diff options
Diffstat (limited to 'fs')
295 files changed, 12279 insertions, 6481 deletions
diff --git a/fs/Kconfig b/fs/Kconfig index aa4c12282301..462253ae483a 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -203,7 +203,7 @@ config TMPFS_XATTR config TMPFS_INODE64 bool "Use 64-bit ino_t by default in tmpfs" - depends on TMPFS && 64BIT + depends on TMPFS && 64BIT && !(S390 || ALPHA) default n help tmpfs has historically used only inode numbers as wide as an unsigned @@ -333,6 +333,10 @@ config NFS_COMMON depends on NFSD || NFS_FS || LOCKD default y +config NFS_V4_2_SSC_HELPER + tristate + default y if NFS_V4=y || NFS_FS=y + source "net/sunrpc/Kconfig" source "fs/ceph/Kconfig" source "fs/cifs/Kconfig" diff --git a/fs/Kconfig.binfmt b/fs/Kconfig.binfmt index 885da6d983b4..c6f1c8c1934e 100644 --- a/fs/Kconfig.binfmt +++ b/fs/Kconfig.binfmt @@ -29,7 +29,7 @@ config BINFMT_ELF latest version). config COMPAT_BINFMT_ELF - bool + def_bool y depends on COMPAT && BINFMT_ELF select ELFCORE @@ -45,7 +45,7 @@ config ARCH_USE_GNU_PROPERTY config BINFMT_ELF_FDPIC bool "Kernel support for FDPIC ELF binaries" default y if !BINFMT_ELF - depends on (ARM || (SUPERH && !MMU) || C6X) + depends on (ARM || (SUPERH && !MMU)) select ELFCORE help ELF FDPIC binaries are based on ELF, but allow the individual load diff --git a/fs/Makefile b/fs/Makefile index 999d1a23f036..3215fe205256 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -64,7 +64,6 @@ obj-$(CONFIG_SYSFS) += sysfs/ obj-$(CONFIG_CONFIGFS_FS) += configfs/ obj-y += devpts/ -obj-$(CONFIG_PROFILING) += dcookies.o obj-$(CONFIG_DLM) += dlm/ # Do not add any filesystems before this line diff --git a/fs/affs/namei.c b/fs/affs/namei.c index 41c5749f4db7..5400a876d73f 100644 --- a/fs/affs/namei.c +++ b/fs/affs/namei.c @@ -460,8 +460,10 @@ affs_xrename(struct inode *old_dir, struct dentry *old_dentry, return -EIO; bh_new = affs_bread(sb, d_inode(new_dentry)->i_ino); - if (!bh_new) + if (!bh_new) { + affs_brelse(bh_old); return -EIO; + } /* Remove old header from its parent directory. */ affs_lock_dir(old_dir); diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 9068d5578a26..7bd659ad959e 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -350,7 +350,7 @@ static int afs_dir_iterate_block(struct afs_vnode *dvnode, unsigned blkoff) { union afs_xdr_dirent *dire; - unsigned offset, next, curr; + unsigned offset, next, curr, nr_slots; size_t nlen; int tmp; @@ -363,13 +363,12 @@ static int afs_dir_iterate_block(struct afs_vnode *dvnode, offset < AFS_DIR_SLOTS_PER_BLOCK; offset = next ) { - next = offset + 1; - /* skip entries marked unused in the bitmap */ if (!(block->hdr.bitmap[offset / 8] & (1 << (offset % 8)))) { _debug("ENT[%zu.%u]: unused", blkoff / sizeof(union afs_xdr_dir_block), offset); + next = offset + 1; if (offset >= curr) ctx->pos = blkoff + next * sizeof(union afs_xdr_dirent); @@ -381,35 +380,39 @@ static int afs_dir_iterate_block(struct afs_vnode *dvnode, nlen = strnlen(dire->u.name, sizeof(*block) - offset * sizeof(union afs_xdr_dirent)); + if (nlen > AFSNAMEMAX - 1) { + _debug("ENT[%zu]: name too long (len %u/%zu)", + blkoff / sizeof(union afs_xdr_dir_block), + offset, nlen); + return afs_bad(dvnode, afs_file_error_dir_name_too_long); + } _debug("ENT[%zu.%u]: %s %zu \"%s\"", blkoff / sizeof(union afs_xdr_dir_block), offset, (offset < curr ? "skip" : "fill"), nlen, dire->u.name); - /* work out where the next possible entry is */ - for (tmp = nlen; tmp > 15; tmp -= sizeof(union afs_xdr_dirent)) { - if (next >= AFS_DIR_SLOTS_PER_BLOCK) { - _debug("ENT[%zu.%u]:" - " %u travelled beyond end dir block" - " (len %u/%zu)", - blkoff / sizeof(union afs_xdr_dir_block), - offset, next, tmp, nlen); - return afs_bad(dvnode, afs_file_error_dir_over_end); - } - if (!(block->hdr.bitmap[next / 8] & - (1 << (next % 8)))) { - _debug("ENT[%zu.%u]:" - " %u unmarked extension (len %u/%zu)", + nr_slots = afs_dir_calc_slots(nlen); + next = offset + nr_slots; + if (next > AFS_DIR_SLOTS_PER_BLOCK) { + _debug("ENT[%zu.%u]:" + " %u extends beyond end dir block" + " (len %zu)", + blkoff / sizeof(union afs_xdr_dir_block), + offset, next, nlen); + return afs_bad(dvnode, afs_file_error_dir_over_end); + } + + /* Check that the name-extension dirents are all allocated */ + for (tmp = 1; tmp < nr_slots; tmp++) { + unsigned int ix = offset + tmp; + if (!(block->hdr.bitmap[ix / 8] & (1 << (ix % 8)))) { + _debug("ENT[%zu.u]:" + " %u unmarked extension (%u/%u)", blkoff / sizeof(union afs_xdr_dir_block), - offset, next, tmp, nlen); + offset, tmp, nr_slots); return afs_bad(dvnode, afs_file_error_dir_unmarked_ext); } - - _debug("ENT[%zu.%u]: ext %u/%zu", - blkoff / sizeof(union afs_xdr_dir_block), - next, tmp, nlen); - next++; } /* skip if starts before the current position */ diff --git a/fs/afs/dir_edit.c b/fs/afs/dir_edit.c index 2ffe09abae7f..f4600c1353ad 100644 --- a/fs/afs/dir_edit.c +++ b/fs/afs/dir_edit.c @@ -215,8 +215,7 @@ void afs_edit_dir_add(struct afs_vnode *vnode, } /* Work out how many slots we're going to need. */ - need_slots = round_up(12 + name->len + 1 + 4, AFS_DIR_DIRENT_SIZE); - need_slots /= AFS_DIR_DIRENT_SIZE; + need_slots = afs_dir_calc_slots(name->len); meta_page = kmap(page0); meta = &meta_page->blocks[0]; @@ -393,8 +392,7 @@ void afs_edit_dir_remove(struct afs_vnode *vnode, } /* Work out how many slots we're going to discard. */ - need_slots = round_up(12 + name->len + 1 + 4, AFS_DIR_DIRENT_SIZE); - need_slots /= AFS_DIR_DIRENT_SIZE; + need_slots = afs_dir_calc_slots(name->len); meta_page = kmap(page0); meta = &meta_page->blocks[0]; diff --git a/fs/afs/main.c b/fs/afs/main.c index accdd8970e7c..b2975256dadb 100644 --- a/fs/afs/main.c +++ b/fs/afs/main.c @@ -193,7 +193,7 @@ static int __init afs_init(void) goto error_cache; #endif - ret = register_pernet_subsys(&afs_net_ops); + ret = register_pernet_device(&afs_net_ops); if (ret < 0) goto error_net; @@ -213,7 +213,7 @@ static int __init afs_init(void) error_proc: afs_fs_exit(); error_fs: - unregister_pernet_subsys(&afs_net_ops); + unregister_pernet_device(&afs_net_ops); error_net: #ifdef CONFIG_AFS_FSCACHE fscache_unregister_netfs(&afs_cache_netfs); @@ -244,7 +244,7 @@ static void __exit afs_exit(void) proc_remove(afs_proc_symlink); afs_fs_exit(); - unregister_pernet_subsys(&afs_net_ops); + unregister_pernet_device(&afs_net_ops); #ifdef CONFIG_AFS_FSCACHE fscache_unregister_netfs(&afs_cache_netfs); #endif diff --git a/fs/afs/xdr_fs.h b/fs/afs/xdr_fs.h index 94f1f398eefa..8ca868164507 100644 --- a/fs/afs/xdr_fs.h +++ b/fs/afs/xdr_fs.h @@ -54,10 +54,16 @@ union afs_xdr_dirent { __be16 hash_next; __be32 vnode; __be32 unique; - u8 name[16]; - u8 overflow[4]; /* if any char of the name (inc - * NUL) reaches here, consume - * the next dirent too */ + u8 name[]; + /* When determining the number of dirent slots needed to + * represent a directory entry, name should be assumed to be 16 + * bytes, due to a now-standardised (mis)calculation, but it is + * in fact 20 bytes in size. afs_dir_calc_slots() should be + * used for this. + * + * For names longer than (16 or) 20 bytes, extra slots should + * be annexed to this one using the extended_name format. + */ } u; u8 extended_name[32]; } __packed; @@ -96,4 +102,15 @@ struct afs_xdr_dir_page { union afs_xdr_dir_block blocks[AFS_DIR_BLOCKS_PER_PAGE]; }; +/* + * Calculate the number of dirent slots required for any given name length. + * The calculation is made assuming the part of the name in the first slot is + * 16 bytes, rather than 20, but this miscalculation is now standardised. + */ +static inline unsigned int afs_dir_calc_slots(size_t name_len) +{ + name_len++; /* NUL-terminated */ + return 1 + ((name_len + 15) / AFS_DIR_DIRENT_SIZE); +} + #endif /* XDR_FS_H */ diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 950bc177238a..b12ba98ae9f5 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -186,6 +186,7 @@ create_elf_tables(struct linux_binprm *bprm, const struct elfhdr *exec, unsigned char k_rand_bytes[16]; int items; elf_addr_t *elf_info; + elf_addr_t flags = 0; int ei_index; const struct cred *cred = current_cred(); struct vm_area_struct *vma; @@ -260,7 +261,9 @@ create_elf_tables(struct linux_binprm *bprm, const struct elfhdr *exec, NEW_AUX_ENT(AT_PHENT, sizeof(struct elf_phdr)); NEW_AUX_ENT(AT_PHNUM, exec->e_phnum); NEW_AUX_ENT(AT_BASE, interp_load_addr); - NEW_AUX_ENT(AT_FLAGS, 0); + if (bprm->interp_flags & BINPRM_FLAGS_PRESERVE_ARGV0) + flags |= AT_FLAGS_PRESERVE_ARGV0; + NEW_AUX_ENT(AT_FLAGS, flags); NEW_AUX_ENT(AT_ENTRY, e_entry); NEW_AUX_ENT(AT_UID, from_kuid_munged(cred->user_ns, cred->uid)); NEW_AUX_ENT(AT_EUID, from_kuid_munged(cred->user_ns, cred->euid)); @@ -1495,7 +1498,7 @@ static void fill_note(struct memelfnote *note, const char *name, int type, * fill up all the fields in prstatus from the given task struct, except * registers which need to be filled up separately. */ -static void fill_prstatus(struct elf_prstatus *prstatus, +static void fill_prstatus(struct elf_prstatus_common *prstatus, struct task_struct *p, long signr) { prstatus->pr_info.si_signo = prstatus->pr_cursig = signr; @@ -1717,11 +1720,11 @@ static void do_thread_regset_writeback(struct task_struct *task, } #ifndef PRSTATUS_SIZE -#define PRSTATUS_SIZE(S, R) sizeof(S) +#define PRSTATUS_SIZE sizeof(struct elf_prstatus) #endif #ifndef SET_PR_FPVALID -#define SET_PR_FPVALID(S, V, R) ((S)->pr_fpvalid = (V)) +#define SET_PR_FPVALID(S) ((S)->pr_fpvalid = 1) #endif static int fill_thread_core_info(struct elf_thread_core_info *t, @@ -1729,7 +1732,6 @@ static int fill_thread_core_info(struct elf_thread_core_info *t, long signr, size_t *total) { unsigned int i; - int regset0_size; /* * NT_PRSTATUS is the one special case, because the regset data @@ -1737,14 +1739,12 @@ static int fill_thread_core_info(struct elf_thread_core_info *t, * than being the whole note contents. We fill the reset in here. * We assume that regset 0 is NT_PRSTATUS. */ - fill_prstatus(&t->prstatus, t->task, signr); - regset0_size = regset_get(t->task, &view->regsets[0], + fill_prstatus(&t->prstatus.common, t->task, signr); + regset_get(t->task, &view->regsets[0], sizeof(t->prstatus.pr_reg), &t->prstatus.pr_reg); - if (regset0_size < 0) - return 0; fill_note(&t->notes[0], "CORE", NT_PRSTATUS, - PRSTATUS_SIZE(t->prstatus, regset0_size), &t->prstatus); + PRSTATUS_SIZE, &t->prstatus); *total += notesize(&t->notes[0]); do_thread_regset_writeback(t->task, &view->regsets[0]); @@ -1772,7 +1772,7 @@ static int fill_thread_core_info(struct elf_thread_core_info *t, continue; if (is_fpreg) - SET_PR_FPVALID(&t->prstatus, 1, regset0_size); + SET_PR_FPVALID(&t->prstatus); fill_note(&t->notes[i], is_fpreg ? "CORE" : "LINUX", note_type, ret, data); @@ -1961,7 +1961,7 @@ static int elf_dump_thread_status(long signr, struct elf_thread_status *t) struct task_struct *p = t->thread; t->num_notes = 0; - fill_prstatus(&t->prstatus, p, signr); + fill_prstatus(&t->prstatus.common, p, signr); elf_core_copy_task_regs(p, &t->prstatus.pr_reg); fill_note(&t->notes[0], "CORE", NT_PRSTATUS, sizeof(t->prstatus), @@ -2040,7 +2040,7 @@ static int fill_note_info(struct elfhdr *elf, int phdrs, } /* now collect the dump for the current */ memset(info->prstatus, 0, sizeof(*info->prstatus)); - fill_prstatus(info->prstatus, current, siginfo->si_signo); + fill_prstatus(&info->prstatus->common, current, siginfo->si_signo); elf_core_copy_regs(&info->prstatus->pr_reg, regs); /* Set up header */ diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index be4062b8ba75..3cfd6cd46f26 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -506,6 +506,7 @@ static int create_elf_fdpic_tables(struct linux_binprm *bprm, char __user *u_platform, *u_base_platform, *p; int loop; int nr; /* reset for each csp adjustment */ + unsigned long flags = 0; #ifdef CONFIG_MMU /* In some cases (e.g. Hyper-Threading), we want to avoid L1 evictions @@ -648,7 +649,9 @@ static int create_elf_fdpic_tables(struct linux_binprm *bprm, NEW_AUX_ENT(AT_PHENT, sizeof(struct elf_phdr)); NEW_AUX_ENT(AT_PHNUM, exec_params->hdr.e_phnum); NEW_AUX_ENT(AT_BASE, interp_params->elfhdr_addr); - NEW_AUX_ENT(AT_FLAGS, 0); + if (bprm->interp_flags & BINPRM_FLAGS_PRESERVE_ARGV0) + flags |= AT_FLAGS_PRESERVE_ARGV0; + NEW_AUX_ENT(AT_FLAGS, flags); NEW_AUX_ENT(AT_ENTRY, exec_params->entry_addr); NEW_AUX_ENT(AT_UID, (elf_addr_t) from_kuid_munged(cred->user_ns, cred->uid)); NEW_AUX_ENT(AT_EUID, (elf_addr_t) from_kuid_munged(cred->user_ns, cred->euid)); @@ -1191,18 +1194,7 @@ static int elf_fdpic_map_file_by_direct_mmap(struct elf_fdpic_params *params, struct elf_prstatus_fdpic { - struct elf_siginfo pr_info; /* Info associated with signal */ - short pr_cursig; /* Current signal */ - unsigned long pr_sigpend; /* Set of pending signals */ - unsigned long pr_sighold; /* Set of held signals */ - pid_t pr_pid; - pid_t pr_ppid; - pid_t pr_pgrp; - pid_t pr_sid; - struct __kernel_old_timeval pr_utime; /* User time */ - struct __kernel_old_timeval pr_stime; /* System time */ - struct __kernel_old_timeval pr_cutime; /* Cumulative user time */ - struct __kernel_old_timeval pr_cstime; /* Cumulative system time */ + struct elf_prstatus_common common; elf_gregset_t pr_reg; /* GP registers */ /* When using FDPIC, the loadmap addresses need to be communicated * to GDB in order for GDB to do the necessary relocations. The @@ -1301,7 +1293,7 @@ static inline void fill_note(struct memelfnote *note, const char *name, int type * fill up all the fields in prstatus from the given task struct, except * registers which need to be filled up separately. */ -static void fill_prstatus(struct elf_prstatus_fdpic *prstatus, +static void fill_prstatus(struct elf_prstatus_common *prstatus, struct task_struct *p, long signr) { prstatus->pr_info.si_signo = prstatus->pr_cursig = signr; @@ -1332,9 +1324,6 @@ static void fill_prstatus(struct elf_prstatus_fdpic *prstatus, } prstatus->pr_cutime = ns_to_kernel_old_timeval(p->signal->cutime); prstatus->pr_cstime = ns_to_kernel_old_timeval(p->signal->cstime); - - prstatus->pr_exec_fdpic_loadmap = p->mm->context.exec_fdpic_loadmap; - prstatus->pr_interp_fdpic_loadmap = p->mm->context.interp_fdpic_loadmap; } static int fill_psinfo(struct elf_prpsinfo *psinfo, struct task_struct *p, @@ -1405,7 +1394,9 @@ static struct elf_thread_status *elf_dump_thread_status(long signr, struct task_ if (!t) return t; - fill_prstatus(&t->prstatus, p, signr); + fill_prstatus(&t->prstatus.common, p, signr); + t->prstatus.pr_exec_fdpic_loadmap = p->mm->context.exec_fdpic_loadmap; + t->prstatus.pr_interp_fdpic_loadmap = p->mm->context.interp_fdpic_loadmap; regset_get(p, &view->regsets[0], sizeof(t->prstatus.pr_reg), &t->prstatus.pr_reg); diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index 3880a82da1dc..c457334de43f 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -153,7 +153,9 @@ static int load_misc_binary(struct linux_binprm *bprm) if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE) goto ret; - if (!(fmt->flags & MISC_FMT_PRESERVE_ARGV0)) { + if (fmt->flags & MISC_FMT_PRESERVE_ARGV0) { + bprm->interp_flags |= BINPRM_FLAGS_PRESERVE_ARGV0; + } else { retval = remove_arg_zero(bprm); if (retval) goto ret; diff --git a/fs/block_dev.c b/fs/block_dev.c index 3e5b02f6606c..ec26179c8062 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -126,11 +126,18 @@ int truncate_bdev_range(struct block_device *bdev, fmode_t mode, bd_abort_claiming(bdev, truncate_bdev_range); return 0; } -EXPORT_SYMBOL(truncate_bdev_range); static void set_init_blocksize(struct block_device *bdev) { - bdev->bd_inode->i_blkbits = blksize_bits(bdev_logical_block_size(bdev)); + unsigned int bsize = bdev_logical_block_size(bdev); + loff_t size = i_size_read(bdev->bd_inode); + + while (bsize < PAGE_SIZE) { + if (size & bsize) + break; + bsize <<= 1; + } + bdev->bd_inode->i_blkbits = blksize_bits(bsize); } int set_blocksize(struct block_device *bdev, int size) @@ -416,7 +423,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) dio->size += bio->bi_iter.bi_size; pos += bio->bi_iter.bi_size; - nr_pages = iov_iter_npages(iter, BIO_MAX_PAGES); + nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_PAGES); if (!nr_pages) { bool polled = false; @@ -481,9 +488,10 @@ blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { int nr_pages; - nr_pages = iov_iter_npages(iter, BIO_MAX_PAGES + 1); - if (!nr_pages) + if (!iov_iter_count(iter)) return 0; + + nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_PAGES + 1); if (is_sync_kiocb(iocb) && nr_pages <= BIO_MAX_PAGES) return __blkdev_direct_IO_simple(iocb, iter, nr_pages); @@ -605,6 +613,8 @@ int thaw_bdev(struct block_device *bdev) error = thaw_super(sb); if (error) bdev->bd_fsfreeze_count++; + else + bdev->bd_fsfreeze_sb = NULL; out: mutex_unlock(&bdev->bd_fsfreeze_mutex); return error; @@ -678,7 +688,7 @@ int blkdev_fsync(struct file *filp, loff_t start, loff_t end, int datasync) * i_mutex and doing so causes performance issues with concurrent * O_SYNC writers to a block device. */ - error = blkdev_issue_flush(bdev, GFP_KERNEL); + error = blkdev_issue_flush(bdev); if (error == -EOPNOTSUPP) error = 0; @@ -774,8 +784,11 @@ static struct kmem_cache * bdev_cachep __read_mostly; static struct inode *bdev_alloc_inode(struct super_block *sb) { struct bdev_inode *ei = kmem_cache_alloc(bdev_cachep, GFP_KERNEL); + if (!ei) return NULL; + memset(&ei->bdev, 0, sizeof(ei->bdev)); + ei->bdev.bd_bdi = &noop_backing_dev_info; return &ei->vfs_inode; } @@ -869,14 +882,12 @@ struct block_device *bdev_alloc(struct gendisk *disk, u8 partno) mapping_set_gfp_mask(&inode->i_data, GFP_USER); bdev = I_BDEV(inode); - memset(bdev, 0, sizeof(*bdev)); mutex_init(&bdev->bd_mutex); mutex_init(&bdev->bd_fsfreeze_mutex); spin_lock_init(&bdev->bd_size_lock); bdev->bd_disk = disk; bdev->bd_partno = partno; bdev->bd_inode = inode; - bdev->bd_bdi = &noop_backing_dev_info; #ifdef CONFIG_SYSFS INIT_LIST_HEAD(&bdev->bd_holder_disks); #endif @@ -1797,13 +1808,11 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start, return error; /* - * Invalidate again; if someone wandered in and dirtied a page, - * the caller will be given -EBUSY. The third argument is - * inclusive, so the rounding here is safe. + * Invalidate the page cache again; if someone wandered in and dirtied + * a page, we just discard it - userspace has no way of knowing whether + * the write happened before or after discard completing... */ - return invalidate_inode_pages2_range(bdev->bd_inode->i_mapping, - start >> PAGE_SHIFT, - end >> PAGE_SHIFT); + return truncate_bdev_range(bdev, file->f_mode, start, end); } const struct file_operations def_blk_fops = { diff --git a/fs/btrfs/Makefile b/fs/btrfs/Makefile index 9f1b1a88e317..b634c42115ea 100644 --- a/fs/btrfs/Makefile +++ b/fs/btrfs/Makefile @@ -1,5 +1,21 @@ # SPDX-License-Identifier: GPL-2.0 +# Subset of W=1 warnings +subdir-ccflags-y += -Wextra -Wunused -Wno-unused-parameter +subdir-ccflags-y += -Wmissing-declarations +subdir-ccflags-y += -Wmissing-format-attribute +subdir-ccflags-y += -Wmissing-prototypes +subdir-ccflags-y += -Wold-style-definition +subdir-ccflags-y += -Wmissing-include-dirs +subdir-ccflags-y += $(call cc-option, -Wunused-but-set-variable) +subdir-ccflags-y += $(call cc-option, -Wunused-const-variable) +subdir-ccflags-y += $(call cc-option, -Wpacked-not-aligned) +subdir-ccflags-y += $(call cc-option, -Wstringop-truncation) +# The following turn off the warnings enabled by -Wextra +subdir-ccflags-y += -Wno-missing-field-initializers +subdir-ccflags-y += -Wno-sign-compare +subdir-ccflags-y += -Wno-type-limits + obj-$(CONFIG_BTRFS_FS) := btrfs.o btrfs-y += super.o ctree.o extent-tree.o print-tree.o root-tree.o dir-item.o \ @@ -11,7 +27,8 @@ btrfs-y += super.o ctree.o extent-tree.o print-tree.o root-tree.o dir-item.o \ compression.o delayed-ref.o relocation.o delayed-inode.o scrub.o \ reada.o backref.o ulist.o qgroup.o send.o dev-replace.o raid56.o \ uuid-tree.o props.o free-space-tree.o tree-checker.o space-info.o \ - block-rsv.o delalloc-space.o block-group.o discard.o reflink.o + block-rsv.o delalloc-space.o block-group.o discard.o reflink.o \ + subpage.o btrfs-$(CONFIG_BTRFS_FS_POSIX_ACL) += acl.o btrfs-$(CONFIG_BTRFS_FS_CHECK_INTEGRITY) += check-integrity.o diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 02d7d7b2563b..f47c1528eb9a 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -1501,7 +1501,13 @@ int btrfs_find_all_roots(struct btrfs_trans_handle *trans, } /** - * btrfs_check_shared - tell us whether an extent is shared + * Check if an extent is shared or not + * + * @root: root inode belongs to + * @inum: inode number of the inode whose extent we are checking + * @bytenr: logical bytenr of the extent we are checking + * @roots: list of roots this extent is shared among + * @tmp: temporary list used for iteration * * btrfs_check_shared uses the backref walking code but will short * circuit as soon as it finds a root or inode that doesn't match the @@ -2541,13 +2547,6 @@ void btrfs_backref_cleanup_node(struct btrfs_backref_cache *cache, list_del(&edge->list[UPPER]); btrfs_backref_free_edge(cache, edge); - if (RB_EMPTY_NODE(&upper->rb_node)) { - BUG_ON(!list_empty(&node->upper)); - btrfs_backref_drop_node(cache, node); - node = upper; - node->lowest = 1; - continue; - } /* * Add the node to leaf node list if no other child block * cached. @@ -2624,7 +2623,7 @@ static int handle_direct_tree_backref(struct btrfs_backref_cache *cache, /* Only reloc backref cache cares about a specific root */ if (cache->is_reloc) { root = find_reloc_root(cache->fs_info, cur->bytenr); - if (WARN_ON(!root)) + if (!root) return -ENOENT; cur->root = root; } else { @@ -3117,7 +3116,7 @@ void btrfs_backref_error_cleanup(struct btrfs_backref_cache *cache, list_del_init(&lower->list); if (lower == node) node = NULL; - btrfs_backref_free_node(cache, lower); + btrfs_backref_drop_node(cache, lower); } btrfs_backref_cleanup_node(cache, node); diff --git a/fs/btrfs/backref.h b/fs/btrfs/backref.h index ff705cc564a9..17abde7f794c 100644 --- a/fs/btrfs/backref.h +++ b/fs/btrfs/backref.h @@ -296,6 +296,9 @@ static inline void btrfs_backref_free_node(struct btrfs_backref_cache *cache, struct btrfs_backref_node *node) { if (node) { + ASSERT(list_empty(&node->list)); + ASSERT(list_empty(&node->lower)); + ASSERT(node->eb == NULL); cache->nr_nodes--; btrfs_put_root(node->root); kfree(node); @@ -340,11 +343,11 @@ static inline void btrfs_backref_drop_node_buffer( static inline void btrfs_backref_drop_node(struct btrfs_backref_cache *tree, struct btrfs_backref_node *node) { - BUG_ON(!list_empty(&node->upper)); + ASSERT(list_empty(&node->upper)); btrfs_backref_drop_node_buffer(node); - list_del(&node->list); - list_del(&node->lower); + list_del_init(&node->list); + list_del_init(&node->lower); if (!RB_EMPTY_NODE(&node->rb_node)) rb_erase(&node->rb_node, &tree->rb_root); btrfs_backref_free_node(tree, node); diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 52f2198d44c9..5064be59dac5 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -15,6 +15,7 @@ #include "delalloc-space.h" #include "discard.h" #include "raid56.h" +#include "zoned.h" /* * Return target flags in extended format or 0 if restripe for this chunk_type @@ -673,7 +674,15 @@ static noinline void caching_thread(struct btrfs_work *work) wake_up(&caching_ctl->wait); } - if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) + /* + * If we are in the transaction that populated the free space tree we + * can't actually cache from the free space tree as our commit root and + * real root are the same, so we could change the contents of the blocks + * while caching. Instead do the slow caching in this case, and after + * the transaction has committed we will be safe. + */ + if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE) && + !