_TRYLOCK); + down_write(&nilfs->ns_segctor_sem); if (!test_bit(NILFS_SC_PRIOR_FLUSH, &sci->sc_flags)) break; @@ -320,6 +375,9 @@ static void nilfs_transaction_lock(struct super_block *sb, } if (gcflag) ti->ti_flags |= NILFS_TI_GC; + + trace_nilfs2_transaction_transition(sb, ti, ti->ti_count, + ti->ti_flags, TRACE_NILFS2_TRANSACTION_LOCK); } static void nilfs_transaction_unlock(struct super_block *sb) @@ -332,6 +390,9 @@ static void nilfs_transaction_unlock(struct super_block *sb) up_write(&nilfs->ns_segctor_sem); current->journal_info = ti->ti_save; + + trace_nilfs2_transaction_transition(sb, ti, ti->ti_count, + ti->ti_flags, TRACE_NILFS2_TRANSACTION_UNLOCK); } static void *nilfs_segctor_map_segsum_entry(struct nilfs_sc_info *sci, @@ -1062,7 +1123,7 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode) size_t ndone; int err = 0; - switch (sci->sc_stage.scnt) { + switch (nilfs_sc_cstage_get(sci)) { case NILFS_ST_INIT: /* Pre-processes */ sci->sc_stage.flags = 0; @@ -1071,7 +1132,7 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode) sci->sc_nblk_inc = 0; sci->sc_curseg->sb_sum.flags = NILFS_SS_LOGBGN; if (mode == SC_LSEG_DSYNC) { - sci->sc_stage.scnt = NILFS_ST_DSYNC; + nilfs_sc_cstage_set(sci, NILFS_ST_DSYNC); goto dsync_mode; } } @@ -1079,10 +1140,10 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode) sci->sc_stage.dirty_file_ptr = NULL; sci->sc_stage.gc_inode_ptr = NULL; if (mode == SC_FLUSH_DAT) { - sci->sc_stage.scnt = NILFS_ST_DAT; + nilfs_sc_cstage_set(sci, NILFS_ST_DAT); goto dat_stage; } - sci->sc_stage.scnt++; /* Fall through */ + nilfs_sc_cstage_inc(sci); /* Fall through */ case NILFS_ST_GC: if (nilfs_doing_gc()) { head = &sci->sc_gc_inodes; @@ -1103,7 +1164,7 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode) } sci->sc_stage.gc_inode_ptr = NULL; } - sci->sc_stage.scnt++; /* Fall through */ + nilfs_sc_cstage_inc(sci); /* Fall through */ case NILFS_ST_FILE: head = &sci->sc_dirty_files; ii = list_prepare_entry(sci->sc_stage.dirty_file_ptr, head, @@ -1125,10 +1186,10 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode) } sci->sc_stage.dirty_file_ptr = NULL; if (mode == SC_FLUSH_FILE) { - sci->sc_stage.scnt = NILFS_ST_DONE; + nilfs_sc_cstage_set(sci, NILFS_ST_DONE); return 0; } - sci->sc_stage.scnt++; + nilfs_sc_cstage_inc(sci); sci->sc_stage.flags |= NILFS_CF_IFILE_STARTED; /* Fall through */ case NILFS_ST_IFILE: @@ -1136,7 +1197,7 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode) &nilfs_sc_file_ops); if (unlikely(err)) break; - sci->sc_stage.scnt++; + nilfs_sc_cstage_inc(sci); /* Creating a checkpoint */ err = nilfs_segctor_create_checkpoint(sci); if (unlikely(err)) @@ -1147,7 +1208,7 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode) &nilfs_sc_file_ops); if (unlikely(err)) break; - sci->sc_stage.scnt++; /* Fall through */ + nilfs_sc_cstage_inc(sci); /* Fall through */ case NILFS_ST_SUFILE: err = nilfs_sufile_freev(nilfs->ns_sufile, sci->sc_freesegs, sci->sc_nfreesegs, &ndone); @@ -1163,7 +1224,7 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode) &nilfs_sc_file_ops); if (unlikely(err)) break; - sci->sc_stage.scnt++; /* Fall through */ + nilfs_sc_cstage_inc(sci); /* Fall through */ case NILFS_ST_DAT: dat_stage: err = nilfs_segctor_scan_file(sci, nilfs->ns_dat, @@ -1171,10 +1232,10 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode) if (unlikely(err)) break; if (mode == SC_FLUSH_DAT) { - sci->sc_stage.scnt = NILFS_ST_DONE; + nilfs_sc_cstage_set(sci, NILFS_ST_DONE); return 0; } - sci->sc_stage.scnt++; /* Fall through */ + nilfs_sc_cstage_inc(sci); /* Fall through */ case NILFS_ST_SR: if (mode == SC_LSEG_SR) { /* Appending a super root */ @@ -1184,7 +1245,7 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode) } /* End of a logical segment */ sci->sc_curseg->sb_sum.flags |= NILFS_SS_LOGEND; - sci->sc_stage.scnt = NILFS_ST_DONE; + nilfs_sc_cstage_set(sci, NILFS_ST_DONE); return 0; case NILFS_ST_DSYNC: dsync_mode: @@ -1197,7 +1258,7 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode) if (unlikely(err)) break; sci->sc_curseg->sb_sum.flags |= NILFS_SS_LOGEND; - sci->sc_stage.scnt = NILFS_ST_DONE; + nilfs_sc_cstage_set(sci, NILFS_ST_DONE); return 0; case NILFS_ST_DONE: return 0; @@ -1442,7 +1503,8 @@ static int nilfs_segctor_collect(struct nilfs_sc_info *sci, goto failed; /* The current segment is filled up */ - if (mode != SC_LSEG_SR || sci->sc_stage.scnt < NILFS_ST_CPFILE) + if (mode != SC_LSEG_SR || + nilfs_sc_cstage_get(sci) < NILFS_ST_CPFILE) break; nilfs_clear_logs(&sci->sc_segbufs); @@ -1946,7 +2008,7 @@ static int nilfs_segctor_do_construct(struct nilfs_sc_info *sci, int mode) struct the_nilfs *nilfs = sci->sc_super->s_fs_info; int err; - sci->sc_stage.scnt = NILFS_ST_INIT; + nilfs_sc_cstage_set(sci, NILFS_ST_INIT); sci->sc_cno = nilfs->ns_cno; err = nilfs_segctor_collect_dirty_files(sci, nilfs); @@ -1974,7 +2036,7 @@ static int nilfs_segctor_do_construct(struct nilfs_sc_info *sci, int mode) goto failed; /* Avoid empty segment */ - if (sci->sc_stage.scnt == NILFS_ST_DONE && + if (nilfs_sc_cstage_get(sci) == NILFS_ST_DONE && nilfs_segbuf_empty(sci->sc_curseg)) { nilfs_segctor_abort_construction(sci, nilfs, 1); goto out; @@ -1988,7 +2050,7 @@ static int nilfs_segctor_do_construct(struct nilfs_sc_info *sci, int mode) nilfs_segctor_fill_in_file_bmap(sci); if (mode == SC_LSEG_SR && - sci->sc_stage.scnt >= NILFS_ST_CPFILE) { + nilfs_sc_cstage_get(sci) >= NILFS_ST_CPFILE) { err = nilfs_segctor_fill_in_checkpoint(sci); if (unlikely(err)) goto failed_to_write; @@ -2007,7 +2069,7 @@ static int nilfs_segctor_do_construct(struct nilfs_sc_info *sci, int mode) if (unlikely(err)) goto failed_to_write; - if (sci->sc_stage.scnt == NILFS_ST_DONE || + if (nilfs_sc_cstage_get(sci) == NILFS_ST_DONE || nilfs->ns_blocksize_bits != PAGE_CACHE_SHIFT) { /* * At this point, we avoid double buffering @@ -2020,7 +2082,7 @@ static int nilfs_segctor_do_construct(struct nilfs_sc_info *sci, int mode) if (err) goto failed_to_write; } - } while (sci->sc_stage.scnt != NILFS_ST_DONE); + } while (nilfs_sc_cstage_get(sci) != NILFS_ST_DONE); out: nilfs_segctor_drop_written_files(sci, nilfs); @@ -2430,7 +2492,6 @@ static void nilfs_segctor_thread_construct(struct nilfs_sc_info *sci, int mode) static void nilfs_segctor_do_immediate_flush(struct nilfs_sc_info *sci) { int mode = 0; - int err; spin_lock(&sci->sc_state_lock); mode = (sci->sc_flush_request & FLUSH_DAT_BIT) ? @@ -2438,7 +2499,7 @@ static void nilfs_segctor_do_immediate_flush(struct nilfs_sc_info *sci) spin_unlock(&sci->sc_state_lock); if (mode) { - err = nilfs_segctor_do_construct(sci, mode); + nilfs_segctor_do_construct(sci, mode); spin_lock(&sci->sc_state_lock); sci->sc_flush_request &= (mode == SC_FLUSH_FILE) ? diff --git a/fs/nilfs2/segment.h b/fs/nilfs2/segment.h index a48d6de..0408b9b 100644 --- a/fs/nilfs2/segment.h +++ b/fs/nilfs2/segment.h @@ -67,7 +67,8 @@ struct nilfs_recovery_info { /** * struct nilfs_cstage - Context of collection stage - * @scnt: Stage count + * @scnt: Stage count, must be accessed via wrappers: + * nilfs_sc_cstage_inc(), nilfs_sc_cstage_set(), nilfs_sc_cstage_get() * @flags: State flags * @dirty_file_ptr: Pointer on dirty_files list, or inode of a target file * @gc_inode_ptr: Pointer on the list of gc-inodes diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c index 2a869c3..52821ff 100644 --- a/fs/nilfs2/sufile.c +++ b/fs/nilfs2/sufile.c @@ -30,6 +30,8 @@ #include "mdt.h" #include "sufile.h" +#include <trace/events/nilfs2.h> + /** * struct nilfs_sufile_info - on-memory private data of sufile * @mi: on-memory private data of metadata file @@ -317,7 +319,7 @@ int nilfs_sufile_alloc(struct inode *sufile, __u64 *segnump) size_t susz = NILFS_MDT(sufile)->mi_entry_size; __u64 segnum, maxsegnum, last_alloc; void *kaddr; - unsigned long nsegments, ncleansegs, nsus, cnt; + unsigned long nsegments, nsus, cnt; int ret, j; down_write(&NILFS_MDT(sufile)->mi_sem); @@ -327,7 +329,6 @@ int nilfs_sufile_alloc(struct inode *sufile, __u64 *segnump) goto out_sem; kaddr = kmap_atomic(header_bh->b_page); header = kaddr + bh_offset(header_bh); - ncleansegs = le64_to_cpu(header->sh_ncleansegs); last_alloc = le64_to_cpu(header->sh_last_alloc); kunmap_atomic(kaddr); @@ -358,6 +359,7 @@ int nilfs_sufile_alloc(struct inode *sufile, __u64 *segnump) break; /* never happens */ } } + trace_nilfs2_segment_usage_check(sufile, segnum, cnt); ret = nilfs_sufile_get_segment_usage_block(sufile, segnum, 1, &su_bh); if (ret < 0) @@ -388,6 +390,9 @@ int nilfs_sufile_alloc(struct inode *sufile, __u64 *segnump) nilfs_mdt_mark_dirty(sufile); brelse(su_bh); *segnump = segnum; + + trace_nilfs2_segment_usage_allocated(sufile, segnum); + goto out_header; } @@ -490,6 +495,8 @@ void nilfs_sufile_do_free(struct