diff options
Diffstat (limited to 'fs')
249 files changed, 3752 insertions, 2177 deletions
diff --git a/fs/Kconfig b/fs/Kconfig index 703a1cea0fc0..7104e3eb38eb 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -347,6 +347,7 @@ config GRACE_PERIOD config LOCKD tristate depends on FILE_LOCKING + select CRC32 select GRACE_PERIOD config LOCKD_V4 diff --git a/fs/affs/file.c b/fs/affs/file.c index 8daeed31e1af..52d11931025c 100644 --- a/fs/affs/file.c +++ b/fs/affs/file.c @@ -595,7 +595,7 @@ affs_extent_file_ofs(struct inode *inode, u32 newsize) BUG_ON(tmp > bsize); AFFS_DATA_HEAD(bh)->ptype = cpu_to_be32(T_DATA); AFFS_DATA_HEAD(bh)->key = cpu_to_be32(inode->i_ino); - AFFS_DATA_HEAD(bh)->sequence = cpu_to_be32(bidx); + AFFS_DATA_HEAD(bh)->sequence = cpu_to_be32(bidx + 1); AFFS_DATA_HEAD(bh)->size = cpu_to_be32(tmp); affs_fix_checksum(sb, bh); bh->b_state &= ~(1UL << BH_New); @@ -724,7 +724,8 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping, tmp = min(bsize - boff, to - from); BUG_ON(boff + tmp > bsize || tmp > bsize); memcpy(AFFS_DATA(bh) + boff, data + from, tmp); - be32_add_cpu(&AFFS_DATA_HEAD(bh)->size, tmp); + AFFS_DATA_HEAD(bh)->size = cpu_to_be32( + max(boff + tmp, be32_to_cpu(AFFS_DATA_HEAD(bh)->size))); affs_fix_checksum(sb, bh); mark_buffer_dirty_inode(bh, inode); written += tmp; @@ -746,7 +747,7 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping, if (buffer_new(bh)) { AFFS_DATA_HEAD(bh)->ptype = cpu_to_be32(T_DATA); AFFS_DATA_HEAD(bh)->key = cpu_to_be32(inode->i_ino); - AFFS_DATA_HEAD(bh)->sequence = cpu_to_be32(bidx); + AFFS_DATA_HEAD(bh)->sequence = cpu_to_be32(bidx + 1); AFFS_DATA_HEAD(bh)->size = cpu_to_be32(bsize); AFFS_DATA_HEAD(bh)->next = 0; bh->b_state &= ~(1UL << BH_New); @@ -780,7 +781,7 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping, if (buffer_new(bh)) { AFFS_DATA_HEAD(bh)->ptype = cpu_to_be32(T_DATA); AFFS_DATA_HEAD(bh)->key = cpu_to_be32(inode->i_ino); - AFFS_DATA_HEAD(bh)->sequence = cpu_to_be32(bidx); + AFFS_DATA_HEAD(bh)->sequence = cpu_to_be32(bidx + 1); AFFS_DATA_HEAD(bh)->size = cpu_to_be32(tmp); AFFS_DATA_HEAD(bh)->next = 0; bh->b_state &= ~(1UL << BH_New); diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c index 24192a7667ed..7a9b1ce9c98a 100644 --- a/fs/anon_inodes.c +++ b/fs/anon_inodes.c @@ -55,15 +55,26 @@ static struct file_system_type anon_inode_fs_type = { .kill_sb = kill_anon_super, }; -static struct inode *anon_inode_make_secure_inode( - const char *name, - const struct inode *context_inode) +/** + * anon_inode_make_secure_inode - allocate an anonymous inode with security context + * @sb: [in] Superblock to allocate from + * @name: [in] Name of the class of the newfile (e.g., "secretmem") + * @context_inode: + * [in] Optional parent inode for security inheritance + * + * The function ensures proper security initialization through the LSM hook + * security_inode_init_security_anon(). + * + * Return: Pointer to new inode on success, ERR_PTR on failure. + */ +struct inode *anon_inode_make_secure_inode(struct super_block *sb, const char *name, + const struct inode *context_inode) { struct inode *inode; const struct qstr qname = QSTR_INIT(name, strlen(name)); int error; - inode = alloc_anon_inode(anon_inode_mnt->mnt_sb); + inode = alloc_anon_inode(sb); if (IS_ERR(inode)) return inode; inode->i_flags &= ~S_PRIVATE; @@ -74,6 +85,7 @@ static struct inode *anon_inode_make_secure_inode( } return inode; } +EXPORT_SYMBOL_GPL(anon_inode_make_secure_inode); static struct file *__anon_inode_getfile(const char *name, const struct file_operations *fops, @@ -88,7 +100,8 @@ static struct file *__anon_inode_getfile(const char *name, return ERR_PTR(-ENOENT); if (secure) { - inode = anon_inode_make_secure_inode(name, context_inode); + inode = anon_inode_make_secure_inode(anon_inode_mnt->mnt_sb, + name, context_inode); if (IS_ERR(inode)) { file = ERR_CAST(inode); goto err; diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 89e7e4826efc..762704eed9ce 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -109,25 +109,6 @@ static struct linux_binfmt elf_format = { #define BAD_ADDR(x) (unlikely((unsigned long)(x) >= TASK_SIZE)) -static int set_brk(unsigned long start, unsigned long end, int prot) -{ - start = ELF_PAGEALIGN(start); - end = ELF_PAGEALIGN(end); - if (end > start) { - /* - * Map the last of the bss segment. - * If the header is requesting these pages to be - * executable, honour that (ppc32 needs this). - */ - int error = vm_brk_flags(start, end - start, - prot & PROT_EXEC ? VM_EXEC : 0); - if (error) - return error; - } - current->mm->start_brk = current->mm->brk = end; - return 0; -} - /* We need to explicitly zero any fractional pages after the data section (i.e. bss). This would contain the junk from the file that should not @@ -248,7 +229,7 @@ create_elf_tables(struct linux_binprm *bprm, const struct elfhdr *exec, } while (0) #ifdef ARCH_DLINFO - /* + /* * ARCH_DLINFO must come first so PPC can do its special alignment of * AUXV. * update AT_VECTOR_SIZE_ARCH if the number of NEW_AUX_ENT() in @@ -401,6 +382,51 @@ static unsigned long elf_map(struct file *filep, unsigned long addr, return(map_addr); } +static unsigned long elf_load(struct file *filep, unsigned long addr, + const struct elf_phdr *eppnt, int prot, int type, + unsigned long total_size) +{ + unsigned long zero_start, zero_end; + unsigned long map_addr; + + if (eppnt->p_filesz) { + map_addr = elf_map(filep, addr, eppnt, prot, type, total_size); + if (BAD_ADDR(map_addr)) + return map_addr; + if (eppnt->p_memsz > eppnt->p_filesz) { + zero_start = map_addr + ELF_PAGEOFFSET(eppnt->p_vaddr) + + eppnt->p_filesz; + zero_end = map_addr + ELF_PAGEOFFSET(eppnt->p_vaddr) + + eppnt->p_memsz; + + /* Zero the end of the last mapped page */ + padzero(zero_start); + } + } else { + map_addr = zero_start = ELF_PAGESTART(addr); + zero_end = zero_start + ELF_PAGEOFFSET(eppnt->p_vaddr) + + eppnt->p_memsz; + } + if (eppnt->p_memsz > eppnt->p_filesz) { + /* + * Map the last of the segment. + * If the header is requesting these pages to be + * executable, honour that (ppc32 needs this). + */ + int error; + + zero_start = ELF_PAGEALIGN(zero_start); + zero_end = ELF_PAGEALIGN(zero_end); + + error = vm_brk_flags(zero_start, zero_end - zero_start, + prot & PROT_EXEC ? VM_EXEC : 0); + if (error) + map_addr = error; + } + return map_addr; +} + + static unsigned long total_mapping_size(const struct elf_phdr *phdr, int nr) { elf_addr_t min_addr = -1; @@ -829,8 +855,8 @@ static int load_elf_binary(struct linux_binprm *bprm) unsigned long error; struct elf_phdr *elf_ppnt, *elf_phdata, *interp_elf_phdata = NULL; struct elf_phdr *elf_property_phdata = NULL; - unsigned long elf_bss, elf_brk; - int bss_prot = 0; + unsigned long elf_brk; + bool brk_moved = false; int retval, i; unsigned long elf_entry; unsigned long e_entry; @@ -1021,8 +1047,7 @@ out_free_interp: executable_stack); if (retval < 0) goto out_free_dentry; - - elf_bss = 0; + elf_brk = 0; start_code = ~0UL; @@ -1042,33 +1067,6 @@ out_free_interp: if (elf_ppnt->p_type != PT_LOAD) continue; - if (unlikely (elf_brk > elf_bss)) { - unsigned long nbyte; - - /* There was a PT_LOAD segment with p_memsz > p_filesz - before this one. Map anonymous pages, if needed, - and clear the area. */ - retval = set_brk(elf_bss + load_bias, - elf_brk + load_bias, - bss_prot); - if (retval) - goto out_free_dentry; - nbyte = ELF_PAGEOFFSET(elf_bss); - if (nbyte) { - nbyte = ELF_MIN_ALIGN - nbyte; - if (nbyte > elf_brk - elf_bss) - nbyte = elf_brk - elf_bss; - if (clear_user((void __user *)elf_bss + - load_bias, nbyte)) { - /* - * This bss-zeroing can fail if the ELF - * file specifies odd protections. So - * we don't check the return value - */ - } - } - } - elf_prot = make_prot(elf_ppnt->p_flags, &arch_state, !!interpreter, false); @@ -1096,15 +1094,49 @@ out_free_interp: * Header for ET_DYN binaries to calculate the * randomization (load_bias) for all the LOAD * Program Headers. + */ + + /* + * Calculate the entire size of the ELF mapping + * (total_size), used for the initial mapping, + * due to load_addr_set which is set to true later + * once the initial mapping is performed. + * + * Note that this is only sensible when the LOAD + * segments are contiguous (or overlapping). If + * used for LOADs that are far apart, this would + * cause the holes between LOADs to be mapped, + * running the risk of having the mapping fail, + * as it would be larger than the ELF file itself. + * + * As a result, only ET_DYN does this, since + * some ET_EXEC (e.g. ia64) may have large virtual + * memory holes between LOADs. + * + */ + total_size = total_mapping_size(elf_phdata, + elf_ex->e_phnum); + if (!total_size) { + retval = -EINVAL; + goto out_free_dentry; + } + + /* Calculate any requested alignment. */ + alignment = maximum_alignment(elf_phdata, elf_ex->e_phnum); + + /** + * DOC: PIE handling * - * There are effectively two types of ET_DYN - * binaries: programs (i.e. PIE: ET_DYN with INTERP) - * and loaders (ET_DYN without INTERP, since they - * _are_ the ELF interpreter). The loaders must - * be loaded away from programs since the program - * may otherwise collide with the loader (especially - * for ET_EXEC which does not have a randomized - * position). For example to handle invocations of + * There are effectively two types of ET_DYN ELF + * binaries: programs (i.e. PIE: ET_DYN with + * PT_INTERP) and loaders (i.e. static PIE: ET_DYN + * without PT_INTERP, usually the ELF interpreter + * itself). Loaders must be loaded away from programs + * since the program may otherwise collide with the + * loader (especially for ET_EXEC which does not have + * a randomized position). + * + * For example, to handle invocations of * "./ld.so someprog" to test out a new version of * the loader, the subsequent program that the * loader loads must avoid the loader itself, so @@ -1117,17 +1149,49 @@ out_free_interp: * ELF_ET_DYN_BASE and loaders are loaded into the * independently randomized mmap region (0 load_bias * without MAP_FIXED nor MAP_FIXED_NOREPLACE). + * + * See below for "brk" handling details, which is + * also affected by program vs loader and ASLR. */ if (interpreter) { + /* On ET_DYN with PT_INTERP, we do the ASLR. */ load_bias = ELF_ET_DYN_BASE; if (current->flags & PF_RANDOMIZE) load_bias += arch_mmap_rnd(); - alignment = maximum_alignment(elf_phdata, elf_ex->e_phnum); + /* Adjust alignment as requested. */ if (alignment) load_bias &= ~(alignment - 1); elf_flags |= MAP_FIXED_NOREPLACE; - } else - load_bias = 0; + } else { + /* + * For ET_DYN without PT_INTERP, we rely on + * the architectures's (potentially ASLR) mmap + * base address (via a load_bias of 0). + * + * When a large alignment is requested, we + * must do the allocation at address "0" right + * now to discover where things will load so + * that we can adjust the resulting alignment. + * In this case (load_bias != 0), we can use + * MAP_FIXED_NOREPLACE to make sure the mapping + * doesn't collide with anything. + */ + if (alignment > ELF_MIN_ALIGN) { + load_bias = elf_load(bprm->file, 0, elf_ppnt, + elf_prot, elf_flags, total_size); + if (BAD_ADDR(load_bias)) { + retval = IS_ERR_VALUE(load_bias) ? + PTR_ERR((void*)load_bias) : -EINVAL; + goto out_free_dentry; + } + vm_munmap(load_bias, total_size); + /* Adjust alignment as requested. */ + if (alignment) + load_bias &= ~(alignment - 1); + elf_flags |= MAP_FIXED_NOREPLACE; + } else + load_bias = 0; + } /* * Since load_bias is used for all subsequent loading @@ -1137,34 +1201,9 @@ out_free_interp: * is then page aligned. */ load_bias = ELF_PAGESTART(load_bias - vaddr); - - /* - * Calculate the entire size of the ELF mapping - * (total_size), used for the initial mapping, - * due to load_addr_set which is set to true later - * once the initial mapping is performed. - * - * Note that this is only sensible when the LOAD - * segments are contiguous (or overlapping). If - * used for LOADs that are far apart, this would - * cause the holes between LOADs to be mapped, - * running the risk of having the mapping fail, - * as it would be larger than the ELF file itself. - * - * As a result, only ET_DYN does this, since - * some ET_EXEC (e.g. ia64) may have large virtual - * memory holes between LOADs. - * - */ - total_size = total_mapping_size(elf_phdata, - elf_ex->e_phnum); - if (!total_size) { - retval = -EINVAL; - goto out_free_dentry; - } } - error = elf_map(bprm->file, load_bias + vaddr, elf_ppnt, + error = elf_load(bprm->file, load_bias + vaddr, elf_ppnt, elf_prot, elf_flags, total_size); if (BAD_ADDR(error)) { retval = IS_ERR((void *)error) ? @@ -1212,41 +1251,23 @@ out_free_interp: k = elf_ppnt->p_vaddr + elf_ppnt->p_filesz; - if (k > elf_bss) - elf_bss = k; if ((elf_ppnt->p_flags & PF_X) && end_code < k) end_code = k; if (end_data < k) end_data = k; k = elf_ppnt->p_vaddr + elf_ppnt->p_memsz; - if (k > elf_brk) { - bss_prot = elf_prot; + if (k > elf_brk) elf_brk = k; - } } e_entry = elf_ex->e_entry + load_bias; phdr_addr += load_bias; - elf_bss += load_bias; elf_brk += load_bias; start_code += load_bias; end_code += load_bias; start_data += load_bias; end_data += load_bias; - /* Calling set_brk effectively mmaps the pages that we need - * for the bss and break sections. We must do this before - * mapping in the interpreter, to make sure it doesn't wind - * up getting placed where the bss needs to go. - */ - retval = set_brk(elf_bss, elf_brk, bss_prot); - if (retval) - goto out_free_dentry; - if (likely(elf_bss != elf_brk) && unlikely(padzero(elf_bss))) { - retval = -EFAULT; /* Nobody gets to see this, but.. */ - goto out_free_dentry; - } - if (interpreter) { elf_entry = load_elf_interp(interp_elf_ex, interpreter, @@ -1302,24 +1323,44 @@ out_free_interp: mm->end_data = end_data; mm->start_stack = bprm->p; - if ((current->flags & PF_RANDOMIZE) && (snapshot_randomize_va_space > 1)) { + /** + * DOC: "brk" handling + * + * For architectures with ELF randomization, when executing a + * loader directly (i.e. static PIE: ET_DYN without PT_INTERP), + * move the brk area out of the mmap region and into the unused + * ELF_ET_DYN_BASE region. Since "brk" grows up it may collide + * early with the stack growing down or other regions being put + * into the mmap region by the kernel (e.g. vdso). + * + * In the CONFIG_COMPAT_BRK case, though, everything is turned + * off because we're not allowed to move the brk at all. + */ + if (!IS_ENABLED(CONFIG_COMPAT_BRK) && + IS_ENABLED(CONFIG_ARCH_HAS_ELF_RANDOMIZE) && + elf_ex->e_type == ET_DYN && !interpreter) { + elf_brk = ELF_ET_DYN_BASE; + /* This counts as moving the brk, so let brk(2) know. */ + brk_moved = true; + } + mm->start_brk = mm->brk = ELF_PAGEALIGN(elf_brk); + + if ((current->flags & PF_RANDOMIZE) && snapshot_randomize_va_space > 1) { /* - * For architectures with ELF randomization, when executing - * a loader directly (i.e. no interpreter listed in ELF - * headers), move the brk area out of the mmap region - * (since it grows up, and may collide early with the stack - * growing down), and into the unused ELF_ET_DYN_BASE region. + * If we didn't move the brk to ELF_ET_DYN_BASE (above), + * leave a gap between .bss and brk. */ - if (IS_ENABLED(CONFIG_ARCH_HAS_ELF_RANDOMIZE) && - elf_ex->e_type == ET_DYN && !interpreter) { - mm->brk = mm->start_brk = ELF_ET_DYN_BASE; - } + if (!brk_moved) + mm->brk = mm->start_brk = mm->brk + PAGE_SIZE; mm->brk = mm->start_brk = arch_randomize_brk(mm); + brk_moved = true; + } + #ifdef compat_brk_randomized + if (brk_moved) current->brk_randomized = 1; #endif - } if (current->personality & MMAP_PAGE_ZERO) { /* Why this, you ask??? Well SVr4 maps page 0 as read-only, @@ -1522,7 +1563,7 @@ static void fill_elf_note_phdr(struct elf_phdr *phdr, int sz, loff_t offset) phdr->p_align = 0; } -static void fill_note(struct memelfnote *note, const char *name, int type, +static void fill_note(struct memelfnote *note, const char *name, int type, unsigned int sz, void *data) { note->name = name; @@ -2005,8 +2046,8 @@ static int elf_dump_thread_status(long signr, struct elf_thread_status *t) t->num_notes = 0; fill_prstatus(&t->prstatus.common, p, signr); - elf_core_copy_task_regs(p, &t->prstatus.pr_reg); - + elf_core_copy_task_regs(p, &t->prstatus.pr_reg); + fill_note(&t->notes[0], "CORE", NT_PRSTATUS, sizeof(t->prstatus), &(t->prstatus)); t->num_notes++; @@ -2296,7 +2337,7 @@ static int elf_core_dump(struct coredump_params *cprm) if (!elf_core_write_extra_phdrs(cprm, offset)) goto end_coredump; - /* write out the notes section */ + /* write out the notes section */ if (!write_note_info(&info, cprm)) goto end_coredump; diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index c71a40927315..b2d3b6e43bb5 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -1603,7 +1603,7 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm) if (!elf_core_write_extra_phdrs(cprm, offset)) goto end_coredump; - /* write out the notes section */ + /* write out the notes section */ if (!writenote(thread_list->notes, cprm)) goto end_coredump; if (!writenote(&psinfo_note, cprm)) diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 0dcf7fecaf55..91440ef79a26 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -1678,6 +1678,17 @@ void btrfs_reclaim_bgs_work(struct work_struct *work) up_write(&space_info->groups_sem); goto next; } + + /* + * Cache the zone_unusable value before turning the block group + * to read only. As soon as the block group is read only it's + * zone_unusable value gets moved to the block group's read-only + * bytes and isn't available for calculations anymore. We also + * cache it before unlocking the block group, to prevent races + * (reports from KCSAN and such tools) with tasks updating it. + */ + zone_unusable = bg->zone_unusable; + spin_unlock(&bg->lock); /* @@ -1693,13 +1704,6 @@ void btrfs_reclaim_bgs_work(struct work_struct *work) goto next; } - /* - * Cache the zone_unusable value before turning the block group - * to read only. As soon as the blog group is read only it's - * zone_unusable value gets moved to the block group's read-only - * bytes and isn't available for calculations anymore. - */ - zone_unusable = bg->zone_unusable; ret = inc_block_group_ro(bg, 0); up_write(&space_info->groups_sem); if (ret < 0) diff --git a/fs/btrfs/discard.c b/fs/btrfs/discard.c index bd9dde374e5d..a90f3cb83c70 100644 --- a/fs/btrfs/discard.c +++ b/fs/btrfs/discard.c @@ -78,8 +78,6 @@ static void __add_to_discard_list(struct btrfs_discard_ctl *discard_ctl, struct btrfs_block_group *block_group) { lockdep_assert_held(&discard_ctl->lock); - if (!btrfs_run_discard_work(discard_ctl)) - return; if (list_empty(&block_group->discard_list) || block_group->discard_index == BTRFS_DISCARD_INDEX_UNUSED) { @@ -102,6 +100,9 @@ static void add_to_discard_list(struct btrfs_discard_ctl *discard_ctl, if (!btrfs_is_block_group_data_only(block_group)) return; + if (!btrfs_run_discard_work(discard_ctl)) + return; + spin_lock(&discard_ctl->lock); __add_to_discard_list(discard_ctl, block_group); spin_unlock(&discard_ctl->lock); @@ -151,13 +152,7 @@ static bool remove_from_discard_list(struct btrfs_discard_ctl *discard_ctl, block_group->discard_eligible_time = 0; queued = !list_empty(&block_group->discard_list); list_del_init(&block_group->discard_list); - /* - * If the block group is currently running in the discard workfn, we - * don't want to deref it, since it's still being used by the workfn. - * The workfn will notice this case and deref the block group when it is - * finished. - */ - if (queued && !running) + if (queued) btrfs_put_block_group(block_group); spin_unlock(&discard_ctl->lock); @@ -233,6 +228,18 @@ again: block_group->used != 0) { if (btrfs_is_block_group_data_only(block_group)) { __add_to_discard_list(discard_ctl, block_group); + /* + * The block group must have been moved to other + * discard list even if discard was disabled in + * the meantime or a transaction abort happened, + * otherwise we can end up in an infinite loop, + * always jumping into the 'again' label and + * keep getting this block group over and over + * in case there are no other block groups in + * the discard lists. + */ + ASSERT(block_group->discard_index != + BTRFS_DISCARD_INDEX_UNUSED); } else { list_del_init(&block_group->discard_list); btrfs_put_block_group(block_group); @@ -243,9 +250,10 @@ again: block_group->discard_cursor = block_group->start; block_group->discard_state = BTRFS_DISCARD_EXTENTS; } - discard_ctl->block_group = block_group; } if (block_group) { + btrfs_get_block_group(block_group); + discard_ctl->block_group = block_group; *discard_state = block_group->discard_state; *discard_index = block_group->discard_index; } @@ -469,9 +477,20 @@ static void btrfs_discard_workfn(struct work_struct *work) block_group = peek_discard_list(discard_ctl, &discard_state, &discard_index, now); - if (!block_group || !btrfs_run_discard_work(discard_ctl)) + if (!block_group) + return; + if (!btrfs_run_discard_work(discard_ctl)) { + spin_lock(&discard_ctl->lock); + btrfs_put_block_group(block_group); + discard_ctl->block_group = NULL; + spin_unlock(&discard_ctl->lock); return; + } if (now < block_group->discard_eligible_time) { + spin_lock(&discard_ctl->lock); + btrfs_put_block_group(block_group); + discard_ctl->block_group = NULL; + spin_unlock(&discard_ctl->lock); btrfs_discard_schedule_work(discard_ctl, false); return; } @@ -523,15 +542,7 @@ static void btrfs_discard_workfn(struct work_struct *work) spin_lock(&discard_ctl->lock); discard_ctl->prev_discard = trimmed; discard_ctl->prev_discard_time = now; - /* - * If the block group was removed from the discard list while it was - * running in this workfn, then we didn't deref it, since this function - * still owned that reference. But we set the discard_ctl->block_group - * back to NULL, so we can use that condition to know that now we need - * to deref the block_group. - */ - if (discard_ctl->block_group == NULL) - btrfs_put_block_group(block_group); + btrfs_put_block_group(block_group); discard_ctl->block_group = NULL; __btrfs_discard_schedule_work(discard_ctl, now, false); spin_unlock(&discard_ctl->lock); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 30fe5ebc3650..76a261cbf39d 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2481,8 +2481,7 @@ static int load_global_roots_objectid(struct btrfs_root *tree_root, found = true; root = read_tree_root_path(tree_root, path, &key); if (IS_ERR(root)) { - if (!btrfs_test_opt(fs_info, IGNOREBADROOTS)) - ret = PTR_ERR(root); + ret = PTR_ERR(root); break; } set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); @@ -4642,6 +4641,14 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) btrfs_cleanup_defrag_inodes(fs_info); /* + * Handle the error fs first, as it will flush and wait for all ordered + * extents. This will generate delayed iputs, thus we want to handle + * it first. + */ + if (unlikely(BTRFS_FS_ERROR(fs_info))) + btrfs_error_commit_super(fs_info); + + /* * Wait for any fixup workers to complete. * If we don't wait for them here and they are still running by the time * we call kthread_stop() against the cleaner kthread further below, we @@ -4662,6 +4669,31 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) btrfs_flush_workqueue(fs_info->delalloc_workers); /* + * We can have ordered extents getting their last reference dropped from + * the fs_info->workers queue because for async writes for data bios we + * queue a work for that queue, at btrfs_wq_submit_bio(), that runs + * run_one_async_done() which calls btrfs_bio_end_io() in case the bio + * has an error, and that later function can do the final + * btrfs_put_ordered_extent() on the ordered extent attached to the bio, + * which adds a delayed iput for the inode. So we must flush the queue + * so that we don't have delayed iputs after committing the current + * transaction below and stopping the cleaner and transaction kthreads. + */ + btrfs_flush_workqueue(fs_info->workers); + + /* + * When finishing a compressed write bio we schedule a work queue item + * to finish an ordered extent - btrfs_finish_compressed_write_work() + * calls btrfs_finish_ordered_extent() which in turns does a call to + * btrfs_queue_ordered_fn(), and that queues the ordered extent + * completion either in the endio_write_workers work queue or in the + * fs_info->endio_freespace_worker work queue. We flush those queues + * below, so before we flush them we must flush this queue for the + * workers of compressed writes. + */ + flush_workqueue(fs_info->compressed_write_workers); + + /* * After we parked the cleaner kthread, ordered extents may have * completed and created new delayed iputs. If one of the async reclaim * tasks is running and in the RUN_DELAYED_IPUTS flush state, then we @@ -4718,9 +4750,6 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) btrfs_err(fs_info, "commit super ret %d", ret); } - if (BTRFS_FS_ERROR(fs_info)) - btrfs_error_commit_super(fs_info); - kthread_stop(fs_info->transaction_kthread); kthread_stop(fs_info->cleaner_kthread); @@ -4876,10 +4905,6 @@ static void btrfs_error_commit_super(struct btrfs_fs_info *fs_info) /* cleanup FS via transaction */ btrfs_cleanup_transaction(fs_info); - mutex_lock(&fs_info->cleaner_mutex); - btrfs_run_delayed_iputs(fs_info); - mutex_unlock(&fs_info->cleaner_mutex); - down_write(&fs_info->cleanup_work_sem); up_write(&fs_info->cleanup_work_sem); } diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 50bc553cc73a..5395e27f9e89 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -179,6 +179,14 @@ search_again: ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item); num_refs = btrfs_extent_refs(leaf, ei); + if (unlikely(num_refs == 0)) { + ret = -EUCLEAN; + btrfs_err(fs_info, + "unexpected zero reference count for extent item (%llu %u %llu)", + key.objectid, key.type, key.offset); + btrfs_abort_transaction(trans, ret); + goto out_free; + } extent_flags = btrfs_extent_flags(leaf, ei); } else { ret = -EINVAL; @@ -190,8 +198,6 @@ search_again: goto out_free; } - - BUG_ON(num_refs == 0); } else { num_refs = 0; extent_flags = 0; @@ -221,10 +227,19 @@ search_again: goto search_again; } spin_lock(&head->lock); - if (head->extent_op && head->extent_op->update_flags) + if (head->extent_op && head->extent_op->update_flags) { extent_flags |= head->extent_op->flags_to_set; - else - BUG_ON(num_refs == 0); + } else if (unlikely(num_refs == 0)) { + spin_unlock(&head->lock); + mutex_unlock(&head->mutex); + spin_unlock(&delayed_refs->lock); + ret = -EUCLEAN; + btrfs_err(fs_info, + "unexpected zero reference count for extent %llu (%s)", + bytenr, metadata ? "metadata" : "data"); + btrfs_abort_transaction(trans, ret); + goto out_free; + } num_refs += head->ref_mod; spin_unlock(&head->lock); @@ -5575,7 +5590,10 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans, ret = btrfs_dec_ref(trans, root, eb, 1); else ret = btrfs_dec_ref(trans, root, eb, 0); - BUG_ON(ret); /* -ENOMEM */ + if (ret) { + btrfs_abort_transaction(trans, ret); + return ret; + } if (is_fstree(root->root_key.objectid)) { ret = btrfs_qgroup_trace_leaf_items(trans, eb); if (ret) { diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 72227c0b4b5a..d5552875f872 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -4459,10 +4459,10 @@ struct extent_buffer *find_extent_buffer(struct btrfs_fs_info *fs_info, return eb; } -#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info, u64 start) { +#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS struct extent_buffer *eb, *exists = NULL; int ret; @@ -4498,8 +4498,11 @@ again: free_eb: btrfs_release_extent_buffer(eb); return exists; -} +#else + /* Stub to avoid linker error when compiled with optimizations turned off. */ + return NULL; #endif +} static struct extent_buffer *grab_extent_buffer( struct btrfs_fs_info *fs_info, struct page *page) diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 9e06d1a0d373..3814f09dc4ae 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -2224,15 +2224,20 @@ static void btrfs_punch_hole_lock_range(struct inode *inode, * will always return true. * So here we need to do extra page alignment for * filemap_range_has_page(). + * + * And do not decrease page_lockend right now, as it can be 0. */ const u64 page_lockstart = round_up(lockstart, PAGE_SIZE); - const u64 page_lockend = round_down(lockend + 1, PAGE_SIZE) - 1; + const u64 page_lockend = round_down(lockend + 1, PAGE_SIZE); while (1) { truncate_pagecache_range(inode, lockstart, lockend); lock_extent(&BTRFS_I(inode)->io_tree, lockstart, lockend, cached_state); + /* The same page or adjacent pages. */ + if (page_lockend <= page_lockstart) + break; /* * We can't have ordered extents in the range, nor dirty/writeback * pages, because we have locked the inode's VFS lock in exclusive @@ -2244,7 +2249,7 @@ static void btrfs_punch_hole_lock_range(struct inode *inode, * we do, unlock the range and retry. */ if (!filemap_range_has_page(inode->i_mapping, page_lockstart, - page_lockend)) + page_lockend - 1)) break; unlock_extent(&BTRFS_I(inode)->io_tree, lockstart, lockend, diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c index 6a44733a95e1..14bdb241ff6b 100644 --- a/fs/btrfs/free-space-tree.c +++ b/fs/btrfs/free-space-tree.c @@ -1098,11 +1098,21 @@ static int populate_free_space_tree(struct btrfs_trans_handle *trans, ret = btrfs_search_slot_for_read(extent_root, &key, path, 1, 0); if (ret < 0) goto out_locked; - ASSERT(ret == 0); + /* + * If ret is 1 (no key found), it means this is an empty block group, + * without any extents allocated from it and there's no block group + * item (key BTRFS_BLOCK_GROUP_ITEM_KEY) located in the extent tree + * because we are using the block group tree feature, so block group + * items are stored in the block group tree. It also means there are no + * extents allocated for block groups with a start offset beyond this + * block group's end offset (this is the last, highest, block group). + */ + if (!btrfs_fs_compat_ro(trans->fs_info, BLOCK_GROUP_TREE)) + ASSERT(ret == 0); start = block_group->start; end = block_group->start + block_group->length; - while (1) { + while (ret == 0) { btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); if (key.type == BTRFS_EXTENT_ITEM_KEY || @@ -1132,8 +1142,6 @@ static int populate_free_space_tree(struct btrfs_trans_handle *trans, ret = btrfs_next_item(extent_root, path); if (ret < 0) goto out_locked; - if (ret) - break; } if (start < end) { ret = __add_to_free_space_tree(trans, block_group, path2, diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index a13ab3abef12..469a622b440b 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1428,6 +1428,7 @@ out_unlock: locked_page, clear_bits, page_ops); + btrfs_qgroup_free_data(inode, NULL, start, cur_alloc_size, NULL); start += cur_alloc_size; } @@ -1441,6 +1442,7 @@ out_unlock: clear_bits |= EXTENT_CLEAR_DATA_RESV; extent_clear_unlock_delalloc(inode, start, end, locked_page, clear_bits, page_ops); + btrfs_qgroup_free_data(inode, NULL, start, end - start + 1, NULL); } return ret; } @@ -2168,13 +2170,15 @@ error: if (nocow) btrfs_dec_nocow_writers(bg); - if (ret && cur_offset < end) + if (ret && cur_offset < end) { extent_clear_unlock_delalloc(inode, cur_offset, end, locked_page, EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DEFRAG | EXTENT_DO_ACCOUNTING, PAGE_UNLOCK | PAGE_START_WRITEBACK | PAGE_END_WRITEBACK); + btrfs_qgroup_free_data(inode, NULL, cur_offset, end - cur_offset + 1, NULL); + } btrfs_free_path(path); return ret; } @@ -4852,7 +4856,6 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry) struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info; int err = 0; struct btrfs_trans_handle *trans; - u64 last_unlink_trans; struct fscrypt_name fname; if (inode->i_size > BTRFS_EMPTY_DIR_SIZE) @@ -4878,6 +4881,23 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry) goto out_notrans; } + /* + * Propagate the last_unlink_trans value of the deleted dir to its + * parent directory. This is to prevent an unrecoverable log tree in the + * case we do something like this: + * 1) create dir foo + * 2) create snapshot under dir foo + * 3) delete the snapshot + * 4) rmdir foo + * 5) mkdir foo + * 6) fsync foo or some file inside foo + * + * This is because we can't unlink other roots when replaying the dir + * deletes for directory foo. + */ + if (BTRFS_I(inode)->last_unlink_trans >= trans->transid) + BTRFS_I(dir)->last_unlink_trans = BTRFS_I(inode)->last_unlink_trans; + if (unlikely(btrfs_ino(BTRFS_I(inode)) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)) { err = btrfs_unlink_subvol(trans, dir, dentry); goto out; @@ -4887,26 +4907,13 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry) if (err) goto out; - last_unlink_trans = BTRFS_I(inode)->last_unlink_trans; - /* now the directory is empty */ err = btrfs_unlink_inode(trans, BTRFS_I(dir), BTRFS_I(d_inode(dentry)), &fname.disk_name); if (!err) { btrfs_i_size_write(BTRFS_I(inode), 0); - /* - * Propagate the last_unlink_trans value of the deleted dir to - * its parent directory. This is to prevent an unrecoverable - * log tree in the case we do something like this: - * 1) create dir foo - * 2) create snapshot under dir foo - * 3) delete the snapshot - * 4) rmdir foo - * 5) mkdir foo - * 6) fsync foo or some file inside foo - */ - if (last_unlink_trans >= trans->transid) - BTRFS_I(dir)->last_unlink_trans = last_unlink_trans; + if (BTRFS_I(inode)->last_unlink_trans >= trans->transid) + btrfs_record_snapshot_destroy(trans, BTRFS_I(dir)); } out: btrfs_end_transaction(trans); @@ -9177,6 +9184,7 @@ static int btrfs_rename_exchange(struct inode *old_dir, int ret; int ret2; bool need_abort = false; + bool logs_pinned = false; struct fscrypt_name old_fname, new_fname; struct fscrypt_str *old_name, *new_name; @@ -9305,6 +9313,31 @@ static int btrfs_rename_exchange(struct inode *old_dir, old_inode->i_ctime = ctime; new_inode->i_ctime = ctime; + if (old_ino != BTRFS_FIRST_FREE_OBJECTID && + new_ino != BTRFS_FIRST_FREE_OBJECTID) { + /* + * If we are renaming in the same directory (and it's not for + * root entries) pin the log early to prevent any concurrent + * task from logging the directory after we removed the old + * entries and before we add the new entries, otherwise that + * task can sync a log without any entry for the inodes we are + * renaming and therefore replaying that log, if a power failure + * happens after syncing the log, would result in deleting the + * inodes. + * + * If the rename affects two different directories, we want to + * make sure the that there's no log commit that contains + * updates for only one of the directories but not for the + * other. + * + * If we are renaming an entry for a root, we don't care about + * log updates since we called btrfs_set_log_full_commit(). + */ + btrfs_pin_log_trans(root); + btrfs_pin_log_trans(dest); + logs_pinned = true; + } + if (old_dentry->d_parent != new_dentry->d_parent) { btrfs_record_unlink_dir(trans, BTRFS_I(old_dir), BTRFS_I(old_inode), 1); @@ -9362,30 +9395,23 @@ static int btrfs_rename_exchange(struct inode *old_dir, BTRFS_I(new_inode)->dir_index = new_idx; /* - * Now pin the logs of the roots. We do it to ensure that no other task - * can sync the logs while we are in progress with the rename, because - * that could result in an inconsistency in case any of the inodes that - * are part of this rename operation were logged before. + * Do the log updates for all inodes. + * + * If either entry is for a root we don't need to update the logs since + * we've called btrfs_set_log_full_commit() before. */ - if (old_ino != BTRFS_FIRST_FREE_OBJECTID) - btrfs_pin_log_trans(root); - if (new_ino != BTRFS_FIRST_FREE_OBJECTID) - btrfs_pin_log_trans(dest); - - /* Do the log updates for all inodes. */ - if (old_ino != BTRFS_FIRST_FREE_OBJECTID) + if (logs_pinned) { btrfs_log_new_name(trans, old_dentry, BTRFS_I(old_dir), old_rename_ctx.index, new_dentry->d_parent); - if (new_ino != BTRFS_FIRST_FREE_OBJECTID) btrfs_log_new_name(trans, new_dentry, BTRFS_I(new_dir), new_rename_ctx.index, old_dentry->d_parent); + } - /* Now unpin the logs. */ - if (old_ino != BTRFS_FIRST_FREE_OBJECTID) +out_fail: + if (logs_pinned) { btrfs_end_log_trans(root); - if (new_ino != BTRFS_FIRST_FREE_OBJECTID) btrfs_end_log_trans(dest); -out_fail: + } ret2 = btrfs_end_transaction(trans); ret = ret ? ret : ret2; out_notrans: @@ -9435,6 +9461,7 @@ static int btrfs_rename(struct user_namespace *mnt_userns, int ret2; u64 old_ino = btrfs_ino(BTRFS_I(old_inode)); struct fscrypt_name old_fname, new_fname; + bool logs_pinned = false; if (btrfs_ino(BTRFS_I(new_dir)) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID) return -EPERM; @@ -9573,6 +9600,29 @@ static int btrfs_rename(struct user_namespace *mnt_userns, new_dir->i_ctime = old_dir->i_mtime; old_inode->i_ctime = old_dir->i_mtime; + if (old_ino != BTRFS_FIRST_FREE_OBJECTID) { + /* + * If we are renaming in the same directory (and it's not a + * root entry) pin the log to prevent any concurrent task from + * logging the directory after we removed the old entry and + * before we add the new entry, otherwise that task can sync + * a log without any entry for the inode we are renaming and + * therefore replaying that log, if a power failure happens + * after syncing the log, would result in deleting the inode. + * + * If the rename affects two different directories, we want to + * make sure the that there's no log commit that contains + * updates for only one of the directories but not for the + * other. + * + * If we are renaming an entry for a root, we don't care about + * log updates since we called btrfs_set_log_full_commit(). + */ + btrfs_pin_log_trans(root); + btrfs_pin_log_trans(dest); + logs_pinned = true; + } + if (old_dentry->d_parent != new_dentry->d_parent) btrfs_record_unlink_dir(trans, BTRFS_I(old_dir), BTRFS_I(old_inode), 1); @@ -9622,7 +9672,7 @@ static int btrfs_rename(struct user_namespace *mnt_userns, if (old_inode->i_nlink == 1) BTRFS_I(old_inode)->dir_index = index; - if (old_ino != BTRFS_FIRST_FREE_OBJECTID) + if (logs_pinned) btrfs_log_new_name(trans, old_dentry, BTRFS_I(old_dir), rename_ctx.index, new_dentry->d_parent); @@ -9638,6 +9688,10 @@ static int btrfs_rename(struct user_namespace *mnt_userns, } } out_fail: + if (logs_pinned) { + btrfs_end_log_trans(root); + btrfs_end_log_trans(dest); + } ret2 = btrfs_end_transaction(trans); ret = ret ? ret : ret2; out_notrans: diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index d6cda0b2e925..fd6ea3fcab33 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -2977,6 +2977,7 @@ static int relocate_one_page(struct inode *inode, struct file_ra_state *ra, int ret; ASSERT(page_index <= last_index); +again: page = find_lock_page(inode->i_mapping, page_index); if (!page) { page_cache_sync_readahead(inode->i_mapping, ra, NULL, @@ -2998,6 +2999,11 @@ static int relocate_one_page(struct inode *inode, struct file_ra_state *ra, ret = -EIO; goto release_page; } + if (page->mapping != inode->i_mapping) { + unlock_page(page); + put_page(page); + goto again; + } } /* diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index a2b95ccb4cf5..0735decec99b 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -431,10 +431,8 @@ static int fs_path_ensure_buf(struct fs_path *p, int len) if (p->buf_len >= len) return 0; - if (len > PATH_MAX) { - WARN_ON(1); - return -ENOMEM; - } + if (WARN_ON(len > PATH_MAX)) + return -ENAMETOOLONG; path_len = p->end - p->start; old_buf_len = p->buf_len; diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index c0ff0c2fc01d..91b19d66449b 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1640,8 +1640,7 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry) subvol_name = btrfs_get_subvol_name_from_objectid(info, BTRFS_I(d_inode(dentry))->root->root_key.objectid); if (!IS_ERR(subvol_name)) { - seq_puts(seq, ",subvol="); - seq_escape(seq, subvol_name, " \t\n\\"); + seq_show_option(seq, "subvol", subvol_name); kfree(subvol_name); } return 0; diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index fdc432b3352a..982dc92bdf1d 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -1085,7 +1085,9 @@ again: search_key.type = BTRFS_INODE_REF_KEY; search_key.offset = parent_objectid; ret = btrfs_search_slot(NULL, root, &search_key, path, 0, 0); - if (ret == 0) { + if (ret < 0) { + return ret; + } else if (ret == 0) { struct btrfs_inode_ref *victim_ref; unsigned long ptr; unsigned long ptr_end; @@ -1158,13 +1160,13 @@ again: struct fscrypt_str victim_name; extref = (struct btrfs_inode_extref *)(base + cur_offset); + victim_name.len = btrfs_inode_extref_name_len(leaf, extref); if (btrfs_inode_extref_parent(leaf, extref) != parent_objectid) goto next; ret = read_alloc_one_name(leaf, &extref->name, - btrfs_inode_extref_name_len(leaf, extref), - &victim_name); + victim_name.len, &victim_name); if (ret) return ret; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index a4177014eb8b..628238493167 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -3203,6 +3203,12 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans, u64 chunk_offset) device->bytes_used - dev_extent_len); atomic64_add(dev_extent_len, &fs_info->free_chunk_space); btrfs_clear_space_info_full(fs_info); + + if (list_empty(&device->post_commit_list)) { + list_add_tail(&device->post_commit_list, + &trans->transaction->dev_update_list); + } + mutex_unlock(&fs_info->chunk_mutex); } } diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 794526ab90d2..1dff64e62047 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -1909,6 +1909,9 @@ bool btrfs_zone_activate(struct btrfs_block_group *block_group) device = map->stripes[i].dev; physical = map->stripes[i].physical; + if (!device->bdev) + continue; + if (device->zone_info->max_active_zones == 0) continue; @@ -2052,6 +2055,9 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ struct btrfs_device *device = map->stripes[i].dev; const u64 physical = map->stripes[i].physical; + if (!device->bdev) + continue; + if (device->zone_info->max_active_zones == 0) continue; diff --git a/fs/cachefiles/io.c b/fs/cachefiles/io.c index 000a28f46e59..5d2a41bab9c1 100644 --- a/fs/cachefiles/io.c +++ b/fs/cachefiles/io.c @@ -356,8 +356,6 @@ int __cachefiles_write(struct cachefiles_object *object, default: ki->was_async = false; cachefiles_write_complete(&ki->iocb, ret); - if (ret > 0) - ret = 0; break; } diff --git a/fs/cachefiles/ondemand.c b/fs/cachefiles/ondemand.c index 3389a373faf6..cfa8f23fdfb6 100644 --- a/fs/cachefiles/ondemand.c +++ b/fs/cachefiles/ondemand.c @@ -84,10 +84,8 @@ static ssize_t cachefiles_ondemand_fd_write_iter(struct kiocb *kiocb, trace_cachefiles_ondemand_fd_write(object, file_inode(file), pos, len); ret = __cachefiles_write(object, file, pos, iter, NULL, NULL); - if (!ret) { - ret = len; + if (ret > 0) kiocb->ki_pos += ret; - } out: fput(file); diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 882eccfd67e8..3336647e64df 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -2043,7 +2043,7 @@ static int ceph_zero_objects(struct inode *inode, loff_t offset, loff_t length) s32 stripe_unit = ci->i_layout.stripe_unit; s32 stripe_count = ci->i_layout.stripe_count; s32 object_size = ci->i_layout.object_size; - u64 object_set_size = object_size * stripe_count; + u64 object_set_size = (u64) object_size * stripe_count; u64 nearly, t; /* round offset up to next period boundary */ diff --git a/fs/ceph/super.c b/fs/ceph/super.c index bd15991166c2..0f56e4ba7812 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -1136,6 +1136,7 @@ static int ceph_set_super(struct super_block *s, struct fs_context *fc) s->s_time_min = 0; s->s_time_max = U32_MAX; s->s_flags |= SB_NODIRATIME | SB_NOATIME; + s->s_magic = CEPH_SUPER_MAGIC; ret = set_anon_super_fc(s, fc); if (ret != 0) diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index ec6519e1ca3b..e017ba188f7b 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -593,7 +593,7 @@ static int populate_attrs(struct config_item *item) break; } } - if (t->ct_bin_attrs) { + if (!error && t->ct_bin_attrs) { for (i = 0; (bin_attr = t->ct_bin_attrs[i]) != NULL; i++) { error = configfs_create_bin_file(item, bin_attr); if (error) diff --git a/fs/coredump.c b/fs/coredump.c index 4d332f147137..b0d782367fcc 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -42,6 +42,7 @@ #include <linux/timekeeping.h> #include <linux/sysctl.h> #include <linux/elf.h> +#include <uapi/linux/pidfd.h> #include <linux/uaccess.h> #include <asm/mmu_context.h> @@ -56,6 +57,13 @@ static bool dump_vma_snapshot(struct coredump_params *cprm); static void free_vma_snapshot(struct coredump_params *cprm); +/* + * File descriptor number for the pidfd for the thread-group leader of + * the coredumping task installed into the usermode helper's file + * descriptor table. + */ +#define COREDUMP_PIDFD_NUMBER 3 + static int core_uses_pid; static unsigned int core_pipe_limit; static char core_pattern[CORENAME_MAX_SIZE] = "core"; @@ -325,6 +333,27 @@ static int format_corename(struct core_name *cn, struct coredump_params *cprm, err = cn_printf(cn, "%lu", rlimit(RLIMIT_CORE)); break; + /* pidfd number */ + case 'F': { + /* + * Installing a pidfd only makes sense if + * we actually spawn a usermode helper. + */ + if (!ispipe) + break; + + /* + * Note that we'll install a pidfd for the + * thread-group leader. We know that task + * linkage hasn't been removed yet and even if + * this @current isn't the actual thread-group + * leader we know that the thread-group leader + * cannot be reaped until @current has exited. + */ + cprm->pid = task_tgid(current); + err = cn_printf(cn, "%d", COREDUMP_PIDFD_NUMBER); + break; + } default: break; } @@ -479,7 +508,7 @@ static void wait_for_dump_helpers(struct file *file) } /* - * umh_pipe_setup + * umh_coredump_setup * helper function to customize the process used * to collect the core in userspace. Specifically * it sets up a pipe and installs it as fd 0 (stdin) @@ -489,21 +518,61 @@ static void wait_for_dump_helpers(struct file *file) * is a special value that we use to trap recursive * core dumps */ -static int umh_pipe_setup(struct subprocess_info *info, struct cred *new) +static int umh_coredump_setup(struct subprocess_info *info, struct cred *new) { struct file *files[2]; + struct file *pidfs_file = NULL; struct coredump_params *cp = (struct coredump_params *)info->data; - int err = create_pipe_files(files, 0); + int err; + + if (cp->pid) { + int fd; + + fd = pidfd_prepare(cp->pid, 0, &pidfs_file); + if (fd < 0) + return fd; + + /* + * We don't care about the fd. We also cannot simply + * replace it below because dup2() will refuse to close + * this file descriptor if its in a larval state. So + * close it! + */ + put_unused_fd(fd); + + /* + * Usermode helpers are childen of either + * system_unbound_wq or of kthreadd. So we know that + * we're starting off with a clean file descriptor + * table. So we should always be able to use + * COREDUMP_PIDFD_NUMBER as our file descriptor value. + */ + err = replace_fd(COREDUMP_PIDFD_NUMBER, pidfs_file, 0); + if (err < 0) + goto out_fail; + + pidfs_file = NULL; + } + + err = create_pipe_files(files, 0); if (err) - return err; + goto out_fail; cp->file = files[1]; err = replace_fd(0, files[0], 0); fput(files[0]); + if (err < 0) + goto out_fail; + /* and disallow core files too */ current->signal->rlim[RLIMIT_CORE] = (struct rlimit){1, 1}; + err = 0; + +out_fail: + if (pidfs_file) + fput(pidfs_file); return err; } @@ -580,7 +649,7 @@ void do_coredump(const kernel_siginfo_t *siginfo) } if (cprm.limit == 1) { - /* See umh_pipe_setup() which sets RLIMIT_CORE = 1. + /* See umh_coredump_setup() which sets RLIMIT_CORE = 1. * * Normally core limits are irrelevant to pipes, since * we're not writing to the file system, but we use @@ -625,7 +694,7 @@ void do_coredump(const kernel_siginfo_t *siginfo) retval = -ENOMEM; sub_info = call_usermodehelper_setup(helper_argv[0], helper_argv, NULL, GFP_KERNEL, - umh_pipe_setup, NULL, &cprm); + umh_coredump_setup, NULL, &cprm); if (sub_info) retval = call_usermodehelper_exec(sub_info, UMH_WAIT_EXEC); diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c index 2c797eb519da..51a641822d6c 100644 --- a/fs/dlm/lowcomms.c +++ b/fs/dlm/lowcomms.c @@ -1863,8 +1863,8 @@ static int dlm_tcp_listen_validate(void) { /* We don't support multi-homed hosts */ if (dlm_local_count > 1) { - log_print("TCP protocol can't handle multi-homed hosts, try SCTP"); - return -EINVAL; + log_print("Detect multi-homed hosts but use only the first IP address."); + log_print("Try SCTP, if you want to enable multi-link."); } return 0; diff --git a/fs/erofs/data.c b/fs/erofs/data.c index 5c2e6fbb70a3..7b648bec61fd 100644 --- a/fs/erofs/data.c +++ b/fs/erofs/data.c @@ -354,6 +354,8 @@ int erofs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, */ static int erofs_read_folio(struct file *file, struct folio *folio) { + trace_erofs_read_folio(folio, true); + return iomap_read_folio(folio, &erofs_iomap_ops); } diff --git a/fs/erofs/decompressor.c b/fs/erofs/decompressor.c index 0eaa9e495346..e524c0b432f3 100644 --- a/fs/erofs/decompressor.c +++ b/fs/erofs/decompressor.c @@ -323,7 +323,7 @@ static int z_erofs_transform_plain(struct z_erofs_decompress_req *rq, const unsigned int lefthalf = rq->outputsize - righthalf; const unsigned int interlaced_offset = rq->alg == Z_EROFS_COMPRESSION_SHIFTED ? 0 : rq->pageofs_out; - unsigned char *src, *dst; + u8 *src; if (outpages > 2 && rq->alg == Z_EROFS_COMPRESSION_SHIFTED) { DBG_BUGON(1); @@ -336,23 +336,18 @@ static int z_erofs_transform_plain(struct z_erofs_decompress_req *rq, } src = kmap_local_page(rq->in[inpages - 1]) + rq->pageofs_in; - if (rq->out[0]) { - dst = kmap_local_page(rq->out[0]); - memcpy(dst + rq->pageofs_out, src + interlaced_offset, - righthalf); - kunmap_local(dst); - } + if (rq->out[0]) + memcpy_to_page(rq->out[0], rq->pageofs_out, + src + interlaced_offset, righthalf); if (outpages > inpages) { DBG_BUGON(!rq->out[outpages - 1]); - if (rq->out[outpages - 1] != rq->in[inpages - 1]) { - dst = kmap_local_page(rq->out[outpages - 1]); - memcpy(dst, interlaced_offset ? src : - (src + righthalf), lefthalf); - kunmap_local(dst); - } else if (!interlaced_offset) { + if (rq->out[outpages - 1] != rq->in[inpages - 1]) + memcpy_to_page(rq->out[outpages - 1], 0, src + + (interlaced_offset ? 