(test_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags))) ret = load_free_space_tree(caching_ctl); else ret = load_extent_tree_free(caching_ctl); @@ -716,6 +725,10 @@ int btrfs_cache_block_group(struct btrfs_block_group *cache, int load_cache_only struct btrfs_caching_control *caching_ctl = NULL; int ret = 0; + /* Allocator for zoned filesystems does not use the cache at all */ + if (btrfs_is_zoned(fs_info)) + return 0; + caching_ctl = kzalloc(sizeof(*caching_ctl), GFP_NOFS); if (!caching_ctl) return -ENOMEM; @@ -888,6 +901,8 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, btrfs_return_cluster_to_free_space(block_group, cluster); spin_unlock(&cluster->refill_lock); + btrfs_clear_treelog_bg(block_group); + path = btrfs_alloc_path(); if (!path) { ret = -ENOMEM; @@ -1000,12 +1015,17 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, WARN_ON(block_group->space_info->total_bytes < block_group->length); WARN_ON(block_group->space_info->bytes_readonly - < block_group->length); + < block_group->length - block_group->zone_unusable); + WARN_ON(block_group->space_info->bytes_zone_unusable + < block_group->zone_unusable); WARN_ON(block_group->space_info->disk_total < block_group->length * factor); } block_group->space_info->total_bytes -= block_group->length; - block_group->space_info->bytes_readonly -= block_group->length; + block_group->space_info->bytes_readonly -= + (block_group->length - block_group->zone_unusable); + block_group->space_info->bytes_zone_unusable -= + block_group->zone_unusable; block_group->space_info->disk_total -= block_group->length * factor; spin_unlock(&block_group->space_info->lock); @@ -1149,7 +1169,7 @@ static int inc_block_group_ro(struct btrfs_block_group *cache, int force) } num_bytes = cache->length - cache->reserved - cache->pinned - - cache->bytes_super - cache->used; + cache->bytes_super - cache->zone_unusable - cache->used; /* * Data never overcommits, even in mixed mode, so do just the straight @@ -1180,6 +1200,12 @@ static int inc_block_group_ro(struct btrfs_block_group *cache, int force) if (!ret) { sinfo->bytes_readonly += num_bytes; + if (btrfs_is_zoned(cache->fs_info)) { + /* Migrate zone_unusable bytes to readonly */ + sinfo->bytes_readonly += cache->zone_unusable; + sinfo->bytes_zone_unusable -= cache->zone_unusable; + cache->zone_unusable = 0; + } cache->ro++; list_add_tail(&cache->ro_list, &sinfo->ro_bgs); } @@ -1254,6 +1280,13 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) if (!test_bit(BTRFS_FS_OPEN, &fs_info->flags)) return; + /* + * Long running balances can keep us blocked here for eternity, so + * simply skip deletion if we're unable to get the mutex. + */ + if (!mutex_trylock(&fs_info->delete_unused_bgs_mutex)) + return; + spin_lock(&fs_info->unused_bgs_lock); while (!list_empty(&fs_info->unused_bgs)) { int trimming; @@ -1273,8 +1306,6 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) btrfs_discard_cancel_work(&fs_info->discard_ctl, block_group); - mutex_lock(&fs_info->delete_unused_bgs_mutex); - /* Don't want to race with allocators so take the groups_sem */ down_write(&space_info->groups_sem); @@ -1363,9 +1394,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) btrfs_space_info_update_bytes_pinned(fs_info, space_info, -block_group->pinned); space_info->bytes_readonly += block_group->pinned; - percpu_counter_add_batch(&space_info->total_bytes_pinned, - -block_group->pinned, - BTRFS_TOTAL_BYTES_PINNED_BATCH); + __btrfs_mod_total_bytes_pinned(space_info, -block_group->pinned); block_group->pinned = 0; spin_unlock(&block_group->lock); @@ -1381,8 +1410,12 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) if (!async_trim_enabled && btrfs_test_opt(fs_info, DISCARD_ASYNC)) goto flip_async; - /* DISCARD can flip during remount */ - trimming = btrfs_test_opt(fs_info, DISCARD_SYNC); + /* + * DISCARD can flip during remount. On zoned filesystems, we + * need to reset sequential-required zones. + */ + trimming = btrfs_test_opt(fs_info, DISCARD_SYNC) || + btrfs_is_zoned(fs_info); /* Implicit trim during transaction commit. */ if (trimming) @@ -1420,11 +1453,11 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) end_trans: btrfs_end_transaction(trans); next: - mutex_unlock(&fs_info->delete_unused_bgs_mutex); btrfs_put_block_group(block_group); spin_lock(&fs_info->unused_bgs_lock); } spin_unlock(&fs_info->unused_bgs_lock); + mutex_unlock(&fs_info->delete_unused_bgs_mutex); return; flip_async: @@ -1553,8 +1586,11 @@ static void set_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags) } /** - * btrfs_rmap_block - Map a physical disk address to a list of logical addresses + * Map a physical disk address to a list of logical addresses + * + * @fs_info: the filesystem * @chunk_start: logical address of block group + * @bdev: physical device to resolve, can be NULL to indicate any device * @physical: physical address to map to logical addresses * @logical: return array of logical addresses which map to @physical * @naddrs: length of @logical @@ -1564,9 +1600,9 @@ static void set_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags) * Used primarily to exclude those portions of a block group that contain super * block copies. */ -EXPORT_FOR_TESTS int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start, - u64 physical, u64 **logical, int *naddrs, int *stripe_len) + struct block_device *bdev, u64 physical, u64 **logical, + int *naddrs, int *stripe_len) { struct extent_map *em; struct map_lookup *map; @@ -1584,6 +1620,7 @@ int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start, map = em->map_lookup; data_stripe_length = em->orig_block_len; io_stripe_size = map->stripe_len; + chunk_start = em->start; /* For RAID5/6 adjust to a full IO stripe length */ if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) @@ -1598,14 +1635,18 @@ int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start, for (i = 0; i < map->num_stripes; i++) { bool already_inserted = false; u64 stripe_nr; + u64 offset; int j; if (!in_range(physical, map->stripes[i].physical, data_stripe_length)) continue; + if (bdev && map->stripes[i].dev->bdev != bdev) + continue; + stripe_nr = physical - map->stripes[i].physical; - stripe_nr = div64_u64(stripe_nr, map->stripe_len); + stripe_nr = div64_u64_rem(stripe_nr, map->stripe_len, &offset); if (map->type & BTRFS_BLOCK_GROUP_RAID10) { stripe_nr = stripe_nr * map->num_stripes + i; @@ -1619,7 +1660,7 @@ int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start, * instead of map->stripe_len */ - bytenr = chunk_start + stripe_nr * io_stripe_size; + bytenr = chunk_start + stripe_nr * io_stripe_size + offset; /* Ensure we don't add duplicate addresses */ for (j = 0; j < nr; j++) { @@ -1661,7 +1702,7 @@ static int exclude_super_stripes(struct btrfs_block_group *cache) for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) { bytenr = btrfs_sb_offset(i); - ret = btrfs_rmap_block(fs_info, cache->start, + ret = btrfs_rmap_block(fs_info, cache->start, NULL, bytenr, &logical, &nr, &stripe_len); if (ret) return ret; @@ -1797,24 +1838,8 @@ static int check_chunk_block_group_mappings(struct btrfs_fs_info *fs_info) return ret; } -static void read_block_group_item(struct btrfs_block_group *cache, - struct btrfs_path *path, - const struct btrfs_key *key) -{ - struct extent_buffer *leaf = path->nodes[0]; - struct btrfs_block_group_item bgi; - int slot = path->slots[0]; - - cache->length = key->offset; - - read_extent_buffer(leaf, &bgi, btrfs_item_ptr_offset(leaf, slot), - sizeof(bgi)); - cache->used = btrfs_stack_block_group_used(&bgi); - cache->flags = btrfs_stack_block_group_flags(&bgi); -} - static int read_one_block_group(struct btrfs_fs_info *info, - struct btrfs_path *path, + struct btrfs_block_group_item *bgi, const struct btrfs_key *key, int need_clear) { @@ -1829,7 +1854,9 @@ static int read_one_block_group(struct btrfs_fs_info *info, if (!cache) return -ENOMEM; - read_block_group_item(cache, path, key); + cache->length = key->offset; + cache->used = btrfs_stack_block_group_used(bgi); + cache->flags = btrfs_stack_block_group_flags(bgi); set_free_space_tree_thresholds(cache); @@ -1856,6 +1883,13 @@ static int read_one_block_group(struct btrfs_fs_info *info, goto error; } + ret = btrfs_load_block_group_zone_info(cache, false); + if (ret) { + btrfs_err(info, "zoned: failed to load zone info of bg %llu", + cache->start); + goto error; + } + /* * We need to exclude the super stripes now so that the space info has * super bytes accounted for, otherwise we'll think we have more space @@ -1869,12 +1903,20 @@ static int read_one_block_group(struct btrfs_fs_info *info, } /* - * Check for two cases, either we are full, and therefore don't need - * to bother with the caching work since we won't find any space, or we - * are empty, and we can just add all the space in and be done with it. - * This saves us _a_lot_ of time, particularly in the full case. + * For zoned filesystem, space after the allocation offset is the only + * free space for a block group. So, we don't need any caching work. + * btrfs_calc_zone_unusable() will set the amount of free space and + * zone_unusable space. + * + * For regular filesystem, check for two cases, either we are full, and + * therefore don't need to bother with the caching work since we won't + * find any space, or we are empty, and we can just add all the space + * in and be done with it. This saves us _a_lot_ of time, particularly + * in the full case. */ - if (cache->length == cache->used) { + if (btrfs_is_zoned(info)) { + btrfs_calc_zone_unusable(cache); + } else if (cache->length == cache->used) { cache->last_byte_to_unpin = (u64)-1; cache->cached = BTRFS_CACHE_FINISHED; btrfs_free_excluded_extents(cache); @@ -1893,7 +1935,8 @@ static int read_one_block_group(struct btrfs_fs_info *info, } trace_btrfs_add_block_group(info, cache, 0); btrfs_update_space_info(info, cache->flags, cache->length, - cache->used, cache->bytes_super, &space_info); + cache->used, cache->bytes_super, + cache->zone_unusable, &space_info); cache->space_info = space_info; @@ -1949,7 +1992,7 @@ static int fill_dummy_bgs(struct btrfs_fs_info *fs_info) break; } btrfs_update_space_info(fs_info, bg->flags, em->len, em->len, - 0, &space_info); + 0, 0, &space_info); bg->space_info = space_info; link_block_group(bg); @@ -1988,19 +2031,29 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info) need_clear = 1; while (1) { + struct btrfs_block_group_item bgi; + struct extent_buffer *leaf; + int slot; + ret = find_first_block_group(info, path, &key); if (ret > 0) break; if (ret != 0) goto error; - btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); - ret = read_one_block_group(info, path, &key, need_clear); + leaf = path->nodes[0]; + slot = path->slots[0]; + + read_extent_buffer(leaf, &bgi, btrfs_item_ptr_offset(leaf, slot), + sizeof(bgi)); + + btrfs_item_key_to_cpu(leaf, &key, slot); + btrfs_release_path(path); + ret = read_one_block_group(info, &bgi, &key, need_clear); if (ret < 0) goto error; key.objectid += key.offset; key.offset = 0; - btrfs_release_path(path); } btrfs_release_path(path); @@ -2132,6 +2185,13 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used, cache->cached = BTRFS_CACHE_FINISHED; if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) cache->needs_free_space = 1; + + ret = btrfs_load_block_group_zone_info(cache, true); + if (ret) { + btrfs_put_block_group(cache); + return ret; + } + ret = exclude_super_stripes(cache); if (ret) { /* We may have excluded something, so call this just in case */ @@ -2173,7 +2233,7 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used, */ trace_btrfs_add_block_group(fs_info, cache, 1); btrfs_update_space_info(fs_info, cache->flags, size, bytes_used, - cache->bytes_super, &cache->space_info); + cache->bytes_super, 0, &cache->space_info); btrfs_update_global_block_rsv(fs_info); link_block_group(cache); @@ -2281,8 +2341,15 @@ void btrfs_dec_block_group_ro(struct btrfs_block_group *cache) spin_lock(&cache->lock); if (!--cache->ro) { num_bytes = cache->length - cache->reserved - - cache->pinned - cache->bytes_super - cache->used; + cache->pinned - cache->bytes_super - + cache->zone_unusable - cache->used; sinfo->bytes_readonly -= num_bytes; + if (btrfs_is_zoned(cache->fs_info)) { + /* Migrate zone_unusable bytes back */ + cache->zone_unusable = cache->alloc_offset - cache->used; + sinfo->bytes_zone_unusable += cache->zone_unusable; + sinfo->bytes_readonly -= cache->zone_unusable; + } list_del_init(&cache->ro_list); } spin_unlock(&cache->lock); @@ -2556,8 +2623,10 @@ again: if (!path) { path = btrfs_alloc_path(); - if (!path) - return -ENOMEM; + if (!path) { + ret = -ENOMEM; + goto out; + } } /* @@ -2651,16 +2720,14 @@ again: btrfs_put_block_group(cache); if (drop_reserve) btrfs_delayed_refs_rsv_release(fs_info, 1); - - if (ret) - break; - /* * Avoid blocking other tasks for too long. It might even save * us from writing caches for block groups that are going to be * removed. */ mutex_unlock(&trans->transaction->cache_write_mutex); + if (ret) + goto out; mutex_lock(&trans->transaction->cache_write_mutex); } mutex_unlock(&trans->transaction->cache_write_mutex); @@ -2669,7 +2736,8 @@ again: * Go through delayed refs for all the stuff we've just kicked off * and then loop back (just once) */ - ret = btrfs_run_delayed_refs(trans, 0); + if (!ret) + ret = btrfs_run_delayed_refs(trans, 0); if (!ret && loops == 0) { loops++; spin_lock(&cur_trans->dirty_bgs_lock); @@ -2683,7 +2751,12 @@ again: goto again; } spin_unlock(&cur_trans->dirty_bgs_lock); - } else if (ret < 0) { + } +out: + if (ret < 0) { + spin_lock(&cur_trans->dirty_bgs_lock); + list_splice_init(&dirty, &cur_trans->dirty_bgs); + spin_unlock(&cur_trans->dirty_bgs_lock); btrfs_cleanup_dirty_bgs(cur_trans, fs_info); } @@ -2887,10 +2960,8 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans, spin_unlock(&cache->lock); spin_unlock(&cache->space_info->lock); - percpu_counter_add_batch( - &cache->space_info->total_bytes_pinned, - num_bytes, - BTRFS_TOTAL_BYTES_PINNED_BATCH); + __btrfs_mod_total_bytes_pinned(cache->space_info, + num_bytes); set_extent_dirty(&trans->transaction->pinned_extents, bytenr, bytenr + num_bytes - 1, GFP_NOFS | __GFP_NOFAIL); diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h index 8f74a96074f7..29678426247d 100644 --- a/fs/btrfs/block-group.h +++ b/fs/btrfs/block-group.h @@ -95,6 +95,8 @@ struct btrfs_block_group { unsigned int iref:1; unsigned int has_caching_ctl:1; unsigned int removed:1; + unsigned int to_copy:1; + unsigned int relocating_repair:1; int disk_cache_state; @@ -181,8 +183,19 @@ struct btrfs_block_group { */ int needs_free_space; + /* Flag indicating this block group is placed on a sequential zone */ + bool seq_zone; + /* Record locked full stripes for RAID5/6 block group */ struct btrfs_full_stripe_locks_tree full_stripe_locks_root; + + /* + * Allocation offset for the block group to implement sequential + * allocation. This is used only on a zoned filesystem. + */ + u64 alloc_offset; + u64 zone_unusable; + u64 meta_write_pointer; }; static inline u64 btrfs_block_group_end(struct btrfs_block_group *block_group) @@ -270,6 +283,9 @@ void btrfs_put_block_group_cache(struct btrfs_fs_info *info); int btrfs_free_block_groups(struct btrfs_fs_info *info); void btrfs_wait_space_cache_v1_finished(struct btrfs_block_group *cache, struct btrfs_caching_control *caching_ctl); +int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start, + struct block_device *bdev, u64 physical, u64 **logical, + int *naddrs, int *stripe_len); static inline u64 btrfs_data_alloc_profile(struct btrfs_fs_info *fs_info) { @@ -296,9 +312,4 @@ static inline int btrfs_block_group_done(struct btrfs_block_group *cache) void btrfs_freeze_block_group(struct btrfs_block_group *cache); void btrfs_unfreeze_block_group(struct btrfs_block_group *cache); -#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS -int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start, - u64 physical, u64 **logical, int *naddrs, int *stripe_len); -#endif - #endif /* BTRFS_BLOCK_GROUP_H */ diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h index 555cbcef6585..28e202e89660 100644 --- a/fs/btrfs/btrfs_inode.h +++ b/fs/btrfs/btrfs_inode.h @@ -42,6 +42,15 @@ enum { * to an inode. */ BTRFS_INODE_NO_XATTRS, + /* + * Set when we are in a context where we need to start a transaction and + * have dirty pages with the respective file range locked. This is to + * ensure that when reserving space for the transaction, if we are low + * on available space and need to flush delalloc, we will not flush + * delalloc for this inode, because that could result in a deadlock (on + * the file range, inode's io_tree). + */ + BTRFS_INODE_NO_DELALLOC_FLUSH, }; /* in memory btrfs inode */ @@ -316,7 +325,8 @@ struct btrfs_dio_private { struct inode *inode; u64 logical_offset; u64 disk_bytenr; - u64 bytes; + /* Used for bio::bi_size */ + u32 bytes; /* * References to this structure. There is one reference per in-flight diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c index 6ff44e53814c..113cb85c1fd4 100644 --- a/fs/btrfs/check-integrity.c +++ b/fs/btrfs/check-integrity.c @@ -2674,7 +2674,7 @@ static void __btrfsic_submit_bio(struct bio *bio) mutex_lock(&btrfsic_mutex); /* since btrfsic_submit_bio() is also called before * btrfsic_mount(), this might return NULL */ - dev_state = btrfsic_dev_state_lookup(bio_dev(bio) + bio->bi_partno); + dev_state = btrfsic_dev_state_lookup(bio->bi_bdev->bd_dev); if (NULL != dev_state && (bio_op(bio) == REQ_OP_WRITE) && bio_has_data(bio)) { unsigned int i = 0; @@ -2690,9 +2690,9 @@ static void __btrfsic_submit_bio(struct bio *bio) bio_is_patched = 0; if (dev_state->state->print_mask & BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH) - pr_info("submit_bio(rw=%d,0x%x, bi_vcnt=%u, bi_sector=%llu (bytenr %llu), bi_disk=%p)\n", + pr_info("submit_bio(rw=%d,0x%x, bi_vcnt=%u, bi_sector=%llu (bytenr %llu), bi_bdev=%p)\n", bio_op(bio), bio->bi_opf, segs, - bio->bi_iter.bi_sector, dev_bytenr, bio->bi_disk); + bio->bi_iter.bi_sector, dev_bytenr, bio->bi_bdev); mapped_datav = kmalloc_array(segs, sizeof(*mapped_datav), GFP_NOFS); @@ -2721,8 +2721,8 @@ static void __btrfsic_submit_bio(struct bio *bio) } else if (NULL != dev_state && (bio->bi_opf & REQ_PREFLUSH)) { if (dev_state->state->print_mask & BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH) - pr_info("submit_bio(rw=%d,0x%x FLUSH, disk=%p)\n", - bio_op(bio), bio->bi_opf, bio->bi_disk); + pr_info("submit_bio(rw=%d,0x%x FLUSH, bdev=%p)\n", + bio_op(bio), bio->bi_opf, bio->bi_bdev); if (!dev_state->dummy_block_for_bio_bh_flush.is_iodone) { if ((dev_state->state->print_mask & (BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH | diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index 5ae3fa0386b7..6d203acfdeb3 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -542,13 +542,19 @@ static noinline int add_ra_bio_pages(struct inode *inode, goto next; } - end = last_offset + PAGE_SIZE - 1; /* * at this point, we have a locked page in the page cache * for these bytes in the file. But, we have to make * sure they map to this compressed extent on disk. */ - set_page_extent_mapped(page); + ret = set_page_extent_mapped(page); + if (ret < 0) { + unlock_page(page); + put_page(page); + break; + } + + end = last_offset + PAGE_SIZE - 1; lock_extent(tree, last_offset, end); read_lock(&em_tree->lock); em = lookup_extent_mapping(em_tree, last_offset, diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 07810891e204..d56730a67885 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -221,9 +221,12 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans, ret = btrfs_inc_ref(trans, root, cow, 1); else ret = btrfs_inc_ref(trans, root, cow, 0); - - if (ret) + if (ret) { + btrfs_tree_unlock(cow); + free_extent_buffer(cow); + btrfs_abort_transaction(trans, ret); return ret; + } btrfs_mark_buffer_dirty(cow); *cow_ret = cow; @@ -1494,6 +1497,7 @@ noinline int btrfs_cow_block(struct btrfs_trans_handle *trans, return ret; } +ALLOW_ERROR_INJECTION(btrfs_cow_block, ERRNO); /* * helper function for defrag to decide if two blocks pointed to by a @@ -2555,8 +2559,14 @@ out: * @p: Holds all btree nodes along the search path * @root: The root node of the tree * @key: The key we are looking for - * @ins_len: Indicates purpose of search, for inserts it is 1, for - * deletions it's -1. 