inode *sufile, __u64 segnum, NILFS_SUI(sufile)->ncleansegs++; nilfs_mdt_mark_dirty(sufile); + + trace_nilfs2_segment_usage_freed(sufile, segnum); } /** diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index f47585b..354013e 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -361,7 +361,7 @@ static int nilfs_move_2nd_super(struct super_block *sb, loff_t sb2off) struct nilfs_super_block *nsbp; sector_t blocknr, newblocknr; unsigned long offset; - int sb2i = -1; /* array index of the secondary superblock */ + int sb2i; /* array index of the secondary superblock */ int ret = 0; /* nilfs->ns_sem must be locked by the caller. */ @@ -372,6 +372,9 @@ static int nilfs_move_2nd_super(struct super_block *sb, loff_t sb2off) } else if (nilfs->ns_sbh[0]->b_blocknr > nilfs->ns_first_data_block) { sb2i = 0; blocknr = nilfs->ns_sbh[0]->b_blocknr; + } else { + sb2i = -1; + blocknr = 0; } if (sb2i >= 0 && (u64)blocknr << nilfs->ns_blocksize_bits == sb2off) goto out; /* super block location is unchanged */ @@ -1405,14 +1408,10 @@ static void nilfs_destroy_cachep(void) */ rcu_barrier(); - if (nilfs_inode_cachep) - kmem_cache_destroy(nilfs_inode_cachep); - if (nilfs_transaction_cachep) - kmem_cache_destroy(nilfs_transaction_cachep); - if (nilfs_segbuf_cachep) - kmem_cache_destroy(nilfs_segbuf_cachep); - if (nilfs_btree_path_cache) - kmem_cache_destroy(nilfs_btree_path_cache); + kmem_cache_destroy(nilfs_inode_cachep); + kmem_cache_destroy(nilfs_transaction_cachep); + kmem_cache_destroy(nilfs_segbuf_cachep); + kmem_cache_destroy(nilfs_btree_path_cache); } static int __init nilfs_init_cachep(void) diff --git a/fs/notify/fdinfo.c b/fs/notify/fdinfo.c index 6b6f0d47..fd98e51 100644 --- a/fs/notify/fdinfo.c +++ b/fs/notify/fdinfo.c @@ -83,9 +83,16 @@ static void inotify_fdinfo(struct seq_file *m, struct fsnotify_mark *mark) inode_mark = container_of(mark, struct inotify_inode_mark, fsn_mark); inode = igrab(mark->inode); if (inode) { + /* + * IN_ALL_EVENTS represents all of the mask bits + * that we expose to userspace. There is at + * least one bit (FS_EVENT_ON_CHILD) which is + * used only internally to the kernel. + */ + u32 mask = mark->mask & IN_ALL_EVENTS; seq_printf(m, "inotify wd:%x ino:%lx sdev:%x mask:%x ignored_mask:%x ", inode_mark->wd, inode->i_ino, inode->i_sb->s_dev, - mark->mask, mark->ignored_mask); + mask, mark->ignored_mask); show_mark_fhandle(m, inode); seq_putc(m, '\n'); iput(inode); diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index 5b1e2a4..b8d08d0 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -706,7 +706,19 @@ SYSCALL_DEFINE3(inotify_add_watch, int, fd, const char __user *, pathname, int ret; unsigned flags = 0; - /* don't allow invalid bits: we don't want flags set */ + /* + * We share a lot of code with fs/dnotify. We also share + * the bit layout between inotify's IN_* and the fsnotify + * FS_*. This check ensures that only the inotify IN_* + * bits get passed in and set in watches/events. + */ + if (unlikely(mask & ~ALL_INOTIFY_BITS)) + return -EINVAL; + /* + * Require at least one valid bit set in the mask. + * Without _something_ set, we would have no events to + * watch for. + */ if (unlikely(!(mask & ALL_INOTIFY_BITS))) return -EINVAL; diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index 262561f..9d383e5 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -525,8 +525,8 @@ static inline int __ntfs_grab_cache_pages(struct address_space *mapping, } } err = add_to_page_cache_lru(*cached_page, mapping, - index, - GFP_KERNEL & mapping_gfp_mask(mapping)); + index, + mapping_gfp_constraint(mapping, GFP_KERNEL)); if (unlikely(err)) { if (err == -EEXIST) continue; diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 64b11d9..7f60472 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -589,6 +589,7 @@ static int ocfs2_direct_IO_get_blocks(struct inode *inode, sector_t iblock, ret = -EIO; goto bail; } + set_buffer_new(bh_result); up_write(&OCFS2_I(inode)->ip_alloc_sem); } @@ -864,6 +865,7 @@ static ssize_t ocfs2_direct_IO_write(struct kiocb *iocb, is_overwrite = ocfs2_is_overwrite(osb, inode, offset); if (is_overwrite < 0) { mlog_errno(is_overwrite); + ret = is_overwrite; ocfs2_inode_unlock(inode, 1); goto clean_orphan; } diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index fa15deb..ddddef0 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -219,7 +219,8 @@ struct o2hb_region { unsigned hr_unclean_stop:1, hr_aborted_start:1, hr_item_pinned:1, - hr_item_dropped:1; + hr_item_dropped:1, + hr_node_deleted:1; /* protected by the hr_callback_sem */ struct task_struct *hr_task; @@ -1078,7 +1079,13 @@ static int o2hb_thread(void *data) set_user_nice(current, MIN_NICE); /* Pin node */ - o2nm_depend_this_node(); + ret = o2nm_depend_this_node(); + if (ret) { + mlog(ML_ERROR, "Node has been deleted, ret = %d\n", ret); + reg->hr_node_deleted = 1; + wake_up(&o2hb_steady_queue); + return 0; + } while (!kthread_should_stop() && !reg->hr_unclean_stop && !reg->hr_aborted_start) { @@ -1787,7 +1794,8 @@ static ssize_t o2hb_region_dev_write(struct o2hb_region *reg, spin_unlock(&o2hb_live_lock); ret = wait_event_interruptible(o2hb_steady_queue, - atomic_read(®->hr_steady_iterations) == 0); + atomic_read(®->hr_steady_iterations) == 0 || + reg->hr_node_deleted); if (ret) { atomic_set(®->hr_steady_iterations, 0); reg->hr_aborted_start = 1; @@ -1798,6 +1806,11 @@ static ssize_t o2hb_region_dev_write(struct o2hb_region *reg, goto out3; } + if (reg->hr_node_deleted) { + ret = -EINVAL; + goto out3; + } + /* Ok, we were woken. Make sure it wasn't by drop_item() */ spin_lock(&o2hb_live_lock); hb_task = reg->hr_task; diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c index 6918f30..2ee7fe7 100644 --- a/fs/ocfs2/dlm/dlmdomain.c +++ b/fs/ocfs2/dlm/dlmdomain.c @@ -1866,6 +1866,7 @@ static int dlm_join_domain(struct dlm_ctxt *dlm) int status; unsigned int backoff; unsigned int total_backoff = 0; + char wq_name[O2NM_MAX_NAME_LEN]; BUG_ON(!dlm); @@ -1895,7 +1896,8 @@ static int dlm_join_domain(struct dlm_ctxt *dlm) goto bail; } - dlm->dlm_worker = create_singlethread_workqueue("dlm_wq"); + snprintf(wq_name, O2NM_MAX_NAME_LEN, "dlm_wq-%s", dlm->name); + dlm->dlm_worker = create_singlethread_workqueue(wq_name); if (!dlm->dlm_worker) { status = -ENOMEM; mlog_errno(status); diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index 46b8b2b..ce38b4c 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -1439,6 +1439,7 @@ int dlm_master_request_handler(struct o2net_msg *msg, u32 len, void *data, int found, ret; int set_maybe; int dispatch_assert = 0; + int dispatched = 0; if (!dlm_grab(dlm)) return DLM_MASTER_RESP_NO; @@ -1657,16 +1658,20 @@ send_response: if (ret < 0) { mlog(ML_ERROR, "failed to dispatch assert master work\n"); response = DLM_MASTER_RESP_ERROR; + spin_unlock(&res->spinlock); dlm_lockres_put(res); - } else + } else { + dispatched = 1; __dlm_lockres_grab_inflight_worker(dlm, res); - spin_unlock(&res->spinlock); + spin_unlock(&res->spinlock); + } } else { if (res) dlm_lockres_put(res); } - dlm_put(dlm); + if (!dispatched) + dlm_put(dlm); return response; } @@ -2090,7 +2095,6 @@ int dlm_dispatch_assert_master(struct dlm_ctxt *dlm, /* queue up work for dlm_assert_master_worker */ - dlm_grab(dlm); /* get an extra ref for the work item */ dlm_init_work_item(dlm, item, dlm_assert_master_worker, NULL); item->u.am.lockres = res; /* already have a ref */ /* can optionally ignore node numbers higher than this node */ diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c index ce12e0b..9e4f862 100644 --- a/fs/ocfs2/dlm/dlmrecovery.c +++ b/fs/ocfs2/dlm/dlmrecovery.c @@ -205,7 +205,7 @@ int dlm_launch_recovery_thread(struct dlm_ctxt *dlm) mlog(0, "starting dlm recovery thread...\n"); dlm->dlm_reco_thread_task = kthread_run(dlm_recovery_thread, dlm, - "dlm_reco_thread"); + "dlm_reco-%s", dlm->name); if (IS_ERR(dlm->dlm_reco_thread_task)) { mlog_errno(PTR_ERR(dlm->dlm_reco_thread_task)); dlm->dlm_reco_thread_task = NULL; @@ -1694,6 +1694,7 @@ int dlm_master_requery_handler(struct o2net_msg *msg, u32 len, void *data, unsigned int hash; int master = DLM_LOCK_RES_OWNER_UNKNOWN; u32 flags = DLM_ASSERT_MASTER_REQUERY; + int dispatched = 0; if (!dlm_grab(dlm)) { /* since the domain has gone away on this @@ -1719,9 +1720,11 @@ int dlm_master_requery_handler(struct o2net_msg *msg, u32 len, void *data, dlm_put(dlm); /* sender will take care of this and retry */ return ret; - } else + } else { + dispatched = 1; __dlm_lockres_grab_inflight_worker(dlm, res); - spin_unlock(&res->spinlock); + spin_unlock(&res->spinlock); + } } else { /* put.. incase we are not the master */ spin_unlock(&res->spinlock); @@ -1730,7 +1733,8 @@ int dlm_master_requery_handler(struct o2net_msg *msg, u32 len, void *data, } spin_unlock(&dlm->spinlock); - dlm_put(dlm); + if (!dispatched) + dlm_put(dlm); return master; } diff --git a/fs/ocfs2/dlm/dlmthread.c b/fs/ocfs2/dlm/dlmthread.c index 2e5e6d5..c5f6c24 100644 --- a/fs/ocfs2/dlm/dlmthread.c +++ b/fs/ocfs2/dlm/dlmthread.c @@ -493,7 +493,8 @@ int dlm_launch_thread(struct dlm_ctxt *dlm) { mlog(0, "Starting dlm_thread...