0 : righthalf), + lefthalf); + else if (!interlaced_offset) memmove(src, src + righthalf, lefthalf); - } } kunmap_local(src); return 0; diff --git a/fs/erofs/dir.c b/fs/erofs/dir.c index 966a88cc529e..963bbed0b699 100644 --- a/fs/erofs/dir.c +++ b/fs/erofs/dir.c @@ -6,21 +6,6 @@ */ #include "internal.h" -static void debug_one_dentry(unsigned char d_type, const char *de_name, - unsigned int de_namelen) -{ -#ifdef CONFIG_EROFS_FS_DEBUG - /* since the on-disk name could not have the trailing '\0' */ - unsigned char dbg_namebuf[EROFS_NAME_LEN + 1]; - - memcpy(dbg_namebuf, de_name, de_namelen); - dbg_namebuf[de_namelen] = '\0'; - - erofs_dbg("found dirent %s de_len %u d_type %d", dbg_namebuf, - de_namelen, d_type); -#endif -} - static int erofs_fill_dentries(struct inode *dir, struct dir_context *ctx, void *dentry_blk, struct erofs_dirent *de, unsigned int nameoff, unsigned int maxsize) @@ -52,10 +37,8 @@ static int erofs_fill_dentries(struct inode *dir, struct dir_context *ctx, return -EFSCORRUPTED; } - debug_one_dentry(d_type, de_name, de_namelen); if (!dir_emit(ctx, de_name, de_namelen, le64_to_cpu(de->nid), d_type)) - /* stopped by some reason */ return 1; ++de; ctx->pos += sizeof(struct erofs_dirent); diff --git a/fs/erofs/inode.c b/fs/erofs/inode.c index 7dcf350b9fef..3cbef6318b7b 100644 --- a/fs/erofs/inode.c +++ b/fs/erofs/inode.c @@ -26,9 +26,6 @@ static void *erofs_read_inode(struct erofs_buf *buf, blkaddr = erofs_blknr(sb, inode_loc); *ofs = erofs_blkoff(sb, inode_loc); - erofs_dbg("%s, reading inode nid %llu at %u of blkaddr %u", - __func__, vi->nid, *ofs, blkaddr); - kaddr = erofs_read_metabuf(buf, sb, blkaddr, EROFS_KMAP); if (IS_ERR(kaddr)) { erofs_err(sb, "failed to get inode (nid: %llu) page, err %ld", diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index d7cd1e619d46..126970932805 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -32,10 +32,8 @@ __printf(3, 4) void _erofs_info(struct super_block *sb, #define erofs_info(sb, fmt, ...) \ _erofs_info(sb, __func__, fmt "\n", ##__VA_ARGS__) #ifdef CONFIG_EROFS_FS_DEBUG -#define erofs_dbg(x, ...) pr_debug(x "\n", ##__VA_ARGS__) #define DBG_BUGON BUG_ON #else -#define erofs_dbg(x, ...) ((void)0) #define DBG_BUGON(x) ((void)(x)) #endif /* !CONFIG_EROFS_FS_DEBUG */ diff --git a/fs/erofs/namei.c b/fs/erofs/namei.c index 8332428b780c..c0d5ffb62420 100644 --- a/fs/erofs/namei.c +++ b/fs/erofs/namei.c @@ -203,16 +203,13 @@ static struct dentry *erofs_lookup(struct inode *dir, struct dentry *dentry, err = erofs_namei(dir, &dentry->d_name, &nid, &d_type); - if (err == -ENOENT) { + if (err == -ENOENT) /* negative dentry */ inode = NULL; - } else if (err) { + else if (err) inode = ERR_PTR(err); - } else { - erofs_dbg("%s, %pd (nid %llu) found, d_type %u", __func__, - dentry, nid, d_type); + else inode = erofs_iget(dir->i_sb, nid); - } return d_splice_alias(inode, dentry); } diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 94e9e0bf3bbd..5e6580217318 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -5,7 +5,6 @@ * Copyright (C) 2022 Alibaba Cloud */ #include "compress.h" -#include <linux/prefetch.h> #include <linux/psi.h> #include <trace/events/erofs.h> @@ -124,9 +123,11 @@ static inline unsigned int z_erofs_pclusterpages(struct z_erofs_pcluster *pcl) /* * bit 30: I/O error occurred on this page + * bit 29: CPU has dirty data in D-cache (needs aliasing handling); * bit 0 - 29: remaining parts to complete this page */ -#define Z_EROFS_PAGE_EIO (1 << 30) +#define Z_EROFS_ONLINEPAGE_EIO 30 +#define Z_EROFS_ONLINEPAGE_DIRTY 29 static inline void z_erofs_onlinepage_init(struct page *page) { @@ -145,29 +146,28 @@ static inline void z_erofs_onlinepage_split(struct page *page) atomic_inc((atomic_t *)&page->private); } -static inline void z_erofs_page_mark_eio(struct page *page) +static void z_erofs_onlinepage_end(struct page *page, int err, bool dirty) { - int orig; + int orig, v; + + DBG_BUGON(!PagePrivate(page)); do { orig = atomic_read((atomic_t *)&page->private); - } while (atomic_cmpxchg((atomic_t *)&page->private, orig, - orig | Z_EROFS_PAGE_EIO) != orig); -} - -static inline void z_erofs_onlinepage_endio(struct page *page) -{ - unsigned int v; + DBG_BUGON(orig <= 0); + v = dirty << Z_EROFS_ONLINEPAGE_DIRTY; + v |= (orig - 1) | (!!err << Z_EROFS_ONLINEPAGE_EIO); + } while (atomic_cmpxchg((atomic_t *)&page->private, orig, v) != orig); - DBG_BUGON(!PagePrivate(page)); - v = atomic_dec_return((atomic_t *)&page->private); - if (!(v & ~Z_EROFS_PAGE_EIO)) { - set_page_private(page, 0); - ClearPagePrivate(page); - if (!(v & Z_EROFS_PAGE_EIO)) - SetPageUptodate(page); - unlock_page(page); - } + if (v & (BIT(Z_EROFS_ONLINEPAGE_DIRTY) - 1)) + return; + set_page_private(page, 0); + ClearPagePrivate(page); + if (v & BIT(Z_EROFS_ONLINEPAGE_DIRTY)) + flush_dcache_page(page); + if (!(v & BIT(Z_EROFS_ONLINEPAGE_EIO))) + SetPageUptodate(page); + unlock_page(page); } #define Z_EROFS_ONSTACK_PAGES 32 @@ -237,14 +237,20 @@ static void z_erofs_bvec_iter_begin(struct z_erofs_bvec_iter *iter, static int z_erofs_bvec_enqueue(struct z_erofs_bvec_iter *iter, struct z_erofs_bvec *bvec, - struct page **candidate_bvpage) + struct page **candidate_bvpage, + struct page **pagepool) { - if (iter->cur == iter->nr) { - if (!*candidate_bvpage) - return -EAGAIN; - + if (iter->cur >= iter->nr) { + struct page *nextpage = *candidate_bvpage; + + if (!nextpage) { + nextpage = erofs_allocpage(pagepool, GFP_NOFS); + if (!nextpage) + return -ENOMEM; + set_page_private(nextpage, Z_EROFS_SHORTLIVED_PAGE); + } DBG_BUGON(iter->bvset->nextpage); - iter->bvset->nextpage = *candidate_bvpage; + iter->bvset->nextpage = nextpage; z_erofs_bvset_flip(iter); iter->bvset->nextpage = NULL; @@ -402,12 +408,12 @@ struct z_erofs_decompress_frontend { struct erofs_map_blocks map; struct z_erofs_bvec_iter biter; + struct page *pagepool; struct page *candidate_bvpage; struct z_erofs_pcluster *pcl; z_erofs_next_pcluster_t owned_head; enum z_erofs_pclustermode mode; - bool readahead; /* used for applying cache strategy on the fly */ bool backmost; erofs_off_t headoffset; @@ -437,8 +443,7 @@ static bool z_erofs_should_alloc_cache(struct z_erofs_decompress_frontend *fe) return false; } -static void z_erofs_bind_cache(struct z_erofs_decompress_frontend *fe, - struct page **pagepool) +static void z_erofs_bind_cache(struct z_erofs_decompress_frontend *fe) { struct address_space *mc = MNGD_MAPPING(EROFS_I_SB(fe->inode)); struct z_erofs_pcluster *pcl = fe->pcl; @@ -479,7 +484,7 @@ static void z_erofs_bind_cache(struct z_erofs_decompress_frontend *fe, * succeeds or fallback to in-place I/O instead * to avoid any direct reclaim. */ - newpage = erofs_allocpage(pagepool, gfp); + newpage = erofs_allocpage(&fe->pagepool, gfp); if (!newpage) continue; set_page_private(newpage, Z_EROFS_PREALLOCATED_PAGE); @@ -492,7 +497,7 @@ static void z_erofs_bind_cache(struct z_erofs_decompress_frontend *fe, if (page) put_page(page); else if (newpage) - erofs_pagepool_add(pagepool, newpage); + erofs_pagepool_add(&fe->pagepool, newpage); } /* @@ -590,7 +595,8 @@ static int z_erofs_attach_page(struct z_erofs_decompress_frontend *fe, !fe->candidate_bvpage) fe->candidate_bvpage = bvec->page; } - ret = z_erofs_bvec_enqueue(&fe->biter, bvec, &fe->candidate_bvpage); + ret = z_erofs_bvec_enqueue(&fe->biter, bvec, &fe->candidate_bvpage, + &fe->pagepool); fe->pcl->vcnt += (ret >= 0); return ret; } @@ -746,10 +752,8 @@ static bool z_erofs_collector_end(struct z_erofs_decompress_frontend *fe) z_erofs_bvec_iter_end(&fe->biter); mutex_unlock(&pcl->lock); - if (fe->candidate_bvpage) { - DBG_BUGON(z_erofs_is_shortlived_page(fe->candidate_bvpage)); + if (fe->candidate_bvpage) fe->candidate_bvpage = NULL; - } /* * if all pending pages are added, don't hold its reference @@ -796,7 +800,7 @@ static int z_erofs_read_fragment(struct inode *inode, erofs_off_t pos, } static int z_erofs_do_read_page(struct z_erofs_decompress_frontend *fe, - struct page *page, struct page **pagepool) + struct page *page) { struct inode *const inode = fe->inode; struct erofs_map_blocks *const map = &fe->map; @@ -815,8 +819,6 @@ repeat: if (offset + cur < map->m_la || offset + cur >= map->m_la + map->m_llen) { - erofs_dbg("out-of-range map @ pos %llu", offset + cur); - if (z_erofs_collector_end(fe)) fe->backmost = false; map->m_la = offset + cur; @@ -857,7 +859,7 @@ repeat: fe->mode = Z_EROFS_PCLUSTER_FOLLOWED_NOINPLACE; } else { /* bind cache first when cached decompression is preferred */ - z_erofs_bind_cache(fe, pagepool); + z_erofs_bind_cache(fe); } hitted: /* @@ -898,24 +900,13 @@ hitted: if (cur) tight &= (fe->mode >= Z_EROFS_PCLUSTER_FOLLOWED); -retry: err = z_erofs_attach_page(fe, &((struct z_erofs_bvec) { .page = page, .offset = offset - map->m_la, .end = end, }), exclusive); - /* should allocate an additional short-lived page for bvset */ - if (err == -EAGAIN && !fe->candidate_bvpage) { - fe->candidate_bvpage = alloc_page(GFP_NOFS | __GFP_NOFAIL); - set_page_private(fe->candidate_bvpage, - Z_EROFS_SHORTLIVED_PAGE); - goto retry; - } - - if (err) { - DBG_BUGON(err == -EAGAIN && fe->candidate_bvpage); + if (err) goto out; - } z_erofs_onlinepage_split(page); /* bump up the number of spiltted parts of a page */ @@ -940,16 +931,11 @@ next_part: goto repeat; out: - if (err) - z_erofs_page_mark_eio(page); - z_erofs_onlinepage_endio(page); - - erofs_dbg("%s, finish page: %pK spiltted: %u map->m_llen %llu", - __func__, page, spiltted, map->m_llen); + z_erofs_onlinepage_end(page, err, false); return err; } -static bool z_erofs_get_sync_decompress_policy(struct erofs_sb_info *sbi, +static bool z_erofs_is_sync_decompress(struct erofs_sb_info *sbi, unsigned int readahead_pages) { /* auto: enable for read_folio, disable for readahead */ @@ -1048,9 +1034,7 @@ static void z_erofs_fill_other_copies(struct z_erofs_decompress_backend *be, cur += len; } kunmap_local(dst); - if (err) - z_erofs_page_mark_eio(bvi->bvec.page); - z_erofs_onlinepage_endio(bvi->bvec.page); + z_erofs_onlinepage_end(bvi->bvec.page, err, true); list_del(p); kfree(bvi); } @@ -1218,9 +1202,7 @@ out: /* recycle all individual short-lived pages */ if (z_erofs_put_shortlivedpage(be->pagepool, page)) continue; - if (err) - z_erofs_page_mark_eio(page); - z_erofs_onlinepage_endio(page); + z_erofs_onlinepage_end(page, err, true); } if (be->decompressed_pages != be->onstack_pages) @@ -1480,9 +1462,8 @@ static void z_erofs_decompressqueue_endio(struct bio *bio) } static void z_erofs_submit_queue(struct z_erofs_decompress_frontend *f, - struct page **pagepool, struct z_erofs_decompressqueue *fgq, - bool *force_fg) + bool *force_fg, bool readahead) { struct super_block *sb = f->inode->i_sb; struct address_space *mc = MNGD_MAPPING(EROFS_SB(sb)); @@ -1538,8 +1519,8 @@ static void z_erofs_submit_queue(struct z_erofs_decompress_frontend *f, do { struct page *page; - page = pickup_page_for_submission(pcl, i++, pagepool, - mc); + page = pickup_page_for_submission(pcl, i++, + &f->pagepool, mc); if (!page) continue; @@ -1568,7 +1549,7 @@ submit_bio_retry: bio->bi_iter.bi_sector = (sector_t)cur << (sb->s_blocksize_bits - 9); bio->bi_private = q[JQ_SUBMIT]; - if (f->readahead) + if (readahead) bio->bi_opf |= REQ_RAHEAD; ++nr_bios; } @@ -1604,16 +1585,16 @@ submit_bio_retry: } static void z_erofs_runqueue(struct z_erofs_decompress_frontend *f, - struct page **pagepool, bool force_fg) + bool force_fg, bool ra) { struct z_erofs_decompressqueue io[NR_JOBQUEUES]; if (f->owned_head == Z_EROFS_PCLUSTER_TAIL) return; - z_erofs_submit_queue(f, pagepool, io, &force_fg); + z_erofs_submit_queue(f, io, &force_fg, ra); /* handle bypass queue (no i/o pclusters) immediately */ - z_erofs_decompress_queue(&io[JQ_BYPASS], pagepool); + z_erofs_decompress_queue(&io[JQ_BYPASS], &f->pagepool); if (!force_fg) return; @@ -1622,7 +1603,7 @@ static void z_erofs_runqueue(struct z_erofs_decompress_frontend *f, wait_for_completion_io(&io[JQ_SUBMIT].u.done); /* handle synchronous decompress queue in the caller context */ - z_erofs_decompress_queue(&io[JQ_SUBMIT], pagepool); + z_erofs_decompress_queue(&io[JQ_SUBMIT], &f->pagepool); } /* @@ -1630,29 +1611,28 @@ static void z_erofs_runqueue(struct z_erofs_decompress_frontend *f, * approximate readmore strategies as a start. */ static void z_erofs_pcluster_readmore(struct z_erofs_decompress_frontend *f, - struct readahead_control *rac, - erofs_off_t end, - struct page **pagepool, - bool backmost) + struct readahead_control *rac, bool backmost) { struct inode *inode = f->inode; struct erofs_map_blocks *map = &f->map; - erofs_off_t cur; + erofs_off_t cur, end, headoffset = f->headoffset; int err; if (backmost) { + if (rac) + end = headoffset + readahead_length(rac) - 1; + else + end = headoffset + PAGE_SIZE - 1; map->m_la = end; err = z_erofs_map_blocks_iter(inode, map, EROFS_GET_BLOCKS_READMORE); if (err) return; - /* expend ra for the trailing edge if readahead */ + /* expand ra for the trailing edge if readahead */ if (rac) { - loff_t newstart = readahead_pos(rac); - cur = round_up(map->m_la + map->m_llen, PAGE_SIZE); - readahead_expand(rac, newstart, cur - newstart); + readahead_expand(rac, headoffset, cur - headoffset); return; } end = round_up(end, PAGE_SIZE); @@ -1673,7 +1653,7 @@ static void z_erofs_pcluster_readmore(struct z_erofs_decompress_frontend *f, if (PageUptodate(page)) { unlock_page(page); } else { - err = z_erofs_do_read_page(f, page, pagepool); + err = z_erofs_do_read_page(f, page); if (err) erofs_err(inode->i_sb, "readmore error at page %lu @ nid %llu", @@ -1690,32 +1670,27 @@ static void z_erofs_pcluster_readmore(struct z_erofs_decompress_frontend *f, static int z_erofs_read_folio(struct file *file, struct folio *folio) { - struct page *page = &folio->page; - struct inode *const inode = page->mapping->host; + struct inode *const inode = folio->mapping->host; struct erofs_sb_info *const sbi = EROFS_I_SB(inode); struct z_erofs_decompress_frontend f = DECOMPRESS_FRONTEND_INIT(inode); - struct page *pagepool = NULL; int err; - trace_erofs_readpage(page, false); - f.headoffset = (erofs_off_t)page->index << PAGE_SHIFT; - - z_erofs_pcluster_readmore(&f, NULL, f.headoffset + PAGE_SIZE - 1, - &pagepool, true); - err = z_erofs_do_read_page(&f, page, &pagepool); - z_erofs_pcluster_readmore(&f, NULL, 0, &pagepool, false); + trace_erofs_read_folio(folio, false); + f.headoffset = (erofs_off_t)folio->index << PAGE_SHIFT; + z_erofs_pcluster_readmore(&f, NULL, true); + err = z_erofs_do_read_page(&f, &folio->page); + z_erofs_pcluster_readmore(&f, NULL, false); (void)z_erofs_collector_end(&f); /* if some compressed cluster ready, need submit them anyway */ - z_erofs_runqueue(&f, &pagepool, - z_erofs_get_sync_decompress_policy(sbi, 0)); + z_erofs_runqueue(&f, z_erofs_is_sync_decompress(sbi, 0), false); if (err) erofs_err(inode->i_sb, "failed to read, err [%d]", err); erofs_put_metabuf(&f.map.buf); - erofs_release_pages(&pagepool); + erofs_release_pages(&f.pagepool); return err; } @@ -1724,14 +1699,12 @@ static void z_erofs_readahead(struct readahead_control *rac) struct inode *const inode = rac->mapping->host; struct erofs_sb_info *const sbi = EROFS_I_SB(inode); struct z_erofs_decompress_frontend f = DECOMPRESS_FRONTEND_INIT(inode); - struct page *pagepool = NULL, *head = NULL, *page; + struct page *head = NULL, *page; unsigned int nr_pages; - f.readahead = true; f.headoffset = readahead_pos(rac); - z_erofs_pcluster_readmore(&f, rac, f.headoffset + - readahead_length(rac) - 1, &pagepool, true); + z_erofs_pcluster_readmore(&f, rac, true); nr_pages = readahead_count(rac); trace_erofs_readpages(inode, readahead_index(rac), nr_pages, false); @@ -1747,20 +1720,19 @@ static void z_erofs_readahead(struct readahead_control *rac) /* traversal in reverse order */ head = (void *)page_private(page); - err = z_erofs_do_read_page(&f, page, &pagepool); + err = z_erofs_do_read_page(&f, page); if (err) erofs_err(inode->i_sb, "readahead error at page %lu @ nid %llu", page->index, EROFS_I(inode)->nid); put_page(page); } - z_erofs_pcluster_readmore(&f, rac, 0, &pagepool, false); + z_erofs_pcluster_readmore(&f, rac, false); (void)z_erofs_collector_end(&f); - z_erofs_runqueue(&f, &pagepool, - z_erofs_get_sync_decompress_policy(sbi, nr_pages)); + z_erofs_runqueue(&f, z_erofs_is_sync_decompress(sbi, nr_pages), true); erofs_put_metabuf(&f.map.buf); - erofs_release_pages(&pagepool); + erofs_release_pages(&f.pagepool); } const struct address_space_operations z_erofs_aops = { diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c index 2cd70cf4c8b2..d2d7fe826091 100644 --- a/fs/erofs/zmap.c +++ b/fs/erofs/zmap.c @@ -603,9 +603,6 @@ static int z_erofs_do_map_blocks(struct inode *inode, unmap_out: erofs_unmap_metabuf(&m.map->buf); - erofs_dbg("%s, m_la %llu m_pa %llu m_llen %llu m_plen %llu m_flags 0%o", - __func__, map->m_la, map->m_pa, - map->m_llen, map->m_plen, map->m_flags); return err; } diff --git a/fs/exec.c b/fs/exec.c index 2039414cc662..b65af8f9a4f9 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -169,7 +169,7 @@ SYSCALL_DEFINE1(uselib, const char __user *, library) exit: fput(file); out: - return error; + return error; } #endif /* #ifdef CONFIG_USELIB */ diff --git a/fs/exfat/balloc.c b/fs/exfat/balloc.c index 5b547a596380..32209acd51be 100644 --- a/fs/exfat/balloc.c +++ b/fs/exfat/balloc.c @@ -160,7 +160,7 @@ int exfat_set_bitmap(struct inode *inode, unsigned int clu, bool sync) return 0; } -void exfat_clear_bitmap(struct inode *inode, unsigned int clu, bool sync) +int exfat_clear_bitmap(struct inode *inode, unsigned int clu, bool sync) { int i, b; unsigned int ent_idx; @@ -169,13 +169,17 @@ void exfat_clear_bitmap(struct inode *inode, unsigned int clu, bool sync) struct exfat_mount_options *opts = &sbi->options; if (!is_valid_cluster(sbi, clu)) - return; + return -EIO; ent_idx = CLUSTER_TO_BITMAP_ENT(clu); i = BITMAP_OFFSET_SECTOR_INDEX(sb, ent_idx); b = BITMAP_OFFSET_BIT_IN_SECTOR(sb, ent_idx); + if (!test_bit_le(b, sbi->vol_amap[i]->b_data)) + return -EIO; + clear_bit_le(b, sbi->vol_amap[i]->b_data); + exfat_update_bh(sbi->vol_amap[i], sync); if (opts->discard) { @@ -190,6 +194,8 @@ void exfat_clear_bitmap(struct inode *inode, unsigned int clu, bool sync) opts->discard = 0; } } + + return 0; } /* diff --git a/fs/exfat/exfat_fs.h b/fs/exfat/exfat_fs.h index c79c78bf265b..5a1251207ab2 100644 --- a/fs/exfat/exfat_fs.h +++ b/fs/exfat/exfat_fs.h @@ -419,7 +419,7 @@ int exfat_count_num_clusters(struct super_block *sb, int exfat_load_bitmap(struct super_block *sb); void exfat_free_bitmap(struct exfat_sb_info *sbi); int exfat_set_bitmap(struct inode *inode, unsigned int clu, bool sync); -void exfat_clear_bitmap(struct inode *inode, unsigned int clu, bool sync); +int exfat_clear_bitmap(struct inode *inode, unsigned int clu, bool sync); unsigned int exfat_find_free_bitmap(struct super_block *sb, unsigned int clu); int exfat_count_used_clusters(struct super_block *sb, unsigned int *ret_count); int exfat_trim_fs(struct inode *inode, struct fstrim_range *range); diff --git a/fs/exfat/fatent.c b/fs/exfat/fatent.c index fe007ae2f23c..9fa4cffabfb6 100644 --- a/fs/exfat/fatent.c +++ b/fs/exfat/fatent.c @@ -175,6 +175,7 @@ static int __exfat_free_cluster(struct inode *inode, struct exfat_chain *p_chain BITMAP_OFFSET_SECTOR_INDEX(sb, CLUSTER_TO_BITMAP_ENT(clu)); if (p_chain->flags == ALLOC_NO_FAT_CHAIN) { + int err; unsigned int last_cluster = p_chain->dir + p_chain->size - 1; do { bool sync = false; @@ -189,7 +190,9 @@ static int __exfat_free_cluster(struct inode *inode, struct exfat_chain *p_chain cur_cmap_i = next_cmap_i; } - exfat_clear_bitmap(inode, clu, (sync && IS_DIRSYNC(inode))); + err = exfat_clear_bitmap(inode, clu, (sync && IS_DIRSYNC(inode))); + if (err) + break; clu++; num_clusters++; } while (num_clusters < p_chain->size); @@ -210,12 +213,13 @@ static int __exfat_free_cluster(struct inode *inode, struct exfat_chain *p_chain cur_cmap_i = next_cmap_i; } - exfat_clear_bitmap(inode, clu, (sync && IS_DIRSYNC(inode))); + if (exfat_clear_bitmap(inode, clu, (sync && IS_DIRSYNC(inode)))) + break; clu = n_clu; num_clusters++; if (err) - goto dec_used_clus; + break; if (num_clusters >= sbi->num_clusters - EXFAT_FIRST_CLUSTER) { /* @@ -229,7 +233,6 @@ static int __exfat_free_cluster(struct inode *inode, struct exfat_chain *p_chain } while (clu != EXFAT_EOF_CLUSTER); } -dec_used_clus: sbi->used_clusters -= num_clusters; return 0; } @@ -262,7 +265,7 @@ int exfat_find_last_cluster(struct super_block *sb, struct exfat_chain *p_chain, clu = next; if (exfat_ent_get(sb, clu, &next)) return -EIO; - } while (next != EXFAT_EOF_CLUSTER); + } while (next != EXFAT_EOF_CLUSTER && count <= p_chain->size); if (p_chain->size != count) { exfat_fs_error(sb, diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index fbd0329cf254..9efe97f3721b 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -638,8 +638,8 @@ static int ext4_has_free_clusters(struct ext4_sb_info *sbi, /* Hm, nope. Are (enough) root reserved clusters available? */ if (uid_eq(sbi->s_resuid, current_fsuid()) || (!gid_eq(sbi->s_resgid, GLOBAL_ROOT_GID) && in_group_p(sbi->s_resgid)) || - capable(CAP_SYS_RESOURCE) || - (flags & EXT4_MB_USE_ROOT_BLOCKS)) { + (flags & EXT4_MB_USE_ROOT_BLOCKS) || + capable(CAP_SYS_RESOURCE)) { if (free_clusters >= (nclusters + dirty_clusters + resv_clusters)) diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c index 6fe3c941b565..4d6ba140276b 100644 --- a/fs/ext4/block_validity.c +++ b/fs/ext4/block_validity.c @@ -351,10 +351,9 @@ int ext4_check_blockref(const char *function, unsigned int line, { __le32 *bref = p; unsigned int blk; + journal_t *journal = EXT4_SB(inode->i_sb)->s_journal; - if (ext4_has_feature_journal(inode->i_sb) && - (inode->i_ino == - le32_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_journal_inum))) + if (journal && inode == journal->j_inode) return 0; while (bref < p+max) { diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index 7ea33c3fe94e..6682b8ab11f1 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -104,6 +104,9 @@ int __ext4_check_dir_entry(const char *function, unsigned int line, else if (unlikely(le32_to_cpu(de->inode) > le32_to_cpu(EXT4_SB(dir->i_sb)->s_es->s_inodes_count))) error_msg = "inode out of bounds"; + else if (unlikely(next_offset == size && de->name_len == 1 && + de->name[0] == '.')) + error_msg = "'.' directory cannot be the last in data block"; else return 0; diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index faa889882e55..903bb01e6dd2 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -3354,6 +3354,13 @@ static inline unsigned int ext4_flex_bg_size(struct ext4_sb_info *sbi) return 1 << sbi->s_log_groups_per_flex; } +static inline loff_t ext4_get_maxbytes(struct inode *inode) +{ + if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) + return inode->i_sb->s_maxbytes; + return EXT4_SB(inode->i_sb)->s_bitmap_maxbytes; +} + #define ext4_std_error(sb, errno) \ do { \ if ((errno)) \ diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 53fd2431062c..1aad4ae0e7ae 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -2374,18 +2374,19 @@ int ext4_ext_calc_credits_for_single_extent(struct inode *inode, int nrblocks, int ext4_ext_index_trans_blocks(struct inode *inode, int extents) { int index; - int depth; /* If we are converting the inline data, only one is needed here. */ if (ext4_has_inline_data(inode)) return 1; - depth = ext_depth(inode); - + /* + * Extent tree can change between the time we estimate credits and + * the time we actually modify the tree. Assume the worst case. + */ if (extents <= 1) - index = depth * 2; + index = EXT4_MAX_EXTENT_DEPTH * 2; else - index = depth * 3; + index = EXT4_MAX_EXTENT_DEPTH * 3; return index; } @@ -4973,12 +4974,7 @@ static const struct iomap_ops ext4_iomap_xattr_ops = { static int ext4_fiemap_check_ranges(struct inode *inode, u64 start, u64 *len) { - u64 maxbytes; - - if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) - maxbytes = inode->i_sb->s_maxbytes; - else - maxbytes = EXT4_SB(inode->i_sb)->s_bitmap_maxbytes; + u64 maxbytes = ext4_get_maxbytes(inode); if (*len == 0) return -EINVAL; diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 202101c2cb05..289b088f4ae5 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -880,12 +880,7 @@ static int ext4_file_open(struct inode *inode, struct file *filp) loff_t ext4_llseek(struct file *file, loff_t offset, int whence) { struct inode *inode = file->f_mapping->host; - loff_t maxbytes; - - if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) - maxbytes = EXT4_SB(inode->i_sb)->s_bitmap_maxbytes; - else - maxbytes = inode->i_sb->s_maxbytes; + loff_t maxbytes = ext4_get_maxbytes(inode); switch (whence) { default: diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 7c9efc9330fe..312be3d7cfb3 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -393,7 +393,7 @@ out: } static int ext4_prepare_inline_data(handle_t *handle, struct inode *inode, - unsigned int len) + loff_t len) { int ret, size, no_expand; struct ext4_inode_info *ei = EXT4_I(inode); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 694af768ac5b..055216f9f464 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -406,10 +406,11 @@ static int __check_block_validity(struct inode *inode, const char *func, unsigned int line, struct ext4_map_blocks *map) { - if (ext4_has_feature_journal(inode->i_sb) && - (inode->i_ino == - le32_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_journal_inum))) + journal_t *journal = EXT4_SB(inode->i_sb)->s_journal; + + if (journal && inode == journal->j_inode) return 0; + if (!ext4_inode_block_valid(inode, map->m_pblk, map->m_len)) { ext4_error_inode(inode, func, line, map->m_pblk, "lblock %lu mapped to illegal pblock %llu " @@ -4776,22 +4777,43 @@ static inline void ext4_inode_set_iversion_queried(struct inode *inode, u64 val) inode_set_iversion_queried(inode, val); } -static const char *check_igot_inode(struct inode *inode, ext4_iget_flags flags) - +static int check_igot_inode(struct inode *inode, ext4_iget_flags flags, + const char *function, unsigned int line) { + const char *err_str; + if (flags & EXT4_IGET_EA_INODE) { - if (!(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) - return "missing EA_INODE flag"; + if (!(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) { + err_str = "missing EA_INODE flag"; + goto error; + } if (ext4_test_inode_state(inode, EXT4_STATE_XATTR) || - EXT4_I(inode)->i_file_acl) - return "ea_inode with extended attributes"; + EXT4_I(inode)->i_file_acl) { + err_str = "ea_inode with extended attributes"; + goto error; + } } else { - if ((EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) - return "unexpected EA_INODE flag"; + if ((EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) { + /* + * open_by_handle_at() could provide an old inode number + * that has since been reused for an ea_inode; this does + * not indicate filesystem corruption + */ + if (flags & EXT4_IGET_HANDLE) + return -ESTALE; + err_str = "unexpected EA_INODE flag"; + goto error; + } + } + if (is_bad_inode(inode) && !(flags & EXT4_IGET_BAD)) { + err_str = "unexpected bad inode w/o EXT4_IGET_BAD"; + goto error; } - if (is_bad_inode(inode) && !(flags & EXT4_IGET_BAD)) - return "unexpected bad inode w/o EXT4_IGET_BAD"; - return NULL; + return 0; + +error: + ext4_error_inode(inode, function, line, 0, err_str); + return -EFSCORRUPTED; } struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, @@ -4803,7 +4825,6 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, struct ext4_inode_info *ei; struct ext4_super_block *es = EXT4_SB(sb)->s_es; struct inode *inode; - const char *err_str; journal_t *journal = EXT4_SB(sb)->s_journal; long ret; loff_t size; @@ -4832,10 +4853,10 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, if (!inode) return ERR_PTR(-ENOMEM); if (!(inode->i_state & I_NEW)) { - if ((err_str = check_igot_inode(inode, flags)) != NULL) { - ext4_error_inode(inode, function, line, 0, err_str); + ret = check_igot_inode(inode, flags, function, line); + if (ret) { iput(inode); - return ERR_PTR(-EFSCORRUPTED); + return ERR_PTR(ret); } return inode; } @@ -4947,7 +4968,8 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, ei->i_file_acl |= ((__u64)le16_to_cpu(raw_inode->i_file_acl_high)) << 32; inode->i_size = ext4_isize(sb, raw_inode); - if ((size = i_size_read(inode)) < 0) { + size = i_size_read(inode); + if (size < 0 || size > ext4_get_maxbytes(inode)) { ext4_error_inode(inode, function, line, 0, "iget: bad i_size value: %lld", size); ret = -EFSCORRUPTED; @@ -5107,13 +5129,21 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, ret = -EFSCORRUPTED; goto bad_inode; } - if ((err_str = check_igot_inode(inode, flags)) != NULL) { - ext4_error_inode(inode, function, line, 0, err_str); - ret = -EFSCORRUPTED; - goto bad_inode; + ret = check_igot_inode(inode, flags, function, line); + /* + * -ESTALE here means there is nothing inherently wrong with the inode, + * it's just not an inode we can return for an fhandle lookup. + */ + if (ret == -ESTALE) { + brelse(iloc.bh); + unlock_new_inode(inode); + iput(inode); + return ERR_PTR(-ESTALE); } - + if (ret) + goto bad_inode; brelse(iloc.bh); + unlock_new_inode(inode); return inode; diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index b6a8b6c851cc..b8683c5acffe 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2041,7 +2041,7 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir, * split it in half by count; each resulting block will have at least * half the space free. */ - if (i > 0) + if (i >= 0) split = count - move; else split = count/2; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 53f1deb049ec..f829f989f2b5 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2741,6 +2741,13 @@ static int ext4_check_opt_consistency(struct fs_context *fc, } if (is_remount) { + if (!sbi->s_journal && + ctx_test_mount_opt(ctx, EXT4_MOUNT_DATA_ERR_ABORT)) { + ext4_msg(NULL, KERN_WARNING, + "Remounting fs w/o journal so ignoring data_err option"); + ctx_clear_mount_opt(ctx, EXT4_MOUNT_DATA_ERR_ABORT); + } + if (ctx_test_mount_opt(ctx, EXT4_MOUNT_DAX_ALWAYS) && (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)) { ext4_msg(NULL, KERN_ERR, "can't mount with " @@ -5318,6 +5325,11 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) "data=, fs mounted w/o journal"); goto failed_mount3a; } + if (test_opt(sb, DATA_ERR_ABORT)) { + ext4_msg(sb, KERN_ERR, + "can't mount with data_err=abort, fs mounted w/o journal"); + goto failed_mount3a; + } sbi->s_def_mount_opt &= ~EXT4_MOUNT_JOURNAL_CHECKSUM; clear_opt(sb, JOURNAL_CHECKSUM); clear_opt(sb, DATA_FLAGS); @@ -6685,22 +6697,29 @@ static int ext4_statfs_project(struct super_block *sb, dquot->dq_dqb.dqb_bhardlimit); limit >>= sb->s_blocksize_bits; - if (limit && buf->f_blocks > limit) { + if (limit) { + uint64_t remaining = 0; + curblock = (dquot->dq_dqb.dqb_curspace + dquot->dq_dqb.dqb_rsvspace) >> sb->s_blocksize_bits; - buf->f_blocks = limit; - buf->f_bfree = buf->f_bavail = - (buf->f_blocks > curblock) ? - (buf->f_blocks - curblock) : 0; + if (limit > curblock) + remaining = limit - curblock; + + buf->f_blocks = min(buf->f_blocks, limit); + buf->f_bfree = min(buf->f_bfree, remaining); + buf->f_bavail = min(buf->f_bavail, remaining); } limit = min_not_zero(dquot->dq_dqb.dqb_isoftlimit, dquot->dq_dqb.dqb_ihardlimit); - if (limit && buf->f_files > limit) { - buf->f_files = limit; - buf->f_ffree = - (buf->f_files > dquot->dq_dqb.dqb_curinodes) ? - (buf->f_files - dquot->dq_dqb.dqb_curinodes) : 0; + if (limit) { + uint64_t remaining = 0; + + if (limit > dquot->dq_dqb.dqb_curinodes) + remaining = limit - dquot->dq_dqb.dqb_curinodes; + + buf->f_files = min(buf->f_files, limit); + buf->f_ffree = min(buf->f_ffree, remaining); } spin_unlock(&dquot->dq_dqb_lock); @@ -6803,12 +6822,25 @@ static int ext4_release_dquot(struct dquot *dquot) { int ret, err; handle_t *handle; + bool freeze_protected = false; + + /* + * Trying to sb_start_intwrite() in a running transaction + * can result in a deadlock. Further, running transactions + * are already protected from freezing. + */ + if (!ext4_journal_current_handle()) { + sb_start_intwrite(dquot->dq_sb); + freeze_protected = true; + } handle = ext4_journal_start(dquot_to_inode(dquot), EXT4_HT_QUOTA, EXT4_QUOTA_DEL_BLOCKS(dquot->dq_sb)); if (IS_ERR(handle)) { /* Release dquot anyway to avoid endless cycle in dqput() */ dquot_release(dquot); + if (freeze_protected) + sb_end_intwrite(dquot->dq_sb); return PTR_ERR(handle); } ret = dquot_release(dquot); @@ -6819,6 +6851,10 @@ static int ext4_release_dquot(struct dquot *dquot) err = ext4_journal_stop(handle); if (!ret) ret = err; + + if (freeze_protected) + sb_end_intwrite(dquot->dq_sb); + return ret; } diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 5598aec75775..95dbc7c9843b 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -1127,15 +1127,24 @@ ext4_xattr_inode_dec_ref_all(handle_t *handle, struct inode *parent, { struct inode *ea_inode; struct ext4_xattr_entry *entry; + struct ext4_iloc iloc; bool dirty = false; unsigned int ea_ino; int err; int credits; + void *end; + + if (block_csum) + end = (void *)bh->b_data + bh->b_size; + else { + ext4_get_inode_loc(parent, &iloc); + end = (void *)ext4_raw_inode(&iloc) + EXT4_SB(parent->i_sb)->s_inode_size; + } /* One credit for dec ref on ea_inode, one for orphan list addition, */ credits = 2 + extra_credits; - for (entry = first; !IS_LAST_ENTRY(entry); + for (entry = first; (void *)entry < end && !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) { if (!entry->e_value_inum) continue; diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 0b0e3d44e158..dc8f283f210c 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -56,8 +56,8 @@ bool f2fs_is_cp_guaranteed(struct page *page) struct inode *inode; struct f2fs_sb_info *sbi; - if (!mapping) - return false; + if (fscrypt_is_bounce_page(page)) + return page_private_gcing(fscrypt_pagecache_page(page)); inode = mapping->host; sbi = F2FS_I_SB(inode); @@ -273,7 +273,7 @@ static void f2fs_read_end_io(struct bio *bio) { struct f2fs_sb_info *sbi = F2FS_P_SB(bio_first_page_all(bio)); struct bio_post_read_ctx *ctx; - bool intask = in_task(); + bool intask = in_task() && !irqs_disabled(); iostat_update_and_unbind_ctx(bio, 0); ctx = bio->bi_private; diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c index f13143efc4b1..a5c63c7da299 100644 --- a/fs/f2fs/extent_cache.c +++ b/fs/f2fs/extent_cache.c @@ -440,7 +440,7 @@ void f2fs_init_read_extent_tree(struct inode *inode, struct page *ipage) struct f2fs_extent *i_ext = &F2FS_INODE(ipage)->i_ext; struct extent_tree *et; struct extent_node *en; - struct extent_info ei; + struct extent_info ei = {0}; if (!__may_extent_tree(inode, EX_READ)) { /* drop largest read extent */ diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 840a45855451..1ad9669666e8 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -1226,7 +1226,7 @@ struct f2fs_bio_info { #define RDEV(i) (raw_super->devs[i]) struct f2fs_dev_info { struct block_device *bdev; - char path[MAX_PATH_LEN]; + char path[MAX_PATH_LEN + 1]; unsigned int total_segments; block_t start_blk; block_t end_blk; @@ -2387,8 +2387,14 @@ static inline void dec_valid_block_count(struct f2fs_sb_info *sbi, blkcnt_t sectors = count << F2FS_LOG_SECTORS_PER_BLOCK; spin_lock(&sbi->stat_lock); - f2fs_bug_on(sbi, sbi->total_valid_block_count < (block_t) count); - sbi->total_valid_block_count -= (block_t)count; + if (unlikely(sbi->total_valid_block_count < count)) { + f2fs_warn(sbi, "Inconsistent total_valid_block_count:%u, ino:%lu, count:%u", + sbi->total_valid_block_count, inode->i_ino, count); + sbi->total_valid_block_count = 0; + set_sbi_flag(sbi, SBI_NEED_FSCK); + } else { + sbi->total_valid_block_count -= count; + } if (sbi->reserved_blocks && sbi->current_reserved_blocks < sbi->reserved_blocks) sbi->current_reserved_blocks = min(sbi->reserved_blocks, diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 0f350368dea7..c02b5ea43f07 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -695,8 +695,12 @@ retry: if (err == -ENOENT) return; + if (err == -EFSCORRUPTED) + goto stop_checkpoint; + if (err == -ENOMEM || ++count <= DEFAULT_RETRY_IO_COUNT) goto retry; +stop_checkpoint: f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_UPDATE_INODE); return; } @@ -827,6 +831,19 @@ retry: f2fs_update_inode_page(inode); if (dquot_initialize_needed(inode)) set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR); + + /* + * If both f2fs_truncate() and f2fs_update_inode_page() failed + * due to fuzzed corrupted inode, call f2fs_inode_synced() to + * avoid triggering later f2fs_bug_on(). + */ + if (is_inode_flag_set(inode, FI_DIRTY_INODE)) { + f2fs_warn(sbi, + "f2fs_evict_inode: inode is dirty, ino:%lu", + inode->i_ino); + f2fs_inode_synced(inode); + set_sbi_flag(sbi, SBI_NEED_FSCK); + } } if (!is_sbi_flag_set(sbi, SBI_IS_FREEZING)) sb_end_intwrite(inode->i_sb); @@ -843,8 +860,12 @@ no_delete: if (likely(!f2fs_cp_error(sbi) && !is_sbi_flag_set(sbi, SBI_CP_DISABLED))) f2fs_bug_on(sbi, is_inode_flag_set(inode, FI_DIRTY_INODE)); - else - f2fs_inode_synced(inode); + + /* + * anyway, it needs to remove the inode from sbi->inode_list[DIRTY_META] + * list to avoid UAF in f2fs_sync_inode_meta() during checkpoint. + */ + f2fs_inode_synced(inode); /* for the case f2fs_new_inode() was failed, .i_ino is zero, skip it */ if (inode->i_ino) diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index 9da104c0743c..f61290a52213 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -401,7 +401,7 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir, if (is_inode_flag_set(dir, FI_PROJ_INHERIT) && (!projid_eq(F2FS_I(dir)->i_projid, - F2FS_I(old_dentry->d_inode)->i_projid))) + F2FS_I(inode)->i_projid))) return -EXDEV; err = f2fs_dquot_initialize(dir); @@ -550,6 +550,15 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry) goto fail; } + if (unlikely(inode->i_nlink == 0)) { + f2fs_warn(F2FS_I_SB(inode), "%s: inode (ino=%lx) has zero i_nlink", + __func__, inode->i_ino); + err = -EFSCORRUPTED; + set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_FSCK); + f2fs_put_page(page, 0); + goto fail; + } + f2fs_balance_fs(sbi, true); f2fs_lock_op(sbi); @@ -896,7 +905,7 @@ static int f2fs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, if (is_inode_flag_set(new_dir, FI_PROJ_INHERIT) && (!projid_eq(F2FS_I(new_dir)->i_projid, - F2FS_I(old_dentry->d_inode)->i_projid))) + F2FS_I(old_inode)->i_projid))) return -EXDEV; /* @@ -1085,10 +1094,10 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry, if ((is_inode_flag_set(new_dir, FI_PROJ_INHERIT) && !projid_eq(F2FS_I(new_dir)->i_projid, - F2FS_I(old_dentry->d_inode)->i_projid)) || - (is_inode_flag_set(new_dir, FI_PROJ_INHERIT) && + F2FS_I(old_inode)->i_projid)) || + (is_inode_flag_set(old_dir, FI_PROJ_INHERIT) && !projid_eq(F2FS_I(old_dir)->i_projid, - F2FS_I(new_dentry->d_inode)->i_projid))) + F2FS_I(new_inode)->i_projid))) return -EXDEV; err = f2fs_dquot_initialize(old_dir); diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 745ecf5523c9..ccc72781e0c6 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -1112,7 +1112,14 @@ int f2fs_truncate_inode_blocks(struct inode *inode, pgoff_t from) trace_f2fs_truncate_inode_blocks_enter(inode, from); level = get_node_path(inode, from, offset, noffset); - if (level < 0) { + if (level <= 0) { + if (!level) { + level = -EFSCORRUPTED; + f2fs_err(sbi, "%s: inode ino=%lx has corrupted node block, from:%lu addrs:%u", + __func__, inode->i_ino, + from, ADDRS_PER_INODE(inode)); + set_sbi_flag(sbi, SBI_NEED_FSCK); + } trace_f2fs_truncate_inode_blocks_exit(inode, level); return level; } diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h index 5ef5a88f47a0..20d4387c661d 100644 --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -625,8 +625,7 @@ static inline void __get_secs_required(struct f2fs_sb_info *sbi, unsigned int dent_blocks = total_dent_blocks % CAP_BLKS_PER_SEC(sbi); unsigned int data_blocks = 0; - if (f2fs_lfs_mode(sbi) && - unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) { + if (f2fs_lfs_mode(sbi)) { total_data_blocks = get_pages(sbi, F2FS_DIRTY_DATA); data_secs = total_data_blocks / CAP_BLKS_PER_SEC(sbi); data_blocks = total_data_blocks % CAP_BLKS_PER_SEC(sbi); @@ -635,7 +634,7 @@ static inline void __get_secs_required(struct f2fs_sb_info *sbi, if (lower_p) *lower_p = node_secs + dent_secs + data_secs; if (upper_p) - *upper_p = node_secs + dent_secs + + *upper_p = node_secs + dent_secs + data_secs + (node_blocks ? 1 : 0) + (dent_blocks ? 1 : 0) + (data_blocks ? 1 : 0); if (curseg_p) diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 72160b906f4b..84fc6591e3f9 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -1753,26 +1753,32 @@ static int f2fs_statfs_project(struct super_block *sb, limit = min_not_zero(dquot->dq_dqb.dqb_bsoftlimit, dquot->dq_dqb.dqb_bhardlimit); - if (limit) - limit >>= sb->s_blocksize_bits; + limit >>= sb->s_blocksize_bits; + + if (limit) { + uint64_t remaining = 0; - if (limit && buf->f_blocks > limit) { curblock = (dquot->dq_dqb.dqb_curspace + dquot->dq_dqb.dqb_rsvspace) >> sb->s_blocksize_bits; - buf->f_blocks = limit; - buf->f_bfree = buf->f_bavail = - (buf->f_blocks > curblock) ? - (buf->f_blocks - curblock) : 0; + if (limit > curblock) + remaining = limit - curblock; + + buf->f_blocks = min(buf->f_blocks, limit); + buf->f_bfree = min(buf->f_bfree, remaining); + buf->f_bavail = min(buf->f_bavail, remaining); } limit = min_not_zero(dquot->dq_dqb.dqb_isoftlimit, dquot->dq_dqb.dqb_ihardlimit); - if (limit && buf->f_files > limit) { - buf->f_files = limit; - buf->f_ffree = - (buf->f_files > dquot->dq_dqb.dqb_curinodes) ? - (buf->f_files - dquot->dq_dqb.dqb_curinodes) : 0; + if (limit) { + uint64_t remaining = 0; + + if (limit > dquot->dq_dqb.dqb_curinodes) + remaining = limit - dquot->dq_dqb.dqb_curinodes; + + buf->f_files = min(buf->f_files, limit); + buf->f_ffree = min(buf->f_ffree, remaining); } spin_unlock(&dquot->dq_dqb_lock); @@ -1830,9 +1836,9 @@ static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_fsid = u64_to_fsid(id); #ifdef CONFIG_QUOTA - if (is_inode_flag_set(dentry->d_inode, FI_PROJ_INHERIT) && + if (is_inode_flag_set(d_inode(dentry), FI_PROJ_INHERIT) && sb_has_quota_limits_enabled(sb, PRJQUOTA)) { - f2fs_statfs_project(sb, F2FS_I(dentry->d_inode)->i_projid, buf); + f2fs_statfs_project(sb, F2FS_I(d_inode(dentry))->i_projid, buf); } #endif return 0; @@ -3499,6 +3505,7 @@ int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi) block_t user_block_count, valid_user_blocks; block_t avail_node_count, valid_node_count; unsigned int nat_blocks, nat_bits_bytes, nat_bits_blocks; + unsigned int sit_blk_cnt; int i, j; total = le32_to_cpu(raw_super->segment_count); @@ -3610,6 +3617,13 @@ skip_cross: return 1; } + sit_blk_cnt = DIV_ROUND_UP(main_segs, SIT_ENTRY_PER_BLOCK); + if (sit_bitmap_size * 8 < sit_blk_cnt) { + f2fs_err(sbi, "Wrong bitmap size: sit: %u, sit_blk_cnt:%u", + sit_bitmap_size, sit_blk_cnt); + return 1; + } + cp_pack_start_sum = __start_sum_addr(sbi); cp_payload = __cp_payload(sbi); if (cp_pack_start_sum < cp_payload + 1 || diff --git a/fs/file.c b/fs/file.c index bc0c087b31bb..2eccbb5dcd86 100644 --- a/fs/file.c +++ b/fs/file.c @@ -362,17 +362,25 @@ struct files_struct *dup_fd(struct files_struct *oldf, struct fd_range *punch_ho old_fds = old_fdt->fd; new_fds = new_fdt->fd; + /* + * We may be racing against fd allocation from other threads using this + * files_struct, despite holding ->file_lock. + * + * alloc_fd() might have already claimed a slot, while fd_install() + * did not populate it yet. Note the latter operates locklessly, so + * the file can show up as we are walking the array below. + * + * At the same time we know no files will disappear as all other + * operations take the lock. + * + * Instead of trying to placate userspace racing with itself, we + * ref the file if we see it and mark the fd slot as unused otherwise. + */ for (i = open_files; i != 0; i--) { - struct file *f = *old_fds++; + struct file *f = rcu_dereference_raw(*old_fds++); if (f) { get_file(f); } else { - /* - * The fd may be claimed in the fd bitmap but not yet - * instantiated in the files array if a sibling thread - * is partway through open(). So make sure that this - * fd is available to the new process. - */ __clear_open_fd(open_files - i, new_fdt); } rcu_assign_pointer(*new_fds++, f); @@ -625,7 +633,7 @@ static struct file *pick_file(struct files_struct *files, unsigned fd) return NULL; fd = array_index_nospec(fd, fdt->max_fds); - file = fdt->fd[fd]; + file = rcu_dereference_raw(fdt->fd[fd]); if (file) { rcu_assign_pointer(fdt->fd[fd], NULL); __put_unused_fd(files, fd); @@ -1093,7 +1101,7 @@ __releases(&files->file_lock) */ fdt = files_fdtable(files); fd = array_index_nospec(fd, fdt->max_fds); - tofree = fdt->fd[fd]; + tofree = rcu_dereference_raw(fdt->fd[fd]); if (!tofree && fd_is_open(fd, fdt)) goto Ebusy; get_file(file); diff --git a/fs/filesystems.c b/fs/filesystems.c index 58b9067b2391..95e5256821a5 100644 --- a/fs/filesystems.c +++ b/fs/filesystems.c @@ -156,15 +156,19 @@ static int fs_index(const char __user * __name) static int fs_name(unsigned int index, char __user * buf) { struct file_system_type * tmp; - int len, res; + int len, res = -EINVAL; read_lock(&file_systems_lock); - for (tmp = file_systems; tmp; tmp = tmp->next, index--) - if (index <= 0 && try_module_get(tmp->owner)) + for (tmp = file_systems; tmp; tmp = tmp->next, index--) { + if (index == 0) { + if (try_module_get(tmp->owner)) + res = 0; break; + } + } read_unlock(&file_systems_lock); - if (!tmp) - return -EINVAL; + if (res) + return res; /* OK, we got the reference, so we can safely block */ len = strlen(tmp->name) + 1; diff --git a/fs/fuse/dax.c b/fs/fuse/dax.c index 6e71904c396f..dc28c28654d9 100644 --- a/fs/fuse/dax.c +++ b/fs/fuse/dax.c @@ -681,7 +681,6 @@ static int __fuse_dax_break_layouts(struct inode *inode, bool *retry, 0, 0, fuse_wait_dax_page(inode)); } -/* dmap_end == 0 leads to unmapping of whole file */ int fuse_dax_break_layouts(struct inode *inode, u64 dmap_start, u64 dmap_end) { diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index aa2be4c1ea8f..0dbacdd7bb0d 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -1068,6 +1068,8 @@ static int fuse_link(struct dentry *entry, struct inode *newdir, else if (err == -EINTR) fuse_invalidate_attr(inode); + if (err == -ENOSYS) + err = -EPERM; return err; } @@ -1445,7 +1447,7 @@ static const char *fuse_get_link(struct dentry *dentry, struct inode *inode, goto out_err; if (fc->cache_symlinks) - return page_get_link(dentry, inode, callback); + return page_get_link_raw(dentry, inode, callback); err = -ECHILD; if (!dentry) @@ -1712,7 +1714,7 @@ int fuse_do_setattr(struct dentry *dentry, struct iattr *attr, if (FUSE_IS_DAX(inode) && is_truncate) { filemap_invalidate_lock(mapping); fault_blocked = true; - err = fuse_dax_break_layouts(inode, 0, 0); + err = fuse_dax_break_layouts(inode, 0, -1); if (err) { filemap_invalidate_unlock(mapping); return err; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 0df1311afb87..723dd9b94e56 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -240,7 +240,7 @@ int fuse_open_common(struct inode *inode, struct file *file, bool isdir) if (dax_truncate) { filemap_invalidate_lock(inode->i_mapping); - err = fuse_dax_break_layouts(inode, 0, 0); + err = fuse_dax_break_layouts(inode, 0, -1); if (err) goto out_inode_unlock; } @@ -3020,7 +3020,7 @@ static long fuse_file_fallocate(struct file *file, int mode, loff_t offset, inode_lock(inode); if (block_faults) { filemap_invalidate_lock(inode->i_mapping); - err = fuse_dax_break_layouts(inode, 0, 0); + err = fuse_dax_break_layouts(inode, 0, -1); if (err) goto out; } diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c index 92d41269f1d3..9e4f2ba0ef9d 100644 --- a/fs/fuse/virtio_fs.c +++ b/fs/fuse/virtio_fs.c @@ -1429,6 +1429,9 @@ static int virtio_fs_get_tree(struct fs_context *fsc) unsigned int virtqueue_size; int err = -EIO; + if (!fsc->source) + return invalf(fsc, "No source specified"); + /* This gets a reference on virtio_fs object. This ptr gets installed * in fc->iq->priv. Once fuse_conn is going away, it calls ->put() * to drop the reference to this object. diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 6ba8460f5331..428c1db295fa 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -885,11 +885,12 @@ static void run_queue(struct gfs2_glock *gl, const int nonblock) __releases(&gl->gl_lockref.lock) __acquires(&gl->gl_lockref.lock) { - struct gfs2_holder *gh = NULL; + struct gfs2_holder *gh; if (test_and_set_bit(GLF_LOCK, &gl->gl_flags)) return; + /* While a demote is in progress, the GLF_LOCK flag must be set. */ GLOCK_BUG_ON(gl, test_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags)); if (test_bit(GLF_DEMOTE, &gl->gl_flags) && @@ -901,18 +902,22 @@ __acquires(&gl->gl_lockref.lock) set_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags); GLOCK_BUG_ON(gl, gl->gl_demote_state == LM_ST_EXCLUSIVE); gl->gl_target = gl->gl_demote_state; + do_xmote(gl, NULL, gl->gl_target); + return; } else { if (test_bit(GLF_DEMOTE, &gl->gl_flags)) gfs2_demote_wake(gl); if (do_promote(gl) == 0) goto out_unlock; gh = find_first_waiter(gl); + if (!gh) + goto out_unlock; gl->gl_target = gh->gh_state; if (!(gh->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB))) do_error(gl, 0); /* Fail queued try locks */ + do_xmote(gl, gh, gl->gl_target); + return; } - do_xmote(gl, gh, gl->gl_target); - return; out_sched: clear_bit(GLF_LOCK, &gl->gl_flags); diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 04fc3e72a96e..06629aeefbe6 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -631,7 +631,8 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, if (!IS_ERR(inode)) { if (S_ISDIR(inode->i_mode)) { iput(inode); - inode = ERR_PTR(-EISDIR); + inode = NULL; + error = -EISDIR; goto fail_gunlock; } d_instantiate(dentry, inode); diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c index 884081730f9f..588760c1a5da 100644 --- a/fs/gfs2/lock_dlm.c +++ b/fs/gfs2/lock_dlm.c @@ -950,14 +950,15 @@ locks_done: if (sdp->sd_args.ar_spectator) { fs_info(sdp, "Recovery is required. Waiting for a " "non-spectator to mount.\n"); + spin_unlock(&ls->ls_recover_spin); msleep_interruptible(1000); } else { fs_info(sdp, "control_mount wait1 block %u start %u " "mount %u lvb %u flags %lx\n", block_gen, start_gen, mount_gen, lvb_gen, ls->ls_recover_flags); + spin_unlock(&ls->ls_recover_spin); } - spin_unlock(&ls->ls_recover_spin); goto restart; } diff --git a/fs/hfs/bnode.c b/fs/hfs/bnode.c index 6add6ebfef89..cb823a8a6ba9 100644 --- a/fs/hfs/bnode.c +++ b/fs/hfs/bnode.c @@ -67,6 +67,12 @@ void hfs_bnode_read_key(struct hfs_bnode *node, void *key, int off) else key_len = tree->max_key_len + 1; + if (key_len > sizeof(hfs_btree_key) || key_len < 1) { + memset(key, 0, sizeof(hfs_btree_key)); + pr_err("hfs: Invalid key length: %d\n", key_len); + return; + } + hfs_bnode_read(node, key, off, key_len); } diff --git a/fs/hfsplus/bnode.c b/fs/hfsplus/bnode.c index 87974d5e6791..079ea80534f7 100644 --- a/fs/hfsplus/bnode.c +++ b/fs/hfsplus/bnode.c @@ -67,6 +67,12 @@ void hfs_bnode_read_key(struct hfs_bnode *node, void *key, int off) else key_len = tree->max_key_len + 2; + if (key_len > sizeof(hfsplus_btree_key) || key_len < 1) { + memset(key, 0, sizeof(hfsplus_btree_key)); + pr_err("hfsplus: Invalid key length: %d\n", key_len); + return; + } + hfs_bnode_read(node, key, off, key_len); } diff --git a/fs/hfsplus/extents.c b/fs/hfsplus/extents.c index 91354e769642..839bf83448c3 100644 --- a/fs/hfsplus/extents.c +++ b/fs/hfsplus/extents.c @@ -342,9 +342,6 @@ static int hfsplus_free_extents(struct super_block *sb, int i; int err = 0; - /* Mapping the allocation file may lock the extent tree */ - WARN_ON(mutex_is_locked(&HFSPLUS_SB(sb)->ext_tree->tree_lock)); - hfsplus_dump_extent(extent); for (i = 0; i < 8; extent++, i++) { count = be32_to_cpu(extent->block_count); diff --git a/fs/isofs/dir.c b/fs/isofs/dir.c index eb2f8273e6f1..09df40b612fb 100644 --- a/fs/isofs/dir.c +++ b/fs/isofs/dir.c @@ -147,7 +147,8 @@ static int do_isofs_readdir(struct inode *inode, struct file *file, de = tmpde; } /* Basic sanity check, whether name doesn't exceed dir entry */ - if (de_len < de->name_len[0] + + if (de_len < sizeof(struct iso_directory_record) || + de_len < de->name_len[0] + sizeof(struct iso_directory_record)) { printk(KERN_NOTICE "iso9660: Corrupted directory entry" " in block %lu of inode %lu\n", block, diff --git a/fs/isofs/export.c b/fs/isofs/export.c index 35768a63fb1d..421d247fae52 100644 --- a/fs/isofs/export.c +++ b/fs/isofs/export.c @@ -180,7 +180,7 @@ static struct dentry *isofs_fh_to_parent(struct super_block *sb, return NULL; return isofs_export_iget(sb, - fh_len > 2 ? ifid->parent_block : 0, + fh_len > 3 ? ifid->parent_block : 0, ifid->parent_offset, fh_len > 4 ? ifid->parent_generation : 0); } diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index 8a6c7fdc1d5f..e3052d3fe5dc 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -1491,9 +1491,16 @@ static int isofs_read_inode(struct inode *inode, int relocated) inode->i_op = &page_symlink_inode_operations; inode_nohighmem(inode); inode->i_data.a_ops = &isofs_symlink_aops; - } else + } else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) || + S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) { /* XXX - parse_rock_ridge_inode() had already set i_rdev. */ init_special_inode(inode, inode->i_mode, inode->i_rdev); + } else { + printk(KERN_DEBUG "ISOFS: Invalid file type 0%04o for inode %lu.