0 for plain searches + * @ins_len: Indicates purpose of search: + * >0 for inserts it's size of item inserted (*) + * <0 for deletions + * 0 for plain searches, not modifying the tree + * + * (*) If size of item inserted doesn't include + * sizeof(struct btrfs_item), then p->search_for_extension must + * be set. * @cow: boolean should CoW operations be performed. Must always be 1 * when modifying the tree. * @@ -2717,6 +2727,20 @@ cow_done: if (level == 0) { p->slots[level] = slot; + /* + * Item key already exists. In this case, if we are + * allowed to insert the item (for example, in dir_item + * case, item key collision is allowed), it will be + * merged with the original item. Only the item size + * grows, no new btrfs item will be added. If + * search_for_extension is not set, ins_len already + * accounts the size btrfs_item, deduct it here so leaf + * space check will be correct. + */ + if (ret == 0 && ins_len > 0 && !p->search_for_extension) { + ASSERT(ins_len >= sizeof(struct btrfs_item)); + ins_len -= sizeof(struct btrfs_item); + } if (ins_len > 0 && btrfs_leaf_free_space(b) < ins_len) { if (write_lock_level < 1) { @@ -2801,6 +2825,7 @@ done: btrfs_release_path(p); return ret; } +ALLOW_ERROR_INJECTION(btrfs_search_slot, ERRNO); /* * Like btrfs_search_slot, this looks for a key in the given tree. It uses the diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 1d3c1e479f3d..3bc00aed13b2 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -131,6 +131,8 @@ enum { * defrag */ BTRFS_FS_STATE_REMOUNTING, + /* Filesystem in RO mode */ + BTRFS_FS_STATE_RO, /* Track if a transaction abort has been reported on this filesystem */ BTRFS_FS_STATE_TRANS_ABORTED, /* @@ -296,7 +298,8 @@ struct btrfs_super_block { BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA | \ BTRFS_FEATURE_INCOMPAT_NO_HOLES | \ BTRFS_FEATURE_INCOMPAT_METADATA_UUID | \ - BTRFS_FEATURE_INCOMPAT_RAID1C34) + BTRFS_FEATURE_INCOMPAT_RAID1C34 | \ + BTRFS_FEATURE_INCOMPAT_ZONED) #define BTRFS_FEATURE_INCOMPAT_SAFE_SET \ (BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF) @@ -367,6 +370,12 @@ struct btrfs_path { unsigned int search_commit_root:1; unsigned int need_commit_sem:1; unsigned int skip_release_on_error:1; + /* + * Indicate that new item (btrfs_search_slot) is extending already + * existing item and ins_len contains only the data size and not item + * header (ie. sizeof(struct btrfs_item) is not included). + */ + unsigned int search_for_extension:1; }; #define BTRFS_MAX_EXTENT_ITEM_SIZE(r) ((BTRFS_LEAF_DATA_SIZE(r->fs_info) >> 4) - \ sizeof(struct btrfs_item)) @@ -555,6 +564,9 @@ enum { /* Indicate that we need to cleanup space cache v1 */ BTRFS_FS_CLEANUP_SPACE_CACHE_V1, + + /* Indicate that we can't trust the free space tree for caching yet */ + BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, }; /* @@ -786,7 +798,7 @@ struct btrfs_fs_info { /* used to keep from writing metadata until there is a nice batch */ struct percpu_counter dirty_metadata_bytes; struct percpu_counter delalloc_bytes; - struct percpu_counter dio_bytes; + struct percpu_counter ordered_bytes; s32 dirty_metadata_batch; s32 delalloc_batch; @@ -922,6 +934,7 @@ struct btrfs_fs_info { /* Used to reclaim the metadata space in the background. */ struct work_struct async_reclaim_work; struct work_struct async_data_reclaim_work; + struct work_struct preempt_reclaim_work; spinlock_t unused_bgs_lock; struct list_head unused_bgs; @@ -963,6 +976,9 @@ struct btrfs_fs_info { /* Max size to emit ZONE_APPEND write command */ u64 max_zone_append_size; + struct mutex zoned_meta_io_lock; + spinlock_t treelog_bg_lock; + u64 treelog_bg; #ifdef CONFIG_BTRFS_FS_REF_VERIFY spinlock_t ref_verify_lock; @@ -1093,7 +1109,7 @@ struct btrfs_root { u32 type; - u64 highest_objectid; + u64 free_objectid; struct btrfs_key defrag_progress; struct btrfs_key defrag_max; @@ -2729,6 +2745,7 @@ enum btrfs_flush_state { ALLOC_CHUNK_FORCE = 8, RUN_DELAYED_IPUTS = 9, COMMIT_TRANS = 10, + FORCE_COMMIT_TRANS = 11, }; int btrfs_subvolume_reserve_metadata(struct btrfs_root *root, @@ -2885,10 +2902,26 @@ static inline int btrfs_fs_closing(struct btrfs_fs_info *fs_info) * If we remount the fs to be R/O or umount the fs, the cleaner needn't do * anything except sleeping. This function is used to check the status of * the fs. + * We check for BTRFS_FS_STATE_RO to avoid races with a concurrent remount, + * since setting and checking for SB_RDONLY in the superblock's flags is not + * atomic. */ static inline int btrfs_need_cleaner_sleep(struct btrfs_fs_info *fs_info) { - return fs_info->sb->s_flags & SB_RDONLY || btrfs_fs_closing(fs_info); + return test_bit(BTRFS_FS_STATE_RO, &fs_info->fs_state) || + btrfs_fs_closing(fs_info); +} + +static inline void btrfs_set_sb_rdonly(struct super_block *sb) +{ + sb->s_flags |= SB_RDONLY; + set_bit(BTRFS_FS_STATE_RO, &btrfs_sb(sb)->fs_state); +} + +static inline void btrfs_clear_sb_rdonly(struct super_block *sb) +{ + sb->s_flags &= ~SB_RDONLY; + clear_bit(BTRFS_FS_STATE_RO, &btrfs_sb(sb)->fs_state); } /* tree mod log functions from ctree.c */ @@ -3073,14 +3106,14 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, u32 min_type); int btrfs_start_delalloc_snapshot(struct btrfs_root *root); -int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr); +int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, long nr, + bool in_reclaim_context); int btrfs_set_extent_delalloc(struct btrfs_inode *inode, u64 start, u64 end, unsigned int extra_bits, struct extent_state **cached_state); int btrfs_create_subvol_root(struct btrfs_trans_handle *trans, struct btrfs_root *new_root, - struct btrfs_root *parent_root, - u64 new_dirid); + struct btrfs_root *parent_root); void btrfs_set_delalloc_extent(struct inode *inode, struct extent_state *state, unsigned *bits); void btrfs_clear_delalloc_extent(struct inode *inode, @@ -3091,6 +3124,8 @@ void btrfs_split_delalloc_extent(struct inode *inode, struct extent_state *orig, u64 split); int btrfs_bio_fits_in_stripe(struct page *page, size_t size, struct bio *bio, unsigned long bio_flags); +bool btrfs_bio_fits_in_ordered_extent(struct page *page, struct bio *bio, + unsigned int size); void btrfs_set_range_writeback(struct extent_io_tree *tree, u64 start, u64 end); vm_fault_t btrfs_page_mkwrite(struct vm_fault *vmf); int btrfs_readpage(struct file *file, struct page *page); diff --git a/fs/btrfs/delalloc-space.c b/fs/btrfs/delalloc-space.c index bacee09b7bfd..56642ca7af10 100644 --- a/fs/btrfs/delalloc-space.c +++ b/fs/btrfs/delalloc-space.c @@ -191,12 +191,14 @@ void btrfs_free_reserved_data_space(struct btrfs_inode *inode, } /** - * btrfs_inode_rsv_release - release any excessive reservation. - * @inode - the inode we need to release from. - * @qgroup_free - free or convert qgroup meta. - * Unlike normal operation, qgroup meta reservation needs to know if we are - * freeing qgroup reservation or just converting it into per-trans. Normally - * @qgroup_free is true for error handling, and false for normal release. + * Release any excessive reservation + * + * @inode: the inode we need to release from + * @qgroup_free: free or convert qgroup meta. Unlike normal operation, qgroup + * meta reservation needs to know if we are freeing qgroup + * reservation or just converting it into per-trans. Normally + * @qgroup_free is true for error handling, and false for normal + * release. * * This is the same as btrfs_block_rsv_release, except that it handles the * tracepoint for the reservation. @@ -361,7 +363,8 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes) } /** - * btrfs_delalloc_release_metadata - release a metadata reservation for an inode + * Release a metadata reservation for an inode + * * @inode: the inode to release the reservation for. * @num_bytes: the number of bytes we are releasing. * @qgroup_free: free qgroup reservation or convert it to per-trans reservation @@ -455,11 +458,13 @@ int btrfs_delalloc_reserve_space(struct btrfs_inode *inode, } /** - * btrfs_delalloc_release_space - release data and metadata space for delalloc - * @inode: inode we're releasing space for - * @start: start position of the space already reserved - * @len: the len of the space already reserved - * @release_bytes: the len of the space we consumed or didn't use + * Release data and metadata space for delalloc + * + * @inode: inode we're releasing space for + * @reserved: list of changed/reserved ranges + * @start: start position of the space already reserved + * @len: length of the space already reserved + * @qgroup_free: should qgroup reserved-space also be freed * * This function will release the metadata space that was not used and will * decrement ->delalloc_bytes and remove it from the fs_info delalloc_inodes diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index 70c0340d839c..ec0b50b8c5d6 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -1154,7 +1154,7 @@ static int __btrfs_run_delayed_items(struct btrfs_trans_handle *trans, int nr) delayed_root = fs_info->delayed_root; curr_node = btrfs_first_delayed_node(delayed_root); - while (curr_node && (!count || (count && nr--))) { + while (curr_node && (!count || nr--)) { ret = __btrfs_commit_inode_delayed_items(trans, path, curr_node); if (ret) { diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c index 353cc2994d10..63be7d01a9a3 100644 --- a/fs/btrfs/delayed-ref.c +++ b/fs/btrfs/delayed-ref.c @@ -69,9 +69,10 @@ int btrfs_should_throttle_delayed_refs(struct btrfs_trans_handle *trans) } /** - * btrfs_delayed_refs_rsv_release - release a ref head's reservation. - * @fs_info - the fs_info for our fs. - * @nr - the number of items to drop. + * Release a ref head's reservation + * + * @fs_info: the filesystem + * @nr: number of items to drop * * This drops the delayed ref head's count from the delayed refs rsv and frees * any excess reservation we had. @@ -114,10 +115,11 @@ void btrfs_update_delayed_refs_rsv(struct btrfs_trans_handle *trans) } /** - * btrfs_migrate_to_delayed_refs_rsv - transfer bytes to our delayed refs rsv. - * @fs_info - the fs info for our fs. - * @src - the source block rsv to transfer from. - * @num_bytes - the number of bytes to transfer. + * Transfer bytes to our delayed refs rsv + * + * @fs_info: the filesystem + * @src: source block rsv to transfer from + * @num_bytes: number of bytes to transfer * * This transfers up to the num_bytes amount from the src rsv to the * delayed_refs_rsv. Any extra bytes are returned to the space info. @@ -162,9 +164,10 @@ void btrfs_migrate_to_delayed_refs_rsv(struct btrfs_fs_info *fs_info, } /** - * btrfs_delayed_refs_rsv_refill - refill based on our delayed refs usage. - * @fs_info - the fs_info for our fs. - * @flush - control how we can flush for this reservation. + * Refill based on our delayed refs usage + * + * @fs_info: the filesystem + * @flush: control how we can flush for this reservation. * * This will refill the delayed block_rsv up to 1 items size worth of space and * will return -ENOSPC if we can't make the reservation. @@ -648,12 +651,12 @@ inserted: */ static noinline void update_existing_head_ref(struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_head *existing, - struct btrfs_delayed_ref_head *update, - int *old_ref_mod_ret) + struct btrfs_delayed_ref_head *update) { struct btrfs_delayed_ref_root *delayed_refs = &trans->transaction->delayed_refs; struct btrfs_fs_info *fs_info = trans->fs_info; + u64 flags = btrfs_ref_head_to_space_flags(existing); int old_ref_mod; BUG_ON(existing->is_data != update->is_data); @@ -701,8 +704,6 @@ static noinline void update_existing_head_ref(struct btrfs_trans_handle *trans, * currently, for refs we just added we know we're a-ok. */ old_ref_mod = existing->total_ref_mod; - if (old_ref_mod_ret) - *old_ref_mod_ret = old_ref_mod; existing->ref_mod += update->ref_mod; existing->total_ref_mod += update->ref_mod; @@ -724,6 +725,27 @@ static noinline void update_existing_head_ref(struct btrfs_trans_handle *trans, trans->delayed_ref_updates += csum_leaves; } } + + /* + * This handles the following conditions: + * + * 1. We had a ref mod of 0 or more and went negative, indicating that + * we may be freeing space, so add our space to the + * total_bytes_pinned counter. + * 2. We were negative and went to 0 or positive, so no longer can say + * that the space would be pinned, decrement our counter from the + * total_bytes_pinned counter. + * 3. We are now at 0 and have ->must_insert_reserved set, which means + * this was a new allocation and then we dropped it, and thus must + * add our space to the total_bytes_pinned counter. + */ + if (existing->total_ref_mod < 0 && old_ref_mod >= 0) + btrfs_mod_total_bytes_pinned(fs_info, flags, existing->num_bytes); + else if (existing->total_ref_mod >= 0 && old_ref_mod < 0) + btrfs_mod_total_bytes_pinned(fs_info, flags, -existing->num_bytes); + else if (existing->total_ref_mod == 0 && existing->must_insert_reserved) + btrfs_mod_total_bytes_pinned(fs_info, flags, existing->num_bytes); + spin_unlock(&existing->lock); } @@ -798,8 +820,7 @@ static noinline struct btrfs_delayed_ref_head * add_delayed_ref_head(struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_head *head_ref, struct btrfs_qgroup_extent_record *qrecord, - int action, int *qrecord_inserted_ret, - int *old_ref_mod, int *new_ref_mod) + int action, int *qrecord_inserted_ret) { struct btrfs_delayed_ref_head *existing; struct btrfs_delayed_ref_root *delayed_refs; @@ -821,8 +842,7 @@ add_delayed_ref_head(struct btrfs_trans_handle *trans, existing = htree_insert(&delayed_refs->href_root, &head_ref->href_node); if (existing) { - update_existing_head_ref(trans, existing, head_ref, - old_ref_mod); + update_existing_head_ref(trans, existing, head_ref); /* * we've updated the existing ref, free the newly * allocated ref @@ -830,14 +850,17 @@ add_delayed_ref_head(struct btrfs_trans_handle *trans, kmem_cache_free(btrfs_delayed_ref_head_cachep, head_ref); head_ref = existing; } else { - if (old_ref_mod) - *old_ref_mod = 0; + u64 flags = btrfs_ref_head_to_space_flags(head_ref); + if (head_ref->is_data && head_ref->ref_mod < 0) { delayed_refs->pending_csums += head_ref->num_bytes; trans->delayed_ref_updates += btrfs_csum_bytes_to_leaves(trans->fs_info, head_ref->num_bytes); } + if (head_ref->ref_mod < 0) + btrfs_mod_total_bytes_pinned(trans->fs_info, flags, + head_ref->num_bytes); delayed_refs->num_heads++; delayed_refs->num_heads_ready++; atomic_inc(&delayed_refs->num_entries); @@ -845,8 +868,6 @@ add_delayed_ref_head(struct btrfs_trans_handle *trans, } if (qrecord_inserted_ret) *qrecord_inserted_ret = qrecord_inserted; - if (new_ref_mod) - *new_ref_mod = head_ref->total_ref_mod; return head_ref; } @@ -909,8 +930,7 @@ static void init_delayed_ref_common(struct btrfs_fs_info *fs_info, */ int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans, struct btrfs_ref *generic_ref, - struct btrfs_delayed_extent_op *extent_op, - int *old_ref_mod, int *new_ref_mod) + struct btrfs_delayed_extent_op *extent_op) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_delayed_tree_ref *ref; @@ -977,8 +997,7 @@ int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans, * the spin lock */ head_ref = add_delayed_ref_head(trans, head_ref, record, - action, &qrecord_inserted, - old_ref_mod, new_ref_mod); + action, &qrecord_inserted); ret = insert_delayed_ref(trans, delayed_refs, head_ref, &ref->node); spin_unlock(&delayed_refs->lock); @@ -1006,8 +1025,7 @@ int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans, */ int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans, struct btrfs_ref *generic_ref, - u64 reserved, int *old_ref_mod, - int *new_ref_mod) + u64 reserved) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_delayed_data_ref *ref; @@ -1073,8 +1091,7 @@ int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans, * the spin lock */ head_ref = add_delayed_ref_head(trans, head_ref, record, - action, &qrecord_inserted, - old_ref_mod, new_ref_mod); + action, &qrecord_inserted); ret = insert_delayed_ref(trans, delayed_refs, head_ref, &ref->node); spin_unlock(&delayed_refs->lock); @@ -1117,7 +1134,7 @@ int btrfs_add_delayed_extent_op(struct btrfs_trans_handle *trans, spin_lock(&delayed_refs->lock); add_delayed_ref_head(trans, head_ref, NULL, BTRFS_UPDATE_DELAYED_HEAD, - NULL, NULL, NULL); + NULL); spin_unlock(&delayed_refs->lock); diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h index 1c977e6d45dc..e22fba272e4f 100644 --- a/fs/btrfs/delayed-ref.h +++ b/fs/btrfs/delayed-ref.h @@ -135,6 +135,11 @@ struct btrfs_delayed_data_ref { u64 offset; }; +enum btrfs_delayed_ref_flags { + /* Indicate that we are flushing delayed refs for the commit */ + BTRFS_DELAYED_REFS_FLUSHING, +}; + struct btrfs_delayed_ref_root { /* head ref rbtree */ struct rb_root_cached href_root; @@ -158,12 +163,7 @@ struct btrfs_delayed_ref_root { u64 pending_csums; - /* - * set when the tree is flushing before a transaction commit, - * used by the throttling code to decide if new updates need - * to be run right away - */ - int flushing; + unsigned long flags; u64 run_delayed_start; @@ -326,6 +326,16 @@ static inline void btrfs_put_delayed_ref(struct btrfs_delayed_ref_node *ref) } } +static inline u64 btrfs_ref_head_to_space_flags( + struct btrfs_delayed_ref_head *head_ref) +{ + if (head_ref->is_data) + return BTRFS_BLOCK_GROUP_DATA; + else if (head_ref->is_system) + return BTRFS_BLOCK_GROUP_SYSTEM; + return BTRFS_BLOCK_GROUP_METADATA; +} + static inline void btrfs_put_delayed_ref_head(struct btrfs_delayed_ref_head *head) { if (refcount_dec_and_test(&head->refs)) @@ -334,12 +344,10 @@ static inline void btrfs_put_delayed_ref_head(struct btrfs_delayed_ref_head *hea int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans, struct btrfs_ref *generic_ref, - struct btrfs_delayed_extent_op *extent_op, - int *old_ref_mod, int *new_ref_mod); + struct btrfs_delayed_extent_op *extent_op); int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans, struct btrfs_ref *generic_ref, - u64 reserved, int *old_ref_mod, - int *new_ref_mod); + u64 reserved); int btrfs_add_delayed_extent_op(struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, struct btrfs_delayed_extent_op *extent_op); diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index a98e33f232d5..3a9c1e046ebe 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -22,6 +22,7 @@ #include "dev-replace.h" #include "sysfs.h" #include "zoned.h" +#include "block-group.h" /* * Device replace overview @@ -459,6 +460,185 @@ static char* btrfs_dev_name(struct btrfs_device *device) return rcu_str_deref(device->name); } +static int mark_block_group_to_copy(struct btrfs_fs_info *fs_info, + struct btrfs_device *src_dev) +{ + struct btrfs_path *path; + struct btrfs_key key; + struct btrfs_key found_key; + struct btrfs_root *root = fs_info->dev_root; + struct btrfs_dev_extent *dev_extent = NULL; + struct btrfs_block_group *cache; + struct btrfs_trans_handle *trans; + int ret = 0; + u64 chunk_offset; + + /* Do not use "to_copy" on non zoned filesystem for now */ + if (!btrfs_is_zoned(fs_info)) + return 0; + + mutex_lock(&fs_info->chunk_mutex); + + /* Ensure we don't have pending new block group */ + spin_lock(&fs_info->trans_lock); + while (fs_info->running_transaction && + !list_empty(&fs_info->running_transaction->dev_update_list)) { + spin_unlock(&fs_info->trans_lock); + mutex_unlock(&fs_info->chunk_mutex); + trans = btrfs_attach_transaction(root); + if (IS_ERR(trans)) { + ret = PTR_ERR(trans); + mutex_lock(&fs_info->chunk_mutex); + if (ret == -ENOENT) { + spin_lock(&fs_info->trans_lock); + continue; + } else { + goto unlock; + } + } + + ret = btrfs_commit_transaction(trans); + mutex_lock(&fs_info->chunk_mutex); + if (ret) + goto unlock; + + spin_lock(&fs_info->trans_lock); + } + spin_unlock(&fs_info->trans_lock); + + path = btrfs_alloc_path(); + if (!path) { + ret = -ENOMEM; + goto unlock; + } + + path->reada = READA_FORWARD; + path->search_commit_root = 1; + path->skip_locking = 1; + + key.objectid = src_dev->devid; + key.type = BTRFS_DEV_EXTENT_KEY; + key.offset = 0; + + ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); + if (ret < 0) + goto free_path; + if (ret > 0) { + if (path->slots[0] >= + btrfs_header_nritems(path->nodes[0])) { + ret = btrfs_next_leaf(root, path); + if (ret < 0) + goto free_path; + if (ret > 0) { + ret = 0; + goto free_path; + } + } else { + ret = 0; + } + } + + while (1) { + struct extent_buffer *leaf = path->nodes[0]; + int slot = path->slots[0]; + + btrfs_item_key_to_cpu(leaf, &found_key, slot); + + if (found_key.objectid != src_dev->devid) + break; + + if (found_key.type != BTRFS_DEV_EXTENT_KEY) + break; + + if (found_key.offset < key.offset) + break; + + dev_extent = btrfs_item_ptr(leaf, slot, struct btrfs_dev_extent); + + chunk_offset = btrfs_dev_extent_chunk_offset(leaf, dev_extent); + + cache = btrfs_lookup_block_group(fs_info, chunk_offset); + if (!cache) + goto skip; + + spin_lock(&cache->lock); + cache->to_copy = 1; + spin_unlock(&cache->lock); + + btrfs_put_block_group(cache); + +skip: + ret = btrfs_next_item(root, path); + if (ret != 0) { + if (ret > 0) + ret = 0; + break; + } + } + +free_path: + btrfs_free_path(path); +unlock: + mutex_unlock(&fs_info->chunk_mutex); + + return ret; +} + +bool btrfs_finish_block_group_to_copy(struct btrfs_device *srcdev, + struct btrfs_block_group *cache, + u64 physical) +{ + struct btrfs_fs_info *fs_info = cache->fs_info; + struct extent_map *em; + struct map_lookup *map; + u64 chunk_offset = cache->start; + int num_extents, cur_extent; + int i; + + /* Do not use "to_copy" on non zoned filesystem for now */ + if (!btrfs_is_zoned(fs_info)) + return true; + + spin_lock(&cache->lock); + if (cache->removed) { + spin_unlock(&cache->lock); + return true; + } + spin_unlock(&cache->lock); + + em = btrfs_get_chunk_map(fs_info, chunk_offset, 1); + ASSERT(!IS_ERR(em)); + map = em->map_lookup; + + num_extents = cur_extent = 0; + for (i = 0; i < map->num_stripes; i++) { + /* We have more device extent to copy */ + if (srcdev != map->stripes[i].dev) + continue; + + num_extents++; + if (physical == map->stripes[i].physical) + cur_extent = i; + } + + free_extent_map(em); + + if (num_extents > 1 && cur_extent < num_extents - 1) { + /* + * Has more stripes on this device. Keep this block group + * readonly until we finish all the stripes. + */ + return false; + } + + /* Last stripe on this device */ + spin_lock(&cache->lock); + cache->to_copy = 0; + spin_unlock(&cache->lock); + + return true; +} + static int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info, const char *tgtdev_name, u64 srcdevid, const char *srcdev_name, int read_src) @@ -500,6 +680,10 @@ static int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info, if (ret) return ret; + ret = mark_block_group_to_copy(fs_info, src_device); + if (ret) + return ret; + down_write(&dev_replace->rwsem); switch (dev_replace->replace_state) { case BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED: @@ -715,7 +899,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, * flush all outstanding I/O and inode extent mappings before the * copy operation is declared as being finished */ - ret = btrfs_start_delalloc_roots(fs_info, U64_MAX); + ret = btrfs_start_delalloc_roots(fs_info, LONG_MAX, false); if (ret) { mutex_unlock(&dev_replace->lock_finishing_cancel_unmount); return ret; diff --git a/fs/btrfs/dev-replace.h b/fs/btrfs/dev-replace.h index 60b70dacc299..3911049a5f23 100644 --- a/fs/btrfs/dev-replace.h +++ b/fs/btrfs/dev-replace.h @@ -18,5 +18,8 @@ int btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info); void btrfs_dev_replace_suspend_for_unmount(struct btrfs_fs_info *fs_info); int btrfs_resume_dev_replace_async(struct btrfs_fs_info *fs_info); int __pure btrfs_dev_replace_is_ongoing(struct btrfs_dev_replace *dev_replace); +bool btrfs_finish_block_group_to_copy(struct btrfs_device *srcdev, + struct btrfs_block_group *cache, + u64 physical); #endif diff --git a/fs/btrfs/discard.c b/fs/btrfs/discard.c index 1db966bf85b2..306ff20af70f 100644 --- a/fs/btrfs/discard.c +++ b/fs/btrfs/discard.c @@ -185,10 +185,12 @@ static struct btrfs_block_group *find_next_block_group( } /** - * peek_discard_list - wrap find_next_block_group() - * @discard_ctl: discard control + * Wrap find_next_block_group() + * + * @discard_ctl: discard control * @discard_state: the discard_state of the block_group after state management * @discard_index: the discard_index of the block_group after state management + * @now: time when discard was invoked, in ns * * This wraps find_next_block_group() and sets the block_group to be in use. * discard_state's control flow is managed here. Variables related to @@ -199,16 +201,15 @@ static struct btrfs_block_group *find_next_block_group( static struct btrfs_block_group *peek_discard_list( struct btrfs_discard_ctl *discard_ctl, enum btrfs_discard_state *discard_state, - int *discard_index) + int *discard_index, u64 now) { struct btrfs_block_group *block_group; - const u64 now = ktime_get_ns(); spin_lock(&discard_ctl->lock); again: block_group = find_next_block_group(discard_ctl, now); - if (block_group && now > block_group->discard_eligible_time) { + if (block_group && now >= block_group->discard_eligible_time) { if (block_group->discard_index == BTRFS_DISCARD_INDEX_UNUSED && block_group->used != 0) { if (btrfs_is_block_group_data_only(block_group)) @@ -222,12 +223,11 @@ again: block_group->discard_state = BTRFS_DISCARD_EXTENTS; } discard_ctl->block_group = block_group; + } + if (block_group) { *discard_state = block_group->discard_state; *discard_index = block_group->discard_index; - } else { - block_group = NULL; } - spin_unlock(&discard_ctl->lock); return block_group; @@ -330,28 +330,15 @@ void btrfs_discard_queue_work(struct btrfs_discard_ctl *discard_ctl, btrfs_discard_schedule_work(discard_ctl, false); } -/** - * btrfs_discard_schedule_work - responsible for scheduling the discard work - * @discard_ctl: discard control - * @override: override the current timer - * - * Discards are issued by a delayed workqueue item. @override is used to - * update the current delay as the baseline delay interval is reevaluated on - * transaction commit. This is also maxed with any other rate limit. - */ -void btrfs_discard_schedule_work(struct btrfs_discard_ctl *discard_ctl, - bool override) +static void __btrfs_discard_schedule_work(struct btrfs_discard_ctl *discard_ctl, + u64 now, bool override) { struct btrfs_block_group *block_group; - const u64 now = ktime_get_ns(); - - spin_lock(&discard_ctl->lock); if (!btrfs_run_discard_work(discard_ctl)) - goto out; - + return; if (!override && delayed_work_pending(&discard_ctl->work)) - goto out; + return; block_group = find_next_block_group(discard_ctl, now); if (block_group) { @@ -393,7 +380,24 @@ void btrfs_discard_schedule_work(struct btrfs_discard_ctl *discard_ctl, mod_delayed_work(discard_ctl->discard_workers, &discard_ctl->work, nsecs_to_jiffies(delay)); } -out: +} + +/* + * btrfs_discard_schedule_work - responsible for scheduling the discard work + * @discard_ctl: discard control + * @override: override the current timer + * + * Discards are issued by a delayed workqueue item. @override is used to + * update the current delay as the baseline delay interval is reevaluated on + * transaction commit. This is also maxed with any other rate limit. + */ +void btrfs_discard_schedule_work(struct btrfs_discard_ctl *discard_ctl, + bool override) +{ + const u64 now = ktime_get_ns(); + + spin_lock(&discard_ctl->lock); + __btrfs_discard_schedule_work(discard_ctl, now, override); spin_unlock(&discard_ctl->lock); } @@ -438,13 +442,18 @@ static void btrfs_discard_workfn(struct work_struct *work) int discard_index = 0; u64 trimmed = 0; u64 minlen = 0; + u64 now = ktime_get_ns(); discard_ctl = container_of(work, struct btrfs_discard_ctl, work.work); block_group = peek_discard_list(discard_ctl, &discard_state, - &discard_index); + &discard_index, now); if (!block_group || !btrfs_run_discard_work(discard_ctl)) return; + if (now < block_group->discard_eligible_time) { + btrfs_discard_schedule_work(discard_ctl, false); + return; + } /* Perform discarding */ minlen = discard_minlen[discard_index]; @@ -474,13 +483,6 @@ static void btrfs_discard_workfn(struct work_struct *work) discard_ctl->discard_extent_bytes += trimmed; } - /* - * Updated without locks as this is inside the workfn and nothing else - * is reading the values - */ - discard_ctl->prev_discard = trimmed; - discard_ctl->prev_discard_time = ktime_get_ns(); - /* Determine next steps for a block_group */ if (block_group->discard_cursor >= btrfs_block_group_end(block_group)) { if (discard_state == BTRFS_DISCARD_BITMAPS) { @@ -496,11 +498,13 @@ static void btrfs_discard_workfn(struct work_struct *work) } } + now = ktime_get_ns(); spin_lock(&discard_ctl->lock); + discard_ctl->prev_discard = trimmed; + discard_ctl->prev_discard_time = now; discard_ctl->block_group = NULL; + __btrfs_discard_schedule_work(discard_ctl, now, false); spin_unlock(&discard_ctl->lock); - - btrfs_discard_schedule_work(discard_ctl, false); } /** diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 765deefda92b..41b718cfea40 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -459,6 +459,12 @@ static int csum_dirty_buffer(struct btrfs_fs_info *fs_info, struct bio_vec *bvec return 0; found_start = btrfs_header_bytenr(eb); + + if (test_bit(EXTENT_BUFFER_NO_CHECK, &eb->bflags)) { + WARN_ON(found_start != 0); + return 0; + } + /* * Please do not consolidate these warnings into a single if. * It is useful to know what went wrong. @@ -591,6 +597,59 @@ out: return ret; } +static int validate_subpage_buffer(struct page *page, u64 start, u64 end, + int mirror) +{ + struct btrfs_fs_info *fs_info = btrfs_sb(page->mapping->host->i_sb); + struct extent_buffer *eb; + bool reads_done; + int ret = 0; + + /* + * We don't allow bio merge for subpage metadata read, so we should + * only get one eb for each endio hook. + */ + ASSERT(end == start + fs_info->nodesize - 1); + ASSERT(PagePrivate(page)); + + eb = find_extent_buffer(fs_info, start); + /* + * When we are reading one tree block, eb must have been inserted into + * the radix tree. If not, something is wrong. + */ + ASSERT(eb); + + reads_done = atomic_dec_and_test(&eb->io_pages); + /* Subpage read must finish in page read */ + ASSERT(reads_done); + + eb->read_mirror = mirror; + if (test_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags)) { + ret = -EIO; + goto err; + } + ret = validate_extent_buffer(eb); + if (ret < 0) + goto err; + + if (test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags)) + btree_readahead_hook(eb, ret); + + set_extent_buffer_uptodate(eb); + + free_extent_buffer(eb); + return ret; +err: + /* + * end_bio_extent_readpage decrements io_pages in case of error, + * make sure it has something to decrement. + */ + atomic_inc(&eb->io_pages); + clear_extent_buffer_uptodate(eb); + free_extent_buffer(eb); + return ret; +} + int btrfs_validate_metadata_buffer(struct btrfs_io_bio *io_bio, struct page *page, u64 start, u64 end, int mirror) @@ -600,6 +659,10 @@ int btrfs_validate_metadata_buffer(struct btrfs_io_bio *io_bio, int reads_done; ASSERT(page->private); + + if (btrfs_sb(page->mapping->host->i_sb)->sectorsize < PAGE_SIZE) + return validate_subpage_buffer(page, start, end, mirror); + eb = (struct extent_buffer *)page->private; /* @@ -646,7 +709,7 @@ static void end_workqueue_bio(struct bio *bio) fs_info = end_io_wq->info; end_io_wq->status = bio->bi_status; - if (bio_op(bio) == REQ_OP_WRITE) { + if (btrfs_op(bio) == BTRFS_MAP_WRITE) { if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA) wq = fs_info->endio_meta_write_workers; else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_FREE_SPACE) @@ -808,6 +871,8 @@ static blk_status_t btree_submit_bio_start(struct inode *inode, struct bio *bio, static int check_async_write(struct btrfs_fs_info *fs_info, struct btrfs_inode *bi) { + if (btrfs_is_zoned(fs_info)) + return 0; if (atomic_read(&bi->sync_writers)) return 0; if (test_bit(BTRFS_FS_CSUM_IMPL_FAST, &fs_info->flags)) @@ -822,7 +887,7 @@ blk_status_t btrfs_submit_metadata_bio(struct inode *inode, struct bio *bio, int async = check_async_write(fs_info, BTRFS_I(inode)); blk_status_t ret; - if (bio_op(bio) != REQ_OP_WRITE) { + if (btrfs_op(bio) != BTRFS_MAP_WRITE) { /* * called for a read, do the setup so that checksum validation * can happen in the async kernel threads @@ -1016,7 +1081,7 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info, root->orphan_cleanup_state = 0; root->last_trans = 0; - root->highest_objectid = 0; + root->free_objectid = 0; root->nr_delalloc_inodes = 0; root->nr_ordered_extents = 0; root->inode_tree = RB_ROOT; @@ -1189,7 +1254,6 @@ static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info) { struct btrfs_root *root; - struct extent_buffer *leaf; root = btrfs_alloc_root(fs_info, BTRFS_TREE_LOG_OBJECTID, GFP_NOFS); if (!root) @@ -1199,6 +1263,14 @@ static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans, root->root_key.type = BTRFS_ROOT_ITEM_KEY; root->root_key.offset = BTRFS_TREE_LOG_OBJECTID; + return root; +} + +int btrfs_alloc_log_tree_node(struct btrfs_trans_handle *trans, + struct btrfs_root *root) +{ + struct extent_buffer *leaf; + /* * DON'T set SHAREABLE bit for log trees. * @@ -1211,16 +1283,15 @@ static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans, leaf = btrfs_alloc_tree_block(trans, root, 0, BTRFS_TREE_LOG_OBJECTID, NULL, 0, 0, 0, BTRFS_NESTING_NORMAL); - if (IS_ERR(leaf)) { - btrfs_put_root(root); - return ERR_CAST(leaf); - } + if (IS_ERR(leaf)) + return PTR_ERR(leaf); root->node = leaf; btrfs_mark_buffer_dirty(root->node); btrfs_tree_unlock(root->node); - return root; + + return 0; } int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans, @@ -1231,6 +1302,16 @@ int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans, log_root = alloc_log_tree(trans, fs_info); if (IS_ERR(log_root)) return PTR_ERR(log_root); + + if (!btrfs_is_zoned(fs_info)) { + int ret = btrfs_alloc_log_tree_node(trans, log_root); + + if (ret) { + btrfs_put_root(log_root); + return ret; + } + } + WARN_ON(fs_info->log_root_tree); fs_info->log_root_tree = log_root; return 0; @@ -1242,11 +1323,18 @@ int btrfs_add_log_tree(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_root *log_root; struct btrfs_inode_item *inode_item; + int ret; log_root = alloc_log_tree(trans, fs_info); if (IS_ERR(log_root)) return PTR_ERR(log_root); + ret = btrfs_alloc_log_tree_node(trans, log_root); + if (ret) { + btrfs_put_root(log_root); + return ret; + } + log_root->last_trans = trans->transid; log_root->root_key.offset = root->root_key.objectid; @@ -1367,14 +1455,13 @@ static int btrfs_init_fs_root(struct btrfs_root *root, dev_t anon_dev) } mutex_lock(&root->objectid_mutex); - ret = btrfs_find_highest_objectid(root, - &root->highest_objectid); + ret = btrfs_init_root_free_objectid(root); if (ret) { mutex_unlock(&root->objectid_mutex); goto fail; } - ASSERT(root->highest_objectid <= BTRFS_LAST_FREE_OBJECTID); + ASSERT(root->free_objectid <= BTRFS_LAST_FREE_OBJECTID); mutex_unlock(&root->objectid_mutex); @@ -1457,7 +1544,7 @@ void btrfs_check_leaked_roots(struct btrfs_fs_info *fs_info) root = list_first_entry(&fs_info->allocated_roots, struct btrfs_root, leak_list); btrfs_err(fs_info, "leaked root %s refcount %d", - btrfs_root_name(root->root_key.objectid, buf), + btrfs_root_name(&root->root_key, buf), refcount_read(&root->refs)); while (refcount_read(&root->refs) > 1) btrfs_put_root(root); @@ -1470,7 +1557,7 @@ void btrfs_free_fs_info(struct btrfs_fs_info *fs_info) { percpu_counter_destroy(&fs_info->dirty_metadata_bytes); percpu_counter_destroy(&fs_info->delalloc_bytes); - percpu_counter_destroy(&fs_info->dio_bytes); + percpu_counter_destroy(&fs_info->ordered_bytes); percpu_counter_destroy(&fs_info->dev_replace.bio_counter); btrfs_free_csum_hash(fs_info); btrfs_free_stripe_hash_table(fs_info); @@ -1729,7 +1816,7 @@ static int cleaner_kthread(void *arg) */ btrfs_delete_unused_bgs(fs_info); sleep: - clear_bit(BTRFS_FS_CLEANER_RUNNING, &fs_info->flags); + clear_and_wake_up_bit(BTRFS_FS_CLEANER_RUNNING, &fs_info->flags); if (kthread_should_park()) kthread_parkme(); if (kthread_should_stop()) @@ -2427,13 +2514,21 @@ static int validate_super(struct btrfs_fs_info *fs_info, btrfs_err(fs_info, "invalid sectorsize %llu", sectorsize); ret = -EINVAL; } - /* Only PAGE SIZE is supported yet */ - if (sectorsize != PAGE_SIZE) { + + /* + * For 4K page size, we only support 4K sector size. + * For 64K page size, we support read-write for 64K sector size, and + * read-only for 4K sector size. + */ + if ((PAGE_SIZE == SZ_4K && sectorsize != PAGE_SIZE) || + (PAGE_SIZE == SZ_64K && (sectorsize != SZ_4K && + sectorsize != SZ_64K))) { btrfs_err(fs_info, - "sectorsize %llu not supported yet, only support %lu", + "sectorsize %llu not yet supported for page size %lu", sectorsize, PAGE_SIZE); ret = -EINVAL; } + if (!is_power_of_2(nodesize) || nodesize < sectorsize || nodesize > BTRFS_MAX_METADATA_BLOCKSIZE) { btrfs_err(fs_info, "invalid nodesize %llu", nodesize); @@ -2646,14 +2741,13 @@ static int __cold init_tree_roots(struct btrfs_fs_info *fs_info) * No need to hold btrfs_root::objectid_mutex since the fs * hasn't been fully initialised and we are the only user */ - ret = btrfs_find_highest_objectid(tree_root, - &tree_root->highest_objectid); + ret = btrfs_init_root_free_objectid(tree_root); if (ret < 0) { handle_error = true; continue; } - ASSERT(tree_root->highest_objectid <= BTRFS_LAST_FREE_OBJECTID); + ASSERT(tree_root->free_objectid <= BTRFS_LAST_FREE_OBJECTID); ret = btrfs_read_roots(fs_info); if (ret < 0) { @@ -2695,11 +2789,13 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info) spin_lock_init(&fs_info->super_lock); spin_lock_init(&fs_info->buffer_lock); spin_lock_init(&fs_info->unused_bgs_lock); + spin_lock_init(&fs_info->treelog_bg_lock); rwlock_init(&fs_info->tree_mod_log_lock); mutex_init(&fs_info->unused_bg_unpin_mutex); mutex_init(&fs_info->delete_unused_bgs_mutex); mutex_init(&fs_info->reloc_mutex); mutex_init(&fs_info->delalloc_root_mutex); + mutex_init(&fs_info->zoned_meta_io_lock); seqlock_init(&fs_info->profiles_lock); INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots); @@ -2804,7 +2900,7 @@ static int init_mount_fs_info(struct btrfs_fs_info *fs_info, struct super_block sb->s_blocksize = BTRFS_BDEV_BLOCKSIZE; sb->s_blocksize_bits = blksize_bits(BTRFS_BDEV_BLOCKSIZE); - ret = percpu_counter_init(&fs_info->dio_bytes, 0, GFP_KERNEL); + ret = percpu_counter_init(&fs_info->ordered_bytes, 0, GFP_KERNEL); if (ret) return ret; @@ -2830,6 +2926,9 @@ static int init_mount_fs_info(struct btrfs_fs_info *fs_info, struct super_block return -ENOMEM; btrfs_init_delayed_root(fs_info->delayed_root); + if (sb_rdonly(sb)) + set_bit(BTRFS_FS_STATE_RO, &fs_info->fs_state); + return btrfs_alloc_stripe_hash_table(fs_info); } @@ -2969,6 +3068,7 @@ int btrfs_start_pre_rw_mount(struct btrfs_fs_info *fs_info) } } + ret = btrfs_find_orphan_roots(fs_info); out: return ret; } @@ -3040,6 +3140,8 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device goto fail_alloc; } + fs_info->csum_size = btrfs_super_csum_size(disk_super); + ret = btrfs_init_csum_hash(fs_info, csum_type); if (ret) { err = ret; @@ -3134,8 +3236,6 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device if (features & BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA) btrfs_info(fs_info, "has skinny extents"); - fs_info->zoned = (features & BTRFS_FEATURE_INCOMPAT_ZONED); - /* * flag our filesystem as having big metadata blocks if * they are bigger than the page size @@ -3157,7 +3257,6 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device fs_info->nodesize = nodesize; fs_info->sectorsize = sectorsize; fs_info->sectorsize_bits = ilog2(sectorsize); - fs_info->csum_size = btrfs_super_csum_size(disk_super); fs_info->csums_per_leaf = BTRFS_MAX_ITEM_SIZE(fs_info) / fs_info->csum_size; fs_info->stripesize = stripesize; @@ -3189,6 +3288,17 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device goto fail_alloc; } + /* For 4K sector size support, it's only read-only */ + if (PAGE_SIZE == SZ_64K && sectorsize == SZ_4K) { + if (!sb_rdonly(sb) || btrfs_super_log_root(disk_super)) { + btrfs_err(fs_info, + "subpage sectorsize %u only supported read-only for page size %lu", + sectorsize, PAGE_SIZE); + err = -EINVAL; + goto fail_alloc; + } + } + ret = btrfs_init_workqueues(fs_info, fs_devices); if (ret) { err = ret; @@ -3256,6 +3366,19 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device goto fail_tree_roots; /* + * Get zone type information of zoned block devices. This will also + * handle emulation of a zoned filesystem if a regular device has the + * zoned incompat feature flag set. + */ + ret = btrfs_get_dev_zone_info_all_devices(fs_info); + if (ret) { + btrfs_err(fs_info, + "zoned: failed to read device zone info: %d", + ret); + goto fail_block_groups; + } + + /* * If we have a uuid root and we're not being told to rescan we need to * check the generation here so we can set the * BTRFS_FS_UPDATE_UUID_TREE_GEN bit. Otherwise we could commit the @@ -3383,10 +3506,6 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device } } - ret = btrfs_find_orphan_roots(fs_info); - if (ret) - goto fail_qgroup; - fs_info->fs_root = btrfs_get_fs_root(fs_info, BTRFS_FS_TREE_OBJECTID, true); if (IS_ERR(fs_info->fs_root)) { err = PTR_ERR(fs_info->fs_root); @@ -4113,6 +4232,7 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) cancel_work_sync(&fs_info->async_reclaim_work); cancel_work_sync(&fs_info->async_data_reclaim_work); + cancel_work_sync(&fs_info->preempt_reclaim_work); /* Cancel or finish ongoing discard work */ btrfs_discard_cleanup(fs_info); @@ -4165,9 +4285,9 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) percpu_counter_sum(&fs_info->delalloc_bytes)); } - if (percpu_counter_sum(&fs_info->dio_bytes)) + if (percpu_counter_sum(&fs_info->ordered_bytes)) btrfs_info(fs_info, "at unmount dio bytes count %lld", - percpu_counter_sum(&fs_info->dio_bytes)); + percpu_counter_sum(&fs_info->ordered_bytes)); btrfs_sysfs_remove_mounted(fs_info); btrfs_sysfs_remove_fsid(fs_info->fs_devices); @@ -4181,6 +4301,9 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) invalidate_inode_pages2(fs_info->btree_inode->i_mapping); btrfs_stop_all_workers(fs_info); + /* We shouldn't have any transaction open at this point */ + ASSERT(list_empty(&fs_info->trans_list)); + clear_bit(BTRFS_FS_OPEN, &fs_info->flags); free_root_pointers(fs_info, true); btrfs_free_fs_roots(fs_info); @@ -4685,6 +4808,8 @@ void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans, EXTENT_DIRTY); btrfs_destroy_pinned_extent(fs_info, &cur_trans->pinned_extents); + btrfs_free_redirty_list(cur_trans); + cur_trans->state =TRANS_STATE_COMPLETED; wake_up(&cur_trans->commit_wait); } @@ -4742,7 +4867,7 @@ static int btrfs_cleanup_transaction(struct btrfs_fs_info *fs_info) return 0; } -int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid) +int btrfs_init_root_free_objectid(struct btrfs_root *root) { struct btrfs_path *path; int ret; @@ -4766,10 +4891,10 @@ int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid) slot = path->slots[0] - 1; l = path->nodes[0]; btrfs_item_key_to_cpu(l, &found_key, slot); - *objectid = max_t(u64, found_key.objectid, - BTRFS_FIRST_FREE_OBJECTID - 1); + root->free_objectid = max_t(u64, found_key.objectid + 1, + BTRFS_FIRST_FREE_OBJECTID); } else { - *objectid = BTRFS_FIRST_FREE_OBJECTID - 1; + root->free_objectid = BTRFS_FIRST_FREE_OBJECTID; } ret = 0; error: @@ -4777,12 +4902,12 @@ error: return ret; } -int btrfs_find_free_objectid(struct btrfs_root *root, u64 *objectid) +int btrfs_get_free_objectid(struct btrfs_root *root, u64 *objectid) { int ret; mutex_lock(&root->objectid_mutex); - if (unlikely(root->highest_objectid >= BTRFS_LAST_FREE_OBJECTID)) { + if (unlikely(root->free_objectid >= BTRFS_LAST_FREE_OBJECTID)) { btrfs_warn(root->fs_info, "the objectid of root %llu reaches its highest value", root->root_key.objectid); @@ -4790,7 +4915,7 @@ int btrfs_find_free_objectid(struct btrfs_root *root, u64 *objectid) goto out; } - *objectid = ++root->highest_objectid; + *objectid = root->free_objectid++; ret = 0; out: mutex_unlock(&root->objectid_mutex); diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index e45057c0c016..0e7e9526b6a8 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -120,6 +120,8 @@ blk_status_t btrfs_wq_submit_bio(struct inode *inode, struct bio *bio, extent_submit_bio_start_t *submit_bio_start); blk_status_t btrfs_submit_bio_done(void *private_data, struct bio *bio, int mirror_num); +int btrfs_alloc_log_tree_node(struct btrfs_trans_handle *trans, + struct btrfs_root *root); int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info); int btrfs_add_log_tree(struct btrfs_trans_handle *trans, @@ -133,8 +135,8 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans, int btree_lock_page_hook(struct page *page, void *data, void (*flush_fn)(void *)); int btrfs_get_num_tolerated_disk_barrier_failures(u64 flags); -int btrfs_find_free_objectid(struct btrfs_root *root, u64 *objectid); -int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid); +int btrfs_get_free_objectid(struct btrfs_root *root, u64 *objectid); +int btrfs_init_root_free_objectid(struct btrfs_root *root); int __init btrfs_end_io_wq_init(void); void __cold btrfs_end_io_wq_exit(void); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 56ea380f5a17..78ad31a59e59 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -34,6 +34,8 @@ #include "block-group.h" #include "discard.h" #include "rcu-string.h" +#include "zoned.h" +#include "dev-replace.h" #undef SCRAMBLE_DELAYED_REFS @@ -82,41 +84,6 @@ void btrfs_free_excluded_extents(struct btrfs_block_group *cache) EXTENT_UPTODATE); } -static u64 generic_ref_to_space_flags(struct btrfs_ref *ref) -{ - if (ref->type == BTRFS_REF_METADATA) { - if (ref->tree_ref.root == BTRFS_CHUNK_TREE_OBJECTID) - return BTRFS_BLOCK_GROUP_SYSTEM; - else - return BTRFS_BLOCK_GROUP_METADATA; - } - return BTRFS_BLOCK_GROUP_DATA; -} - -static void add_pinned_bytes(struct btrfs_fs_info *fs_info, - struct btrfs_ref *ref) -{ - struct btrfs_space_info *space_info; - u64 flags = generic_ref_to_space_flags(ref); - - space_info = btrfs_find_space_info(fs_info, flags); - ASSERT(space_info); - percpu_counter_add_batch(&space_info->total_bytes_pinned, ref->len, - BTRFS_TOTAL_BYTES_PINNED_BATCH); -} - -static void sub_pinned_bytes(struct btrfs_fs_info *fs_info, - struct btrfs_ref *ref) -{ - struct btrfs_space_info *space_info; - u64 flags = generic_ref_to_space_flags(ref); - - space_info = btrfs_find_space_info(fs_info, flags); - ASSERT(space_info); - percpu_counter_add_batch(&space_info->total_bytes_pinned, -ref->len, - BTRFS_TOTAL_BYTES_PINNED_BATCH); -} - /* simple helper to search for an existing data extent at a given offset */ int btrfs_lookup_data_extent(struct btrfs_fs_info *fs_info, u64 start, u64 len) { @@ -844,6 +811,7 @@ int lookup_inline_extent_backref(struct btrfs_trans_handle *trans, want = extent_ref_type(parent, owner); if (insert) { extra_size = btrfs_extent_inline_ref_size(want); + path->search_for_extension = 1; path->keep_locks = 1; } else extra_size = -1; @@ -996,6 +964,7 @@ again: out: if (insert) { path->keep_locks = 0; + path->search_for_extension = 0; btrfs_unlock_up_safe(path, 1); } return err; @@ -1297,6 +1266,46 @@ static int btrfs_issue_discard(struct block_device *bdev, u64 start, u64 len, return ret; } +static int do_discard_extent(struct btrfs_bio_stripe *stripe, u64 *bytes) +{ + struct btrfs_device *dev = stripe->dev; + struct btrfs_fs_info *fs_info = dev->fs_info; + struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace; + u64 phys = stripe->physical; + u64 len = stripe->length; + u64 discarded = 0; + int ret = 0; + + /* Zone reset on a zoned filesystem */ + if (btrfs_can_zone_reset(dev, phys, len)) { + u64 src_disc; + + ret = btrfs_reset_device_zone(dev, phys, len, &discarded); + if (ret) + goto out; + + if (!btrfs_dev_replace_is_ongoing(dev_replace) || + dev != dev_replace->srcdev) + goto out; + + src_disc = discarded; + + /* Send to replace target as well */ + ret = btrfs_reset_device_zone(dev_replace->tgtdev, phys, len, + &discarded); + discarded += src_disc; + } else if (blk_queue_discard(bdev_get_queue(stripe->dev->bdev))) { + ret = btrfs_issue_discard(dev->bdev, phys, len, &discarded); + } else { + ret = 0; + *bytes = 0; + } + +out: + *bytes = discarded; + return ret; +} + int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr, u64 num_bytes, u64 *actual_bytes) { @@ -1331,20 +1340,13 @@ int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr, stripe = bbio->stripes; for (i = 0; i < bbio->num_stripes; i++, stripe++) { u64 bytes; - struct request_queue *req_q; if (!stripe->dev->bdev) { ASSERT(btrfs_test_opt(fs_info, DEGRADED)); continue; } - req_q = bdev_get_queue(stripe->dev->bdev); - if (!blk_queue_discard(req_q)) - continue; - ret = btrfs_issue_discard(stripe->dev->bdev, - stripe->physical, - stripe->length, - &bytes); + ret = do_discard_extent(stripe, &bytes); if (!ret) { discarded_bytes += bytes; } else if (ret != -EOPNOTSUPP) { @@ -1386,7 +1388,6 @@ int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, struct btrfs_ref *generic_ref) { struct btrfs_fs_info *fs_info = trans->fs_info; - int old_ref_mod, new_ref_mod; int ret; ASSERT(generic_ref->type != BTRFS_REF_NOT_SET && @@ -1395,17 +1396,12 @@ int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, generic_ref->tree_ref.root == BTRFS_TREE_LOG_OBJECTID); if (generic_ref->type == BTRFS_REF_METADATA) - ret = btrfs_add_delayed_tree_ref(trans, generic_ref, - NULL, &old_ref_mod, &new_ref_mod); + ret = btrfs_add_delayed_tree_ref(trans, generic_ref, NULL); else - ret = btrfs_add_delayed_data_ref(trans, generic_ref, 0, - &old_ref_mod, &new_ref_mod); + ret = btrfs_add_delayed_data_ref(trans, generic_ref, 0); btrfs_ref_tree_mod(fs_info, generic_ref); - if (ret == 0 && old_ref_mod < 0 && new_ref_mod >= 0) - sub_pinned_bytes(fs_info, generic_ref); - return ret; } @@ -1793,34 +1789,28 @@ void btrfs_cleanup_ref_head_accounting(struct btrfs_fs_info *fs_info, { int nr_items = 1; /* Dropping this ref head update. */ - if (head->total_ref_mod < 0) { - struct btrfs_space_info *space_info; - u64 flags; + /* + * We had csum deletions accounted for in our delayed refs rsv, we need + * to drop the csum leaves for this update from our delayed_refs_rsv. + */ + if (head->total_ref_mod < 0 && head->is_data) { + spin_lock(&delayed_refs->lock); + delayed_refs->pending_csums -= head->num_bytes; + spin_unlock(&delayed_refs->lock); + nr_items += btrfs_csum_bytes_to_leaves(fs_info, head->num_bytes); + } - if (head->is_data) - flags = BTRFS_BLOCK_GROUP_DATA; - else if (head->is_system) - flags = BTRFS_BLOCK_GROUP_SYSTEM; - else - flags = BTRFS_BLOCK_GROUP_METADATA; - space_info = btrfs_find_space_info(fs_info, flags); - ASSERT(space_info); - percpu_counter_add_batch(&space_info->total_bytes_pinned, - -head->num_bytes, - BTRFS_TOTAL_BYTES_PINNED_BATCH); + /* + * We were dropping refs, or had a new ref and dropped it, and thus must + * adjust down our total_bytes_pinned, the space may or may not have + * been pinned and so is accounted for properly in the pinned space by + * now. + */ + if (head->total_ref_mod < 0 || + (head->total_ref_mod == 0 && head->must_insert_reserved)) { + u64 flags = btrfs_ref_head_to_space_flags(head); - /* - * We had csum deletions accounted for in our delayed refs rsv, - * we need to drop the csum leaves for this update from our - * delayed_refs_rsv. - */ - if (head->is_data) { - spin_lock(&delayed_refs->lock); - delayed_refs->pending_csums -= head->num_bytes; - spin_unlock(&delayed_refs->lock); - nr_items += btrfs_csum_bytes_to_leaves(fs_info, - head->num_bytes); - } + btrfs_mod_total_bytes_pinned(fs_info, flags, -head->num_bytes); } btrfs_delayed_refs_rsv_release(fs_info, nr_items); @@ -2158,7 +2148,7 @@ int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans, delayed_refs = &trans->transaction->delayed_refs; if (count == 0) - count = atomic_read(&delayed_refs->num_entries) * 2; + count = delayed_refs->num_heads_ready; again: #ifdef SCRAMBLE_DELAYED_REFS @@ -2570,8 +2560,7 @@ static int pin_down_extent(struct btrfs_trans_handle *trans, spin_unlock(&cache->lock); spin_unlock(&cache->space_info->lock); - percpu_counter_add_batch(&cache->space_info->total_bytes_pinned, - num_bytes, BTRFS_TOTAL_BYTES_PINNED_BATCH); + __btrfs_mod_total_bytes_pinned(cache->space_info, num_bytes); set_extent_dirty(&trans->transaction->pinned_extents, bytenr, bytenr + num_bytes - 1, GFP_NOFS | __GFP_NOFAIL); return 0; @@ -2600,8 +2589,6 @@ int btrfs_pin_extent_for_log_replay(struct btrfs_trans_handle *trans, struct btrfs_block_group *cache; int ret; - btrfs_add_excluded_extent(trans->fs_info, bytenr, num_bytes); - cache = btrfs_lookup_block_group(trans->fs_info, bytenr); if (!cache) return -EINVAL; @@ -2613,11 +2600,19 @@ int btrfs_pin_extent_for_log_replay(struct btrfs_trans_handle *trans, * the pinned extents. */ btrfs_cache_block_group(cache, 1); + /* + * Make sure we wait until the cache is completely built in case it is + * missing or is invalid and therefore needs to be rebuilt. + */ + ret = btrfs_wait_block_group_cache_done(cache); + if (ret) + goto out; pin_down_extent(trans, cache, bytenr, num_bytes, 0); /* remove us from the free space cache (if we're there at all) */ ret = btrfs_remove_free_space(cache, bytenr, num_bytes); +out: btrfs_put_block_group(cache); return ret; } @@ -2627,50 +2622,22 @@ static int __exclude_logged_extent(struct btrfs_fs_info *fs_info, { int ret; struct btrfs_block_group *block_group; - struct btrfs_caching_control *caching_ctl; block_group = btrfs_lookup_block_group(fs_info, start); if (!block_group) return -EINVAL; - btrfs_cache_block_group(block_group, 0); - caching_ctl = btrfs_get_caching_control(block_group); - - if (!caching_ctl) { - /* Logic error */ - BUG_ON(!btrfs_block_group_done(block_group)); - ret = btrfs_remove_free_space(block_group, start, num_bytes); - } else { - /* - * We must wait for v1 caching to finish, otherwise we may not - * remove our space. - */ - btrfs_wait_space_cache_v1_finished(block_group, caching_ctl); - mutex_lock(&caching_ctl->mutex); - - if (start >= caching_ctl->progress) { - ret = btrfs_add_excluded_extent(fs_info, start, - num_bytes); - } else if (start + num_bytes <= caching_ctl->progress) { - ret = btrfs_remove_free_space(block_group, - start, num_bytes); - } else { - num_bytes = caching_ctl->progress - start; - ret = btrfs_remove_free_space(block_group, - start, num_bytes); - if (ret) - goto out_lock; + btrfs_cache_block_group(block_group, 1); + /* + * Make sure we wait until the cache is completely built in case it is + * missing or is invalid and therefore needs to be rebuilt. + */ + ret = btrfs_wait_block_group_cache_done(block_group); + if (ret) + goto out; - num_bytes = (start + num_bytes) - - caching_ctl->progress; - start = caching_ctl->progress; - ret = btrfs_add_excluded_extent(fs_info, start, - num_bytes); - } -out_lock: - mutex_unlock(&caching_ctl->mutex); - btrfs_put_caching_control(caching_ctl); - } + ret = btrfs_remove_free_space(block_group, start, num_bytes); +out: btrfs_put_block_group(block_group); return ret; } @@ -2804,11 +2771,14 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info, cache->pinned -= len; btrfs_space_info_update_bytes_pinned(fs_info, space_info, -len); space_info->max_extent_size = 0; - percpu_counter_add_batch(&space_info->total_bytes_pinned, - -len, BTRFS_TOTAL_BYTES_PINNED_BATCH); + __btrfs_mod_total_bytes_pinned(space_info, -len); if (cache->ro) { space_info->bytes_readonly += len; readonly = true; + } else if (btrfs_is_zoned(fs_info)) { + /* Need reset before reusing in a zoned block group */ + space_info->bytes_zone_unusable += len; + readonly = true; } spin_unlock(&cache->lock); if (!readonly && return_free_space && @@ -2861,9 +2831,6 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans) mutex_unlock(&fs_info->unused_bg_unpin_mutex); break; } - if (test_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags)) - clear_extent_bits(&fs_info->excluded_extents, start, - end, EXTENT_UPTODATE); if (btrfs_test_opt(fs_info, DISCARD_SYNC)) ret = btrfs_discard_extent(fs_info, start, @@ -3341,7 +3308,6 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, { struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_ref generic_ref = { 0 }; - int pin = 1; int ret; btrfs_init_generic_ref(&generic_ref, BTRFS_DROP_DELAYED_REF, @@ -3350,13 +3316,9 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, root->root_key.objectid); if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) { - int old_ref_mod, new_ref_mod; - btrfs_ref_tree_mod(fs_info, &generic_ref); - ret = btrfs_add_delayed_tree_ref(trans, &generic_ref, NULL, - &old_ref_mod, &new_ref_mod); + ret = btrfs_add_delayed_tree_ref(trans, &generic_ref, NULL); BUG_ON(ret); /* -ENOMEM */ - pin = old_ref_mod >= 0 && new_ref_mod < 0; } if (last_ref && btrfs_header_generation(buf) == trans->transid) { @@ -3364,11 +3326,12 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) { ret = check_ref_cleanup(trans, buf->start); - if (!ret) + if (!ret) { + btrfs_redirty_list_add(trans->transaction, buf); goto out; + } } - pin = 0; cache = btrfs_lookup_block_group(fs_info, buf->start); if (btrfs_header_flag(buf, BTRFS_HEADER_FLAG_WRITTEN)) { @@ -3377,6 +3340,13 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, goto out; } + if (btrfs_is_zoned(fs_info)) { + btrfs_redirty_list_add(trans->transaction, buf); + pin_down_extent(trans, cache, buf->start, buf->len, 1); + btrfs_put_block_group(cache); + goto out; + } + WARN_ON(test_bit(EXTENT_BUFFER_DIRTY, &buf->bflags)); btrfs_add_free_space(cache, buf->start, buf->len); @@ -3385,9 +3355,6 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, trace_btrfs_reserved_extent_free(fs_info, buf->start, buf->len); } out: - if (pin) - add_pinned_bytes(fs_info, &generic_ref); - if (last_ref) { /* * Deleting the buffer, clear the corrupt flag since it doesn't @@ -3401,7 +3368,6 @@ out: int btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_ref *ref) { struct btrfs_fs_info *fs_info = trans->fs_info; - int old_ref_mod, new_ref_mod; int ret; if (btrfs_is_testing(fs_info)) @@ -3417,14 +3383,11 @@ int btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_ref *ref) ref->data_ref.ref_root == BTRFS_TREE_LOG_OBJECTID)) { /* unlocks the pinned mutex */ btrfs_pin_extent(trans, ref->bytenr, ref->len, 1); - old_ref_mod = new_ref_mod = 0; ret = 0; } else if (ref->type == BTRFS_REF_METADATA) { - ret = btrfs_add_delayed_tree_ref(trans, ref, NULL, - &old_ref_mod, &new_ref_mod); + ret = btrfs_add_delayed_tree_ref(trans, ref, NULL); } else { - ret = btrfs_add_delayed_data_ref(trans, ref, 0, - &old_ref_mod, &new_ref_mod); + ret = btrfs_add_delayed_data_ref(trans, ref, 0); } if (!((ref->type == BTRFS_REF_METADATA && @@ -3433,9 +3396,6 @@ int btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_ref *ref) ref->data_ref.ref_root == BTRFS_TREE_LOG_OBJECTID))) btrfs_ref_tree_mod(fs_info, ref); - if (ret == 0 && old_ref_mod >= 0 && new_ref_mod < 0) - add_pinned_bytes(fs_info, ref); - return ret; } @@ -3512,6 +3472,7 @@ btrfs_release_block_group(struct btrfs_block_group *cache, enum btrfs_extent_allocation_policy { BTRFS_EXTENT_ALLOC_CLUSTERED, + BTRFS_EXTENT_ALLOC_ZONED, }; /* @@ -3536,6 +3497,9 @@ struct find_free_extent_ctl { bool have_caching_bg; bool orig_have_caching_bg; + /* Allocation is called for tree-log */ + bool for_treelog; + /* RAID index, converted from flags */ int index; @@ -3764,6 +3728,118 @@ static int do_allocation_clustered(struct btrfs_block_group *block_group, return find_free_extent_unclustered(block_group, ffe_ctl); } +/* + * Tree-log block group locking + * ============================ + * + * fs_info::treelog_bg_lock protects the fs_info::treelog_bg which + * indicates the starting address of a block group, which is reserved only + * for tree-log metadata. + * + * Lock nesting + * ============ + * + * space_info::lock + * block_group::lock + * fs_info::treelog_bg_lock + */ + +/* + * Simple allocator for sequential-only block group. It only allows sequential + * allocation. No need to play with trees. This function also reserves the + * bytes as in btrfs_add_reserved_bytes. + */ +static int do_allocation_zoned(struct btrfs_block_group *block_group, + struct find_free_extent_ctl *ffe_ctl, + struct btrfs_block_group **bg_ret) +{ + struct btrfs_fs_info *fs_info = block_group->fs_info; + struct btrfs_space_info *space_info = block_group->space_info; + struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; + u64 start = block_group->start; + u64 num_bytes = ffe_ctl->num_bytes; + u64 avail; + u64 bytenr = block_group->start; + u64 log_bytenr; + int ret = 0; + bool skip; + + ASSERT(btrfs_is_zoned(block_group->fs_info)); + + /* + * Do not allow non-tree-log blocks in the dedicated tree-log block + * group, and vice versa. + */ + spin_lock(&fs_info->treelog_bg_lock); + log_bytenr = fs_info->treelog_bg; + skip = log_bytenr && ((ffe_ctl->for_treelog && bytenr != log_bytenr) || + (!ffe_ctl->for_treelog && bytenr == log_bytenr)); + spin_unlock(&fs_info->treelog_bg_lock); + if (skip) + return 1; + + spin_lock(&space_info->lock); + spin_lock(&block_group->lock); + spin_lock(&fs_info->treelog_bg_lock); + + ASSERT(!ffe_ctl->for_treelog || + block_group->start == fs_info->treelog_bg || + fs_info->treelog_bg == 0); + + if (block_group->ro) { + ret = 1; + goto out; + } + + /* + * Do not allow currently using block group to be tree-log dedicated + * block group. + */ + if (ffe_ctl->for_treelog && !fs_info->treelog_bg && + (block_group->used || block_group->reserved)) { + ret = 1; + goto out; + } + + avail = block_group->length - block_group->alloc_offset; + if (avail < num_bytes) { + if (ffe_ctl->max_extent_size < avail) { + /* + * With sequential allocator, free space is always + * contiguous + */ + ffe_ctl->max_extent_size = avail; + ffe_ctl->total_free_space = avail; + } + ret = 1; + goto out; + } + + if (ffe_ctl->for_treelog && !fs_info->treelog_bg) + fs_info->treelog_bg = block_group->start; + + ffe_ctl->found_offset = start + block_group->alloc_offset; + block_group->alloc_offset += num_bytes; + spin_lock(&ctl->tree_lock); + ctl->free_space -= num_bytes; + spin_unlock(&ctl->tree_lock); + + /* + * We do not check if found_offset is aligned to stripesize. The + * address is anyway rewritten when using zone append writing. + */ + + ffe_ctl->search_start = ffe_ctl->found_offset; + +out: + if (ret && ffe_ctl->for_treelog) + fs_info->treelog_bg = 0; + spin_unlock(&fs_info->treelog_bg_lock); + spin_unlock(&block_group->lock); + spin_unlock(&space_info->lock); + return ret; +} + static int do_allocation(struct btrfs_block_group *block_group, struct find_free_extent_ctl *ffe_ctl, struct btrfs_block_group **bg_ret) @@ -3771,6 +3847,8 @@ static int do_allocation(struct btrfs_block_group *block_group, switch (ffe_ctl->policy) { case BTRFS_EXTENT_ALLOC_CLUSTERED: return do_allocation_clustered(block_group, ffe_ctl, bg_ret); + case BTRFS_EXTENT_ALLOC_ZONED: + return do_allocation_zoned(block_group, ffe_ctl, bg_ret); default: BUG(); } @@ -3785,6 +3863,9 @@ static void release_block_group(struct btrfs_block_group *block_group, ffe_ctl->retry_clustered = false; ffe_ctl->retry_unclustered = false; break; + case BTRFS_EXTENT_ALLOC_ZONED: + /* Nothing to do */ + break; default: BUG(); } @@ -3813,6 +3894,9 @@ static void found_extent(struct find_free_extent_ctl *ffe_ctl, case BTRFS_EXTENT_ALLOC_CLUSTERED: found_extent_clustered(ffe_ctl, ins); break; + case BTRFS_EXTENT_ALLOC_ZONED: + /* Nothing to do */ + break; default: BUG(); } @@ -3828,6 +3912,9 @@ static int chunk_allocation_failed(struct find_free_extent_ctl *ffe_ctl) */ ffe_ctl->loop = LOOP_NO_EMPTY_SIZE; return 0; + case BTRFS_EXTENT_ALLOC_ZONED: + /* Give up here */ + return -ENOSPC; default: BUG(); } @@ -3996,6 +4083,14 @@ static int prepare_allocation(struct btrfs_fs_info *fs_info, case BTRFS_EXTENT_ALLOC_CLUSTERED: return prepare_allocation_clustered(fs_info, ffe_ctl, space_info, ins); + case BTRFS_EXTENT_ALLOC_ZONED: + if (ffe_ctl->for_treelog) { + spin_lock(&fs_info->treelog_bg_lock); + if (fs_info->treelog_bg) + ffe_ctl->hint_byte = fs_info->treelog_bg; + spin_unlock(&fs_info->treelog_bg_lock); + } + return 0; default: BUG(); } @@ -4038,6 +4133,7 @@ static noinline int find_free_extent(struct btrfs_root *root, struct find_free_extent_ctl ffe_ctl = {0}; struct btrfs_space_info *space_info; bool full_search = false; + bool for_treelog = (root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID); WARN_ON(num_bytes < fs_info->sectorsize); @@ -4051,6 +4147,7 @@ static noinline int find_free_extent(struct btrfs_root *root, ffe_ctl.orig_have_caching_bg = false; ffe_ctl.found_offset = 0; ffe_ctl.hint_byte = hint_byte_orig; + ffe_ctl.for_treelog = for_treelog; ffe_ctl.policy = BTRFS_EXTENT_ALLOC_CLUSTERED; /* For clustered allocation */ @@ -4059,6 +4156,9 @@ static noinline int find_free_extent(struct btrfs_root *root, ffe_ctl.last_ptr = NULL; ffe_ctl.use_cluster = true; + if (btrfs_is_zoned(fs_info)) + ffe_ctl.policy = BTRFS_EXTENT_ALLOC_ZONED; + ins->type = BTRFS_EXTENT_ITEM_KEY; ins->objectid = 0; ins->offset = 0; @@ -4122,8 +4222,11 @@ search: struct btrfs_block_group *bg_ret; /* If the block group is read-only, we can skip it entirely. */ - if (unlikely(block_group->ro)) + if (unlikely(block_group->ro)) { + if (for_treelog) + btrfs_clear_treelog_bg(block_group); continue; + } btrfs_grab_block_group(block_group, delalloc); ffe_ctl.search_start = block_group->start; @@ -4201,20 +4304,21 @@ have_block_group: /* move on to the next group */ if (ffe_ctl.search_start + num_bytes > block_group->start + block_group->length) { - btrfs_add_free_space(block_group, ffe_ctl.found_offset, - num_bytes); + btrfs_add_free_space_unused(block_group, + ffe_ctl.found_offset, num_bytes); goto loop; } if (ffe_ctl.found_offset < ffe_ctl.search_start) - btrfs_add_free_space(block_group, ffe_ctl.found_offset, - ffe_ctl.search_start - ffe_ctl.found_offset); + btrfs_add_free_space_unused(block_group, + ffe_ctl.found_offset, + ffe_ctl.search_start - ffe_ctl.found_offset); ret = btrfs_add_reserved_bytes(block_group, ram_bytes, num_bytes, delalloc); if (ret == -EAGAIN) { - btrfs_add_free_space(block_group, ffe_ctl.found_offset, - num_bytes); + btrfs_add_free_space_unused(block_group, + ffe_ctl.found_offset, num_bytes); goto loop; } btrfs_inc_block_group_reservations(block_group); @@ -4308,6 +4412,7 @@ int btrfs_reserve_extent(struct btrfs_root *root, u64 ram_bytes, bool final_tried = num_bytes == min_alloc_size; u64 flags; int ret; + bool for_treelog = (root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID); flags = get_alloc_profile_by_root(root, is_data); again: @@ -4331,8 +4436,8 @@ again: sinfo = btrfs_find_space_info(fs_info, flags); btrfs_err(fs_info, - "allocation failed flags %llu, wanted %llu", - flags, num_bytes); + "allocation failed flags %llu, wanted %llu tree-log %d", + flags, num_bytes, for_treelog); if (sinfo) btrfs_dump_space_info(fs_info, sinfo, num_bytes, 1); @@ -4514,7 +4619,6 @@ static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans, } if (node->type == BTRFS_SHARED_BLOCK_REF_KEY) { - BUG_ON(!(flags & BTRFS_BLOCK_FLAG_FULL_BACKREF)); btrfs_set_extent_inline_ref_type(leaf, iref, BTRFS_SHARED_BLOCK_REF_KEY); btrfs_set_extent_inline_ref_offset(leaf, iref, ref->parent); @@ -4551,7 +4655,6 @@ int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans, struct btrfs_key *ins) { struct btrfs_ref generic_ref = { 0 }; - int ret; BUG_ON(root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID); @@ -4559,9 +4662,8 @@ int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans, ins->objectid, ins->offset, 0); btrfs_init_data_ref(&generic_ref, root->root_key.objectid, owner, offset); btrfs_ref_tree_mod(root->fs_info, &generic_ref); - ret = btrfs_add_delayed_data_ref(trans, &generic_ref, - ram_bytes, NULL, NULL); - return ret; + + return btrfs_add_delayed_data_ref(trans, &generic_ref, ram_bytes); } /* @@ -4643,6 +4745,7 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root, __btrfs_tree_lock(buf, nest); btrfs_clean_tree_block(buf); clear_bit(EXTENT_BUFFER_STALE, &buf->bflags); + clear_bit(EXTENT_BUFFER_NO_CHECK, &buf->bflags); set_extent_buffer_uptodate(buf); @@ -4753,8 +4856,7 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans, generic_ref.real_root = root->root_key.objectid; btrfs_init_tree_ref(&generic_ref, level, root_objectid); btrfs_ref_tree_mod(fs_info, &generic_ref); - ret = btrfs_add_delayed_tree_ref(trans, &generic_ref, - extent_op, NULL, NULL); + ret = btrfs_add_delayed_tree_ref(trans, &generic_ref, extent_op); if (ret) goto out_free_delayed; } @@ -5547,7 +5649,15 @@ int btrfs_drop_snapshot(struct btrfs_root *root, int update_ref, int for_reloc) goto out_free; } - trans = btrfs_start_transaction(tree_root, 0); + /* + * Use join to avoid potential EINTR from transaction + * start. See wait_reserve_ticket and the whole + * reservation callchain. + */ + if (for_reloc) + trans = btrfs_join_transaction(tree_root); + else + trans = btrfs_start_transaction(tree_root, 0); if (IS_ERR(trans)) { err = PTR_ERR(trans); goto out_free; diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 6e3b72e63e42..4dfb3ead1175 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -24,6 +24,9 @@ #include "rcu-string.h" #include "backref.h" #include "disk-io.h" +#include "subpage.h" +#include "zoned.h" +#include "block-group.h" static struct kmem_cache *extent_state_cache; static struct kmem_cache *extent_buffer_cache; @@ -389,16 +392,16 @@ do_insert: } /** - * __etree_search - searche @tree for an entry that contains @offset. Such - * entry would have entry->start <= offset && entry->end >= offset. + * Search @tree for an entry that contains @offset. Such entry would have + * entry->start <= offset && entry->end >= offset. * - * @tree - the tree to search - * @offset - offset that should fall within an entry in @tree - * @next_ret - pointer to the first entry whose range ends after @offset - * @prev - pointer to the first entry whose range begins before @offset - * @p_ret - pointer where new node should be anchored (used when inserting an - * entry in the tree) - * @parent_ret - points to entry which would have been the parent of the entry, + * @tree: the tree to search + * @offset: offset that should fall within an entry in @tree + * @next_ret: pointer to the first entry whose range ends after @offset + * @prev_ret: pointer to the first entry whose range begins before @offset + * @p_ret: pointer where new node should be anchored (used when inserting an + * entry in the tree) + * @parent_ret: points to entry which would have been the parent of the entry, * containing @offset * * This function returns a pointer to the entry that contains @offset byte @@ -676,9 +679,7 @@ alloc_extent_state_atomic(struct extent_state *prealloc) static void extent_io_tree_panic(struct extent_io_tree *tree, int err) { - struct inode *inode = tree->private_data; - - btrfs_panic(btrfs_sb(inode->i_sb), err, + btrfs_panic(tree->fs_info, err, "locking error: extent tree was modified by another thread while locked"); } @@ -1590,12 +1591,13 @@ out: } /** - * find_contiguous_extent_bit: find a contiguous area of bits - * @tree - io tree to check - * @start - offset to start the search from - * @start_ret - the first offset we found with the bits set - * @end_ret - the final contiguous range of the bits that were set - * @bits - bits to look for + * Find a contiguous area of bits + * + * @tree: io tree to check + * @start: offset to start the search from + * @start_ret: the first offset we found with the bits set + * @end_ret: the final contiguous range of the bits that were set + * @bits: bits to look for * * set_extent_bit and clear_extent_bit can temporarily split contiguous ranges * to set bits appropriately, and then merge them again. During this time it @@ -1627,14 +1629,14 @@ int find_contiguous_extent_bit(struct extent_io_tree *tree, u64 start, } /** - * find_first_clear_extent_bit - find the first range that has @bits not set. - * This range could start before @start. + * Find the first range that has @bits not set. This range could start before + * @start. * - * @tree - the tree to search - * @start - the offset at/after which the found extent should start - * @start_ret - records the beginning of the range - * @end_ret - records the end of the range (inclusive) - * @bits - the set of bits which must be unset + * @tree: the tree to search + * @start: offset at/after which the found extent should start + * @start_ret: records the beginning of the range + * @end_ret: records the end of the range (inclusive) + * @bits: the set of bits which must be unset * * Since unallocated range is also considered one which doesn't have the bits * set it's possible that @end_ret contains -1, this happens in case the range @@ -1977,10 +1979,10 @@ static int __process_pages_contig(struct address_space *mapping, pages_processed++; continue; } - if (page_ops & PAGE_CLEAR_DIRTY) + if (page_ops & PAGE_START_WRITEBACK) { clear_page_dirty_for_io(pages[i]); - if (page_ops & PAGE_SET_WRITEBACK) set_page_writeback(pages[i]); + } if (page_ops & PAGE_SET_ERROR) SetPageError(pages[i]); if (page_ops & PAGE_END_WRITEBACK) @@ -2258,6 +2260,9 @@ int repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start, ASSERT(!