\n"); - dlm->dlm_thread_task = kthread_run(dlm_thread, dlm, "dlm_thread"); + dlm->dlm_thread_task = kthread_run(dlm_thread, dlm, "dlm-%s", + dlm->name); if (IS_ERR(dlm->dlm_thread_task)) { mlog_errno(PTR_ERR(dlm->dlm_thread_task)); dlm->dlm_thread_task = NULL; diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 1c91103..20276e3 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -2998,7 +2998,8 @@ int ocfs2_dlm_init(struct ocfs2_super *osb) } /* launch downconvert thread */ - osb->dc_task = kthread_run(ocfs2_downconvert_thread, osb, "ocfs2dc"); + osb->dc_task = kthread_run(ocfs2_downconvert_thread, osb, "ocfs2dc-%s", + osb->uuid_str); if (IS_ERR(osb->dc_task)) { status = PTR_ERR(osb->dc_task); osb->dc_task = NULL; diff --git a/fs/ocfs2/inode.h b/fs/ocfs2/inode.h index ca3431e..aac8b86 100644 --- a/fs/ocfs2/inode.h +++ b/fs/ocfs2/inode.h @@ -112,6 +112,8 @@ struct ocfs2_inode_info #define OCFS2_INODE_OPEN_DIRECT 0x00000020 /* Tell the inode wipe code it's not in orphan dir */ #define OCFS2_INODE_SKIP_ORPHAN_DIR 0x00000040 +/* Entry in orphan dir with 'dio-' prefix */ +#define OCFS2_INODE_DIO_ORPHAN_ENTRY 0x00000080 static inline struct ocfs2_inode_info *OCFS2_I(struct inode *inode) { diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index ff82b28..13534f4 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -1090,7 +1090,7 @@ int ocfs2_journal_load(struct ocfs2_journal *journal, int local, int replayed) /* Launch the commit thread */ if (!local) { osb->commit_task = kthread_run(ocfs2_commit_thread, osb, - "ocfs2cmt"); + "ocfs2cmt-%s", osb->uuid_str); if (IS_ERR(osb->commit_task)) { status = PTR_ERR(osb->commit_task); osb->commit_task = NULL; @@ -1507,7 +1507,7 @@ void ocfs2_recovery_thread(struct ocfs2_super *osb, int node_num) goto out; osb->recovery_thread_task = kthread_run(__ocfs2_recovery_thread, osb, - "ocfs2rec"); + "ocfs2rec-%s", osb->uuid_str); if (IS_ERR(osb->recovery_thread_task)) { mlog_errno((int)PTR_ERR(osb->recovery_thread_task)); osb->recovery_thread_task = NULL; @@ -2021,6 +2021,7 @@ struct ocfs2_orphan_filldir_priv { struct dir_context ctx; struct inode *head; struct ocfs2_super *osb; + enum ocfs2_orphan_reco_type orphan_reco_type; }; static int ocfs2_orphan_filldir(struct dir_context *ctx, const char *name, @@ -2036,12 +2037,22 @@ static int ocfs2_orphan_filldir(struct dir_context *ctx, const char *name, if (name_len == 2 && !strncmp("..", name, 2)) return 0; + /* do not include dio entry in case of orphan scan */ + if ((p->orphan_reco_type == ORPHAN_NO_NEED_TRUNCATE) && + (!strncmp(name, OCFS2_DIO_ORPHAN_PREFIX, + OCFS2_DIO_ORPHAN_PREFIX_LEN))) + return 0; + /* Skip bad inodes so that recovery can continue */ iter = ocfs2_iget(p->osb, ino, OCFS2_FI_FLAG_ORPHAN_RECOVERY, 0); if (IS_ERR(iter)) return 0; + if (!strncmp(name, OCFS2_DIO_ORPHAN_PREFIX, + OCFS2_DIO_ORPHAN_PREFIX_LEN)) + OCFS2_I(iter)->ip_flags |= OCFS2_INODE_DIO_ORPHAN_ENTRY; + /* Skip inodes which are already added to recover list, since dio may * happen concurrently with unlink/rename */ if (OCFS2_I(iter)->ip_next_orphan) { @@ -2060,14 +2071,16 @@ static int ocfs2_orphan_filldir(struct dir_context *ctx, const char *name, static int ocfs2_queue_orphans(struct ocfs2_super *osb, int slot, - struct inode **head) + struct inode **head, + enum ocfs2_orphan_reco_type orphan_reco_type) { int status; struct inode *orphan_dir_inode = NULL; struct ocfs2_orphan_filldir_priv priv = { .ctx.actor = ocfs2_orphan_filldir, .osb = osb, - .head = *head + .head = *head, + .orphan_reco_type = orphan_reco_type }; orphan_dir_inode = ocfs2_get_system_file_inode(osb, @@ -2170,7 +2183,7 @@ static int ocfs2_recover_orphans(struct ocfs2_super *osb, trace_ocfs2_recover_orphans(slot); ocfs2_mark_recovering_orphan_dir(osb, slot); - ret = ocfs2_queue_orphans(osb, slot, &inode); + ret = ocfs2_queue_orphans(osb, slot, &inode, orphan_reco_type); ocfs2_clear_recovering_orphan_dir(osb, slot); /* Error here should be noted, but we want to continue with as @@ -2186,25 +2199,51 @@ static int ocfs2_recover_orphans(struct ocfs2_super *osb, iter = oi->ip_next_orphan; oi->ip_next_orphan = NULL; - mutex_lock(&inode->i_mutex); - ret = ocfs2_rw_lock(inode, 1); - if (ret < 0) { - mlog_errno(ret); - goto next; - } - /* - * We need to take and drop the inode lock to - * force read inode from disk. - */ - ret = ocfs2_inode_lock(inode, &di_bh, 1); - if (ret) { - mlog_errno(ret); - goto unlock_rw; - } + if (oi->ip_flags & OCFS2_INODE_DIO_ORPHAN_ENTRY) { + mutex_lock(&inode->i_mutex); + ret = ocfs2_rw_lock(inode, 1); + if (ret < 0) { + mlog_errno(ret); + goto unlock_mutex; + } + /* + * We need to take and drop the inode lock to + * force read inode from disk. + */ + ret = ocfs2_inode_lock(inode, &di_bh, 1); + if (ret) { + mlog_errno(ret); + goto unlock_rw; + } - di = (struct ocfs2_dinode *)di_bh->b_data; + di = (struct ocfs2_dinode *)di_bh->b_data; - if (inode->i_nlink == 0) { + if (di->i_flags & cpu_to_le32(OCFS2_DIO_ORPHANED_FL)) { + ret = ocfs2_truncate_file(inode, di_bh, + i_size_read(inode)); + if (ret < 0) { + if (ret != -ENOSPC) + mlog_errno(ret); + goto unlock_inode; + } + + ret = ocfs2_del_inode_from_orphan(osb, inode, + di_bh, 0, 0); + if (ret) + mlog_errno(ret); + } +unlock_inode: + ocfs2_inode_unlock(inode, 1); + brelse(di_bh); + di_bh = NULL; +unlock_rw: + ocfs2_rw_unlock(inode, 1); +unlock_mutex: + mutex_unlock(&inode->i_mutex); + + /* clear dio flag in ocfs2_inode_info */ + oi->ip_flags &= ~OCFS2_INODE_DIO_ORPHAN_ENTRY; + } else { spin_lock(&oi->ip_lock); /* Set the proper information to get us going into * ocfs2_delete_inode. */ @@ -2212,28 +2251,6 @@ static int ocfs2_recover_orphans(struct ocfs2_super *osb, spin_unlock(&oi->ip_lock); } - if ((orphan_reco_type == ORPHAN_NEED_TRUNCATE) && - (di->i_flags & cpu_to_le32(OCFS2_DIO_ORPHANED_FL))) { - ret = ocfs2_truncate_file(inode, di_bh, - i_size_read(inode)); - if (ret < 0) { - if (ret != -ENOSPC) - mlog_errno(ret); - goto unlock_inode; - } - - ret = ocfs2_del_inode_from_orphan(osb, inode, di_bh, 0, 0); - if (ret) - mlog_errno(ret); - } /* else if ORPHAN_NO_NEED_TRUNCATE, do nothing */ -unlock_inode: - ocfs2_inode_unlock(inode, 1); - brelse(di_bh); - di_bh = NULL; -unlock_rw: - ocfs2_rw_unlock(inode, 1); -next: - mutex_unlock(&inode->i_mutex); iput(inode); inode = iter; } diff --git a/fs/ocfs2/locks.c b/fs/ocfs2/locks.c index 6b6d092..652ece4 100644 --- a/fs/ocfs2/locks.c +++ b/fs/ocfs2/locks.c @@ -66,7 +66,7 @@ static int ocfs2_do_flock(struct file *file, struct inode *inode, * level. */ - flock_lock_file_wait(file, + locks_lock_file_wait(file, &(struct file_lock){.fl_type = F_UNLCK}); ocfs2_file_unlock(file); @@ -81,7 +81,7 @@ static int ocfs2_do_flock(struct file *file, struct inode *inode, goto out; } - ret = flock_lock_file_wait(file, fl); + ret = locks_lock_file_wait(file, fl); if (ret) ocfs2_file_unlock(file); @@ -98,7 +98,7 @@ static int ocfs2_do_funlock(struct file *file, int cmd, struct file_lock *fl) mutex_lock(&fp->fp_mutex); ocfs2_file_unlock(file); - ret = flock_lock_file_wait(file, fl); + ret = locks_lock_file_wait(file, fl); mutex_unlock(&fp->fp_mutex); return ret; @@ -119,7 +119,7 @@ int ocfs2_flock(struct file *file, int cmd, struct file_lock *fl) if ((osb->s_mount_opt & OCFS2_MOUNT_LOCALFLOCKS) || ocfs2_mount_local(osb)) - return flock_lock_file_wait(file, fl); + return locks_lock_file_wait(file, fl); if (fl->fl_type == F_UNLCK) return ocfs2_do_funlock(file, cmd, fl); diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index b7dfac2..3b48ac2 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -106,8 +106,6 @@ static int ocfs2_double_lock(struct ocfs2_super *osb, static void ocfs2_double_unlock(struct inode *inode1, struct inode *inode2); /* An orphan dir name is an 8 byte value, printed as a hex string */ #define OCFS2_ORPHAN_NAMELEN ((int)(2 * sizeof(u64))) -#define OCFS2_DIO_ORPHAN_PREFIX "dio-" -#define OCFS2_DIO_ORPHAN_PREFIX_LEN 4 static struct dentry *ocfs2_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) @@ -657,9 +655,18 @@ static int ocfs2_mknod_locked(struct ocfs2_super *osb, return status; } - return __ocfs2_mknod_locked(dir, inode, dev, new_fe_bh, + status = __ocfs2_mknod_locked(dir, inode, dev, new_fe_bh, parent_fe_bh, handle, inode_ac, fe_blkno, suballoc_loc, suballoc_bit); + if (status < 0) { + u64 bg_blkno = ocfs2_which_suballoc_group(fe_blkno, suballoc_bit); + int tmp = ocfs2_free_suballoc_bits(handle, inode_ac->ac_inode, + inode_ac->ac_bh, suballoc_bit, bg_blkno, 1); + if (tmp) + mlog_errno(tmp); + } + + return status; } static int ocfs2_mkdir(struct inode *dir, diff --git a/fs/ocfs2/namei.h b/fs/ocfs2/namei.h index e173329..1155918 100644 --- a/fs/ocfs2/namei.h +++ b/fs/ocfs2/namei.h @@ -26,6 +26,9 @@ #ifndef OCFS2_NAMEI_H #define OCFS2_NAMEI_H +#define OCFS2_DIO_ORPHAN_PREFIX "dio-" +#define OCFS2_DIO_ORPHAN_PREFIX_LEN 4 + extern const struct inode_operations ocfs2_dir_iops; struct dentry *ocfs2_get_parent(struct dentry *child); diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index e5d57cd..2521198 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -2920,16 +2920,13 @@ int ocfs2_duplicate_clusters_by_page(handle_t *handle, u64 new_block = ocfs2_clusters_to_blocks(sb, new_cluster); struct page *page; pgoff_t page_index; - unsigned int from, to, readahead_pages; + unsigned int from, to; loff_t offset, end, map_end; struct address_space *mapping = inode->i_mapping; trace_ocfs2_duplicate_clusters_by_page(cpos, old_cluster, new_cluster, new_len); - readahead_pages = - (ocfs2_cow_contig_clusters(sb) << - OCFS2_SB(sb)->s_clustersize_bits) >> PAGE_CACHE_SHIFT; offset = ((loff_t)cpos) << OCFS2_SB(sb)->s_clustersize_bits; end = offset + (new_len << OCFS2_SB(sb)->s_clustersize_bits); /* diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c index d83d260..fc6d25f 100644 --- a/fs/ocfs2/suballoc.c +++ b/fs/ocfs2/suballoc.c @@ -1920,7 +1920,10 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_alloc_context *ac, status = ocfs2_search_chain(ac, handle, bits_wanted, min_bits, res, &bits_left); if (!status) { - hint = ocfs2_group_from_res(res); + if (ocfs2_is_cluster_bitmap(ac->ac_inode)) + hint = res->sr_bg_blkno; + else + hint = ocfs2_group_from_res(res); goto set_hint; } if (status < 0 && status != -ENOSPC) { diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index 84d693d..871fcb6 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -81,11 +81,11 @@ static int ovl_copy_up_data(struct path *old, struct path *new, loff_t len) if (len == 0) return 0; - old_file = ovl_path_open(old, O_RDONLY); + old_file = ovl_path_open(old, O_LARGEFILE | O_RDONLY); if (IS_ERR(old_file)) return PTR_ERR(old_file); - new_file = ovl_path_open(new, O_WRONLY); + new_file = ovl_path_open(new, O_LARGEFILE | O_WRONLY); if (IS_ERR(new_file)) { error = PTR_ERR(new_file); goto out_fput; @@ -267,7 +267,7 @@ out: out_cleanup: ovl_cleanup(wdir, newdentry); - goto out; + goto out2; } /* diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index d9da5a4..ec0c2a050 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -363,6 +363,9 @@ struct inode *ovl_d_select_inode(struct dentry *dentry, unsigned file_flags) ovl_path_upper(dentry, &realpath); } + if (realpath.dentry->d_flags & DCACHE_OP_SELECT_INODE) + return realpath.dentry->d_op->d_select_inode(realpath.dentry, file_flags); + return d_backing_inode(realpath.dentry); } diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 79073d6..e38ee0f 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -544,6 +544,7 @@ static void ovl_put_super(struct super_block *sb) mntput(ufs->upper_mnt); for (i = 0; i < ufs->numlower; i++) mntput(ufs->lower_mnt[i]); + kfree(ufs->lower_mnt); kfree(ufs->config.lowerdir); kfree(ufs->config.upperdir); @@ -1048,6 +1049,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) oe->lowerstack[i].dentry = stack[i].dentry; oe->lowerstack[i].mnt = ufs->lower_mnt[i]; } + kfree(stack); root_dentry->d_fsdata = oe; @@ -366,18 +366,17 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) int offset = buf->offset + buf->len; if (ops->can_merge && offset + chars <= PAGE_SIZE) { - int error = ops->confirm(pipe, buf); - if (error) + ret = ops->confirm(pipe, buf); + if (ret) goto out; ret = copy_page_from_iter(buf->page, offset, chars, from); if (unlikely(ret < chars)) { - error = -EFAULT; + ret = -EFAULT; goto out; } do_wakeup = 1; - buf->len += chars; - ret = chars; + buf->len += ret; if (!iov_iter_count(from)) goto out; } @@ -693,17 +692,20 @@ int create_pipe_files(struct file **res, int flags) d_instantiate(path.dentry, inode); - err = -ENFILE; f = alloc_file(&path, FMODE_WRITE, &pipefifo_fops); - if (IS_ERR(f)) + if (IS_ERR(f)) { + err = PTR_ERR(f); goto err_dentry; + } f->f_flags = O_WRONLY | (flags & (O_NONBLOCK | O_DIRECT)); f->private_data = inode->i_pipe; res[0] = alloc_file(&path, FMODE_READ, &pipefifo_fops); - if (IS_ERR(res[0])) + if (IS_ERR(res[0])) { + err = PTR_ERR(res[0]); goto err_file; + } path_get(&path); res[0]->private_data = inode->i_pipe; diff --git a/fs/proc/array.c b/fs/proc/array.c index f60f012..d73291f 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -91,18 +91,18 @@ static inline void task_name(struct seq_file *m, struct task_struct *p) { char *buf; + size_t size; char tcomm[sizeof(p->comm)]; + int ret; get_task_comm(tcomm, p); seq_puts(m, "Name:\t"); - buf = m->buf + m->count; - /* Ignore error for now */ - buf += string_escape_str(tcomm, buf, m->size - m->count, - ESCAPE_SPACE | ESCAPE_SPECIAL, "\n\\"); + size = seq_get_buf(m, &buf); + ret = string_escape_str(tcomm, buf, size, ESCAPE_SPACE | ESCAPE_SPECIAL, "\n\\"); + seq_commit(m, ret < size ? ret : -1); - m->count = buf - m->buf; seq_putc(m, '\n'); } @@ -375,7 +375,7 @@ int proc_pid_status(struct seq_file *m, struct pid_namespace *ns, static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task, int whole) { - unsigned long vsize, eip, esp, wchan = ~0UL; + unsigned long vsize, eip, esp, wchan = 0; int priority, nice; int tty_pgrp = -1, tty_nr = 0; sigset_t sigign, sigcatch; @@ -507,7 +507,19 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, seq_put_decimal_ull(m, ' ', task->blocked.sig[0] & 0x7fffffffUL); seq_put_decimal_ull(m, ' ', sigign.sig[0] & 0x7fffffffUL); seq_put_decimal_ull(m, ' ', sigcatch.sig[0] & 0x7fffffffUL); - seq_put_decimal_ull(m, ' ', wchan); + + /* + * We used to output the absolute kernel address, but that's an + * information leak - so instead we show a 0/1 flag here, to signal + * to user-space whether there's a wchan field in /proc/PID/wchan. + * + * This works with older implementations of procps as well. + */ + if (wchan) + seq_puts(m, " 1"); + else + seq_puts(m, " 0"); + seq_put_decimal_ull(m, ' ', 0); seq_put_decimal_ull(m, ' ', 0); seq_put_decimal_ll(m, ' ', task->exit_signal); diff --git a/fs/proc/base.c b/fs/proc/base.c index b25eee4..bd3e9e6 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -430,13 +430,10 @@ static int proc_pid_wchan(struct seq_file *m, struct pid_namespace *ns, wchan = get_wchan(task); - if (lookup_symbol_name(wchan, symname) < 0) { - if (!ptrace_may_access(task, PTRACE_MODE_READ)) - return 0; - seq_printf(m, "%lu", wchan); - } else { + if (wchan && ptrace_may_access(task, PTRACE_MODE_READ) && !lookup_symbol_name(wchan, symname)) seq_printf(m, "%s", symname); - } + else + seq_putc(m, '0'); return 0; } @@ -1035,6 +1032,16 @@ static ssize_t oom_adj_read(struct file *file, char __user *buf, size_t count, return simple_read_from_buffer(buf, count, ppos, buffer, len); } +/* + * /proc/pid/oom_adj exists solely for backwards compatibility with previous + * kernels. The effective policy is defined by oom_score_adj, which has a + * different scale: oom_adj grew exponentially and oom_score_adj grows linearly. + * Values written to oom_adj are simply mapped linearly to oom_score_adj. + * Processes that become oom disabled via oom_adj will still be oom disabled + * with this implementation. + * + * oom_adj cannot be removed since existing userspace binaries use it. + */ static ssize_t oom_adj_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { diff --git a/fs/proc/fd.c b/fs/proc/fd.c index 6e5fcd0..3c2a915 100644 --- a/fs/proc/fd.c +++ b/fs/proc/fd.c @@ -291,11 +291,19 @@ static struct dentry *proc_lookupfd(struct inode *dir, struct dentry *dentry, */ int proc_fd_permission(struct inode *inode, int mask) { - int rv = generic_permission(inode, mask); + struct task_struct *p; + int rv; + + rv = generic_permission(inode, mask); if (rv == 0) - return 0; - if (task_tgid(current) == proc_pid(inode)) + return rv; + + rcu_read_lock(); + p = pid_task(proc_pid(inode), PIDTYPE_PID); + if (p && same_thread_group(p, current)) rv = 0; + rcu_read_unlock(); + return rv; } diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index d3ebf2e..9155a5a 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -27,7 +27,6 @@ static int meminfo_proc_show(struct seq_file *m, void *v) { struct sysinfo i; unsigned long committed; - struct vmalloc_info vmi; long cached; long available; unsigned long pagecache; @@ -49,8 +48,6 @@ static int meminfo_proc_show(struct seq_file *m, void *v) if (cached < 0) cached = 0; - get_vmalloc_info(&vmi); - for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++) pages[lru] = global_page_state(NR_LRU_BASE + lru); @@ -191,8 +188,8 @@ static int meminfo_proc_show(struct seq_file *m, void *v) K(vm_commit_limit()), K(committed), (unsigned long)VMALLOC_TOTAL >> 10, - vmi.used >> 10, - vmi.largest_chunk >> 10 + 0ul, // used to be vmalloc 'used' + 0ul // used to be vmalloc 'largest_chunk' #ifdef CONFIG_MEMORY_FAILURE , atomic_long_read(&num_poisoned_pages) << (PAGE_SHIFT - 10) #endif diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index fdda62e..fe5b6e6 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -948,7 +948,7 @@ static struct ctl_dir *get_subdir(struct ctl_dir *dir, found: subdir->header.nreg++; failed: - if (unlikely(IS_ERR(subdir))) { + if (IS_ERR(subdir)) { pr_err("sysctl could not get directory: "); sysctl_print_dir(dir); pr_cont("/%*.