\n", + inode->i_mode, inode->i_ino); + ret = -EIO; + goto fail; + } ret = 0; out: diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 55ada2b88146..41ab2dfd1ac2 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -1711,7 +1711,6 @@ int jbd2_journal_update_sb_log_tail(journal_t *journal, tid_t tail_tid, /* Log is no longer empty */ write_lock(&journal->j_state_lock); - WARN_ON(!sb->s_sequence); journal->j_flags &= ~JBD2_FLUSHED; write_unlock(&journal->j_state_lock); diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 6ef5022949c4..ca6f3f8729f3 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -1518,7 +1518,7 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh) jh->b_next_transaction == transaction); spin_unlock(&jh->b_state_lock); } - if (jh->b_modified == 1) { + if (data_race(jh->b_modified == 1)) { /* If it's in our transaction it must be in BJ_Metadata list. */ if (data_race(jh->b_transaction == transaction && jh->b_jlist != BJ_Metadata)) { @@ -1537,7 +1537,6 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh) goto out; } - journal = transaction->t_journal; spin_lock(&jh->b_state_lock); if (is_handle_aborted(handle)) { @@ -1552,6 +1551,8 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh) goto out_unlock_bh; } + journal = transaction->t_journal; + if (jh->b_modified == 0) { /* * This buffer's got modified and becoming part diff --git a/fs/jffs2/erase.c b/fs/jffs2/erase.c index ef3a1e1b6cb0..fda9f4d6093f 100644 --- a/fs/jffs2/erase.c +++ b/fs/jffs2/erase.c @@ -425,7 +425,9 @@ static void jffs2_mark_erased_block(struct jffs2_sb_info *c, struct jffs2_eraseb .totlen = cpu_to_je32(c->cleanmarker_size) }; - jffs2_prealloc_raw_node_refs(c, jeb, 1); + ret = jffs2_prealloc_raw_node_refs(c, jeb, 1); + if (ret) + goto filebad; marker.hdr_crc = cpu_to_je32(crc32(0, &marker, sizeof(struct jffs2_unknown_node)-4)); diff --git a/fs/jffs2/scan.c b/fs/jffs2/scan.c index 29671e33a171..62879c218d4b 100644 --- a/fs/jffs2/scan.c +++ b/fs/jffs2/scan.c @@ -256,7 +256,9 @@ int jffs2_scan_medium(struct jffs2_sb_info *c) jffs2_dbg(1, "%s(): Skipping %d bytes in nextblock to ensure page alignment\n", __func__, skip); - jffs2_prealloc_raw_node_refs(c, c->nextblock, 1); + ret = jffs2_prealloc_raw_node_refs(c, c->nextblock, 1); + if (ret) + goto out; jffs2_scan_dirty_space(c, c->nextblock, skip); } #endif diff --git a/fs/jffs2/summary.c b/fs/jffs2/summary.c index 4fe64519870f..d83372d3e1a0 100644 --- a/fs/jffs2/summary.c +++ b/fs/jffs2/summary.c @@ -858,7 +858,10 @@ int jffs2_sum_write_sumnode(struct jffs2_sb_info *c) spin_unlock(&c->erase_completion_lock); jeb = c->nextblock; - jffs2_prealloc_raw_node_refs(c, jeb, 1); + ret = jffs2_prealloc_raw_node_refs(c, jeb, 1); + + if (ret) + goto out; if (!c->summary->sum_num || !c->summary->sum_list_head) { JFFS2_WARNING("Empty summary info!!!\n"); @@ -872,6 +875,8 @@ int jffs2_sum_write_sumnode(struct jffs2_sb_info *c) datasize += padsize; ret = jffs2_sum_write_data(c, jeb, infosize, datasize, padsize); + +out: spin_lock(&c->erase_completion_lock); return ret; } diff --git a/fs/jfs/jfs_dinode.h b/fs/jfs/jfs_dinode.h index 6b231d0d0071..603aae17a693 100644 --- a/fs/jfs/jfs_dinode.h +++ b/fs/jfs/jfs_dinode.h @@ -96,7 +96,7 @@ struct dinode { #define di_gengen u._file._u1._imap._gengen union { - xtpage_t _xtroot; + xtroot_t _xtroot; struct { u8 unused[16]; /* 16: */ dxd_t _dxd; /* 16: */ diff --git a/fs/jfs/jfs_dmap.c b/fs/jfs/jfs_dmap.c index 6509102e581a..c761291f59ac 100644 --- a/fs/jfs/jfs_dmap.c +++ b/fs/jfs/jfs_dmap.c @@ -178,41 +178,30 @@ int dbMount(struct inode *ipbmap) dbmp_le = (struct dbmap_disk *) mp->data; bmp->db_mapsize = le64_to_cpu(dbmp_le->dn_mapsize); bmp->db_nfree = le64_to_cpu(dbmp_le->dn_nfree); - bmp->db_l2nbperpage = le32_to_cpu(dbmp_le->dn_l2nbperpage); - if (bmp->db_l2nbperpage > L2PSIZE - L2MINBLOCKSIZE || - bmp->db_l2nbperpage < 0) { - err = -EINVAL; - goto err_release_metapage; - } - bmp->db_numag = le32_to_cpu(dbmp_le->dn_numag); - if (!bmp->db_numag || bmp->db_numag > MAXAG) { - err = -EINVAL; - goto err_release_metapage; - } - bmp->db_maxlevel = le32_to_cpu(dbmp_le->dn_maxlevel); bmp->db_maxag = le32_to_cpu(dbmp_le->dn_maxag); bmp->db_agpref = le32_to_cpu(dbmp_le->dn_agpref); - if (bmp->db_maxag >= MAXAG || bmp->db_maxag < 0 || - bmp->db_agpref >= MAXAG || bmp->db_agpref < 0) { - err = -EINVAL; - goto err_release_metapage; - } - bmp->db_aglevel = le32_to_cpu(dbmp_le->dn_aglevel); bmp->db_agheight = le32_to_cpu(dbmp_le->dn_agheight); bmp->db_agwidth = le32_to_cpu(dbmp_le->dn_agwidth); bmp->db_agstart = le32_to_cpu(dbmp_le->dn_agstart); bmp->db_agl2size = le32_to_cpu(dbmp_le->dn_agl2size); - if (bmp->db_agl2size > L2MAXL2SIZE - L2MAXAG || - bmp->db_agl2size < 0) { - err = -EINVAL; - goto err_release_metapage; - } - if (((bmp->db_mapsize - 1) >> bmp->db_agl2size) > MAXAG) { + if ((bmp->db_l2nbperpage > L2PSIZE - L2MINBLOCKSIZE) || + (bmp->db_l2nbperpage < 0) || + !bmp->db_numag || (bmp->db_numag > MAXAG) || + (bmp->db_maxag >= MAXAG) || (bmp->db_maxag < 0) || + (bmp->db_agpref >= MAXAG) || (bmp->db_agpref < 0) || + (bmp->db_agheight < 0) || (bmp->db_agheight > (L2LPERCTL >> 1)) || + (bmp->db_agwidth < 1) || (bmp->db_agwidth > (LPERCTL / MAXAG)) || + (bmp->db_agwidth > (1 << (L2LPERCTL - (bmp->db_agheight << 1)))) || + (bmp->db_agstart < 0) || + (bmp->db_agstart > (CTLTREESIZE - 1 - bmp->db_agwidth * (MAXAG - 1))) || + (bmp->db_agl2size > L2MAXL2SIZE - L2MAXAG) || + (bmp->db_agl2size < 0) || + ((bmp->db_mapsize - 1) >> bmp->db_agl2size) > MAXAG) { err = -EINVAL; goto err_release_metapage; } @@ -1820,8 +1809,10 @@ dbAllocCtl(struct bmap * bmp, s64 nblocks, int l2nb, s64 blkno, s64 * results) return -EIO; dp = (struct dmap *) mp->data; - if (dp->tree.budmin < 0) + if (dp->tree.budmin < 0) { + release_metapage(mp); return -EIO; + } /* try to allocate the blocks. */ @@ -3403,7 +3394,7 @@ int dbExtendFS(struct inode *ipbmap, s64 blkno, s64 nblocks) oldl2agsize = bmp->db_agl2size; bmp->db_agl2size = l2agsize; - bmp->db_agsize = 1 << l2agsize; + bmp->db_agsize = (s64)1 << l2agsize; /* compute new number of AG */ agno = bmp->db_numag; @@ -3666,8 +3657,8 @@ void dbFinalizeBmap(struct inode *ipbmap) * system size is not a multiple of the group size). */ inactfree = (inactags && ag_rem) ? - ((inactags - 1) << bmp->db_agl2size) + ag_rem - : inactags << bmp->db_agl2size; + (((s64)inactags - 1) << bmp->db_agl2size) + ag_rem + : ((s64)inactags << bmp->db_agl2size); /* determine how many free blocks are in the active * allocation groups plus the average number of free blocks diff --git a/fs/jfs/jfs_dtree.c b/fs/jfs/jfs_dtree.c index 8f85177f284b..93db6eec4465 100644 --- a/fs/jfs/jfs_dtree.c +++ b/fs/jfs/jfs_dtree.c @@ -117,7 +117,8 @@ do { \ if (!(RC)) { \ if (((P)->header.nextindex > \ (((BN) == 0) ? DTROOTMAXSLOT : (P)->header.maxslot)) || \ - ((BN) && ((P)->header.maxslot > DTPAGEMAXSLOT))) { \ + ((BN) && (((P)->header.maxslot > DTPAGEMAXSLOT) || \ + ((P)->header.stblindex >= DTPAGEMAXSLOT)))) { \ BT_PUTPAGE(MP); \ jfs_error((IP)->i_sb, \ "DT_GETPAGE: dtree page corrupt\n"); \ diff --git a/fs/jfs/jfs_imap.c b/fs/jfs/jfs_imap.c index c72e97f06579..1f2e452a7676 100644 --- a/fs/jfs/jfs_imap.c +++ b/fs/jfs/jfs_imap.c @@ -102,7 +102,7 @@ int diMount(struct inode *ipimap) * allocate/initialize the in-memory inode map control structure */ /* allocate the in-memory inode map control structure. */ - imap = kmalloc(sizeof(struct inomap), GFP_KERNEL); + imap = kzalloc(sizeof(struct inomap), GFP_KERNEL); if (imap == NULL) return -ENOMEM; @@ -456,7 +456,7 @@ struct inode *diReadSpecial(struct super_block *sb, ino_t inum, int secondary) dp += inum % 8; /* 8 inodes per 4K page */ /* copy on-disk inode to in-memory inode */ - if ((copy_from_dinode(dp, ip)) != 0) { + if ((copy_from_dinode(dp, ip) != 0) || (ip->i_nlink == 0)) { /* handle bad return by returning NULL for ip */ set_nlink(ip, 1); /* Don't want iput() deleting it */ iput(ip); @@ -673,7 +673,7 @@ int diWrite(tid_t tid, struct inode *ip) * This is the special xtree inside the directory for storing * the directory table */ - xtpage_t *p, *xp; + xtroot_t *p, *xp; xad_t *xad; jfs_ip->xtlid = 0; @@ -687,7 +687,7 @@ int diWrite(tid_t tid, struct inode *ip) * copy xtree root from inode to dinode: */ p = &jfs_ip->i_xtroot; - xp = (xtpage_t *) &dp->di_dirtable; + xp = (xtroot_t *) &dp->di_dirtable; lv = ilinelock->lv; for (n = 0; n < ilinelock->index; n++, lv++) { memcpy(&xp->xad[lv->offset], &p->xad[lv->offset], @@ -716,7 +716,7 @@ int diWrite(tid_t tid, struct inode *ip) * regular file: 16 byte (XAD slot) granularity */ if (type & tlckXTREE) { - xtpage_t *p, *xp; + xtroot_t *p, *xp; xad_t *xad; /* @@ -3029,14 +3029,23 @@ static void duplicateIXtree(struct super_block *sb, s64 blkno, * * RETURN VALUES: * 0 - success - * -ENOMEM - insufficient memory + * -EINVAL - unexpected inode type */ static int copy_from_dinode(struct dinode * dip, struct inode *ip) { struct jfs_inode_info *jfs_ip = JFS_IP(ip); struct jfs_sb_info *sbi = JFS_SBI(ip->i_sb); + int fileset = le32_to_cpu(dip->di_fileset); + + switch (fileset) { + case AGGR_RESERVED_I: case AGGREGATE_I: case BMAP_I: + case LOG_I: case BADBLOCK_I: case FILESYSTEM_I: + break; + default: + return -EINVAL; + } - jfs_ip->fileset = le32_to_cpu(dip->di_fileset); + jfs_ip->fileset = fileset; jfs_ip->mode2 = le32_to_cpu(dip->di_mode); jfs_set_inode_flags(ip); diff --git a/fs/jfs/jfs_incore.h b/fs/jfs/jfs_incore.h index 721def69e732..dd4264aa9bed 100644 --- a/fs/jfs/jfs_incore.h +++ b/fs/jfs/jfs_incore.h @@ -66,7 +66,7 @@ struct jfs_inode_info { lid_t xtlid; /* lid of xtree lock on directory */ union { struct { - xtpage_t _xtroot; /* 288: xtree root */ + xtroot_t _xtroot; /* 288: xtree root */ struct inomap *_imap; /* 4: inode map header */ } file; struct { diff --git a/fs/jfs/jfs_txnmgr.c b/fs/jfs/jfs_txnmgr.c index ce4b4760fcb1..dccc8b3f1045 100644 --- a/fs/jfs/jfs_txnmgr.c +++ b/fs/jfs/jfs_txnmgr.c @@ -783,7 +783,7 @@ struct tlock *txLock(tid_t tid, struct inode *ip, struct metapage * mp, if (mp->xflag & COMMIT_PAGE) p = (xtpage_t *) mp->data; else - p = &jfs_ip->i_xtroot; + p = (xtpage_t *) &jfs_ip->i_xtroot; xtlck->lwm.offset = le16_to_cpu(p->header.nextindex); } @@ -1676,7 +1676,7 @@ static void xtLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, if (tlck->type & tlckBTROOT) { lrd->log.redopage.type |= cpu_to_le16(LOG_BTROOT); - p = &JFS_IP(ip)->i_xtroot; + p = (xtpage_t *) &JFS_IP(ip)->i_xtroot; if (S_ISDIR(ip->i_mode)) lrd->log.redopage.type |= cpu_to_le16(LOG_DIR_XTREE); diff --git a/fs/jfs/jfs_xtree.c b/fs/jfs/jfs_xtree.c index 2d304cee884c..5ee618d17e77 100644 --- a/fs/jfs/jfs_xtree.c +++ b/fs/jfs/jfs_xtree.c @@ -1213,7 +1213,7 @@ xtSplitRoot(tid_t tid, struct xtlock *xtlck; int rc; - sp = &JFS_IP(ip)->i_xtroot; + sp = (xtpage_t *) &JFS_IP(ip)->i_xtroot; INCREMENT(xtStat.split); @@ -2098,7 +2098,7 @@ int xtAppend(tid_t tid, /* transaction id */ */ void xtInitRoot(tid_t tid, struct inode *ip) { - xtpage_t *p; + xtroot_t *p; /* * acquire a transaction lock on the root diff --git a/fs/jfs/jfs_xtree.h b/fs/jfs/jfs_xtree.h index 142caafc73b1..15da4e16d8b2 100644 --- a/fs/jfs/jfs_xtree.h +++ b/fs/jfs/jfs_xtree.h @@ -65,24 +65,33 @@ struct xadlist { #define XTPAGEMAXSLOT 256 #define XTENTRYSTART 2 -/* - * xtree page: - */ -typedef union { - struct xtheader { - __le64 next; /* 8: */ - __le64 prev; /* 8: */ +struct xtheader { + __le64 next; /* 8: */ + __le64 prev; /* 8: */ - u8 flag; /* 1: */ - u8 rsrvd1; /* 1: */ - __le16 nextindex; /* 2: next index = number of entries */ - __le16 maxentry; /* 2: max number of entries */ - __le16 rsrvd2; /* 2: */ + u8 flag; /* 1: */ + u8 rsrvd1; /* 1: */ + __le16 nextindex; /* 2: next index = number of entries */ + __le16 maxentry; /* 2: max number of entries */ + __le16 rsrvd2; /* 2: */ - pxd_t self; /* 8: self */ - } header; /* (32) */ + pxd_t self; /* 8: self */ +}; +/* + * xtree root (in inode): + */ +typedef union { + struct xtheader header; xad_t xad[XTROOTMAXSLOT]; /* 16 * maxentry: xad array */ +} xtroot_t; + +/* + * xtree page: + */ +typedef union { + struct xtheader header; + xad_t xad[XTPAGEMAXSLOT]; /* 16 * maxentry: xad array */ } xtpage_t; /* diff --git a/fs/jfs/xattr.c b/fs/jfs/xattr.c index 2b9b98ff2dd6..e6f2c619b30a 100644 --- a/fs/jfs/xattr.c +++ b/fs/jfs/xattr.c @@ -559,11 +559,16 @@ static int ea_get(struct inode *inode, struct ea_buffer *ea_buf, int min_size) size_check: if (EALIST_SIZE(ea_buf->xattr) != ea_size) { - int size = clamp_t(int, ea_size, 0, EALIST_SIZE(ea_buf->xattr)); - - printk(KERN_ERR "ea_get: invalid extended attribute\n"); - print_hex_dump(KERN_ERR, "", DUMP_PREFIX_ADDRESS, 16, 1, - ea_buf->xattr, size, 1); + if (unlikely(EALIST_SIZE(ea_buf->xattr) > INT_MAX)) { + printk(KERN_ERR "ea_get: extended attribute size too large: %u > INT_MAX\n", + EALIST_SIZE(ea_buf->xattr)); + } else { + int size = clamp_t(int, ea_size, 0, EALIST_SIZE(ea_buf->xattr)); + + printk(KERN_ERR "ea_get: invalid extended attribute\n"); + print_hex_dump(KERN_ERR, "", DUMP_PREFIX_ADDRESS, 16, 1, + ea_buf->xattr, size, 1); + } ea_release(inode, ea_buf); rc = -EIO; goto clean_up; diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 2c74b24fc22a..a259fe3471a9 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -1532,8 +1532,9 @@ void kernfs_break_active_protection(struct kernfs_node *kn) * invoked before finishing the kernfs operation. Note that while this * function restores the active reference, it doesn't and can't actually * restore the active protection - @kn may already or be in the process of - * being removed. Once kernfs_break_active_protection() is invoked, that - * protection is irreversibly gone for the kernfs operation instance. + * being drained and removed. Once kernfs_break_active_protection() is + * invoked, that protection is irreversibly gone for the kernfs operation + * instance. * * While this function may be called at any point after * kernfs_break_active_protection() is invoked, its most useful location diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index adf3536cfec8..cf57b7cc3a43 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -820,8 +820,9 @@ bool kernfs_should_drain_open_files(struct kernfs_node *kn) /* * @kn being deactivated guarantees that @kn->attr.open can't change * beneath us making the lockless test below safe. + * Callers post kernfs_unbreak_active_protection may be counted in + * kn->active by now, do not WARN_ON because of them. */ - WARN_ON_ONCE(atomic_read(&kn->active) != KN_DEACTIVATED_BIAS); rcu_read_lock(); on = rcu_dereference(kn->attr.open); diff --git a/fs/namei.c b/fs/namei.c index 166d71c82d7a..6ce07cde1c27 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -5156,10 +5156,9 @@ const char *vfs_get_link(struct dentry *dentry, struct delayed_call *done) EXPORT_SYMBOL(vfs_get_link); /* get the link contents into pagecache */ -const char *page_get_link(struct dentry *dentry, struct inode *inode, - struct delayed_call *callback) +static char *__page_get_link(struct dentry *dentry, struct inode *inode, + struct delayed_call *callback) { - char *kaddr; struct page *page; struct address_space *mapping = inode->i_mapping; @@ -5178,8 +5177,23 @@ const char *page_get_link(struct dentry *dentry, struct inode *inode, } set_delayed_call(callback, page_put_link, page); BUG_ON(mapping_gfp_mask(mapping) & __GFP_HIGHMEM); - kaddr = page_address(page); - nd_terminate_link(kaddr, inode->i_size, PAGE_SIZE - 1); + return page_address(page); +} + +const char *page_get_link_raw(struct dentry *dentry, struct inode *inode, + struct delayed_call *callback) +{ + return __page_get_link(dentry, inode, callback); +} +EXPORT_SYMBOL_GPL(page_get_link_raw); + +const char *page_get_link(struct dentry *dentry, struct inode *inode, + struct delayed_call *callback) +{ + char *kaddr = __page_get_link(dentry, inode, callback); + + if (!IS_ERR(kaddr)) + nd_terminate_link(kaddr, inode->i_size, PAGE_SIZE - 1); return kaddr; } diff --git a/fs/namespace.c b/fs/namespace.c index 59a9f877738b..f0fa2a1a6b05 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -629,15 +629,11 @@ int __legitimize_mnt(struct vfsmount *bastard, unsigned seq) return 0; mnt = real_mount(bastard); mnt_add_count(mnt, 1); - smp_mb(); // see mntput_no_expire() + smp_mb(); // see mntput_no_expire() and do_umount() if (likely(!read_seqretry(&mount_lock, seq))) return 0; - if (bastard->mnt_flags & MNT_SYNC_UMOUNT) { - mnt_add_count(mnt, -1); - return 1; - } lock_mount_hash(); - if (unlikely(bastard->mnt_flags & MNT_DOOMED)) { + if (unlikely(bastard->mnt_flags & (MNT_SYNC_UMOUNT | MNT_DOOMED))) { mnt_add_count(mnt, -1); unlock_mount_hash(); return 1; @@ -1707,6 +1703,7 @@ static int do_umount(struct mount *mnt, int flags) umount_tree(mnt, UMOUNT_PROPAGATE); retval = 0; } else { + smp_mb(); // paired with __legitimize_mnt() shrink_submounts(mnt); retval = -EBUSY; if (!propagate_mount_busy(mnt, 2)) { @@ -1777,6 +1774,7 @@ static void warn_mandlock(void) static int can_umount(const struct path *path, int flags) { struct mount *mnt = real_mount(path->mnt); + struct super_block *sb = path->dentry->d_sb; if (!may_mount()) return -EPERM; @@ -1786,7 +1784,7 @@ static int can_umount(const struct path *path, int flags) return -EINVAL; if (mnt->mnt.mnt_flags & MNT_LOCKED) /* Check optimistically */ return -EINVAL; - if (flags & MNT_FORCE && !capable(CAP_SYS_ADMIN)) + if (flags & MNT_FORCE && !ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) return -EPERM; return 0; } @@ -2020,6 +2018,11 @@ struct vfsmount *clone_private_mount(const struct path *path) if (!check_mnt(old_mnt)) goto invalid; + if (!ns_capable(old_mnt->mnt_ns->user_ns, CAP_SYS_ADMIN)) { + up_read(&namespace_sem); + return ERR_PTR(-EPERM); + } + if (has_locked_children(old_mnt, path->dentry)) goto invalid; @@ -2251,14 +2254,14 @@ static int attach_recursive_mnt(struct mount *source_mnt, hlist_for_each_entry_safe(child, n, &tree_list, mnt_hash) { struct mount *q; hlist_del_init(&child->mnt_hash); - q = __lookup_mnt(&child->mnt_parent->mnt, - child->mnt_mountpoint); - if (q) - mnt_change_mountpoint(child, smp, q); /* Notice when we are propagating across user namespaces */ if (child->mnt_parent->mnt_ns->user_ns != user_ns) lock_mnt_tree(child); child->mnt.mnt_flags &= ~MNT_LOCKED; + q = __lookup_mnt(&child->mnt_parent->mnt, + child->mnt_mountpoint); + if (q) + mnt_change_mountpoint(child, smp, q); commit_tree(child); } put_mountpoint(smp); @@ -2373,6 +2376,10 @@ static int do_change_type(struct path *path, int ms_flags) return -EINVAL; namespace_lock(); + if (!check_mnt(mnt)) { + err = -EINVAL; + goto out_unlock; + } if (type == MS_SHARED) { err = invent_group_ids(mnt, recurse); if (err) @@ -2811,7 +2818,7 @@ static int do_set_group(struct path *from_path, struct path *to_path) if (IS_MNT_SLAVE(from)) { struct mount *m = from->mnt_master; - list_add(&to->mnt_slave, &m->mnt_slave_list); + list_add(&to->mnt_slave, &from->mnt_slave); to->mnt_master = m; } diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index 14a72224b657..899e25e9b4eb 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -2,6 +2,7 @@ config NFS_FS tristate "NFS client support" depends on INET && FILE_LOCKING && MULTIUSER + select CRC32 select LOCKD select SUNRPC select NFS_ACL_SUPPORT if NFS_V3_ACL @@ -194,7 +195,6 @@ config NFS_USE_KERNEL_DNS config NFS_DEBUG bool depends on NFS_FS && SUNRPC_DEBUG - select CRC32 default y config NFS_DISABLE_UDP_SUPPORT diff --git a/fs/nfs/client.c b/fs/nfs/client.c index a8930e6c417f..de4ad41b14e2 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -1052,6 +1052,8 @@ struct nfs_server *nfs_create_server(struct fs_context *fc) if (server->namelen == 0 || server->namelen > NFS2_MAXNAMLEN) server->namelen = NFS2_MAXNAMLEN; } + /* Linux 'subtree_check' borkenness mandates this setting */ + server->fh_expire_type = NFS_FH_VOL_RENAME; if (!(fattr->valid & NFS_ATTR_FATTR)) { error = ctx->nfs_mod->rpc_ops->getattr(server, ctx->mntfh, diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index 39c697e100b1..17b38da17288 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -297,7 +297,8 @@ nfs_start_delegation_return_locked(struct nfs_inode *nfsi) if (delegation == NULL) goto out; spin_lock(&delegation->lock); - if (!test_and_set_bit(NFS_DELEGATION_RETURNING, &delegation->flags)) { + if (delegation->inode && + !test_and_set_bit(NFS_DELEGATION_RETURNING, &delegation->flags)) { clear_bit(NFS_DELEGATION_RETURN_DELAYED, &delegation->flags); /* Refcount matched in nfs_end_delegation_return() */ ret = nfs_get_delegation(delegation); @@ -570,17 +571,6 @@ static bool nfs_delegation_need_return(struct nfs_delegation *delegation) if (test_and_clear_bit(NFS_DELEGATION_RETURN, &delegation->flags)) ret = true; - else if (test_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags)) { - struct inode *inode; - - spin_lock(&delegation->lock); - inode = delegation->inode; - if (inode && list_empty(&NFS_I(inode)->open_files)) - ret = true; - spin_unlock(&delegation->lock); - } - if (ret) - clear_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags); if (test_bit(NFS_DELEGATION_RETURNING, &delegation->flags) || test_bit(NFS_DELEGATION_RETURN_DELAYED, &delegation->flags) || test_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) @@ -821,11 +811,25 @@ int nfs4_inode_make_writeable(struct inode *inode) return nfs4_inode_return_delegation(inode); } -static void nfs_mark_return_if_closed_delegation(struct nfs_server *server, - struct nfs_delegation *delegation) +static void +nfs_mark_return_if_closed_delegation(struct nfs_server *server, + struct nfs_delegation *delegation) { - set_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags); - set_bit(NFS4CLNT_DELEGRETURN, &server->nfs_client->cl_state); + struct inode *inode; + + if (test_bit(NFS_DELEGATION_RETURN, &delegation->flags) || + test_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags)) + return; + spin_lock(&delegation->lock); + inode = delegation->inode; + if (!inode) + goto out; + if (list_empty(&NFS_I(inode)->open_files)) + nfs_mark_return_delegation(server, delegation); + else + set_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags); +out: + spin_unlock(&delegation->lock); } static bool nfs_server_mark_return_all_delegations(struct nfs_server *server) diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 70660ff248b7..3c98049912df 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1825,9 +1825,7 @@ static void block_revalidate(struct dentry *dentry) static void unblock_revalidate(struct dentry *dentry) { - /* store_release ensures wait_var_event() sees the update */ - smp_store_release(&dentry->d_fsdata, NULL); - wake_up_var(&dentry->d_fsdata); + store_release_wake_up(&dentry->d_fsdata, NULL); } /* @@ -2632,6 +2630,18 @@ nfs_unblock_rename(struct rpc_task *task, struct nfs_renamedata *data) unblock_revalidate(new_dentry); } +static bool nfs_rename_is_unsafe_cross_dir(struct dentry *old_dentry, + struct dentry *new_dentry) +{ + struct nfs_server *server = NFS_SB(old_dentry->d_sb); + + if (old_dentry->d_parent != new_dentry->d_parent) + return false; + if (server->fh_expire_type & NFS_FH_RENAME_UNSAFE) + return !(server->fh_expire_type & NFS_FH_NOEXPIRE_WITH_OPEN); + return true; +} + /* * RENAME * FIXME: Some nfsds, like the Linux user space nfsd, may generate a @@ -2719,7 +2729,8 @@ int nfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, } - if (S_ISREG(old_inode->i_mode)) + if (S_ISREG(old_inode->i_mode) && + nfs_rename_is_unsafe_cross_dir(old_dentry, new_dentry)) nfs_sync_inode(old_inode); task = nfs_async_rename(old_dir, new_dir, old_dentry, new_dentry, must_unblock ? nfs_unblock_rename : NULL); diff --git a/fs/nfs/export.c b/fs/nfs/export.c index 9fe9586a51b7..aacf6220ab44 100644 --- a/fs/nfs/export.c +++ b/fs/nfs/export.c @@ -66,14 +66,21 @@ nfs_fh_to_dentry(struct super_block *sb, struct fid *fid, { struct nfs_fattr *fattr = NULL; struct nfs_fh *server_fh = nfs_exp_embedfh(fid->raw); - size_t fh_size = offsetof(struct nfs_fh, data) + server_fh->size; + size_t fh_size = offsetof(struct nfs_fh, data); const struct nfs_rpc_ops *rpc_ops; struct dentry *dentry; struct inode *inode; - int len = EMBED_FH_OFF + XDR_QUADLEN(fh_size); + int len = EMBED_FH_OFF; u32 *p = fid->raw; int ret; + /* Initial check of bounds */ + if (fh_len < len + XDR_QUADLEN(fh_size) || + fh_len > XDR_QUADLEN(NFS_MAXFHSIZE)) + return NULL; + /* Calculate embedded filehandle size */ + fh_size += server_fh->size; + len += XDR_QUADLEN(fh_size); /* NULL translates to ESTALE */ if (fh_len < len || fh_type != len) return NULL; diff --git a/fs/nfs/filelayout/filelayoutdev.c b/fs/nfs/filelayout/filelayoutdev.c index acf4b88889dc..d5f1fbfd9a0c 100644 --- a/fs/nfs/filelayout/filelayoutdev.c +++ b/fs/nfs/filelayout/filelayoutdev.c @@ -75,6 +75,7 @@ nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev, struct page *scratch; struct list_head dsaddrs; struct nfs4_pnfs_ds_addr *da; + struct net *net = server->nfs_client->cl_net; /* set up xdr stream */ scratch = alloc_page(gfp_flags); @@ -158,8 +159,7 @@ nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev, mp_count = be32_to_cpup(p); /* multipath count */ for (j = 0; j < mp_count; j++) { - da = nfs4_decode_mp_ds_addr(server->nfs_client->cl_net, - &stream, gfp_flags); + da = nfs4_decode_mp_ds_addr(net, &stream, gfp_flags); if (da) list_add_tail(&da->da_node, &dsaddrs); } @@ -169,7 +169,7 @@ nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev, goto out_err_free_deviceid; } - dsaddr->ds_list[i] = nfs4_pnfs_ds_add(&dsaddrs, gfp_flags); + dsaddr->ds_list[i] = nfs4_pnfs_ds_add(net, &dsaddrs, gfp_flags); if (!dsaddr->ds_list[i]) goto out_err_drain_dsaddrs; diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index 8056b05bd8dc..5dd16f4ae74d 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -745,14 +745,14 @@ ff_layout_choose_ds_for_read(struct pnfs_layout_segment *lseg, { struct nfs4_ff_layout_segment *fls = FF_LAYOUT_LSEG(lseg); struct nfs4_ff_layout_mirror *mirror; - struct nfs4_pnfs_ds *ds; + struct nfs4_pnfs_ds *ds = ERR_PTR(-EAGAIN); u32 idx; /* mirrors are initially sorted by efficiency */ for (idx = start_idx; idx < fls->mirror_array_cnt; idx++) { mirror = FF_LAYOUT_COMP(lseg, idx); ds = nfs4_ff_layout_prepare_ds(lseg, mirror, false); - if (!ds) + if (IS_ERR(ds)) continue; if (check_device && @@ -760,10 +760,10 @@ ff_layout_choose_ds_for_read(struct pnfs_layout_segment *lseg, continue; *best_idx = idx; - return ds; + break; } - return NULL; + return ds; } static struct nfs4_pnfs_ds * @@ -933,7 +933,7 @@ retry: for (i = 0; i < pgio->pg_mirror_count; i++) { mirror = FF_LAYOUT_COMP(pgio->pg_lseg, i); ds = nfs4_ff_layout_prepare_ds(pgio->pg_lseg, mirror, true); - if (!ds) { + if (IS_ERR(ds)) { if (!ff_layout_no_fallback_to_mds(pgio->pg_lseg)) goto out_mds; pnfs_generic_pg_cleanup(pgio); @@ -1096,6 +1096,7 @@ static void ff_layout_reset_read(struct nfs_pgio_header *hdr) } static int ff_layout_async_handle_error_v4(struct rpc_task *task, + u32 op_status, struct nfs4_state *state, struct nfs_client *clp, struct pnfs_layout_segment *lseg, @@ -1106,32 +1107,42 @@ static int ff_layout_async_handle_error_v4(struct rpc_task *task, struct nfs4_deviceid_node *devid = FF_LAYOUT_DEVID_NODE(lseg, idx); struct nfs4_slot_table *tbl = &clp->cl_session->fc_slot_table; - switch (task->tk_status) { - 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: + switch (op_status) { + case NFS4_OK: + case NFS4ERR_NXIO: + break; + case NFSERR_PERM: + if (!task->tk_xprt) + break; + xprt_force_disconnect(task->tk_xprt); + goto out_retry; + 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. Exchangeid " "flags 0x%x\n", __func__, task->tk_status, clp->cl_exchange_flags); nfs4_schedule_session_recovery(clp->cl_session, task->tk_status); - break; - case -NFS4ERR_DELAY: - case -NFS4ERR_GRACE: + goto out_retry; + case NFS4ERR_DELAY: + nfs_inc_stats(lseg->pls_layout->plh_inode, NFSIOS_DELAY); + fallthrough; + case NFS4ERR_GRACE: rpc_delay(task, FF_LAYOUT_POLL_RETRY_MAX); - break; - case -NFS4ERR_RETRY_UNCACHED_REP: - break; + goto out_retry; + case NFS4ERR_RETRY_UNCACHED_REP: + goto out_retry; /* Invalidate Layout errors */ - case -NFS4ERR_PNFS_NO_LAYOUT: - case -ESTALE: /* mapped NFS4ERR_STALE */ - case -EBADHANDLE: /* mapped NFS4ERR_BADHANDLE */ - case -EISDIR: /* mapped NFS4ERR_ISDIR */ - case -NFS4ERR_FHEXPIRED: - case -NFS4ERR_WRONG_TYPE: + case NFS4ERR_PNFS_NO_LAYOUT: + case NFS4ERR_STALE: + case NFS4ERR_BADHANDLE: + case NFS4ERR_ISDIR: + case NFS4ERR_FHEXPIRED: + case NFS4ERR_WRONG_TYPE: dprintk("%s Invalid layout error %d\n", __func__, task->tk_status); /* @@ -1144,6 +1155,11 @@ static int ff_layout_async_handle_error_v4(struct rpc_task *task, pnfs_destroy_layout(NFS_I(inode)); rpc_wake_up(&tbl->slot_tbl_waitq); goto reset; + default: + break; + } + + switch (task->tk_status) { /* RPC connection errors */ case -ECONNREFUSED: case -EHOSTDOWN: @@ -1159,26 +1175,56 @@ static int ff_layout_async_handle_error_v4(struct rpc_task *task, nfs4_delete_deviceid(devid->ld, devid->nfs_client, &devid->deviceid); rpc_wake_up(&tbl->slot_tbl_waitq); - fallthrough; + break; default: - if (ff_layout_avoid_mds_available_ds(lseg)) - return -NFS4ERR_RESET_TO_PNFS; -reset: - dprintk("%s Retry through MDS. Error %d\n", __func__, - task->tk_status); - return -NFS4ERR_RESET_TO_MDS; + break; } + + if (ff_layout_avoid_mds_available_ds(lseg)) + return -NFS4ERR_RESET_TO_PNFS; +reset: + dprintk("%s Retry through MDS. Error %d\n", __func__, + task->tk_status); + return -NFS4ERR_RESET_TO_MDS; + +out_retry: task->tk_status = 0; return -EAGAIN; } /* Retry all errors through either pNFS or MDS except for -EJUKEBOX */ static int ff_layout_async_handle_error_v3(struct rpc_task *task, + u32 op_status, + struct nfs_client *clp, struct pnfs_layout_segment *lseg, u32 idx) { struct nfs4_deviceid_node *devid = FF_LAYOUT_DEVID_NODE(lseg, idx); + switch (op_status) { + case NFS_OK: + case NFSERR_NXIO: + break; + case NFSERR_PERM: + if (!task->tk_xprt) + break; + xprt_force_disconnect(task->tk_xprt); + goto out_retry; + case NFSERR_ACCES: + case NFSERR_BADHANDLE: + case NFSERR_FBIG: + case NFSERR_IO: + case NFSERR_NOSPC: + case NFSERR_ROFS: + case NFSERR_STALE: + goto out_reset_to_pnfs; + case NFSERR_JUKEBOX: + nfs_inc_stats(lseg->pls_layout->plh_inode, NFSIOS_DELAY); + goto out_retry; + default: + break; + } + switch (task->tk_status) { /* File access problems. Don't mark the device as unavailable */ case -EACCES: @@ -1197,6 +1243,7 @@ static int ff_layout_async_handle_error_v3(struct rpc_task *task, nfs4_delete_deviceid(devid->ld, devid->nfs_client, &devid->deviceid); } +out_reset_to_pnfs: /* FIXME: Need to prevent infinite looping here. */ return -NFS4ERR_RESET_TO_PNFS; out_retry: @@ -1207,6 +1254,7 @@ out_retry: } static int ff_layout_async_handle_error(struct rpc_task *task, + u32 op_status, struct nfs4_state *state, struct nfs_client *clp, struct pnfs_layout_segment *lseg, @@ -1225,10 +1273,11 @@ static int ff_layout_async_handle_error(struct rpc_task *task, switch (vers) { case 3: - return ff_layout_async_handle_error_v3(task, lseg, idx); - case 4: - return ff_layout_async_handle_error_v4(task, state, clp, + return ff_layout_async_handle_error_v3(task, op_status, clp, lseg, idx); + case 4: + return ff_layout_async_handle_error_v4(task, op_status, state, + clp, lseg, idx); default: /* should never happen */ WARN_ON_ONCE(1); @@ -1255,6 +1304,7 @@ static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg, case -ECONNRESET: case -EHOSTDOWN: case -EHOSTUNREACH: + case -ENETDOWN: case -ENETUNREACH: case -EADDRINUSE: case -ENOBUFS: @@ -1280,6 +1330,7 @@ static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg, switch (status) { case NFS4ERR_DELAY: case NFS4ERR_GRACE: + case NFS4ERR_PERM: break; case NFS4ERR_NXIO: ff_layout_mark_ds_unreachable(lseg, idx); @@ -1312,7 +1363,8 @@ static int ff_layout_read_done_cb(struct rpc_task *task, trace_ff_layout_read_error(hdr); } - err = ff_layout_async_handle_error(task, hdr->args.context->state, + err = ff_layout_async_handle_error(task, hdr->res.op_status, + hdr->args.context->state, hdr->ds_clp, hdr->lseg, hdr->pgio_mirror_idx); @@ -1482,7 +1534,8 @@ static int ff_layout_write_done_cb(struct rpc_task *task, trace_ff_layout_write_error(hdr); } - err = ff_layout_async_handle_error(task, hdr->args.context->state, + err = ff_layout_async_handle_error(task, hdr->res.op_status, + hdr->args.context->state, hdr->ds_clp, hdr->lseg, hdr->pgio_mirror_idx); @@ -1528,8 +1581,9 @@ static int ff_layout_commit_done_cb(struct rpc_task *task, trace_ff_layout_commit_error(data); } - err = ff_layout_async_handle_error(task, NULL, data->ds_clp, - data->lseg, data->ds_commit_index); + err = ff_layout_async_handle_error(task, data->res.op_status, + NULL, data->ds_clp, data->lseg, + data->ds_commit_index); trace_nfs4_pnfs_commit_ds(data, err); switch (err) { @@ -1785,6 +1839,7 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr) u32 idx = hdr->pgio_mirror_idx; int vers; struct nfs_fh *fh; + bool ds_fatal_error = false; dprintk("--> %s ino %lu pgbase %u req %zu@%llu\n", __func__, hdr->inode->i_ino, @@ -1792,8 +1847,10 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr) mirror = FF_LAYOUT_COMP(lseg, idx); ds = nfs4_ff_layout_prepare_ds(lseg, mirror, false); - if (!ds) + if (IS_ERR(ds)) { + ds_fatal_error = nfs_error_is_fatal(PTR_ERR(ds)); goto out_failed; + } ds_clnt = nfs4_ff_find_or_create_ds_client(mirror, ds->ds_clp, hdr->inode); @@ -1834,7 +1891,7 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr) return PNFS_ATTEMPTED; out_failed: - if (ff_layout_avoid_mds_available_ds(lseg)) + if (ff_layout_avoid_mds_available_ds(lseg) && !ds_fatal_error) return PNFS_TRY_AGAIN; trace_pnfs_mds_fallback_read_pagelist(hdr->inode, hdr->args.offset, hdr->args.count, @@ -1855,11 +1912,14 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync) int vers; struct nfs_fh *fh; u32 idx = hdr->pgio_mirror_idx; + bool ds_fatal_error = false; mirror = FF_LAYOUT_COMP(lseg, idx); ds = nfs4_ff_layout_prepare_ds(lseg, mirror, true); - if (!ds) + if (IS_ERR(ds)) { + ds_fatal_error = nfs_error_is_fatal(PTR_ERR(ds)); goto out_failed; + } ds_clnt = nfs4_ff_find_or_create_ds_client(mirror, ds->ds_clp, hdr->inode); @@ -1902,7 +1962,7 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync) return PNFS_ATTEMPTED; out_failed: - if (ff_layout_avoid_mds_available_ds(lseg)) + if (ff_layout_avoid_mds_available_ds(lseg) && !ds_fatal_error) return PNFS_TRY_AGAIN; trace_pnfs_mds_fallback_write_pagelist(hdr->inode, hdr->args.offset, hdr->args.count, @@ -1944,7 +2004,7 @@ static int ff_layout_initiate_commit(struct nfs_commit_data *data, int how) idx = calc_ds_index_from_commit(lseg, data->ds_commit_index); mirror = FF_LAYOUT_COMP(lseg, idx); ds = nfs4_ff_layout_prepare_ds(lseg, mirror, true); - if (!ds) + if (IS_ERR(ds)) goto out_err; ds_clnt = nfs4_ff_find_or_create_ds_client(mirror, ds->ds_clp, diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c index e028f5a0ef5f..95d5dca67145 100644 --- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c +++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c @@ -49,6 +49,7 @@ nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev, struct nfs4_pnfs_ds_addr *da; struct nfs4_ff_layout_ds *new_ds = NULL; struct nfs4_ff_ds_version *ds_versions = NULL; + struct net *net = server->nfs_client->cl_net; u32 mp_count; u32 version_count; __be32 *p; @@ -80,8 +81,7 @@ nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev, for (i = 0; i < mp_count; i++) { /* multipath ds */ - da = nfs4_decode_mp_ds_addr(server->nfs_client->cl_net, - &stream, gfp_flags); + da = nfs4_decode_mp_ds_addr(net, &stream, gfp_flags); if (da) list_add_tail(&da->da_node, &dsaddrs); } @@ -149,7 +149,7 @@ nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev, new_ds->ds_versions = ds_versions; new_ds->ds_versions_cnt = version_count; - new_ds->ds = nfs4_pnfs_ds_add(&dsaddrs, gfp_flags); + new_ds->ds = nfs4_pnfs_ds_add(net, &dsaddrs, gfp_flags); if (!new_ds->ds) goto out_err_drain_dsaddrs; @@ -370,11 +370,11 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, struct nfs4_ff_layout_mirror *mirror, bool fail_return) { - struct nfs4_pnfs_ds *ds = NULL; + struct nfs4_pnfs_ds *ds; struct inode *ino = lseg->pls_layout->plh_inode; struct nfs_server *s = NFS_SERVER(ino); unsigned int max_payload; - int status; + int status = -EAGAIN; if (!ff_layout_init_mirror_ds(lseg->pls_layout, mirror)) goto noconnect; @@ -412,7 +412,7 @@ noconnect: ff_layout_send_layouterror(lseg); if (fail_return || !ff_layout_has_available_ds(lseg)) pnfs_error_mark_layout_for_return(ino, lseg); - ds = NULL; + ds = ERR_PTR(status); out: return ds; } diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 964df0725f4c..627410be2e88 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -74,6 +74,8 @@ nfs_fattr_to_ino_t(struct nfs_fattr *fattr) int nfs_wait_bit_killable(struct wait_bit_key *key, int mode) { + if (unlikely(nfs_current_task_exiting())) + return -EINTR; schedule(); if (signal_pending_state(mode, current)) return -ERESTARTSYS; @@ -553,6 +555,8 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr) set_nlink(inode, fattr->nlink); else if (fattr_supported & NFS_ATTR_FATTR_NLINK) nfs_set_cache_invalid(inode, NFS_INO_INVALID_NLINK); + else + set_nlink(inode, 1); if (fattr->valid & NFS_ATTR_FATTR_OWNER) inode->i_uid = fattr->uid; else if (fattr_supported & NFS_ATTR_FATTR_OWNER) @@ -2427,15 +2431,26 @@ EXPORT_SYMBOL_GPL(nfs_net_id); static int nfs_net_init(struct net *net) { struct nfs_net *nn = net_generic(net, nfs_net_id); + int err; nfs_clients_init(net); if (!rpc_proc_register(net, &nn->rpcstats)) { - nfs_clients_exit(net); - return -ENOMEM; + err = -ENOMEM; + goto err_proc_rpc; } - return nfs_fs_proc_net_init(net); + err = nfs_fs_proc_net_init(net); + if (err) + goto err_proc_nfs; + + return 0; + +err_proc_nfs: + rpc_proc_unregister(net, "nfs"); +err_proc_rpc: + nfs_clients_exit(net); + return err; } static void nfs_net_exit(struct net *net) diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 7fa23a6368e0..6ea10abfa851 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -598,9 +598,12 @@ nfs_write_match_verf(const struct nfs_writeverf *verf, static inline gfp_t nfs_io_gfp_mask(void) { - if (current->flags & PF_WQ_WORKER) - return GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN; - return GFP_KERNEL; + gfp_t ret = current_gfp_context(GFP_KERNEL); + + /* For workers __GFP_NORETRY only with __GFP_IO or __GFP_FS */ + if ((current->flags & PF_WQ_WORKER) && ret == GFP_KERNEL) + ret |= __GFP_NORETRY | __GFP_NOWARN; + return ret; } /* @@ -826,33 +829,16 @@ u64 nfs_timespec_to_change_attr(const struct timespec64 *ts) return ((u64)ts->tv_sec << 30) + ts->tv_nsec; } -#ifdef CONFIG_CRC32 -/** - * nfs_fhandle_hash - calculate the crc32 hash for the filehandle - * @fh - pointer to filehandle - * - * returns a crc32 hash for the filehandle that is compatible with - * the one displayed by "wireshark". - */ -static inline u32 nfs_fhandle_hash(const struct nfs_fh *fh) -{ - return ~crc32_le(0xFFFFFFFF, &fh->data[0], fh->size); -} static inline u32 nfs_stateid_hash(const nfs4_stateid *stateid) { return ~crc32_le(0xFFFFFFFF, &stateid->other[0], NFS4_STATEID_OTHER_SIZE); } -#else -static inline u32 nfs_fhandle_hash(const struct nfs_fh *fh) -{ - return 0; -} -static inline u32 nfs_stateid_hash(nfs4_stateid *stateid) + +static inline bool nfs_current_task_exiting(void) { - return 0; + return (current->flags & PF_EXITING) != 0; } -#endif static inline bool nfs_error_is_fatal(int err) { diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index 2e7579626cf0..f036d30f7515 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -39,7 +39,7 @@ nfs3_rpc_wrapper(struct rpc_clnt *clnt, struct rpc_message *msg, int flags) __set_current_state(TASK_KILLABLE|TASK_FREEZABLE_UNSAFE); schedule_timeout(NFS_JUKEBOX_RETRY_TIME); res = -ERESTARTSYS; - } while (!fatal_signal_pending(current)); + } while (!fatal_signal_pending(current) && !nfs_current_task_exiting()); return res; } diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 5b06b8d4e014..4abac68a4f0f 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -422,6 +422,8 @@ static int nfs4_delay_killable(long *timeout) { might_sleep(); + if (unlikely(nfs_current_task_exiting())) + return -EINTR; __set_current_state(TASK_KILLABLE|TASK_FREEZABLE_UNSAFE); schedule_timeout(nfs4_update_delay(timeout)); if (!__fatal_signal_pending(current)) @@ -433,6 +435,8 @@ static int nfs4_delay_interruptible(long *timeout) { might_sleep(); + if (unlikely(nfs_current_task_exiting())) + return -EINTR; __set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE_UNSAFE); schedule_timeout(nfs4_update_delay(timeout)); if (!signal_pending(current)) @@ -1712,7 +1716,8 @@ static void nfs_set_open_stateid_locked(struct nfs4_state *state, rcu_read_unlock(); trace_nfs4_open_stateid_update_wait(state->inode, stateid, 0); - if (!fatal_signal_pending(current)) { + if (!fatal_signal_pending(current) && + !nfs_current_task_exiting()) { if (schedule_timeout(5*HZ) == 0) status = -EAGAIN; else @@ -3500,7 +3505,7 @@ static bool nfs4_refresh_open_old_stateid(nfs4_stateid *dst, write_sequnlock(&state->seqlock); trace_nfs4_close_stateid_update_wait(state->inode, dst, 0); - if (fatal_signal_pending(current)) + if (fatal_signal_pending(current) || nfs_current_task_exiting()) status = -EINTR; else if (schedule_timeout(5*HZ) != 0) @@ -6060,6 +6065,8 @@ static ssize_t nfs4_proc_get_acl(struct inode *inode, void *buf, size_t buflen, struct nfs_server *server = NFS_SERVER(inode); int ret; + if (unlikely(NFS_FH(inode)->size == 0)) + return -ENODATA; if (!nfs4_server_supports_acls(server, type)) return -EOPNOTSUPP; ret = nfs_revalidate_inode(inode, NFS_INO_INVALID_CHANGE); @@ -6134,6 +6141,9 @@ static int nfs4_proc_set_acl(struct inode *inode, const void *buf, { struct nfs4_exception exception = { }; int err; + + if (unlikely(NFS_FH(inode)->size == 0)) + return -ENODATA; do { err = __nfs4_proc_set_acl(inode, buf, buflen, type); trace_nfs4_set_acl(inode, err); @@ -6886,10 +6896,18 @@ static struct nfs4_unlockdata *nfs4_alloc_unlockdata(struct file_lock *fl, struct nfs4_unlockdata *p; struct nfs4_state *state = lsp->ls_state; struct inode *inode = state->inode; + struct nfs_lock_context *l_ctx; p = kzalloc(sizeof(*p), GFP_KERNEL); if (p == NULL) return NULL; + l_ctx = nfs_get_lock_context(ctx); + if (!IS_ERR(l_ctx)) { + p->l_ctx = l_ctx; + } else { + kfree(p); + return NULL; + } p->arg.fh = NFS_FH(inode); p->arg.fl = &p->fl; p->arg.seqid = seqid; @@ -6897,7 +6915,6 @@ static struct nfs4_unlockdata *nfs4_alloc_unlockdata(struct file_lock *fl, p->lsp = lsp; /* Ensure we don't close file until we're done freeing locks! */ p->ctx = get_nfs_open_context(ctx); - p->l_ctx = nfs_get_lock_context(ctx); locks_init_lock(&p->fl); locks_copy_lock(&p->fl, fl); p->server = NFS_SERVER(inode); @@ -10618,7 +10635,7 @@ const struct nfs4_minor_version_ops *nfs_v4_minor_ops[] = { static ssize_t nfs4_listxattr(struct dentry *dentry, char *list, size_t size) { - ssize_t error, error2, error3; + ssize_t error, error2, error3, error4 = 0; size_t left = size; error = generic_listxattr(dentry, list, left); @@ -10641,8 +10658,18 @@ static ssize_t nfs4_listxattr(struct dentry *dentry, char *list, size_t size) error3 = nfs4_listxattr_nfs4_user(d_inode(dentry), list, left); if (error3 < 0) return error3; + if (list) { + list += error3; + left -= error3; + } + + if (!nfs_server_capable(d_inode(dentry), NFS_CAP_SECURITY_LABEL)) { + error4 = security_inode_listsecurity(d_inode(dentry), list, left); + if (error4 < 0) + return error4; + } - error += error2 + error3; + error += error2 + error3 + error4; if (size && error > size) return -ERANGE; return error; diff --git a/fs/nfs/nfs4session.h b/fs/nfs/nfs4session.h index 351616c61df5..f9c291e2165c 100644 --- a/fs/nfs/nfs4session.h +++ b/fs/nfs/nfs4session.h @@ -148,16 +148,12 @@ static inline void nfs4_copy_sessionid(struct nfs4_sessionid *dst, memcpy(dst->data, src->data, NFS4_MAX_SESSIONID_LEN); } -#ifdef CONFIG_CRC32 /* * nfs_session_id_hash - calculate the crc32 hash for the session id * @session - pointer to session */ #define nfs_session_id_hash(sess_id) \ (~crc32_le(0xFFFFFFFF, &(sess_id)->data[0], sizeof((sess_id)->data))) -#else -#define nfs_session_id_hash(session) (0) -#endif #else /* defined(CONFIG_NFS_V4_1) */ static inline int nfs4_init_session(struct nfs_client *clp) diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 48ea40660422..80a7c5bd7a47 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -2737,7 +2737,15 @@ out_error: pr_warn_ratelimited("NFS: state manager%s%s failed on NFSv4 server %s" " with error %d\n", section_sep, section, clp->cl_hostname, -status); - ssleep(1); + switch (status) { + case -ENETDOWN: + case -ENETUNREACH: + nfs_mark_client_ready(clp, -EIO); + break; + default: + ssleep(1); + break; + } out_drain: memalloc_nofs_restore(memflags); nfs4_end_drain_session(clp); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index f68286932019..7f48e0d870bd 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -732,6 +732,14 @@ pnfs_mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo, return remaining; } +static void pnfs_reset_return_info(struct pnfs_layout_hdr *lo) +{ + struct pnfs_layout_segment *lseg; + + list_for_each_entry(lseg, &lo->plh_return_segs, pls_list) + pnfs_set_plh_return_info(lo, lseg->pls_range.iomode, 0); +} + static void pnfs_free_returned_lsegs(struct pnfs_layout_hdr *lo, struct list_head *free_me, @@ -1180,6 +1188,7 @@ void pnfs_layoutreturn_free_lsegs(struct pnfs_layout_hdr *lo, pnfs_mark_matching_lsegs_invalid(lo, &freeme, range, seq); pnfs_free_returned_lsegs(lo, &freeme, range, seq); pnfs_set_layout_stateid(lo, stateid, NULL, true); + pnfs_reset_return_info(lo); } else pnfs_mark_layout_stateid_invalid(lo, &freeme); out_unlock: @@ -1921,8 +1930,10 @@ static void nfs_layoutget_begin(struct pnfs_layout_hdr *lo) static void nfs_layoutget_end(struct pnfs_layout_hdr *lo) { if (atomic_dec_and_test(&lo->plh_outstanding) && - test_and_clear_bit(NFS_LAYOUT_DRAIN, &lo->plh_flags)) + test_and_clear_bit(NFS_LAYOUT_DRAIN, &lo->plh_flags)) { + smp_mb__after_atomic(); wake_up_bit(&lo->plh_flags, NFS_LAYOUT_DRAIN); + } } static bool pnfs_is_first_layoutget(struct pnfs_layout_hdr *lo) diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index e3e6a41f19de..f5173c188184 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -59,6 +59,7 @@ struct nfs4_pnfs_ds { struct list_head ds_node; /* nfs4_pnfs_dev_hlist dev_dslist */ char *ds_remotestr; /* comma sep list of addrs */ struct list_head ds_addrs; + const struct net *ds_net; struct nfs_client *ds_clp; refcount_t ds_count; unsigned long ds_state; @@ -405,7 +406,8 @@ int pnfs_generic_commit_pagelist(struct inode *inode, int pnfs_generic_scan_commit_lists(struct nfs_commit_info *cinfo, int max); void pnfs_generic_write_commit_done(struct rpc_task *task, void *data); void nfs4_pnfs_ds_put(struct nfs4_pnfs_ds *ds); -struct nfs4_pnfs_ds *nfs4_pnfs_ds_add(struct list_head *dsaddrs, +struct nfs4_pnfs_ds *nfs4_pnfs_ds_add(const struct net *net, + struct list_head *dsaddrs, gfp_t gfp_flags); void nfs4_pnfs_v3_ds_connect_unload(void); int nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds, diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index 47a8da3f5c9f..31afa88742f6 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -651,12 +651,12 @@ _same_data_server_addrs_locked(const struct list_head *dsaddrs1, * Lookup DS by addresses. nfs4_ds_cache_lock is held */ static struct nfs4_pnfs_ds * -_data_server_lookup_locked(const struct list_head *dsaddrs) +_data_server_lookup_locked(const struct net *net, const struct list_head *dsaddrs) { struct nfs4_pnfs_ds *ds; list_for_each_entry(ds, &nfs4_data_server_cache, ds_node) - if (_same_data_server_addrs_locked(&ds->ds_addrs, dsaddrs)) + if (ds->ds_net == net && _same_data_server_addrs_locked(&ds->ds_addrs, dsaddrs)) return ds; return NULL; } @@ -763,7 +763,7 @@ out_err: * uncached and return cached struct nfs4_pnfs_ds. */ struct nfs4_pnfs_ds * -nfs4_pnfs_ds_add(struct list_head *dsaddrs, gfp_t gfp_flags) +nfs4_pnfs_ds_add(const struct net *net, struct list_head *dsaddrs, gfp_t gfp_flags) { struct nfs4_pnfs_ds *tmp_ds, *ds = NULL; char *remotestr; @@ -781,13 +781,14 @@ nfs4_pnfs_ds_add(struct list_head *dsaddrs, gfp_t gfp_flags) remotestr = nfs4_pnfs_remotestr(dsaddrs, gfp_flags); spin_lock(&nfs4_ds_cache_lock); - tmp_ds = _data_server_lookup_locked(dsaddrs); + tmp_ds = _data_server_lookup_locked(net, dsaddrs); if (tmp_ds == NULL) { INIT_LIST_HEAD(&ds->ds_addrs); list_splice_init(dsaddrs, &ds->ds_addrs); ds->ds_remotestr = remotestr; refcount_set(&ds->ds_count, 1); INIT_LIST_HEAD(&ds->ds_node); + ds->ds_net = net; ds->ds_clp = NULL; list_add(&ds->ds_node, &nfs4_data_server_cache); dprintk("%s add new data server %s\n", __func__, diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 3dffeb1d17b9..2dca011da034 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -1018,6 +1018,16 @@ int nfs_reconfigure(struct fs_context *fc) sync_filesystem(sb); /* + * The SB_RDONLY flag has been removed from the superblock during + * mounts to prevent interference between different filesystems. + * Similarly, it is also necessary to ignore the SB_RDONLY flag + * during reconfiguration; otherwise, it may also result in the + * creation of redundant superblocks when mounting a directory with + * different rw and ro flags multiple times. + */ + fc->sb_flags_mask &= ~SB_RDONLY; + + /* * Userspace mount programs that send binary options generally send * them populated with default values. We have no way to know which * ones were explicitly specified. Fall back to legacy behavior and @@ -1273,8 +1283,17 @@ int nfs_get_tree_common(struct fs_context *fc) if (IS_ERR(server)) return PTR_ERR(server); + /* + * When NFS_MOUNT_UNSHARED is not set, NFS forces the sharing of a + * superblock among each filesystem that mounts sub-directories + * belonging to a single exported root path. + * To prevent interference between different filesystems, the + * SB_RDONLY flag should be removed from the superblock. + */ if (server->flags & NFS_MOUNT_UNSHARED) compare_super = NULL; + else + fc->sb_flags &= ~SB_RDONLY; /* -o noac implies -o sync */ if (server->flags & NFS_MOUNT_NOAC) diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig index 7c441f2bd444..4f704f868d9c 100644 --- a/fs/nfsd/Kconfig +++ b/fs/nfsd/Kconfig @@ -4,6 +4,7 @@ config NFSD depends on INET depends on FILE_LOCKING depends on FSNOTIFY + select CRC32 select LOCKD select SUNRPC select EXPORTFS diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 6eb02390bd42..a5e017d94215 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -3536,7 +3536,8 @@ bool nfsd4_spo_must_allow(struct svc_rqst *rqstp) struct nfs4_op_map *allow = &cstate->clp->cl_spo_must_allow; u32 opiter; - if (!cstate->minorversion) + if (rqstp->rq_procinfo != &nfsd_version4.vs_proc[NFSPROC4_COMPOUND] || + cstate->minorversion == 0) return false; if (cstate->spo_must_allowed) diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index f6fa719ee326..bdee95d714d0 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1069,6 +1069,12 @@ static struct nfs4_ol_stateid * nfs4_alloc_open_stateid(struct nfs4_client *clp) return openlockstateid(stid); } +/* + * As the sc_free callback of deleg, this may be called by nfs4_put_stid + * in nfsd_break_one_deleg. + * Considering nfsd_break_one_deleg is called with the flc->flc_lock held, + * this function mustn't ever sleep. + */ static void nfs4_free_deleg(struct nfs4_stid *stid) { struct nfs4_delegation *dp = delegstateid(stid); @@ -4923,6 +4929,7 @@ static const struct nfsd4_callback_ops nfsd4_cb_recall_ops = { static void nfsd_break_one_deleg(struct nfs4_delegation *dp) { + bool queued; /* * We're assuming the state code never drops its reference * without first removing the lease. Since we're in this lease @@ -4931,7 +4938,10 @@ static void nfsd_break_one_deleg(struct