(fs_info->sb->s_flags & SB_RDONLY)); BUG_ON(!mirror_num); + if (btrfs_is_zoned(fs_info)) + return btrfs_repair_one_zone(fs_info, logical); + bio = btrfs_io_bio_alloc(1); bio->bi_iter.bi_size = 0; map_length = length; @@ -2734,6 +2739,7 @@ static void end_bio_extent_writepage(struct bio *bio) u64 start; u64 end; struct bvec_iter_all iter_all; + bool first_bvec = true; ASSERT(!bio_flagged(bio, BIO_CLONED)); bio_for_each_segment_all(bvec, bio, iter_all) { @@ -2760,6 +2766,11 @@ static void end_bio_extent_writepage(struct bio *bio) start = page_offset(page); end = start + bvec->bv_offset + bvec->bv_len - 1; + if (first_bvec) { + btrfs_record_physical_zoned(inode, start, bio); + first_bvec = false; + } + end_extent_writepage(page, error, start, end); end_page_writeback(page); } @@ -2777,7 +2788,7 @@ struct processed_extent { struct btrfs_inode *inode; /* Start of the range in @inode */ u64 start; - /* End of the range in in @inode */ + /* End of the range in @inode */ u64 end; bool uptodate; }; @@ -2840,15 +2851,38 @@ update: processed->uptodate = uptodate; } -static void endio_readpage_update_page_status(struct page *page, bool uptodate) +static void begin_page_read(struct btrfs_fs_info *fs_info, struct page *page) { + ASSERT(PageLocked(page)); + if (fs_info->sectorsize == PAGE_SIZE) + return; + + ASSERT(PagePrivate(page)); + btrfs_subpage_start_reader(fs_info, page, page_offset(page), PAGE_SIZE); +} + +static void end_page_read(struct page *page, bool uptodate, u64 start, u32 len) +{ + struct btrfs_fs_info *fs_info = btrfs_sb(page->mapping->host->i_sb); + + ASSERT(page_offset(page) <= start && + start + len <= page_offset(page) + PAGE_SIZE); + if (uptodate) { - SetPageUptodate(page); + btrfs_page_set_uptodate(fs_info, page, start, len); } else { - ClearPageUptodate(page); - SetPageError(page); + btrfs_page_clear_uptodate(fs_info, page, start, len); + btrfs_page_set_error(fs_info, page, start, len); } - unlock_page(page); + + if (fs_info->sectorsize == PAGE_SIZE) + unlock_page(page); + else if (is_data_inode(page->mapping->host)) + /* + * For subpage data, unlock the page if we're the last reader. + * For subpage metadata, page lock is not utilized for read. + */ + btrfs_subpage_end_reader(fs_info, page, start, len); } /* @@ -2985,7 +3019,7 @@ readpage_ok: bio_offset += len; /* Update page status and unlock */ - endio_readpage_update_page_status(page, uptodate); + end_page_read(page, uptodate, start, len); endio_readpage_release_extent(&processed, BTRFS_I(inode), start, end, uptodate); } @@ -3060,14 +3094,67 @@ struct bio *btrfs_bio_clone_partial(struct bio *orig, int offset, int size) return bio; } +/** + * Attempt to add a page to bio + * + * @bio: destination bio + * @page: page to add to the bio + * @disk_bytenr: offset of the new bio or to check whether we are adding + * a contiguous page to the previous one + * @pg_offset: starting offset in the page + * @size: portion of page that we want to write + * @prev_bio_flags: flags of previous bio to see if we can merge the current one + * @bio_flags: flags of the current bio to see if we can merge them + * @return: true if page was added, false otherwise + * + * Attempt to add a page to bio considering stripe alignment etc. + * + * Return true if successfully page added. Otherwise, return false. + */ +static bool btrfs_bio_add_page(struct bio *bio, struct page *page, + u64 disk_bytenr, unsigned int size, + unsigned int pg_offset, + unsigned long prev_bio_flags, + unsigned long bio_flags) +{ + const sector_t sector = disk_bytenr >> SECTOR_SHIFT; + bool contig; + int ret; + + if (prev_bio_flags != bio_flags) + return false; + + if (prev_bio_flags & EXTENT_BIO_COMPRESSED) + contig = bio->bi_iter.bi_sector == sector; + else + contig = bio_end_sector(bio) == sector; + if (!contig) + return false; + + if (btrfs_bio_fits_in_stripe(page, size, bio, bio_flags)) + return false; + + if (bio_op(bio) == REQ_OP_ZONE_APPEND) { + struct page *first_page = bio_first_bvec_all(bio)->bv_page; + + if (!btrfs_bio_fits_in_ordered_extent(first_page, bio, size)) + return false; + ret = bio_add_zone_append_page(bio, page, size, pg_offset); + } else { + ret = bio_add_page(bio, page, size, pg_offset); + } + + return ret == size; +} + /* * @opf: bio REQ_OP_* and REQ_* flags as one value * @wbc: optional writeback control for io accounting * @page: page to add to the bio + * @disk_bytenr: logical bytenr where the write will be + * @size: portion of page that we want to write to * @pg_offset: offset of the new bio or to check whether we are adding * a contiguous page to the previous one - * @size: portion of page that we want to write - * @offset: starting offset in the page * @bio_ret: must be valid pointer, newly allocated bio will be stored there * @end_io_func: end_io callback for new bio * @mirror_num: desired mirror to read/write @@ -3076,7 +3163,7 @@ struct bio *btrfs_bio_clone_partial(struct bio *orig, int offset, int size) */ static int submit_extent_page(unsigned int opf, struct writeback_control *wbc, - struct page *page, u64 offset, + struct page *page, u64 disk_bytenr, size_t size, unsigned long pg_offset, struct bio **bio_ret, bio_end_io_t end_io_func, @@ -3088,27 +3175,17 @@ static int submit_extent_page(unsigned int opf, int ret = 0; struct bio *bio; size_t io_size = min_t(size_t, size, PAGE_SIZE); - sector_t sector = offset >> 9; - struct extent_io_tree *tree = &BTRFS_I(page->mapping->host)->io_tree; + struct btrfs_inode *inode = BTRFS_I(page->mapping->host); + struct extent_io_tree *tree = &inode->io_tree; + struct btrfs_fs_info *fs_info = inode->root->fs_info; ASSERT(bio_ret); if (*bio_ret) { - bool contig; - bool can_merge = true; - bio = *bio_ret; - if (prev_bio_flags & EXTENT_BIO_COMPRESSED) - contig = bio->bi_iter.bi_sector == sector; - else - contig = bio_end_sector(bio) == sector; - - if (btrfs_bio_fits_in_stripe(page, io_size, bio, bio_flags)) - can_merge = false; - - if (prev_bio_flags != bio_flags || !contig || !can_merge || - force_bio_submit || - bio_add_page(bio, page, io_size, pg_offset) < io_size) { + if (force_bio_submit || + !btrfs_bio_add_page(bio, page, disk_bytenr, io_size, + pg_offset, prev_bio_flags, bio_flags)) { ret = submit_one_bio(bio, mirror_num, prev_bio_flags); if (ret < 0) { *bio_ret = NULL; @@ -3122,7 +3199,7 @@ static int submit_extent_page(unsigned int opf, } } - bio = btrfs_bio_alloc(offset); + bio = btrfs_bio_alloc(disk_bytenr); bio_add_page(bio, page, io_size, pg_offset); bio->bi_end_io = end_io_func; bio->bi_private = tree; @@ -3131,20 +3208,39 @@ static int submit_extent_page(unsigned int opf, if (wbc) { struct block_device *bdev; - bdev = BTRFS_I(page->mapping->host)->root->fs_info->fs_devices->latest_bdev; + bdev = fs_info->fs_devices->latest_bdev; bio_set_dev(bio, bdev); wbc_init_bio(wbc, bio); wbc_account_cgroup_owner(wbc, page, io_size); } + if (btrfs_is_zoned(fs_info) && bio_op(bio) == REQ_OP_ZONE_APPEND) { + struct extent_map *em; + struct map_lookup *map; + + em = btrfs_get_chunk_map(fs_info, disk_bytenr, io_size); + if (IS_ERR(em)) + return PTR_ERR(em); + + map = em->map_lookup; + /* We only support single profile for now */ + ASSERT(map->num_stripes == 1); + btrfs_io_bio(bio)->device = map->stripes[0].dev; + + free_extent_map(em); + } *bio_ret = bio; return ret; } -static void attach_extent_buffer_page(struct extent_buffer *eb, - struct page *page) +static int attach_extent_buffer_page(struct extent_buffer *eb, + struct page *page, + struct btrfs_subpage *prealloc) { + struct btrfs_fs_info *fs_info = eb->fs_info; + int ret = 0; + /* * If the page is mapped to btree inode, we should hold the private * lock to prevent race. @@ -3154,16 +3250,62 @@ static void attach_extent_buffer_page(struct extent_buffer *eb, if (page->mapping) lockdep_assert_held(&page->mapping->private_lock); - if (!PagePrivate(page)) - attach_page_private(page, eb); + if (fs_info->sectorsize == PAGE_SIZE) { + if (!PagePrivate(page)) + attach_page_private(page, eb); + else + WARN_ON(page->private != (unsigned long)eb); + return 0; + } + + /* Already mapped, just free prealloc */ + if (PagePrivate(page)) { + btrfs_free_subpage(prealloc); + return 0; + } + + if (prealloc) + /* Has preallocated memory for subpage */ + attach_page_private(page, prealloc); else - WARN_ON(page->private != (unsigned long)eb); + /* Do new allocation to attach subpage */ + ret = btrfs_attach_subpage(fs_info, page, + BTRFS_SUBPAGE_METADATA); + return ret; +} + +int set_page_extent_mapped(struct page *page) +{ + struct btrfs_fs_info *fs_info; + + ASSERT(page->mapping); + + if (PagePrivate(page)) + return 0; + + fs_info = btrfs_sb(page->mapping->host->i_sb); + + if (fs_info->sectorsize < PAGE_SIZE) + return btrfs_attach_subpage(fs_info, page, BTRFS_SUBPAGE_DATA); + + attach_page_private(page, (void *)EXTENT_PAGE_PRIVATE); + return 0; } -void set_page_extent_mapped(struct page *page) +void clear_page_extent_mapped(struct page *page) { + struct btrfs_fs_info *fs_info; + + ASSERT(page->mapping); + if (!PagePrivate(page)) - attach_page_private(page, (void *)EXTENT_PAGE_PRIVATE); + return; + + fs_info = btrfs_sb(page->mapping->host->i_sb); + if (fs_info->sectorsize < PAGE_SIZE) + return btrfs_detach_subpage(fs_info, page); + + detach_page_private(page); } static struct extent_map * @@ -3204,6 +3346,7 @@ int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, unsigned int read_flags, u64 *prev_em_start) { struct inode *inode = page->mapping->host; + struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); u64 start = page_offset(page); const u64 end = start + PAGE_SIZE - 1; u64 cur = start; @@ -3220,12 +3363,19 @@ int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, unsigned long this_bio_flag = 0; struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree; - set_page_extent_mapped(page); + ret = set_page_extent_mapped(page); + if (ret < 0) { + unlock_extent(tree, start, end); + btrfs_page_set_error(fs_info, page, start, PAGE_SIZE); + unlock_page(page); + goto out; + } if (!PageUptodate(page)) { if (cleancache_get_page(page) == 0) { BUG_ON(blocksize != PAGE_SIZE); unlock_extent(tree, start, end); + unlock_page(page); goto out; } } @@ -3242,9 +3392,10 @@ int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, kunmap_atomic(userpage); } } + begin_page_read(fs_info, page); while (cur <= end) { bool force_bio_submit = false; - u64 offset; + u64 disk_bytenr; if (cur >= last_byte) { char *userpage; @@ -3259,13 +3410,14 @@ int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, &cached, GFP_NOFS); unlock_extent_cached(tree, cur, cur + iosize - 1, &cached); + end_page_read(page, true, cur, iosize); break; } em = __get_extent_map(inode, page, pg_offset, cur, end - cur + 1, em_cached); if (IS_ERR_OR_NULL(em)) { - SetPageError(page); unlock_extent(tree, cur, end); + end_page_read(page, false, cur, end + 1 - cur); break; } extent_offset = cur - em->start; @@ -3282,9 +3434,9 @@ int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, cur_end = min(extent_map_end(em) - 1, end); iosize = ALIGN(iosize, blocksize); if (this_bio_flag & EXTENT_BIO_COMPRESSED) - offset = em->block_start; + disk_bytenr = em->block_start; else - offset = em->block_start + extent_offset; + disk_bytenr = em->block_start + extent_offset; block_start = em->block_start; if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) block_start = EXTENT_MAP_HOLE; @@ -3348,6 +3500,7 @@ int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, &cached, GFP_NOFS); unlock_extent_cached(tree, cur, cur + iosize - 1, &cached); + end_page_read(page, true, cur, iosize); cur = cur + iosize; pg_offset += iosize; continue; @@ -3357,6 +3510,7 @@ int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, EXTENT_UPTODATE, 1, NULL)) { check_page_uptodate(tree, page); unlock_extent(tree, cur, cur + iosize - 1); + end_page_read(page, true, cur, iosize); cur = cur + iosize; pg_offset += iosize; continue; @@ -3365,15 +3519,15 @@ int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, * to date. Error out */ if (block_start == EXTENT_MAP_INLINE) { - SetPageError(page); unlock_extent(tree, cur, cur + iosize - 1); + end_page_read(page, false, cur, iosize); cur = cur + iosize; pg_offset += iosize; continue; } ret = submit_extent_page(REQ_OP_READ | read_flags, NULL, - page, offset, iosize, + page, disk_bytenr, iosize, pg_offset, bio, end_bio_extent_readpage, 0, *bio_flags, @@ -3383,19 +3537,14 @@ int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, nr++; *bio_flags = this_bio_flag; } else { - SetPageError(page); unlock_extent(tree, cur, cur + iosize - 1); + end_page_read(page, false, cur, iosize); goto out; } cur = cur + iosize; pg_offset += iosize; } out: - if (!nr) { - if (!PageError(page)) - SetPageUptodate(page); - unlock_page(page); - } return ret; } @@ -3515,23 +3664,21 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode, unsigned long nr_written, int *nr_ret) { + struct btrfs_fs_info *fs_info = inode->root->fs_info; struct extent_io_tree *tree = &inode->io_tree; u64 start = page_offset(page); - u64 page_end = start + PAGE_SIZE - 1; - u64 end; + u64 end = start + PAGE_SIZE - 1; u64 cur = start; u64 extent_offset; u64 block_start; - u64 iosize; struct extent_map *em; - size_t pg_offset = 0; - size_t blocksize; int ret = 0; int nr = 0; + u32 opf = REQ_OP_WRITE; const unsigned int write_flags = wbc_to_write_flags(wbc); bool compressed; - ret = btrfs_writepage_cow_fixup(page, start, page_end); + ret = btrfs_writepage_cow_fixup(page, start, end); if (ret) { /* Fixup worker will requeue */ redirty_page_for_writepage(wbc, page); @@ -3546,16 +3693,13 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode, */ update_nr_written(wbc, nr_written + 1); - end = page_end; - blocksize = inode->vfs_inode.i_sb->s_blocksize; - while (cur <= end) { + u64 disk_bytenr; u64 em_end; - u64 offset; + u32 iosize; if (cur >= i_size) { - btrfs_writepage_endio_finish_ordered(page, cur, - page_end, 1); + btrfs_writepage_endio_finish_ordered(page, cur, end, 1); break; } em = btrfs_get_extent(inode, NULL, 0, cur, end - cur + 1); @@ -3567,13 +3711,20 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode, extent_offset = cur - em->start; em_end = extent_map_end(em); - BUG_ON(em_end <= cur); - BUG_ON(end < cur); - iosize = min(em_end - cur, end - cur + 1); - iosize = ALIGN(iosize, blocksize); - offset = em->block_start + extent_offset; + ASSERT(cur <= em_end); + ASSERT(cur < end); + ASSERT(IS_ALIGNED(em->start, fs_info->sectorsize)); + ASSERT(IS_ALIGNED(em->len, fs_info->sectorsize)); block_start = em->block_start; compressed = test_bit(EXTENT_FLAG_COMPRESSED, &em->flags); + disk_bytenr = em->block_start + extent_offset; + + /* Note that em_end from extent_map_end() is exclusive */ + iosize = min(em_end, end + 1) - cur; + + if (btrfs_use_zone_append(inode, em)) + opf = REQ_OP_ZONE_APPEND; + free_extent_map(em); em = NULL; @@ -3589,7 +3740,6 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode, btrfs_writepage_endio_finish_ordered(page, cur, cur + iosize - 1, 1); cur += iosize; - pg_offset += iosize; continue; } @@ -3600,9 +3750,9 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode, page->index, cur, end); } - ret = submit_extent_page(REQ_OP_WRITE | write_flags, wbc, - page, offset, iosize, pg_offset, - &epd->bio, + ret = submit_extent_page(opf | write_flags, wbc, page, + disk_bytenr, iosize, + cur - page_offset(page), &epd->bio, end_bio_extent_writepage, 0, 0, 0, false); if (ret) { @@ -3611,8 +3761,7 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode, end_page_writeback(page); } - cur = cur + iosize; - pg_offset += iosize; + cur += iosize; nr++; } *nr_ret = nr; @@ -3665,7 +3814,11 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc, flush_dcache_page(page); } - set_page_extent_mapped(page); + ret = set_page_extent_mapped(page); + if (ret < 0) { + SetPageError(page); + goto done; + } if (!epd->extent_locked) { ret = writepage_delalloc(BTRFS_I(inode), page, wbc, start, @@ -3925,7 +4078,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb, struct writeback_control *wbc, struct extent_page_data *epd) { - u64 offset = eb->start; + u64 disk_bytenr = eb->start; u32 nritems; int i, num_pages; unsigned long start, end; @@ -3958,7 +4111,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb, clear_page_dirty_for_io(p); set_page_writeback(p); ret = submit_extent_page(REQ_OP_WRITE | write_flags, wbc, - p, offset, PAGE_SIZE, 0, + p, disk_bytenr, PAGE_SIZE, 0, &epd->bio, end_bio_extent_buffer_writepage, 0, 0, 0, false); @@ -3971,7 +4124,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb, ret = -EIO; break; } - offset += PAGE_SIZE; + disk_bytenr += PAGE_SIZE; update_nr_written(wbc, 1); unlock_page(p); } @@ -4012,6 +4165,7 @@ static int submit_eb_page(struct page *page, struct writeback_control *wbc, struct extent_buffer **eb_context) { struct address_space *mapping = page->mapping; + struct btrfs_block_group *cache = NULL; struct extent_buffer *eb; int ret; @@ -4044,13 +4198,31 @@ static int submit_eb_page(struct page *page, struct writeback_control *wbc, if (!ret) return 0; + if (!btrfs_check_meta_write_pointer(eb->fs_info, eb, &cache)) { + /* + * If for_sync, this hole will be filled with + * trasnsaction commit. + */ + if (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync) + ret = -EAGAIN; + else + ret = 0; + free_extent_buffer(eb); + return ret; + } + *eb_context = eb; ret = lock_extent_buffer_for_io(eb, epd); if (ret <= 0) { + btrfs_revert_meta_write_pointer(cache, eb); + if (cache) + btrfs_put_block_group(cache); free_extent_buffer(eb); return ret; } + if (cache) + btrfs_put_block_group(cache); ret = write_one_eb(eb, wbc, epd); free_extent_buffer(eb); if (ret < 0) @@ -4096,6 +4268,7 @@ int btree_write_cache_pages(struct address_space *mapping, tag = PAGECACHE_TAG_TOWRITE; else tag = PAGECACHE_TAG_DIRTY; + btrfs_zoned_meta_io_lock(fs_info); retry: if (wbc->sync_mode == WB_SYNC_ALL) tag_pages_for_writeback(mapping, index, end); @@ -4136,7 +4309,7 @@ retry: } if (ret < 0) { end_write_bio(&epd, ret); - return ret; + goto out; } /* * If something went wrong, don't allow any metadata write bio to be @@ -4171,14 +4344,17 @@ retry: ret = -EROFS; end_write_bio(&epd, ret); } +out: + btrfs_zoned_meta_io_unlock(fs_info); return ret; } /** - * write_cache_pages - walk the list of dirty pages of the given address space and write all of them. + * Walk the list of dirty pages of the given address space and write all of them. + * * @mapping: address space structure to write - * @wbc: subtract the number of written pages from *@wbc->nr_to_write - * @data: data passed to __extent_writepage function + * @wbc: subtract the number of written pages from *@wbc->nr_to_write + * @epd: holds context for the write, namely the bio * * If a page is already under I/O, write_cache_pages() skips it, even * if it's dirty. This is desirable behaviour for memory-cleaning writeback, @@ -4977,25 +5153,39 @@ int extent_buffer_under_io(const struct extent_buffer *eb) test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)); } -/* - * Release all pages attached to the extent buffer. - */ -static void btrfs_release_extent_buffer_pages(struct extent_buffer *eb) +static bool page_range_has_eb(struct btrfs_fs_info *fs_info, struct page *page) { - int i; - int num_pages; - int mapped = !test_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags); + struct btrfs_subpage *subpage; - BUG_ON(extent_buffer_under_io(eb)); + lockdep_assert_held(&page->mapping->private_lock); - num_pages = num_extent_pages(eb); - for (i = 0; i < num_pages; i++) { - struct page *page = eb->pages[i]; + if (PagePrivate(page)) { + subpage = (struct btrfs_subpage *)page->private; + if (atomic_read(&subpage->eb_refs)) + return true; + } + return false; +} - if (!page) - continue; +static void detach_extent_buffer_page(struct extent_buffer *eb, struct page *page) +{ + struct btrfs_fs_info *fs_info = eb->fs_info; + const bool mapped = !test_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags); + + /* + * For mapped eb, we're going to change the page private, which should + * be done under the private_lock. + */ + if (mapped) + spin_lock(&page->mapping->private_lock); + + if (!PagePrivate(page)) { if (mapped) - spin_lock(&page->mapping->private_lock); + spin_unlock(&page->mapping->private_lock); + return; + } + + if (fs_info->sectorsize == PAGE_SIZE) { /* * We do this since we'll remove the pages after we've * removed the eb from the radix tree, so we could race @@ -5014,9 +5204,49 @@ static void btrfs_release_extent_buffer_pages(struct extent_buffer *eb) */ detach_page_private(page); } - if (mapped) spin_unlock(&page->mapping->private_lock); + return; + } + + /* + * For subpage, we can have dummy eb with page private. In this case, + * we can directly detach the private as such page is only attached to + * one dummy eb, no sharing. + */ + if (!mapped) { + btrfs_detach_subpage(fs_info, page); + return; + } + + btrfs_page_dec_eb_refs(fs_info, page); + + /* + * We can only detach the page private if there are no other ebs in the + * page range. + */ + if (!page_range_has_eb(fs_info, page)) + btrfs_detach_subpage(fs_info, page); + + spin_unlock(&page->mapping->private_lock); +} + +/* Release all pages attached to the extent buffer */ +static void btrfs_release_extent_buffer_pages(struct extent_buffer *eb) +{ + int i; + int num_pages; + + ASSERT(!extent_buffer_under_io(eb)); + + num_pages = num_extent_pages(eb); + for (i = 0; i < num_pages; i++) { + struct page *page = eb->pages[i]; + + if (!page) + continue; + + detach_extent_buffer_page(eb, page); /* One for when we allocated the page */ put_page(page); @@ -5048,6 +5278,7 @@ __alloc_extent_buffer(struct btrfs_fs_info *fs_info, u64 start, btrfs_leak_debug_add(&fs_info->eb_leak_lock, &eb->leak_list, &fs_info->allocated_ebs); + INIT_LIST_HEAD(&eb->release_list); spin_lock_init(&eb->refs_lock); atomic_set(&eb->refs, 1); @@ -5069,21 +5300,32 @@ struct extent_buffer *btrfs_clone_extent_buffer(const struct extent_buffer *src) if (new == NULL) return NULL; + /* + * Set UNMAPPED before calling btrfs_release_extent_buffer(), as + * btrfs_release_extent_buffer() have different behavior for + * UNMAPPED subpage extent buffer. + */ + set_bit(EXTENT_BUFFER_UNMAPPED, &new->bflags); + for (i = 0; i < num_pages; i++) { + int ret; + p = alloc_page(GFP_NOFS); if (!p) { btrfs_release_extent_buffer(new); return NULL; } - attach_extent_buffer_page(new, p); + ret = attach_extent_buffer_page(new, p, NULL); + if (ret < 0) { + put_page(p); + btrfs_release_extent_buffer(new); + return NULL; + } WARN_ON(PageDirty(p)); - SetPageUptodate(p); new->pages[i] = p; copy_page(page_address(p), page_address(src->pages[i])); } - - set_bit(EXTENT_BUFFER_UPTODATE, &new->bflags); - set_bit(EXTENT_BUFFER_UNMAPPED, &new->bflags); + set_extent_buffer_uptodate(new); return new; } @@ -5101,9 +5343,14 @@ struct extent_buffer *__alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info, num_pages = num_extent_pages(eb); for (i = 0; i < num_pages; i++) { + int ret; + eb->pages[i] = alloc_page(GFP_NOFS); if (!eb->pages[i]) goto err; + ret = attach_extent_buffer_page(eb, eb->pages[i], NULL); + if (ret < 0) + goto err; } set_extent_buffer_uptodate(eb); btrfs_set_header_nritems(eb, 0); @@ -5111,8 +5358,10 @@ struct extent_buffer *__alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info, return eb; err: - for (; i > 0; i--) + for (; i > 0; i--) { + detach_extent_buffer_page(eb, eb->pages[i - 1]); __free_page(eb->pages[i - 1]); + } __free_extent_buffer(eb); return NULL; } @@ -5254,6 +5503,38 @@ free_eb: } #endif +static struct extent_buffer *grab_extent_buffer( + struct btrfs_fs_info *fs_info, struct page *page) +{ + struct extent_buffer *exists; + + /* + * For subpage case, we completely rely on radix tree to ensure we + * don't try to insert two ebs for the same bytenr. So here we always + * return NULL and just continue. + */ + if (fs_info->sectorsize < PAGE_SIZE) + return NULL; + + /* Page not yet attached to an extent buffer */ + if (!PagePrivate(page)) + return NULL; + + /* + * We could have already allocated an eb for this page and attached one + * so lets see if we can get a ref on the existing eb, and if we can we + * know it's good and we can just return that one, else we know we can + * just overwrite page->private. + */ + exists = (struct extent_buffer *)page->private; + if (atomic_inc_not_zero(&exists->refs)) + return exists; + + WARN_ON(PageDirty(page)); + detach_page_private(page); + return NULL; +} + struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, u64 start, u64 owner_root, int level) { @@ -5292,36 +5573,58 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, num_pages = num_extent_pages(eb); for (i = 0; i < num_pages; i++, index++) { + struct btrfs_subpage *prealloc = NULL; + p = find_or_create_page(mapping, index, GFP_NOFS|__GFP_NOFAIL); if (!p) { exists = ERR_PTR(-ENOMEM); goto