*s %ld\n", diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index e2d46ad..187b3b5 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -70,6 +70,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) ptes >> 10, pmds >> 10, swap << (PAGE_SHIFT-10)); + hugetlb_report_usage(m, mm); } unsigned long task_vsize(struct mm_struct *mm) @@ -446,6 +447,8 @@ struct mem_size_stats { unsigned long anonymous; unsigned long anonymous_thp; unsigned long swap; + unsigned long shared_hugetlb; + unsigned long private_hugetlb; u64 pss; u64 swap_pss; }; @@ -625,12 +628,44 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma) seq_putc(m, '\n'); } +#ifdef CONFIG_HUGETLB_PAGE +static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask, + unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + struct mem_size_stats *mss = walk->private; + struct vm_area_struct *vma = walk->vma; + struct page *page = NULL; + + if (pte_present(*pte)) { + page = vm_normal_page(vma, addr, *pte); + } else if (is_swap_pte(*pte)) { + swp_entry_t swpent = pte_to_swp_entry(*pte); + + if (is_migration_entry(swpent)) + page = migration_entry_to_page(swpent); + } + if (page) { + int mapcount = page_mapcount(page); + + if (mapcount >= 2) + mss->shared_hugetlb += huge_page_size(hstate_vma(vma)); + else + mss->private_hugetlb += huge_page_size(hstate_vma(vma)); + } + return 0; +} +#endif /* HUGETLB_PAGE */ + static int show_smap(struct seq_file *m, void *v, int is_pid) { struct vm_area_struct *vma = v; struct mem_size_stats mss; struct mm_walk smaps_walk = { .pmd_entry = smaps_pte_range, +#ifdef CONFIG_HUGETLB_PAGE + .hugetlb_entry = smaps_hugetlb_range, +#endif .mm = vma->vm_mm, .private = &mss, }; @@ -652,6 +687,8 @@ static int show_smap(struct seq_file *m, void *v, int is_pid) "Referenced: %8lu kB\n" "Anonymous: %8lu kB\n" "AnonHugePages: %8lu kB\n" + "Shared_Hugetlb: %8lu kB\n" + "Private_Hugetlb: %7lu kB\n" "Swap: %8lu kB\n" "SwapPss: %8lu kB\n" "KernelPageSize: %8lu kB\n" @@ -667,6 +704,8 @@ static int show_smap(struct seq_file *m, void *v, int is_pid) mss.referenced >> 10, mss.anonymous >> 10, mss.anonymous_thp >> 10, + mss.shared_hugetlb >> 10, + mss.private_hugetlb >> 10, mss.swap >> 10, (unsigned long)(mss.swap_pss >> (10 + PSS_SHIFT)), vma_kernel_pagesize(vma) >> 10, @@ -753,36 +792,37 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma, pte_t ptent = *pte; if (pte_present(ptent)) { + ptent = ptep_modify_prot_start(vma->vm_mm, addr, pte); ptent = pte_wrprotect(ptent); - ptent = pte_clear_flags(ptent, _PAGE_SOFT_DIRTY); + ptent = pte_clear_soft_dirty(ptent); + ptep_modify_prot_commit(vma->vm_mm, addr, pte, ptent); } else if (is_swap_pte(ptent)) { ptent = pte_swp_clear_soft_dirty(ptent); + set_pte_at(vma->vm_mm, addr, pte, ptent); } - - set_pte_at(vma->vm_mm, addr, pte, ptent); } +#else +static inline void clear_soft_dirty(struct vm_area_struct *vma, + unsigned long addr, pte_t *pte) +{ +} +#endif +#if defined(CONFIG_MEM_SOFT_DIRTY) && defined(CONFIG_TRANSPARENT_HUGEPAGE) static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmdp) { - pmd_t pmd = *pmdp; + pmd_t pmd = pmdp_huge_get_and_clear(vma->vm_mm, addr, pmdp); pmd = pmd_wrprotect(pmd); - pmd = pmd_clear_flags(pmd, _PAGE_SOFT_DIRTY); + pmd = pmd_clear_soft_dirty(pmd); if (vma->vm_flags & VM_SOFTDIRTY) vma->vm_flags &= ~VM_SOFTDIRTY; set_pmd_at(vma->vm_mm, addr, pmdp, pmd); } - #else - -static inline void clear_soft_dirty(struct vm_area_struct *vma, - unsigned long addr, pte_t *pte) -{ -} - static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmdp) { diff --git a/fs/pstore/Kconfig b/fs/pstore/Kconfig index 916b8e2..360ae43 100644 --- a/fs/pstore/Kconfig +++ b/fs/pstore/Kconfig @@ -1,5 +1,5 @@ config PSTORE - bool "Persistent store support" + tristate "Persistent store support" default n select ZLIB_DEFLATE select ZLIB_INFLATE diff --git a/fs/pstore/Makefile b/fs/pstore/Makefile index e647d8e..b8803cc 100644 --- a/fs/pstore/Makefile +++ b/fs/pstore/Makefile @@ -2,12 +2,12 @@ # Makefile for the linux pstorefs routines. # -obj-y += pstore.o +obj-$(CONFIG_PSTORE) += pstore.o pstore-objs += inode.o platform.o -obj-$(CONFIG_PSTORE_FTRACE) += ftrace.o +pstore-$(CONFIG_PSTORE_FTRACE) += ftrace.o -obj-$(CONFIG_PSTORE_PMSG) += pmsg.o +pstore-$(CONFIG_PSTORE_PMSG) += pmsg.o ramoops-objs += ram.o ram_core.o obj-$(CONFIG_PSTORE_RAM) += ramoops.o diff --git a/fs/pstore/ftrace.c b/fs/pstore/ftrace.c index 76a4eeb..d488770 100644 --- a/fs/pstore/ftrace.c +++ b/fs/pstore/ftrace.c @@ -104,22 +104,23 @@ static const struct file_operations pstore_knob_fops = { .write = pstore_ftrace_knob_write, }; +static struct dentry *pstore_ftrace_dir; + void pstore_register_ftrace(void) { - struct dentry *dir; struct dentry *file; if (!psinfo->write_buf) return; - dir = debugfs_create_dir("pstore", NULL); - if (!dir) { + pstore_ftrace_dir = debugfs_create_dir("pstore", NULL); + if (!pstore_ftrace_dir) { pr_err("%s: unable to create pstore directory\n", __func__); return; } - file = debugfs_create_file("record_ftrace", 0600, dir, NULL, - &pstore_knob_fops); + file = debugfs_create_file("record_ftrace", 0600, pstore_ftrace_dir, + NULL, &pstore_knob_fops); if (!file) { pr_err("%s: unable to create record_ftrace file\n", __func__); goto err_file; @@ -127,5 +128,17 @@ void pstore_register_ftrace(void) return; err_file: - debugfs_remove(dir); + debugfs_remove(pstore_ftrace_dir); +} + +void pstore_unregister_ftrace(void) +{ + mutex_lock(&pstore_ftrace_lock); + if (pstore_ftrace_enabled) { + unregister_ftrace_function(&pstore_ftrace_ops); + pstore_ftrace_enabled = 0; + } + mutex_unlock(&pstore_ftrace_lock); + + debugfs_remove_recursive(pstore_ftrace_dir); } diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c index 3adcc46..d8c439d 100644 --- a/fs/pstore/inode.c +++ b/fs/pstore/inode.c @@ -178,6 +178,7 @@ static loff_t pstore_file_llseek(struct file *file, loff_t off, int whence) } static const struct file_operations pstore_file_operations = { + .owner = THIS_MODULE, .open = pstore_file_open, .read = pstore_file_read, .llseek = pstore_file_llseek, @@ -287,7 +288,7 @@ static const struct super_operations pstore_ops = { static struct super_block *pstore_sb; -int pstore_is_mounted(void) +bool pstore_is_mounted(void) { return pstore_sb != NULL; } @@ -456,6 +457,7 @@ static void pstore_kill_sb(struct super_block *sb) } static struct file_system_type pstore_fs_type = { + .owner = THIS_MODULE, .name = "pstore", .mount = pstore_mount, .kill_sb = pstore_kill_sb, @@ -479,5 +481,12 @@ out: } module_init(init_pstore_fs) +static void __exit exit_pstore_fs(void) +{ + unregister_filesystem(&pstore_fs_type); + sysfs_remove_mount_point(fs_kobj, "pstore"); +} +module_exit(exit_pstore_fs) + MODULE_AUTHOR("Tony Luck <tony.luck@intel.com>"); MODULE_LICENSE("GPL"); diff --git a/fs/pstore/internal.h b/fs/pstore/internal.h index c36ba2c..e38a22b 100644 --- a/fs/pstore/internal.h +++ b/fs/pstore/internal.h @@ -41,14 +41,18 @@ pstore_ftrace_decode_cpu(struct pstore_ftrace_record *rec) #ifdef CONFIG_PSTORE_FTRACE extern void pstore_register_ftrace(void); +extern void pstore_unregister_ftrace(void); #else static inline void pstore_register_ftrace(void) {} +static inline void pstore_unregister_ftrace(void) {} #endif #ifdef CONFIG_PSTORE_PMSG extern void pstore_register_pmsg(void); +extern void pstore_unregister_pmsg(void); #else static inline void pstore_register_pmsg(void) {} +static inline void pstore_unregister_pmsg(void) {} #endif extern struct pstore_info *psinfo; @@ -59,6 +63,6 @@ extern int pstore_mkfile(enum pstore_type_id, char *psname, u64 id, int count, char *data, bool compressed, size_t size, struct timespec time, struct pstore_info *psi); -extern int pstore_is_mounted(void); +extern bool pstore_is_mounted(void); #endif diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index 791743d..588461b 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -237,6 +237,14 @@ static void allocate_buf_for_compression(void) } +static void free_buf_for_compression(void) +{ + kfree(stream.workspace); + stream.workspace = NULL; + kfree(big_oops_buf); + big_oops_buf = NULL; +} + /* * Called when compression fails, since the printk buffer * would be fetched for compression calling it again when @@ -353,6 +361,19 @@ static struct kmsg_dumper pstore_dumper = { .dump = pstore_dump, }; +/* + * Register with kmsg_dump to save last part of console log on panic. + */ +static void pstore_register_kmsg(void) +{ + kmsg_dump_register(&pstore_dumper); +} + +static void pstore_unregister_kmsg(void) +{ + kmsg_dump_unregister(&pstore_dumper); +} + #ifdef CONFIG_PSTORE_CONSOLE static void pstore_console_write(struct console *con, const char *s, unsigned c) { @@ -390,8 +411,14 @@ static void pstore_register_console(void) { register_console(&pstore_console); } + +static void pstore_unregister_console(void) +{ + unregister_console(&pstore_console); +} #else static void pstore_register_console(void) {} +static void pstore_unregister_console(void) {} #endif static int pstore_write_compat(enum pstore_type_id type, @@ -410,8 +437,6 @@ static int pstore_write_compat(enum pstore_type_id type, * read function right away to populate the file system. If not * then the pstore mount code will call us later to fill out * the file system. - * - * Register with kmsg_dump to save last part of console log on panic. */ int pstore_register(struct pstore_info *psi) { @@ -442,7 +467,7 @@ int pstore_register(struct pstore_info *psi) if (pstore_is_mounted()) pstore_get_records(0); - kmsg_dump_register(&pstore_dumper); + pstore_register_kmsg(); if ((psi->flags & PSTORE_FLAGS_FRAGILE) == 0) { pstore_register_console(); @@ -462,12 +487,28 @@ int pstore_register(struct pstore_info *psi) */ backend = psi->name; + module_put(owner); + pr_info("Registered %s as persistent store backend\n", psi->name); return 0; } EXPORT_SYMBOL_GPL(pstore_register); +void pstore_unregister(struct pstore_info *psi) +{ + pstore_unregister_pmsg(); + pstore_unregister_ftrace(); + pstore_unregister_console(); + pstore_unregister_kmsg(); + + free_buf_for_compression(); + + psinfo = NULL; + backend = NULL; +} +EXPORT_SYMBOL_GPL(pstore_unregister); + /* * Read all the records from the persistent store. Create * files in our filesystem. Don't warn about -EEXIST errors diff --git a/fs/pstore/pmsg.c b/fs/pstore/pmsg.c index feb5dd2..7de20cd 100644 --- a/fs/pstore/pmsg.c +++ b/fs/pstore/pmsg.c @@ -37,6 +37,8 @@ static ssize_t write_pmsg(struct file *file, const char __user *buf, if (buffer_size > PMSG_MAX_BOUNCE_BUFFER_SIZE) buffer_size = PMSG_MAX_BOUNCE_BUFFER_SIZE; buffer = vmalloc(buffer_size); + if (!buffer) + return -ENOMEM; mutex_lock(&pmsg_lock); for (i = 0; i < count; ) { @@ -112,3 +114,10 @@ err_class: err: return; } + +void pstore_unregister_pmsg(void) +{ + device_destroy(pmsg_class, MKDEV(pmsg_major, 0)); + class_destroy(pmsg_class); + unregister_chrdev(pmsg_major, PMSG_NAME); +} diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index 6c26c4d..319c3a6 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -578,30 +578,27 @@ fail_out: return err; } -static int __exit ramoops_remove(struct platform_device *pdev) +static int ramoops_remove(struct platform_device *pdev) { -#if 0 - /* TODO(kees): We cannot unload ramoops since pstore doesn't support - * unregistering yet. - */ struct ramoops_context *cxt = &oops_cxt; - iounmap(cxt->virt_addr); - release_mem_region(cxt->phys_addr, cxt->size); + pstore_unregister(&cxt->pstore); cxt->max_dump_cnt = 0; - /* TODO(kees): When pstore supports unregistering, call it here. */ kfree(cxt->pstore.buf); cxt->pstore.bufsize = 0; + persistent_ram_free(cxt->mprz); + persistent_ram_free(cxt->fprz); + persistent_ram_free(cxt->cprz); + ramoops_free_przs(cxt); + return 0; -#endif - return -EBUSY; } static struct platform_driver ramoops_driver = { .probe = ramoops_probe, - .remove = __exit_p(ramoops_remove), + .remove = ramoops_remove, .driver = { .name = "ramoops", }, diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c index ba1323a..a586467 100644 --- a/fs/ramfs/file-nommu.c +++ b/fs/ramfs/file-nommu.c @@ -70,6 +70,7 @@ int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize) unsigned order; void *data; int ret; + gfp_t gfp = mapping_gfp_mask(inode->i_mapping); /* make various checks */ order = get_order(newsize); @@ -84,7 +85,7 @@ int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize) /* allocate enough contiguous pages to be able to satisfy the * request */ - pages = alloc_pages(mapping_gfp_mask(inode->i_mapping), order); + pages = alloc_pages(gfp, order); if (!pages) return -ENOMEM; @@ -108,7 +109,7 @@ int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize) struct page *page = pages + loop; ret = add_to_page_cache_lru(page, inode->i_mapping, loop, - GFP_KERNEL); + gfp); if (ret < 0) goto add_error; diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c index 5f1c9c2..47f9698 100644 --- a/fs/reiserfs/namei.c +++ b/fs/reiserfs/namei.c @@ -712,9 +712,6 @@ static int reiserfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode 2 * (REISERFS_QUOTA_INIT_BLOCKS(dir->i_sb) + REISERFS_QUOTA_TRANS_BLOCKS(dir->i_sb)); - if (!new_valid_dev(rdev)) - return -EINVAL; - retval = dquot_initialize(dir); if (retval) return retval; diff --git a/fs/seq_file.c b/fs/seq_file.c index 225586e..e85664b 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -13,6 +13,7 @@ #include <linux/cred.h> #include <linux/mm.h> #include <linux/printk.h> +#include <linux/string_helpers.h> #include <asm/uaccess.h> #include <asm/page.h> @@ -25,12 +26,17 @@ static void seq_set_overflow(struct seq_file *m) static void *seq_buf_alloc(unsigned long size) { void *buf; + gfp_t gfp = GFP_KERNEL; /* - * __GFP_NORETRY to avoid oom-killings with high-order allocations - - * it's better to fall back to vmalloc() than to kill things. + * For high order allocations, use __GFP_NORETRY to avoid oom-killing - + * it's better to fall back to vmalloc() than to kill things. For small + * allocations, just use GFP_KERNEL which will oom kill, thus no need + * for vmalloc fallback. */ - buf = kmalloc(size, GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN); + if (size > PAGE_SIZE) + gfp |= __GFP_NORETRY | __GFP_NOWARN; + buf = kmalloc(size, gfp); if (!buf && size > PAGE_SIZE) buf = vmalloc(size); return buf; @@ -377,26 +383,12 @@ EXPORT_SYMBOL(seq_release); */ void seq_escape(struct seq_file *m, const char *s, const char *esc) { - char *end = m->buf + m->size; - char *p; - char c; + char *buf; + size_t size = seq_get_buf(m, &buf); + int ret; - for (p = m->buf + m->count; (c = *s) != '\0' && p < end; s++) { - if (!strchr(esc, c)) { - *p++ = c; - continue; - } - if (p + 3 < end) { - *p++ = '\\'; - *p++ = '0' + ((c & 0300) >> 6); - *p++ = '0' + ((c & 070) >> 3); - *p++ = '0' + (c & 07); - continue; - } - seq_set_overflow(m); - return; - } - m->count = p - m->buf; + ret = string_escape_str(s, buf, size, ESCAPE_OCTAL, esc); + seq_commit(m, ret < size ? ret : -1); } EXPORT_SYMBOL(seq_escape); @@ -773,6 +765,8 @@ void seq_hex_dump(struct seq_file *m, const char *prefix_str, int prefix_type, { const u8 *ptr = buf; int i, linelen, remaining = len; + char *buffer; + size_t size; int ret; if (rowsize != 16 && rowsize != 32) @@ -794,15 +788,12 @@ void seq_hex_dump(struct seq_file *m, const char *prefix_str, int prefix_type, break; } + size = seq_get_buf(m, &buffer); ret = hex_dump_to_buffer(ptr + i, linelen, rowsize, groupsize, - m->buf + m->count, m->size - m->count, - ascii); - if (ret >= m->size - m->count) { - seq_set_overflow(m); - } else { - m->count += ret; - seq_putc(m, '\n'); - } + buffer, size, ascii); + seq_commit(m, ret < size ? ret : -1); + + seq_putc(m, '\n'); } } EXPORT_SYMBOL(seq_hex_dump); diff --git a/fs/splice.c b/fs/splice.c index 5fc1e50..801c21c 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -360,7 +360,7 @@ __generic_file_splice_read(struct file *in, loff_t *ppos, break; error = add_to_page_cache_lru(page, mapping, index, - GFP_KERNEL & mapping_gfp_mask(mapping)); + mapping_gfp_constraint(mapping, GFP_KERNEL)); if (unlikely(error)) { page_cache_release(page); if (error == -EEXIST) @@ -367,8 +367,6 @@ static long cp_new_stat64(struct kstat *stat, struct stat64 __user *statbuf) INIT_STRUCT_STAT64_PADDING(tmp); #ifdef CONFIG_MIPS /* mips has weird padding, so we don't get 64 bits there */ - if (!new_valid_dev(stat->dev) || !new_valid_dev(stat->rdev)) - return -EOVERFLOW; tmp.st_dev = new_encode_dev(stat->dev); tmp.st_rdev = new_encode_dev(stat->rdev); #else @@ -86,7 +86,12 @@ static void fdatawrite_one_bdev(struct block_device *bdev, void *arg) static void fdatawait_one_bdev(struct