nfs4_delegation *dp) * we know it's safe to take a reference. */ refcount_inc(&dp->dl_stid.sc_count); - WARN_ON_ONCE(!nfsd4_run_cb(&dp->dl_recall)); + queued = nfsd4_run_cb(&dp->dl_recall); + WARN_ON_ONCE(!queued); + if (!queued) + refcount_dec(&dp->dl_stid.sc_count); } /* Called from break_lease() with flc_lock held. */ @@ -6237,14 +6247,19 @@ deleg_reaper(struct nfsd_net *nn) spin_lock(&nn->client_lock); list_for_each_safe(pos, next, &nn->client_lru) { clp = list_entry(pos, struct nfs4_client, cl_lru); - if (clp->cl_state != NFSD4_ACTIVE || - list_empty(&clp->cl_delegations) || - atomic_read(&clp->cl_delegs_in_recall) || - test_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags) || - (ktime_get_boottime_seconds() - - clp->cl_ra_time < 5)) { + + if (clp->cl_state != NFSD4_ACTIVE) + continue; + if (list_empty(&clp->cl_delegations)) + continue; + if (atomic_read(&clp->cl_delegs_in_recall)) + continue; + if (test_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags)) + continue; + if (ktime_get_boottime_seconds() - clp->cl_ra_time < 5) + continue; + if (clp->cl_cb_state != NFSD4_CB_UP) continue; - } list_add(&clp->cl_ra_cblist, &cblist); /* release in nfsd4_cb_recall_any_release */ diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h index 513e028b0bbe..40aee06ebd95 100644 --- a/fs/nfsd/nfsfh.h +++ b/fs/nfsd/nfsfh.h @@ -263,7 +263,6 @@ static inline bool fh_fsid_match(const struct knfsd_fh *fh1, return true; } -#ifdef CONFIG_CRC32 /** * knfsd_fh_hash - calculate the crc32 hash for the filehandle * @fh - pointer to filehandle @@ -275,12 +274,6 @@ static inline u32 knfsd_fh_hash(const struct knfsd_fh *fh) { return ~crc32_le(0xFFFFFFFF, fh->fh_raw, fh->fh_size); } -#else -static inline u32 knfsd_fh_hash(const struct knfsd_fh *fh) -{ - return 0; -} -#endif /** * fh_clear_pre_post_attrs - Reset pre/post attributes diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 80a2b3631adb..0f6428892e06 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -427,13 +427,13 @@ static int nfsd_startup_net(struct net *net, const struct cred *cred) if (ret) goto out_filecache; +#ifdef CONFIG_NFSD_V4_2_INTER_SSC + nfsd4_ssc_init_umount_work(nn); +#endif ret = nfs4_state_start_net(net); if (ret) goto out_reply_cache; -#ifdef CONFIG_NFSD_V4_2_INTER_SSC - nfsd4_ssc_init_umount_work(nn); -#endif nn->nfsd_net_up = true; return 0; diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c index 3139a1863751..29cb1236e1a9 100644 --- a/fs/nilfs2/btree.c +++ b/fs/nilfs2/btree.c @@ -2094,11 +2094,13 @@ static int nilfs_btree_propagate(struct nilfs_bmap *btree, ret = nilfs_btree_do_lookup(btree, path, key, NULL, level + 1, 0); if (ret < 0) { - if (unlikely(ret == -ENOENT)) + if (unlikely(ret == -ENOENT)) { nilfs_crit(btree->b_inode->i_sb, "writing node/leaf block does not appear in b-tree (ino=%lu) at key=%llu, level=%d", btree->b_inode->i_ino, (unsigned long long)key, level); + ret = -EINVAL; + } goto out; } diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c index 889e3e570213..0f3753af1674 100644 --- a/fs/nilfs2/dir.c +++ b/fs/nilfs2/dir.c @@ -64,12 +64,6 @@ static inline unsigned int nilfs_chunk_size(struct inode *inode) return inode->i_sb->s_blocksize; } -static inline void nilfs_put_page(struct page *page) -{ - kunmap(page); - put_page(page); -} - /* * Return the offset into page `page_nr' of the last valid * byte in that page, plus one. @@ -450,8 +444,7 @@ int nilfs_inode_by_name(struct inode *dir, const struct qstr *qstr, ino_t *ino) return 0; } -/* Releases the page */ -void nilfs_set_link(struct inode *dir, struct nilfs_dir_entry *de, +int nilfs_set_link(struct inode *dir, struct nilfs_dir_entry *de, struct page *page, struct inode *inode) { unsigned int from = (char *)de - (char *)page_address(page); @@ -461,12 +454,15 @@ void nilfs_set_link(struct inode *dir, struct nilfs_dir_entry *de, lock_page(page); err = nilfs_prepare_chunk(page, from, to); - BUG_ON(err); + if (unlikely(err)) { + unlock_page(page); + return err; + } de->inode = cpu_to_le64(inode->i_ino); nilfs_set_de_type(de, inode); nilfs_commit_chunk(page, mapping, from, to); - nilfs_put_page(page); dir->i_mtime = dir->i_ctime = current_time(dir); + return 0; } /* @@ -569,7 +565,7 @@ out_unlock: /* * nilfs_delete_entry deletes a directory entry by merging it with the - * previous entry. Page is up-to-date. Releases the page. + * previous entry. Page is up-to-date. */ int nilfs_delete_entry(struct nilfs_dir_entry *dir, struct page *page) { @@ -598,14 +594,16 @@ int nilfs_delete_entry(struct nilfs_dir_entry *dir, struct page *page) from = (char *)pde - (char *)page_address(page); lock_page(page); err = nilfs_prepare_chunk(page, from, to); - BUG_ON(err); + if (unlikely(err)) { + unlock_page(page); + goto out; + } if (pde) pde->rec_len = nilfs_rec_len_to_disk(to - from); dir->inode = 0; nilfs_commit_chunk(page, mapping, from, to); inode->i_ctime = inode->i_mtime = current_time(inode); out: - nilfs_put_page(page); return err; } diff --git a/fs/nilfs2/direct.c b/fs/nilfs2/direct.c index 893ab36824cc..2d8dc6b35b54 100644 --- a/fs/nilfs2/direct.c +++ b/fs/nilfs2/direct.c @@ -273,6 +273,9 @@ static int nilfs_direct_propagate(struct nilfs_bmap *bmap, dat = nilfs_bmap_get_dat(bmap); key = nilfs_bmap_data_get_key(bmap, bh); ptr = nilfs_direct_get_ptr(bmap, key); + if (ptr == NILFS_BMAP_INVALID_PTR) + return -EINVAL; + if (!buffer_nilfs_volatile(bh)) { oldreq.pr_entry_nr = ptr; newreq.pr_entry_nr = ptr; diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 452fb23d2e4c..1eb6c90fb7f4 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -517,11 +517,18 @@ static int __nilfs_read_inode(struct super_block *sb, inode->i_op = &nilfs_symlink_inode_operations; inode_nohighmem(inode); inode->i_mapping->a_ops = &nilfs_aops; - } else { + } else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) || + S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) { inode->i_op = &nilfs_special_inode_operations; init_special_inode( inode, inode->i_mode, huge_decode_dev(le64_to_cpu(raw_inode->i_device_code))); + } else { + nilfs_error(sb, + "invalid file type bits in mode 0%o for inode %lu", + inode->i_mode, ino); + err = -EIO; + goto failed_unmap; } nilfs_ifile_unmap_inode(root->ifile, ino, bh); brelse(bh); diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c index a14f6342a025..67d66207fae1 100644 --- a/fs/nilfs2/namei.c +++ b/fs/nilfs2/namei.c @@ -297,6 +297,7 @@ static int nilfs_do_unlink(struct inode *dir, struct dentry *dentry) set_nlink(inode, 1); } err = nilfs_delete_entry(de, page); + nilfs_put_page(page); if (err) goto out; @@ -405,7 +406,10 @@ static int nilfs_rename(struct user_namespace *mnt_userns, err = PTR_ERR(new_de); goto out_dir; } - nilfs_set_link(new_dir, new_de, new_page, old_inode); + err = nilfs_set_link(new_dir, new_de, new_page, old_inode); + nilfs_put_page(new_page); + if (unlikely(err)) + goto out_dir; nilfs_mark_inode_dirty(new_dir); new_inode->i_ctime = current_time(new_inode); if (dir_de) @@ -428,28 +432,27 @@ static int nilfs_rename(struct user_namespace *mnt_userns, */ old_inode->i_ctime = current_time(old_inode); - nilfs_delete_entry(old_de, old_page); - - if (dir_de) { - nilfs_set_link(old_inode, dir_de, dir_page, new_dir); - drop_nlink(old_dir); + err = nilfs_delete_entry(old_de, old_page); + if (likely(!err)) { + if (dir_de) { + err = nilfs_set_link(old_inode, dir_de, dir_page, + new_dir); + drop_nlink(old_dir); + } + nilfs_mark_inode_dirty(old_dir); } - nilfs_mark_inode_dirty(old_dir); nilfs_mark_inode_dirty(old_inode); - err = nilfs_transaction_commit(old_dir->i_sb); - return err; - out_dir: - if (dir_de) { - kunmap(dir_page); - put_page(dir_page); - } + if (dir_de) + nilfs_put_page(dir_page); out_old: - kunmap(old_page); - put_page(old_page); + nilfs_put_page(old_page); out: - nilfs_transaction_abort(old_dir->i_sb); + if (likely(!err)) + err = nilfs_transaction_commit(old_dir->i_sb); + else + nilfs_transaction_abort(old_dir->i_sb); return err; } diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h index 5a880b4edf3d..dadafad2fae7 100644 --- a/fs/nilfs2/nilfs.h +++ b/fs/nilfs2/nilfs.h @@ -240,8 +240,14 @@ nilfs_find_entry(struct inode *, const struct qstr *, struct page **); extern int nilfs_delete_entry(struct nilfs_dir_entry *, struct page *); extern int nilfs_empty_dir(struct inode *); extern struct nilfs_dir_entry *nilfs_dotdot(struct inode *, struct page **); -extern void nilfs_set_link(struct inode *, struct nilfs_dir_entry *, - struct page *, struct inode *); +int nilfs_set_link(struct inode *dir, struct nilfs_dir_entry *de, + struct page *page, struct inode *inode); + +static inline void nilfs_put_page(struct page *page) +{ + kunmap(page); + put_page(page); +} /* file.c */ extern int nilfs_sync_file(struct file *, loff_t, loff_t, int); diff --git a/fs/ntfs3/attrib.c b/fs/ntfs3/attrib.c index 0388e6b42100..feda45c7ca8e 100644 --- a/fs/ntfs3/attrib.c +++ b/fs/ntfs3/attrib.c @@ -176,7 +176,7 @@ out: int attr_allocate_clusters(struct ntfs_sb_info *sbi, struct runs_tree *run, CLST vcn, CLST lcn, CLST len, CLST *pre_alloc, enum ALLOCATE_OPT opt, CLST *alen, const size_t fr, - CLST *new_lcn) + CLST *new_lcn, CLST *new_len) { int err; CLST flen, vcn0 = vcn, pre = pre_alloc ? *pre_alloc : 0; @@ -196,20 +196,36 @@ int attr_allocate_clusters(struct ntfs_sb_info *sbi, struct runs_tree *run, if (err) goto out; - if (new_lcn && vcn == vcn0) - *new_lcn = lcn; + if (vcn == vcn0) { + /* Return the first fragment. */ + if (new_lcn) + *new_lcn = lcn; + if (new_len) + *new_len = flen; + } /* Add new fragment into run storage. */ - if (!run_add_entry(run, vcn, lcn, flen, opt == ALLOCATE_MFT)) { + if (!run_add_entry(run, vcn, lcn, flen, opt & ALLOCATE_MFT)) { /* Undo last 'ntfs_look_for_free_space' */ mark_as_free_ex(sbi, lcn, len, false); err = -ENOMEM; goto out; } + if (opt & ALLOCATE_ZERO) { + u8 shift = sbi->cluster_bits - SECTOR_SHIFT; + + err = blkdev_issue_zeroout(sbi->sb->s_bdev, + (sector_t)lcn << shift, + (sector_t)flen << shift, + GFP_NOFS, 0); + if (err) + goto out; + } + vcn += flen; - if (flen >= len || opt == ALLOCATE_MFT || + if (flen >= len || (opt & ALLOCATE_MFT) || (fr && run->count - cnt >= fr)) { *alen = vcn - vcn0; return 0; @@ -287,7 +303,8 @@ int attr_make_nonresident(struct ntfs_inode *ni, struct ATTRIB *attr, const char *data = resident_data(attr); err = attr_allocate_clusters(sbi, run, 0, 0, len, NULL, - ALLOCATE_DEF, &alen, 0, NULL); + ALLOCATE_DEF, &alen, 0, NULL, + NULL); if (err) goto out1; @@ -582,13 +599,13 @@ add_alloc_in_same_attr_seg: /* ~3 bytes per fragment. */ err = attr_allocate_clusters( sbi, run, vcn, lcn, to_allocate, &pre_alloc, - is_mft ? ALLOCATE_MFT : 0, &alen, + is_mft ? ALLOCATE_MFT : ALLOCATE_DEF, &alen, is_mft ? 0 : (sbi->record_size - le32_to_cpu(rec->used) + 8) / 3 + 1, - NULL); + NULL, NULL); if (err) goto out; } @@ -886,8 +903,19 @@ bad_inode: return err; } +/* + * attr_data_get_block - Returns 'lcn' and 'len' for given 'vcn'. + * + * @new == NULL means just to get current mapping for 'vcn' + * @new != NULL means allocate real cluster if 'vcn' maps to hole + * @zero - zeroout new allocated clusters + * + * NOTE: + * - @new != NULL is called only for sparsed or compressed attributes. + * - new allocated clusters are zeroed via blkdev_issue_zeroout. + */ int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn, - CLST *len, bool *new) + CLST *len, bool *new, bool zero) { int err = 0; struct runs_tree *run = &ni->file.run; @@ -896,29 +924,27 @@ int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn, struct ATTRIB *attr = NULL, *attr_b; struct ATTR_LIST_ENTRY *le, *le_b; struct mft_inode *mi, *mi_b; - CLST hint, svcn, to_alloc, evcn1, next_svcn, asize, end; + CLST hint, svcn, to_alloc, evcn1, next_svcn, asize, end, vcn0, alen; + unsigned int fr; u64 total_size; - u32 clst_per_frame; - bool ok; if (new) *new = false; + /* Try to find in cache. */ down_read(&ni->file.run_lock); - ok = run_lookup_entry(run, vcn, lcn, len, NULL); + if (!run_lookup_entry(run, vcn, lcn, len, NULL)) + *len = 0; up_read(&ni->file.run_lock); - if (ok && (*lcn != SPARSE_LCN || !new)) { - /* Normal way. */ - return 0; + if (*len) { + if (*lcn != SPARSE_LCN || !new) + return 0; /* Fast normal way without allocation. */ + else if (clen > *len) + clen = *len; } - if (!clen) - clen = 1; - - if (ok && clen > *len) - clen = *len; - + /* No cluster in cache or we need to allocate cluster in hole. */ sbi = ni->mi.sbi; cluster_bits = sbi->cluster_bits; @@ -944,12 +970,6 @@ int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn, goto out; } - clst_per_frame = 1u << attr_b->nres.c_unit; - to_alloc = (clen + clst_per_frame - 1) & ~(clst_per_frame - 1); - - if (vcn + to_alloc > asize) - to_alloc = asize - vcn; - svcn = le64_to_cpu(attr_b->nres.svcn); evcn1 = le64_to_cpu(attr_b->nres.evcn) + 1; @@ -968,36 +988,68 @@ int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn, evcn1 = le64_to_cpu(attr->nres.evcn) + 1; } + /* Load in cache actual information. */ err = attr_load_runs(attr, ni, run, NULL); if (err) goto out; - if (!ok) { - ok = run_lookup_entry(run, vcn, lcn, len, NULL); - if (ok && (*lcn != SPARSE_LCN || !new)) { - /* Normal way. */ - err = 0; - goto ok; - } + if (!*len) { + if (run_lookup_entry(run, vcn, lcn, len, NULL)) { + if (*lcn != SPARSE_LCN || !new) + goto ok; /* Slow normal way without allocation. */ - if (!ok && !new) { - *len = 0; - err = 0; + if (clen > *len) + clen = *len; + } else if (!new) { + /* Here we may return -ENOENT. + * In any case caller gets zero length. */ goto ok; } - - if (ok && clen > *len) { - clen = *len; - to_alloc = (clen + clst_per_frame - 1) & - ~(clst_per_frame - 1); - } } if (!is_attr_ext(attr_b)) { + /* The code below only for sparsed or compressed attributes. */ err = -EINVAL; goto out; } + vcn0 = vcn; + to_alloc = clen; + fr = (sbi->record_size - le32_to_cpu(mi->mrec->used) + 8) / 3 + 1; + /* Allocate frame aligned clusters. + * ntfs.sys usually uses 16 clusters per frame for sparsed or compressed. + * ntfs3 uses 1 cluster per frame for new created sparsed files. */ + if (attr_b->nres.c_unit) { + CLST clst_per_frame = 1u << attr_b->nres.c_unit; + CLST cmask = ~(clst_per_frame - 1); + + /* Get frame aligned vcn and to_alloc. */ + vcn = vcn0 & cmask; + to_alloc = ((vcn0 + clen + clst_per_frame - 1) & cmask) - vcn; + if (fr < clst_per_frame) + fr = clst_per_frame; + zero = true; + + /* Check if 'vcn' and 'vcn0' in different attribute segments. */ + if (vcn < svcn || evcn1 <= vcn) { + /* Load attribute for truncated vcn. */ + attr = ni_find_attr(ni, attr_b, &le, ATTR_DATA, NULL, 0, + &vcn, &mi); + if (!attr) { + err = -EINVAL; + goto out; + } + svcn = le64_to_cpu(attr->nres.svcn); + evcn1 = le64_to_cpu(attr->nres.evcn) + 1; + err = attr_load_runs(attr, ni, run, NULL); + if (err) + goto out; + } + } + + if (vcn + to_alloc > asize) + to_alloc = asize - vcn; + /* Get the last LCN to allocate from. */ hint = 0; @@ -1011,18 +1063,33 @@ int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn, hint = -1; } - err = attr_allocate_clusters( - sbi, run, vcn, hint + 1, to_alloc, NULL, 0, len, - (sbi->record_size - le32_to_cpu(mi->mrec->used) + 8) / 3 + 1, - lcn); + /* Allocate and zeroout new clusters. */ + err = attr_allocate_clusters(sbi, run, vcn, hint + 1, to_alloc, NULL, + zero ? ALLOCATE_ZERO : ALLOCATE_DEF, &alen, + fr, lcn, len); if (err) goto out; *new = true; - end = vcn + *len; - + end = vcn + alen; total_size = le64_to_cpu(attr_b->nres.total_size) + - ((u64)*len << cluster_bits); + ((u64)alen << cluster_bits); + + if (vcn != vcn0) { + if (!run_lookup_entry(run, vcn0, lcn, len, NULL)) { + err = -EINVAL; + goto out; + } + if (*lcn == SPARSE_LCN) { + /* Internal error. Should not happened. */ + WARN_ON(1); + err = -EINVAL; + goto out; + } + /* Check case when vcn0 + len overlaps new allocated clusters. */ + if (vcn0 + *len > end) + *len = end - vcn0; + } repack: err = mi_pack_runs(mi, attr, run, max(end, evcn1) - svcn); @@ -1547,7 +1614,7 @@ int attr_allocate_frame(struct ntfs_inode *ni, CLST frame, size_t compr_size, struct ATTRIB *attr = NULL, *attr_b; struct ATTR_LIST_ENTRY *le, *le_b; struct mft_inode *mi, *mi_b; - CLST svcn, evcn1, next_svcn, lcn, len; + CLST svcn, evcn1, next_svcn, len; CLST vcn, end, clst_data; u64 total_size, valid_size, data_size; @@ -1623,8 +1690,9 @@ int attr_allocate_frame(struct ntfs_inode *ni, CLST frame, size_t compr_size, } err = attr_allocate_clusters(sbi, run, vcn + clst_data, - hint + 1, len - clst_data, NULL, 0, - &alen, 0, &lcn); + hint + 1, len - clst_data, NULL, + ALLOCATE_DEF, &alen, 0, NULL, + NULL); if (err) goto out; diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c index 70b38465aee3..6d9c1dfe9b1b 100644 --- a/fs/ntfs3/file.c +++ b/fs/ntfs3/file.c @@ -122,8 +122,8 @@ static int ntfs_extend_initialized_size(struct file *file, bits = sbi->cluster_bits; vcn = pos >> bits; - err = attr_data_get_block(ni, vcn, 0, &lcn, &clen, - NULL); + err = attr_data_get_block(ni, vcn, 1, &lcn, &clen, NULL, + false); if (err) goto out; @@ -196,18 +196,18 @@ static int ntfs_zero_range(struct inode *inode, u64 vbo, u64 vbo_to) struct address_space *mapping = inode->i_mapping; u32 blocksize = 1 << inode->i_blkbits; pgoff_t idx = vbo >> PAGE_SHIFT; - u32 z_start = vbo & (PAGE_SIZE - 1); + u32 from = vbo & (PAGE_SIZE - 1); pgoff_t idx_end = (vbo_to + PAGE_SIZE - 1) >> PAGE_SHIFT; loff_t page_off; struct buffer_head *head, *bh; - u32 bh_next, bh_off, z_end; + u32 bh_next, bh_off, to; sector_t iblock; struct page *page; - for (; idx < idx_end; idx += 1, z_start = 0) { + for (; idx < idx_end; idx += 1, from = 0) { page_off = (loff_t)idx << PAGE_SHIFT; - z_end = (page_off + PAGE_SIZE) > vbo_to ? (vbo_to - page_off) - : PAGE_SIZE; + to = (page_off + PAGE_SIZE) > vbo_to ? (vbo_to - page_off) + : PAGE_SIZE; iblock = page_off >> inode->i_blkbits; page = find_or_create_page(mapping, idx, @@ -224,7 +224,7 @@ static int ntfs_zero_range(struct inode *inode, u64 vbo, u64 vbo_to) do { bh_next = bh_off + blocksize; - if (bh_next <= z_start || bh_off >= z_end) + if (bh_next <= from || bh_off >= to) continue; if (!buffer_mapped(bh)) { @@ -258,7 +258,7 @@ static int ntfs_zero_range(struct inode *inode, u64 vbo, u64 vbo_to) } while (bh_off = bh_next, iblock += 1, head != (bh = bh->b_this_page)); - zero_user_segment(page, z_start, z_end); + zero_user_segment(page, from, to); unlock_page(page); put_page(page); @@ -270,81 +270,6 @@ out: } /* - * ntfs_sparse_cluster - Helper function to zero a new allocated clusters. - * - * NOTE: 512 <= cluster size <= 2M - */ -void ntfs_sparse_cluster(struct inode *inode, struct page *page0, CLST vcn, - CLST len) -{ - struct address_space *mapping = inode->i_mapping; - struct ntfs_sb_info *sbi = inode->i_sb->s_fs_info; - u64 vbo = (u64)vcn << sbi->cluster_bits; - u64 bytes = (u64)len << sbi->cluster_bits; - u32 blocksize = 1 << inode->i_blkbits; - pgoff_t idx0 = page0 ? page0->index : -1; - loff_t vbo_clst = vbo & sbi->cluster_mask_inv; - loff_t end = ntfs_up_cluster(sbi, vbo + bytes); - pgoff_t idx = vbo_clst >> PAGE_SHIFT; - u32 from = vbo_clst & (PAGE_SIZE - 1); - pgoff_t idx_end = (end + PAGE_SIZE - 1) >> PAGE_SHIFT; - loff_t page_off; - u32 to; - bool partial; - struct page *page; - - for (; idx < idx_end; idx += 1, from = 0) { - page = idx == idx0 ? page0 : grab_cache_page(mapping, idx); - - if (!page) - continue; - - page_off = (loff_t)idx << PAGE_SHIFT; - to = (page_off + PAGE_SIZE) > end ? (end - page_off) - : PAGE_SIZE; - partial = false; - - if ((from || PAGE_SIZE != to) && - likely(!page_has_buffers(page))) { - create_empty_buffers(page, blocksize, 0); - } - - if (page_has_buffers(page)) { - struct buffer_head *head, *bh; - u32 bh_off = 0; - - bh = head = page_buffers(page); - do { - u32 bh_next = bh_off + blocksize; - - if (from <= bh_off && bh_next <= to) { - set_buffer_uptodate(bh); - mark_buffer_dirty(bh); - } else if (!buffer_uptodate(bh)) { - partial = true; - } - bh_off = bh_next; - } while (head != (bh = bh->b_this_page)); - } - - zero_user_segment(page, from, to); - - if (!partial) { - if (!PageUptodate(page)) - SetPageUptodate(page); - set_page_dirty(page); - } - - if (idx != idx0) { - unlock_page(page); - put_page(page); - } - cond_resched(); - } - mark_inode_dirty(inode); -} - -/* * ntfs_file_mmap - file_operations::mmap */ static int ntfs_file_mmap(struct file *file, struct vm_area_struct *vma) @@ -385,18 +310,17 @@ static int ntfs_file_mmap(struct file *file, struct vm_area_struct *vma) for (; vcn < end; vcn += len) { err = attr_data_get_block(ni, vcn, 1, &lcn, - &len, &new); + &len, &new, true); if (err) goto out; - - if (!new) - continue; - ntfs_sparse_cluster(inode, NULL, vcn, 1); } } if (ni->i_valid < to) { - inode_lock(inode); + if (!inode_trylock(inode)) { + err = -EAGAIN; + goto out; + } err = ntfs_extend_initialized_size(file, ni, ni->i_valid, to); inode_unlock(inode); @@ -433,6 +357,7 @@ static int ntfs_extend(struct inode *inode, loff_t pos, size_t count, } if (extend_init && !is_compressed(ni)) { + WARN_ON(ni->i_valid >= pos); err = ntfs_extend_initialized_size(file, ni, ni->i_valid, pos); if (err) goto out; @@ -532,7 +457,8 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len) struct ntfs_sb_info *sbi = sb->s_fs_info; struct ntfs_inode *ni = ntfs_i(inode); loff_t end = vbo + len; - loff_t vbo_down = round_down(vbo, PAGE_SIZE); + loff_t vbo_down = round_down(vbo, max_t(unsigned long, + sbi->cluster_size, PAGE_SIZE)); bool is_supported_holes = is_sparsed(ni) || is_compressed(ni); loff_t i_size, new_size; bool map_locked; @@ -585,11 +511,8 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len) u32 frame_size; loff_t mask, vbo_a, end_a, tmp; - err = filemap_write_and_wait_range(mapping, vbo, end - 1); - if (err) - goto out; - - err = filemap_write_and_wait_range(mapping, end, LLONG_MAX); + err = filemap_write_and_wait_range(mapping, vbo_down, + LLONG_MAX); if (err) goto out; @@ -692,39 +615,35 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len) goto out; if (is_supported_holes) { - CLST vcn_v = ni->i_valid >> sbi->cluster_bits; CLST vcn = vbo >> sbi->cluster_bits; CLST cend = bytes_to_cluster(sbi, end); + CLST cend_v = bytes_to_cluster(sbi, ni->i_valid); CLST lcn, clen; bool new; + if (cend_v > cend) + cend_v = cend; + /* - * Allocate but do not zero new clusters. (see below comments) - * This breaks security: One can read unused on-disk areas. + * Allocate and zero new clusters. * Zeroing these clusters may be too long. - * Maybe we should check here for root rights? + */ + for (; vcn < cend_v; vcn += clen) { + err = attr_data_get_block(ni, vcn, cend_v - vcn, + &lcn, &clen, &new, + true); + if (err) + goto out; + } + /* + * Allocate but not zero new clusters. */ for (; vcn < cend; vcn += clen) { err = attr_data_get_block(ni, vcn, cend - vcn, - &lcn, &clen, &new); + &lcn, &clen, &new, + false); if (err) goto out; - if (!new || vcn >= vcn_v) - continue; - - /* - * Unwritten area. - * NTFS is not able to store several unwritten areas. - * Activate 'ntfs_sparse_cluster' to zero new allocated clusters. - * - * Dangerous in case: - * 1G of sparsed clusters + 1 cluster of data => - * valid_size == 1G + 1 cluster - * fallocate(1G) will zero 1G and this can be very long - * xfstest 016/086 will fail without 'ntfs_sparse_cluster'. - */ - ntfs_sparse_cluster(inode, NULL, vcn, - min(vcn_v - vcn, clen)); } } @@ -945,8 +864,8 @@ static ssize_t ntfs_compress_write(struct kiocb *iocb, struct iov_iter *from) frame_vbo = valid & ~(frame_size - 1); off = valid & (frame_size - 1); - err = attr_data_get_block(ni, frame << NTFS_LZNT_CUNIT, 0, &lcn, - &clen, NULL); + err = attr_data_get_block(ni, frame << NTFS_LZNT_CUNIT, 1, &lcn, + &clen, NULL, false); if (err) goto out; diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c index d41ddc06f207..fb572688f919 100644 --- a/fs/ntfs3/frecord.c +++ b/fs/ntfs3/frecord.c @@ -2297,7 +2297,7 @@ int ni_decompress_file(struct ntfs_inode *ni) for (vcn = vbo >> sbi->cluster_bits; vcn < end; vcn += clen) { err = attr_data_get_block(ni, vcn, cend - vcn, &lcn, - &clen, &new); + &clen, &new, false); if (err) goto out; } diff --git a/fs/ntfs3/index.c b/fs/ntfs3/index.c index 2589f6d1215f..ee6de53d2ad1 100644 --- a/fs/ntfs3/index.c +++ b/fs/ntfs3/index.c @@ -617,7 +617,7 @@ static bool index_hdr_check(const struct INDEX_HDR *hdr, u32 bytes) u32 off = le32_to_cpu(hdr->de_off); if (!IS_ALIGNED(off, 8) || tot > bytes || end > tot || - off + sizeof(struct NTFS_DE) > end) { + size_add(off, sizeof(struct NTFS_DE)) > end) { /* incorrect index buffer. */ return false; } @@ -736,7 +736,7 @@ fill_table: if (end > total) return NULL; - if (off + sizeof(struct NTFS_DE) > end) + if (size_add(off, sizeof(struct NTFS_DE)) > end) return NULL; e = Add2Ptr(hdr, off); @@ -1442,8 +1442,8 @@ static int indx_create_allocate(struct ntfs_index *indx, struct ntfs_inode *ni, run_init(&run); - err = attr_allocate_clusters(sbi, &run, 0, 0, len, NULL, 0, &alen, 0, - NULL); + err = attr_allocate_clusters(sbi, &run, 0, 0, len, NULL, ALLOCATE_DEF, + &alen, 0, NULL, NULL); if (err) goto out; @@ -2166,6 +2166,10 @@ static int indx_get_entry_to_replace(struct ntfs_index *indx, e = hdr_first_de(&n->index->ihdr); fnd_push(fnd, n, e); + if (!e) { + err = -EINVAL; + goto out; + } if (!de_is_last(e)) { /* @@ -2187,6 +2191,10 @@ static int indx_get_entry_to_replace(struct ntfs_index *indx, n = fnd->nodes[level]; te = hdr_first_de(&n->index->ihdr); + if (!te) { + err = -EINVAL; + goto out; + } /* Copy the candidate entry into the replacement entry buffer. */ re = kmalloc(le16_to_cpu(te->size) + sizeof(u64), GFP_NOFS); if (!re) { diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c index 057aa3cec902..5baf6a2b3d48 100644 --- a/fs/ntfs3/inode.c +++ b/fs/ntfs3/inode.c @@ -592,7 +592,8 @@ static noinline int ntfs_get_block_vbo(struct inode *inode, u64 vbo, off = vbo & sbi->cluster_mask; new = false; - err = attr_data_get_block(ni, vcn, 1, &lcn, &len, create ? &new : NULL); + err = attr_data_get_block(ni, vcn, 1, &lcn, &len, create ? &new : NULL, + create && sbi->cluster_size > PAGE_SIZE); if (err) goto out; @@ -610,11 +611,8 @@ static noinline int ntfs_get_block_vbo(struct inode *inode, u64 vbo, WARN_ON(1); } - if (new) { + if (new) set_buffer_new(bh); - if ((len << cluster_bits) > block_size) - ntfs_sparse_cluster(inode, page, vcn, len); - } lbo = ((u64)lcn << cluster_bits) + off; @@ -1533,8 +1531,8 @@ struct inode *ntfs_create_inode(struct user_namespace *mnt_userns, cpu_to_le64(ntfs_up_cluster(sbi, nsize)); err = attr_allocate_clusters(sbi, &ni->file.run, 0, 0, - clst, NULL, 0, &alen, 0, - NULL); + clst, NULL, ALLOCATE_DEF, + &alen, 0, NULL, NULL); if (err) goto out5; diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h index 26dbe1b46fdd..f2f32e304b3d 100644 --- a/fs/ntfs3/ntfs_fs.h +++ b/fs/ntfs3/ntfs_fs.h @@ -42,9 +42,11 @@ enum utf16_endian; #define MINUS_ONE_T ((size_t)(-1)) /* Biggest MFT / smallest cluster */ #define MAXIMUM_BYTES_PER_MFT 4096 +#define MAXIMUM_SHIFT_BYTES_PER_MFT 12 #define NTFS_BLOCKS_PER_MFT_RECORD (MAXIMUM_BYTES_PER_MFT / 512) #define MAXIMUM_BYTES_PER_INDEX 4096 +#define MAXIMUM_SHIFT_BYTES_PER_INDEX 12 #define NTFS_BLOCKS_PER_INODE (MAXIMUM_BYTES_PER_INDEX / 512) /* NTFS specific error code when fixup failed. */ @@ -126,6 +128,7 @@ struct ntfs_buffers { enum ALLOCATE_OPT { ALLOCATE_DEF = 0, // Allocate all clusters. ALLOCATE_MFT = 1, // Allocate for MFT. + ALLOCATE_ZERO = 2, // Zeroout new allocated clusters }; enum bitmap_mutex_classes { @@ -416,7 +419,7 @@ enum REPARSE_SIGN { int attr_allocate_clusters(struct ntfs_sb_info *sbi, struct runs_tree *run, CLST vcn, CLST lcn, CLST len, CLST *pre_alloc, enum ALLOCATE_OPT opt, CLST *alen, const size_t fr, - CLST *new_lcn); + CLST *new_lcn, CLST *new_len); int attr_make_nonresident(struct ntfs_inode *ni, struct ATTRIB *attr, struct ATTR_LIST_ENTRY *le, struct mft_inode *mi, u64 new_size, struct runs_tree *run, @@ -426,7 +429,7 @@ int attr_set_size(struct ntfs_inode *ni, enum ATTR_TYPE type, u64 new_size, const u64 *new_valid, bool keep_prealloc, struct ATTRIB **ret); int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn, - CLST *len, bool *new); + CLST *len, bool *new, bool zero); int attr_data_read_resident(struct ntfs_inode *ni, struct page *page); int attr_data_write_resident(struct ntfs_inode *ni, struct page *page); int attr_load_runs_vcn(struct ntfs_inode *ni, enum ATTR_TYPE type, @@ -491,8 +494,6 @@ extern const struct file_operations ntfs_dir_operations; /* Globals from file.c */ int ntfs_getattr(struct user_namespace *mnt_userns, const struct path *path, struct kstat *stat, u32 request_mask, u32 flags); -void ntfs_sparse_cluster(struct inode *inode, struct page *page0, CLST vcn, - CLST len); int ntfs3_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, struct iattr *attr); int ntfs_file_open(struct inode *inode, struct file *file); diff --git a/fs/ntfs3/record.c b/fs/ntfs3/record.c index b2b98631a000..bfb1f4c2f271 100644 --- a/fs/ntfs3/record.c +++ b/fs/ntfs3/record.c @@ -325,6 +325,9 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr) } else { if (attr->nres.c_unit) return NULL; + + if (alloc_size > mi->sbi->volume.size) + return NULL; } return attr; diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c index eee54214f4a3..674a16c0c66b 100644 --- a/fs/ntfs3/super.c +++ b/fs/ntfs3/super.c @@ -680,7 +680,7 @@ static u32 true_sectors_per_clst(const struct NTFS_BOOT *boot) * ntfs_init_from_boot - Init internal info from on-disk boot sector. */ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size, - u64 dev_size) + u64 dev_size) { struct ntfs_sb_info *sbi = sb->s_fs_info; int err; @@ -705,12 +705,12 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size, /* 0x55AA is not mandaroty. Thanks Maxim Suhanov*/ /*if (0x55 != boot->boot_magic[0] || 0xAA != boot->boot_magic[1]) - * goto out; + * goto out; */ boot_sector_size = (u32)boot->bytes_per_sector[1] << 8; if (boot->bytes_per_sector[0] || boot_sector_size < SECTOR_SIZE || - !is_power_of_2(boot_sector_size)) { + !is_power_of_2(boot_sector_size)) { goto out; } @@ -733,15 +733,49 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size, /* Check MFT record size. */ if ((boot->record_size < 0 && - SECTOR_SIZE > (2U << (-boot->record_size))) || - (boot->record_size >= 0 && !is_power_of_2(boot->record_size))) { + SECTOR_SIZE > (2U << (-boot->record_size))) || + (boot->record_size >= 0 && !is_power_of_2(boot->record_size))) { + goto out; + } + + /* Calculate cluster size */ + sbi->cluster_size = boot_sector_size * sct_per_clst; + sbi->cluster_bits = blksize_bits(sbi->cluster_size); + + if (boot->record_size >= 0) { + record_size = (u32)boot->record_size << sbi->cluster_bits; + } else if (-boot->record_size <= MAXIMUM_SHIFT_BYTES_PER_MFT) { + record_size = 1u << (-boot->record_size); + } else { + ntfs_err(sb, "%s: invalid record size %d.", "NTFS", + boot->record_size); + goto out; + } + + sbi->record_size = record_size; + sbi->record_bits = blksize_bits(record_size); + sbi->attr_size_tr = (5 * record_size >> 4); // ~320 bytes + + if (record_size > MAXIMUM_BYTES_PER_MFT) { + ntfs_err(sb, "Unsupported bytes per MFT record %u.", + record_size); + goto out; + } + + if (boot->index_size >= 0) { + sbi->index_size = (u32)boot->index_size << sbi->cluster_bits; + } else if (-boot->index_size <= MAXIMUM_SHIFT_BYTES_PER_INDEX) { + sbi->index_size = 1u << (-boot->index_size); + } else { + ntfs_err(sb, "%s: invalid index size %d.", "NTFS", + boot->index_size); goto out; } /* Check index record size. */ if ((boot->index_size < 0 && - SECTOR_SIZE > (2U << (-boot->index_size))) || - (boot->index_size >= 0 && !is_power_of_2(boot->index_size))) { + SECTOR_SIZE > (2U << (-boot->index_size))) || + (boot->index_size >= 0 && !is_power_of_2(boot->index_size))) { goto out; } @@ -762,9 +796,6 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size, dev_size += sector_size - 1; } - sbi->cluster_size = boot_sector_size * sct_per_clst; - sbi->cluster_bits = blksize_bits(sbi->cluster_size); - sbi->mft.lbo = mlcn << sbi->cluster_bits; sbi->mft.lbo2 = mlcn2 << sbi->cluster_bits; @@ -785,9 +816,9 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size, sbi->cluster_mask = sbi->cluster_size - 1; sbi->cluster_mask_inv = ~(u64)sbi->cluster_mask; sbi->record_size = record_size = boot->record_size < 0 - ? 1 << (-boot->record_size) - : (u32)boot->record_size - << sbi->cluster_bits; + ? 1 << (-boot->record_size) + : (u32)boot->record_size + << sbi->cluster_bits; if (record_size > MAXIMUM_BYTES_PER_MFT || record_size < SECTOR_SIZE) goto out; @@ -801,8 +832,8 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size, ALIGN(sizeof(enum ATTR_TYPE), 8); sbi->index_size = boot->index_size < 0 - ? 1u << (-boot->index_size) - : (u32)boot->index_size << sbi->cluster_bits; + ? 1u << (-boot->index_size) + : (u32)boot->index_size << sbi->cluster_bits; sbi->volume.ser_num = le64_to_cpu(boot->serial_num); @@ -871,13 +902,6 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size, sb->s_maxbytes = 0xFFFFFFFFull << sbi->cluster_bits; #endif - /* - * Compute the MFT zone at two steps. - * It would be nice if we are able to allocate 1/8 of - * total clusters for MFT but not more then 512 MB. - */ - sbi->zone_max = min_t(CLST, 0x20000000 >> sbi->cluster_bits, clusters >> 3); - err = 0; out: diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index 51c93929a146..7f11ffacc915 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -1796,6 +1796,14 @@ static int __ocfs2_find_path(struct ocfs2_caching_info *ci, el = root_el; while (el->l_tree_depth) { + if (unlikely(le16_to_cpu(el->l_tree_depth) >= OCFS2_MAX_PATH_DEPTH)) { + ocfs2_error(ocfs2_metadata_cache_get_super(ci), + "Owner %llu has invalid tree depth %u in extent list\n", + (unsigned long long)ocfs2_metadata_cache_owner(ci), + le16_to_cpu(el->l_tree_depth)); + ret = -EROFS; + goto out; + } if (le16_to_cpu(el->l_next_free_rec) == 0) { ocfs2_error(ocfs2_metadata_cache_get_super(ci), "Owner %llu has empty extent list at depth %u\n", diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index 775766856a54..7f5fd16d3740 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -173,7 +173,7 @@ int ocfs2_recovery_init(struct ocfs2_super *osb) struct ocfs2_recovery_map *rm; mutex_init(&osb->recovery_lock); - osb->disable_recovery = 0; + osb->recovery_state = OCFS2_REC_ENABLED; osb->recovery_thread_task = NULL; init_waitqueue_head(&osb->recovery_event); @@ -192,31 +192,53 @@ int ocfs2_recovery_init(struct ocfs2_super *osb) return 0; } -/* we can't grab the goofy sem lock from inside wait_event, so we use - * memory barriers to make sure that we'll see the null task before - * being woken up */ static int ocfs2_recovery_thread_running(struct ocfs2_super *osb) { - mb(); return osb->recovery_thread_task != NULL; } -void ocfs2_recovery_exit(struct ocfs2_super *osb) +static void ocfs2_recovery_disable(struct ocfs2_super *osb, + enum ocfs2_recovery_state state) { - struct ocfs2_recovery_map *rm; - - /* disable any new recovery threads and wait for any currently - * running ones to exit. Do this before setting the vol_state. */ mutex_lock(&osb->recovery_lock); - osb->disable_recovery = 1; + /* + * If recovery thread is not running, we can directly transition to + * final state. + */ + if (!ocfs2_recovery_thread_running(osb)) { + osb->recovery_state = state + 1; + goto out_lock; + } + osb->recovery_state = state; + /* Wait for recovery thread to acknowledge state transition */ + wait_event_cmd(osb->recovery_event, + !ocfs2_recovery_thread_running(osb) || + osb->recovery_state >= state + 1, + mutex_unlock(&osb->recovery_lock), + mutex_lock(&osb->recovery_lock)); +out_lock: mutex_unlock(&osb->recovery_lock); - wait_event(osb->recovery_event, !ocfs2_recovery_thread_running(osb)); - /* At this point, we know that no more recovery threads can be - * launched, so wait for any recovery completion work to - * complete. */ + /* + * At this point we know that no more recovery work can be queued so + * wait for any recovery completion work to complete. + */ if (osb->ocfs2_wq) flush_workqueue(osb->ocfs2_wq); +} + +void ocfs2_recovery_disable_quota(struct ocfs2_super *osb) +{ + ocfs2_recovery_disable(osb, OCFS2_REC_QUOTA_WANT_DISABLE); +} + +void ocfs2_recovery_exit(struct ocfs2_super *osb) +{ + struct ocfs2_recovery_map *rm; + + /* disable any new recovery threads and wait for any currently + * running ones to exit. Do this before setting the vol_state. */ + ocfs2_recovery_disable(osb, OCFS2_REC_WANT_DISABLE); /* * Now that recovery is shut down, and the osb is about to be @@ -1439,6 +1461,18 @@ static int __ocfs2_recovery_thread(void *arg) } } restart: + if (quota_enabled) { + mutex_lock(&osb->recovery_lock); + /* Confirm that recovery thread will no longer recover quotas */ + if (osb->recovery_state == OCFS2_REC_QUOTA_WANT_DISABLE) { + osb->recovery_state = OCFS2_REC_QUOTA_DISABLED; + wake_up(&osb->recovery_event); + } + if (osb->recovery_state >= OCFS2_REC_QUOTA_DISABLED) + quota_enabled = 0; + mutex_unlock(&osb->recovery_lock); + } + status = ocfs2_super_lock(osb, 1); if (status < 0) { mlog_errno(status); @@ -1536,27 +1570,29 @@ bail: ocfs2_free_replay_slots(osb); osb->recovery_thread_task = NULL; - mb(); /* sync with ocfs2_recovery_thread_running */ + if (osb->recovery_state == OCFS2_REC_WANT_DISABLE) + osb->recovery_state = OCFS2_REC_DISABLED; wake_up(&osb->recovery_event); mutex_unlock(&osb->recovery_lock); - if (quota_enabled) - kfree(rm_quota); + kfree(rm_quota); return status; } void ocfs2_recovery_thread(struct ocfs2_super *osb, int node_num) { + int was_set = -1; + mutex_lock(&osb->recovery_lock); + if (osb->recovery_state < OCFS2_REC_WANT_DISABLE) + was_set = ocfs2_recovery_map_set(osb, node_num); trace_ocfs2_recovery_thread(node_num, osb->node_num, - osb->disable_recovery, osb->recovery_thread_task, - osb->disable_recovery ? - -1 : ocfs2_recovery_map_set(osb, node_num)); + osb->recovery_state, osb->recovery_thread_task, was_set); - if (osb->disable_recovery) + if (osb->recovery_state >= OCFS2_REC_WANT_DISABLE) goto out; if (osb->recovery_thread_task) diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h index 689c340c6363..5ebde794a653 100644 --- a/fs/ocfs2/journal.h +++ b/fs/ocfs2/journal.h @@ -148,6 +148,7 @@ void ocfs2_wait_for_recovery(struct ocfs2_super *osb); int ocfs2_recovery_init(struct ocfs2_super *osb); void ocfs2_recovery_exit(struct ocfs2_super *osb); +void ocfs2_recovery_disable_quota(struct ocfs2_super *osb); int ocfs2_compute_replay_slots(struct ocfs2_super *osb); void ocfs2_free_replay_slots(struct ocfs2_super *osb); diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index 740b64238312..22882c636bfb 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -284,6 +284,21 @@ enum ocfs2_mount_options #define OCFS2_OSB_ERROR_FS 0x0004 #define OCFS2_DEFAULT_ATIME_QUANTUM 60 +enum ocfs2_recovery_state { + OCFS2_REC_ENABLED = 0, + OCFS2_REC_QUOTA_WANT_DISABLE, + /* + * Must be OCFS2_REC_QUOTA_WANT_DISABLE + 1 for + * ocfs2_recovery_disable_quota() to work. + */ + OCFS2_REC_QUOTA_DISABLED, + OCFS2_REC_WANT_DISABLE, + /* + * Must be OCFS2_REC_WANT_DISABLE + 1 for ocfs2_recovery_exit() to work + */ + OCFS2_REC_DISABLED, +}; + struct ocfs2_journal; struct ocfs2_slot_info; struct ocfs2_recovery_map; @@ -346,7 +361,7 @@ struct ocfs2_super struct ocfs2_recovery_map *recovery_map; struct ocfs2_replay_map *replay_map; struct task_struct *recovery_thread_task; - int disable_recovery; + enum ocfs2_recovery_state recovery_state; wait_queue_head_t checkpoint_event; struct ocfs2_journal *journal; unsigned long osb_commit_interval; diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c index 4b4fa58cd32f..c7bda48b5fb2 100644 --- a/fs/ocfs2/quota_local.c +++ b/fs/ocfs2/quota_local.c @@ -453,8 +453,7 @@ out: /* Sync changes in local quota file into global quota file and * reinitialize local quota file. - * The function expects local quota file to be already locked and - * s_umount locked in shared mode. */ + * The function expects local quota file to be already locked. */ static int ocfs2_recover_local_quota_file(struct inode *lqinode, int type, struct ocfs2_quota_recovery *rec) @@ -585,7 +584,6 @@ int ocfs2_finish_quota_recovery(struct ocfs2_super *osb, { unsigned int ino[OCFS2_MAXQUOTAS] = { LOCAL_USER_QUOTA_SYSTEM_INODE, LOCAL_GROUP_QUOTA_SYSTEM_INODE }; - struct super_block *sb = osb->sb; struct ocfs2_local_disk_dqinfo *ldinfo; struct buffer_head *bh; handle_t *handle; @@ -597,7 +595,6 @@ int ocfs2_finish_quota_recovery(struct ocfs2_super *osb, printk(KERN_NOTICE "ocfs2: Finishing quota recovery on device (%s) for " "slot %u\n", osb->dev_str, slot_num); - down_read(&sb->s_umount); for (type = 0; type < OCFS2_MAXQUOTAS; type++) { if (list_empty(&(rec->r_list[type]))) continue; @@ -674,8 +671,7 @@ out_put: break; } out: - up_read(&sb->s_umount); - kfree(rec); + ocfs2_free_quota_recovery(rec); return status; } @@ -840,8 +836,7 @@ static int ocfs2_local_free_info(struct super_block *sb, int type) ocfs2_release_local_quota_bitmaps(&oinfo->dqi_chunk); /* - * s_umount held in exclusive mode protects us against racing with - * recovery thread... + * ocfs2_dismount_volume() has already aborted quota recovery... */ if (oinfo->dqi_rec) { ocfs2_free_quota_recovery(oinfo->dqi_rec); diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 8f7bb76d9cde..b30f9d71a35d 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -1869,6 +1869,9 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err) /* Orphan scan should be stopped as early as possible */ ocfs2_orphan_scan_stop(osb); + /* Stop quota recovery so that we can disable quotas */ + ocfs2_recovery_disable_quota(osb); + ocfs2_disable_quotas(osb); /* All dquots should be freed by now */ diff --git a/fs/omfs/file.c b/fs/omfs/file.c index fa7fe2393ff6..425ff6800c41 100644 --- a/fs/omfs/file.c +++ b/fs/omfs/file.c @@ -14,7 +14,7 @@ static u32 omfs_max_extents(struct omfs_sb_info *sbi, int offset) { return (sbi->s_sys_blocksize - offset - sizeof(struct omfs_extent)) / - sizeof(struct omfs_extent_entry) + 1; + sizeof(struct omfs_extent_entry); } void omfs_make_empty_table(struct buffer_head *bh, int offset) @@ -24,8 +24,8 @@ void omfs_make_empty_table(struct buffer_head *bh, int offset) oe->e_next = ~cpu_to_be64(0ULL); oe->e_extent_count = cpu_to_be32(1), oe->e_fill = cpu_to_be32(0x22), - oe->e_entry.e_cluster = ~cpu_to_be64(0ULL); - oe->e_entry.e_blocks = ~cpu_to_be64(0ULL); + oe->e_entry[0].e_cluster = ~cpu_to_be64(0ULL); + oe->e_entry[0].e_blocks = ~cpu_to_be64(0ULL); } int omfs_shrink_inode(struct inode *inode) @@ -68,7 +68,7 @@ int omfs_shrink_inode(struct inode *inode) last = next; next = be64_to_cpu(oe->e_next); - entry = &oe->e_entry; + entry = oe->e_entry; /* ignore last entry as it is the terminator */ for (; extent_count > 1; extent_count--) { @@ -117,7 +117,7 @@ static int omfs_grow_extent(struct inode *inode, struct omfs_extent *oe, u64 *ret_block) { struct omfs_extent_entry *terminator; - struct omfs_extent_entry *entry = &oe->e_entry; + struct omfs_extent_entry *entry = oe->e_entry; struct omfs_sb_info *sbi = OMFS_SB(inode->i_sb); u32 extent_count = be32_to_cpu(oe->e_extent_count); u64 new_block = 0; @@ -245,7 +245,7 @@ static int omfs_get_block(struct inode *inode, sector_t block, extent_count = be32_to_cpu(oe->e_extent_count); next = be64_to_cpu(oe->e_next); - entry = &oe->e_entry; + entry = oe->e_entry; if (extent_count > max_extents) goto out_brelse; diff --git a/fs/omfs/omfs_fs.h b/fs/omfs/omfs_fs.h index caecb3d5a344..1ff6b9e41297 100644 --- a/fs/omfs/omfs_fs.h +++ b/fs/omfs/omfs_fs.h @@ -77,7 +77,7 @@ struct omfs_extent { __be64 e_next; /* next extent table location */ __be32 e_extent_count; /* total # extents in this table */ __be32 e_fill; - struct omfs_extent_entry e_entry; /* start of extent entries */ + struct omfs_extent_entry e_entry[]; /* start of extent entries */ }; #endif diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c index b3bbb5a5787a..cc81ff6ac735 100644 --- a/fs/orangefs/inode.c +++ b/fs/orangefs/inode.c @@ -23,9 +23,9 @@ static int orangefs_writepage_locked(struct page *page, struct orangefs_write_range *wr = NULL; struct iov_iter iter; struct bio_vec bv; - size_t len, wlen; + size_t wlen; ssize_t ret; - loff_t off; + loff_t len, off; set_page_writeback(page); @@ -94,8 +94,7 @@ static int orangefs_writepages_work(struct orangefs_writepages *ow, struct orangefs_write_range *wrp, wr; struct iov_iter iter; ssize_t ret; - size_t len; - loff_t off; + loff_t len, off; int i; len = i_size_read(inode); diff --git a/fs/orangefs/orangefs-debugfs.c b/fs/orangefs/orangefs-debugfs.c index fa41db088488..b57140ebfad0 100644 --- a/fs/orangefs/orangefs-debugfs.c +++ b/fs/orangefs/orangefs-debugfs.c @@ -728,8 +728,8 @@ static void do_k_string(void *k_mask, int index) if (*mask & s_kmod_keyword_mask_map[index].mask_val) { if ((strlen(kernel_debug_string) + - strlen(s_kmod_keyword_mask_map[index].keyword)) - < ORANGEFS_MAX_DEBUG_STRING_LEN - 1) { + strlen(s_kmod_keyword_mask_map[index].keyword) + 1) + < ORANGEFS_MAX_DEBUG_STRING_LEN) { strcat(kernel_debug_string, s_kmod_keyword_mask_map[index].keyword); strcat(kernel_debug_string, ","); @@ -756,7 +756,7 @@ static void do_c_string(void *c_mask, int index) (mask->mask2 & cdm_array[index].mask2)) { if ((strlen(client_debug_string) + strlen(cdm_array[index].keyword) + 1) - < ORANGEFS_MAX_DEBUG_STRING_LEN - 2) { + < ORANGEFS_MAX_DEBUG_STRING_LEN) { strcat(client_debug_string, cdm_array[index].keyword); strcat(client_debug_string, ","); diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c index 83cd20f79c5c..6922d8d705cb 100644 --- a/fs/overlayfs/util.c +++ b/fs/overlayfs/util.c @@ -229,7 +229,9 @@ enum ovl_path_type ovl_path_realdata(struct dentry *dentry, struct path *path) struct dentry *ovl_dentry_upper(struct dentry *dentry) { - return ovl_upperdentry_dereference(OVL_I(d_inode(dentry))); + struct inode *inode = d_inode(dentry); + + return inode ? ovl_upperdentry_dereference(OVL_I(inode)) : NULL; } struct dentry *ovl_dentry_lower(struct dentry *dentry) diff --git a/fs/proc/base.c b/fs/proc/base.c index ecc45389ea79..fb169bdfd9a8 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -415,7 +415,7 @@ static const struct file_operations proc_pid_cmdline_ops = { #ifdef CONFIG_KALLSYMS /* * Provides a wchan file via kallsyms in a proper one-value-per-file format. - * Returns the resolved symbol. If that fails, simply return the address. + * Returns the resolved symbol to user space. */ static int proc_pid_wchan(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) @@ -2633,10 +2633,11 @@ static ssize_t timerslack_ns_write(struct file *file, const char __user *buf, } task_lock(p); - if (slack_ns == 0) - p->timer_slack_ns = p->default_timer_slack_ns; - else - p->timer_slack_ns = slack_ns; + if (task_is_realtime(p)) + slack_ns = 0; + else if (slack_ns == 0) + slack_ns = p->default_timer_slack_ns; + p->timer_slack_ns = slack_ns; task_unlock(p); out: diff --git a/fs/proc/generic.c b/fs/proc/generic.c index 587b91d9d998..c3a809e1d719 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -558,10 +558,18 @@ struct proc_dir_entry *proc_create_reg(const char *name, umode_t mode, return p; } -static inline void pde_set_flags(struct proc_dir_entry *pde) +static void pde_set_flags(struct proc_dir_entry *pde) { if (pde->proc_ops->proc_flags & PROC_ENTRY_PERMANENT) pde->flags |= PROC_ENTRY_PERMANENT; + if (pde->proc_ops->proc_read_iter) + pde->flags |= PROC_ENTRY_proc_read_iter; +#ifdef CONFIG_COMPAT + if (pde->proc_ops->proc_compat_ioctl) + pde->flags |= PROC_ENTRY_proc_compat_ioctl; +#endif + if (pde->proc_ops->proc_lseek) + pde->flags |= PROC_ENTRY_proc_lseek; } struct proc_dir_entry *proc_create_data(const char *name, umode_t mode, @@ -625,6 +633,7 @@ struct proc_dir_entry *proc_create_seq_private(const char *name, umode_t mode, p->proc_ops = &proc_seq_ops; p->seq_ops = ops; p->state_size = state_size; + pde_set_flags(p); return proc_register(parent, p); } EXPORT_SYMBOL(proc_create_seq_private); @@ -655,6 +664,7 @@ struct proc_dir_entry *proc_create_single_data(const char *name, umode_t mode, return NULL; p->proc_ops = &proc_single_ops; p->single_show = show; + pde_set_flags(p); return proc_register(parent, p); } EXPORT_SYMBOL(proc_create_single_data); diff --git a/fs/proc/inode.c b/fs/proc/inode.c index f495fdb39151..623aa0d97a6d 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -52,7 +52,7 @@ static void proc_evict_inode(struct inode *inode) head = ei->sysctl; if (head) { - RCU_INIT_POINTER(ei->sysctl, NULL); + WRITE_ONCE(ei->sysctl, NULL); proc_sys_evict_inode(inode, head); } } @@ -494,7 +494,7 @@ static int proc_reg_open(struct inode *inode, struct file *file) typeof_member(struct proc_ops, proc_release) release; struct pde_opener *pdeo; - if (!pde->proc_ops->proc_lseek) + if (!pde_has_proc_lseek(pde)) file->f_mode &= ~FMODE_LSEEK; if (pde_is_permanent(pde)) { @@ -679,13 +679,13 @@ struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de) if (S_ISREG(inode->i_mode)) { inode->i_op = de->proc_iops; - if (de->proc_ops->proc_read_iter) + if (pde_has_proc_read_iter(de)) inode->i_fop = &proc_iter_file_ops; else inode->i_fop = &proc_reg_file_ops; #ifdef CONFIG_COMPAT - if (de->proc_ops->proc_compat_ioctl) { - if (de->proc_ops->proc_read_iter) + if (pde_has_proc_compat_ioctl(de)) { + if (pde_has_proc_read_iter(de)) inode->i_fop = &proc_iter_file_ops_compat; else inode->i_fop = &proc_reg_file_ops_compat; diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 6b921826d85b..019137261a03 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -84,6 +84,25 @@ static inline void pde_make_permanent(struct proc_dir_entry *pde) pde->flags |= PROC_ENTRY_PERMANENT; } +static inline bool pde_has_proc_read_iter(const struct proc_dir_entry *pde) +{ + return pde->flags & PROC_ENTRY_proc_read_iter; +} + +static inline bool pde_has_proc_compat_ioctl(const struct proc_dir_entry *pde) +{ +#ifdef CONFIG_COMPAT + return pde->flags & PROC_ENTRY_proc_compat_ioctl; +#else + return false; +#endif +} + +static inline bool pde_has_proc_lseek(const struct proc_dir_entry *pde) +{ + return pde->flags & PROC_ENTRY_proc_lseek; +} + extern struct kmem_cache *proc_dir_entry_cache; void pde_free(struct proc_dir_entry *pde); diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index df77a7bcce49..6db1489abc68 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -924,17 +924,21 @@ static int proc_sys_compare(const struct dentry *dentry, struct ctl_table_header *head; struct inode *inode; - /* Although proc doesn't have negative dentries, rcu-walk means - * that inode here can be NULL */ - /* AV: can it, indeed? */ - inode = d_inode_rcu(dentry); - if (!inode) - return 1; if (name->len != len) return 1; if (memcmp(name->name, str, len)) return 1; - head = rcu_dereference(PROC_I(inode)->sysctl); + + // false positive is fine here - we'll recheck anyway + if (d_in_lookup(dentry)) + return 0; + + inode = d_inode_rcu(dentry); + // we just might have run into dentry in the middle of __dentry_kill() + if (!inode) + return 1; + + head = READ_ONCE(PROC_I(inode)->sysctl); return !head || !sysctl_is_seen(head); } diff --git a/fs/select.c b/fs/select.c index 3f730b8581f6..e66b6189845e 100644 --- a/fs/select.c +++ b/fs/select.c @@ -77,19 +77,16 @@ u64 select_estimate_accuracy(struct timespec64 *tv) { u64 ret; struct timespec64 now; + u64 slack = current->timer_slack_ns; - /* - * Realtime tasks get a slack of 0 for obvious reasons. - */ - - if (rt_task(current)) + if (slack == 0) return 0; ktime_get_ts64(&now); now = timespec64_sub(*tv, now); ret = __estimate_accuracy(&now); - if (ret < current->timer_slack_ns) - return current->timer_slack_ns; + if (ret < slack) + return slack; return ret; } diff --git a/fs/smb/client/asn1.c b/fs/smb/client/asn1.c index b5724ef9f182..214a44509e7b 100644 --- a/fs/smb/client/asn1.c +++ b/fs/smb/client/asn1.c @@ -52,6 +52,8 @@ int cifs_neg_token_init_mech_type(void *context, size_t hdrlen, server->sec_kerberos = true; else