free_eb; } - spin_lock(&mapping->private_lock); - if (PagePrivate(p)) { - /* - * We could have already allocated an eb for this page - * and attached one so lets see if we can get a ref on - * the existing eb, and if we can we know it's good and - * we can just return that one, else we know we can just - * overwrite page->private. - */ - exists = (struct extent_buffer *)p->private; - if (atomic_inc_not_zero(&exists->refs)) { - spin_unlock(&mapping->private_lock); - unlock_page(p); - put_page(p); - mark_extent_buffer_accessed(exists, p); - goto free_eb; - } - exists = NULL; + /* + * Preallocate page->private for subpage case, so that we won't + * allocate memory with private_lock hold. The memory will be + * freed by attach_extent_buffer_page() or freed manually if + * we exit earlier. + * + * Although we have ensured one subpage eb can only have one + * page, but it may change in the future for 16K page size + * support, so we still preallocate the memory in the loop. + */ + ret = btrfs_alloc_subpage(fs_info, &prealloc, + BTRFS_SUBPAGE_METADATA); + if (ret < 0) { + unlock_page(p); + put_page(p); + exists = ERR_PTR(ret); + goto free_eb; + } - WARN_ON(PageDirty(p)); - detach_page_private(p); + spin_lock(&mapping->private_lock); + exists = grab_extent_buffer(fs_info, p); + if (exists) { + spin_unlock(&mapping->private_lock); + unlock_page(p); + put_page(p); + mark_extent_buffer_accessed(exists, p); + btrfs_free_subpage(prealloc); + goto free_eb; } - attach_extent_buffer_page(eb, p); + /* Should not fail, as we have preallocated the memory */ + ret = attach_extent_buffer_page(eb, p, prealloc); + ASSERT(!ret); + /* + * To inform we have extra eb under allocation, so that + * detach_extent_buffer_page() won't release the page private + * when the eb hasn't yet been inserted into radix tree. + * + * The ref will be decreased when the eb released the page, in + * detach_extent_buffer_page(). + * Thus needs no special handling in error path. + */ + btrfs_page_inc_eb_refs(fs_info, p); spin_unlock(&mapping->private_lock); + WARN_ON(PageDirty(p)); eb->pages[i] = p; if (!PageUptodate(p)) @@ -5527,33 +5830,103 @@ bool set_extent_buffer_dirty(struct extent_buffer *eb) void clear_extent_buffer_uptodate(struct extent_buffer *eb) { - int i; + struct btrfs_fs_info *fs_info = eb->fs_info; struct page *page; int num_pages; + int i; clear_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags); num_pages = num_extent_pages(eb); for (i = 0; i < num_pages; i++) { page = eb->pages[i]; if (page) - ClearPageUptodate(page); + btrfs_page_clear_uptodate(fs_info, page, + eb->start, eb->len); } } void set_extent_buffer_uptodate(struct extent_buffer *eb) { - int i; + struct btrfs_fs_info *fs_info = eb->fs_info; struct page *page; int num_pages; + int i; set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags); num_pages = num_extent_pages(eb); for (i = 0; i < num_pages; i++) { page = eb->pages[i]; - SetPageUptodate(page); + btrfs_page_set_uptodate(fs_info, page, eb->start, eb->len); } } +static int read_extent_buffer_subpage(struct extent_buffer *eb, int wait, + int mirror_num) +{ + struct btrfs_fs_info *fs_info = eb->fs_info; + struct extent_io_tree *io_tree; + struct page *page = eb->pages[0]; + struct bio *bio = NULL; + int ret = 0; + + ASSERT(!test_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags)); + ASSERT(PagePrivate(page)); + io_tree = &BTRFS_I(fs_info->btree_inode)->io_tree; + + if (wait == WAIT_NONE) { + ret = try_lock_extent(io_tree, eb->start, + eb->start + eb->len - 1); + if (ret <= 0) + return ret; + } else { + ret = lock_extent(io_tree, eb->start, eb->start + eb->len - 1); + if (ret < 0) + return ret; + } + + ret = 0; + if (test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags) || + PageUptodate(page) || + btrfs_subpage_test_uptodate(fs_info, page, eb->start, eb->len)) { + set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags); + unlock_extent(io_tree, eb->start, eb->start + eb->len - 1); + return ret; + } + + clear_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags); + eb->read_mirror = 0; + atomic_set(&eb->io_pages, 1); + check_buffer_tree_ref(eb); + btrfs_subpage_clear_error(fs_info, page, eb->start, eb->len); + + ret = submit_extent_page(REQ_OP_READ | REQ_META, NULL, page, eb->start, + eb->len, eb->start - page_offset(page), &bio, + end_bio_extent_readpage, mirror_num, 0, 0, + true); + if (ret) { + /* + * In the endio function, if we hit something wrong we will + * increase the io_pages, so here we need to decrease it for + * error path. + */ + atomic_dec(&eb->io_pages); + } + if (bio) { + int tmp; + + tmp = submit_one_bio(bio, mirror_num, 0); + if (tmp < 0) + return tmp; + } + if (ret || wait != WAIT_COMPLETE) + return ret; + + wait_extent_bit(io_tree, eb->start, eb->start + eb->len - 1, EXTENT_LOCKED); + if (!test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags)) + ret = -EIO; + return ret; +} + int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num) { int i; @@ -5570,10 +5943,20 @@ int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num) if (test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags)) return 0; + if (eb->fs_info->sectorsize < PAGE_SIZE) + return read_extent_buffer_subpage(eb, wait, mirror_num); + num_pages = num_extent_pages(eb); for (i = 0; i < num_pages; i++) { page = eb->pages[i]; if (wait == WAIT_NONE) { + /* + * WAIT_NONE is only utilized by readahead. If we can't + * acquire the lock atomically it means either the eb + * is being read out or under modification. + * Either way the eb will be or has been cached, + * readahead can exit safely. + */ if (!trylock_page(page)) goto unlock_exit; } else { @@ -5825,6 +6208,8 @@ void write_extent_buffer(const struct extent_buffer *eb, const void *srcv, char *src = (char *)srcv; unsigned long i = get_eb_page_index(start); + WARN_ON(test_bit(EXTENT_BUFFER_NO_CHECK, &eb->bflags)); + if (check_eb_range(eb, start, len)) return; @@ -6171,13 +6556,115 @@ void memmove_extent_buffer(const struct extent_buffer *dst, } } +static struct extent_buffer *get_next_extent_buffer( + struct btrfs_fs_info *fs_info, struct page *page, u64 bytenr) +{ + struct extent_buffer *gang[BTRFS_SUBPAGE_BITMAP_SIZE]; + struct extent_buffer *found = NULL; + u64 page_start = page_offset(page); + int ret; + int i; + + ASSERT(in_range(bytenr, page_start, PAGE_SIZE)); + ASSERT(PAGE_SIZE / fs_info->nodesize <= BTRFS_SUBPAGE_BITMAP_SIZE); + lockdep_assert_held(&fs_info->buffer_lock); + + ret = radix_tree_gang_lookup(&fs_info->buffer_radix, (void **)gang, + bytenr >> fs_info->sectorsize_bits, + PAGE_SIZE / fs_info->nodesize); + for (i = 0; i < ret; i++) { + /* Already beyond page end */ + if (gang[i]->start >= page_start + PAGE_SIZE) + break; + /* Found one */ + if (gang[i]->start >= bytenr) { + found = gang[i]; + break; + } + } + return found; +} + +static int try_release_subpage_extent_buffer(struct page *page) +{ + struct btrfs_fs_info *fs_info = btrfs_sb(page->mapping->host->i_sb); + u64 cur = page_offset(page); + const u64 end = page_offset(page) + PAGE_SIZE; + int ret; + + while (cur < end) { + struct extent_buffer *eb = NULL; + + /* + * Unlike try_release_extent_buffer() which uses page->private + * to grab buffer, for subpage case we rely on radix tree, thus + * we need to ensure radix tree consistency. + * + * We also want an atomic snapshot of the radix tree, thus go + * with spinlock rather than RCU. + */ + spin_lock(&fs_info->buffer_lock); + eb = get_next_extent_buffer(fs_info, page, cur); + if (!eb) { + /* No more eb in the page range after or at cur */ + spin_unlock(&fs_info->buffer_lock); + break; + } + cur = eb->start + eb->len; + + /* + * The same as try_release_extent_buffer(), to ensure the eb + * won't disappear out from under us. + */ + spin_lock(&eb->refs_lock); + if (atomic_read(&eb->refs) != 1 || extent_buffer_under_io(eb)) { + spin_unlock(&eb->refs_lock); + spin_unlock(&fs_info->buffer_lock); + break; + } + spin_unlock(&fs_info->buffer_lock); + + /* + * If tree ref isn't set then we know the ref on this eb is a + * real ref, so just return, this eb will likely be freed soon + * anyway. + */ + if (!test_and_clear_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags)) { + spin_unlock(&eb->refs_lock); + break; + } + + /* + * Here we don't care about the return value, we will always + * check the page private at the end. And + * release_extent_buffer() will release the refs_lock. + */ + release_extent_buffer(eb); + } + /* + * Finally to check if we have cleared page private, as if we have + * released all ebs in the page, the page private should be cleared now. + */ + spin_lock(&page->mapping->private_lock); + if (!PagePrivate(page)) + ret = 1; + else + ret = 0; + spin_unlock(&page->mapping->private_lock); + return ret; + +} + int try_release_extent_buffer(struct page *page) { struct extent_buffer *eb; + if (btrfs_sb(page->mapping->host->i_sb)->sectorsize < PAGE_SIZE) + return try_release_subpage_extent_buffer(page); + /* - * We need to make sure nobody is attaching this page to an eb right - * now. + * We need to make sure nobody is changing page->private, as we rely on + * page->private as the pointer to extent buffer. */ spin_lock(&page->mapping->private_lock); if (!PagePrivate(page)) { diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 19221095c635..824640cb0ace 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -31,16 +31,17 @@ enum { EXTENT_BUFFER_IN_TREE, /* write IO error */ EXTENT_BUFFER_WRITE_ERR, + EXTENT_BUFFER_NO_CHECK, }; /* these are flags for __process_pages_contig */ #define PAGE_UNLOCK (1 << 0) -#define PAGE_CLEAR_DIRTY (1 << 1) -#define PAGE_SET_WRITEBACK (1 << 2) -#define PAGE_END_WRITEBACK (1 << 3) -#define PAGE_SET_PRIVATE2 (1 << 4) -#define PAGE_SET_ERROR (1 << 5) -#define PAGE_LOCK (1 << 6) +/* Page starts writeback, clear dirty bit and set writeback bit */ +#define PAGE_START_WRITEBACK (1 << 1) +#define PAGE_END_WRITEBACK (1 << 2) +#define PAGE_SET_PRIVATE2 (1 << 3) +#define PAGE_SET_ERROR (1 << 4) +#define PAGE_LOCK (1 << 5) /* * page->private values. Every page that is controlled by the extent @@ -93,6 +94,7 @@ struct extent_buffer { struct rw_semaphore lock; struct page *pages[INLINE_EXTENT_BUFFER_PAGES]; + struct list_head release_list; #ifdef CONFIG_BTRFS_DEBUG struct list_head leak_list; #endif @@ -178,7 +180,8 @@ int btree_write_cache_pages(struct address_space *mapping, void extent_readahead(struct readahead_control *rac); int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len); -void set_page_extent_mapped(struct page *page); +int set_page_extent_mapped(struct page *page); +void clear_page_extent_mapped(struct page *page); struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, u64 start, u64 owner_root, int level); diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c index bd6229fb2b6f..4a8e02f7b6c7 100644 --- a/fs/btrfs/extent_map.c +++ b/fs/btrfs/extent_map.c @@ -385,9 +385,12 @@ static void extent_map_device_clear_bits(struct extent_map *em, unsigned bits) } /** - * add_extent_mapping - add new extent map to the extent tree + * Add new extent map to the extent tree + * * @tree: tree to insert new map in * @em: map to insert + * @modified: indicate whether the given @em should be added to the + * modified list, which indicates the extent needs to be logged * * Insert @em into @tree or perform a simple forward/backward merge with * existing mappings. The extent_map struct passed in will be inserted @@ -574,12 +577,13 @@ static noinline int merge_extent_mapping(struct extent_map_tree *em_tree, } /** - * btrfs_add_extent_mapping - add extent mapping into em_tree - * @fs_info - used for tracepoint - * @em_tree - the extent tree into which we want to insert the extent mapping - * @em_in - extent we are inserting - * @start - start of the logical range btrfs_get_extent() is requesting - * @len - length of the logical range btrfs_get_extent() is requesting + * Add extent mapping into em_tree + * + * @fs_info: the filesystem + * @em_tree: extent tree into which we want to insert the extent mapping + * @em_in: extent we are inserting + * @start: start of the logical range btrfs_get_extent() is requesting + * @len: length of the logical range btrfs_get_extent() is requesting * * Note that @em_in's range may be different from [start, start+len), * but they must be overlapped. diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index 1545c22ef280..47cd3a6dc635 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -24,8 +24,10 @@ PAGE_SIZE)) /** - * @inode - the inode we want to update the disk_i_size for - * @new_i_size - the i_size we want to set to, 0 if we use i_size + * Set inode's size according to filesystem options + * + * @inode: inode we want to update the disk_i_size for + * @new_i_size: i_size we want to set to, 0 if we use i_size * * With NO_HOLES set this simply sets the disk_is_size to whatever i_size_read() * returns as it is perfectly fine with a file that has holes without hole file @@ -62,9 +64,11 @@ void btrfs_inode_safe_disk_i_size_write(struct btrfs_inode *inode, u64 new_i_siz } /** - * @inode - the inode we're modifying - * @start - the start file offset of the file extent we've inserted - * @len - the logical length of the file extent item + * Mark range within a file as having a new extent inserted + * + * @inode: inode being modified + * @start: start file offset of the file extent we've inserted + * @len: logical length of the file extent item * * Call when we are inserting a new file extent where there was none before. * Does not need to call this in the case where we're replacing an existing file @@ -88,9 +92,11 @@ int btrfs_inode_set_file_extent_range(struct btrfs_inode *inode, u64 start, } /** - * @inode - the inode we're modifying - * @start - the start file offset of the file extent we've inserted - * @len - the logical length of the file extent item + * Marks an inode range as not having a backing extent + * + * @inode: inode being modified + * @start: start file offset of the file extent we've inserted + * @len: logical length of the file extent item * * Called when we drop a file extent, for example when we truncate. Doesn't * need to be called for cases where we're replacing a file extent, like when @@ -1016,8 +1022,10 @@ again: } btrfs_release_path(path); + path->search_for_extension = 1; ret = btrfs_search_slot(trans, root, &file_key, path, csum_size, 1); + path->search_for_extension = 0; if (ret < 0) goto out; diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 0e41459b8de6..be9e3900cce8 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -453,12 +453,11 @@ static void btrfs_drop_pages(struct page **pages, size_t num_pages) } /* - * after copy_from_user, pages need to be dirtied and we need to make - * sure holes are created between the current EOF and the start of - * any next extents (if required). - * - * this also makes the decision about creating an inline extent vs - * doing real data extents, marking pages dirty and delalloc as required. + * After btrfs_copy_from_user(), update the following things for delalloc: + * - Mark newly dirtied pages as DELALLOC in the io tree. + * Used to advise which range is to be written back. + * - Mark modified pages as Uptodate/Dirty and not needing COW fixup + * - Update inode size for past EOF write */ int btrfs_dirty_pages(struct btrfs_inode *inode, struct page **pages, size_t num_pages, loff_t pos, size_t write_bytes, @@ -1370,6 +1369,12 @@ again: goto fail; } + err = set_page_extent_mapped(pages[i]); + if (err < 0) { + faili = i; + goto fail; + } + if (i == 0) err = prepare_uptodate_page(inode, pages[i], pos, force_uptodate); @@ -1454,23 +1459,11 @@ lock_and_cleanup_extent_if_need(struct btrfs_inode *inode, struct page **pages, } /* - * It's possible the pages are dirty right now, but we don't want - * to clean them yet because copy_from_user may catch a page fault - * and we might have to fall back to one page at a time. If that - * happens, we'll unlock these pages and we'd have a window where - * reclaim could sneak in and drop the once-dirty page on the floor - * without writing it. - * - * We have the pages locked and the extent range locked, so there's - * no way someone can start IO on any dirty pages in this range. - * - * We'll call btrfs_dirty_pages() later on, and that will flip around - * delalloc bits and dirty the pages as required. + * We should be called after prepare_pages() which should have locked + * all pages in the range. */ - for (i = 0; i < num_pages; i++) { - set_page_extent_mapped(pages[i]); + for (i = 0; i < num_pages; i++) WARN_ON(!PageLocked(pages[i])); - } return ret; } @@ -1949,8 +1942,8 @@ relock: goto buffered; } - dio = __iomap_dio_rw(iocb, from, &btrfs_dio_iomap_ops, - &btrfs_dio_ops, is_sync_kiocb(iocb)); + dio = __iomap_dio_rw(iocb, from, &btrfs_dio_iomap_ops, &btrfs_dio_ops, + 0); btrfs_inode_unlock(inode, ilock_flags); @@ -1997,9 +1990,7 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; - struct inode *inode = file_inode(file); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - struct btrfs_root *root = BTRFS_I(inode)->root; + struct btrfs_inode *inode = BTRFS_I(file_inode(file)); ssize_t num_written = 0; const bool sync = iocb->ki_flags & IOCB_DSYNC; @@ -2008,7 +1999,7 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb, * have opened a file as writable, we have to stop this write operation * to ensure consistency. */ - if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) + if (test_bit(BTRFS_FS_STATE_ERROR, &inode->root->fs_info->fs_state)) return -EROFS; if (!(iocb->ki_flags & IOCB_DIRECT) && @@ -2016,7 +2007,7 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb, return -EOPNOTSUPP; if (sync) - atomic_inc(&BTRFS_I(inode)->sync_writers); + atomic_inc(&inode->sync_writers); if (iocb->ki_flags & IOCB_DIRECT) num_written = btrfs_direct_write(iocb, from); @@ -2028,14 +2019,14 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb, * otherwise subsequent syncs to a file that's been synced in this * transaction will appear to have already occurred. */ - spin_lock(&BTRFS_I(inode)->lock); - BTRFS_I(inode)->last_sub_trans = root->log_transid; - spin_unlock(&BTRFS_I(inode)->lock); + spin_lock(&inode->lock); + inode->last_sub_trans = inode->root->log_transid; + spin_unlock(&inode->lock); if (num_written > 0) num_written = generic_write_sync(iocb, num_written); if (sync) - atomic_dec(&BTRFS_I(inode)->sync_writers); + atomic_dec(&inode->sync_writers); current->backing_dev_info = NULL; return num_written; @@ -2177,8 +2168,12 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) * commit waits for their completion, to avoid data loss if we fsync, * the current transaction commits before the ordered extents complete * and a power failure happens right after that. + * + * For zoned filesystem, if a write IO uses a ZONE_APPEND command, the + * logical address recorded in the ordered extent may change. We need + * to wait for the IO to stabilize the logical address. */ - if (full_sync) { + if (full_sync || btrfs_is_zoned(fs_info)) { ret = btrfs_wait_ordered_range(inode, start, len); } else { /* @@ -2241,6 +2236,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) ret = PTR_ERR(trans); goto out_release_extents; } + trans->in_fsync = true; ret = btrfs_log_dentry_safe(trans, dentry, &ctx); btrfs_release_log_ctx_extents(&ctx); @@ -3622,8 +3618,7 @@ static ssize_t btrfs_direct_read(struct kiocb *iocb, struct iov_iter *to) return 0; btrfs_inode_lock(inode, BTRFS_ILOCK_SHARED); - ret = iomap_dio_rw(iocb, to, &btrfs_dio_iomap_ops, &btrfs_dio_ops, - is_sync_kiocb(iocb)); + ret = iomap_dio_rw(iocb, to, &btrfs_dio_iomap_ops, &btrfs_dio_ops, 0); btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED); return ret; } diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 4d8897879c9c..5400294bd271 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -198,7 +198,7 @@ int create_free_space_inode(struct btrfs_trans_handle *trans, int ret; u64 ino; - ret = btrfs_find_free_objectid(trans->fs_info->tree_root, &ino); + ret = btrfs_get_free_objectid(trans->fs_info->tree_root, &ino); if (ret < 0) return ret; @@ -431,11 +431,22 @@ static int io_ctl_prepare_pages(struct btrfs_io_ctl *io_ctl, bool uptodate) int i; for (i = 0; i < io_ctl->num_pages; i++) { + int ret; + page = find_or_create_page(inode->i_mapping, i, mask); if (!page) { io_ctl_drop_pages(io_ctl); return -ENOMEM; } + + ret = set_page_extent_mapped(page); + if (ret < 0) { + unlock_page(page); + put_page(page); + io_ctl_drop_pages(io_ctl); + return ret; + } + io_ctl->pages[i] = page; if (uptodate && !PageUptodate(page)) { btrfs_readpage(NULL, page); @@ -455,10 +466,8 @@ static int io_ctl_prepare_pages(struct btrfs_io_ctl *io_ctl, bool uptodate) } } - for (i = 0; i < io_ctl->num_pages; i++) { + for (i = 0; i < io_ctl->num_pages; i++) clear_page_dirty_for_io(io_ctl->pages[i]); - set_page_extent_mapped(io_ctl->pages[i]); - } return 0; } @@ -775,8 +784,10 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode, while (num_entries) { e = kmem_cache_zalloc(btrfs_free_space_cachep, GFP_NOFS); - if (!e) + if (!e) { + ret = -ENOMEM; goto free_cache; + } ret = io_ctl_read_entry(&io_ctl, e, &type); if (ret) { @@ -785,6 +796,7 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode, } if (!e->bytes) { + ret = -1; kmem_cache_free(btrfs_free_space_cachep, e); goto free_cache; } @@ -805,6 +817,7 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode, e->bitmap = kmem_cache_zalloc( btrfs_free_space_bitmap_cachep, GFP_NOFS); if (!e->bitmap) { + ret = -ENOMEM; kmem_cache_free( btrfs_free_space_cachep, e); goto free_cache; @@ -1295,11 +1308,14 @@ int btrfs_wait_cache_io(struct btrfs_trans_handle *trans, } /** - * __btrfs_write_out_cache - write out cached info to an inode - * @root - the root the inode belongs to - * @ctl - the free space cache we are going to write out - * @block_group - the block_group for this cache if it belongs to a block_group - * @trans - the trans handle + * Write out cached info to an inode + * + * @root: root the inode belongs to + * @inode: freespace inode we are writing out + * @ctl: free space cache we are going to write out + * @block_group: block_group for this cache if it belongs to a block_group + * @io_ctl: holds context for the io + * @trans: the trans handle * * This function writes out a free space cache struct to disk for quick recovery * on mount. This will return 0 if it was successful in writing the cache out, @@ -2461,6 +2477,8 @@ int __btrfs_add_free_space(struct btrfs_fs_info *fs_info, int ret = 0; u64 filter_bytes = bytes; + ASSERT(!btrfs_is_zoned(fs_info)); + info = kmem_cache_zalloc(btrfs_free_space_cachep, GFP_NOFS); if (!info) return -ENOMEM; @@ -2518,11 +2536,49 @@ out: return ret; } +static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group, + u64 bytenr, u64 size, bool used) +{ + struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; + u64 offset = bytenr - block_group->start; + u64 to_free, to_unusable; + + spin_lock(&ctl->tree_lock); + if (!used) + to_free = size; + else if (offset >= block_group->alloc_offset) + to_free = size; + else if (offset + size <= block_group->alloc_offset) + to_free = 0; + else + to_free = offset + size - block_group->alloc_offset; + to_unusable = size - to_free; + + ctl->free_space += to_free; + block_group->zone_unusable += to_unusable; + spin_unlock(&ctl->tree_lock); + if (!used) { + spin_lock(&block_group->lock); + block_group->alloc_offset -= size; + spin_unlock(&block_group->lock); + } + + /* All the region is now unusable. Mark it as unused and reclaim */ + if (block_group->zone_unusable == block_group->length) + btrfs_mark_bg_unused(block_group); + + return 0; +} + int btrfs_add_free_space(struct btrfs_block_group *block_group, u64 bytenr, u64 