block_device *bdev, void *arg) { - filemap_fdatawait(bdev->bd_inode->i_mapping); + /* + * We keep the error status of individual mapping so that + * applications can catch the writeback error using fsync(2). + * See filemap_fdatawait_keep_errors() for details. + */ + filemap_fdatawait_keep_errors(bdev->bd_inode->i_mapping); } /* @@ -343,7 +348,8 @@ SYSCALL_DEFINE4(sync_file_range, int, fd, loff_t, offset, loff_t, nbytes, } if (flags & SYNC_FILE_RANGE_WRITE) { - ret = filemap_fdatawrite_range(mapping, offset, endbyte); + ret = __filemap_fdatawrite_range(mapping, offset, endbyte, + WB_SYNC_NONE); if (ret < 0) goto out_put; } diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index 6c95628..f35523d 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -108,6 +108,7 @@ static ssize_t sysfs_kf_read(struct kernfs_open_file *of, char *buf, { const struct sysfs_ops *ops = sysfs_file_ops(of->kn); struct kobject *kobj = of->kn->parent->priv; + size_t len; /* * If buf != of->prealloc_buf, we don't know how @@ -115,7 +116,8 @@ static ssize_t sysfs_kf_read(struct kernfs_open_file *of, char *buf, */ if (pos || WARN_ON_ONCE(buf != of->prealloc_buf)) return 0; - return ops->show(kobj, of->kn->priv, buf); + len = ops->show(kobj, of->kn->priv, buf); + return min(count, len); } /* kernfs write callback for regular sysfs files */ diff --git a/fs/sysfs/group.c b/fs/sysfs/group.c index 39a0199..e123659 100644 --- a/fs/sysfs/group.c +++ b/fs/sysfs/group.c @@ -352,3 +352,47 @@ void sysfs_remove_link_from_group(struct kobject *kobj, const char *group_name, } } EXPORT_SYMBOL_GPL(sysfs_remove_link_from_group); + +/** + * __compat_only_sysfs_link_entry_to_kobj - add a symlink to a kobject pointing + * to a group or an attribute + * @kobj: The kobject containing the group. + * @target_kobj: The target kobject. + * @target_name: The name of the target group or attribute. + */ +int __compat_only_sysfs_link_entry_to_kobj(struct kobject *kobj, + struct kobject *target_kobj, + const char *target_name) +{ + struct kernfs_node *target; + struct kernfs_node *entry; + struct kernfs_node *link; + + /* + * We don't own @target_kobj and it may be removed at any time. + * Synchronize using sysfs_symlink_target_lock. See sysfs_remove_dir() + * for details. + */ + spin_lock(&sysfs_symlink_target_lock); + target = target_kobj->sd; + if (target) + kernfs_get(target); + spin_unlock(&sysfs_symlink_target_lock); + if (!target) + return -ENOENT; + + entry = kernfs_find_and_get(target_kobj->sd, target_name); + if (!entry) { + kernfs_put(target); + return -ENOENT; + } + + link = kernfs_create_link(kobj->sd, target_name, entry); + if (IS_ERR(link) && PTR_ERR(link) == -EEXIST) + sysfs_warn_dup(kobj->sd, target_name); + + kernfs_put(entry); + kernfs_put(target); + return IS_ERR(link) ? PTR_ERR(link) : 0; +} +EXPORT_SYMBOL_GPL(__compat_only_sysfs_link_entry_to_kobj); diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c index cbc8d5d..c66f242 100644 --- a/fs/tracefs/inode.c +++ b/fs/tracefs/inode.c @@ -340,8 +340,12 @@ static struct dentry *start_creating(const char *name, struct dentry *parent) dput(dentry); dentry = ERR_PTR(-EEXIST); } - if (IS_ERR(dentry)) + + if (IS_ERR(dentry)) { mutex_unlock(&parent->d_inode->i_mutex); + simple_release_fs(&tracefs_mount, &tracefs_mount_count); + } + return dentry; } diff --git a/fs/ubifs/Kconfig b/fs/ubifs/Kconfig index ba66d50..7ff7712 100644 --- a/fs/ubifs/Kconfig +++ b/fs/ubifs/Kconfig @@ -35,3 +35,18 @@ config UBIFS_FS_ZLIB default y help Zlib compresses better than LZO but it is slower. Say 'Y' if unsure. + +config UBIFS_ATIME_SUPPORT + bool "Access time support" if UBIFS_FS + depends on UBIFS_FS + default n + help + Originally UBIFS did not support atime, because it looked like a bad idea due + increased flash wear. This option adds atime support and it is disabled by default + to preserve the old behavior. If you enable this option, UBIFS starts updating atime, + which means that file-system read operations will cause writes (inode atime + updates). This may affect file-system performance and increase flash device wear, + so be careful. How often atime is updated depends on the selected strategy: + strictatime is the "heavy", relatime is "lighter", etc. + + If unsure, say 'N' diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c index 4c46a98..595ca0d 100644 --- a/fs/ubifs/debug.c +++ b/fs/ubifs/debug.c @@ -2573,7 +2573,7 @@ int dbg_leb_write(struct ubifs_info *c, int lnum, const void *buf, { int err, failing; - if (c->dbg->pc_happened) + if (dbg_is_power_cut(c)) return -EROFS; failing = power_cut_emulated(c, lnum, 1); @@ -2595,7 +2595,7 @@ int dbg_leb_change(struct ubifs_info *c, int lnum, const void *buf, { int err; - if (c->dbg->pc_happened) + if (dbg_is_power_cut(c)) return -EROFS; if (power_cut_emulated(c, lnum, 1)) return -EROFS; @@ -2611,7 +2611,7 @@ int dbg_leb_unmap(struct ubifs_info *c, int lnum) { int err; - if (c->dbg->pc_happened) + if (dbg_is_power_cut(c)) return -EROFS; if (power_cut_emulated(c, lnum, 0)) return -EROFS; @@ -2627,7 +2627,7 @@ int dbg_leb_map(struct ubifs_info *c, int lnum) { int err; - if (c->dbg->pc_happened) + if (dbg_is_power_cut(c)) return -EROFS; if (power_cut_emulated(c, lnum, 0)) return -EROFS; diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index 5c27c66..e49bd28 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -449,13 +449,14 @@ static int ubifs_readdir(struct file *file, struct dir_context *ctx) } out: + kfree(file->private_data); + file->private_data = NULL; + if (err != -ENOENT) { ubifs_err(c, "cannot find next direntry, error %d", err); return err; } - kfree(file->private_data); - file->private_data = NULL; /* 2 is a special value indicating that there are no more direntries */ ctx->pos = 2; return 0; @@ -787,9 +788,6 @@ static int ubifs_mknod(struct inode *dir, struct dentry *dentry, dbg_gen("dent '%pd' in dir ino %lu", dentry, dir->i_ino); - if (!new_valid_dev(rdev)) - return -EINVAL; - if (S_ISBLK(mode) || S_ISCHR(mode)) { dev = kmalloc(sizeof(union ubifs_dev_desc), GFP_NOFS); if (!dev) @@ -1188,6 +1186,9 @@ const struct inode_operations ubifs_dir_inode_operations = { .getxattr = ubifs_getxattr, .listxattr = ubifs_listxattr, .removexattr = ubifs_removexattr, +#ifdef CONFIG_UBIFS_ATIME_SUPPORT + .update_time = ubifs_update_time, +#endif }; const struct file_operations ubifs_dir_operations = { diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index a3dfe2a..0edc128 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -1354,6 +1354,47 @@ static inline int mctime_update_needed(const struct inode *inode, return 0; } +#ifdef CONFIG_UBIFS_ATIME_SUPPORT +/** + * ubifs_update_time - update time of inode. + * @inode: inode to update + * + * This function updates time of the inode. + */ +int ubifs_update_time(struct inode *inode, struct timespec *time, + int flags) +{ + struct ubifs_inode *ui = ubifs_inode(inode); + struct ubifs_info *c = inode->i_sb->s_fs_info; + struct ubifs_budget_req req = { .dirtied_ino = 1, + .dirtied_ino_d = ALIGN(ui->data_len, 8) }; + int iflags = I_DIRTY_TIME; + int err, release; + + err = ubifs_budget_space(c, &req); + if (err) + return err; + + mutex_lock(&ui->ui_mutex); + if (flags & S_ATIME) + inode->i_atime = *time; + if (flags & S_CTIME) + inode->i_ctime = *time; + if (flags & S_MTIME) + inode->i_mtime = *time; + + if (!(inode->i_sb->s_flags & MS_LAZYTIME)) + iflags |= I_DIRTY_SYNC; + + release = ui->dirty; + __mark_inode_dirty(inode, iflags); + mutex_unlock(&ui->ui_mutex); + if (release) + ubifs_release_budget(c, &req); + return 0; +} +#endif + /** * update_ctime - update mtime and ctime of an inode. * @inode: inode to update @@ -1537,6 +1578,9 @@ static int ubifs_file_mmap(struct file *file, struct vm_area_struct *vma) if (err) return err; vma->vm_ops = &ubifs_file_vm_ops; +#ifdef CONFIG_UBIFS_ATIME_SUPPORT + file_accessed(file); +#endif return 0; } @@ -1557,6 +1601,9 @@ const struct inode_operations ubifs_file_inode_operations = { .getxattr = ubifs_getxattr, .listxattr = ubifs_listxattr, .removexattr = ubifs_removexattr, +#ifdef CONFIG_UBIFS_ATIME_SUPPORT + .update_time = ubifs_update_time, +#endif }; const struct inode_operations ubifs_symlink_inode_operations = { @@ -1568,6 +1615,9 @@ const struct inode_operations ubifs_symlink_inode_operations = { .getxattr = ubifs_getxattr, .listxattr = ubifs_listxattr, .removexattr = ubifs_removexattr, +#ifdef CONFIG_UBIFS_ATIME_SUPPORT + .update_time = ubifs_update_time, +#endif }; const struct file_operations ubifs_file_operations = { diff --git a/fs/ubifs/lpt.c b/fs/ubifs/lpt.c index dc9f27e..9a51710 100644 --- a/fs/ubifs/lpt.c +++ b/fs/ubifs/lpt.c @@ -1498,11 +1498,10 @@ static struct ubifs_nnode *dirty_cow_nnode(struct ubifs_info *c, } /* nnode is being