if (oid == OID_ntlmssp) server->sec_ntlmssp = true; + else if (oid == OID_IAKerb) + server->sec_iakerb = true; else { char buf[50]; diff --git a/fs/smb/client/cached_dir.h b/fs/smb/client/cached_dir.h index 2f4e764c9ca9..dad31f0b7ffb 100644 --- a/fs/smb/client/cached_dir.h +++ b/fs/smb/client/cached_dir.h @@ -21,10 +21,10 @@ struct cached_dirent { struct cached_dirents { bool is_valid:1; bool is_failed:1; - struct dir_context *ctx; /* - * Only used to make sure we only take entries - * from a single context. Never dereferenced. - */ + struct file *file; /* + * Used to associate the cache with a single + * open file instance. + */ struct mutex de_mutex; int pos; /* Expected ctx->pos */ struct list_head entries; diff --git a/fs/smb/client/cifs_dfs_ref.c b/fs/smb/client/cifs_dfs_ref.c index 020e71fe1454..876f9a43a99d 100644 --- a/fs/smb/client/cifs_dfs_ref.c +++ b/fs/smb/client/cifs_dfs_ref.c @@ -258,6 +258,31 @@ compose_mount_options_err: goto compose_mount_options_out; } +static int set_dest_addr(struct smb3_fs_context *ctx, const char *full_path) +{ + struct sockaddr *addr = (struct sockaddr *)&ctx->dstaddr; + char *str_addr = NULL; + int rc; + + rc = dns_resolve_server_name_to_ip(full_path, &str_addr, NULL); + if (rc < 0) + goto out; + + rc = cifs_convert_address(addr, str_addr, strlen(str_addr)); + if (!rc) { + cifs_dbg(FYI, "%s: failed to convert ip address\n", __func__); + rc = -EINVAL; + goto out; + } + + cifs_set_port(addr, ctx->port); + rc = 0; + +out: + kfree(str_addr); + return rc; +} + /* * Create a vfsmount that we can automount */ @@ -295,8 +320,7 @@ static struct vfsmount *cifs_dfs_do_automount(struct path *path) ctx = smb3_fc2context(fc); page = alloc_dentry_path(); - /* always use tree name prefix */ - full_path = build_path_from_dentry_optional_prefix(mntpt, page, true); + full_path = dfs_get_automount_devname(mntpt, page); if (IS_ERR(full_path)) { mnt = ERR_CAST(full_path); goto out; @@ -315,6 +339,12 @@ static struct vfsmount *cifs_dfs_do_automount(struct path *path) goto out; } + rc = set_dest_addr(ctx, full_path); + if (rc) { + mnt = ERR_PTR(rc); + goto out; + } + rc = smb3_parse_devname(full_path, ctx); if (!rc) mnt = fc_mount(fc); diff --git a/fs/smb/client/cifs_spnego.c b/fs/smb/client/cifs_spnego.c index 1e6819daaaa7..8b58f494235f 100644 --- a/fs/smb/client/cifs_spnego.c +++ b/fs/smb/client/cifs_spnego.c @@ -130,11 +130,13 @@ cifs_get_spnego_key(struct cifs_ses *sesInfo, dp = description + strlen(description); - /* for now, only sec=krb5 and sec=mskrb5 are valid */ + /* for now, only sec=krb5 and sec=mskrb5 and iakerb are valid */ if (server->sec_kerberos) sprintf(dp, ";sec=krb5"); else if (server->sec_mskerberos) sprintf(dp, ";sec=mskrb5"); + else if (server->sec_iakerb) + sprintf(dp, ";sec=iakerb"); else { cifs_dbg(VFS, "unknown or missing server auth type, use krb5\n"); sprintf(dp, ";sec=krb5"); diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index 71e519bf65e2..6df50ff6d918 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -148,6 +148,7 @@ enum securityEnum { NTLMv2, /* Legacy NTLM auth with NTLMv2 hash */ RawNTLMSSP, /* NTLMSSP without SPNEGO, NTLMv2 hash */ Kerberos, /* Kerberos via SPNEGO */ + IAKerb, /* Kerberos proxy */ }; struct session_key { @@ -674,8 +675,10 @@ struct TCP_Server_Info { char workstation_RFC1001_name[RFC1001_NAME_LEN_WITH_NULL]; __u32 sequence_number; /* for signing, protected by srv_mutex */ __u32 reconnect_instance; /* incremented on each reconnect */ + __le32 session_key_id; /* retrieved from negotiate response and send in session setup request */ struct session_key session_key; unsigned long lstrp; /* when we got last response from this server */ + unsigned long neg_start; /* when negotiate started (jiffies) */ struct cifs_secmech secmech; /* crypto sec mech functs, descriptors */ #define CIFS_NEGFLAVOR_UNENCAP 1 /* wct == 17, but no ext_sec */ #define CIFS_NEGFLAVOR_EXTENDED 2 /* wct == 17, ext_sec bit set */ @@ -685,6 +688,7 @@ struct TCP_Server_Info { bool sec_kerberosu2u; /* supports U2U Kerberos */ bool sec_kerberos; /* supports plain Kerberos */ bool sec_mskerberos; /* supports legacy MS Kerberos */ + bool sec_iakerb; /* supports pass-through auth for Kerberos (krb5 proxy) */ bool large_buf; /* is current buffer large? */ /* use SMBD connection instead of socket */ bool rdma; @@ -2049,6 +2053,8 @@ static inline char *get_security_type_str(enum securityEnum sectype) return "Kerberos"; case NTLMv2: return "NTLMv2"; + case IAKerb: + return "IAKerb"; default: return "Unknown"; } diff --git a/fs/smb/client/cifspdu.h b/fs/smb/client/cifspdu.h index 9cb457706334..a682c50d7ace 100644 --- a/fs/smb/client/cifspdu.h +++ b/fs/smb/client/cifspdu.h @@ -557,7 +557,7 @@ typedef union smb_com_session_setup_andx { __le16 MaxBufferSize; __le16 MaxMpxCount; __le16 VcNumber; - __u32 SessionKey; + __le32 SessionKey; __le16 SecurityBlobLength; __u32 Reserved; __le32 Capabilities; /* see below */ @@ -576,7 +576,7 @@ typedef union smb_com_session_setup_andx { __le16 MaxBufferSize; __le16 MaxMpxCount; __le16 VcNumber; - __u32 SessionKey; + __le32 SessionKey; __le16 CaseInsensitivePasswordLength; /* ASCII password len */ __le16 CaseSensitivePasswordLength; /* Unicode password length*/ __u32 Reserved; /* see below */ @@ -614,7 +614,7 @@ typedef union smb_com_session_setup_andx { __le16 MaxBufferSize; __le16 MaxMpxCount; __le16 VcNumber; - __u32 SessionKey; + __le32 SessionKey; __le16 PasswordLength; __u32 Reserved; /* encrypt key len and offset */ __le16 ByteCount; diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h index f37e4da0fe40..9a30425b75a9 100644 --- a/fs/smb/client/cifsproto.h +++ b/fs/smb/client/cifsproto.h @@ -30,6 +30,9 @@ extern void cifs_small_buf_release(void *); extern void free_rsp_buf(int, void *); extern int smb_send(struct TCP_Server_Info *, struct smb_hdr *, unsigned int /* length */); +extern int smb_send_kvec(struct TCP_Server_Info *server, + struct msghdr *msg, + size_t *sent); extern unsigned int _get_xid(void); extern void _free_xid(unsigned int); #define get_xid() \ @@ -57,8 +60,29 @@ extern void exit_cifs_idmap(void); extern int init_cifs_spnego(void); extern void exit_cifs_spnego(void); extern const char *build_path_from_dentry(struct dentry *, void *); +char *__build_path_from_dentry_optional_prefix(struct dentry *direntry, void *page, + const char *tree, int tree_len, + bool prefix); extern char *build_path_from_dentry_optional_prefix(struct dentry *direntry, void *page, bool prefix); + +#ifdef CONFIG_CIFS_DFS_UPCALL +static inline char *dfs_get_automount_devname(struct dentry *dentry, void *page) +{ + struct cifs_sb_info *cifs_sb = CIFS_SB(dentry->d_sb); + struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb); + struct TCP_Server_Info *server = tcon->ses->server; + + if (unlikely(!server->origin_fullpath)) + return ERR_PTR(-EREMOTE); + + return __build_path_from_dentry_optional_prefix(dentry, page, + server->origin_fullpath, + strlen(server->origin_fullpath), + true); +} +#endif + static inline void *alloc_dentry_path(void) { return __getname(); @@ -152,6 +176,8 @@ extern int cifs_get_writable_path(struct cifs_tcon *tcon, const char *name, extern struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *, bool); extern int cifs_get_readable_path(struct cifs_tcon *tcon, const char *name, struct cifsFileInfo **ret_file); +extern int cifs_get_hardlink_path(struct cifs_tcon *tcon, struct inode *inode, + struct file *file); extern unsigned int smbCalcSize(void *buf); extern int decode_negTokenInit(unsigned char *security_blob, int length, struct TCP_Server_Info *server); diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c index 6077fe1dcc9c..0c6ade196894 100644 --- a/fs/smb/client/cifssmb.c +++ b/fs/smb/client/cifssmb.c @@ -469,6 +469,7 @@ CIFSSMBNegotiate(const unsigned int xid, server->max_rw = le32_to_cpu(pSMBr->MaxRawSize); cifs_dbg(NOISY, "Max buf = %d\n", ses->server->maxBuf); server->capabilities = le32_to_cpu(pSMBr->Capabilities); + server->session_key_id = pSMBr->SessionKey; server->timeAdj = (int)(__s16)le16_to_cpu(pSMBr->ServerTimeZone); server->timeAdj *= 60; diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index db30c4b8a221..c3480e84f5c6 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -410,6 +410,13 @@ static int __cifs_reconnect(struct TCP_Server_Info *server, if (!cifs_tcp_ses_needs_reconnect(server, 1)) return 0; + /* + * if smb session has been marked for reconnect, also reconnect all + * connections. This way, the other connections do not end up bad. + */ + if (mark_smb_session) + cifs_signal_cifsd_for_reconnect(server, mark_smb_session); + cifs_mark_tcp_ses_conns_for_reconnect(server, mark_smb_session); cifs_abort_connection(server); @@ -682,12 +689,12 @@ server_unresponsive(struct TCP_Server_Info *server) /* * If we're in the process of mounting a share or reconnecting a session * and the server abruptly shut down (e.g. socket wasn't closed, packet - * had been ACK'ed but no SMB response), don't wait longer than 20s to - * negotiate protocol. + * had been ACK'ed but no SMB response), don't wait longer than 20s from + * when negotiate actually started. */ spin_lock(&server->srv_lock); if (server->tcpStatus == CifsInNegotiate && - time_after(jiffies, server->lstrp + 20 * HZ)) { + time_after(jiffies, server->neg_start + 20 * HZ)) { spin_unlock(&server->srv_lock); cifs_reconnect(server, false); return true; @@ -1881,9 +1888,8 @@ out_err: /* this function must be called with ses_lock and chan_lock held */ static int match_session(struct cifs_ses *ses, struct smb3_fs_context *ctx) { - if (ctx->sectype != Unspecified && - ctx->sectype != ses->sectype) - return 0; + struct TCP_Server_Info *server = ses->server; + enum securityEnum ctx_sec, ses_sec; /* * If an existing session is limited to less channels than @@ -1892,11 +1898,20 @@ static int match_session(struct cifs_ses *ses, struct smb3_fs_context *ctx) if (ses->chan_max < ctx->max_channels) return 0; - switch (ses->sectype) { + ctx_sec = server->ops->select_sectype(server, ctx->sectype); + ses_sec = server->ops->select_sectype(server, ses->sectype); + + if (ctx_sec != ses_sec) + return 0; + + switch (ctx_sec) { + case IAKerb: case Kerberos: if (!uid_eq(ctx->cred_uid, ses->cred_uid)) return 0; break; + case NTLMv2: + case RawNTLMSSP: default: /* NULL username means anonymous session */ if (ses->user_name == NULL) { @@ -2409,6 +2424,8 @@ static int match_tcon(struct cifs_tcon *tcon, struct smb3_fs_context *ctx) return 0; if (tcon->nodelete != ctx->nodelete) return 0; + if (tcon->posix_extensions != ctx->linux_ext) + return 0; return 1; } @@ -2956,8 +2973,10 @@ ip_rfc1001_connect(struct TCP_Server_Info *server) * sessinit is sent but no second negprot */ struct rfc1002_session_packet req = {}; - struct smb_hdr *smb_buf = (struct smb_hdr *)&req; + struct msghdr msg = {}; + struct kvec iov = {}; unsigned int len; + size_t sent; req.trailer.session_req.called_len = sizeof(req.trailer.session_req.called_name); @@ -2986,10 +3005,18 @@ ip_rfc1001_connect(struct TCP_Server_Info *server) * As per rfc1002, @len must be the number of bytes that follows the * length field of a rfc1002 session request payload. */ - len = sizeof(req) - offsetof(struct rfc1002_session_packet, trailer.session_req); + len = sizeof(req.trailer.session_req); + req.type = RFC1002_SESSION_REQUEST; + req.flags = 0; + req.length = cpu_to_be16(len); + len += offsetof(typeof(req), trailer.session_req); + iov.iov_base = &req; + iov.iov_len = len; + iov_iter_kvec(&msg.msg_iter, ITER_SOURCE, &iov, 1, len); + rc = smb_send_kvec(server, &msg, &sent); + if (rc < 0 || len != sent) + return (rc == -EINTR || rc == -EAGAIN) ? rc : -ECONNABORTED; - smb_buf->smb_buf_length = cpu_to_be32((RFC1002_SESSION_REQUEST << 24) | len); - rc = smb_send(server, smb_buf, len); /* * RFC1001 layer in at least one server requires very short break before * negprot presumably because not expecting negprot to follow so fast. @@ -2998,7 +3025,7 @@ ip_rfc1001_connect(struct TCP_Server_Info *server) */ usleep_range(1000, 2000); - return rc; + return 0; } static int @@ -4168,11 +4195,13 @@ int cifs_negotiate_protocol(const unsigned int xid, struct cifs_ses *ses, struct TCP_Server_Info *server) { + bool in_retry = false; int rc = 0; if (!server->ops->need_neg || !server->ops->negotiate) return -ENOSYS; +retry: /* only send once per connect */ spin_lock(&server->srv_lock); if (server->tcpStatus != CifsGood && @@ -4188,10 +4217,20 @@ cifs_negotiate_protocol(const unsigned int xid, struct cifs_ses *ses, return 0; } + server->lstrp = jiffies; server->tcpStatus = CifsInNegotiate; + server->neg_start = jiffies; spin_unlock(&server->srv_lock); rc = server->ops->negotiate(xid, ses, server); + if (rc == -EAGAIN) { + /* Allow one retry attempt */ + if (!in_retry) { + in_retry = true; + goto retry; + } + rc = -EHOSTDOWN; + } if (rc == 0) { spin_lock(&server->srv_lock); if (server->tcpStatus == CifsInNegotiate) diff --git a/fs/smb/client/dir.c b/fs/smb/client/dir.c index 863c7bc3db86..477302157ab3 100644 --- a/fs/smb/client/dir.c +++ b/fs/smb/client/dir.c @@ -78,14 +78,13 @@ build_path_from_dentry(struct dentry *direntry, void *page) prefix); } -char * -build_path_from_dentry_optional_prefix(struct dentry *direntry, void *page, - bool prefix) +char *__build_path_from_dentry_optional_prefix(struct dentry *direntry, void *page, + const char *tree, int tree_len, + bool prefix) { int dfsplen; int pplen = 0; struct cifs_sb_info *cifs_sb = CIFS_SB(direntry->d_sb); - struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb); char dirsep = CIFS_DIR_SEP(cifs_sb); char *s; @@ -93,7 +92,7 @@ build_path_from_dentry_optional_prefix(struct dentry *direntry, void *page, return ERR_PTR(-ENOMEM); if (prefix) - dfsplen = strnlen(tcon->tree_name, MAX_TREE_SIZE + 1); + dfsplen = strnlen(tree, tree_len + 1); else dfsplen = 0; @@ -123,7 +122,7 @@ build_path_from_dentry_optional_prefix(struct dentry *direntry, void *page, } if (dfsplen) { s -= dfsplen; - memcpy(s, tcon->tree_name, dfsplen); + memcpy(s, tree, dfsplen); if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) { int i; for (i = 0; i < dfsplen; i++) { @@ -135,6 +134,16 @@ build_path_from_dentry_optional_prefix(struct dentry *direntry, void *page, return s; } +char *build_path_from_dentry_optional_prefix(struct dentry *direntry, void *page, + bool prefix) +{ + struct cifs_sb_info *cifs_sb = CIFS_SB(direntry->d_sb); + struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb); + + return __build_path_from_dentry_optional_prefix(direntry, page, tcon->tree_name, + MAX_TREE_SIZE, prefix); +} + /* * Don't allow path components longer than the server max. * Don't allow the separator character in a path component. diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index d23dfc83de50..3551054ef097 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -687,6 +687,11 @@ int cifs_open(struct inode *inode, struct file *file) } else { _cifsFileInfo_put(cfile, true, false); } + } else { + /* hard link on the defeered close file */ + rc = cifs_get_hardlink_path(tcon, inode, file); + if (rc) + cifs_close_deferred_file(CIFS_I(inode)); } if (server->oplocks) @@ -1735,6 +1740,29 @@ cifs_move_llist(struct list_head *source, struct list_head *dest) list_move(li, dest); } +int +cifs_get_hardlink_path(struct cifs_tcon *tcon, struct inode *inode, + struct file *file) +{ + struct cifsFileInfo *open_file = NULL; + struct cifsInodeInfo *cinode = CIFS_I(inode); + int rc = 0; + + spin_lock(&tcon->open_file_lock); + spin_lock(&cinode->open_file_lock); + + list_for_each_entry(open_file, &cinode->openFileList, flist) { + if (file->f_flags == open_file->f_flags) { + rc = -EINVAL; + break; + } + } + + spin_unlock(&cinode->open_file_lock); + spin_unlock(&tcon->open_file_lock); + return rc; +} + void cifs_free_llist(struct list_head *llist) { @@ -5161,7 +5189,8 @@ void cifs_oplock_break(struct work_struct *work) struct cifsFileInfo *cfile = container_of(work, struct cifsFileInfo, oplock_break); struct inode *inode = d_inode(cfile->dentry); - struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); + struct super_block *sb = inode->i_sb; + struct cifs_sb_info *cifs_sb = CIFS_SB(sb); struct cifsInodeInfo *cinode = CIFS_I(inode); struct cifs_tcon *tcon; struct TCP_Server_Info *server; @@ -5171,6 +5200,12 @@ void cifs_oplock_break(struct work_struct *work) __u64 persistent_fid, volatile_fid; __u16 net_fid; + /* + * Hold a reference to the superblock to prevent it and its inodes from + * being freed while we are accessing cinode. Otherwise, _cifsFileInfo_put() + * may release the last reference to the sb and trigger inode eviction. + */ + cifs_sb_active(sb); wait_on_bit(&cinode->flags, CIFS_INODE_PENDING_WRITERS, TASK_UNINTERRUPTIBLE); @@ -5243,6 +5278,7 @@ oplock_break_ack: cifs_put_tlink(tlink); out: cifs_done_oplock_break(cinode); + cifs_sb_deactive(sb); } /* diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c index ca39d01077cd..e6d2e4162b08 100644 --- a/fs/smb/client/fs_context.c +++ b/fs/smb/client/fs_context.c @@ -1078,21 +1078,21 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, ctx->got_wsize = true; break; case Opt_acregmax: - ctx->acregmax = HZ * result.uint_32; - if (ctx->acregmax > CIFS_MAX_ACTIMEO) { + if (result.uint_32 > CIFS_MAX_ACTIMEO / HZ) { cifs_errorf(fc, "acregmax too large\n"); goto cifs_parse_mount_err; } + ctx->acregmax = HZ * result.uint_32; break; case Opt_acdirmax: - ctx->acdirmax = HZ * result.uint_32; - if (ctx->acdirmax > CIFS_MAX_ACTIMEO) { + if (result.uint_32 > CIFS_MAX_ACTIMEO / HZ) { cifs_errorf(fc, "acdirmax too large\n"); goto cifs_parse_mount_err; } + ctx->acdirmax = HZ * result.uint_32; break; case Opt_actimeo: - if (HZ * result.uint_32 > CIFS_MAX_ACTIMEO) { + if (result.uint_32 > CIFS_MAX_ACTIMEO / HZ) { cifs_errorf(fc, "timeout too large\n"); goto cifs_parse_mount_err; } @@ -1104,13 +1104,18 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, ctx->acdirmax = ctx->acregmax = HZ * result.uint_32; break; case Opt_closetimeo: - ctx->closetimeo = HZ * result.uint_32; - if (ctx->closetimeo > SMB3_MAX_DCLOSETIMEO) { + if (result.uint_32 > SMB3_MAX_DCLOSETIMEO / HZ) { cifs_errorf(fc, "closetimeo too large\n"); goto cifs_parse_mount_err; } + ctx->closetimeo = HZ * result.uint_32; break; case Opt_echo_interval: + if (result.uint_32 < SMB_ECHO_INTERVAL_MIN || + result.uint_32 > SMB_ECHO_INTERVAL_MAX) { + cifs_errorf(fc, "echo interval is out of bounds\n"); + goto cifs_parse_mount_err; + } ctx->echo_interval = result.uint_32; break; case Opt_snapshot: diff --git a/fs/smb/client/ioctl.c b/fs/smb/client/ioctl.c index ae9905e2b9d4..7402070b7a06 100644 --- a/fs/smb/client/ioctl.c +++ b/fs/smb/client/ioctl.c @@ -246,7 +246,9 @@ static int cifs_dump_full_key(struct cifs_tcon *tcon, struct smb3_full_key_debug spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(server_it, &cifs_tcp_ses_list, tcp_ses_list) { list_for_each_entry(ses_it, &server_it->smb_ses_list, smb_ses_list) { - if (ses_it->Suid == out.session_id) { + spin_lock(&ses_it->ses_lock); + if (ses_it->ses_status != SES_EXITING && + ses_it->Suid == out.session_id) { ses = ses_it; /* * since we are using the session outside the crit @@ -254,9 +256,11 @@ static int cifs_dump_full_key(struct cifs_tcon *tcon, struct smb3_full_key_debug * so increment its refcount */ ses->ses_count++; + spin_unlock(&ses_it->ses_lock); found = true; goto search_end; } + spin_unlock(&ses_it->ses_lock); } } search_end: diff --git a/fs/smb/client/link.c b/fs/smb/client/link.c index c0f101fc1e5d..d71feb3fdbd2 100644 --- a/fs/smb/client/link.c +++ b/fs/smb/client/link.c @@ -269,7 +269,7 @@ cifs_query_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, struct cifs_open_parms oparms; struct cifs_io_parms io_parms = {0}; int buf_type = CIFS_NO_BUFFER; - FILE_ALL_INFO file_info; + struct cifs_open_info_data query_data; oparms = (struct cifs_open_parms) { .tcon = tcon, @@ -281,11 +281,11 @@ cifs_query_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, .fid = &fid, }; - rc = CIFS_open(xid, &oparms, &oplock, &file_info); + rc = tcon->ses->server->ops->open(xid, &oparms, &oplock, &query_data); if (rc) return rc; - if (file_info.EndOfFile != cpu_to_le64(CIFS_MF_SYMLINK_FILE_SIZE)) { + if (query_data.fi.EndOfFile != cpu_to_le64(CIFS_MF_SYMLINK_FILE_SIZE)) { rc = -ENOENT; /* it's not a symlink */ goto out; @@ -324,7 +324,7 @@ cifs_create_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, .fid = &fid, }; - rc = CIFS_open(xid, &oparms, &oplock, NULL); + rc = tcon->ses->server->ops->open(xid, &oparms, &oplock, NULL); if (rc) return rc; diff --git a/fs/smb/client/misc.c b/fs/smb/client/misc.c index 3826f7176608..99a0a1fe6618 100644 --- a/fs/smb/client/misc.c +++ b/fs/smb/client/misc.c @@ -307,6 +307,14 @@ check_smb_hdr(struct smb_hdr *smb) if (smb->Command == SMB_COM_LOCKING_ANDX) return 0; + /* + * Windows NT server returns error resposne (e.g. STATUS_DELETE_PENDING + * or STATUS_OBJECT_NAME_NOT_FOUND or ERRDOS/ERRbadfile or any other) + * for some TRANS2 requests without the RESPONSE flag set in header. + */ + if (smb->Command == SMB_COM_TRANSACTION2 && smb->Status.CifsError != 0) + return 0; + cifs_dbg(VFS, "Server sent request, not response. mid=%u\n", get_mid(smb)); return 1; diff --git a/fs/smb/client/readdir.c b/fs/smb/client/readdir.c index 9a1f1913fb59..20955d595e6a 100644 --- a/fs/smb/client/readdir.c +++ b/fs/smb/client/readdir.c @@ -765,7 +765,10 @@ find_cifs_entry(const unsigned int xid, struct cifs_tcon *tcon, loff_t pos, else cifs_buf_release(cfile->srch_inf. ntwrk_buf_start); + /* Reset all pointers to the network buffer to prevent stale references */ cfile->srch_inf.ntwrk_buf_start = NULL; + cfile->srch_inf.srch_entries_start = NULL; + cfile->srch_inf.last_entry = NULL; } rc = initiate_cifs_search(xid, file, full_path); if (rc) { @@ -788,11 +791,11 @@ find_cifs_entry(const unsigned int xid, struct cifs_tcon *tcon, loff_t pos, rc = server->ops->query_dir_next(xid, tcon, &cfile->fid, search_flags, &cfile->srch_inf); + if (rc) + return -ENOENT; /* FindFirst/Next set last_entry to NULL on malformed reply */ if (cfile->srch_inf.last_entry) cifs_save_resume_key(cfile->srch_inf.last_entry, cfile); - if (rc) - return -ENOENT; } if (index_to_find < cfile->srch_inf.index_of_last_entry) { /* we found the buffer that contains the entry */ @@ -879,9 +882,9 @@ static bool emit_cached_dirents(struct cached_dirents *cde, } static void update_cached_dirents_count(struct cached_dirents *cde, - struct dir_context *ctx) + struct file *file) { - if (cde->ctx != ctx) + if (cde->file != file) return; if (cde->is_valid || cde->is_failed) return; @@ -890,9 +893,9 @@ static void update_cached_dirents_count(struct cached_dirents *cde, } static void finished_cached_dirents_count(struct cached_dirents *cde, - struct dir_context *ctx) + struct dir_context *ctx, struct file *file) { - if (cde->ctx != ctx) + if (cde->file != file) return; if (cde->is_valid || cde->is_failed) return; @@ -905,11 +908,12 @@ static void finished_cached_dirents_count(struct cached_dirents *cde, static void add_cached_dirent(struct cached_dirents *cde, struct dir_context *ctx, const char *name, int namelen, - struct cifs_fattr *fattr) + struct cifs_fattr *fattr, + struct file *file) { struct cached_dirent *de; - if (cde->ctx != ctx) + if (cde->file != file) return; if (cde->is_valid || cde->is_failed) return; @@ -939,7 +943,8 @@ static void add_cached_dirent(struct cached_dirents *cde, static bool cifs_dir_emit(struct dir_context *ctx, const char *name, int namelen, struct cifs_fattr *fattr, - struct cached_fid *cfid) + struct cached_fid *cfid, + struct file *file) { bool rc; ino_t ino = cifs_uniqueid_to_ino_t(fattr->cf_uniqueid); @@ -951,7 +956,7 @@ static bool cifs_dir_emit(struct dir_context *ctx, if (cfid) { mutex_lock(&cfid->dirents.de_mutex); add_cached_dirent(&cfid->dirents, ctx, name, namelen, - fattr); + fattr, file); mutex_unlock(&cfid->dirents.de_mutex); } @@ -1051,7 +1056,7 @@ static int cifs_filldir(char *find_entry, struct file *file, cifs_prime_dcache(file_dentry(file), &name, &fattr); return !cifs_dir_emit(ctx, name.name, name.len, - &fattr, cfid); + &fattr, cfid, file); } @@ -1102,8 +1107,8 @@ int cifs_readdir(struct file *file, struct dir_context *ctx) * we need to initialize scanning and storing the * directory content. */ - if (ctx->pos == 0 && cfid->dirents.ctx == NULL) { - cfid->dirents.ctx = ctx; + if (ctx->pos == 0 && cfid->dirents.file == NULL) { + cfid->dirents.file = file; cfid->dirents.pos = 2; } /* @@ -1171,7 +1176,7 @@ int cifs_readdir(struct file *file, struct dir_context *ctx) } else { if (cfid) { mutex_lock(&cfid->dirents.de_mutex); - finished_cached_dirents_count(&cfid->dirents, ctx); + finished_cached_dirents_count(&cfid->dirents, ctx, file); mutex_unlock(&cfid->dirents.de_mutex); } cifs_dbg(FYI, "Could not find entry\n"); @@ -1212,7 +1217,7 @@ int cifs_readdir(struct file *file, struct dir_context *ctx) ctx->pos++; if (cfid) { mutex_lock(&cfid->dirents.de_mutex); - update_cached_dirents_count(&cfid->dirents, ctx); + update_cached_dirents_count(&cfid->dirents, file); mutex_unlock(&cfid->dirents.de_mutex); } diff --git a/fs/smb/client/sess.c b/fs/smb/client/sess.c index b8e14bcd2c68..883d1cb1fc8b 100644 --- a/fs/smb/client/sess.c +++ b/fs/smb/client/sess.c @@ -605,6 +605,7 @@ static __u32 cifs_ssetup_hdr(struct cifs_ses *ses, USHRT_MAX)); pSMB->req.MaxMpxCount = cpu_to_le16(server->maxReq); pSMB->req.VcNumber = cpu_to_le16(1); + pSMB->req.SessionKey = server->session_key_id; /* Now no need to set SMBFLG_CASELESS or obsolete CANONICAL PATH */ @@ -1209,12 +1210,13 @@ cifs_select_sectype(struct TCP_Server_Info *server, enum securityEnum requested) switch (requested) { case Kerberos: case RawNTLMSSP: + case IAKerb: return requested; case Unspecified: if (server->sec_ntlmssp && (global_secflags & CIFSSEC_MAY_NTLMSSP)) return RawNTLMSSP; - if ((server->sec_kerberos || server->sec_mskerberos) && + if ((server->sec_kerberos || server->sec_mskerberos || server->sec_iakerb) && (global_secflags & CIFSSEC_MAY_KRB5)) return Kerberos; fallthrough; diff --git a/fs/smb/client/smb1ops.c b/fs/smb/client/smb1ops.c index 225cc7e0304c..1489b9d21b60 100644 --- a/fs/smb/client/smb1ops.c +++ b/fs/smb/client/smb1ops.c @@ -426,13 +426,6 @@ cifs_negotiate(const unsigned int xid, { int rc; rc = CIFSSMBNegotiate(xid, ses, server); - if (rc == -EAGAIN) { - /* retry only once on 1st time connection */ - set_credits(server, 1); - rc = CIFSSMBNegotiate(xid, ses, server); - if (rc == -EAGAIN) - rc = -EHOSTDOWN; - } return rc; } diff --git a/fs/smb/client/smb2file.c b/fs/smb/client/smb2file.c index a7475bc05cac..afdc78e92ee9 100644 --- a/fs/smb/client/smb2file.c +++ b/fs/smb/client/smb2file.c @@ -108,16 +108,25 @@ int smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, __u32 int err_buftype = CIFS_NO_BUFFER; struct cifs_fid *fid = oparms->fid; struct network_resiliency_req nr_ioctl_req; + bool retry_without_read_attributes = false; smb2_path = cifs_convert_path_to_utf16(oparms->path, oparms->cifs_sb); if (smb2_path == NULL) return -ENOMEM; - oparms->desired_access |= FILE_READ_ATTRIBUTES; + if (!(oparms->desired_access & FILE_READ_ATTRIBUTES)) { + oparms->desired_access |= FILE_READ_ATTRIBUTES; + retry_without_read_attributes = true; + } smb2_oplock = SMB2_OPLOCK_LEVEL_BATCH; rc = SMB2_open(xid, oparms, smb2_path, &smb2_oplock, smb2_data, NULL, &err_iov, &err_buftype); + if (rc == -EACCES && retry_without_read_attributes) { + oparms->desired_access &= ~FILE_READ_ATTRIBUTES; + rc = SMB2_open(xid, oparms, smb2_path, &smb2_oplock, smb2_data, NULL, &err_iov, + &err_buftype); + } if (rc && data) { struct smb2_hdr *hdr = err_iov.iov_base; diff --git a/fs/smb/client/smb2misc.c b/fs/smb/client/smb2misc.c index 8c149cb531d3..01352d7c10f1 100644 --- a/fs/smb/client/smb2misc.c +++ b/fs/smb/client/smb2misc.c @@ -814,11 +814,12 @@ smb2_handle_cancelled_close(struct cifs_tcon *tcon, __u64 persistent_fid, WARN_ONCE(tcon->tc_count < 0, "tcon refcount is negative"); spin_unlock(&cifs_tcp_ses_lock); - if (tcon->ses) + if (tcon->ses) { server = tcon->ses->server; - - cifs_server_dbg(FYI, "tid=0x%x: tcon is closing, skipping async close retry of fid %llu %llu\n", - tcon->tid, persistent_fid, volatile_fid); + cifs_server_dbg(FYI, + "tid=0x%x: tcon is closing, skipping async close retry of fid %llu %llu\n", + tcon->tid, persistent_fid, volatile_fid); + } return 0; } diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index a62f3e5a7689..7d720cf9fe72 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -422,9 +422,6 @@ smb2_negotiate(const unsigned int xid, server->CurrentMid = 0; spin_unlock(&server->mid_lock); rc = SMB2_negotiate(xid, ses, server); - /* BB we probably don't need to retry with modern servers */ - if (rc == -EAGAIN) - rc = -EHOSTDOWN; return rc; } @@ -4500,6 +4497,7 @@ crypt_message(struct TCP_Server_Info *server, int num_rqst, u8 key[SMB3_ENC_DEC_KEY_SIZE]; struct aead_request *req; u8 *iv; + DECLARE_CRYPTO_WAIT(wait); unsigned int crypt_len = le32_to_cpu(tr_hdr->OriginalMessageSize); void *creq; @@ -4548,7 +4546,11 @@ crypt_message(struct TCP_Server_Info *server, int num_rqst, aead_request_set_crypt(req, sg, sg, crypt_len, iv); aead_request_set_ad(req, assoc_data_len); - rc = enc ? crypto_aead_encrypt(req) : crypto_aead_decrypt(req); + aead_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG, + crypto_req_done, &wait); + + rc = crypto_wait_req(enc ? crypto_aead_encrypt(req) + : crypto_aead_decrypt(req), &wait); if (!rc && enc) memcpy(&tr_hdr->Signature, sign, SMB2_SIGNATURE_SIZE); diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 217d381eb9fe..c28e39c67c4f 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -1270,7 +1270,7 @@ smb2_select_sectype(struct TCP_Server_Info *server, enum securityEnum requested) if (server->sec_ntlmssp && (global_secflags & CIFSSEC_MAY_NTLMSSP)) return RawNTLMSSP; - if ((server->sec_kerberos || server->sec_mskerberos) && + if ((server->sec_kerberos || server->sec_mskerberos || server->sec_iakerb) && (global_secflags & CIFSSEC_MAY_KRB5)) return Kerberos; fallthrough; @@ -1999,7 +1999,7 @@ tcon_exit: tcon_error_exit: if (rsp && rsp->hdr.Status == STATUS_BAD_NETWORK_NAME) - cifs_tcon_dbg(VFS, "BAD_NETWORK_NAME: %s\n", tree); + cifs_dbg(VFS | ONCE, "BAD_NETWORK_NAME: %s\n", tree); goto tcon_exit; } @@ -2826,7 +2826,7 @@ int smb311_posix_mkdir(const unsigned int xid, struct inode *inode, /* Eventually save off posix specific response info and timestaps */ err_free_rsp_buf: - free_rsp_buf(resp_buftype, rsp); + free_rsp_buf(resp_buftype, rsp_iov.iov_base); kfree(pc_buf); err_free_req: cifs_small_buf_release(req); diff --git a/fs/smb/client/smbdirect.c b/fs/smb/client/smbdirect.c index cf923f211c51..d47eae133a20 100644 --- a/fs/smb/client/smbdirect.c +++ b/fs/smb/client/smbdirect.c @@ -455,7 +455,6 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc) if (wc->status != IB_WC_SUCCESS || wc->opcode != IB_WC_RECV) { log_rdma_recv(INFO, "wc->status=%d opcode=%d\n", wc->status, wc->opcode); - smbd_disconnect_rdma_connection(info); goto error; } @@ -472,8 +471,9 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc) info->full_packet_received = true; info->negotiate_done = process_negotiation_response(response, wc->byte_len); + put_receive_buffer(info, response); complete(&info->negotiate_completion); - break; + return; /* SMBD data transfer packet */ case SMBD_TRANSFER_DATA: @@ -530,14 +530,16 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc) } return; - - default: - log_rdma_recv(ERR, - "unexpected response type=%d\n", response->type); } + /* + * This is an internal error! + */ + log_rdma_recv(ERR, "unexpected response type=%d\n", response->type); + WARN_ON_ONCE(response->type != SMBD_TRANSFER_DATA); error: put_receive_buffer(info, response); + smbd_disconnect_rdma_connection(info); } static struct rdma_cm_id *smbd_create_id( diff --git a/fs/smb/client/transport.c b/fs/smb/client/transport.c index 3fdafb9297f1..d2867bd263c5 100644 --- a/fs/smb/client/transport.c +++ b/fs/smb/client/transport.c @@ -178,7 +178,7 @@ delete_mid(struct mid_q_entry *mid) * Our basic "send data to server" function. Should be called with srv_mutex * held. The caller is responsible for handling the results. */ -static int +int smb_send_kvec(struct TCP_Server_Info *server, struct msghdr *smb_msg, size_t *sent) { diff --git a/fs/smb/server/auth.c b/fs/smb/server/auth.c index 8e24a6665abd..f8a192cc82f2 100644 --- a/fs/smb/server/auth.c +++ b/fs/smb/server/auth.c @@ -544,7 +544,19 @@ int ksmbd_krb5_authenticate(struct ksmbd_session *sess, char *in_blob, retval = -ENOMEM; goto out; } - sess->user = user; + + if (!sess->user) { + /* First successful authentication */ + sess->user = user; + } else { + if (!ksmbd_compare_user(sess->user, user)) { + ksmbd_debug(AUTH, "different user tried to reuse session\n"); + retval = -EPERM; + ksmbd_free_user(user); + goto out; + } + ksmbd_free_user(user); + } memcpy(sess->sess_key, resp->payload, resp->session_key_len); memcpy(out_blob, resp->payload + resp->session_key_len, @@ -1010,9 +1022,9 @@ static int ksmbd_get_encryption_key(struct ksmbd_work *work, __u64 ses_id, ses_enc_key = enc ? sess->smb3encryptionkey : sess->smb3decryptionkey; - if (enc) - ksmbd_user_session_get(sess); memcpy(key, ses_enc_key, SMB3_ENC_DEC_KEY_SIZE); + if (!enc) + ksmbd_user_session_put(sess); return 0; } @@ -1211,7 +1223,7 @@ free_iv: free_sg: kfree(sg); free_req: - kfree(req); + aead_request_free(req); free_ctx: ksmbd_release_crypto_ctx(ctx); return rc; diff --git a/fs/smb/server/connection.h b/fs/smb/server/connection.h index 0e04cf8b1d89..0e72be594e91 100644 --- a/fs/smb/server/connection.h +++ b/fs/smb/server/connection.h @@ -45,6 +45,7 @@ struct ksmbd_conn { struct mutex srv_mutex; int status; unsigned int cli_cap; + __be32 inet_addr; char *request_buf; struct ksmbd_transport *transport; struct nls_table *local_nls; diff --git a/fs/smb/server/mgmt/user_session.c b/fs/smb/server/mgmt/user_session.c index b1c2219ec0b4..f00fa7760412 100644 --- a/fs/smb/server/mgmt/user_session.c +++ b/fs/smb/server/mgmt/user_session.c @@ -180,7 +180,7 @@ static void ksmbd_expire_session(struct ksmbd_conn *conn) down_write(&sessions_table_lock); down_write(&conn->session_lock); xa_for_each(&conn->sessions, id, sess) { - if (atomic_read(&sess->refcnt) == 0 && + if (atomic_read(&sess->refcnt) <= 1 && (sess->state != SMB2_SESSION_VALID || time_after(jiffies, sess->last_active + SMB2_SESSION_TIMEOUT))) { @@ -229,7 +229,11 @@ void ksmbd_sessions_deregister(struct ksmbd_conn *conn) if (!ksmbd_chann_del(conn, sess) && xa_empty(&sess->ksmbd_chann_list)) { hash_del(&sess->hlist); - ksmbd_session_destroy(sess); + down_write(&conn->session_lock); + xa_erase(&conn->sessions, sess->id); + up_write(&conn->session_lock); + if (atomic_dec_and_test(&sess->refcnt)) + ksmbd_session_destroy(sess); } } } @@ -248,13 +252,30 @@ void ksmbd_sessions_deregister(struct ksmbd_conn *conn) if (xa_empty(&sess->ksmbd_chann_list)) { xa_erase(&conn->sessions, sess->id); hash_del(&sess->hlist); - ksmbd_session_destroy(sess); + if (atomic_dec_and_test(&sess->refcnt)) + ksmbd_session_destroy(sess); } } up_write(&conn->session_lock); up_write(&sessions_table_lock); } +bool is_ksmbd_session_in_connection(struct ksmbd_conn *conn, + unsigned long long id) +{ + struct ksmbd_session *sess; + + down_read(&conn->session_lock); + sess = xa_load(&conn->sessions, id); + if (sess) { + up_read(&conn->session_lock); + return true; + } + up_read(&conn->session_lock); + + return false; +} + struct ksmbd_session *ksmbd_session_lookup(struct ksmbd_conn *conn, unsigned long long id) { @@ -308,8 +329,8 @@ void ksmbd_user_session_put(struct ksmbd_session *sess) if (atomic_read(&sess->refcnt) <= 0) WARN_ON(1); - else - atomic_dec(&sess->refcnt); + else if (atomic_dec_and_test(&sess->refcnt)) + ksmbd_session_destroy(sess); } struct preauth_session *ksmbd_preauth_session_alloc(struct ksmbd_conn *conn, @@ -380,7 +401,7 @@ static struct ksmbd_session *__session_create(int protocol) xa_init(&sess->rpc_handle_list); sess->sequence_number = 1; rwlock_init(&sess->tree_conns_lock); - atomic_set(&sess->refcnt, 1); + atomic_set(&sess->refcnt, 2); ret = __init_smb2_session(sess); if (ret) diff --git a/fs/smb/server/mgmt/user_session.h b/fs/smb/server/mgmt/user_session.h index ce91b1d698e7..f4da293c4dbb 100644 --- a/fs/smb/server/mgmt/user_session.h +++ b/fs/smb/server/mgmt/user_session.h @@ -87,6 +87,8 @@ void ksmbd_session_destroy(struct ksmbd_session *sess); struct ksmbd_session *ksmbd_session_lookup_slowpath(unsigned long long id); struct ksmbd_session *ksmbd_session_lookup(struct ksmbd_conn *conn, unsigned long long id); +bool is_ksmbd_session_in_connection(struct ksmbd_conn *conn, + unsigned long long id); int ksmbd_session_register(struct ksmbd_conn *conn, struct ksmbd_session *sess); void ksmbd_sessions_deregister(struct ksmbd_conn *conn); diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index b29e78b517bf..258ed9978b90 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -1515,7 +1515,7 @@ void create_lease_buf(u8 *rbuf, struct lease *lease) * @open_req: buffer containing smb2 file open(create) request * @is_dir: whether leasing file is directory * - * Return: oplock state, -ENOENT if create lease context not found + * Return: allocated lease context object on success, otherwise NULL */ struct lease_ctx_info *parse_lease_state(void *open_req, bool is_dir) { @@ -1534,6 +1534,10 @@ struct lease_ctx_info *parse_lease_state(void *open_req, bool is_dir) if (sizeof(struct lease_context_v2) == le32_to_cpu(cc->DataLength)) { struct create_lease_v2 *lc = (struct create_lease_v2 *)cc; + if (le16_to_cpu(cc->DataOffset) + le32_to_cpu(cc->DataLength) < + sizeof(struct create_lease_v2) - 4) + goto err_out; + memcpy(lreq->lease_key, lc->lcontext.LeaseKey, SMB2_LEASE_KEY_SIZE); if (is_dir) { lreq->req_state = lc->lcontext.LeaseState & @@ -1551,6 +1555,10 @@ struct lease_ctx_info *parse_lease_state(void *open_req, bool is_dir) } else { struct create_lease *lc = (struct create_lease *)cc; + if (le16_to_cpu(cc->DataOffset) + le32_to_cpu(cc->DataLength) < + sizeof(struct create_lease)) + goto err_out; + memcpy(lreq->lease_key, lc->lcontext.LeaseKey, SMB2_LEASE_KEY_SIZE); lreq->req_state = lc->lcontext.LeaseState; lreq->flags = lc->lcontext.LeaseFlags; @@ -1558,6 +1566,9 @@ struct lease_ctx_info *parse_lease_state(void *open_req, bool is_dir) lreq->version = 1; } return lreq; +err_out: + kfree(lreq); + return NULL; } /** diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 9d041fc558e3..3e2cd22fb2bd 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -1356,8 +1356,7 @@ static int ntlm_negotiate(struct ksmbd_work *work, return rc; sz = le16_to_cpu(rsp->SecurityBufferOffset); - chgblob = - (struct challenge_message *)((char *)&rsp->hdr.ProtocolId + sz); + chgblob = (struct challenge_message *)rsp->Buffer; memset(chgblob, 0, sizeof(struct challenge_message)); if (!work->conn->use_spnego) { @@ -1390,8 +1389,7 @@ static int ntlm_negotiate(struct ksmbd_work *work, goto out; } - sz = le16_to_cpu(rsp->SecurityBufferOffset); - memcpy((char *)&rsp->hdr.ProtocolId + sz, spnego_blob, spnego_blob_len); + memcpy(rsp->Buffer, spnego_blob, spnego_blob_len); rsp->SecurityBufferLength = cpu_to_le16(spnego_blob_len); out: @@ -1473,8 +1471,7 @@ static int ntlm_authenticate(struct ksmbd_work *work, if (rc) return -ENOMEM; - sz = le16_to_cpu(rsp->SecurityBufferOffset); - memcpy((char *)&rsp->hdr.ProtocolId + sz, spnego_blob, spnego_blob_len); + memcpy(rsp->Buffer, spnego_blob, spnego_blob_len); rsp->SecurityBufferLength = cpu_to_le16(spnego_blob_len); kfree(spnego_blob); } @@ -1610,27 +1607,38 @@ static int krb5_authenticate(struct ksmbd_work *work, out_len = work->response_sz - (le16_to_cpu(rsp->SecurityBufferOffset) + 4); - /* Check previous session */ - prev_sess_id = le64_to_cpu(req->PreviousSessionId); - if (prev_sess_id && prev_sess_id != sess->id) - destroy_previous_session(conn, sess->user, prev_sess_id); - - if (sess->state == SMB2_SESSION_VALID) - ksmbd_free_user(sess->user); - retval = ksmbd_krb5_authenticate(sess, in_blob, in_len, out_blob, &out_len); if (retval) { ksmbd_debug(SMB, "krb5 authentication failed\n"); return -EINVAL; } + + /* Check previous session */ + prev_sess_id = le64_to_cpu(req->PreviousSessionId); + if (prev_sess_id && prev_sess_id != sess->id) + destroy_previous_session(conn, sess->user, prev_sess_id); + rsp->SecurityBufferLength = cpu_to_le16(out_len); - if ((conn->sign || server_conf.enforced_signing) || + /* + * If session state is SMB2_SESSION_VALID, We can assume + * that it is reauthentication. And the user/password + * has been verified, so return it here. + */ + if (sess->state == SMB2_SESSION_VALID) { + if (conn->binding) + goto binding_session; + return 0; + } + + if ((rsp->SessionFlags != SMB2_SESSION_FLAG_IS_GUEST_LE && + (conn->sign || server_conf.enforced_signing)) || (req->SecurityMode & SMB2_NEGOTIATE_SIGNING_REQUIRED)) sess->sign = true; - if (smb3_encryption_negotiated(conn)) { + if (smb3_encryption_negotiated(conn) && + !(req->Flags & SMB2_SESSION_REQ_FLAG_BINDING)) { retval = conn->ops->generate_encryptionkey(conn, sess); if (retval) { ksmbd_debug(SMB, @@ -1643,6 +1651,7 @@ static int krb5_authenticate(struct ksmbd_work *work, sess->sign = false; } +binding_session: if (conn->dialect >= SMB30_PROT_ID) { chann = lookup_chann_list(sess, conn); if (!chann) { @@ -1723,44 +1732,38 @@ int smb2_sess_setup(struct ksmbd_work *work) if (conn->dialect != sess->dialect) { rc = -EINVAL; - ksmbd_user_session_put(sess); goto out_err; } if (!(req->hdr.Flags & SMB2_FLAGS_SIGNED)) { rc = -EINVAL; - ksmbd_user_session_put(sess); goto out_err; } if (strncmp(conn->ClientGUID, sess->ClientGUID, SMB2_CLIENT_GUID_SIZE)) { rc = -ENOENT; - ksmbd_user_session_put(sess); goto out_err; } if (sess->state == SMB2_SESSION_IN_PROGRESS) { rc = -EACCES; - ksmbd_user_session_put(sess); goto out_err; } if (sess->state == SMB2_SESSION_EXPIRED) { rc = -EFAULT; - ksmbd_user_session_put(sess); goto out_err; } - ksmbd_user_session_put(sess); if (ksmbd_conn_need_reconnect(conn)) { rc = -EFAULT; + ksmbd_user_session_put(sess); sess = NULL; goto out_err; } - sess = ksmbd_session_lookup(conn, sess_id); - if (!sess) { + if (is_ksmbd_session_in_connection(conn, sess_id)) { rc = -EACCES; goto out_err; } @@ -1839,8 +1842,6 @@ int smb2_sess_setup(struct ksmbd_work *work) ksmbd_conn_set_good(conn); sess->state = SMB2_SESSION_VALID; } - kfree(sess->Preauth_HashValue); - sess->Preauth_HashValue = NULL; } else if (conn->preferred_auth_mech == KSMBD_AUTH_NTLMSSP) { if (negblob->MessageType == NtLmNegotiate) { rc = ntlm_negotiate(work, negblob, negblob_len, rsp); @@ -1867,8 +1868,6 @@ int smb2_sess_setup(struct ksmbd_work *work) kfree(preauth_sess); } } - kfree(sess->Preauth_HashValue); - sess->Preauth_HashValue = NULL; } else { pr_info_ratelimited("Unknown NTLMSSP message type : 0x%x\n", le32_to_cpu(negblob->MessageType)); @@ -1926,6 +1925,8 @@ out_err: sess->last_active = jiffies; sess->state = SMB2_SESSION_EXPIRED; + ksmbd_user_session_put(sess); + work->sess = NULL; if (try_delay) { ksmbd_conn_set_need_reconnect(conn); ssleep(5); @@ -2246,13 +2247,14 @@ int smb2_session_logoff(struct ksmbd_work *work) return -ENOENT; } - ksmbd_destroy_file_table(&sess->file_table); down_write(&conn->session_lock); sess->state = SMB2_SESSION_EXPIRED; up_write(&conn->session_lock); - ksmbd_free_user(sess->user); - sess->user = NULL; + if (sess->user) { + ksmbd_free_user(sess->user); + sess->user = NULL; + } ksmbd_all_conn_set_status(sess_id, KSMBD_SESS_NEED_NEGOTIATE); rsp->StructureSize = cpu_to_le16(4); @@ -2691,7 +2693,7 @@ int smb2_open(struct ksmbd_work *work) int req_op_level = 0, open_flags = 0, may_flags = 0, file_info = 0; int rc = 0; int contxt_cnt = 0, query_disk_id = 0; - int maximal_access_ctxt = 0, posix_ctxt = 0; + bool maximal_access_ctxt = false, posix_ctxt = false; int s_type = 0; int next_off = 0; char *name = NULL; @@ -2718,6 +2720,27 @@ int smb2_open(struct ksmbd_work *work) return create_smb2_pipe(work); } + if (req->CreateContextsOffset && tcon->posix_extensions) { + context = smb2_find_context_vals(req, SMB2_CREATE_TAG_POSIX, 16); + if (IS_ERR(context)) { + rc = PTR_ERR(context); + goto err_out2; + } else if (context) { + struct create_posix *posix = (struct create_posix *)context; + + if (le16_to_cpu(context->DataOffset) + + le32_to_cpu(context->DataLength) < + sizeof(struct create_posix) - 4) { + rc = -EINVAL; + goto err_out2; + } + ksmbd_debug(SMB, "get posix context\n"); + + posix_mode = le32_to_cpu(posix->Mode); + posix_ctxt = true; + } + } + if (req->NameLength) { if ((req->CreateOptions & FILE_DIRECTORY_FILE_LE) && *(char *)req->Buffer == '\\') { @@ -2749,9 +2772,11 @@ int smb2_open(struct ksmbd_work *work) goto err_out2; } - rc = ksmbd_validate_filename(name); - if (rc < 0) - goto err_out2; + if (posix_ctxt == false) { + rc = ksmbd_validate_filename(name); + if (rc < 0) + goto err_out2; + } if (ksmbd_share_veto_filename(share, name)) { rc = -ENOENT; @@ -2866,28 +2891,6 @@ int smb2_open(struct ksmbd_work *work) rc = -EBADF; goto err_out2; } - - if (tcon->posix_extensions) { - context = smb2_find_context_vals(req, - SMB2_CREATE_TAG_POSIX, 16); - if (IS_ERR(context)) { - rc = PTR_ERR(context); - goto err_out2; - } else if (context) { - struct create_posix *posix = - (struct create_posix *)context; - if (le16_to_cpu(context->DataOffset) + - le32_to_cpu(context->DataLength) < - sizeof(struct create_posix) - 4) { - rc = -EINVAL; - goto err_out2; - } - ksmbd_debug(SMB, "get posix context\n"); - - posix_mode = le32_to_cpu(posix->Mode); - posix_ctxt = 1; - } - } } if (ksmbd_override_fsids(work)) { @@ -3244,7 +3247,7 @@ int smb2_open(struct ksmbd_work *work) goto err_out1; } } else { - if (req_op_level == SMB2_OPLOCK_LEVEL_LEASE) { + if (req_op_level == SMB2_OPLOCK_LEVEL_LEASE && lc) { /* * Compare parent lease using parent key. If there is no * a lease that has same parent key, Send lease break @@ -7124,17 +7127,17 @@ out_check_cl: } no_check_cl: + flock = smb_lock->fl; + list_del(&smb_lock->llist); + if (smb_lock->zero_len) { err = 0; goto skip; } - - flock = smb_lock->fl; - list_del(&smb_lock->llist); retry: rc = vfs_lock_file(filp, smb_lock->cmd, flock, NULL); skip: - if (flags & SMB2_LOCKFLAG_UNLOCK) { + if (smb_lock->flags & SMB2_LOCKFLAG_UNLOCK) { if (!rc) { ksmbd_debug(SMB, "File unlocked\n"); } else if (rc == -ENOENT) { @@ -8151,11 +8154,6 @@ static void smb20_oplock_break_ack(struct ksmbd_work *work) goto err_out; } - opinfo->op_state = OPLOCK_STATE_NONE; - wake_up_interruptible_all(&opinfo->oplock_q); - opinfo_put(opinfo); - ksmbd_fd_put(work, fp); - rsp->StructureSize = cpu_to_le16(24); rsp->OplockLevel = rsp_oplevel; rsp->Reserved = 0; @@ -8163,16 +8161,15 @@ static void smb20_oplock_break_ack(struct ksmbd_work *work) rsp->VolatileFid = volatile_id; rsp->PersistentFid = persistent_id; ret = ksmbd_iov_pin_rsp(work, rsp, sizeof(struct smb2_oplock_break)); - if (!ret) - return; - + if (ret) { err_out: + smb2_set_err_rsp(work); + } + opinfo->op_state = OPLOCK_STATE_NONE; wake_up_interruptible_all(&opinfo->oplock_q); - opinfo_put(opinfo); ksmbd_fd_put(work, fp); - smb2_set_err_rsp(work); } static int check_lease_state(struct lease *lease, __le32 req_state) @@ -8302,11 +8299,6 @@ static void smb21_lease_break_ack(struct ksmbd_work *work) } lease_state = lease->state; - opinfo->op_state = OPLOCK_STATE_NONE; - wake_up_interruptible_all(&opinfo->oplock_q); - atomic_dec(&opinfo->breaking_cnt); - wake_up_interruptible_all(&opinfo->oplock_brk); - opinfo_put(opinfo); rsp->StructureSize = cpu_to_le16(36); rsp->Reserved = 0; @@ -8315,16 +8307,16 @@ static void smb21_lease_break_ack(struct ksmbd_work *work) rsp->LeaseState = lease_state; rsp->LeaseDuration = 0; ret = ksmbd_iov_pin_rsp(work, rsp, sizeof(struct smb2_lease_ack)); - if (!ret) - return; - + if (ret) { err_out: + smb2_set_err_rsp(work); + } + + opinfo->op_state = OPLOCK_STATE_NONE; wake_up_interruptible_all(&opinfo->oplock_q); atomic_dec(&opinfo->breaking_cnt); wake_up_interruptible_all(&opinfo->oplock_brk); - opinfo_put(opinfo); - smb2_set_err_rsp(work); } /** diff --git a/fs/smb/server/smb_common.c b/fs/smb/server/smb_common.c index 7134abeeb53e..2850802f4a50 100644 --- a/fs/smb/server/smb_common.c +++ b/fs/smb/server/smb_common.c @@ -508,7 +508,7 @@ int ksmbd_extract_shortname(struct ksmbd_conn *conn, const char *longname, p = strrchr(longname, '.'); if (p == longname) { /*name starts with a dot*/ - strscpy(extension, "___", strlen("___")); + strscpy(extension, "___", sizeof(extension)); } else { if (p) { p++; diff --git a/fs/smb/server/smbacl.c b/fs/smb/server/smbacl.c index 6fd3560028d3..90c5e3edbf46 100644 --- a/fs/smb/server/smbacl.c +++ b/fs/smb/server/smbacl.c @@ -270,6 +270,11 @@ static int sid_to_id(struct user_namespace *user_ns, return -EIO; } + if (psid->num_subauth == 0) { + pr_err("%s: zero subauthorities!\n", __func__); + return -EIO; + } + if (sidtype == SIDOWNER) { kuid_t uid; uid_t id; @@ -398,7 +403,9 @@ static void parse_dacl(struct user_namespace *user_ns, if (num_aces <= 0) return; - if (num_aces > ULONG_MAX / sizeof(struct smb_ace *)) + if (num_aces > (le16_to_cpu(pdacl->size) - sizeof(struct smb_acl)) / + (offsetof(struct smb_ace, sid) + + offsetof(struct smb_sid, sub_auth) + sizeof(__le16))) return; ret = init_acl_state(&acl_state, num_aces); @@ -432,6 +439,7 @@ static void parse_dacl(struct user_namespace *user_ns, offsetof(struct smb_sid, sub_auth); if (end_of_acl - acl_base < acl_size || + ppace[i]->sid.num_subauth == 0 || ppace[i]->sid.num_subauth > SID_MAX_SUB_AUTHORITIES || (end_of_acl - acl_base < acl_size + sizeof(__le32) * ppace[i]->sid.num_subauth) || diff --git a/fs/smb/server/transport_ipc.c b/fs/smb/server/transport_ipc.c index 496855f755ac..7fc4b33b89e3 100644 --- a/fs/smb/server/transport_ipc.c +++ b/fs/smb/server/transport_ipc.c @@ -267,6 +267,7 @@ static int handle_response(int type, void *payload, size_t sz) if (entry->type + 1 != type) { pr_err("Waiting for IPC type %d, got %d. Ignore.\n", entry->type + 1, type); + continue; } entry->response = kvzalloc(sz, GFP_KERNEL); @@ -295,7 +296,11 @@ static int ipc_server_config_on_startup(struct ksmbd_startup_request *req) server_conf.signing = req->signing; server_conf.tcp_port = req->tcp_port; server_conf.ipc_timeout = req->ipc_timeout * HZ; - server_conf.deadtime = req->deadtime * SMB_ECHO_INTERVAL; + if (check_mul_overflow(req->deadtime, SMB_ECHO_INTERVAL, + &server_conf.deadtime)) { + ret = -EINVAL; + goto out; + } server_conf.share_fake_fscaps = req->share_fake_fscaps; ksmbd_init_domain(req->sub_auth); @@ -318,6 +323,7 @@ static int ipc_server_config_on_startup(struct ksmbd_startup_request *req) ret |= ksmbd_set_work_group(req->work_group); ret |= ksmbd_tcp_set_interfaces(KSMBD_STARTUP_CONFIG_INTERFACES(req), req->ifc_list_sz); +out: if (ret) { pr_err("Server configuration error: %s %s %s\n", req->netbios_name, req->server_string, diff --git a/fs/smb/server/transport_rdma.c b/fs/smb/server/transport_rdma.c index 8faa25c6e129..7d59ed6e1383 100644 --- a/fs/smb/server/transport_rdma.c +++ b/fs/smb/server/transport_rdma.c @@ -128,9 +128,6 @@ struct smb_direct_transport { spinlock_t recvmsg_queue_lock; struct list_head recvmsg_queue; - spinlock_t empty_recvmsg_queue_lock; - struct list_head empty_recvmsg_queue; - int send_credit_target; atomic_t send_credits; spinlock_t lock_new_recv_credits; @@ -266,40 +263,19 @@ smb_direct_recvmsg *get_free_recvmsg(struct smb_direct_transport *t) static void put_recvmsg(struct smb_direct_transport *t, struct smb_direct_recvmsg *recvmsg) { - ib_dma_unmap_single(t->cm_id->device, recvmsg->sge.addr, - recvmsg->sge.length, DMA_FROM_DEVICE); + if (likely(recvmsg->sge.length != 0)) { + ib_dma_unmap_single(t->cm_id->device, + recvmsg->sge.addr, + recvmsg->sge.length, + DMA_FROM_DEVICE); + recvmsg->sge.length = 0; + } spin_lock(&t->recvmsg_queue_lock); list_add(&recvmsg->list, &t->recvmsg_queue); spin_unlock(&t->recvmsg_queue_lock); } -static struct -smb_direct_recvmsg *get_empty_recvmsg(struct smb_direct_transport *t) -{ - struct smb_direct_recvmsg *recvmsg = NULL; - - spin_lock(&t->empty_recvmsg_queue_lock); - if (!list_empty(&t->empty_recvmsg_queue)) { - recvmsg = list_first_entry(&t->empty_recvmsg_queue, - struct smb_direct_recvmsg, list); - list_del(&recvmsg->list); - } - spin_unlock(&t->empty_recvmsg_queue_lock); - return recvmsg; -} - -static void put_empty_recvmsg(struct smb_direct_transport *t, - struct smb_direct_recvmsg *recvmsg) -{ - ib_dma_unmap_single(t->cm_id->device, recvmsg->sge.addr, - recvmsg->sge.length, DMA_FROM_DEVICE); - - spin_lock(&t->empty_recvmsg_queue_lock); - list_add_tail(&recvmsg->list, &t->empty_recvmsg_queue); - spin_unlock(&t->empty_recvmsg_queue_lock); -} - static void enqueue_reassembly(struct smb_direct_transport *t, struct smb_direct_recvmsg *recvmsg, int data_length) @@ -384,9 +360,6 @@ static struct smb_direct_transport *alloc_transport(struct rdma_cm_id *cm_id) spin_lock_init(&t->recvmsg_queue_lock); INIT_LIST_HEAD(&t->recvmsg_queue); - spin_lock_init(&t->empty_recvmsg_queue_lock); - INIT_LIST_HEAD(&t->empty_recvmsg_queue); - init_waitqueue_head(&t->wait_send_pending); atomic_set(&t->send_pending, 0); @@ -426,7 +399,8 @@ static void free_transport(struct smb_direct_transport *t) if (t->qp) { ib_drain_qp(t->qp); ib_mr_pool_destroy(t->qp, &t->qp->rdma_mrs); - ib_destroy_qp(t->qp); + t->qp = NULL; + rdma_destroy_qp(t->cm_id); } ksmbd_debug(RDMA, "drain the reassembly queue\n"); @@ -541,13 +515,13 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc) t = recvmsg->transport; if (wc->status != IB_WC_SUCCESS || wc->opcode != IB_WC_RECV) { + put_recvmsg(t, recvmsg); if (wc->status != IB_WC_WR_FLUSH_ERR) { pr_err("Recv error. status='%s (%d)' opcode=%d\n", ib_wc_status_msg(wc->status), wc->status, wc->opcode); smb_direct_disconnect_rdma_connection(t); } - put_empty_recvmsg(t, recvmsg); return; } @@ -561,7 +535,8 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc) switch (recvmsg->type) { case SMB_DIRECT_MSG_NEGOTIATE_REQ: if (wc->byte_len < sizeof(struct smb_direct_negotiate_req)) { - put_empty_recvmsg(t, recvmsg); + put_recvmsg(t, recvmsg); + smb_direct_disconnect_rdma_connection(t); return; } t->negotiation_requested = true; @@ -569,7 +544,7 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc) t->status = SMB_DIRECT_CS_CONNECTED; enqueue_reassembly(t, recvmsg, 0); wake_up_interruptible(&t->wait_status); - break; + return; case SMB_DIRECT_MSG_DATA_TRANSFER: { struct smb_direct_data_transfer *data_transfer = (struct smb_direct_data_transfer *)recvmsg->packet; @@ -578,7 +553,8 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc) if (wc->byte_len < offsetof(struct smb_direct_data_transfer, padding)) { - put_empty_recvmsg(t, recvmsg); + put_recvmsg(t, recvmsg); + smb_direct_disconnect_rdma_connection(t); return; } @@ -586,7 +562,8 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc) if (data_length) { if (wc->byte_len < sizeof(struct smb_direct_data_transfer) + (u64)data_length) { - put_empty_recvmsg(t, recvmsg); + put_recvmsg(t, recvmsg); + smb_direct_disconnect_rdma_connection(t); return; } @@ -598,16 +575,11 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc) else t->full_packet_received = true; - enqueue_reassembly(t, recvmsg, (int)data_length); - wake_up_interruptible(&t->wait_reassembly_queue); - spin_lock(&t->receive_credit_lock); receive_credits = --(t->recv_credits); avail_recvmsg_count = t->count_avail_recvmsg; spin_unlock(&t->receive_credit_lock); } else { - put_empty_recvmsg(t, recvmsg); - spin_lock(&t->receive_credit_lock); receive_credits = --(t->recv_credits); avail_recvmsg_count = ++(t->count_avail_recvmsg); @@ -629,11 +601,23 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc) if (is_receive_credit_post_required(receive_credits, avail_recvmsg_count)) mod_delayed_work(smb_direct_wq, &t->post_recv_credits_work, 0); - break; + + if (data_length) { + enqueue_reassembly(t, recvmsg, (int)data_length); + wake_up_interruptible(&t->wait_reassembly_queue); + } else + put_recvmsg(t, recvmsg); + + return; } - default: - break; } + + /* + * This is an internal error! + */ + WARN_ON_ONCE(recvmsg->type != SMB_DIRECT_MSG_DATA_TRANSFER); + put_recvmsg(t, recvmsg); + smb_direct_disconnect_rdma_connection(t); } static int smb_direct_post_recv(struct smb_direct_transport *t, @@ -663,6 +647,7 @@ static int smb_direct_post_recv(struct smb_direct_transport *t, ib_dma_unmap_single(t->cm_id->device, recvmsg->sge.addr, recvmsg->sge.length, DMA_FROM_DEVICE); + recvmsg->sge.length = 0; smb_direct_disconnect_rdma_connection(t); return ret; } @@ -804,7 +789,6 @@ static void smb_direct_post_recv_credits(struct work_struct *work) struct smb_direct_recvmsg *recvmsg; int receive_credits, credits = 0; int ret; - int use_free = 1; spin_lock(&t->receive_credit_lock); receive_credits = t->recv_credits; @@ -812,18 +796,9 @@ static void smb_direct_post_recv_credits(struct work_struct *work) if (receive_credits < t->recv_credit_target) { while (true) { - if (use_free) - recvmsg = get_free_recvmsg(t); - else - recvmsg = get_empty_recvmsg(t); - if (!recvmsg) { - if (use_free) { - use_free = 0; - continue; - } else { - break; - } - } + recvmsg = get_free_recvmsg(t); + if (!recvmsg) + break; recvmsg->type = SMB_DIRECT_MSG_DATA_TRANSFER; recvmsg->first_segment = false; @@ -1799,8 +1774,6 @@ static void smb_direct_destroy_pools(struct smb_direct_transport *t) while ((recvmsg = get_free_recvmsg(t))) mempool_free(recvmsg, t->recvmsg_mempool); - while ((recvmsg = get_empty_recvmsg(t))) - mempool_free(recvmsg, t->recvmsg_mempool); mempool_destroy(t->recvmsg_mempool); t->recvmsg_mempool = NULL; @@ -1856,6 +1829,7 @@ static int smb_direct_create_pools(struct smb_direct_transport *t) if (!recvmsg) goto err; recvmsg->transport = t; + recvmsg->sge.length = 0; list_add(&recvmsg->list, &t->recvmsg_queue); } t->count_avail_recvmsg = t->recv_credit_max; @@ -1934,8 +1908,8 @@ static int smb_direct_create_qpair(struct smb_direct_transport *t, return 0; err: if (t->qp) { - ib_destroy_qp(t->qp); t->qp = NULL; + rdma_destroy_qp(t->cm_id); } if (t->recv_cq) { ib_destroy_cq(t->recv_cq); diff --git a/fs/smb/server/transport_tcp.c b/fs/smb/server/transport_tcp.c index 25f7c86ba9b9..1222cf6be5ef 100644 --- a/fs/smb/server/transport_tcp.c +++ b/fs/smb/server/transport_tcp.c @@ -87,6 +87,7 @@ static struct tcp_transport *alloc_transport(struct socket *client_sk) return NULL; } + conn->inet_addr = inet_sk(client_sk->sk)->inet_daddr; conn->transport = KSMBD_TRANS(t); KSMBD_TRANS(t)->conn = conn; KSMBD_TRANS(t)->ops = &ksmbd_tcp_transport_ops; @@ -226,6 +227,8 @@ static int ksmbd_kthread_fn(void *p) { struct socket *client_sk = NULL; struct interface *iface = (struct interface *)p; + struct inet_sock *csk_inet; + struct ksmbd_conn *conn; int ret; while (!kthread_should_stop()) { @@ -244,6 +247,20 @@ static int ksmbd_kthread_fn(void *p) continue; } + /* + * Limits repeated connections from clients with the same IP. + */ + csk_inet = inet_sk(client_sk->sk); + down_read(&conn_list_lock); + list_for_each_entry(conn, &conn_list, conns_list) + if (csk_inet->inet_daddr == conn->inet_addr) { + ret = -EAGAIN; + break; + } + up_read(&conn_list_lock); + if (ret == -EAGAIN) + continue; + if (server_conf.max_connections && atomic_inc_return(&active_num_conn) >= server_conf.max_connections) { pr_info_ratelimited("Limit the maximum number of connections(%u)\n", diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c index 396d4ea77d34..871c0d8e5012 100644 --- a/fs/smb/server/vfs.c +++ b/fs/smb/server/vfs.c @@ -423,10 +423,15 @@ static int ksmbd_vfs_stream_write(struct ksmbd_file *fp, char *buf, loff_t *pos, ksmbd_debug(VFS, "write stream data pos : %llu, count : %zd\n", *pos, count); + if (*pos >= XATTR_SIZE_MAX) { + pr_err("stream write position %lld is out of bounds\n", *pos); + return -EINVAL; + } + size = *pos + count; if (size > XATTR_SIZE_MAX) { size = XATTR_SIZE_MAX; - count = (*pos + count) - XATTR_SIZE_MAX; + count = XATTR_SIZE_MAX - *pos; } v_len = ksmbd_vfs_getcasexattr(user_ns, @@ -493,7 +498,8 @@ int ksmbd_vfs_write(struct ksmbd_work *work, struct ksmbd_file *fp, int err = 0; if (work->conn->connection_type) { - if (!(fp->daccess & (FILE_WRITE_DATA_LE | FILE_APPEND_DATA_LE))) { + if (!(fp->daccess & (FILE_WRITE_DATA_LE | FILE_APPEND_DATA_LE)) || + S_ISDIR(file_inode(fp->filp)->i_mode)) { pr_err("no right to write(%pD)\n", fp->filp); err = -EACCES; goto out; @@ -556,7 +562,8 @@ int ksmbd_vfs_getattr(const struct path *path, struct kstat *stat) { int err; - err = vfs_getattr(path, stat, STATX_BTIME, AT_STATX_SYNC_AS_STAT); + err = vfs_getattr(path, stat, STATX_BASIC_STATS | STATX_BTIME, + AT_STATX_SYNC_AS_STAT); if (err) pr_err("getattr failed, err %d\n", err); return err; @@ -1277,6 +1284,7 @@ out1: err = ksmbd_vfs_lock_parent(parent_path->dentry, path->dentry); if (err) { + mnt_drop_write(parent_path->mnt); path_put(path); path_put(parent_path); } diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c index 32565dafa7f3..37579c07f6fd 100644 --- a/fs/squashfs/super.c +++ b/fs/squashfs/super.c @@ -137,6 +137,11 @@ static int squashfs_fill_super(struct super_block *sb, struct fs_context *fc) msblk->panic_on_errors = (opts->errors == Opt_errors_panic); msblk->devblksize = sb_min_blocksize(sb, SQUASHFS_DEVBLK_SIZE); + if (!msblk->devblksize) { + errorf(fc, "squashfs: unable to set blocksize\n"); + return -EINVAL; + } + msblk->devblksize_log2 = ffz(~msblk->devblksize); mutex_init(&msblk->meta_index_mutex); diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 82101a2cf933..fcf96f52b2e9 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -1426,6 +1426,9 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, if (prev != vma) mas_next(&mas, ULONG_MAX); + if (vma->vm_start < start) + prev = vma; + ret = 0; do { cond_resched(); @@ -1603,6 +1606,9 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, if (prev != vma) mas_next(&mas, ULONG_MAX); + if (vma->vm_start < start) + prev = vma; + ret = 0; do { cond_resched(); diff --git a/fs/vboxsf/super.c b/fs/vboxsf/super.c index 74952e58cca0..48f33d4994dc 100644 --- a/fs/vboxsf/super.c +++ b/fs/vboxsf/super.c @@ -21,7 +21,8 @@ #define VBOXSF_SUPER_MAGIC 0x786f4256 /* 'VBox' little endian */ -static const unsigned char VBSF_MOUNT_SIGNATURE[4] = "\000\377\376\375"; +static const unsigned char VBSF_MOUNT_SIGNATURE[4] = { '\000', '\377', '\376', + '\375' }; static int follow_symlinks; module_param(follow_symlinks, int, 0444); diff --git a/fs/xfs/Kconfig b/fs/xfs/Kconfig index 9fac5ea8d0e4..dff90db507e3 100644 --- a/fs/xfs/Kconfig +++ b/fs/xfs/Kconfig @@ -154,6 +154,18 @@ config XFS_DEBUG Say N unless you are an XFS developer, or you play one on TV. +config XFS_DEBUG_EXPENSIVE + bool "XFS expensive debugging checks" + depends on XFS_FS && XFS_DEBUG + help + Say Y here to get an XFS build with expensive debugging checks + enabled. These checks may affect performance significantly. + + Note that the resulting code will be HUGER and SLOWER, and probably + not useful unless you are debugging a particular problem. + + Say N unless you are an XFS developer, or you play one on TV. + config XFS_ASSERT_FATAL bool "XFS fatal asserts" default y diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c index bf47efe08a58..9743fa5b5388 100644 --- a/fs/xfs/libxfs/xfs_ag.c +++ b/fs/xfs/libxfs/xfs_ag.c @@ -259,6 +259,30 @@ xfs_agino_range( return __xfs_agino_range(mp, xfs_ag_block_count(mp, agno), first, last); } +/* + * Free perag within the specified AG range, it is only used to free unused + * perags under the error handling path. + */ +void +xfs_free_unused_perag_range( + struct xfs_mount *mp, + xfs_agnumber_t agstart, + xfs_agnumber_t agend) +{ + struct xfs_perag *pag; + xfs_agnumber_t index; + + for (index = agstart; index < agend; index++) { + spin_lock(&mp->m_perag_lock); + pag = radix_tree_delete(&mp->m_perag_tree, index); + spin_unlock(&mp->m_perag_lock); + if (!pag) + break; + xfs_buf_hash_destroy(pag); + kmem_free(pag); + } +} + int xfs_initialize_perag( struct xfs_mount *mp, @@ -345,18 +369,14 @@ xfs_initialize_perag( return 0; out_remove_pag: + spin_lock(&mp->m_perag_lock); radix_tree_delete(&mp->m_perag_tree, index); + spin_unlock(&mp->m_perag_lock); out_free_pag: kmem_free(pag); out_unwind_new_pags: /* unwind any prior newly initialized pags */ - for (index = first_initialised; index < agcount; index++) { - pag = radix_tree_delete(&mp->m_perag_tree, index); - if (!pag) - break; - xfs_buf_hash_destroy(pag); - kmem_free(pag); - } + xfs_free_unused_perag_range(mp, first_initialised, agcount); return error; } @@ -906,7 +926,10 @@ xfs_ag_shrink_space( if (err2 != -ENOSPC) goto resv_err; - __xfs_free_extent_later(*tpp, args.fsbno, delta, NULL, true); + err2 = __xfs_free_extent_later(*tpp, args.fsbno, delta, NULL, + XFS_AG_RESV_NONE, true); + if (err2) + goto resv_err; /* * Roll the transaction before trying to re-init the per-ag @@ -981,10 +1004,8 @@ xfs_ag_extend_space( if (error) return error; - error = xfs_free_extent(tp, XFS_AGB_TO_FSB(pag->pag_mount, pag->pag_agno, - be32_to_cpu(agf->agf_length) - len), - len, &XFS_RMAP_OINFO_SKIP_UPDATE, - XFS_AG_RESV_NONE); + error = xfs_free_extent(tp, pag, be32_to_cpu(agf->agf_length) - len, + len, &XFS_RMAP_OINFO_SKIP_UPDATE, XFS_AG_RESV_NONE); if (error) return error; diff --git a/fs/xfs/libxfs/xfs_ag.h b/fs/xfs/libxfs/xfs_ag.h index 191b22b9a35b..eb84af1c8628 100644 --- a/fs/xfs/libxfs/xfs_ag.h +++ b/fs/xfs/libxfs/xfs_ag.h @@ -106,6 +106,9 @@ struct xfs_perag { #endif /* __KERNEL__ */ }; + +void xfs_free_unused_perag_range(struct xfs_mount *mp, xfs_agnumber_t agstart, + xfs_agnumber_t agend); int xfs_initialize_perag(struct xfs_mount *mp, xfs_agnumber_t agcount, xfs_rfsblock_t dcount, xfs_agnumber_t *maxagi); int xfs_initialize_perag_data(struct xfs_mount *mp, xfs_agnumber_t agno); diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index 74d039bdc9f7..cd5b197d7046 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -2485,45 +2485,53 @@ xfs_agfl_reset( * the real allocation can proceed. Deferring the free disconnects freeing up * the AGFL slot from freeing the block. */ -STATIC void +static int xfs_defer_agfl_block( struct xfs_trans *tp, xfs_agnumber_t agno, - xfs_fsblock_t agbno, + xfs_agblock_t agbno, struct xfs_owner_info *oinfo) { struct xfs_mount *mp = tp->t_mountp; - struct xfs_extent_free_item *new; /* new element */ + struct xfs_extent_free_item *xefi; + xfs_fsblock_t fsbno = XFS_AGB_TO_FSB(mp, agno, agbno); ASSERT(xfs_extfree_item_cache != NULL); ASSERT(oinfo != NULL); - new = kmem_cache_zalloc(xfs_extfree_item_cache, + if (XFS_IS_CORRUPT(mp, !xfs_verify_fsbno(mp, fsbno))) + return -EFSCORRUPTED; + + xefi = kmem_cache_zalloc(xfs_extfree_item_cache, GFP_KERNEL | __GFP_NOFAIL); - new->xefi_startblock = XFS_AGB_TO_FSB(mp, agno, agbno); - new->xefi_blockcount = 1; - new->xefi_owner = oinfo->oi_owner; + xefi->xefi_startblock = fsbno; + xefi->xefi_blockcount = 1; + xefi->xefi_owner = oinfo->oi_owner; + xefi->xefi_agresv = XFS_AG_RESV_AGFL; trace_xfs_agfl_free_defer(mp, agno, 0, agbno, 1); - xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_AGFL_FREE, &new->xefi_list); + xfs_extent_free_get_group(mp, xefi); + xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_AGFL_FREE, &xefi->xefi_list); + return 0; } /* * Add the extent to the list of extents to be free at transaction end. * The list is maintained sorted (by block number). */ -void +int __xfs_free_extent_later( struct xfs_trans *tp, xfs_fsblock_t bno, xfs_filblks_t len, const struct xfs_owner_info *oinfo, + enum xfs_ag_resv_type type, bool skip_discard) { - struct xfs_extent_free_item *new; /* new element */ -#ifdef DEBUG + struct xfs_extent_free_item *xefi; struct xfs_mount *mp = tp->t_mountp; +#ifdef DEBUG xfs_agnumber_t agno; xfs_agblock_t agbno; @@ -2539,28 +2547,36 @@ __xfs_free_extent_later( ASSERT(agbno + len <= mp->m_sb.sb_agblocks); #endif ASSERT(xfs_extfree_item_cache != NULL); + ASSERT(type != XFS_AG_RESV_AGFL); - new = kmem_cache_zalloc(xfs_extfree_item_cache, + if (XFS_IS_CORRUPT(mp, !xfs_verify_fsbext(mp, bno, len))) + return -EFSCORRUPTED; + + xefi = kmem_cache_zalloc(xfs_extfree_item_cache, GFP_KERNEL | __GFP_NOFAIL); - new->xefi_startblock = bno; - new->xefi_blockcount = (xfs_extlen_t)len; + xefi->xefi_startblock = bno; + xefi->xefi_blockcount = (xfs_extlen_t)len; + xefi->xefi_agresv = type; if (skip_discard) - new->xefi_flags |= XFS_EFI_SKIP_DISCARD; + xefi->xefi_flags |= XFS_EFI_SKIP_DISCARD; if (oinfo) { ASSERT(oinfo->oi_offset == 0); if (oinfo->oi_flags & XFS_OWNER_INFO_ATTR_FORK) - new->xefi_flags |= XFS_EFI_ATTR_FORK; + xefi->xefi_flags |= XFS_EFI_ATTR_FORK; if (oinfo->oi_flags & XFS_OWNER_INFO_BMBT_BLOCK) - new->xefi_flags |= XFS_EFI_BMBT_BLOCK; - new->xefi_owner = oinfo->oi_owner; + xefi->xefi_flags |= XFS_EFI_BMBT_BLOCK; + xefi->xefi_owner = oinfo->oi_owner; } else { - new->xefi_owner = XFS_RMAP_OWN_NULL; + xefi->xefi_owner = XFS_RMAP_OWN_NULL; } - trace_xfs_bmap_free_defer(tp->t_mountp, + trace_xfs_bmap_free_defer(mp, XFS_FSB_TO_AGNO(tp->t_mountp, bno), 0, XFS_FSB_TO_AGBNO(tp->t_mountp, bno), len); - xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_FREE, &new->xefi_list); + + xfs_extent_free_get_group(mp, xefi); + xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_FREE, &xefi->xefi_list); + return 0; } #ifdef DEBUG @@ -2720,7 +2736,9 @@ xfs_alloc_fix_freelist( goto out_agbp_relse; /* defer agfl frees */ - xfs_defer_agfl_block(tp, args->agno, bno, &targs.oinfo); + error = xfs_defer_agfl_block(tp, args->agno, bno, &targs.oinfo); + if (error) + goto out_agbp_relse; } targs.tp = tp; @@ -3447,7 +3465,8 @@ xfs_free_extent_fix_freelist( int __xfs_free_extent( struct xfs_trans *tp, - xfs_fsblock_t bno, + struct xfs_perag *pag, + xfs_agblock_t agbno, xfs_extlen_t len, const struct xfs_owner_info *oinfo, enum xfs_ag_resv_type type, @@ -3455,12 +3474,9 @@ __xfs_free_extent( { struct xfs_mount *mp = tp->t_mountp; struct xfs_buf *agbp; - xfs_agnumber_t agno = XFS_FSB_TO_AGNO(mp, bno); - xfs_agblock_t agbno = XFS_FSB_TO_AGBNO(mp, bno); struct xfs_agf *agf; int error; unsigned int busy_flags = 0; - struct xfs_perag *pag; ASSERT(len != 0); ASSERT(type != XFS_AG_RESV_AGFL); @@ -3469,10 +3485,9 @@ __xfs_free_extent( XFS_ERRTAG_FREE_EXTENT)) return -EIO; - pag = xfs_perag_get(mp, agno); error = xfs_free_extent_fix_freelist(tp, pag, &agbp); if (error) - goto err; + return error; agf = agbp->b_addr; if (XFS_IS_CORRUPT(mp, agbno >= mp->m_sb.sb_agblocks)) { @@ -3486,20 +3501,18 @@ __xfs_free_extent( goto err_release; } - error = xfs_free_ag_extent(tp, agbp, agno, agbno, len, oinfo, type); + error = xfs_free_ag_extent(tp, agbp, pag->pag_agno, agbno, len, oinfo, + type); if (error) goto err_release; if (skip_discard) busy_flags |= XFS_EXTENT_BUSY_SKIP_DISCARD; xfs_extent_busy_insert(tp, pag, agbno, len, busy_flags); - xfs_perag_put(pag); return 0; err_release: xfs_trans_brelse(tp, agbp); -err: - xfs_perag_put(pag); return error; } @@ -3532,15 +3545,11 @@ xfs_alloc_query_range( xfs_alloc_query_range_fn fn, void *priv) { - union xfs_btree_irec low_brec; - union xfs_btree_irec high_brec; - struct xfs_alloc_query_range_info query; + union xfs_btree_irec low_brec = { .a = *low_rec }; + union xfs_btree_irec high_brec = { .a = *high_rec }; + struct xfs_alloc_query_range_info query = { .priv = priv, .fn = fn }; ASSERT(cur->bc_btnum == XFS_BTNUM_BNO); - low_brec.a = *low_rec; - high_brec.a = *high_rec; - query.priv = priv; - query.fn = fn; return xfs_btree_query_range(cur, &low_brec, &high_brec, xfs_alloc_query_range_helper, &query); } diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h index 2c3f762dfb58..2dd93d62150f 100644 --- a/fs/xfs/libxfs/xfs_alloc.h +++ b/fs/xfs/libxfs/xfs_alloc.h @@ -130,7 +130,8 @@ xfs_alloc_vextent( int /* error */ __xfs_free_extent( struct xfs_trans *tp, /* transaction pointer */ - xfs_fsblock_t bno, /* starting block number of extent */ + struct xfs_perag *pag, + xfs_agblock_t agbno, xfs_extlen_t len, /* length of extent */ const struct xfs_owner_info *oinfo, /* extent owner */ enum xfs_ag_resv_type type, /* block reservation type */ @@ -139,12 +140,13 @@ __xfs_free_extent( static inline int xfs_free_extent( struct xfs_trans *tp, - xfs_fsblock_t bno, + struct xfs_perag *pag, + xfs_agblock_t agbno, xfs_extlen_t len, const struct xfs_owner_info *oinfo, enum xfs_ag_resv_type type) { - return __xfs_free_extent(tp, bno, len, oinfo, type, false); + return __xfs_free_extent(tp, pag, agbno, len, oinfo, type, false); } int /* error */ @@ -211,9 +213,9 @@ xfs_buf_to_agfl_bno( return bp->b_addr; } -void __xfs_free_extent_later(struct xfs_trans *tp, xfs_fsblock_t bno, +int __xfs_free_extent_later(struct xfs_trans *tp, xfs_fsblock_t bno, xfs_filblks_t len, const struct xfs_owner_info *oinfo, - bool skip_discard); + enum xfs_ag_resv_type type, bool skip_discard); /* * List of extents to be free "later". @@ -224,21 +226,27 @@ struct xfs_extent_free_item { uint64_t xefi_owner; xfs_fsblock_t xefi_startblock;/* starting fs block number */ xfs_extlen_t xefi_blockcount;/* number of blocks in extent */ + struct xfs_perag *xefi_pag; unsigned int xefi_flags; + enum xfs_ag_resv_type xefi_agresv; }; +void xfs_extent_free_get_group(struct xfs_mount *mp, + struct xfs_extent_free_item *xefi); + #define XFS_EFI_SKIP_DISCARD (1U << 0) /* don't issue discard */ #define XFS_EFI_ATTR_FORK (1U << 1) /* freeing attr fork block */ #define XFS_EFI_BMBT_BLOCK (1U << 2) /* freeing bmap btree block */ -static inline void +static inline int xfs_free_extent_later( struct xfs_trans *tp, xfs_fsblock_t bno, xfs_filblks_t len, - const struct xfs_owner_info *oinfo) + const struct xfs_owner_info *oinfo, + enum xfs_ag_resv_type type) { - __xfs_free_extent_later(tp, bno, len, oinfo, false); + return __xfs_free_extent_later(tp, bno, len, oinfo, type, false); } diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c index e28d93d232de..32d350e97e0f 100644 --- a/fs/xfs/libxfs/xfs_attr.c +++ b/fs/xfs/libxfs/xfs_attr.c @@ -421,10 +421,10 @@ xfs_attr_complete_op( bool do_replace = args->op_flags & XFS_DA_OP_REPLACE; args->op_flags &= ~XFS_DA_OP_REPLACE; - if (do_replace) { - args->attr_filter &= ~XFS_ATTR_INCOMPLETE; + args->attr_filter &= ~XFS_ATTR_INCOMPLETE; + if (do_replace) return replace_state; - } + return XFS_DAS_DONE; } diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c index d440393b40eb..54de405cbab5 100644 --- a/fs/xfs/libxfs/xfs_attr_remote.c +++ b/fs/xfs/libxfs/xfs_attr_remote.c @@ -619,7 +619,6 @@ xfs_attr_rmtval_set_blk( if (error) return error; - ASSERT(nmap == 1); ASSERT((map->br_startblock != DELAYSTARTBLOCK) && (map->br_startblock != HOLESTARTBLOCK)); diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 27d3121e6da9..14b0d230f61b 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -21,7 +21,7 @@ #include "xfs_bmap.h" #include "xfs_bmap_util.h" #include "xfs_bmap_btree.h" -#include "xfs_rtalloc.h" +#include "xfs_rtbitmap.h" #include "xfs_errortag.h" #include "xfs_error.h" #include "xfs_quota.h" @@ -572,8 +572,13 @@ xfs_bmap_btree_to_extents( cblock = XFS_BUF_TO_BLOCK(cbp); if ((error = xfs_btree_check_block(cur, cblock, 0, cbp))) return error; + xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, whichfork); - xfs_free_extent_later(cur->bc_tp, cbno, 1, &oinfo); + error = xfs_free_extent_later(cur->bc_tp, cbno, 1, &oinfo, + XFS_AG_RESV_NONE); + if (error) + return error; + ip->i_nblocks--; xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L); xfs_trans_binval(tp, cbp); @@ -1525,6 +1530,7 @@ xfs_bmap_add_extent_delay_real( if (error) goto done; } + ASSERT(da_new <= da_old); break; case BMAP_LEFT_FILLING | BMAP_RIGHT_FILLING | BMAP_LEFT_CONTIG: @@ -1554,6 +1560,7 @@ xfs_bmap_add_extent_delay_real( if (error) goto done; } + ASSERT(da_new <= da_old); break; case BMAP_LEFT_FILLING | BMAP_RIGHT_FILLING | BMAP_RIGHT_CONTIG: @@ -1587,6 +1594,7 @@ xfs_bmap_add_extent_delay_real( if (error) goto done; } + ASSERT(da_new <= da_old); break; case BMAP_LEFT_FILLING | BMAP_RIGHT_FILLING: @@ -1619,6 +1627,7 @@ xfs_bmap_add_extent_delay_real( goto done; } } + ASSERT(da_new <= da_old); break; case BMAP_LEFT_FILLING | BMAP_LEFT_CONTIG: @@ -1656,6 +1665,7 @@ xfs_bmap_add_extent_delay_real( if (error) goto done; } + ASSERT(da_new <= da_old); break; case BMAP_LEFT_FILLING: @@ -1743,6 +1753,7 @@ xfs_bmap_add_extent_delay_real( xfs_iext_update_extent(bma->ip, state, &bma->icur, &PREV); xfs_iext_next(ifp, &bma->icur); xfs_iext_update_extent(bma->ip, state, &bma->icur, &RIGHT); + ASSERT(da_new <= da_old); break; case BMAP_RIGHT_FILLING: @@ -1790,6 +1801,7 @@ xfs_bmap_add_extent_delay_real( PREV.br_blockcount = temp; xfs_iext_insert(bma->ip, &bma->icur, &PREV, state); xfs_iext_next(ifp, &bma->icur); + ASSERT(da_new <= da_old); break; case 0: @@ -1910,11 +1922,9 @@ xfs_bmap_add_extent_delay_real( } /* adjust for changes in reserved delayed indirect blocks */ - if (da_new != da_old) { - ASSERT(state == 0 || da_new < da_old); + if (da_new != da_old) error = xfs_mod_fdblocks(mp, (int64_t)(da_old - da_new), - false); - } + true); xfs_bmap_check_leaf_extents(bma->cur, bma->ip, whichfork); done: @@ -3949,20 +3959,32 @@ xfs_bmapi_reserve_delalloc( xfs_extlen_t alen; xfs_extlen_t indlen; int error; - xfs_fileoff_t aoff = off; + xfs_fileoff_t aoff; + bool use_cowextszhint = + whichfork == XFS_COW_FORK && !prealloc; +retry: /* * Cap the alloc length. Keep track of prealloc so we know whether to * tag the inode before we return. */ + aoff = off; alen = XFS_FILBLKS_MIN(len + prealloc, XFS_MAX_BMBT_EXTLEN); if (!eof) alen = XFS_FILBLKS_MIN(alen, got->br_startoff - aoff); if (prealloc && alen >= len) prealloc = alen - len; - /* Figure out the extent size, adjust alen */ - if (whichfork == XFS_COW_FORK) { + /* + * If we're targetting the COW fork but aren't creating a speculative + * posteof preallocation, try to expand the reservation to align with + * the COW extent size hint if there's sufficient free space. + * + * Unlike the data fork, the CoW cancellation functions will free all + * the reservations at inactivation, so we don't require that every + * delalloc reservation have a dirty pagecache. + */ + if (use_cowextszhint) { struct xfs_bmbt_irec prev; xfs_extlen_t extsz = xfs_get_cowextsz_hint(ip); @@ -3981,7 +4003,7 @@ xfs_bmapi_reserve_delalloc( */ error = xfs_quota_reserve_blkres(ip, alen); if (error) - return error; + goto out; /* * Split changing sb for alen and indlen since they could be coming @@ -4026,6 +4048,17 @@ out_unreserve_blocks: out_unreserve_quota: if (XFS_IS_QUOTA_ON(mp)) xfs_quota_unreserve_blkres(ip, alen); +out: + if (error == -ENOSPC || error == -EDQUOT) { + trace_xfs_delalloc_enospc(ip, off, len); + + if (prealloc || use_cowextszhint) { + /* retry without any preallocation */ + use_cowextszhint = false; + prealloc = 0; + goto retry; + } + } return error; } @@ -4108,8 +4141,10 @@ xfs_bmapi_allocate( } else { error = xfs_bmap_alloc_userdata(bma); } - if (error || bma->blkno == NULLFSBLOCK) + if (error) return error; + if (bma->blkno == NULLFSBLOCK) + return -ENOSPC; if (bma->flags & XFS_BMAPI_ZERO) { error = xfs_zero_extent(bma->ip, bma->blkno, bma->length); @@ -4289,6 +4324,15 @@ xfs_bmapi_finish( * extent state if necessary. Details behaviour is controlled by the flags * parameter. Only allocates blocks from a single allocation group, to avoid * locking problems. + * + * Returns 0 on success and places the extent mappings in mval. nmaps is used + * as an input/output parameter where the caller specifies the maximum number + * of mappings that may be returned and xfs_bmapi_write passes back the number + * of mappings (including existing mappings) it found. + * + * Returns a negative error code on failure, including -ENOSPC when it could not + * allocate any blocks and -ENOSR when it did allocate blocks to convert a + * delalloc range, but those blocks were before the passed in range. */ int xfs_bmapi_write( @@ -4416,10 +4460,16 @@ xfs_bmapi_write( ASSERT(len > 0); ASSERT(bma.length > 0); error = xfs_bmapi_allocate(&bma); - if (error) + if (error) { + /* + * If we already allocated space in a previous + * iteration return what we go so far when + * running out of space. + */ + if (error == -ENOSPC && bma.nallocs) + break; goto error0; - if (bma.blkno == NULLFSBLOCK) - break; + } /* * If this is a CoW allocation, record the data in @@ -4457,7 +4507,6 @@ xfs_bmapi_write( if (!xfs_iext_next_extent(ifp, &bma.icur, &bma.got)) eof = true; } - *nmap = n; error = xfs_bmap_btree_to_extents(tp, ip, bma.cur, &bma.logflags, whichfork); @@ -4468,7 +4517,22 @@ xfs_bmapi_write( ifp->if_nextents > XFS_IFORK_MAXEXT(ip, whichfork)); xfs_bmapi_finish(&bma, whichfork, 0); xfs_bmap_validate_ret(orig_bno, orig_len, orig_flags, orig_mval, - orig_nmap, *nmap); + orig_nmap, n); + + /* + * When converting delayed allocations, xfs_bmapi_allocate ignores + * the passed in bno and always converts from the start of the found + * delalloc extent. + * + * To avoid a successful return with *nmap set to 0, return the magic + * -ENOSR error code for this particular case so that the caller can + * handle it. + */ + if (!n) { + ASSERT(bma.nallocs >= *nmap); + return -ENOSR; + } + *nmap = n; return 0; error0: xfs_bmapi_finish(&bma, whichfork, error); @@ -4481,8 +4545,8 @@ error0: * invocations to allocate the target offset if a large enough physical extent * is not available. */ -int -xfs_bmapi_convert_delalloc( +static int +xfs_bmapi_convert_one_delalloc( struct xfs_inode *ip, int whichfork, xfs_off_t offset, @@ -4539,7 +4603,8 @@ xfs_bmapi_convert_delalloc( if (!isnullstartblock(bma.got.br_startblock)) { xfs_bmbt_to_iomap(ip, iomap, &bma.got, 0, flags, xfs_iomap_inode_sequence(ip, flags)); - *seq = READ_ONCE(ifp->if_seq); + if (seq) + *seq = READ_ONCE(ifp->if_seq); goto out_trans_cancel; } @@ -4575,9 +4640,6 @@ xfs_bmapi_convert_delalloc( if (error) goto out_finish; - error = -ENOSPC; - if (WARN_ON_ONCE(bma.blkno == NULLFSBLOCK)) - goto out_finish; error = -EFSCORRUPTED; if (WARN_ON_ONCE(!xfs_valid_startblock(ip, bma.got.br_startblock))) goto out_finish; @@ -4588,7 +4650,8 @@ xfs_bmapi_convert_delalloc( ASSERT(!isnullstartblock(bma.got.br_startblock)); xfs_bmbt_to_iomap(ip, iomap, &bma.got, 0, flags, xfs_iomap_inode_sequence(ip, flags)); - *seq = READ_ONCE(ifp->if_seq); + if (seq) + *seq = READ_ONCE(ifp->if_seq); if (whichfork == XFS_COW_FORK) xfs_refcount_alloc_cow_extent(tp, bma.blkno, bma.length); @@ -4611,6 +4674,36 @@ out_trans_cancel: return error; } +/* + * Pass in a dellalloc extent and convert it to real extents, return the real + * extent that maps offset_fsb in iomap. + */ +int +xfs_bmapi_convert_delalloc( + struct xfs_inode *ip, + int whichfork, + loff_t offset, + struct iomap *iomap, + unsigned int *seq) +{ + int error; + + /* + * Attempt to allocate whatever delalloc extent currently backs offset + * and put the result into iomap. Allocate in a loop because it may + * take several attempts to allocate real blocks for a contiguous + * delalloc extent if free space is sufficiently fragmented. + */ + do { + error = xfs_bmapi_convert_one_delalloc(ip, whichfork, offset, + iomap, seq); + if (error) + return error; + } while (iomap->offset + iomap->length <= offset); + + return 0; +} + int xfs_bmapi_remap( struct xfs_trans *tp, @@ -4994,7 +5087,6 @@ xfs_bmap_del_extent_real( xfs_fileoff_t del_endoff; /* first offset past del */ int do_fx; /* free extent at end of routine */ int error; /* error return value */ - int flags = 0;/* inode logging flags */ struct xfs_bmbt_irec got; /* current extent entry */ xfs_fileoff_t got_endoff; /* first offset past got */ int i; /* temp state */ @@ -5007,6 +5099,8 @@ xfs_bmap_del_extent_real( uint32_t state = xfs_bmap_fork_to_state(whichfork); struct xfs_bmbt_irec old; + *logflagsp = 0; + mp = ip->i_mount; XFS_STATS_INC(mp, xs_del_exlist); @@ -5019,7 +5113,6 @@ xfs_bmap_del_extent_real( ASSERT(got_endoff >= del_endoff); ASSERT(!isnullstartblock(got.br_startblock)); qfield = 0; - error = 0; /* * If it's the case where the directory code is running with no block @@ -5035,13 +5128,13 @@ xfs_bmap_del_extent_real( del->br_startoff > got.br_startoff && del_endoff < got_endoff) return -ENOSPC; - flags = XFS_ILOG_CORE; + *logflagsp = XFS_ILOG_CORE; if (whichfork == XFS_DATA_FORK && XFS_IS_REALTIME_INODE(ip)) { if (!(bflags & XFS_BMAPI_REMAP)) { error = xfs_rtfree_blocks(tp, del->br_startblock, del->br_blockcount); if (error) - goto done; + return error; } do_fx = 0; @@ -5056,11 +5149,9 @@ xfs_bmap_del_extent_real( if (cur) { error = xfs_bmbt_lookup_eq(cur, &got, &i); if (error) - goto done; - if (XFS_IS_CORRUPT(mp, i != 1)) { - error = -EFSCORRUPTED; - goto done; - } + return error; + if (XFS_IS_CORRUPT(mp, i != 1)) + return -EFSCORRUPTED; } if (got.br_startoff == del->br_startoff) @@ -5077,17 +5168,15 @@ xfs_bmap_del_extent_real( xfs_iext_prev(ifp, icur); ifp->if_nextents--; - flags |= XFS_ILOG_CORE; + *logflagsp |= XFS_ILOG_CORE; if (!cur) { - flags |= xfs_ilog_fext(whichfork); + *logflagsp |= xfs_ilog_fext(whichfork); break; } if ((error = xfs_btree_delete(cur, &i))) - goto done; - if (XFS_IS_CORRUPT(mp, i != 1)) { - error = -EFSCORRUPTED; - goto done; - } + return error; + if (XFS_IS_CORRUPT(mp, i != 1)) + return -EFSCORRUPTED; break; case BMAP_LEFT_FILLING: /* @@ -5098,12 +5187,12 @@ xfs_bmap_del_extent_real( got.br_blockcount -= del->br_blockcount; xfs_iext_update_extent(ip, state, icur, &got); if (!cur) { - flags |= xfs_ilog_fext(whichfork); + *logflagsp |= xfs_ilog_fext(whichfork); break; } error = xfs_bmbt_update(cur, &got); if (error) - goto done; + return error; break; case BMAP_RIGHT_FILLING: /* @@ -5112,12 +5201,12 @@ xfs_bmap_del_extent_real( got.br_blockcount -= del->br_blockcount; xfs_iext_update_extent(ip, state, icur, &got); if (!cur) { - flags |= xfs_ilog_fext(whichfork); + *logflagsp |= xfs_ilog_fext(whichfork); break; } error = xfs_bmbt_update(cur, &got); if (error) - goto done; + return error; break; case 0: /* @@ -5134,18 +5223,18 @@ xfs_bmap_del_extent_real( new.br_state = got.br_state; new.br_startblock = del_endblock; - flags |= XFS_ILOG_CORE; + *logflagsp |= XFS_ILOG_CORE; if (cur) { error = xfs_bmbt_update(cur, &got); if (error) - goto done; + return error; error = xfs_btree_increment(cur, 0, &i); if (error) - goto done; + return error; cur->bc_rec.b = new; error = xfs_btree_insert(cur, &i); if (error && error != -ENOSPC) - goto done; + return error; /* * If get no-space back from btree insert, it tried a * split, and we have a zero block reservation. Fix up @@ -5158,33 +5247,28 @@ xfs_bmap_del_extent_real( */ error = xfs_bmbt_lookup_eq(cur, &got, &i); if (error) - goto done; - if (XFS_IS_CORRUPT(mp, i != 1)) { - error = -EFSCORRUPTED; - goto done; - } + return error; + if (XFS_IS_CORRUPT(mp, i != 1)) + return -EFSCORRUPTED; /* * Update the btree record back * to the original value. */ error = xfs_bmbt_update(cur, &old); if (error) - goto done; + return error; /* * Reset the extent record back * to the original value. */ xfs_iext_update_extent(ip, state, icur, &old); - flags = 0; - error = -ENOSPC; - goto done; - } - if (XFS_IS_CORRUPT(mp, i != 1)) { - error = -EFSCORRUPTED; - goto done; + *logflagsp = 0; + return -ENOSPC; } + if (XFS_IS_CORRUPT(mp, i != 1)) + return -EFSCORRUPTED; } else - flags |= xfs_ilog_fext(whichfork); + *logflagsp |= xfs_ilog_fext(whichfork); ifp->if_nextents++; xfs_iext_next(ifp, icur); @@ -5202,10 +5286,13 @@ xfs_bmap_del_extent_real( if (xfs_is_reflink_inode(ip) && whichfork == XFS_DATA_FORK) { xfs_refcount_decrease_extent(tp, del); } else { - __xfs_free_extent_later(tp, del->br_startblock, + error = __xfs_free_extent_later(tp, del->br_startblock, del->br_blockcount, NULL, - (bflags & XFS_BMAPI_NODISCARD) || - del->br_state == XFS_EXT_UNWRITTEN); + XFS_AG_RESV_NONE, + ((bflags & XFS_BMAPI_NODISCARD) || + del->br_state == XFS_EXT_UNWRITTEN)); + if (error) + return error; } } @@ -5220,9 +5307,7 @@ xfs_bmap_del_extent_real( if (qfield && !(bflags & XFS_BMAPI_REMAP)) xfs_trans_mod_dquot_byino(tp, ip, qfield, (long)-nblks); -done: - *logflagsp = flags; - return error; + return 0; } /* @@ -6119,39 +6204,37 @@ xfs_bmap_unmap_extent( int xfs_bmap_finish_one( struct xfs_trans *tp, - struct xfs_inode *ip, - enum xfs_bmap_intent_type type, - int whichfork, - xfs_fileoff_t startoff, - xfs_fsblock_t startblock, - xfs_filblks_t *blockcount, - xfs_exntst_t state) + struct xfs_bmap_intent *bi) { + struct xfs_bmbt_irec *bmap = &bi->bi_bmap; int error = 0; ASSERT(tp->t_firstblock == NULLFSBLOCK); trace_xfs_bmap_deferred(tp->t_mountp, - XFS_FSB_TO_AGNO(tp->t_mountp, startblock), type, - XFS_FSB_TO_AGBNO(tp->t_mountp, startblock), - ip->i_ino, whichfork, startoff, *blockcount, state); + XFS_FSB_TO_AGNO(tp->t_mountp, bmap->br_startblock), + bi->bi_type, + XFS_FSB_TO_AGBNO(tp->t_mountp, bmap->br_startblock), + bi->bi_owner->i_ino, bi->bi_whichfork, + bmap->br_startoff, bmap->br_blockcount, + bmap->br_state); - if (WARN_ON_ONCE(whichfork != XFS_DATA_FORK)) + if (WARN_ON_ONCE(bi->bi_whichfork != XFS_DATA_FORK)) return -EFSCORRUPTED; if (XFS_TEST_ERROR(false, tp->t_mountp, XFS_ERRTAG_BMAP_FINISH_ONE)) return -EIO; - switch (type) { + switch (bi->bi_type) { case XFS_BMAP_MAP: - error = xfs_bmapi_remap(tp, ip, startoff, *blockcount, - startblock, 0); - *blockcount = 0; + error = xfs_bmapi_remap(tp, bi->bi_owner, bmap->br_startoff, + bmap->br_blockcount, bmap->br_startblock, 0); + bmap->br_blockcount = 0; break; case XFS_BMAP_UNMAP: - error = __xfs_bunmapi(tp, ip, startoff, blockcount, - XFS_BMAPI_REMAP, 1); + error = __xfs_bunmapi(tp, bi->bi_owner, bmap->br_startoff, + &bmap->br_blockcount, XFS_BMAPI_REMAP, 1); break; default: ASSERT(0); diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h index 08c16e4edc0f..524912f276f8 100644 --- a/fs/xfs/libxfs/xfs_bmap.h +++ b/fs/xfs/libxfs/xfs_bmap.h @@ -236,10 +236,7 @@ struct xfs_bmap_intent { struct xfs_bmbt_irec bi_bmap; }; -int xfs_bmap_finish_one(struct xfs_trans *tp, struct xfs_inode *ip, - enum xfs_bmap_intent_type type, int whichfork, - xfs_fileoff_t startoff, xfs_fsblock_t startblock, - xfs_filblks_t *blockcount, xfs_exntst_t state); +int xfs_bmap_finish_one(struct xfs_trans *tp, struct xfs_bmap_intent *bi); void xfs_bmap_map_extent(struct xfs_trans *tp, struct xfs_inode *ip, struct xfs_bmbt_irec *imap); void xfs_bmap_unmap_extent(struct xfs_trans *tp, struct xfs_inode *ip, diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c index 18de4fbfef4e..57f401f2492d 100644 --- a/fs/xfs/libxfs/xfs_bmap_btree.c +++ b/fs/xfs/libxfs/xfs_bmap_btree.c @@ -285,11 +285,15 @@ xfs_bmbt_free_block( struct xfs_trans *tp = cur->bc_tp; xfs_fsblock_t fsbno = XFS_DADDR_TO_FSB(mp, xfs_buf_daddr(bp)); struct xfs_owner_info oinfo; + int error; xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, cur->bc_ino.whichfork); - xfs_free_extent_later(cur->bc_tp, fsbno, 1, &oinfo); - ip->i_nblocks--; + error = xfs_free_extent_later(cur->bc_tp, fsbno, 1, &oinfo, + XFS_AG_RESV_NONE); + if (error) + return error; + ip->i_nblocks--; xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L); return 0; diff --git a/fs/xfs/libxfs/xfs_btree_staging.c b/fs/xfs/libxfs/xfs_btree_staging.c index dd75e208b543..29e3f8ccb185 100644 --- a/fs/xfs/libxfs/xfs_btree_staging.c +++ b/fs/xfs/libxfs/xfs_btree_staging.c @@ -342,9 +342,7 @@ xfs_btree_bload_drop_buf( if (*bpp == NULL) return; - if (!xfs_buf_delwri_queue(*bpp, buffers_list)) - ASSERT(0); - + xfs_buf_delwri_queue_here(*bpp, buffers_list); xfs_buf_relse(*bpp); *bpp = NULL; } diff --git a/fs/xfs/libxfs/xfs_btree_staging.h b/fs/xfs/libxfs/xfs_btree_staging.h index f0d2976050ae..5f638f711246 100644 --- a/fs/xfs/libxfs/xfs_btree_staging.h +++ b/fs/xfs/libxfs/xfs_btree_staging.h @@ -37,12 +37,6 @@ struct xbtree_ifakeroot { /* Number of bytes available for this fork in the inode. */ unsigned int if_fork_size; - - /* Fork format. */ - unsigned int if_format; - - /* Number of records. */ - unsigned int if_extents; }; /* Cursor interactions with fake roots for inode-rooted btrees. */ diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c index e576560b46e9..12e3cca804b7 100644 --- a/fs/xfs/libxfs/xfs_da_btree.c +++ b/fs/xfs/libxfs/xfs_da_btree.c @@ -2158,8 +2158,8 @@ xfs_da_grow_inode_int( struct xfs_inode *dp = args->dp; int w = args->whichfork; xfs_rfsblock_t nblks = dp->i_nblocks; - struct xfs_bmbt_irec map, *mapp; - int nmap, error, got, i, mapi; + struct xfs_bmbt_irec map, *mapp = ↦ + int nmap, error, got, i, mapi = 1; /* * Find a spot in the file space to put the new block. @@ -2175,14 +2175,7 @@ xfs_da_grow_inode_int( error = xfs_bmapi_write(tp, dp, *bno, count, xfs_bmapi_aflag(w)|XFS_BMAPI_METADATA|XFS_BMAPI_CONTIG, args->total, &map, &nmap); - if (error) - return error; - - ASSERT(nmap <= 1); - if (nmap == 1) { - mapp = ↦ - mapi = 1; - } else if (nmap == 0 && count > 1) { + if (error == -ENOSPC && count > 1) { xfs_fileoff_t b; int c; @@ -2199,16 +2192,13 @@ xfs_da_grow_inode_int( args->total, &mapp[mapi], &nmap); if (error) goto out_free_map; - if (nmap < 1) - break; mapi += nmap; b = mapp[mapi - 1].br_startoff + mapp[mapi - 1].br_blockcount; } - } else { - mapi = 0; - mapp = NULL; } + if (error) + goto out_free_map; /* * Count the blocks we got, make sure it matches the total. @@ -2316,10 +2306,17 @@ xfs_da3_swap_lastblock( return error; /* * Copy the last block into the dead buffer and log it. + * On CRC-enabled file systems, also update the stamped in blkno. */ memcpy(dead_buf->b_addr, last_buf->b_addr, args->geo->blksize); + if (xfs_has_crc(mp)) { + struct xfs_da3_blkinfo *da3 = dead_buf->b_addr; + + da3->blkno = cpu_to_be64(xfs_buf_daddr(dead_buf)); + } xfs_trans_log_buf(tp, dead_buf, 0, args->geo->blksize - 1); dead_info = dead_buf->b_addr; + /* * Get values from the moved block. */ diff --git a/fs/xfs/libxfs/xfs_dir2_data.c b/fs/xfs/libxfs/xfs_dir2_data.c index dbcf58979a59..e1d5da6d8d4a 100644 --- a/fs/xfs/libxfs/xfs_dir2_data.c +++ b/fs/xfs/libxfs/xfs_dir2_data.c @@ -177,6 +177,14 @@ __xfs_dir3_data_check( while (offset < end) { struct xfs_dir2_data_unused *dup = bp->b_addr + offset; struct xfs_dir2_data_entry *dep = bp->b_addr + offset; + unsigned int reclen; + + /* + * Are the remaining bytes large enough to hold an + * unused entry? + */ + if (offset > end - xfs_dir2_data_unusedsize(1)) + return __this_address; /* * If it's unused, look for the space in the bestfree table. @@ -186,9 +194,13 @@ __xfs_dir3_data_check( if (be16_to_cpu(dup->freetag) == XFS_DIR2_DATA_FREE_TAG) { xfs_failaddr_t fa; + reclen = xfs_dir2_data_unusedsize( + be16_to_cpu(dup->length)); if (lastfree != 0) return __this_address; - if (offset + be16_to_cpu(dup->length) > end) + if (be16_to_cpu(dup->length) != reclen) + return __this_address; + if (offset + reclen > end) return __this_address; if (be16_to_cpu(*xfs_dir2_data_unused_tag_p(dup)) != offset) @@ -206,10 +218,18 @@ __xfs_dir3_data_check( be16_to_cpu(bf[2].length)) return __this_address; } - offset += be16_to_cpu(dup->length); + offset += reclen; lastfree = 1; continue; } + + /* + * This is not an unused entry. Are the remaining bytes + * large enough for a dirent with a single-byte name? + */ + if (offset > end - xfs_dir2_data_entsize(mp, 1)) + return __this_address; + /* * It's a real entry. Validate the fields. * If this is a block directory then make sure it's @@ -218,9 +238,10 @@ __xfs_dir3_data_check( */ if (dep->namelen == 0) return __this_address; - if (!xfs_verify_dir_ino(mp, be64_to_cpu(dep->inumber))) + reclen = xfs_dir2_data_entsize(mp, dep->namelen); + if (offset + reclen > end) return __this_address; - if (offset + xfs_dir2_data_entsize(mp, dep->namelen) > end) + if (!xfs_verify_dir_ino(mp, be64_to_cpu(dep->inumber))) return __this_address; if (be16_to_cpu(*xfs_dir2_data_entry_tag_p(mp, dep)) != offset) return __this_address; @@ -244,7 +265,7 @@ __xfs_dir3_data_check( if (i >= be32_to_cpu(btp->count)) return __this_address; } - offset += xfs_dir2_data_entsize(mp, dep->namelen); + offset += reclen; } /* * Need to have seen all the entries and all the bestfree slots. diff --git a/fs/xfs/libxfs/xfs_dir2_priv.h b/fs/xfs/libxfs/xfs_dir2_priv.h index 7404a9ff1a92..9046d08554e9 100644 --- a/fs/xfs/libxfs/xfs_dir2_priv.h +++ b/fs/xfs/libxfs/xfs_dir2_priv.h @@ -188,6 +188,13 @@ extern int xfs_readdir(struct xfs_trans *tp, struct xfs_inode *dp, struct dir_context *ctx, size_t bufsize); static inline unsigned int +xfs_dir2_data_unusedsize( + unsigned int len) +{ + return round_up(len, XFS_DIR2_DATA_ALIGN); +} + +static inline unsigned int xfs_dir2_data_entsize( struct xfs_mount *mp, unsigned int namelen) diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h index 371dc07233e0..20acb8573d7a 100644 --- a/fs/xfs/libxfs/xfs_format.h +++ b/fs/xfs/libxfs/xfs_format.h @@ -98,7 +98,7 @@ typedef struct xfs_sb { uint32_t sb_blocksize; /* logical block size, bytes */ xfs_rfsblock_t sb_dblocks; /* number of data blocks */ xfs_rfsblock_t sb_rblocks; /* number of realtime blocks */ - xfs_rtblock_t sb_rextents; /* number of realtime extents */ + xfs_rtbxlen_t sb_rextents; /* number of realtime extents */ uuid_t sb_uuid; /* user-visible file system unique id */ xfs_fsblock_t sb_logstart; /* starting block of log if internal */ xfs_ino_t sb_rootino; /* root inode number */ diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index 120dbec16f5c..d1472cbd48ff 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -1827,7 +1827,7 @@ xfs_dialloc( * might be sparse and only free the regions that are allocated as part of the * chunk. */ -STATIC void +static int xfs_difree_inode_chunk( struct xfs_trans *tp, xfs_agnumber_t agno, @@ -1844,10 +1844,10 @@ xfs_difree_inode_chunk( if (!xfs_inobt_issparse(rec->ir_holemask)) { /* not sparse, calculate extent info directly */ - xfs_free_extent_later(tp, XFS_AGB_TO_FSB(mp, agno, sagbno), - M_IGEO(mp)->ialloc_blks, - &XFS_RMAP_OINFO_INODES); - return; + return xfs_free_extent_later(tp, + XFS_AGB_TO_FSB(mp, agno, sagbno), + M_IGEO(mp)->ialloc_blks, &XFS_RMAP_OINFO_INODES, + XFS_AG_RESV_NONE); } /* holemask is only 16-bits (fits in an unsigned long) */ @@ -1864,6 +1864,8 @@ xfs_difree_inode_chunk( XFS_INOBT_HOLEMASK_BITS); nextbit = startidx + 1; while (startidx < XFS_INOBT_HOLEMASK_BITS) { + int error; + nextbit = find_next_zero_bit(holemask, XFS_INOBT_HOLEMASK_BITS, nextbit); /* @@ -1889,8 +1891,11 @@ xfs_difree_inode_chunk( ASSERT(agbno % mp->m_sb.sb_spino_align == 0); ASSERT(contigblk % mp->m_sb.sb_spino_align == 0); - xfs_free_extent_later(tp, XFS_AGB_TO_FSB(mp, agno, agbno), - contigblk, &XFS_RMAP_OINFO_INODES); + error = xfs_free_extent_later(tp, + XFS_AGB_TO_FSB(mp, agno, agbno), contigblk, + &XFS_RMAP_OINFO_INODES, XFS_AG_RESV_NONE); + if (error) + return error; /* reset range to current bit and carry on... */ startidx = endidx = nextbit; @@ -1898,6 +1903,7 @@ xfs_difree_inode_chunk( next: nextbit++; } + return 0; } STATIC int @@ -1998,7 +2004,9 @@ xfs_difree_inobt( goto error0; } - xfs_difree_inode_chunk(tp, pag->pag_agno, &rec); + error = xfs_difree_inode_chunk(tp, pag->pag_agno, &rec); + if (error) + goto error0; } else { xic->deleted = false; diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c index 8c83e265770c..7125447cde1a 100644 --- a/fs/xfs/libxfs/xfs_ialloc_btree.c +++ b/fs/xfs/libxfs/xfs_ialloc_btree.c @@ -156,9 +156,11 @@ __xfs_inobt_free_block( struct xfs_buf *bp, enum xfs_ag_resv_type resv) { + xfs_fsblock_t fsbno; + xfs_inobt_mod_blockcount(cur, -1); - return xfs_free_extent(cur->bc_tp, - XFS_DADDR_TO_FSB(cur->bc_mp, xfs_buf_daddr(bp)), 1, + fsbno = XFS_DADDR_TO_FSB(cur->bc_mp, xfs_buf_daddr(bp)); + return xfs_free_extent_later(cur->bc_tp, fsbno, 1, &XFS_RMAP_OINFO_INOBT, resv); } diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c index 601b05ca5fc2..3c611c8ac158 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.c +++ b/fs/xfs/libxfs/xfs_inode_buf.c @@ -365,17 +365,40 @@ xfs_dinode_verify_fork( /* * For fork types that can contain local data, check that the fork * format matches the size of local data contained within the fork. - * - * For all types, check that when the size says the should be in extent - * or btree format, the inode isn't claiming it is in local format. */ if (whichfork == XFS_DATA_FORK) { - if (S_ISDIR(mode) || S_ISLNK(mode)) { + /* + * A directory small enough to fit in the inode must be stored + * in local format. The directory sf <-> extents conversion + * code updates the directory size accordingly. Directories + * being truncated have zero size and are not subject to this + * check. + */ + if (S_ISDIR(mode)) { + if (dip->di_size && + be64_to_cpu(dip->di_size) <= fork_size && + fork_format != XFS_DINODE_FMT_LOCAL) + return __this_address; + } + + /* + * A symlink with a target small enough to fit in the inode can + * be stored in extents format if xattrs were added (thus + * converting the data fork from shortform to remote format) + * and then removed. + */ + if (S_ISLNK(mode)) { if (be64_to_cpu(dip->di_size) <= fork_size && + fork_format != XFS_DINODE_FMT_EXTENTS && fork_format != XFS_DINODE_FMT_LOCAL) return __this_address; } + /* + * For all types, check that when the size says the fork should + * be in extent or btree format, the inode isn't claiming to be + * in local format. + */ if (be64_to_cpu(dip->di_size) > fork_size && fork_format == XFS_DINODE_FMT_LOCAL) return __this_address; @@ -491,9 +514,19 @@ xfs_dinode_verify( if (mode && xfs_mode_to_ftype(mode) == XFS_DIR3_FT_UNKNOWN) return __this_address; - /* No zero-length symlinks/dirs. */ - if ((S_ISLNK(mode) || S_ISDIR(mode)) && di_size == 0) - return __this_address; + /* + * No zero-length symlinks/dirs unless they're unlinked and hence being + * inactivated. + */ + if ((S_ISLNK(mode) || S_ISDIR(mode)) && di_size == 0) { + if (dip->di_version > 1) { + if (dip->di_nlink) + return __this_address; + } else { + if (dip->di_onlink) + return __this_address; + } + } fa = xfs_dinode_verify_nrext64(mp, dip); if (fa) diff --git a/fs/xfs/libxfs/xfs_log_recover.h b/fs/xfs/libxfs/xfs_log_recover.h index 2420865f3007..a5100a11faf9 100644 --- a/fs/xfs/libxfs/xfs_log_recover.h +++ b/fs/xfs/libxfs/xfs_log_recover.h @@ -131,4 +131,26 @@ void xlog_check_buf_cancel_table(struct xlog *log); #define xlog_check_buf_cancel_table(log) do { } while (0) #endif +/* + * Transform a regular reservation into one suitable for recovery of a log + * intent item. + * + * Intent recovery only runs a single step of the transaction chain and defers + * the rest to a separate transaction. Therefore, we reduce logcount to 1 here + * to avoid livelocks if the log grant space is nearly exhausted due to the + * recovered intent pinning the tail. Keep the same logflags to avoid tripping + * asserts elsewhere. Struct copies abound below. + */ +static inline struct xfs_trans_res +xlog_recover_resv(const struct xfs_trans_res *r) +{ + struct xfs_trans_res ret = { + .tr_logres = r->tr_logres, + .tr_logcount = 1, + .tr_logflags = r->tr_logflags, + }; + + return ret; +} + #endif /* __XFS_LOG_RECOVER_H__ */ diff --git a/fs/xfs/libxfs/xfs_quota_defs.h b/fs/xfs/libxfs/xfs_quota_defs.h index cb035da3f990..fb05f44f6c75 100644 --- a/fs/xfs/libxfs/xfs_quota_defs.h +++ b/fs/xfs/libxfs/xfs_quota_defs.h @@ -56,7 +56,7 @@ typedef uint8_t xfs_dqtype_t; * And, of course, we also need to take into account the dquot log format item * used to describe each dquot. */ -#define XFS_DQUOT_LOGRES(mp) \ +#define XFS_DQUOT_LOGRES \ ((sizeof(struct xfs_dq_logformat) + sizeof(struct xfs_disk_dquot)) * 6) #define XFS_IS_QUOTA_ON(mp) ((mp)->m_qflags & XFS_ALL_QUOTA_ACCT) diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c index 6f7ed9288fe4..7e16e76fd2e1 100644 --- a/fs/xfs/libxfs/xfs_refcount.c +++ b/fs/xfs/libxfs/xfs_refcount.c @@ -1129,8 +1129,11 @@ xfs_refcount_adjust_extents( fsbno = XFS_AGB_TO_FSB(cur->bc_mp, cur->bc_ag.pag->pag_agno, tmp.rc_startblock); - xfs_free_extent_later(cur->bc_tp, fsbno, - tmp.rc_blockcount, NULL); + error = xfs_free_extent_later(cur->bc_tp, fsbno, + tmp.rc_blockcount, NULL, + XFS_AG_RESV_NONE); + if (error) + goto out_error; } (*agbno) += tmp.rc_blockcount; @@ -1188,8 +1191,11 @@ xfs_refcount_adjust_extents( fsbno = XFS_AGB_TO_FSB(cur->bc_mp, cur->bc_ag.pag->pag_agno, ext.rc_startblock); - xfs_free_extent_later(cur->bc_tp, fsbno, - ext.rc_blockcount, NULL); + error = xfs_free_extent_later(cur->bc_tp, fsbno, + ext.rc_blockcount, NULL, + XFS_AG_RESV_NONE); + if (error) + goto out_error; } skip: @@ -1213,37 +1219,33 @@ out_error: STATIC int xfs_refcount_adjust( struct xfs_btree_cur *cur, - xfs_agblock_t agbno, - xfs_extlen_t aglen, - xfs_agblock_t *new_agbno, - xfs_extlen_t *new_aglen, + xfs_agblock_t *agbno, + xfs_extlen_t *aglen, enum xfs_refc_adjust_op adj) { bool shape_changed; int shape_changes = 0; int error; - *new_agbno = agbno; - *new_aglen = aglen; if (adj == XFS_REFCOUNT_ADJUST_INCREASE) - trace_xfs_refcount_increase(cur->bc_mp, cur->bc_ag.pag->pag_agno, - agbno, aglen); + trace_xfs_refcount_increase(cur->bc_mp, + cur->bc_ag.pag->pag_agno, *agbno, *aglen); else - trace_xfs_refcount_decrease(cur->bc_mp, cur->bc_ag.pag->pag_agno, - agbno, aglen); + trace_xfs_refcount_decrease(cur->bc_mp, + cur->bc_ag.pag->pag_agno, *agbno, *aglen); /* * Ensure that no rcextents cross the boundary of the adjustment range. */ error = xfs_refcount_split_extent(cur, XFS_REFC_DOMAIN_SHARED, - agbno, &shape_changed); + *agbno, &shape_changed); if (error) goto out_error; if (shape_changed) shape_changes++; error = xfs_refcount_split_extent(cur, XFS_REFC_DOMAIN_SHARED, - agbno + aglen, &shape_changed); + *agbno + *aglen, &shape_changed); if (error) goto out_error; if (shape_changed) @@ -1253,7 +1255,7 @@ xfs_refcount_adjust( * Try to merge with the left or right extents of the range. */ error = xfs_refcount_merge_extents(cur, XFS_REFC_DOMAIN_SHARED, - new_agbno, new_aglen, adj, &shape_changed); + agbno, aglen, adj, &shape_changed); if (error) goto out_error; if (shape_changed) @@ -1262,7 +1264,7 @@ xfs_refcount_adjust( cur->bc_ag.refc.shape_changes++; /* Now that we've taken care of the ends, adjust the middle extents */ - error = xfs_refcount_adjust_extents(cur, new_agbno, new_aglen, adj); + error = xfs_refcount_adjust_extents(cur, agbno, aglen, adj); if (error) goto out_error; @@ -1298,21 +1300,20 @@ xfs_refcount_finish_one_cleanup( static inline int xfs_refcount_continue_op( struct xfs_btree_cur *cur, - xfs_fsblock_t startblock, - xfs_agblock_t new_agbno, - xfs_extlen_t new_len, - xfs_fsblock_t *new_fsbno) + struct xfs_refcount_intent *ri, + xfs_agblock_t new_agbno) { struct xfs_mount *mp = cur->bc_mp; struct xfs_perag *pag = cur->bc_ag.pag; - if (XFS_IS_CORRUPT(mp, !xfs_verify_agbext(pag, new_agbno, new_len))) + if (XFS_IS_CORRUPT(mp, !xfs_verify_agbext(pag, new_agbno, + ri->ri_blockcount))) return -EFSCORRUPTED; - *new_fsbno = XFS_AGB_TO_FSB(mp, pag->pag_agno, new_agbno); + ri->ri_startblock = XFS_AGB_TO_FSB(mp, pag->pag_agno, new_agbno); - ASSERT(xfs_verify_fsbext(mp, *new_fsbno, new_len)); - ASSERT(pag->pag_agno == XFS_FSB_TO_AGNO(mp, *new_fsbno)); + ASSERT(xfs_verify_fsbext(mp, ri->ri_startblock, ri->ri_blockcount)); + ASSERT(pag->pag_agno == XFS_FSB_TO_AGNO(mp, ri->ri_startblock)); return 0; } @@ -1327,11 +1328,7 @@ xfs_refcount_continue_op( int xfs_refcount_finish_one( struct xfs_trans *tp, - enum xfs_refcount_intent_type type, - xfs_fsblock_t startblock, - xfs_extlen_t blockcount, - xfs_fsblock_t *new_fsb, - xfs_extlen_t *new_len, + struct xfs_refcount_intent *ri, struct xfs_btree_cur **pcur) { struct xfs_mount *mp = tp->t_mountp; @@ -1339,17 +1336,16 @@ xfs_refcount_finish_one( struct xfs_buf *agbp = NULL; int error = 0; xfs_agblock_t bno; - xfs_agblock_t new_agbno; unsigned long nr_ops = 0; int shape_changes = 0; struct xfs_perag *pag; - pag = xfs_perag_get(mp, XFS_FSB_TO_AGNO(mp, startblock)); - bno = XFS_FSB_TO_AGBNO(mp, startblock); + pag = xfs_perag_get(mp, XFS_FSB_TO_AGNO(mp, ri->ri_startblock)); + bno = XFS_FSB_TO_AGBNO(mp, ri->ri_startblock); - trace_xfs_refcount_deferred(mp, XFS_FSB_TO_AGNO(mp, startblock), - type, XFS_FSB_TO_AGBNO(mp, startblock), - blockcount); + trace_xfs_refcount_deferred(mp, XFS_FSB_TO_AGNO(mp, ri->ri_startblock), + ri->ri_type, XFS_FSB_TO_AGBNO(mp, ri->ri_startblock), + ri->ri_blockcount); if (XFS_TEST_ERROR(false, mp, XFS_ERRTAG_REFCOUNT_FINISH_ONE)) { error = -EIO; @@ -1380,42 +1376,42 @@ xfs_refcount_finish_one( } *pcur = rcur; - switch (type) { + switch (ri->ri_type) { case XFS_REFCOUNT_INCREASE: - error = xfs_refcount_adjust(rcur, bno, blockcount, &new_agbno, - new_len, XFS_REFCOUNT_ADJUST_INCREASE); + error = xfs_refcount_adjust(rcur, &bno, &ri->ri_blockcount, + XFS_REFCOUNT_ADJUST_INCREASE); if (error) goto out_drop; - if (*new_len > 0) - error = xfs_refcount_continue_op(rcur, startblock, - new_agbno, *new_len, new_fsb); + if (ri->ri_blockcount > 0) + error = xfs_refcount_continue_op(rcur, ri, bno); break; case XFS_REFCOUNT_DECREASE: - error = xfs_refcount_adjust(rcur, bno, blockcount, &new_agbno, - new_len, XFS_REFCOUNT_ADJUST_DECREASE); + error = xfs_refcount_adjust(rcur, &bno, &ri->ri_blockcount, + XFS_REFCOUNT_ADJUST_DECREASE); if (error) goto out_drop; - if (*new_len > 0) - error = xfs_refcount_continue_op(rcur, startblock, - new_agbno, *new_len, new_fsb); + if (ri->ri_blockcount > 0) + error = xfs_refcount_continue_op(rcur, ri, bno); break; case XFS_REFCOUNT_ALLOC_COW: - *new_fsb = startblock + blockcount; - *new_len = 0; - error = __xfs_refcount_cow_alloc(rcur, bno, blockcount); + error = __xfs_refcount_cow_alloc(rcur, bno, ri->ri_blockcount); + if (error) + goto out_drop; + ri->ri_blockcount = 0; break; case XFS_REFCOUNT_FREE_COW: - *new_fsb = startblock + blockcount; - *new_len = 0; - error = __xfs_refcount_cow_free(rcur, bno, blockcount); + error = __xfs_refcount_cow_free(rcur, bno, ri->ri_blockcount); + if (error) + goto out_drop; + ri->ri_blockcount = 0; break; default: ASSERT(0); error = -EFSCORRUPTED; } - if (!error && *new_len > 0) - trace_xfs_refcount_finish_one_leftover(mp, pag->pag_agno, type, - bno, blockcount, new_agbno, *new_len); + if (!error && ri->ri_blockcount > 0) + trace_xfs_refcount_finish_one_leftover(mp, pag->pag_agno, + ri->ri_type, bno, ri->ri_blockcount); out_drop: xfs_perag_put(pag); return error; @@ -1907,8 +1903,13 @@ xfs_refcount_recover_cow_leftovers( struct xfs_buf *agbp; struct xfs_refcount_recovery *rr, *n; struct list_head debris; - union xfs_btree_irec low; - union xfs_btree_irec high; + union xfs_btree_irec low = { + .rc.rc_domain = XFS_REFC_DOMAIN_COW, + }; + union xfs_btree_irec high = { + .rc.rc_domain = XFS_REFC_DOMAIN_COW, + .rc.rc_startblock = -1U, + }; xfs_fsblock_t fsb; int error; @@ -1939,10 +1940,6 @@ xfs_refcount_recover_cow_leftovers( cur = xfs_refcountbt_init_cursor(mp, tp, agbp, pag); /* Find all the leftover CoW staging extents. */ - memset(&low, 0, sizeof(low)); - memset(&high, 0, sizeof(high)); - low.rc.rc_domain = high.rc.rc_domain = XFS_REFC_DOMAIN_COW; - high.rc.rc_startblock = -1U; error = xfs_btree_query_range(cur, &low, &high, xfs_refcount_recover_extent, &debris); xfs_btree_del_cursor(cur, error); @@ -1968,7 +1965,11 @@ xfs_refcount_recover_cow_leftovers( rr->rr_rrec.rc_blockcount); /* Free the block. */ - xfs_free_extent_later(tp, fsb, rr->rr_rrec.rc_blockcount, NULL); + error = xfs_free_extent_later(tp, fsb, + rr->rr_rrec.rc_blockcount, NULL, + XFS_AG_RESV_NONE); + if (error) + goto out_trans; error = xfs_trans_commit(tp); if (error) diff --git a/fs/xfs/libxfs/xfs_refcount.h b/fs/xfs/libxfs/xfs_refcount.h index 452f30556f5a..c633477ce3ce 100644 --- a/fs/xfs/libxfs/xfs_refcount.h +++ b/fs/xfs/libxfs/xfs_refcount.h @@ -75,9 +75,7 @@ void xfs_refcount_decrease_extent(struct xfs_trans *tp, extern void xfs_refcount_finish_one_cleanup(struct xfs_trans *tp, struct xfs_btree_cur *rcur, int error); extern int xfs_refcount_finish_one(struct xfs_trans *tp, - enum xfs_refcount_intent_type type, xfs_fsblock_t startblock, - xfs_extlen_t blockcount, xfs_fsblock_t *new_fsb, - xfs_extlen_t *new_len, struct xfs_btree_cur **pcur); + struct xfs_refcount_intent *ri, struct xfs_btree_cur **pcur); extern int xfs_refcount_find_shared(struct xfs_btree_cur *cur, xfs_agblock_t agbno, xfs_extlen_t aglen, xfs_agblock_t *fbno, diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c index e1f789866683..fbd53b6951a9 100644 --- a/fs/xfs/libxfs/xfs_refcount_btree.c +++ b/fs/xfs/libxfs/xfs_refcount_btree.c @@ -106,18 +106,13 @@ xfs_refcountbt_free_block( struct xfs_buf *agbp = cur->bc_ag.agbp; struct xfs_agf *agf = agbp->b_addr; xfs_fsblock_t fsbno = XFS_DADDR_TO_FSB(mp, xfs_buf_daddr(bp)); - int error; trace_xfs_refcountbt_free_block(cur->bc_mp, cur->bc_ag.pag->pag_agno, XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno), 1); be32_add_cpu(&agf->agf_refcount_blocks, -1); xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_REFCOUNT_BLOCKS); - error = xfs_free_extent(cur->bc_tp, fsbno, 1, &XFS_RMAP_OINFO_REFC, - XFS_AG_RESV_METADATA); - if (error) - return error; - - return error; + return xfs_free_extent_later(cur->bc_tp, fsbno, 1, + &XFS_RMAP_OINFO_REFC, XFS_AG_RESV_METADATA); } STATIC int diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c index b56aca1e7c66..95d3599561ce 100644 --- a/fs/xfs/libxfs/xfs_rmap.c +++ b/fs/xfs/libxfs/xfs_rmap.c @@ -2337,14 +2337,10 @@ xfs_rmap_query_range( xfs_rmap_query_range_fn fn, void *priv) { - union xfs_btree_irec low_brec; - union xfs_btree_irec high_brec; - struct xfs_rmap_query_range_info query; + union xfs_btree_irec low_brec = { .r = *low_rec }; + union xfs_btree_irec high_brec = { .r = *high_rec }; + struct xfs_rmap_query_range_info query = { .priv = priv, .fn = fn }; - low_brec.r = *low_rec; - high_brec.r = *high_rec; - query.priv = priv; - query.fn = fn; return xfs_btree_query_range(cur, &low_brec, &high_brec, xfs_rmap_query_range_helper, &query); } diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c index 655108a4cd05..760172a65aff 100644 --- a/fs/xfs/libxfs/xfs_rtbitmap.c +++ b/fs/xfs/libxfs/xfs_rtbitmap.c @@ -16,6 +16,7 @@ #include "xfs_trans.h" #include "xfs_rtalloc.h" #include "xfs_error.h" +#include "xfs_rtbitmap.h" /* * Realtime allocator bitmap functions shared with userspace. @@ -1129,3 +1130,4 @@ xfs_rtalloc_extent_is_free( *is_free = matches; return 0; } + diff --git a/fs/xfs/libxfs/xfs_rtbitmap.h b/fs/xfs/libxfs/xfs_rtbitmap.h new file mode 100644 index 000000000000..b89712983347 --- /dev/null +++ b/fs/xfs/libxfs/xfs_rtbitmap.h @@ -0,0 +1,83 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2000-2003,2005 Silicon Graphics, Inc. + * All Rights Reserved. + */ +#ifndef __XFS_RTBITMAP_H__ +#define __XFS_RTBITMAP_H__ + +/* + * XXX: Most of the realtime allocation functions deal in units of realtime + * extents, not realtime blocks. This looks funny when paired with the type + * name and screams for a larger cleanup. + */ +struct xfs_rtalloc_rec { + xfs_rtblock_t ar_startext; + xfs_rtbxlen_t ar_extcount; +}; + +typedef int (*xfs_rtalloc_query_range_fn)( + struct xfs_mount *mp, + struct xfs_trans *tp, + const struct xfs_rtalloc_rec *rec, + void *priv); + +#ifdef CONFIG_XFS_RT +int xfs_rtbuf_get(struct xfs_mount *mp, struct xfs_trans *tp, + xfs_rtblock_t block, int issum, struct xfs_buf **bpp); +int xfs_rtcheck_range(struct xfs_mount *mp, struct xfs_trans *tp, + xfs_rtblock_t start, xfs_extlen_t len, int val, + xfs_rtblock_t *new, int *stat); +int xfs_rtfind_back(struct xfs_mount *mp, struct xfs_trans *tp, + xfs_rtblock_t start, xfs_rtblock_t limit, + xfs_rtblock_t *rtblock); +int xfs_rtfind_forw(struct xfs_mount *mp, struct xfs_trans *tp, + xfs_rtblock_t start, xfs_rtblock_t limit, + xfs_rtblock_t *rtblock); +int xfs_rtmodify_range(struct xfs_mount *mp, struct xfs_trans *tp, + xfs_rtblock_t start, xfs_extlen_t len, int val); +int xfs_rtmodify_summary_int(struct xfs_mount *mp, struct xfs_trans *tp, + int log, xfs_rtblock_t bbno, int delta, + struct xfs_buf **rbpp, xfs_fsblock_t *rsb, + xfs_suminfo_t *sum); +int xfs_rtmodify_summary(struct xfs_mount *mp, struct xfs_trans *tp, int log, + xfs_rtblock_t bbno, int delta, struct xfs_buf **rbpp, + xfs_fsblock_t *rsb); +int xfs_rtfree_range(struct xfs_mount *mp, struct xfs_trans *tp, + xfs_rtblock_t start, xfs_extlen_t len, + struct xfs_buf **rbpp, xfs_fsblock_t *rsb); +int xfs_rtalloc_query_range(struct xfs_mount *mp, struct xfs_trans *tp, + const struct xfs_rtalloc_rec *low_rec, + const struct xfs_rtalloc_rec *high_rec, + xfs_rtalloc_query_range_fn fn, void *priv); +int xfs_rtalloc_query_all(struct xfs_mount *mp, struct xfs_trans *tp, + xfs_rtalloc_query_range_fn fn, + void *priv); +bool xfs_verify_rtbno(struct xfs_mount *mp, xfs_rtblock_t rtbno); +int xfs_rtalloc_extent_is_free(struct xfs_mount *mp, struct xfs_trans *tp, + xfs_rtblock_t start, xfs_extlen_t len, + bool *is_free); +/* + * Free an extent in the realtime subvolume. Length is expressed in + * realtime extents, as is the block number. + */ +int /* error */ +xfs_rtfree_extent( + struct xfs_trans *tp, /* transaction pointer */ + xfs_rtblock_t bno, /* starting block number to free */ + xfs_extlen_t len); /* length of extent freed */ + +/* Same as above, but in units of rt blocks. */ +int xfs_rtfree_blocks(struct xfs_trans *tp, xfs_fsblock_t rtbno, + xfs_filblks_t rtlen); + +#else /* CONFIG_XFS_RT */ +# define xfs_rtfree_extent(t,b,l) (-ENOSYS) +# define xfs_rtfree_blocks(t,rb,rl) (-ENOSYS) +# define xfs_rtalloc_query_range(m,t,l,h,f,p) (-ENOSYS) +# define xfs_rtalloc_query_all(m,t,f,p) (-ENOSYS) +# define xfs_rtbuf_get(m,t,b,i,p) (-ENOSYS) +# define xfs_rtalloc_extent_is_free(m,t,s,l,i) (-ENOSYS) +#endif /* CONFIG_XFS_RT */ + +#endif /* __XFS_RTBITMAP_H__ */ diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c index d214233ef532..8e0a176b8e0b 100644 --- a/fs/xfs/libxfs/xfs_sb.c +++ b/fs/xfs/libxfs/xfs_sb.c @@ -25,6 +25,7 @@ #include "xfs_da_format.h" #include "xfs_health.h" #include "xfs_ag.h" +#include "xfs_rtbitmap.h" /* * Physical superblock buffer manipulations. Shared with libxfs in userspace. @@ -501,8 +502,9 @@ xfs_validate_sb_common( rbmblocks = howmany_64(sbp->sb_rextents, NBBY * sbp->sb_blocksize); - if (sbp->sb_rextents != rexts || - sbp->sb_rextslog != xfs_highbit32(sbp->sb_rextents) || + if (!xfs_validate_rtextents(rexts) || + sbp->sb_rextents != rexts || + sbp->sb_rextslog != xfs_compute_rextslog(rexts) || sbp->sb_rbmblocks != rbmblocks) { xfs_notice(mp, "realtime geometry sanity check failed"); @@ -1020,11 +1022,12 @@ xfs_log_sb( * and hence we don't need have to update it here. */ if (xfs_has_lazysbcount(mp)) { - mp->m_sb.sb_icount = percpu_counter_sum(&mp->m_icount); + mp->m_sb.sb_icount = percpu_counter_sum_positive(&mp->m_icount); mp->m_sb.sb_ifree = min_t(uint64_t, - percpu_counter_sum(&mp->m_ifree), + percpu_counter_sum_positive(&mp->m_ifree), mp->m_sb.sb_icount); - mp->m_sb.sb_fdblocks = percpu_counter_sum(&mp->m_fdblocks); + mp->m_sb.sb_fdblocks = + percpu_counter_sum_positive(&mp->m_fdblocks); } xfs_sb_to_disk(bp->b_addr, &mp->m_sb); @@ -1365,3 +1368,17 @@ xfs_validate_stripe_geometry( } return true; } + +/* + * Compute the maximum level number of the realtime summary file, as defined by + * mkfs. The historic use of highbit32 on a 64-bit quantity prohibited correct + * use of rt volumes with more than 2^32 extents. + */ +uint8_t +xfs_compute_rextslog( + xfs_rtbxlen_t rtextents) +{ + if (!rtextents) + return 0; + return xfs_highbit64(rtextents); +} diff --git a/fs/xfs/libxfs/xfs_sb.h b/fs/xfs/libxfs/xfs_sb.h index 19134b23c10b..2e8e8d63d4eb 100644 --- a/fs/xfs/libxfs/xfs_sb.h +++ b/fs/xfs/libxfs/xfs_sb.h @@ -38,4 +38,6 @@ extern int xfs_sb_get_secondary(struct xfs_mount *mp, extern bool xfs_validate_stripe_geometry(struct xfs_mount *mp, __s64 sunit, __s64 swidth, int sectorsize, bool silent); +uint8_t xfs_compute_rextslog(xfs_rtbxlen_t rtextents); + #endif /* __XFS_SB_H__ */ diff --git a/fs/xfs/libxfs/xfs_trans_resv.c b/fs/xfs/libxfs/xfs_trans_resv.c index 5b2f27cbdb80..1bb2891b26ff 100644 --- a/fs/xfs/libxfs/xfs_trans_resv.c +++ b/fs/xfs/libxfs/xfs_trans_resv.c @@ -334,11 +334,11 @@ xfs_calc_write_reservation( blksz); t1 += adj; t3 += adj; - return XFS_DQUOT_LOGRES(mp) + max3(t1, t2, t3); + return XFS_DQUOT_LOGRES + max3(t1, t2, t3); } t4 = xfs_calc_refcountbt_reservation(mp, 1); - return XFS_DQUOT_LOGRES(mp) + max(t4, max3(t1, t2, t3)); + return XFS_DQUOT_LOGRES + max(t4, max3(t1, t2, t3)); } unsigned int @@ -406,11 +406,11 @@ xfs_calc_itruncate_reservation( xfs_refcountbt_block_count(mp, 4), blksz); - return XFS_DQUOT_LOGRES(mp) + max3(t1, t2, t3); + return XFS_DQUOT_LOGRES + max3(t1, t2, t3); } t4 = xfs_calc_refcountbt_reservation(mp, 2); - return XFS_DQUOT_LOGRES(mp) + max(t4, max3(t1, t2, t3)); + return XFS_DQUOT_LOGRES + max(t4, max3(t1, t2, t3)); } unsigned int @@ -436,7 +436,7 @@ STATIC uint xfs_calc_rename_reservation( struct xfs_mount *mp) { - return XFS_DQUOT_LOGRES(mp) + + return XFS_DQUOT_LOGRES + max((xfs_calc_inode_res(mp, 5) + xfs_calc_buf_res(2 * XFS_DIROP_LOG_COUNT(mp), XFS_FSB_TO_B(mp, 1))), @@ -475,7 +475,7 @@ STATIC uint xfs_calc_link_reservation( struct xfs_mount *mp) { - return XFS_DQUOT_LOGRES(mp) + + return XFS_DQUOT_LOGRES + xfs_calc_iunlink_remove_reservation(mp) + max((xfs_calc_inode_res(mp, 2) + xfs_calc_buf_res(XFS_DIROP_LOG_COUNT(mp), @@ -513,7 +513,7 @@ STATIC uint xfs_calc_remove_reservation( struct xfs_mount *mp) { - return XFS_DQUOT_LOGRES(mp) + + return XFS_DQUOT_LOGRES + xfs_calc_iunlink_add_reservation(mp) + max((xfs_calc_inode_res(mp, 2) + xfs_calc_buf_res(XFS_DIROP_LOG_COUNT(mp), @@ -572,7 +572,7 @@ xfs_calc_icreate_resv_alloc( STATIC uint xfs_calc_icreate_reservation(xfs_mount_t *mp) { - return XFS_DQUOT_LOGRES(mp) + + return XFS_DQUOT_LOGRES + max(xfs_calc_icreate_resv_alloc(mp), xfs_calc_create_resv_modify(mp)); } @@ -581,7 +581,7 @@ STATIC uint xfs_calc_create_tmpfile_reservation( struct xfs_mount *mp) { - uint res = XFS_DQUOT_LOGRES(mp); + uint res = XFS_DQUOT_LOGRES; res += xfs_calc_icreate_resv_alloc(mp); return res + xfs_calc_iunlink_add_reservation(mp); @@ -630,7 +630,7 @@ STATIC uint xfs_calc_ifree_reservation( struct xfs_mount *mp) { - return XFS_DQUOT_LOGRES(mp) + + return XFS_DQUOT_LOGRES + xfs_calc_inode_res(mp, 1) + xfs_calc_buf_res(3, mp->m_sb.sb_sectsize) + xfs_calc_iunlink_remove_reservation(mp) + @@ -647,7 +647,7 @@ STATIC uint xfs_calc_ichange_reservation( struct xfs_mount *mp) { - return XFS_DQUOT_LOGRES(mp) + + return XFS_DQUOT_LOGRES + xfs_calc_inode_res(mp, 1) + xfs_calc_buf_res(1, mp->m_sb.sb_sectsize); @@ -756,7 +756,7 @@ STATIC uint xfs_calc_addafork_reservation( struct xfs_mount *mp) { - return XFS_DQUOT_LOGRES(mp) + + return XFS_DQUOT_LOGRES + xfs_calc_inode_res(mp, 1) + xfs_calc_buf_res(2, mp->m_sb.sb_sectsize) + xfs_calc_buf_res(1, mp->m_dir_geo->blksize) + @@ -804,7 +804,7 @@ STATIC uint xfs_calc_attrsetm_reservation( struct xfs_mount *mp) { - return XFS_DQUOT_LOGRES(mp) + + return XFS_DQUOT_LOGRES + xfs_calc_inode_res(mp, 1) + xfs_calc_buf_res(1, mp->m_sb.sb_sectsize) + xfs_calc_buf_res(XFS_DA_NODE_MAXDEPTH, XFS_FSB_TO_B(mp, 1)); @@ -844,7 +844,7 @@ STATIC uint xfs_calc_attrrm_reservation( struct xfs_mount *mp) { - return XFS_DQUOT_LOGRES(mp) + + return XFS_DQUOT_LOGRES + max((xfs_calc_inode_res(mp, 1) + xfs_calc_buf_res(XFS_DA_NODE_MAXDEPTH, XFS_FSB_TO_B(mp, 1)) + diff --git a/fs/xfs/libxfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h index 5ebdda7e1078..42fed04f038d 100644 --- a/fs/xfs/libxfs/xfs_types.h +++ b/fs/xfs/libxfs/xfs_types.h @@ -31,6 +31,7 @@ typedef uint64_t xfs_rfsblock_t; /* blockno in filesystem (raw) */ typedef uint64_t xfs_rtblock_t; /* extent (block) in realtime area */ typedef uint64_t xfs_fileoff_t; /* block number in a file */ typedef uint64_t xfs_filblks_t; /* number of blocks in a file */ +typedef uint64_t xfs_rtbxlen_t; /* rtbitmap extent length in rtextents */ typedef int64_t xfs_srtblock_t; /* signed version of xfs_rtblock_t */ @@ -227,4 +228,16 @@ bool xfs_verify_fileoff(struct xfs_mount *mp, xfs_fileoff_t off); bool xfs_verify_fileext(struct xfs_mount *mp, xfs_fileoff_t off, xfs_fileoff_t len); +/* Do we support an rt volume having this number of rtextents? */ +static inline bool +xfs_validate_rtextents( + xfs_rtbxlen_t rtextents) +{ + /* No runt rt volumes */ + if (rtextents == 0) + return false; + + return true; +} + #endif /* __XFS_TYPES_H__ */ diff --git a/fs/xfs/scrub/attr.c b/fs/xfs/scrub/attr.c index b6f0c9f3f124..f51771e5c3fe 100644 --- a/fs/xfs/scrub/attr.c +++ b/fs/xfs/scrub/attr.c @@ -159,6 +159,11 @@ xchk_xattr_listent( args.value = xchk_xattr_valuebuf(sx->sc); args.valuelen = valuelen; + /* + * Get the attr value to ensure that lookup can find this attribute + * through the dabtree indexing and that remote value retrieval also + * works correctly. + */ error = xfs_attr_get_ilocked(&args); /* ENODATA means the hash lookup failed and the attr is bad */ if (error == -ENODATA) diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c index f0b9cb6506fd..45b135929144 100644 --- a/fs/xfs/scrub/bmap.c +++ b/fs/xfs/scrub/bmap.c @@ -647,7 +647,13 @@ xchk_bmap( } break; case XFS_ATTR_FORK: - if (!xfs_has_attr(mp) && !xfs_has_attr2(mp)) + /* + * "attr" means that an attr fork was created at some point in + * the life of this filesystem. "attr2" means that inodes have + * variable-sized data/attr fork areas. Hence we only check + * attr here. + */ + if (!xfs_has_attr(mp)) xchk_ino_set_corrupt(sc, sc->ip->i_ino); break; default: diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c index c18bd039fce9..e0ed0ebfdaea 100644 --- a/fs/xfs/scrub/repair.c +++ b/fs/xfs/scrub/repair.c @@ -582,7 +582,8 @@ xrep_reap_block( else if (resv == XFS_AG_RESV_AGFL) error = xrep_put_freelist(sc, agbno); else - error = xfs_free_extent(sc->tp, fsbno, 1, oinfo, resv); + error = xfs_free_extent(sc->tp, sc->sa.pag, agbno, 1, oinfo, + resv); if (agf_bp != sc->sa.agf_bp) xfs_trans_brelse(sc->tp, agf_bp); if (error) diff --git a/fs/xfs/scrub/rtbitmap.c b/fs/xfs/scrub/rtbitmap.c index 0a3bde64c675..fad7c353ada6 100644 --- a/fs/xfs/scrub/rtbitmap.c +++ b/fs/xfs/scrub/rtbitmap.c @@ -11,9 +11,10 @@ #include "xfs_mount.h" #include "xfs_log_format.h" #include "xfs_trans.h" -#include "xfs_rtalloc.h" +#include "xfs_rtbitmap.h" #include "xfs_inode.h" #include "xfs_bmap.h" +#include "xfs_sb.h" #include "scrub/scrub.h" #include "scrub/common.h" diff --git a/fs/xfs/xfs.h b/fs/xfs/xfs.h index f6ffb4f248f7..9355ccad9503 100644 --- a/fs/xfs/xfs.h +++ b/fs/xfs/xfs.h @@ -10,6 +10,10 @@ #define DEBUG 1 #endif +#ifdef CONFIG_XFS_DEBUG_EXPENSIVE +#define DEBUG_EXPENSIVE 1 +#endif + #ifdef CONFIG_XFS_ASSERT_FATAL #define XFS_ASSERT_FATAL 1 #endif diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 21c241e96d48..50a7f2745514 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -225,45 +225,6 @@ xfs_imap_valid( return true; } -/* - * Pass in a dellalloc extent and convert it to real extents, return the real - * extent that maps offset_fsb in wpc->iomap. - * - * The current page is held locked so nothing could have removed the block - * backing offset_fsb, although it could have moved from the COW to the data - * fork by another thread. - */ -static int -xfs_convert_blocks( - struct iomap_writepage_ctx *wpc, - struct xfs_inode *ip, - int whichfork, - loff_t offset) -{ - int error; - unsigned *seq; - - if (whichfork == XFS_COW_FORK) - seq = &XFS_WPC(wpc)->cow_seq; - else - seq = &XFS_WPC(wpc)->data_seq; - - /* - * Attempt to allocate whatever delalloc extent currently backs offset - * and put the result into wpc->iomap. Allocate in a loop because it - * may take several attempts to allocate real blocks for a contiguous - * delalloc extent if free space is sufficiently fragmented. - */ - do { - error = xfs_bmapi_convert_delalloc(ip, whichfork, offset, - &wpc->iomap, seq); - if (error) - return error; - } while (wpc->iomap.offset + wpc->iomap.length <= offset); - - return 0; -} - static int xfs_map_blocks( struct iomap_writepage_ctx *wpc, @@ -281,6 +242,7 @@ xfs_map_blocks( struct xfs_iext_cursor icur; int retries = 0; int error = 0; + unsigned int *seq; if (xfs_is_shutdown(mp)) return -EIO; @@ -376,7 +338,19 @@ retry: trace_xfs_map_blocks_found(ip, offset, count, whichfork, &imap); return 0; allocate_blocks: - error = xfs_convert_blocks(wpc, ip, whichfork, offset); + /* + * Convert a dellalloc extent to a real one. The current page is held + * locked so nothing could have removed the block backing offset_fsb, + * although it could have moved from the COW to the data fork by another + * thread. + */ + if (whichfork == XFS_COW_FORK) + seq = &XFS_WPC(wpc)->cow_seq; + else + seq = &XFS_WPC(wpc)->data_seq; + + error = xfs_bmapi_convert_delalloc(ip, whichfork, offset, + &wpc->iomap, seq); if (error) { /* * If we failed to find the extent in the COW fork we might have diff --git a/fs/xfs/xfs_attr_item.c b/fs/xfs/xfs_attr_item.c index 2788a6f2edcd..4a712f1565c1 100644 --- a/fs/xfs/xfs_attr_item.c +++ b/fs/xfs/xfs_attr_item.c @@ -329,6 +329,13 @@ xfs_xattri_finish_update( goto out; } + /* If an attr removal is trivially complete, we're done. */ + if (attr->xattri_op_flags == XFS_ATTRI_OP_FLAGS_REMOVE && + !xfs_inode_hasattr(args->dp)) { + error = 0; + goto out; + } + error = xfs_attr_set_iter(attr); if (!error && attr->xattri_dela_state != XFS_DAS_DONE) error = -EAGAIN; @@ -503,6 +510,9 @@ xfs_attri_validate( unsigned int op = attrp->alfi_op_flags & XFS_ATTRI_OP_FLAGS_TYPE_MASK; + if (!xfs_sb_version_haslogxattrs(&mp->m_sb)) + return false; + if (attrp->__pad != 0) return false; @@ -547,7 +557,7 @@ xfs_attri_item_recover( struct xfs_inode *ip; struct xfs_da_args *args; struct xfs_trans *tp; - struct xfs_trans_res tres; + struct xfs_trans_res resv; struct xfs_attri_log_format *attrp; struct xfs_attri_log_nameval *nv = attrip->attri_nameval; int error; @@ -594,8 +604,6 @@ xfs_attri_item_recover( args->op_flags = XFS_DA_OP_RECOVERY | XFS_DA_OP_OKNOENT | XFS_DA_OP_LOGGED; - ASSERT(xfs_sb_version_haslogxattrs(&mp->m_sb)); - switch (attr->xattri_op_flags) { case XFS_ATTRI_OP_FLAGS_SET: case XFS_ATTRI_OP_FLAGS_REPLACE: @@ -608,8 +616,6 @@ xfs_attri_item_recover( attr->xattri_dela_state = xfs_attr_init_add_state(args); break; case XFS_ATTRI_OP_FLAGS_REMOVE: - if (!xfs_inode_hasattr(args->dp)) - goto out; attr->xattri_dela_state = xfs_attr_init_remove_state(args); break; default: @@ -618,8 +624,9 @@ xfs_attri_item_recover( goto out; } - xfs_init_attr_trans(args, &tres, &total); - error = xfs_trans_alloc(mp, &tres, total, 0, XFS_TRANS_RESERVE, &tp); + xfs_init_attr_trans(args, &resv, &total); + resv = xlog_recover_resv(&resv); + error = xfs_trans_alloc(mp, &resv, total, 0, XFS_TRANS_RESERVE, &tp); if (error) goto out; @@ -710,48 +717,111 @@ xlog_recover_attri_commit_pass2( const void *attr_value = NULL; const void *attr_name; size_t len; - - attri_formatp = item->ri_buf[0].i_addr; - attr_name = item->ri_buf[1].i_addr; + unsigned int op, i = 0; /* Validate xfs_attri_log_format before the large memory allocation */ len = sizeof(struct xfs_attri_log_format); - if (item->ri_buf[0].i_len != len) { + if (item->ri_buf[i].i_len != len) { XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, item->ri_buf[0].i_addr, item->ri_buf[0].i_len); return -EFSCORRUPTED; } + attri_formatp = item->ri_buf[i].i_addr; if (!xfs_attri_validate(mp, attri_formatp)) { XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, - item->ri_buf[0].i_addr, item->ri_buf[0].i_len); + attri_formatp, len); return -EFSCORRUPTED; } + /* Check the number of log iovecs makes sense for the op code. */ + op = attri_formatp->alfi_op_flags & XFS_ATTRI_OP_FLAGS_TYPE_MASK; + switch (op) { + case XFS_ATTRI_OP_FLAGS_SET: + case XFS_ATTRI_OP_FLAGS_REPLACE: + /* Log item, attr name, attr value */ + if (item->ri_total != 3) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + attri_formatp, len); + return -EFSCORRUPTED; + } + break; + case XFS_ATTRI_OP_FLAGS_REMOVE: + /* Log item, attr name */ + if (item->ri_total != 2) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + attri_formatp, len); + return -EFSCORRUPTED; + } + break; + default: + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + attri_formatp, len); + return -EFSCORRUPTED; + } + i++; + /* Validate the attr name */ - if (item->ri_buf[1].i_len != + if (item->ri_buf[i].i_len != xlog_calc_iovec_len(attri_formatp->alfi_name_len)) { XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, - item->ri_buf[0].i_addr, item->ri_buf[0].i_len); + attri_formatp, len); return -EFSCORRUPTED; } + attr_name = item->ri_buf[i].i_addr; if (!xfs_attr_namecheck(attr_name, attri_formatp->alfi_name_len)) { XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, - item->ri_buf[1].i_addr, item->ri_buf[1].i_len); + attri_formatp, len); return -EFSCORRUPTED; } + i++; /* Validate the attr value, if present */ if (attri_formatp->alfi_value_len != 0) { - if (item->ri_buf[2].i_len != xlog_calc_iovec_len(attri_formatp->alfi_value_len)) { + if (item->ri_buf[i].i_len != xlog_calc_iovec_len(attri_formatp->alfi_value_len)) { XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, item->ri_buf[0].i_addr, item->ri_buf[0].i_len); return -EFSCORRUPTED; } - attr_value = item->ri_buf[2].i_addr; + attr_value = item->ri_buf[i].i_addr; + i++; + } + + /* + * Make sure we got the correct number of buffers for the operation + * that we just loaded. + */ + if (i != item->ri_total) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + attri_formatp, len); + return -EFSCORRUPTED; + } + + switch (op) { + case XFS_ATTRI_OP_FLAGS_REMOVE: + /* Regular remove operations operate only on names. */ + if (attr_value != NULL || attri_formatp->alfi_value_len != 0) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + attri_formatp, len); + return -EFSCORRUPTED; + } + fallthrough; + case XFS_ATTRI_OP_FLAGS_SET: + case XFS_ATTRI_OP_FLAGS_REPLACE: + /* + * Regular xattr set/remove/replace operations require a name + * and do not take a newname. Values are optional for set and + * replace. + */ + if (attr_name == NULL || attri_formatp->alfi_name_len == 0) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + attri_formatp, len); + return -EFSCORRUPTED; + } + break; } /* diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c index 41323da523d1..1058603db3ac 100644 --- a/fs/xfs/xfs_bmap_item.c +++ b/fs/xfs/xfs_bmap_item.c @@ -246,18 +246,11 @@ static int xfs_trans_log_finish_bmap_update( struct xfs_trans *tp, struct xfs_bud_log_item *budp, - enum xfs_bmap_intent_type type, - struct xfs_inode *ip, - int whichfork, - xfs_fileoff_t startoff, - xfs_fsblock_t startblock, - xfs_filblks_t *blockcount, - xfs_exntst_t state) + struct xfs_bmap_intent *bi) { int error; - error = xfs_bmap_finish_one(tp, ip, type, whichfork, startoff, - startblock, blockcount, state); + error = xfs_bmap_finish_one(tp, bi); /* * Mark the transaction dirty, even on error. This ensures the @@ -378,25 +371,17 @@ xfs_bmap_update_finish_item( struct list_head *item, struct xfs_btree_cur **state) { - struct xfs_bmap_intent *bmap; - xfs_filblks_t count; + struct xfs_bmap_intent *bi; int error; - bmap = container_of(item, struct xfs_bmap_intent, bi_list); - count = bmap->bi_bmap.br_blockcount; - error = xfs_trans_log_finish_bmap_update(tp, BUD_ITEM(done), - bmap->bi_type, - bmap->bi_owner, bmap->bi_whichfork, - bmap->bi_bmap.br_startoff, - bmap->bi_bmap.br_startblock, - &count, - bmap->bi_bmap.br_state); - if (!error && count > 0) { - ASSERT(bmap->bi_type == XFS_BMAP_UNMAP); - bmap->bi_bmap.br_blockcount = count; + bi = container_of(item, struct xfs_bmap_intent, bi_list); + + error = xfs_trans_log_finish_bmap_update(tp, BUD_ITEM(done), bi); + if (!error && bi->bi_bmap.br_blockcount > 0) { + ASSERT(bi->bi_type == XFS_BMAP_UNMAP); return -EAGAIN; } - kmem_cache_free(xfs_bmap_intent_cache, bmap); + kmem_cache_free(xfs_bmap_intent_cache, bi); return error; } @@ -471,17 +456,14 @@ xfs_bui_item_recover( struct xfs_log_item *lip, struct list_head *capture_list) { - struct xfs_bmbt_irec irec; + struct xfs_bmap_intent fake = { }; + struct xfs_trans_res resv; struct xfs_bui_log_item *buip = BUI_ITEM(lip); struct xfs_trans *tp; struct xfs_inode *ip = NULL; struct xfs_mount *mp = lip->li_log->l_mp; - struct xfs_map_extent *bmap; + struct xfs_map_extent *map; struct xfs_bud_log_item *budp; - xfs_filblks_t count; - xfs_exntst_t state; - unsigned int bui_type; - int whichfork; int iext_delta; int error = 0; @@ -491,19 +473,18 @@ xfs_bui_item_recover( return -EFSCORRUPTED; } - bmap = &buip->bui_format.bui_extents[0]; - state = (bmap->me_flags & XFS_BMAP_EXTENT_UNWRITTEN) ? - XFS_EXT_UNWRITTEN : XFS_EXT_NORM; - whichfork = (bmap->me_flags & XFS_BMAP_EXTENT_ATTR_FORK) ? + map = &buip->bui_format.bui_extents[0]; + fake.bi_whichfork = (map->me_flags & XFS_BMAP_EXTENT_ATTR_FORK) ? XFS_ATTR_FORK : XFS_DATA_FORK; - bui_type = bmap->me_flags & XFS_BMAP_EXTENT_TYPE_MASK; + fake.bi_type = map->me_flags & XFS_BMAP_EXTENT_TYPE_MASK; - error = xlog_recover_iget(mp, bmap->me_owner, &ip); + error = xlog_recover_iget(mp, map->me_owner, &ip); if (error) return error; /* Allocate transaction and do the work. */ - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, + resv = xlog_recover_resv(&M_RES(mp)->tr_itruncate); + error = xfs_trans_alloc(mp, &resv, XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK), 0, 0, &tp); if (error) goto err_rele; @@ -512,34 +493,34 @@ xfs_bui_item_recover( xfs_ilock(ip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, ip, 0); - if (bui_type == XFS_BMAP_MAP) + if (fake.bi_type == XFS_BMAP_MAP) iext_delta = XFS_IEXT_ADD_NOSPLIT_CNT; else iext_delta = XFS_IEXT_PUNCH_HOLE_CNT; - error = xfs_iext_count_may_overflow(ip, whichfork, iext_delta); + error = xfs_iext_count_may_overflow(ip, fake.bi_whichfork, iext_delta); if (error == -EFBIG) error = xfs_iext_count_upgrade(tp, ip, iext_delta); if (error) goto err_cancel; - count = bmap->me_len; - error = xfs_trans_log_finish_bmap_update(tp, budp, bui_type, ip, - whichfork, bmap->me_startoff, bmap->me_startblock, - &count, state); + fake.bi_owner = ip; + fake.bi_bmap.br_startblock = map->me_startblock; + fake.bi_bmap.br_startoff = map->me_startoff; + fake.bi_bmap.br_blockcount = map->me_len; + fake.bi_bmap.br_state = (map->me_flags & XFS_BMAP_EXTENT_UNWRITTEN) ? + XFS_EXT_UNWRITTEN : XFS_EXT_NORM; + + error = xfs_trans_log_finish_bmap_update(tp, budp, &fake); if (error == -EFSCORRUPTED) - XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bmap, - sizeof(*bmap)); + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, map, + sizeof(*map)); if (error) goto err_cancel; - if (count > 0) { - ASSERT(bui_type == XFS_BMAP_UNMAP); - irec.br_startblock = bmap->me_startblock; - irec.br_blockcount = count; - irec.br_startoff = bmap->me_startoff; - irec.br_state = state; - xfs_bmap_unmap_extent(tp, ip, &irec); + if (fake.bi_bmap.br_blockcount > 0) { + ASSERT(fake.bi_type == XFS_BMAP_UNMAP); + xfs_bmap_unmap_extent(tp, ip, &fake.bi_bmap); } /* diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 468bb61a5e46..bab8ba224e10 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -636,13 +636,11 @@ out_unlock: /* * Test whether it is appropriate to check an inode for and free post EOF - * blocks. The 'force' parameter determines whether we should also consider - * regular files that are marked preallocated or append-only. + * blocks. */ bool xfs_can_free_eofblocks( - struct xfs_inode *ip, - bool force) + struct xfs_inode *ip) { struct xfs_bmbt_irec imap; struct xfs_mount *mp = ip->i_mount; @@ -676,11 +674,11 @@ xfs_can_free_eofblocks( return false; /* - * Do not free real preallocated or append-only files unless the file - * has delalloc blocks and we are forced to remove them. + * Only free real extents for inodes with persistent preallocations or + * the append-only flag. */ if (ip->i_diflags & (XFS_DIFLAG_PREALLOC | XFS_DIFLAG_APPEND)) - if (!force || ip->i_delayed_blks == 0) + if (ip->i_delayed_blks == 0) return false; /* @@ -734,6 +732,22 @@ xfs_free_eofblocks( /* Wait on dio to ensure i_size has settled. */ inode_dio_wait(VFS_I(ip)); + /* + * For preallocated files only free delayed allocations. + * + * Note that this means we also leave speculative preallocations in + * place for preallocated files. + */ + if (ip->i_diflags & (XFS_DIFLAG_PREALLOC | XFS_DIFLAG_APPEND)) { + if (ip->i_delayed_blks) { + xfs_bmap_punch_delalloc_range(ip, + round_up(XFS_ISIZE(ip), mp->m_sb.sb_blocksize), + LLONG_MAX); + } + xfs_inode_clear_eofblocks_tag(ip); + return 0; + } + error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp); if (error) { ASSERT(xfs_is_shutdown(mp)); @@ -868,33 +882,32 @@ xfs_alloc_file_space( if (error) goto error; - error = xfs_bmapi_write(tp, ip, startoffset_fsb, - allocatesize_fsb, XFS_BMAPI_PREALLOC, 0, imapp, - &nimaps); - if (error) - goto error; - - ip->i_diflags |= XFS_DIFLAG_PREALLOC; - xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); - - error = xfs_trans_commit(tp); - xfs_iunlock(ip, XFS_ILOCK_EXCL); - if (error) - break; - /* * If the allocator cannot find a single free extent large * enough to cover the start block of the requested range, - * xfs_bmapi_write will return 0 but leave *nimaps set to 0. + * xfs_bmapi_write will return -ENOSR. * * In that case we simply need to keep looping with the same * startoffset_fsb so that one of the following allocations * will eventually reach the requested range. */ - if (nimaps) { + error = xfs_bmapi_write(tp, ip, startoffset_fsb, + allocatesize_fsb, XFS_BMAPI_PREALLOC, 0, imapp, + &nimaps); + if (error) { + if (error != -ENOSR) + goto error; + error = 0; + } else { startoffset_fsb += imapp->br_blockcount; allocatesize_fsb -= imapp->br_blockcount; } + + ip->i_diflags |= XFS_DIFLAG_PREALLOC; + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); + + error = xfs_trans_commit(tp); + xfs_iunlock(ip, XFS_ILOCK_EXCL); } return error; @@ -950,14 +963,18 @@ xfs_flush_unmap_range( xfs_off_t offset, xfs_off_t len) { - struct xfs_mount *mp = ip->i_mount; struct inode *inode = VFS_I(ip); xfs_off_t rounding, start, end; int error; - rounding = max_t(xfs_off_t, mp->m_sb.sb_blocksize, PAGE_SIZE); - start = round_down(offset, rounding); - end = round_up(offset + len, rounding) - 1; + /* + * Make sure we extend the flush out to extent alignment + * boundaries so any extent range overlapping the start/end + * of the modification we are about to do is clean and idle. + */ + rounding = max_t(xfs_off_t, xfs_inode_alloc_unitsize(ip), PAGE_SIZE); + start = rounddown_64(offset, rounding); + end = roundup_64(offset + len, rounding) - 1; error = filemap_write_and_wait_range(inode->i_mapping, start, end); if (error) @@ -1042,14 +1059,14 @@ xfs_prepare_shift( struct xfs_inode *ip, loff_t offset) { - struct xfs_mount *mp = ip->i_mount; + unsigned int rounding; int error; /* * Trim eofblocks to avoid shifting uninitialized post-eof preallocation * into the accessible region of the file. */ - if (xfs_can_free_eofblocks(ip, true)) { + if (xfs_can_free_eofblocks(ip)) { error = xfs_free_eofblocks(ip); if (error) return error; @@ -1060,11 +1077,13 @@ xfs_prepare_shift( * with the full range of the operation. If we don't, a COW writeback * completion could race with an insert, front merge with the start * extent (after split) during the shift and corrupt the file. Start - * with the block just prior to the start to stabilize the boundary. + * with the allocation unit just prior to the start to stabilize the + * boundary. */ - offset = round_down(offset, mp->m_sb.sb_blocksize); + rounding = xfs_inode_alloc_unitsize(ip); + offset = rounddown_64(offset, rounding); if (offset) - offset -= mp->m_sb.sb_blocksize; + offset -= rounding; /* * Writeback and invalidate cache for the remainder of the file as we're diff --git a/fs/xfs/xfs_bmap_util.h b/fs/xfs/xfs_bmap_util.h index 6888078f5c31..1383019ccdb7 100644 --- a/fs/xfs/xfs_bmap_util.h +++ b/fs/xfs/xfs_bmap_util.h @@ -63,7 +63,7 @@ int xfs_insert_file_space(struct xfs_inode *, xfs_off_t offset, xfs_off_t len); /* EOF block manipulation functions */ -bool xfs_can_free_eofblocks(struct xfs_inode *ip, bool force); +bool xfs_can_free_eofblocks(struct xfs_inode *ip); int xfs_free_eofblocks(struct xfs_inode *ip); int xfs_swap_extents(struct xfs_inode *ip, struct xfs_inode *tip, diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 54c774af6e1c..257945cdf63b 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -2040,6 +2040,14 @@ error_free: return NULL; } +static inline void +xfs_buf_list_del( + struct xfs_buf *bp) +{ + list_del_init(&bp->b_list); + wake_up_var(&bp->b_list); +} + /* * Cancel a delayed write list. * @@ -2057,7 +2065,7 @@ xfs_buf_delwri_cancel( xfs_buf_lock(bp); bp->b_flags &= ~_XBF_DELWRI_Q; - list_del_init(&bp->b_list); + xfs_buf_list_del(bp); xfs_buf_relse(bp); } } @@ -2111,6 +2119,34 @@ xfs_buf_delwri_queue( } /* + * Queue a buffer to this delwri list as part of a data integrity operation. + * If the buffer is on any other delwri list, we'll wait for that to clear + * so that the caller can submit the buffer for IO and wait for the result. + * Callers must ensure the buffer is not already on the list. + */ +void +xfs_buf_delwri_queue_here( + struct xfs_buf *bp, + struct list_head *buffer_list) +{ + /* + * We need this buffer to end up on the /caller's/ delwri list, not any + * old list. This can happen if the buffer is marked stale (which + * clears DELWRI_Q) after the AIL queues the buffer to its list but + * before the AIL has a chance to submit the list. + */ + while (!list_empty(&bp->b_list)) { + xfs_buf_unlock(bp); + wait_var_event(&bp->b_list, list_empty(&bp->b_list)); + xfs_buf_lock(bp); + } + + ASSERT(!(bp->b_flags & _XBF_DELWRI_Q)); + + xfs_buf_delwri_queue(bp, buffer_list); +} + +/* * Compare function is more complex than it needs to be because * the return value is only 32 bits and we are doing comparisons * on 64 bit values @@ -2172,7 +2208,7 @@ xfs_buf_delwri_submit_buffers( * reference and remove it from the list here. */ if (!(bp->b_flags & _XBF_DELWRI_Q)) { - list_del_init(&bp->b_list); + xfs_buf_list_del(bp); xfs_buf_relse(bp); continue; } @@ -2192,7 +2228,7 @@ xfs_buf_delwri_submit_buffers( list_move_tail(&bp->b_list, wait_list); } else { bp->b_flags |= XBF_ASYNC; - list_del_init(&bp->b_list); + xfs_buf_list_del(bp); } __xfs_buf_submit(bp, false); } @@ -2246,7 +2282,7 @@ xfs_buf_delwri_submit( while (!list_empty(&wait_list)) { bp = list_first_entry(&wait_list, struct xfs_buf, b_list); - list_del_init(&bp->b_list); + xfs_buf_list_del(bp); /* * Wait on the locked buffer, check for errors and unlock and diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index 549c60942208..6cf0332ba62c 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -305,6 +305,7 @@ extern void xfs_buf_stale(struct xfs_buf *bp); /* Delayed Write Buffer Routines */ extern void xfs_buf_delwri_cancel(struct list_head *); extern bool xfs_buf_delwri_queue(struct xfs_buf *, struct list_head *); +void xfs_buf_delwri_queue_here(struct xfs_buf *bp, struct list_head *bl); extern int xfs_buf_delwri_submit(struct list_head *); extern int xfs_buf_delwri_submit_nowait(struct list_head *); extern int xfs_buf_delwri_pushbuf(struct xfs_buf *, struct list_head *); diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index 023d4e0385dd..b02ce568de0c 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -22,6 +22,7 @@ #include "xfs_trace.h" #include "xfs_log.h" #include "xfs_log_priv.h" +#include "xfs_error.h" struct kmem_cache *xfs_buf_item_cache; @@ -781,8 +782,39 @@ xfs_buf_item_committed( return lsn; } +#ifdef DEBUG_EXPENSIVE +static int +xfs_buf_item_precommit( + struct xfs_trans *tp, + struct xfs_log_item *lip) +{ + struct xfs_buf_log_item *bip = BUF_ITEM(lip); + struct xfs_buf *bp = bip->bli_buf; + struct xfs_mount *mp = bp->b_mount; + xfs_failaddr_t fa; + + if (!bp->b_ops || !bp->b_ops->verify_struct) + return 0; + if (bip->bli_flags & XFS_BLI_STALE) + return 0; + + fa = bp->b_ops->verify_struct(bp); + if (fa) { + xfs_buf_verifier_error(bp, -EFSCORRUPTED, bp->b_ops->name, + bp->b_addr, BBTOB(bp->b_length), fa); + xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); + ASSERT(fa == NULL); + } + + return 0; +} +#else +# define xfs_buf_item_precommit NULL +#endif + static const struct xfs_item_ops xfs_buf_item_ops = { .iop_size = xfs_buf_item_size, + .iop_precommit = xfs_buf_item_precommit, .iop_format = xfs_buf_item_format, .iop_pin = xfs_buf_item_pin, .iop_unpin = xfs_buf_item_unpin, diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c index a8b2f3b278ea..6186b69be50a 100644 --- a/fs/xfs/xfs_dquot.c +++ b/fs/xfs/xfs_dquot.c @@ -333,7 +333,6 @@ xfs_dquot_disk_alloc( goto err_cancel; ASSERT(map.br_blockcount == XFS_DQUOT_CLUSTER_SIZE_FSB); - ASSERT(nmaps == 1); ASSERT((map.br_startblock != DELAYSTARTBLOCK) && (map.br_startblock != HOLESTARTBLOCK)); diff --git a/fs/xfs/xfs_dquot_item.c b/fs/xfs/xfs_dquot_item.c index 6a1aae799cf1..7d19091215b0 100644 --- a/fs/xfs/xfs_dquot_item.c +++ b/fs/xfs/xfs_dquot_item.c @@ -17,6 +17,7 @@ #include "xfs_trans_priv.h" #include "xfs_qm.h" #include "xfs_log.h" +#include "xfs_error.h" static inline struct xfs_dq_logitem *DQUOT_ITEM(struct xfs_log_item *lip) { @@ -193,8 +194,38 @@ xfs_qm_dquot_logitem_committing( return xfs_qm_dquot_logitem_release(lip); } +#ifdef DEBUG_EXPENSIVE +static int +xfs_qm_dquot_logitem_precommit( + struct xfs_trans *tp, + struct xfs_log_item *lip) +{ + struct xfs_dquot *dqp = DQUOT_ITEM(lip)->qli_dquot; + struct xfs_mount *mp = dqp->q_mount; + struct xfs_disk_dquot ddq = { }; + xfs_failaddr_t fa; + + xfs_dquot_to_disk(&ddq, dqp); + fa = xfs_dquot_verify(mp, &ddq, dqp->q_id); + if (fa) { + XFS_CORRUPTION_ERROR("Bad dquot during logging", + XFS_ERRLEVEL_LOW, mp, &ddq, sizeof(ddq)); + xfs_alert(mp, + "Metadata corruption detected at %pS, dquot 0x%x", + fa, dqp->q_id); + xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); + ASSERT(fa == NULL); + } + + return 0; +} +#else +# define xfs_qm_dquot_logitem_precommit NULL +#endif + static const struct xfs_item_ops xfs_dquot_item_ops = { .iop_size = xfs_qm_dquot_logitem_size, + .iop_precommit = xfs_qm_dquot_logitem_precommit, .iop_format = xfs_qm_dquot_logitem_format, .iop_pin = xfs_qm_dquot_logitem_pin, .iop_unpin = xfs_qm_dquot_logitem_unpin, diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c index d5130d1fcfae..be9f279a5c75 100644 --- a/fs/xfs/xfs_extfree_item.c +++ b/fs/xfs/xfs_extfree_item.c @@ -345,23 +345,29 @@ static int xfs_trans_free_extent( struct xfs_trans *tp, struct xfs_efd_log_item *efdp, - xfs_fsblock_t start_block, - xfs_extlen_t ext_len, - const struct xfs_owner_info *oinfo, - bool skip_discard) + struct xfs_extent_free_item *xefi) { + struct xfs_owner_info oinfo = { }; struct xfs_mount *mp = tp->t_mountp; struct xfs_extent *extp; uint next_extent; - xfs_agnumber_t agno = XFS_FSB_TO_AGNO(mp, start_block); xfs_agblock_t agbno = XFS_FSB_TO_AGBNO(mp, - start_block); + xefi->xefi_startblock); int error; - trace_xfs_bmap_free_deferred(tp->t_mountp, agno, 0, agbno, ext_len); + oinfo.oi_owner = xefi->xefi_owner; + if (xefi->xefi_flags & XFS_EFI_ATTR_FORK) + oinfo.oi_flags |= XFS_OWNER_INFO_ATTR_FORK; + if (xefi->xefi_flags & XFS_EFI_BMBT_BLOCK) + oinfo.oi_flags |= XFS_OWNER_INFO_BMBT_BLOCK; + + trace_xfs_bmap_free_deferred(tp->t_mountp, xefi->xefi_pag->pag_agno, 0, + agbno, xefi->xefi_blockcount); + + error = __xfs_free_extent(tp, xefi->xefi_pag, agbno, + xefi->xefi_blockcount, &oinfo, xefi->xefi_agresv, + xefi->xefi_flags & XFS_EFI_SKIP_DISCARD); - error = __xfs_free_extent(tp, start_block, ext_len, - oinfo, XFS_AG_RESV_NONE, skip_discard); /* * Mark the transaction dirty, even on error. This ensures the * transaction is aborted, which: @@ -375,8 +381,8 @@ xfs_trans_free_extent( next_extent = efdp->efd_next_extent; ASSERT(next_extent < efdp->efd_format.efd_nextents); extp = &(efdp->efd_format.efd_extents[next_extent]); - extp->ext_start = start_block; - extp->ext_len = ext_len; + extp->ext_start = xefi->xefi_startblock; + extp->ext_len = xefi->xefi_blockcount; efdp->efd_next_extent++; return error; @@ -389,14 +395,13 @@ xfs_extent_free_diff_items( const struct list_head *a, const struct list_head *b) { - struct xfs_mount *mp = priv; struct xfs_extent_free_item *ra; struct xfs_extent_free_item *rb; ra = container_of(a, struct xfs_extent_free_item, xefi_list); rb = container_of(b, struct xfs_extent_free_item, xefi_list); - return XFS_FSB_TO_AGNO(mp, ra->xefi_startblock) - - XFS_FSB_TO_AGNO(mp, rb->xefi_startblock); + + return ra->xefi_pag->pag_agno - rb->xefi_pag->pag_agno; } /* Log a free extent to the intent item. */ @@ -404,7 +409,7 @@ STATIC void xfs_extent_free_log_item( struct xfs_trans *tp, struct xfs_efi_log_item *efip, - struct xfs_extent_free_item *free) + struct xfs_extent_free_item *xefi) { uint next_extent; struct xfs_extent *extp; @@ -420,8 +425,8 @@ xfs_extent_free_log_item( next_extent = atomic_inc_return(&efip->efi_next_extent) - 1; ASSERT(next_extent < efip->efi_format.efi_nextents); extp = &efip->efi_format.efi_extents[next_extent]; - extp->ext_start = free->xefi_startblock; - extp->ext_len = free->xefi_blockcount; + extp->ext_start = xefi->xefi_startblock; + extp->ext_len = xefi->xefi_blockcount; } static struct xfs_log_item * @@ -433,15 +438,15 @@ xfs_extent_free_create_intent( { struct xfs_mount *mp = tp->t_mountp; struct xfs_efi_log_item *efip = xfs_efi_init(mp, count); - struct xfs_extent_free_item *free; + struct xfs_extent_free_item *xefi; ASSERT(count > 0); xfs_trans_add_item(tp, &efip->efi_item); if (sort) list_sort(mp, items, xfs_extent_free_diff_items); - list_for_each_entry(free, items, xefi_list) - xfs_extent_free_log_item(tp, efip, free); + list_for_each_entry(xefi, items, xefi_list) + xfs_extent_free_log_item(tp, efip, xefi); return &efip->efi_item; } @@ -455,6 +460,26 @@ xfs_extent_free_create_done( return &xfs_trans_get_efd(tp, EFI_ITEM(intent), count)->efd_item; } +/* Take a passive ref to the AG containing the space we're freeing. */ +void +xfs_extent_free_get_group( + struct xfs_mount *mp, + struct xfs_extent_free_item *xefi) +{ + xfs_agnumber_t agno; + + agno = XFS_FSB_TO_AGNO(mp, xefi->xefi_startblock); + xefi->xefi_pag = xfs_perag_get(mp, agno); +} + +/* Release a passive AG ref after some freeing work. */ +static inline void +xfs_extent_free_put_group( + struct xfs_extent_free_item *xefi) +{ + xfs_perag_put(xefi->xefi_pag); +} + /* Process a free extent. */ STATIC int xfs_extent_free_finish_item( @@ -463,21 +488,15 @@ xfs_extent_free_finish_item( struct list_head *item, struct xfs_btree_cur **state) { - struct xfs_owner_info oinfo = { }; - struct xfs_extent_free_item *free; + struct xfs_extent_free_item *xefi; int error; - free = container_of(item, struct xfs_extent_free_item, xefi_list); - oinfo.oi_owner = free->xefi_owner; - if (free->xefi_flags & XFS_EFI_ATTR_FORK) - oinfo.oi_flags |= XFS_OWNER_INFO_ATTR_FORK; - if (free->xefi_flags & XFS_EFI_BMBT_BLOCK) - oinfo.oi_flags |= XFS_OWNER_INFO_BMBT_BLOCK; - error = xfs_trans_free_extent(tp, EFD_ITEM(done), - free->xefi_startblock, - free->xefi_blockcount, - &oinfo, free->xefi_flags & XFS_EFI_SKIP_DISCARD); - kmem_cache_free(xfs_extfree_item_cache, free); + xefi = container_of(item, struct xfs_extent_free_item, xefi_list); + + error = xfs_trans_free_extent(tp, EFD_ITEM(done), xefi); + + xfs_extent_free_put_group(xefi); + kmem_cache_free(xfs_extfree_item_cache, xefi); return error; } @@ -494,10 +513,12 @@ STATIC void xfs_extent_free_cancel_item( struct list_head *item) { - struct xfs_extent_free_item *free; + struct xfs_extent_free_item *xefi; - free = container_of(item, struct xfs_extent_free_item, xefi_list); - kmem_cache_free(xfs_extfree_item_cache, free); + xefi = container_of(item, struct xfs_extent_free_item, xefi_list); + + xfs_extent_free_put_group(xefi); + kmem_cache_free(xfs_extfree_item_cache, xefi); } const struct xfs_defer_op_type xfs_extent_free_defer_type = { @@ -523,28 +544,25 @@ xfs_agfl_free_finish_item( struct xfs_owner_info oinfo = { }; struct xfs_mount *mp = tp->t_mountp; struct xfs_efd_log_item *efdp = EFD_ITEM(done); - struct xfs_extent_free_item *free; + struct xfs_extent_free_item *xefi; struct xfs_extent *extp; struct xfs_buf *agbp; int error; - xfs_agnumber_t agno; xfs_agblock_t agbno; uint next_extent; - struct xfs_perag *pag; - free = container_of(item, struct xfs_extent_free_item, xefi_list); - ASSERT(free->xefi_blockcount == 1); - agno = XFS_FSB_TO_AGNO(mp, free->xefi_startblock); - agbno = XFS_FSB_TO_AGBNO(mp, free->xefi_startblock); - oinfo.oi_owner = free->xefi_owner; + xefi = container_of(item, struct xfs_extent_free_item, xefi_list); + ASSERT(xefi->xefi_blockcount == 1); + agbno = XFS_FSB_TO_AGBNO(mp, xefi->xefi_startblock); + oinfo.oi_owner = xefi->xefi_owner; - trace_xfs_agfl_free_deferred(mp, agno, 0, agbno, free->xefi_blockcount); + trace_xfs_agfl_free_deferred(mp, xefi->xefi_pag->pag_agno, 0, agbno, + xefi->xefi_blockcount); - pag = xfs_perag_get(mp, agno); - error = xfs_alloc_read_agf(pag, tp, 0, &agbp); + error = xfs_alloc_read_agf(xefi->xefi_pag, tp, 0, &agbp); if (!error) - error = xfs_free_agfl_block(tp, agno, agbno, agbp, &oinfo); - xfs_perag_put(pag); + error = xfs_free_agfl_block(tp, xefi->xefi_pag->pag_agno, + agbno, agbp, &oinfo); /* * Mark the transaction dirty, even on error. This ensures the @@ -559,11 +577,12 @@ xfs_agfl_free_finish_item( next_extent = efdp->efd_next_extent; ASSERT(next_extent < efdp->efd_format.efd_nextents); extp = &(efdp->efd_format.efd_extents[next_extent]); - extp->ext_start = free->xefi_startblock; - extp->ext_len = free->xefi_blockcount; + extp->ext_start = xefi->xefi_startblock; + extp->ext_len = xefi->xefi_blockcount; efdp->efd_next_extent++; - kmem_cache_free(xfs_extfree_item_cache, free); + xfs_extent_free_put_group(xefi); + kmem_cache_free(xfs_extfree_item_cache, xefi); return error; } @@ -595,11 +614,11 @@ xfs_efi_item_recover( struct xfs_log_item *lip, struct list_head *capture_list) { + struct xfs_trans_res resv; struct xfs_efi_log_item *efip = EFI_ITEM(lip); struct xfs_mount *mp = lip->li_log->l_mp; struct xfs_efd_log_item *efdp; struct xfs_trans *tp; - struct xfs_extent *extp; int i; int error = 0; @@ -618,16 +637,27 @@ xfs_efi_item_recover( } } - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp); + resv = xlog_recover_resv(&M_RES(mp)->tr_itruncate); + error = xfs_trans_alloc(mp, &resv, 0, 0, 0, &tp); if (error) return error; efdp = xfs_trans_get_efd(tp, efip, efip->efi_format.efi_nextents); for (i = 0; i < efip->efi_format.efi_nextents; i++) { + struct xfs_extent_free_item fake = { + .xefi_owner = XFS_RMAP_OWN_UNKNOWN, + .xefi_agresv = XFS_AG_RESV_NONE, + }; + struct xfs_extent *extp; + extp = &efip->efi_format.efi_extents[i]; - error = xfs_trans_free_extent(tp, efdp, extp->ext_start, - extp->ext_len, - &XFS_RMAP_OINFO_ANY_OWNER, false); + + fake.xefi_startblock = extp->ext_start; + fake.xefi_blockcount = extp->ext_len; + + xfs_extent_free_get_group(mp, &fake); + error = xfs_trans_free_extent(tp, efdp, &fake); + xfs_extent_free_put_group(&fake); if (error == -EFSCORRUPTED) XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, extp, sizeof(*extp)); diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 821cb86a83bd..3c910e36da69 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -24,6 +24,7 @@ #include "xfs_pnfs.h" #include "xfs_iomap.h" #include "xfs_reflink.h" +#include "xfs_file.h" #include <linux/dax.h> #include <linux/falloc.h> @@ -38,33 +39,25 @@ static const struct vm_operations_struct xfs_file_vm_ops; * Decide if the given file range is aligned to the size of the fundamental * allocation unit for the file. */ -static bool +bool xfs_is_falloc_aligned( struct xfs_inode *ip, loff_t pos, long long int len) { - struct xfs_mount *mp = ip->i_mount; - uint64_t mask; - - if (XFS_IS_REALTIME_INODE(ip)) { - if (!is_power_of_2(mp->m_sb.sb_rextsize)) { - u64 rextbytes; - u32 mod; - - rextbytes = XFS_FSB_TO_B(mp, mp->m_sb.sb_rextsize); - div_u64_rem(pos, rextbytes, &mod); - if (mod) - return false; - div_u64_rem(len, rextbytes, &mod); - return mod == 0; - } - mask = XFS_FSB_TO_B(mp, mp->m_sb.sb_rextsize) - 1; - } else { - mask = mp->m_sb.sb_blocksize - 1; + unsigned int alloc_unit = xfs_inode_alloc_unitsize(ip); + + if (!is_power_of_2(alloc_unit)) { + u32 mod; + + div_u64_rem(pos, alloc_unit, &mod); + if (mod) + return false; + div_u64_rem(len, alloc_unit, &mod); + return mod == 0; } - return !