committed, so copy it */ - n = kmalloc(sizeof(struct ubifs_nnode), GFP_NOFS); + n = kmemdup(nnode, sizeof(struct ubifs_nnode), GFP_NOFS); if (unlikely(!n)) return ERR_PTR(-ENOMEM); - memcpy(n, nnode, sizeof(struct ubifs_nnode)); n->cnext = NULL; __set_bit(DIRTY_CNODE, &n->flags); __clear_bit(COW_CNODE, &n->flags); @@ -1549,11 +1548,10 @@ static struct ubifs_pnode *dirty_cow_pnode(struct ubifs_info *c, } /* pnode is being committed, so copy it */ - p = kmalloc(sizeof(struct ubifs_pnode), GFP_NOFS); + p = kmemdup(pnode, sizeof(struct ubifs_pnode), GFP_NOFS); if (unlikely(!p)) return ERR_PTR(-ENOMEM); - memcpy(p, pnode, sizeof(struct ubifs_pnode)); p->cnext = NULL; __set_bit(DIRTY_CNODE, &p->flags); __clear_bit(COW_CNODE, &p->flags); diff --git a/fs/ubifs/misc.h b/fs/ubifs/misc.h index ee7cb5e..8ece6ca 100644 --- a/fs/ubifs/misc.h +++ b/fs/ubifs/misc.h @@ -155,13 +155,8 @@ static inline int ubifs_wbuf_sync(struct ubifs_wbuf *wbuf) */ static inline int ubifs_encode_dev(union ubifs_dev_desc *dev, dev_t rdev) { - if (new_valid_dev(rdev)) { - dev->new = cpu_to_le32(new_encode_dev(rdev)); - return sizeof(dev->new); - } else { - dev->huge = cpu_to_le64(huge_encode_dev(rdev)); - return sizeof(dev->huge); - } + dev->new = cpu_to_le32(new_encode_dev(rdev)); + return sizeof(dev->new); } /** diff --git a/fs/ubifs/recovery.c b/fs/ubifs/recovery.c index 695fc71..586d593 100644 --- a/fs/ubifs/recovery.c +++ b/fs/ubifs/recovery.c @@ -789,7 +789,7 @@ struct ubifs_scan_leb *ubifs_recover_leb(struct ubifs_info *c, int lnum, corrupted_rescan: /* Re-scan the corrupted data with verbose messages */ ubifs_err(c, "corruption %d", ret); - ubifs_scan_a_node(c, buf, len, lnum, offs, 1); + ubifs_scan_a_node(c, buf, len, lnum, offs, 0); corrupted: ubifs_scanned_corruption(c, lnum, offs, buf); err = -EUCLEAN; @@ -1331,8 +1331,7 @@ void ubifs_destroy_size_tree(struct ubifs_info *c) struct size_entry *e, *n; rbtree_postorder_for_each_entry_safe(e, n, &c->size_tree, rb) { - if (e->inode) - iput(e->inode); + iput(e->inode); kfree(e); } @@ -1533,8 +1532,7 @@ int ubifs_recover_size(struct ubifs_info *c) err = fix_size_in_place(c, e); if (err) return err; - if (e->inode) - iput(e->inode); + iput(e->inode); } } diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 9547a278..8ee3133 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -128,7 +128,10 @@ struct inode *ubifs_iget(struct super_block *sb, unsigned long inum) if (err) goto out_ino; - inode->i_flags |= (S_NOCMTIME | S_NOATIME); + inode->i_flags |= S_NOCMTIME; +#ifndef CONFIG_UBIFS_ATIME_SUPPORT + inode->i_flags |= S_NOATIME; +#endif set_nlink(inode, le32_to_cpu(ino->nlink)); i_uid_write(inode, le32_to_cpu(ino->uid)); i_gid_write(inode, le32_to_cpu(ino->gid)); @@ -2139,7 +2142,12 @@ static struct dentry *ubifs_mount(struct file_system_type *fs_type, int flags, if (err) goto out_deact; /* We do not support atime */ - sb->s_flags |= MS_ACTIVE | MS_NOATIME; + sb->s_flags |= MS_ACTIVE; +#ifndef CONFIG_UBIFS_ATIME_SUPPORT + sb->s_flags |= MS_NOATIME; +#else + ubifs_msg(c, "full atime support is enabled."); +#endif } /* 'fill_super()' opens ubi again so we must close it here */ diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c index 957f575..fa9a20c 100644 --- a/fs/ubifs/tnc.c +++ b/fs/ubifs/tnc.c @@ -198,11 +198,10 @@ static struct ubifs_znode *copy_znode(struct ubifs_info *c, { struct ubifs_znode *zn; - zn = kmalloc(c->max_znode_sz, GFP_NOFS); + zn = kmemdup(znode, c->max_znode_sz, GFP_NOFS); if (unlikely(!zn)) return ERR_PTR(-ENOMEM); - memcpy(zn, znode, c->max_znode_sz); zn->cnext = NULL; __set_bit(DIRTY_ZNODE, &zn->flags); __clear_bit(COW_ZNODE, &zn->flags); diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index de75902..01142e1 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -858,9 +858,9 @@ struct ubifs_compressor { * @mod_dent: non-zero if the operation removes or modifies an existing * directory entry * @new_ino: non-zero if the operation adds a new inode - * @new_ino_d: now much data newly created inode contains + * @new_ino_d: how much data newly created inode contains * @dirtied_ino: how many inodes the operation makes dirty - * @dirtied_ino_d: now much data dirtied inode contains + * @dirtied_ino_d: how much data dirtied inode contains * @idx_growth: how much the index will supposedly grow * @data_growth: how much new data the operation will supposedly add * @dd_growth: how much data that makes other data dirty the operation will @@ -1746,6 +1746,9 @@ int ubifs_calc_dark(const struct ubifs_info *c, int spc); /* file.c */ int ubifs_fsync(struct file *file, loff_t start, loff_t end, int datasync); int ubifs_setattr(struct dentry *dentry, struct iattr *attr); +#ifdef CONFIG_UBIFS_ATIME_SUPPORT +int ubifs_update_time(struct inode *inode, struct timespec *time, int flags); +#endif /* dir.c */ struct inode *ubifs_new_inode(struct ubifs_info *c, const struct inode *dir, diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c index 96f3448..259fbab 100644 --- a/fs/ubifs/xattr.c +++ b/fs/ubifs/xattr.c @@ -200,6 +200,7 @@ static int change_xattr(struct ubifs_info *c, struct inode *host, int err; struct ubifs_inode *host_ui = ubifs_inode(host); struct ubifs_inode *ui = ubifs_inode(inode); + void *buf = NULL; struct ubifs_budget_req req = { .dirtied_ino = 2, .dirtied_ino_d = ALIGN(size, 8) + ALIGN(host_ui->data_len, 8) }; @@ -208,14 +209,17 @@ static int change_xattr(struct ubifs_info *c, struct inode *host, if (err) return err; - kfree(ui->data); - ui->data = kmemdup(value, size, GFP_NOFS); - if (!ui->data) { + buf = kmemdup(value, size, GFP_NOFS); + if (!buf) { err = -ENOMEM; goto out_free; } + mutex_lock(&ui->ui_mutex); + kfree(ui->data); + ui->data = buf; inode->i_size = ui->ui_size = size; ui->data_len = size; + mutex_unlock(&ui->ui_mutex); mutex_lock(&host_ui->ui_mutex); host->i_ctime = ubifs_current_time(host); @@ -409,6 +413,7 @@ ssize_t ubifs_getxattr(struct dentry *dentry, const char *name, void *buf, ubifs_assert(inode->i_size == ui->data_len); ubifs_assert(ubifs_inode(host)->xattr_size > ui->data_len); + mutex_lock(&ui->ui_mutex); if (buf) { /* If @buf is %NULL we are supposed to return the length */ if (ui->data_len > size) { @@ -423,6 +428,7 @@ ssize_t ubifs_getxattr(struct dentry *dentry, const char *name, void *buf, err = ui->data_len; out_iput: + mutex_unlock(&ui->ui_mutex); iput(inode); out_unlock: kfree(xent); @@ -652,11 +658,8 @@ int ubifs_init_security(struct inode *dentry, struct inode *inode, { int err; - mutex_lock(&inode->i_mutex); err = security_inode_init_security(inode, dentry, qstr, &init_xattrs, 0); - mutex_unlock(&inode->i_mutex); - if (err) { struct ubifs_info *c = dentry->i_sb->s_fs_info; ubifs_err(c, "cannot initialize security for inode %lu, error %d", diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index f9aeb40..5031170 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -467,8 +467,8 @@ static int userfaultfd_release(struct inode *inode, struct file *file) * the fault_*wqh. */ spin_lock(&ctx->fault_pending_wqh.lock); - __wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL, 0, &range); - __wake_up_locked_key(&ctx->fault_wqh, TASK_NORMAL, 0, &range); + __wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL, &range); + __wake_up_locked_key(&ctx->fault_wqh, TASK_NORMAL, &range); spin_unlock(&ctx->fault_pending_wqh.lock); wake_up_poll(&ctx->fd_wqh, POLLHUP); @@ -650,10 +650,10 @@ static void __wake_userfault(struct userfaultfd_ctx *ctx, spin_lock(&ctx->fault_pending_wqh.lock); /* wake all in the range and autoremove */ if (waitqueue_active(&ctx->fault_pending_wqh)) - __wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL, 0, + __wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL, range); if (waitqueue_active(&ctx->fault_wqh)) - __wake_up_locked_key(&ctx->fault_wqh, TASK_NORMAL, 0, range); + __wake_up_locked_key(&ctx->fault_wqh, TASK_NORMAL, range); spin_unlock(&ctx->fault_pending_wqh.lock); } diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 39743ef..f5392ab 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -1521,7 +1521,7 @@ xfs_filemap_page_mkwrite( if (IS_DAX(inode)) { ret = __dax_mkwrite(vma, vmf, xfs_get_blocks_dax_fault, NULL); } else { - ret = __block_page_mkwrite(vma, vmf, xfs_get_blocks); + ret = block_page_mkwrite(vma, vmf, xfs_get_blocks); ret = block_page_mkwrite_return(ret); } diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index 7af7648..532ab79 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -525,7 +525,7 @@ xfs_qm_shrink_scan( unsigned long freed; int error; - if ((sc->gfp_mask & (__GFP_FS|__GFP_WAIT)) != (__GFP_FS|__GFP_WAIT)) + if ((sc->gfp_mask & (__GFP_FS|__GFP_DIRECT_RECLAIM)) != (__GFP_FS|__GFP_DIRECT_RECLAIM)) return 0; INIT_LIST_HEAD(&isol.buffers); |