((pos | len) & mask); + return !((pos | len) & (alloc_unit - 1)); } /* diff --git a/fs/xfs/xfs_file.h b/fs/xfs/xfs_file.h new file mode 100644 index 000000000000..2ad91f755caf --- /dev/null +++ b/fs/xfs/xfs_file.h @@ -0,0 +1,15 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2000-2005 Silicon Graphics, Inc. + * All Rights Reserved. + */ +#ifndef __XFS_FILE_H__ +#define __XFS_FILE_H__ + +extern const struct file_operations xfs_file_operations; +extern const struct file_operations xfs_dir_file_operations; + +bool xfs_is_falloc_aligned(struct xfs_inode *ip, loff_t pos, + long long int len); + +#endif /* __XFS_FILE_H__ */ diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c index 062e5dc5db9f..a0668a1ef100 100644 --- a/fs/xfs/xfs_fsmap.c +++ b/fs/xfs/xfs_fsmap.c @@ -23,7 +23,7 @@ #include "xfs_refcount.h" #include "xfs_refcount_btree.h" #include "xfs_alloc_btree.h" -#include "xfs_rtalloc.h" +#include "xfs_rtbitmap.h" #include "xfs_ag.h" /* Convert an xfs_fsmap to an fsmap. */ @@ -71,7 +71,7 @@ xfs_fsmap_owner_to_rmap( switch (src->fmr_owner) { case 0: /* "lowest owner id possible" */ case -1ULL: /* "highest owner id possible" */ - dest->rm_owner = 0; + dest->rm_owner = src->fmr_owner; break; case XFS_FMR_OWN_FREE: dest->rm_owner = XFS_RMAP_OWN_NULL; @@ -160,9 +160,18 @@ struct xfs_getfsmap_info { struct xfs_buf *agf_bp; /* AGF, for refcount queries */ struct xfs_perag *pag; /* AG info, if applicable */ xfs_daddr_t next_daddr; /* next daddr we expect */ + /* daddr of low fsmap key when we're using the rtbitmap */ + xfs_daddr_t low_daddr; u64 missing_owner; /* owner of holes */ u32 dev; /* device id */ - struct xfs_rmap_irec low; /* low rmap key */ + /* + * Low rmap key for the query. If low.rm_blockcount is nonzero, this + * is the second (or later) call to retrieve the recordset in pieces. + * xfs_getfsmap_rec_before_start will compare all records retrieved + * by the rmapbt query to filter out any records that start before + * the last record. + */ + struct xfs_rmap_irec low; struct xfs_rmap_irec high; /* high rmap key */ bool last; /* last extent? */ }; @@ -237,16 +246,31 @@ xfs_getfsmap_format( xfs_fsmap_from_internal(rec, xfm); } +static inline bool +xfs_getfsmap_rec_before_start( + struct xfs_getfsmap_info *info, + const struct xfs_rmap_irec *rec, + xfs_daddr_t rec_daddr) +{ + if (info->low_daddr != XFS_BUF_DADDR_NULL) + return rec_daddr < info->low_daddr; + if (info->low.rm_blockcount) + return xfs_rmap_compare(rec, &info->low) < 0; + return false; +} + /* * Format a reverse mapping for getfsmap, having translated rm_startblock - * into the appropriate daddr units. + * into the appropriate daddr units. Pass in a nonzero @len_daddr if the + * length could be larger than rm_blockcount in struct xfs_rmap_irec. */ STATIC int xfs_getfsmap_helper( struct xfs_trans *tp, struct xfs_getfsmap_info *info, const struct xfs_rmap_irec *rec, - xfs_daddr_t rec_daddr) + xfs_daddr_t rec_daddr, + xfs_daddr_t len_daddr) { struct xfs_fsmap fmr; struct xfs_mount *mp = tp->t_mountp; @@ -256,12 +280,15 @@ xfs_getfsmap_helper( if (fatal_signal_pending(current)) return -EINTR; + if (len_daddr == 0) + len_daddr = XFS_FSB_TO_BB(mp, rec->rm_blockcount); + /* * Filter out records that start before our startpoint, if the * caller requested that. */ - if (xfs_rmap_compare(rec, &info->low) < 0) { - rec_daddr += XFS_FSB_TO_BB(mp, rec->rm_blockcount); + if (xfs_getfsmap_rec_before_start(info, rec, rec_daddr)) { + rec_daddr += len_daddr; if (info->next_daddr < rec_daddr) info->next_daddr = rec_daddr; return 0; @@ -280,7 +307,7 @@ xfs_getfsmap_helper( info->head->fmh_entries++; - rec_daddr += XFS_FSB_TO_BB(mp, rec->rm_blockcount); + rec_daddr += len_daddr; if (info->next_daddr < rec_daddr) info->next_daddr = rec_daddr; return 0; @@ -320,7 +347,7 @@ xfs_getfsmap_helper( if (error) return error; fmr.fmr_offset = XFS_FSB_TO_BB(mp, rec->rm_offset); - fmr.fmr_length = XFS_FSB_TO_BB(mp, rec->rm_blockcount); + fmr.fmr_length = len_daddr; if (rec->rm_flags & XFS_RMAP_UNWRITTEN) fmr.fmr_flags |= FMR_OF_PREALLOC; if (rec->rm_flags & XFS_RMAP_ATTR_FORK) @@ -337,7 +364,7 @@ xfs_getfsmap_helper( xfs_getfsmap_format(mp, &fmr, info); out: - rec_daddr += XFS_FSB_TO_BB(mp, rec->rm_blockcount); + rec_daddr += len_daddr; if (info->next_daddr < rec_daddr) info->next_daddr = rec_daddr; return 0; @@ -358,7 +385,7 @@ xfs_getfsmap_datadev_helper( fsb = XFS_AGB_TO_FSB(mp, cur->bc_ag.pag->pag_agno, rec->rm_startblock); rec_daddr = XFS_FSB_TO_DADDR(mp, fsb); - return xfs_getfsmap_helper(cur->bc_tp, info, rec, rec_daddr); + return xfs_getfsmap_helper(cur->bc_tp, info, rec, rec_daddr, 0); } /* Transform a bnobt irec into a fsmap */ @@ -382,7 +409,7 @@ xfs_getfsmap_datadev_bnobt_helper( irec.rm_offset = 0; irec.rm_flags = 0; - return xfs_getfsmap_helper(cur->bc_tp, info, &irec, rec_daddr); + return xfs_getfsmap_helper(cur->bc_tp, info, &irec, rec_daddr, 0); } /* Set rmap flags based on the getfsmap flags */ @@ -409,31 +436,25 @@ xfs_getfsmap_logdev( { struct xfs_mount *mp = tp->t_mountp; struct xfs_rmap_irec rmap; - int error; + xfs_daddr_t rec_daddr, len_daddr; + xfs_fsblock_t start_fsb, end_fsb; + uint64_t eofs; - /* Set up search keys */ - info->low.rm_startblock = XFS_BB_TO_FSBT(mp, keys[0].fmr_physical); - info->low.rm_offset = XFS_BB_TO_FSBT(mp, keys[0].fmr_offset); - error = xfs_fsmap_owner_to_rmap(&info->low, keys); - if (error) - return error; - info->low.rm_blockcount = 0; - xfs_getfsmap_set_irec_flags(&info->low, &keys[0]); + eofs = XFS_FSB_TO_BB(mp, mp->m_sb.sb_logblocks); + if (keys[0].fmr_physical >= eofs) + return 0; + start_fsb = XFS_BB_TO_FSBT(mp, + keys[0].fmr_physical + keys[0].fmr_length); + end_fsb = XFS_BB_TO_FSB(mp, min(eofs - 1, keys[1].fmr_physical)); - error = xfs_fsmap_owner_to_rmap(&info->high, keys + 1); - if (error) - return error; - info->high.rm_startblock = -1U; - info->high.rm_owner = ULLONG_MAX; - info->high.rm_offset = ULLONG_MAX; - info->high.rm_blockcount = 0; - info->high.rm_flags = XFS_RMAP_KEY_FLAGS | XFS_RMAP_REC_FLAGS; - info->missing_owner = XFS_FMR_OWN_FREE; + /* Adjust the low key if we are continuing from where we left off. */ + if (keys[0].fmr_length > 0) + info->low_daddr = XFS_FSB_TO_BB(mp, start_fsb); - trace_xfs_fsmap_low_key(mp, info->dev, NULLAGNUMBER, &info->low); - trace_xfs_fsmap_high_key(mp, info->dev, NULLAGNUMBER, &info->high); + trace_xfs_fsmap_low_key_linear(mp, info->dev, start_fsb); + trace_xfs_fsmap_high_key_linear(mp, info->dev, end_fsb); - if (keys[0].fmr_physical > 0) + if (start_fsb > 0) return 0; /* Fabricate an rmap entry for the external log device. */ @@ -443,7 +464,9 @@ xfs_getfsmap_logdev( rmap.rm_offset = 0; rmap.rm_flags = 0; - return xfs_getfsmap_helper(tp, info, &rmap, 0); + rec_daddr = XFS_FSB_TO_BB(mp, rmap.rm_startblock); + len_daddr = XFS_FSB_TO_BB(mp, rmap.rm_blockcount); + return xfs_getfsmap_helper(tp, info, &rmap, rec_daddr, len_daddr); } #ifdef CONFIG_XFS_RT @@ -457,72 +480,58 @@ xfs_getfsmap_rtdev_rtbitmap_helper( { struct xfs_getfsmap_info *info = priv; struct xfs_rmap_irec irec; - xfs_daddr_t rec_daddr; + xfs_rtblock_t rtbno; + xfs_daddr_t rec_daddr, len_daddr; + + rtbno = rec->ar_startext * mp->m_sb.sb_rextsize; + rec_daddr = XFS_FSB_TO_BB(mp, rtbno); + irec.rm_startblock = rtbno; + + rtbno = rec->ar_extcount * mp->m_sb.sb_rextsize; + len_daddr = XFS_FSB_TO_BB(mp, rtbno); + irec.rm_blockcount = rtbno; - irec.rm_startblock = rec->ar_startext * mp->m_sb.sb_rextsize; - rec_daddr = XFS_FSB_TO_BB(mp, irec.rm_startblock); - irec.rm_blockcount = rec->ar_extcount * mp->m_sb.sb_rextsize; irec.rm_owner = XFS_RMAP_OWN_NULL; /* "free" */ irec.rm_offset = 0; irec.rm_flags = 0; - return xfs_getfsmap_helper(tp, info, &irec, rec_daddr); + return xfs_getfsmap_helper(tp, info, &irec, rec_daddr, len_daddr); } -/* Execute a getfsmap query against the realtime device. */ +/* Execute a getfsmap query against the realtime device rtbitmap. */ STATIC int -__xfs_getfsmap_rtdev( +xfs_getfsmap_rtdev_rtbitmap( struct xfs_trans *tp, const struct xfs_fsmap *keys, - int (*query_fn)(struct xfs_trans *, - struct xfs_getfsmap_info *), struct xfs_getfsmap_info *info) { + + struct xfs_rtalloc_rec alow = { 0 }; + struct xfs_rtalloc_rec ahigh = { 0 }; struct xfs_mount *mp = tp->t_mountp; - xfs_fsblock_t start_fsb; - xfs_fsblock_t end_fsb; + xfs_rtblock_t start_rtb; + xfs_rtblock_t end_rtb; uint64_t eofs; - int error = 0; + int error; - eofs = XFS_FSB_TO_BB(mp, mp->m_sb.sb_rblocks); + eofs = XFS_FSB_TO_BB(mp, mp->m_sb.sb_rextents * mp->m_sb.sb_rextsize); if (keys[0].fmr_physical >= eofs) return 0; - start_fsb = XFS_BB_TO_FSBT(mp, keys[0].fmr_physical); - end_fsb = XFS_BB_TO_FSB(mp, min(eofs - 1, keys[1].fmr_physical)); + start_rtb = XFS_BB_TO_FSBT(mp, + keys[0].fmr_physical + keys[0].fmr_length); + end_rtb = XFS_BB_TO_FSB(mp, min(eofs - 1, keys[1].fmr_physical)); - /* Set up search keys */ - info->low.rm_startblock = start_fsb; - error = xfs_fsmap_owner_to_rmap(&info->low, &keys[0]); - if (error) - return error; - info->low.rm_offset = XFS_BB_TO_FSBT(mp, keys[0].fmr_offset); - info->low.rm_blockcount = 0; - xfs_getfsmap_set_irec_flags(&info->low, &keys[0]); - - info->high.rm_startblock = end_fsb; - error = xfs_fsmap_owner_to_rmap(&info->high, &keys[1]); - if (error) - return error; - info->high.rm_offset = XFS_BB_TO_FSBT(mp, keys[1].fmr_offset); - info->high.rm_blockcount = 0; - xfs_getfsmap_set_irec_flags(&info->high, &keys[1]); + info->missing_owner = XFS_FMR_OWN_UNKNOWN; - trace_xfs_fsmap_low_key(mp, info->dev, NULLAGNUMBER, &info->low); - trace_xfs_fsmap_high_key(mp, info->dev, NULLAGNUMBER, &info->high); + /* Adjust the low key if we are continuing from where we left off. */ + if (keys[0].fmr_length > 0) { + info->low_daddr = XFS_FSB_TO_BB(mp, start_rtb); + if (info->low_daddr >= eofs) + return 0; + } - return query_fn(tp, info); -} - -/* Actually query the realtime bitmap. */ -STATIC int -xfs_getfsmap_rtdev_rtbitmap_query( - struct xfs_trans *tp, - struct xfs_getfsmap_info *info) -{ - struct xfs_rtalloc_rec alow = { 0 }; - struct xfs_rtalloc_rec ahigh = { 0 }; - struct xfs_mount *mp = tp->t_mountp; - int error; + trace_xfs_fsmap_low_key_linear(mp, info->dev, start_rtb); + trace_xfs_fsmap_high_key_linear(mp, info->dev, end_rtb); xfs_ilock(mp->m_rbmip, XFS_ILOCK_SHARED); @@ -530,8 +539,8 @@ xfs_getfsmap_rtdev_rtbitmap_query( * Set up query parameters to return free rtextents covering the range * we want. */ - alow.ar_startext = info->low.rm_startblock; - ahigh.ar_startext = info->high.rm_startblock; + alow.ar_startext = start_rtb; + ahigh.ar_startext = end_rtb; do_div(alow.ar_startext, mp->m_sb.sb_rextsize); if (do_div(ahigh.ar_startext, mp->m_sb.sb_rextsize)) ahigh.ar_startext++; @@ -554,19 +563,20 @@ err: xfs_iunlock(mp->m_rbmip, XFS_ILOCK_SHARED); return error; } +#endif /* CONFIG_XFS_RT */ -/* Execute a getfsmap query against the realtime device rtbitmap. */ -STATIC int -xfs_getfsmap_rtdev_rtbitmap( - struct xfs_trans *tp, - const struct xfs_fsmap *keys, - struct xfs_getfsmap_info *info) +static inline bool +rmap_not_shareable(struct xfs_mount *mp, const struct xfs_rmap_irec *r) { - info->missing_owner = XFS_FMR_OWN_UNKNOWN; - return __xfs_getfsmap_rtdev(tp, keys, xfs_getfsmap_rtdev_rtbitmap_query, - info); + if (!xfs_has_reflink(mp)) + return true; + if (XFS_RMAP_NON_INODE_OWNER(r->rm_owner)) + return true; + if (r->rm_flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK | + XFS_RMAP_UNWRITTEN)) + return true; + return false; } -#endif /* CONFIG_XFS_RT */ /* Execute a getfsmap query against the regular data device. */ STATIC int @@ -601,14 +611,30 @@ __xfs_getfsmap_datadev( * low to the fsmap low key and max out the high key to the end * of the AG. */ - info->low.rm_startblock = XFS_FSB_TO_AGBNO(mp, start_fsb); info->low.rm_offset = XFS_BB_TO_FSBT(mp, keys[0].fmr_offset); error = xfs_fsmap_owner_to_rmap(&info->low, &keys[0]); if (error) return error; - info->low.rm_blockcount = 0; + info->low.rm_blockcount = XFS_BB_TO_FSBT(mp, keys[0].fmr_length); xfs_getfsmap_set_irec_flags(&info->low, &keys[0]); + /* Adjust the low key if we are continuing from where we left off. */ + if (info->low.rm_blockcount == 0) { + /* No previous record from which to continue */ + } else if (rmap_not_shareable(mp, &info->low)) { + /* Last record seen was an unshareable extent */ + info->low.rm_owner = 0; + info->low.rm_offset = 0; + + start_fsb += info->low.rm_blockcount; + if (XFS_FSB_TO_DADDR(mp, start_fsb) >= eofs) + return 0; + } else { + /* Last record seen was a shareable file data extent */ + info->low.rm_offset += info->low.rm_blockcount; + } + info->low.rm_startblock = XFS_FSB_TO_AGBNO(mp, start_fsb); + info->high.rm_startblock = -1U; info->high.rm_owner = ULLONG_MAX; info->high.rm_offset = ULLONG_MAX; @@ -659,12 +685,8 @@ __xfs_getfsmap_datadev( * Set the AG low key to the start of the AG prior to * moving on to the next AG. */ - if (pag->pag_agno == start_ag) { - info->low.rm_startblock = 0; - info->low.rm_owner = 0; - info->low.rm_offset = 0; - info->low.rm_flags = 0; - } + if (pag->pag_agno == start_ag) + memset(&info->low, 0, sizeof(info->low)); /* * If this is the last AG, report any gap at the end of it @@ -791,6 +813,19 @@ xfs_getfsmap_check_keys( struct xfs_fsmap *low_key, struct xfs_fsmap *high_key) { + if (low_key->fmr_flags & (FMR_OF_SPECIAL_OWNER | FMR_OF_EXTENT_MAP)) { + if (low_key->fmr_offset) + return false; + } + if (high_key->fmr_flags != -1U && + (high_key->fmr_flags & (FMR_OF_SPECIAL_OWNER | + FMR_OF_EXTENT_MAP))) { + if (high_key->fmr_offset && high_key->fmr_offset != -1ULL) + return false; + } + if (high_key->fmr_length && high_key->fmr_length != -1ULL) + return false; + if (low_key->fmr_device > high_key->fmr_device) return false; if (low_key->fmr_device < high_key->fmr_device) @@ -834,15 +869,15 @@ xfs_getfsmap_check_keys( * ---------------- * There are multiple levels of keys and counters at work here: * xfs_fsmap_head.fmh_keys -- low and high fsmap keys passed in; - * these reflect fs-wide sector addrs. + * these reflect fs-wide sector addrs. * dkeys -- fmh_keys used to query each device; - * these are fmh_keys but w/ the low key - * bumped up by fmr_length. + * these are fmh_keys but w/ the low key + * bumped up by fmr_length. * xfs_getfsmap_info.next_daddr -- next disk addr we expect to see; this * is how we detect gaps in the fsmap records and report them. * xfs_getfsmap_info.low/high -- per-AG low/high keys computed from - * dkeys; used to query the metadata. + * dkeys; used to query the metadata. */ int xfs_getfsmap( @@ -863,6 +898,8 @@ xfs_getfsmap( if (!xfs_getfsmap_is_valid_device(mp, &head->fmh_keys[0]) || !xfs_getfsmap_is_valid_device(mp, &head->fmh_keys[1])) return -EINVAL; + if (!xfs_getfsmap_check_keys(&head->fmh_keys[0], &head->fmh_keys[1])) + return -EINVAL; use_rmap = xfs_has_rmapbt(mp) && has_capability_noaudit(current, CAP_SYS_ADMIN); @@ -901,26 +938,15 @@ xfs_getfsmap( * blocks could be mapped to several other files/offsets. * According to rmapbt record ordering, the minimal next * possible record for the block range is the next starting - * offset in the same inode. Therefore, bump the file offset to - * continue the search appropriately. For all other low key - * mapping types (attr blocks, metadata), bump the physical - * offset as there can be no other mapping for the same physical - * block range. + * offset in the same inode. Therefore, each fsmap backend bumps + * the file offset to continue the search appropriately. For + * all other low key mapping types (attr blocks, metadata), each + * fsmap backend bumps the physical offset as there can be no + * other mapping for the same physical block range. */ dkeys[0] = head->fmh_keys[0]; - if (dkeys[0].fmr_flags & (FMR_OF_SPECIAL_OWNER | FMR_OF_EXTENT_MAP)) { - dkeys[0].fmr_physical += dkeys[0].fmr_length; - dkeys[0].fmr_owner = 0; - if (dkeys[0].fmr_offset) - return -EINVAL; - } else - dkeys[0].fmr_offset += dkeys[0].fmr_length; - dkeys[0].fmr_length = 0; memset(&dkeys[1], 0xFF, sizeof(struct xfs_fsmap)); - if (!xfs_getfsmap_check_keys(dkeys, &head->fmh_keys[1])) - return -EINVAL; - info.next_daddr = head->fmh_keys[0].fmr_physical + head->fmh_keys[0].fmr_length; info.fsmap_recs = fsmap_recs; @@ -960,6 +986,8 @@ xfs_getfsmap( info.dev = handlers[i].dev; info.last = false; info.pag = NULL; + info.low_daddr = XFS_BUF_DADDR_NULL; + info.low.rm_blockcount = 0; error = handlers[i].fn(tp, dkeys, &info); if (error) break; diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index 77b14f788214..96e9d64fbe62 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -153,7 +153,7 @@ xfs_growfs_data_private( (delta > 0 ? XFS_GROWFS_SPACE_RES(mp) : -delta), 0, XFS_TRANS_RESERVE, &tp); if (error) - return error; + goto out_free_unused_perag; last_pag = xfs_perag_get(mp, oagcount - 1); if (delta > 0) { @@ -227,6 +227,9 @@ xfs_growfs_data_private( out_trans_cancel: xfs_trans_cancel(tp); +out_free_unused_perag: + if (nagcount > oagcount) + xfs_free_unused_perag_range(mp, oagcount, nagcount); return error; } diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index 6df826fc787c..586d26c05160 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -1186,7 +1186,7 @@ xfs_inode_free_eofblocks( } *lockflags |= XFS_IOLOCK_EXCL; - if (xfs_can_free_eofblocks(ip, false)) + if (xfs_can_free_eofblocks(ip)) return xfs_free_eofblocks(ip); /* inode could be preallocated or append-only */ diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 26961b0dae03..3ccbc31767b3 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -983,10 +983,12 @@ xfs_create( prid = xfs_get_initial_prid(dp); /* - * Make sure that we have allocated dquot(s) on disk. + * Make sure that we have allocated dquot(s) on disk. The uid/gid + * computation code must match what the VFS uses to assign i_[ug]id. + * INHERIT adjusts the gid computation for setgid/grpid systems. */ - error = xfs_qm_vop_dqalloc(dp, mapped_fsuid(mnt_userns, &init_user_ns), - mapped_fsgid(mnt_userns, &init_user_ns), prid, + error = xfs_qm_vop_dqalloc(dp, mapped_fsuid(mnt_userns, i_user_ns(VFS_I(dp))), + mapped_fsgid(mnt_userns, i_user_ns(VFS_I(dp))), prid, XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT, &udqp, &gdqp, &pdqp); if (error) @@ -1132,10 +1134,12 @@ xfs_create_tmpfile( prid = xfs_get_initial_prid(dp); /* - * Make sure that we have allocated dquot(s) on disk. + * Make sure that we have allocated dquot(s) on disk. The uid/gid + * computation code must match what the VFS uses to assign i_[ug]id. + * INHERIT adjusts the gid computation for setgid/grpid systems. */ - error = xfs_qm_vop_dqalloc(dp, mapped_fsuid(mnt_userns, &init_user_ns), - mapped_fsgid(mnt_userns, &init_user_ns), prid, + error = xfs_qm_vop_dqalloc(dp, mapped_fsuid(mnt_userns, i_user_ns(VFS_I(dp))), + mapped_fsgid(mnt_userns, i_user_ns(VFS_I(dp))), prid, XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT, &udqp, &gdqp, &pdqp); if (error) @@ -1459,7 +1463,7 @@ xfs_release( if (!xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL)) return 0; - if (xfs_can_free_eofblocks(ip, false)) { + if (xfs_can_free_eofblocks(ip)) { /* * Check if the inode is being opened, written and closed * frequently and we have delayed allocation blocks outstanding @@ -1675,15 +1679,13 @@ xfs_inode_needs_inactive( /* * This file isn't being freed, so check if there are post-eof blocks - * to free. @force is true because we are evicting an inode from the - * cache. Post-eof blocks must be freed, lest we end up with broken - * free space accounting. + * to free. * * Note: don't bother with iolock here since lockdep complains about * acquiring it in reclaim context. We have the only reference to the * inode at this point anyways. */ - return xfs_can_free_eofblocks(ip, true); + return xfs_can_free_eofblocks(ip); } /* @@ -1734,15 +1736,11 @@ xfs_inactive( if (VFS_I(ip)->i_nlink != 0) { /* - * force is true because we are evicting an inode from the - * cache. Post-eof blocks must be freed, lest we end up with - * broken free space accounting. - * * Note: don't bother with iolock here since lockdep complains * about acquiring it in reclaim context. We have the only * reference to the inode at this point anyways. */ - if (xfs_can_free_eofblocks(ip, true)) + if (xfs_can_free_eofblocks(ip)) error = xfs_free_eofblocks(ip); goto out; @@ -3777,3 +3775,16 @@ xfs_inode_reload_unlinked( return error; } + +/* Returns the size of fundamental allocation unit for a file, in bytes. */ +unsigned int +xfs_inode_alloc_unitsize( + struct xfs_inode *ip) +{ + unsigned int blocks = 1; + + if (XFS_IS_REALTIME_INODE(ip)) + blocks = ip->i_mount->m_sb.sb_rextsize; + + return XFS_FSB_TO_B(ip->i_mount, blocks); +} diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index c177c92f3aa5..c4f426eadf8e 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -622,4 +622,6 @@ xfs_inode_unlinked_incomplete( int xfs_inode_reload_unlinked_bucket(struct xfs_trans *tp, struct xfs_inode *ip); int xfs_inode_reload_unlinked(struct xfs_inode *ip); +unsigned int xfs_inode_alloc_unitsize(struct xfs_inode *ip); + #endif /* __XFS_INODE_H__ */ diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index 91c847a84e10..a734ca8d8f03 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -36,6 +36,36 @@ xfs_inode_item_sort( return INODE_ITEM(lip)->ili_inode->i_ino; } +#ifdef DEBUG_EXPENSIVE +static void +xfs_inode_item_precommit_check( + struct xfs_inode *ip) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_dinode *dip; + xfs_failaddr_t fa; + + dip = kzalloc(mp->m_sb.sb_inodesize, GFP_KERNEL | GFP_NOFS); + if (!dip) { + ASSERT(dip != NULL); + return; + } + + xfs_inode_to_disk(ip, dip, 0); + xfs_dinode_calc_crc(mp, dip); + fa = xfs_dinode_verify(mp, ip->i_ino, dip); + if (fa) { + xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__, dip, + sizeof(*dip), fa); + xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); + ASSERT(fa == NULL); + } + kfree(dip); +} +#else +# define xfs_inode_item_precommit_check(ip) ((void)0) +#endif + /* * Prior to finally logging the inode, we have to ensure that all the * per-modification inode state changes are applied. This includes VFS inode @@ -168,6 +198,8 @@ xfs_inode_item_precommit( iip->ili_fields |= (flags | iip->ili_last_fields); spin_unlock(&iip->ili_lock); + xfs_inode_item_precommit_check(ip); + /* * We are done with the log item transaction dirty state, so clear it so * that it doesn't pollute future transactions. @@ -556,6 +588,9 @@ xfs_inode_to_log_dinode( memset(to->di_pad2, 0, sizeof(to->di_pad2)); uuid_copy(&to->di_uuid, &ip->i_mount->m_sb.sb_meta_uuid); to->di_v3_pad = 0; + + /* dummy value for initialisation */ + to->di_crc = 0; } else { to->di_version = 2; to->di_flushiter = ip->i_flushiter; diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index c7cb496dc345..ef3dc0778566 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -38,6 +38,7 @@ #include "xfs_reflink.h" #include "xfs_ioctl.h" #include "xfs_xattr.h" +#include "xfs_file.h" #include <linux/mount.h> #include <linux/namei.h> @@ -1127,6 +1128,17 @@ xfs_ioctl_setattr_xflags( /* Can't change realtime flag if any extents are allocated. */ if (ip->i_df.if_nextents || ip->i_delayed_blks) return -EINVAL; + + /* + * If S_DAX is enabled on this file, we can only switch the + * device if both support fsdax. We can't update S_DAX because + * there might be other threads walking down the access paths. + */ + if (IS_DAX(VFS_I(ip)) && + (mp->m_ddev_targp->bt_daxdev == NULL || + (mp->m_rtdev_targp && + mp->m_rtdev_targp->bt_daxdev == NULL))) + return -EINVAL; } if (rtflag) { diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index ab5512c0bcf7..28a1c19dfdb3 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -309,14 +309,6 @@ xfs_iomap_write_direct( if (error) goto out_unlock; - /* - * Copy any maps to caller's array and return any error. - */ - if (nimaps == 0) { - error = -ENOSPC; - goto out_unlock; - } - if (unlikely(!xfs_valid_startblock(ip, imap->br_startblock))) error = xfs_alert_fsblock_zero(ip, imap); @@ -1005,6 +997,24 @@ xfs_buffered_write_iomap_begin( } /* + * For zeroing, trim a delalloc extent that extends beyond the EOF + * block. If it starts beyond the EOF block, convert it to an + * unwritten extent. + */ + if ((flags & IOMAP_ZERO) && imap.br_startoff <= offset_fsb && + isnullstartblock(imap.br_startblock)) { + xfs_fileoff_t eof_fsb = XFS_B_TO_FSB(mp, XFS_ISIZE(ip)); + + if (offset_fsb >= eof_fsb) + goto convert_delay; + if (end_fsb > eof_fsb) { + end_fsb = eof_fsb; + xfs_trim_extent(&imap, offset_fsb, + end_fsb - offset_fsb); + } + } + + /* * Search the COW fork extent list even if we did not find a data fork * extent. This serves two purposes: first this implements the * speculative preallocation using cowextsize, so that we also unshare @@ -1105,47 +1115,48 @@ xfs_buffered_write_iomap_begin( } } -retry: - error = xfs_bmapi_reserve_delalloc(ip, allocfork, offset_fsb, - end_fsb - offset_fsb, prealloc_blocks, - allocfork == XFS_DATA_FORK ? &imap : &cmap, - allocfork == XFS_DATA_FORK ? &icur : &ccur, - allocfork == XFS_DATA_FORK ? eof : cow_eof); - switch (error) { - case 0: - break; - case -ENOSPC: - case -EDQUOT: - /* retry without any preallocation */ - trace_xfs_delalloc_enospc(ip, offset, count); - if (prealloc_blocks) { - prealloc_blocks = 0; - goto retry; - } - fallthrough; - default: - goto out_unlock; - } - if (allocfork == XFS_COW_FORK) { + error = xfs_bmapi_reserve_delalloc(ip, allocfork, offset_fsb, + end_fsb - offset_fsb, prealloc_blocks, &cmap, + &ccur, cow_eof); + if (error) + goto out_unlock; + trace_xfs_iomap_alloc(ip, offset, count, allocfork, &cmap); goto found_cow; } + error = xfs_bmapi_reserve_delalloc(ip, allocfork, offset_fsb, + end_fsb - offset_fsb, prealloc_blocks, &imap, &icur, + eof); + if (error) + goto out_unlock; + /* * Flag newly allocated delalloc blocks with IOMAP_F_NEW so we punch * them out if the write happens to fail. */ seq = xfs_iomap_inode_sequence(ip, IOMAP_F_NEW); - xfs_iunlock(ip, XFS_ILOCK_EXCL); + xfs_iunlock(ip, lockmode); trace_xfs_iomap_alloc(ip, offset, count, allocfork, &imap); return xfs_bmbt_to_iomap(ip, iomap, &imap, flags, IOMAP_F_NEW, seq); found_imap: seq = xfs_iomap_inode_sequence(ip, 0); - xfs_iunlock(ip, XFS_ILOCK_EXCL); + xfs_iunlock(ip, lockmode); return xfs_bmbt_to_iomap(ip, iomap, &imap, flags, 0, seq); +convert_delay: + xfs_iunlock(ip, lockmode); + truncate_pagecache(inode, offset); + error = xfs_bmapi_convert_delalloc(ip, XFS_DATA_FORK, offset, + iomap, NULL); + if (error) + return error; + + trace_xfs_iomap_alloc(ip, offset, count, XFS_DATA_FORK, &imap); + return 0; + found_cow: seq = xfs_iomap_inode_sequence(ip, 0); if (imap.br_startoff <= offset_fsb) { @@ -1153,17 +1164,17 @@ found_cow: if (error) goto out_unlock; seq = xfs_iomap_inode_sequence(ip, IOMAP_F_SHARED); - xfs_iunlock(ip, XFS_ILOCK_EXCL); + xfs_iunlock(ip, lockmode); return xfs_bmbt_to_iomap(ip, iomap, &cmap, flags, IOMAP_F_SHARED, seq); } xfs_trim_extent(&cmap, offset_fsb, imap.br_startoff - offset_fsb); - xfs_iunlock(ip, XFS_ILOCK_EXCL); + xfs_iunlock(ip, lockmode); return xfs_bmbt_to_iomap(ip, iomap, &cmap, flags, 0, seq); out_unlock: - xfs_iunlock(ip, XFS_ILOCK_EXCL); + xfs_iunlock(ip, lockmode); return error; } diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 6fbdc0a19e54..9ca1b8bf1f05 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -25,6 +25,7 @@ #include "xfs_error.h" #include "xfs_ioctl.h" #include "xfs_xattr.h" +#include "xfs_file.h" #include <linux/posix_acl.h> #include <linux/security.h> diff --git a/fs/xfs/xfs_iops.h b/fs/xfs/xfs_iops.h index e570dcb5df8d..73ff92355eaa 100644 --- a/fs/xfs/xfs_iops.h +++ b/fs/xfs/xfs_iops.h @@ -8,9 +8,6 @@ struct xfs_inode; -extern const struct file_operations xfs_file_operations; -extern const struct file_operations xfs_dir_file_operations; - extern ssize_t xfs_vn_listxattr(struct dentry *, char *data, size_t size); int xfs_vn_setattr_size(struct user_namespace *mnt_userns, diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c index 858e3e9eb4a8..dfd7b824e32b 100644 --- a/fs/xfs/xfs_refcount_item.c +++ b/fs/xfs/xfs_refcount_item.c @@ -252,17 +252,12 @@ static int xfs_trans_log_finish_refcount_update( struct xfs_trans *tp, struct xfs_cud_log_item *cudp, - enum xfs_refcount_intent_type type, - xfs_fsblock_t startblock, - xfs_extlen_t blockcount, - xfs_fsblock_t *new_fsb, - xfs_extlen_t *new_len, + struct xfs_refcount_intent *ri, struct xfs_btree_cur **pcur) { int error; - error = xfs_refcount_finish_one(tp, type, startblock, - blockcount, new_fsb, new_len, pcur); + error = xfs_refcount_finish_one(tp, ri, pcur); /* * Mark the transaction dirty, even on error. This ensures the @@ -378,25 +373,20 @@ xfs_refcount_update_finish_item( struct list_head *item, struct xfs_btree_cur **state) { - struct xfs_refcount_intent *refc; - xfs_fsblock_t new_fsb; - xfs_extlen_t new_aglen; + struct xfs_refcount_intent *ri; int error; - refc = container_of(item, struct xfs_refcount_intent, ri_list); - error = xfs_trans_log_finish_refcount_update(tp, CUD_ITEM(done), - refc->ri_type, refc->ri_startblock, refc->ri_blockcount, - &new_fsb, &new_aglen, state); + ri = container_of(item, struct xfs_refcount_intent, ri_list); + error = xfs_trans_log_finish_refcount_update(tp, CUD_ITEM(done), ri, + state); /* Did we run out of reservation? Requeue what we didn't finish. */ - if (!error && new_aglen > 0) { - ASSERT(refc->ri_type == XFS_REFCOUNT_INCREASE || - refc->ri_type == XFS_REFCOUNT_DECREASE); - refc->ri_startblock = new_fsb; - refc->ri_blockcount = new_aglen; + if (!error && ri->ri_blockcount > 0) { + ASSERT(ri->ri_type == XFS_REFCOUNT_INCREASE || + ri->ri_type == XFS_REFCOUNT_DECREASE); return -EAGAIN; } - kmem_cache_free(xfs_refcount_intent_cache, refc); + kmem_cache_free(xfs_refcount_intent_cache, ri); return error; } @@ -463,18 +453,14 @@ xfs_cui_item_recover( struct xfs_log_item *lip, struct list_head *capture_list) { - struct xfs_bmbt_irec irec; + struct xfs_trans_res resv; struct xfs_cui_log_item *cuip = CUI_ITEM(lip); - struct xfs_phys_extent *refc; struct xfs_cud_log_item *cudp; struct xfs_trans *tp; struct xfs_btree_cur *rcur = NULL; struct xfs_mount *mp = lip->li_log->l_mp; - xfs_fsblock_t new_fsb; - xfs_extlen_t new_len; unsigned int refc_type; bool requeue_only = false; - enum xfs_refcount_intent_type type; int i; int error = 0; @@ -505,14 +491,18 @@ xfs_cui_item_recover( * doesn't fit. We need to reserve enough blocks to handle a * full btree split on either end of the refcount range. */ - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, - mp->m_refc_maxlevels * 2, 0, XFS_TRANS_RESERVE, &tp); + resv = xlog_recover_resv(&M_RES(mp)->tr_itruncate); + error = xfs_trans_alloc(mp, &resv, mp->m_refc_maxlevels * 2, 0, + XFS_TRANS_RESERVE, &tp); if (error) return error; cudp = xfs_trans_get_cud(tp, cuip); for (i = 0; i < cuip->cui_format.cui_nextents; i++) { + struct xfs_refcount_intent fake = { }; + struct xfs_phys_extent *refc; + refc = &cuip->cui_format.cui_extents[i]; refc_type = refc->pe_flags & XFS_REFCOUNT_EXTENT_TYPE_MASK; switch (refc_type) { @@ -520,7 +510,7 @@ xfs_cui_item_recover( case XFS_REFCOUNT_DECREASE: case XFS_REFCOUNT_ALLOC_COW: case XFS_REFCOUNT_FREE_COW: - type = refc_type; + fake.ri_type = refc_type; break; default: XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, @@ -529,13 +519,12 @@ xfs_cui_item_recover( error = -EFSCORRUPTED; goto abort_error; } - if (requeue_only) { - new_fsb = refc->pe_startblock; - new_len = refc->pe_len; - } else + + fake.ri_startblock = refc->pe_startblock; + fake.ri_blockcount = refc->pe_len; + if (!requeue_only) error = xfs_trans_log_finish_refcount_update(tp, cudp, - type, refc->pe_startblock, refc->pe_len, - &new_fsb, &new_len, &rcur); + &fake, &rcur); if (error == -EFSCORRUPTED) XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, &cuip->cui_format, @@ -544,10 +533,13 @@ xfs_cui_item_recover( goto abort_error; /* Requeue what we didn't finish. */ - if (new_len > 0) { - irec.br_startblock = new_fsb; - irec.br_blockcount = new_len; - switch (type) { + if (fake.ri_blockcount > 0) { + struct xfs_bmbt_irec irec = { + .br_startblock = fake.ri_startblock, + .br_blockcount = fake.ri_blockcount, + }; + + switch (fake.ri_type) { case XFS_REFCOUNT_INCREASE: xfs_refcount_increase_extent(tp, &irec); break; diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index cbdc23217a42..d539487eaf1a 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -431,13 +431,6 @@ xfs_reflink_fill_cow_hole( if (error) return error; - /* - * Allocation succeeded but the requested range was not even partially - * satisfied? Bail out! - */ - if (nimaps == 0) - return -ENOSPC; - convert: return xfs_reflink_convert_unwritten(ip, imap, cmap, convert_now); @@ -500,13 +493,6 @@ xfs_reflink_fill_delalloc( error = xfs_trans_commit(tp); if (error) return error; - - /* - * Allocation succeeded but the requested range was not even - * partially satisfied? Bail out! - */ - if (nimaps == 0) - return -ENOSPC; } while (cmap->br_startoff + cmap->br_blockcount <= imap->br_startoff); return xfs_reflink_convert_unwritten(ip, imap, cmap, convert_now); @@ -618,8 +604,11 @@ xfs_reflink_cancel_cow_blocks( xfs_refcount_free_cow_extent(*tpp, del.br_startblock, del.br_blockcount); - xfs_free_extent_later(*tpp, del.br_startblock, - del.br_blockcount, NULL); + error = xfs_free_extent_later(*tpp, del.br_startblock, + del.br_blockcount, NULL, + XFS_AG_RESV_NONE); + if (error) + break; /* Roll the transaction */ error = xfs_defer_finish(tpp); @@ -729,12 +718,6 @@ xfs_reflink_end_cow_extent( int nmaps; int error; - /* No COW extents? That's easy! */ - if (ifp->if_bytes == 0) { - *offset_fsb = end_fsb; - return 0; - } - resblks = XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK); error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, XFS_TRANS_RESERVE, &tp); diff --git a/fs/xfs/xfs_rmap_item.c b/fs/xfs/xfs_rmap_item.c index 534504ede1a3..2043cea261c0 100644 --- a/fs/xfs/xfs_rmap_item.c +++ b/fs/xfs/xfs_rmap_item.c @@ -492,6 +492,7 @@ xfs_rui_item_recover( struct xfs_log_item *lip, struct list_head *capture_list) { + struct xfs_trans_res resv; struct xfs_rui_log_item *ruip = RUI_ITEM(lip); struct xfs_map_extent *rmap; struct xfs_rud_log_item *rudp; @@ -519,8 +520,9 @@ xfs_rui_item_recover( } } - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, - mp->m_rmap_maxlevels, 0, XFS_TRANS_RESERVE, &tp); + resv = xlog_recover_resv(&M_RES(mp)->tr_itruncate); + error = xfs_trans_alloc(mp, &resv, mp->m_rmap_maxlevels, 0, + XFS_TRANS_RESERVE, &tp); if (error) return error; rudp = xfs_trans_get_rud(tp, ruip); diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c index 0bfbbc1dd0da..fc21b4e81ade 100644 --- a/fs/xfs/xfs_rtalloc.c +++ b/fs/xfs/xfs_rtalloc.c @@ -19,6 +19,7 @@ #include "xfs_icache.h" #include "xfs_rtalloc.h" #include "xfs_sb.h" +#include "xfs_rtbitmap.h" /* * Read and return the summary information for a given extent size, @@ -317,7 +318,7 @@ xfs_rtallocate_extent_block( /* * Searched the whole thing & didn't find a maxlen free extent. */ - if (minlen < maxlen && besti != -1) { + if (minlen <= maxlen && besti != -1) { xfs_extlen_t p; /* amount to trim length by */ /* @@ -839,8 +840,6 @@ xfs_growfs_rt_alloc( nmap = 1; error = xfs_bmapi_write(tp, ip, oblocks, nblocks - oblocks, XFS_BMAPI_METADATA, 0, &map, &nmap); - if (!error && nmap < 1) - error = -ENOSPC; if (error) goto out_trans_cancel; /* @@ -917,6 +916,39 @@ xfs_alloc_rsum_cache( } /* + * If we changed the rt extent size (meaning there was no rt volume previously) + * and the root directory had EXTSZINHERIT and RTINHERIT set, it's possible + * that the extent size hint on the root directory is no longer congruent with + * the new rt extent size. Log the rootdir inode to fix this. + */ +static int +xfs_growfs_rt_fixup_extsize( + struct xfs_mount *mp) +{ + struct xfs_inode *ip = mp->m_rootip; + struct xfs_trans *tp; + int error = 0; + + xfs_ilock(ip, XFS_IOLOCK_EXCL); + if (!(ip->i_diflags & XFS_DIFLAG_RTINHERIT) || + !(ip->i_diflags & XFS_DIFLAG_EXTSZINHERIT)) + goto out_iolock; + + error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_ichange, 0, 0, false, + &tp); + if (error) + goto out_iolock; + + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); + error = xfs_trans_commit(tp); + xfs_iunlock(ip, XFS_ILOCK_EXCL); + +out_iolock: + xfs_iunlock(ip, XFS_IOLOCK_EXCL); + return error; +} + +/* * Visible (exported) functions. */ @@ -945,6 +977,7 @@ xfs_growfs_rt( xfs_sb_t *sbp; /* old superblock */ xfs_fsblock_t sumbno; /* summary block number */ uint8_t *rsum_cache; /* old summary cache */ + xfs_agblock_t old_rextsize = mp->m_sb.sb_rextsize; sbp = &mp->m_sb; @@ -954,34 +987,39 @@ xfs_growfs_rt( /* Needs to have been mounted with an rt device. */ if (!XFS_IS_REALTIME_MOUNT(mp)) return -EINVAL; + + if (!mutex_trylock(&mp->m_growlock)) + return -EWOULDBLOCK; /* * Mount should fail if the rt bitmap/summary files don't load, but * we'll check anyway. */ + error = -EINVAL; if (!mp->m_rbmip || !mp->m_rsumip) - return -EINVAL; + goto out_unlock; /* Shrink not supported. */ if (in->newblocks <= sbp->sb_rblocks) - return -EINVAL; + goto out_unlock; /* Can only change rt extent size when adding rt volume. */ if (sbp->sb_rblocks > 0 && in->extsize != sbp->sb_rextsize) - return -EINVAL; + goto out_unlock; /* Range check the extent size. */ if (XFS_FSB_TO_B(mp, in->extsize) > XFS_MAX_RTEXTSIZE || XFS_FSB_TO_B(mp, in->extsize) < XFS_MIN_RTEXTSIZE) - return -EINVAL; + goto out_unlock; /* Unsupported realtime features. */ + error = -EOPNOTSUPP; if (xfs_has_rmapbt(mp) || xfs_has_reflink(mp) || xfs_has_quota(mp)) - return -EOPNOTSUPP; + goto out_unlock; nrblocks = in->newblocks; error = xfs_sb_validate_fsb_count(sbp, nrblocks); if (error) - return error; + goto out_unlock; /* * Read in the last block of the device, make sure it exists. */ @@ -989,7 +1027,7 @@ xfs_growfs_rt( XFS_FSB_TO_BB(mp, nrblocks - 1), XFS_FSB_TO_BB(mp, 1), 0, &bp, NULL); if (error) - return error; + goto out_unlock; xfs_buf_relse(bp); /* @@ -997,8 +1035,12 @@ xfs_growfs_rt( */ nrextents = nrblocks; do_div(nrextents, in->extsize); + if (!xfs_validate_rtextents(nrextents)) { + error = -EINVAL; + goto out_unlock; + } nrbmblocks = howmany_64(nrextents, NBBY * sbp->sb_blocksize); - nrextslog = xfs_highbit32(nrextents); + nrextslog = xfs_compute_rextslog(nrextents); nrsumlevels = nrextslog + 1; nrsumsize = (uint)sizeof(xfs_suminfo_t) * nrsumlevels * nrbmblocks; nrsumblocks = XFS_B_TO_FSB(mp, nrsumsize); @@ -1008,8 +1050,11 @@ xfs_growfs_rt( * the log. This prevents us from getting a log overflow, * since we'll log basically the whole summary file at once. */ - if (nrsumblocks > (mp->m_sb.sb_logblocks >> 1)) - return -EINVAL; + if (nrsumblocks > (mp->m_sb.sb_logblocks >> 1)) { + error = -EINVAL; + goto out_unlock; + } + /* * Get the old block counts for bitmap and summary inodes. * These can't change since other growfs callers are locked out. @@ -1021,10 +1066,10 @@ xfs_growfs_rt( */ error = xfs_growfs_rt_alloc(mp, rbmblocks, nrbmblocks, mp->m_rbmip); if (error) - return error; + goto out_unlock; error = xfs_growfs_rt_alloc(mp, rsumblocks, nrsumblocks, mp->m_rsumip); if (error) - return error; + goto out_unlock; rsum_cache = mp->m_rsum_cache; if (nrbmblocks != sbp->sb_rbmblocks) @@ -1060,13 +1105,16 @@ xfs_growfs_rt( nsbp->sb_rextents = nsbp->sb_rblocks; do_div(nsbp->sb_rextents, nsbp->sb_rextsize); ASSERT(nsbp->sb_rextents != 0); - nsbp->sb_rextslog = xfs_highbit32(nsbp->sb_rextents); + nsbp->sb_rextslog = xfs_compute_rextslog(nsbp->sb_rextents); nrsumlevels = nmp->m_rsumlevels = nsbp->sb_rextslog + 1; nrsumsize = (uint)sizeof(xfs_suminfo_t) * nrsumlevels * nsbp->sb_rbmblocks; nrsumblocks = XFS_B_TO_FSB(mp, nrsumsize); nmp->m_rsumsize = nrsumsize = XFS_FSB_TO_B(mp, nrsumblocks); + /* recompute growfsrt reservation from new rsumsize */ + xfs_trans_resv_calc(nmp, &nmp->m_resv); + /* * Start a transaction, get the log reservation. */ @@ -1150,6 +1198,8 @@ error_cancel: */ mp->m_rsumlevels = nrsumlevels; mp->m_rsumsize = nrsumsize; + /* recompute growfsrt reservation from new rsumsize */ + xfs_trans_resv_calc(mp, &mp->m_resv); error = xfs_trans_commit(tp); if (error) @@ -1161,6 +1211,12 @@ error_cancel: if (error) goto out_free; + if (old_rextsize != in->extsize) { + error = xfs_growfs_rt_fixup_extsize(mp); + if (error) + goto out_free; + } + /* Update secondary superblocks now the physical grow has completed */ error = xfs_update_secondary_sbs(mp); @@ -1184,6 +1240,8 @@ out_free: } } +out_unlock: + mutex_unlock(&mp->m_growlock); return error; } diff --git a/fs/xfs/xfs_rtalloc.h b/fs/xfs/xfs_rtalloc.h index 65c284e9d33e..11859c259a1c 100644 --- a/fs/xfs/xfs_rtalloc.h +++ b/fs/xfs/xfs_rtalloc.h @@ -11,22 +11,6 @@ struct xfs_mount; struct xfs_trans; -/* - * XXX: Most of the realtime allocation functions deal in units of realtime - * extents, not realtime blocks. This looks funny when paired with the type - * name and screams for a larger cleanup. - */ -struct xfs_rtalloc_rec { - xfs_rtblock_t ar_startext; - xfs_rtblock_t ar_extcount; -}; - -typedef int (*xfs_rtalloc_query_range_fn)( - struct xfs_mount *mp, - struct xfs_trans *tp, - const struct xfs_rtalloc_rec *rec, - void *priv); - #ifdef CONFIG_XFS_RT /* * Function prototypes for exported functions. @@ -48,19 +32,6 @@ xfs_rtallocate_extent( xfs_extlen_t prod, /* extent product factor */ xfs_rtblock_t *rtblock); /* out: start block allocated */ -/* - * Free an extent in the realtime subvolume. Length is expressed in - * realtime extents, as is the block number. - */ -int /* error */ -xfs_rtfree_extent( - struct xfs_trans *tp, /* transaction pointer */ - xfs_rtblock_t bno, /* starting block number to free */ - xfs_extlen_t len); /* length of extent freed */ - -/* Same as above, but in units of rt blocks. */ -int xfs_rtfree_blocks(struct xfs_trans *tp, xfs_fsblock_t rtbno, - xfs_filblks_t rtlen); /* * Initialize realtime fields in the mount structure. @@ -102,55 +73,11 @@ xfs_growfs_rt( struct xfs_mount *mp, /* file system mount structure */ xfs_growfs_rt_t *in); /* user supplied growfs struct */ -/* - * From xfs_rtbitmap.c - */ -int xfs_rtbuf_get(struct xfs_mount *mp, struct xfs_trans *tp, - xfs_rtblock_t block, int issum, struct xfs_buf **bpp); -int xfs_rtcheck_range(struct xfs_mount *mp, struct xfs_trans *tp, - xfs_rtblock_t start, xfs_extlen_t len, int val, - xfs_rtblock_t *new, int *stat); -int xfs_rtfind_back(struct xfs_mount *mp, struct xfs_trans *tp, - xfs_rtblock_t start, xfs_rtblock_t limit, - xfs_rtblock_t *rtblock); -int xfs_rtfind_forw(struct xfs_mount *mp, struct xfs_trans *tp, - xfs_rtblock_t start, xfs_rtblock_t limit, - xfs_rtblock_t *rtblock); -int xfs_rtmodify_range(struct xfs_mount *mp, struct xfs_trans *tp, - xfs_rtblock_t start, xfs_extlen_t len, int val); -int xfs_rtmodify_summary_int(struct xfs_mount *mp, struct xfs_trans *tp, - int log, xfs_rtblock_t bbno, int delta, - struct xfs_buf **rbpp, xfs_fsblock_t *rsb, - xfs_suminfo_t *sum); -int xfs_rtmodify_summary(struct xfs_mount *mp, struct xfs_trans *tp, int log, - xfs_rtblock_t bbno, int delta, struct xfs_buf **rbpp, - xfs_fsblock_t *rsb); -int xfs_rtfree_range(struct xfs_mount *mp, struct xfs_trans *tp, - xfs_rtblock_t start, xfs_extlen_t len, - struct xfs_buf **rbpp, xfs_fsblock_t *rsb); -int xfs_rtalloc_query_range(struct xfs_mount *mp, struct xfs_trans *tp, - const struct xfs_rtalloc_rec *low_rec, - const struct xfs_rtalloc_rec *high_rec, - xfs_rtalloc_query_range_fn fn, void *priv); -int xfs_rtalloc_query_all(struct xfs_mount *mp, struct xfs_trans *tp, - xfs_rtalloc_query_range_fn fn, - void *priv); -bool xfs_verify_rtbno(struct xfs_mount *mp, xfs_rtblock_t rtbno); -int xfs_rtalloc_extent_is_free(struct xfs_mount *mp, struct xfs_trans *tp, - xfs_rtblock_t start, xfs_extlen_t len, - bool *is_free); int xfs_rtalloc_reinit_frextents(struct xfs_mount *mp); #else # define xfs_rtallocate_extent(t,b,min,max,l,f,p,rb) (-ENOSYS) -# define xfs_rtfree_extent(t,b,l) (-ENOSYS) -# define xfs_rtfree_blocks(t,rb,rl) (-ENOSYS) # define xfs_rtpick_extent(m,t,l,rb) (-ENOSYS) # define xfs_growfs_rt(mp,in) (-ENOSYS) -# define xfs_rtalloc_query_range(m,t,l,h,f,p) (-ENOSYS) -# define xfs_rtalloc_query_all(m,t,f,p) (-ENOSYS) -# define xfs_rtbuf_get(m,t,b,i,p) (-ENOSYS) -# define xfs_verify_rtbno(m, r) (false) -# define xfs_rtalloc_extent_is_free(m,t,s,l,i) (-ENOSYS) # define xfs_rtalloc_reinit_frextents(m) (0) static inline int /* error */ xfs_rtmount_init( diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c index 8389f3ef88ef..78bd02a98aa5 100644 --- a/fs/xfs/xfs_symlink.c +++ b/fs/xfs/xfs_symlink.c @@ -191,10 +191,12 @@ xfs_symlink( prid = xfs_get_initial_prid(dp); /* - * Make sure that we have allocated dquot(s) on disk. + * Make sure that we have allocated dquot(s) on disk. The uid/gid + * computation code must match what the VFS uses to assign i_[ug]id. + * INHERIT adjusts the gid computation for setgid/grpid systems. */ - error = xfs_qm_vop_dqalloc(dp, mapped_fsuid(mnt_userns, &init_user_ns), - mapped_fsgid(mnt_userns, &init_user_ns), prid, + error = xfs_qm_vop_dqalloc(dp, mapped_fsuid(mnt_userns, i_user_ns(VFS_I(dp))), + mapped_fsgid(mnt_userns, i_user_ns(VFS_I(dp))), prid, XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT, &udqp, &gdqp, &pdqp); if (error) diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index 0cd62031e53f..a9e3081b6625 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -3208,17 +3208,14 @@ DEFINE_REFCOUNT_DEFERRED_EVENT(xfs_refcount_deferred); TRACE_EVENT(xfs_refcount_finish_one_leftover, TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, - int type, xfs_agblock_t agbno, xfs_extlen_t len, - xfs_agblock_t new_agbno, xfs_extlen_t new_len), - TP_ARGS(mp, agno, type, agbno, len, new_agbno, new_len), + int type, xfs_agblock_t agbno, xfs_extlen_t len), + TP_ARGS(mp, agno, type, agbno, len), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_agnumber_t, agno) __field(int, type) __field(xfs_agblock_t, agbno) __field(xfs_extlen_t, len) - __field(xfs_agblock_t, new_agbno) - __field(xfs_extlen_t, new_len) ), TP_fast_assign( __entry->dev = mp->m_super->s_dev; @@ -3226,17 +3223,13 @@ TRACE_EVENT(xfs_refcount_finish_one_leftover, __entry->type = type; __entry->agbno = agbno; __entry->len = len; - __entry->new_agbno = new_agbno; - __entry->new_len = new_len; ), - TP_printk("dev %d:%d type %d agno 0x%x agbno 0x%x fsbcount 0x%x new_agbno 0x%x new_fsbcount 0x%x", + TP_printk("dev %d:%d type %d agno 0x%x agbno 0x%x fsbcount 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->type, __entry->agno, __entry->agbno, - __entry->len, - __entry->new_agbno, - __entry->new_len) + __entry->len) ); /* simple inode-based error/%ip tracepoint class */ @@ -3498,6 +3491,31 @@ DEFINE_FSMAP_EVENT(xfs_fsmap_low_key); DEFINE_FSMAP_EVENT(xfs_fsmap_high_key); DEFINE_FSMAP_EVENT(xfs_fsmap_mapping); +DECLARE_EVENT_CLASS(xfs_fsmap_linear_class, + TP_PROTO(struct xfs_mount *mp, u32 keydev, uint64_t bno), + TP_ARGS(mp, keydev, bno), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(dev_t, keydev) + __field(xfs_fsblock_t, bno) + ), + TP_fast_assign( + __entry->dev = mp->m_super->s_dev; + __entry->keydev = new_decode_dev(keydev); + __entry->bno = bno; + ), + TP_printk("dev %d:%d keydev %d:%d bno 0x%llx", + MAJOR(__entry->dev), MINOR(__entry->dev), + MAJOR(__entry->keydev), MINOR(__entry->keydev), + __entry->bno) +) +#define DEFINE_FSMAP_LINEAR_EVENT(name) \ +DEFINE_EVENT(xfs_fsmap_linear_class, name, \ + TP_PROTO(struct xfs_mount *mp, u32 keydev, uint64_t bno), \ + TP_ARGS(mp, keydev, bno)) +DEFINE_FSMAP_LINEAR_EVENT(xfs_fsmap_low_key_linear); +DEFINE_FSMAP_LINEAR_EVENT(xfs_fsmap_high_key_linear); + DECLARE_EVENT_CLASS(xfs_getfsmap_class, TP_PROTO(struct xfs_mount *mp, struct xfs_fsmap *fsmap), TP_ARGS(mp, fsmap), |