size) { enum btrfs_trim_state trim_state = BTRFS_TRIM_STATE_UNTRIMMED; + if (btrfs_is_zoned(block_group->fs_info)) + return __btrfs_add_free_space_zoned(block_group, bytenr, size, + true); + if (btrfs_test_opt(block_group->fs_info, DISCARD_SYNC)) trim_state = BTRFS_TRIM_STATE_TRIMMED; @@ -2531,6 +2587,16 @@ int btrfs_add_free_space(struct btrfs_block_group *block_group, bytenr, size, trim_state); } +int btrfs_add_free_space_unused(struct btrfs_block_group *block_group, + u64 bytenr, u64 size) +{ + if (btrfs_is_zoned(block_group->fs_info)) + return __btrfs_add_free_space_zoned(block_group, bytenr, size, + false); + + return btrfs_add_free_space(block_group, bytenr, size); +} + /* * This is a subtle distinction because when adding free space back in general, * we want it to be added as untrimmed for async. But in the case where we add @@ -2541,6 +2607,10 @@ int btrfs_add_free_space_async_trimmed(struct btrfs_block_group *block_group, { enum btrfs_trim_state trim_state = BTRFS_TRIM_STATE_UNTRIMMED; + if (btrfs_is_zoned(block_group->fs_info)) + return __btrfs_add_free_space_zoned(block_group, bytenr, size, + true); + if (btrfs_test_opt(block_group->fs_info, DISCARD_SYNC) || btrfs_test_opt(block_group->fs_info, DISCARD_ASYNC)) trim_state = BTRFS_TRIM_STATE_TRIMMED; @@ -2558,6 +2628,23 @@ int btrfs_remove_free_space(struct btrfs_block_group *block_group, int ret; bool re_search = false; + if (btrfs_is_zoned(block_group->fs_info)) { + /* + * This can happen with conventional zones when replaying log. + * Since the allocation info of tree-log nodes are not recorded + * to the extent-tree, calculate_alloc_pointer() failed to + * advance the allocation pointer after last allocated tree log + * node blocks. + * + * This function is called from + * btrfs_pin_extent_for_log_replay() when replaying the log. + * Advance the pointer not to overwrite the tree-log nodes. + */ + if (block_group->alloc_offset < offset + bytes) + block_group->alloc_offset = offset + bytes; + return 0; + } + spin_lock(&ctl->tree_lock); again: @@ -2652,6 +2739,16 @@ void btrfs_dump_free_space(struct btrfs_block_group *block_group, struct rb_node *n; int count = 0; + /* + * Zoned btrfs does not use free space tree and cluster. Just print + * out the free space after the allocation offset. + */ + if (btrfs_is_zoned(fs_info)) { + btrfs_info(fs_info, "free space %llu", + block_group->length - block_group->alloc_offset); + return; + } + spin_lock(&ctl->tree_lock); for (n = rb_first(&ctl->free_space_offset); n; n = rb_next(n)) { info = rb_entry(n, struct btrfs_free_space, offset_index); @@ -2845,6 +2942,8 @@ u64 btrfs_find_space_for_alloc(struct btrfs_block_group *block_group, u64 align_gap_len = 0; enum btrfs_trim_state align_gap_trim_state = BTRFS_TRIM_STATE_UNTRIMMED; + ASSERT(!btrfs_is_zoned(block_group->fs_info)); + spin_lock(&ctl->tree_lock); entry = find_free_space(ctl, &offset, &bytes_search, block_group->full_stripe_len, max_extent_size); @@ -2976,6 +3075,8 @@ u64 btrfs_alloc_from_cluster(struct btrfs_block_group *block_group, struct rb_node *node; u64 ret = 0; + ASSERT(!btrfs_is_zoned(block_group->fs_info)); + spin_lock(&cluster->lock); if (bytes > cluster->max_size) goto out; @@ -3752,6 +3853,8 @@ int btrfs_trim_block_group(struct btrfs_block_group *block_group, int ret; u64 rem = 0; + ASSERT(!btrfs_is_zoned(block_group->fs_info)); + *trimmed = 0; spin_lock(&block_group->lock); diff --git a/fs/btrfs/free-space-cache.h b/fs/btrfs/free-space-cache.h index ecb09a02d544..1f23088d43f9 100644 --- a/fs/btrfs/free-space-cache.h +++ b/fs/btrfs/free-space-cache.h @@ -107,6 +107,8 @@ int __btrfs_add_free_space(struct btrfs_fs_info *fs_info, enum btrfs_trim_state trim_state); int btrfs_add_free_space(struct btrfs_block_group *block_group, u64 bytenr, u64 size); +int btrfs_add_free_space_unused(struct btrfs_block_group *block_group, + u64 bytenr, u64 size); int btrfs_add_free_space_async_trimmed(struct btrfs_block_group *block_group, u64 bytenr, u64 size); int btrfs_remove_free_space(struct btrfs_block_group *block_group, diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c index e33a65bd9a0c..a33bca94d133 100644 --- a/fs/btrfs/free-space-tree.c +++ b/fs/btrfs/free-space-tree.c @@ -1150,6 +1150,7 @@ int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info) return PTR_ERR(trans); set_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags); + set_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags); free_space_root = btrfs_create_tree(trans, BTRFS_FREE_SPACE_TREE_OBJECTID); if (IS_ERR(free_space_root)) { @@ -1171,11 +1172,18 @@ int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info) btrfs_set_fs_compat_ro(fs_info, FREE_SPACE_TREE); btrfs_set_fs_compat_ro(fs_info, FREE_SPACE_TREE_VALID); clear_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags); + ret = btrfs_commit_transaction(trans); - return btrfs_commit_transaction(trans); + /* + * Now that we've committed the transaction any reading of our commit + * root will be safe, so we can cache from the free space tree now. + */ + clear_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags); + return ret; abort: clear_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags); + clear_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags); btrfs_abort_transaction(trans, ret); btrfs_end_transaction(trans); return ret; diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 8e23780acfae..535abf898225 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -50,6 +50,7 @@ #include "delalloc-space.h" #include "block-group.h" #include "space-info.h" +#include "zoned.h" struct btrfs_iget_args { u64 ino; @@ -692,8 +693,7 @@ cont: NULL, clear_flags, PAGE_UNLOCK | - PAGE_CLEAR_DIRTY | - PAGE_SET_WRITEBACK | + PAGE_START_WRITEBACK | page_error_op | PAGE_END_WRITEBACK); @@ -917,7 +917,6 @@ retry: ins.objectid, async_extent->ram_size, ins.offset, - BTRFS_ORDERED_COMPRESSED, async_extent->compress_type); if (ret) { btrfs_drop_extent_cache(inode, async_extent->start, @@ -934,8 +933,7 @@ retry: async_extent->start + async_extent->ram_size - 1, NULL, EXTENT_LOCKED | EXTENT_DELALLOC, - PAGE_UNLOCK | PAGE_CLEAR_DIRTY | - PAGE_SET_WRITEBACK); + PAGE_UNLOCK | PAGE_START_WRITEBACK); if (btrfs_submit_compressed_write(inode, async_extent->start, async_extent->ram_size, ins.objectid, @@ -971,9 +969,8 @@ out_free: NULL, EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DELALLOC_NEW | EXTENT_DEFRAG | EXTENT_DO_ACCOUNTING, - PAGE_UNLOCK | PAGE_CLEAR_DIRTY | - PAGE_SET_WRITEBACK | PAGE_END_WRITEBACK | - PAGE_SET_ERROR); + PAGE_UNLOCK | PAGE_START_WRITEBACK | + PAGE_END_WRITEBACK | PAGE_SET_ERROR); free_async_extent_pages(async_extent); kfree(async_extent); goto again; @@ -1071,8 +1068,7 @@ static noinline int cow_file_range(struct btrfs_inode *inode, EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DELALLOC_NEW | EXTENT_DEFRAG | EXTENT_DO_ACCOUNTING, PAGE_UNLOCK | - PAGE_CLEAR_DIRTY | PAGE_SET_WRITEBACK | - PAGE_END_WRITEBACK); + PAGE_START_WRITEBACK | PAGE_END_WRITEBACK); *nr_written = *nr_written + (end - start + PAGE_SIZE) / PAGE_SIZE; *page_started = 1; @@ -1127,7 +1123,8 @@ static noinline int cow_file_range(struct btrfs_inode *inode, free_extent_map(em); ret = btrfs_add_ordered_extent(inode, start, ins.objectid, - ram_size, cur_alloc_size, 0); + ram_size, cur_alloc_size, + BTRFS_ORDERED_REGULAR); if (ret) goto out_drop_extent_cache; @@ -1194,8 +1191,7 @@ out_reserve: out_unlock: clear_bits = EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DELALLOC_NEW | EXTENT_DEFRAG | EXTENT_CLEAR_META_RESV; - page_ops = PAGE_UNLOCK | PAGE_CLEAR_DIRTY | PAGE_SET_WRITEBACK | - PAGE_END_WRITEBACK; + page_ops = PAGE_UNLOCK | PAGE_START_WRITEBACK | PAGE_END_WRITEBACK; /* * If we reserved an extent for our delalloc range (or a subrange) and * failed to create the respective ordered extent, then it means that @@ -1320,9 +1316,8 @@ static int cow_file_range_async(struct btrfs_inode *inode, unsigned clear_bits = EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DELALLOC_NEW | EXTENT_DEFRAG | EXTENT_DO_ACCOUNTING; - unsigned long page_ops = PAGE_UNLOCK | PAGE_CLEAR_DIRTY | - PAGE_SET_WRITEBACK | PAGE_END_WRITEBACK | - PAGE_SET_ERROR; + unsigned long page_ops = PAGE_UNLOCK | PAGE_START_WRITEBACK | + PAGE_END_WRITEBACK | PAGE_SET_ERROR; extent_clear_unlock_delalloc(inode, start, end, locked_page, clear_bits, page_ops); @@ -1399,6 +1394,29 @@ static int cow_file_range_async(struct btrfs_inode *inode, return 0; } +static noinline int run_delalloc_zoned(struct btrfs_inode *inode, + struct page *locked_page, u64 start, + u64 end, int *page_started, + unsigned long *nr_written) +{ + int ret; + + ret = cow_file_range(inode, locked_page, start, end, page_started, + nr_written, 0); + if (ret) + return ret; + + if (*page_started) + return 0; + + __set_page_dirty_nobuffers(locked_page); + account_page_redirty(locked_page); + extent_write_locked_range(&inode->vfs_inode, start, end, WB_SYNC_ALL); + *page_started = 1; + + return 0; +} + static noinline int csum_exist_in_range(struct btrfs_fs_info *fs_info, u64 bytenr, u64 num_bytes) { @@ -1519,8 +1537,7 @@ static noinline int run_delalloc_nocow(struct btrfs_inode *inode, EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, PAGE_UNLOCK | - PAGE_CLEAR_DIRTY | - PAGE_SET_WRITEBACK | + PAGE_START_WRITEBACK | PAGE_END_WRITEBACK); return -ENOMEM; } @@ -1842,8 +1859,7 @@ error: locked_page, EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DEFRAG | EXTENT_DO_ACCOUNTING, PAGE_UNLOCK | - PAGE_CLEAR_DIRTY | - PAGE_SET_WRITEBACK | + PAGE_START_WRITEBACK | PAGE_END_WRITEBACK); btrfs_free_path(path); return ret; @@ -1878,17 +1894,24 @@ int btrfs_run_delalloc_range(struct btrfs_inode *inode, struct page *locked_page { int ret; int force_cow = need_force_cow(inode, start, end); + const bool zoned = btrfs_is_zoned(inode->root->fs_info); if (inode->flags & BTRFS_INODE_NODATACOW && !force_cow) { + ASSERT(!zoned); ret = run_delalloc_nocow(inode, locked_page, start, end, page_started, 1, nr_written); } else if (inode->flags & BTRFS_INODE_PREALLOC && !force_cow) { + ASSERT(!zoned); ret = run_delalloc_nocow(inode, locked_page, start, end, page_started, 0, nr_written); } else if (!inode_can_compress(inode) || !inode_need_compress(inode, start, end)) { - ret = cow_file_range(inode, locked_page, start, end, - page_started, nr_written, 1); + if (zoned) + ret = run_delalloc_zoned(inode, locked_page, start, end, + page_started, nr_written); + else + ret = cow_file_range(inode, locked_page, start, end, + page_started, nr_written, 1); } else { set_bit(BTRFS_INODE_HAS_ASYNC_EXTENT, &inode->runtime_flags); ret = cow_file_range_async(inode, wbc, locked_page, start, end, @@ -2183,9 +2206,10 @@ int btrfs_bio_fits_in_stripe(struct page *page, size_t size, struct bio *bio, struct inode *inode = page->mapping->host; struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); u64 logical = bio->bi_iter.bi_sector << 9; + struct extent_map *em; u64 length = 0; u64 map_length; - int ret; + int ret = 0; struct btrfs_io_geometry geom; if (bio_flags & EXTENT_BIO_COMPRESSED) @@ -2193,14 +2217,19 @@ int btrfs_bio_fits_in_stripe(struct page *page, size_t size, struct bio *bio, length = bio->bi_iter.bi_size; map_length = length; - ret = btrfs_get_io_geometry(fs_info, btrfs_op(bio), logical, map_length, - &geom); + em = btrfs_get_chunk_map(fs_info, logical, map_length); + if (IS_ERR(em)) + return PTR_ERR(em); + ret = btrfs_get_io_geometry(fs_info, em, btrfs_op(bio), logical, + map_length, &geom); if (ret < 0) - return ret; + goto out; if (geom.len < length + size) - return 1; - return 0; + ret = 1; +out: + free_extent_map(em); + return ret; } /* @@ -2217,6 +2246,119 @@ static blk_status_t btrfs_submit_bio_start(struct inode *inode, struct bio *bio, return btrfs_csum_one_bio(BTRFS_I(inode), bio, 0, 0); } +bool btrfs_bio_fits_in_ordered_extent(struct page *page, struct bio *bio, + unsigned int size) +{ + struct btrfs_inode *inode = BTRFS_I(page->mapping->host); + struct btrfs_fs_info *fs_info = inode->root->fs_info; + struct btrfs_ordered_extent *ordered; + u64 len = bio->bi_iter.bi_size + size; + bool ret = true; + + ASSERT(btrfs_is_zoned(fs_info)); + ASSERT(fs_info->max_zone_append_size > 0); + ASSERT(bio_op(bio) == REQ_OP_ZONE_APPEND); + + /* Ordered extent not yet created, so we're good */ + ordered = btrfs_lookup_ordered_extent(inode, page_offset(page)); + if (!ordered) + return ret; + + if ((bio->bi_iter.bi_sector << SECTOR_SHIFT) + len > + ordered->disk_bytenr + ordered->disk_num_bytes) + ret = false; + + btrfs_put_ordered_extent(ordered); + + return ret; +} + +static blk_status_t extract_ordered_extent(struct btrfs_inode *inode, + struct bio *bio, loff_t file_offset) +{ + struct btrfs_ordered_extent *ordered; + struct extent_map *em = NULL, *em_new = NULL; + struct extent_map_tree *em_tree = &inode->extent_tree; + u64 start = (u64)bio->bi_iter.bi_sector << SECTOR_SHIFT; + u64 len = bio->bi_iter.bi_size; + u64 end = start + len; + u64 ordered_end; + u64 pre, post; + int ret = 0; + + ordered = btrfs_lookup_ordered_extent(inode, file_offset); + if (WARN_ON_ONCE(!ordered)) + return BLK_STS_IOERR; + + /* No need to split */ + if (ordered->disk_num_bytes == len) + goto out; + + /* We cannot split once end_bio'd ordered extent */ + if (WARN_ON_ONCE(ordered->bytes_left != ordered->disk_num_bytes)) { + ret = -EINVAL; + goto out; + } + + /* We cannot split a compressed ordered extent */ + if (WARN_ON_ONCE(ordered->disk_num_bytes != ordered->num_bytes)) { + ret = -EINVAL; + goto out; + } + + ordered_end = ordered->disk_bytenr + ordered->disk_num_bytes; + /* bio must be in one ordered extent */ + if (WARN_ON_ONCE(start < ordered->disk_bytenr || end > ordered_end)) { + ret = -EINVAL; + goto out; + } + + /* Checksum list should be empty */ + if (WARN_ON_ONCE(!list_empty(&ordered->list))) { + ret = -EINVAL; + goto out; + } + + pre = start - ordered->disk_bytenr; + post = ordered_end - end; + + ret = btrfs_split_ordered_extent(ordered, pre, post); + if (ret) + goto out; + + read_lock(&em_tree->lock); + em = lookup_extent_mapping(em_tree, ordered->file_offset, len); + if (!em) { + read_unlock(&em_tree->lock); + ret = -EIO; + goto out; + } + read_unlock(&em_tree->lock); + + ASSERT(!test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)); + /* + * We cannot reuse em_new here but have to create a new one, as + * unpin_extent_cache() expects the start of the extent map to be the + * logical offset of the file, which does not hold true anymore after + * splitting. + */ + em_new = create_io_em(inode, em->start + pre, len, + em->start + pre, em->block_start + pre, len, + len, len, BTRFS_COMPRESS_NONE, + BTRFS_ORDERED_REGULAR); + if (IS_ERR(em_new)) { + ret = PTR_ERR(em_new); + goto out; + } + free_extent_map(em_new); + +out: + free_extent_map(em); + btrfs_put_ordered_extent(ordered); + + return errno_to_blk_status(ret); +} + /* * extent_io.c submission hook. This does the right thing for csum calculation * on write, or reading the csums from the tree before a read. @@ -2252,7 +2394,16 @@ blk_status_t btrfs_submit_data_bio(struct inode *inode, struct bio *bio, if (btrfs_is_free_space_inode(BTRFS_I(inode))) metadata = BTRFS_WQ_ENDIO_FREE_SPACE; - if (bio_op(bio) != REQ_OP_WRITE) { + if (bio_op(bio) == REQ_OP_ZONE_APPEND) { + struct page *page = bio_first_bvec_all(bio)->bv_page; + loff_t file_offset = page_offset(page); + + ret = extract_ordered_extent(BTRFS_I(inode), bio, file_offset); + if (ret) + goto out; + } + + if (btrfs_op(bio) != BTRFS_MAP_WRITE) { ret = btrfs_bio_wq_end_io(fs_info, bio, metadata); if (ret) goto out; @@ -2754,6 +2905,9 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent) goto out; } + if (ordered_extent->disk) + btrfs_rewrite_logical_zoned(ordered_extent); + btrfs_free_io_failure_record(inode, start, end); if (test_bit(BTRFS_ORDERED_TRUNCATED, &ordered_extent->flags)) { @@ -3103,14 +3257,16 @@ void btrfs_run_delayed_iputs(struct btrfs_fs_info *fs_info) } /** - * btrfs_wait_on_delayed_iputs - wait on the delayed iputs to be done running - * @fs_info - the fs_info for this fs - * @return - EINTR if we were killed, 0 if nothing's pending + * Wait for flushing all delayed iputs + * + * @fs_info: the filesystem * * This will wait on any delayed iputs that are currently running with KILLABLE * set. Once they are all done running we will return, unless we are killed in * which case we return EINTR. This helps in user operations like fallocate etc * that might get blocked on the iputs. + * + * Return EINTR if we were killed, 0 if nothing's pending */ int btrfs_wait_on_delayed_iputs(struct btrfs_fs_info *fs_info) { @@ -4720,6 +4876,9 @@ again: ret = -ENOMEM; goto out; } + ret = set_page_extent_mapped(page); + if (ret < 0) + goto out_unlock; if (!PageUptodate(page)) { ret = btrfs_readpage(NULL, page); @@ -4737,7 +4896,6 @@ again: wait_on_page_writeback(page); lock_extent_bits(io_tree, block_start, block_end, &cached_state); - set_page_extent_mapped(page); ordered = btrfs_lookup_ordered_extent(inode, block_start); if (ordered) { @@ -5011,6 +5169,15 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr) btrfs_drew_write_unlock(&root->snapshot_lock); btrfs_end_transaction(trans); } else { + struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + + if (btrfs_is_zoned(fs_info)) { + ret = btrfs_wait_ordered_range(inode, + ALIGN(newsize, fs_info->sectorsize), + (u64)-1); + if (ret) + return ret; + } /* * We're truncating a file that used to have good data down to @@ -6371,7 +6538,7 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry, if (IS_ERR(trans)) return PTR_ERR(trans); - err = btrfs_find_free_objectid(root, &objectid); + err = btrfs_get_free_objectid(root, &objectid); if (err) goto out_unlock; @@ -6435,7 +6602,7 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry, if (IS_ERR(trans)) return PTR_ERR(trans); - err = btrfs_find_free_objectid(root, &objectid); + err = btrfs_get_free_objectid(root, &objectid); if (err) goto out_unlock; @@ -6579,7 +6746,7 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) if (IS_ERR(trans)) return PTR_ERR(trans); - err = btrfs_find_free_objectid(root, &objectid); + err = btrfs_get_free_objectid(root, &objectid); if (err) goto out_fail; @@ -7103,9 +7270,6 @@ static struct extent_map *btrfs_new_extent_direct(struct btrfs_inode *inode, * @strict: if true, omit optimizations that might force us into unnecessary * cow. e.g., don't trust generation number. * - * This function will flush ordered extents in the range to ensure proper - * nocow checks for (nowait == false) case. - * * Return: * >0 and update @len if we can do nocow write * 0 if we can't do nocow write @@ -7613,6 +7777,9 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start, iomap->bdev = fs_info->fs_devices->latest_bdev; iomap->length = len; + if (write && btrfs_use_zone_append(BTRFS_I(inode), em)) + iomap->flags |= IOMAP_F_ZONE_APPEND; + free_extent_map(em); return 0; @@ -7682,7 +7849,7 @@ static void btrfs_dio_private_put(struct btrfs_dio_private *dip) if (!refcount_dec_and_test(&dip->refs)) return; - if (bio_op(dip->dio_bio) == REQ_OP_WRITE) { + if (btrfs_op(dip->dio_bio) == BTRFS_MAP_WRITE) { __endio_write_update_ordered(BTRFS_I(dip->inode), dip->logical_offset, dip->bytes, @@ -7797,10 +7964,8 @@ static void __endio_write_update_ordered(struct btrfs_inode *inode, NULL); btrfs_queue_work(wq, &ordered->work); } - /* - * If btrfs_dec_test_ordered_pending does not find any ordered - * extent in the range, we can exit. - */ + + /* No ordered extent found in the range, exit */ if (ordered_offset == last_offset) return; /* @@ -7841,6 +8006,8 @@ static void btrfs_end_dio_bio(struct bio *bio) if (err) dip->dio_bio->bi_status = err; + btrfs_record_physical_zoned(dip->inode, dip->logical_offset, bio); + bio_put(bio); btrfs_dio_private_put(dip); } @@ -7850,7 +8017,7 @@ static inline blk_status_t btrfs_submit_dio_bio(struct bio *bio, { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_dio_private *dip = bio->bi_private; - bool write = bio_op(bio) == REQ_OP_WRITE; + bool write = btrfs_op(bio) == BTRFS_MAP_WRITE; blk_status_t ret; /* Check btrfs_submit_bio_hook() for rules about async submit. */ @@ -7900,7 +8067,7 @@ static struct btrfs_dio_private *btrfs_create_dio_private(struct bio *dio_bio, struct inode *inode, loff_t file_offset) { - const bool write = (bio_op(dio_bio) == REQ_OP_WRITE); + const bool write = (btrfs_op(dio_bio) == BTRFS_MAP_WRITE); const bool csum = !(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM); size_t dip_size; struct btrfs_dio_private *dip; @@ -7930,7 +8097,7 @@ static struct btrfs_dio_private *btrfs_create_dio_private(struct bio *dio_bio, static blk_qc_t btrfs_submit_direct(struct inode *inode, struct iomap *iomap, struct bio *dio_bio, loff_t file_offset) { - const bool write = (bio_op(dio_bio) == REQ_OP_WRITE); + const bool write = (btrfs_op(dio_bio) == BTRFS_MAP_WRITE); struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); const bool raid56 = (btrfs_data_alloc_profile(fs_info) & BTRFS_BLOCK_GROUP_RAID56_MASK); @@ -7941,10 +8108,12 @@ static blk_qc_t btrfs_submit_direct(struct inode *inode, struct iomap *iomap, u64 submit_len; int clone_offset = 0; int clone_len; + u64 logical; int ret; blk_status_t status; struct btrfs_io_geometry geom; struct btrfs_dio_data *dio_data = iomap->private; + struct extent_map *em = NULL; dip = btrfs_create_dio_private(dio_bio, inode, file_offset); if (!dip) { @@ -7973,12 +8142,18 @@ static blk_qc_t btrfs_submit_direct(struct inode *inode, struct iomap *iomap, submit_len = dio_bio->bi_iter.bi_size; do { - ret = btrfs_get_io_geometry(fs_info, btrfs_op(dio_bio), - start_sector << 9, submit_len, - &geom); + logical = start_sector << 9; + em = btrfs_get_chunk_map(fs_info, logical, submit_len); + if (IS_ERR(em)) { + status = errno_to_blk_status(PTR_ERR(em)); + em = NULL; + goto out_err_em; + } + ret = btrfs_get_io_geometry(fs_info, em, btrfs_op(dio_bio), + logical, submit_len, &geom); if (ret) { status = errno_to_blk_status(ret); - goto out_err; + goto out_err_em; } ASSERT(geom.len <= INT_MAX); @@ -7993,6 +8168,19 @@ static blk_qc_t btrfs_submit_direct(struct inode *inode, struct iomap *iomap, bio->bi_end_io = btrfs_end_dio_bio; btrfs_io_bio(bio)->logical = file_offset; + WARN_ON_ONCE(write && btrfs_is_zoned(fs_info) && + fs_info->max_zone_append_size && + bio_op(bio) != REQ_OP_ZONE_APPEND); + + if (bio_op(bio) == REQ_OP_ZONE_APPEND) { + status = extract_ordered_extent(BTRFS_I(inode), bio, + file_offset); + if (status) { + bio_put(bio); + goto out_err; + } + } + ASSERT(submit_len >= clone_len); submit_len -= clone_len; @@ -8023,19 +8211,24 @@ static blk_qc_t btrfs_submit_direct(struct inode *inode, struct iomap *iomap, bio_put(bio); if (submit_len > 0) refcount_dec(&dip->refs); - goto out_err; + goto out_err_em; } dio_data->submitted += clone_len; clone_offset += clone_len; start_sector += clone_len >> 9; file_offset += clone_len; + + free_extent_map(em); } while (submit_len > 0); return BLK_QC_T_NONE; +out_err_em: + free_extent_map(em); out_err: dip->dio_bio->bi_status = status; btrfs_dio_private_put(dip); + return BLK_QC_T_NONE; } @@ -8117,7 +8310,7 @@ static int __btrfs_releasepage(struct page *page, gfp_t gfp_flags) { int ret = try_release_extent_mapping(page, gfp_flags); if (ret == 1) - detach_page_private(page); + clear_page_extent_mapped(page); return ret; } @@ -8186,8 +8379,9 @@ static void btrfs_invalidatepage(struct page *page, unsigned int offset, if (!inode_evicting) lock_extent_bits(tree, page_start, page_end, &cached_state); -again: + start = page_start; +again: ordered = btrfs_lookup_ordered_range(inode, start, page_end - start + 1); if (ordered) { found_ordered = true; @@ -8276,7 +8470,7 @@ again: } ClearPageChecked(page); - detach_page_private(page); + clear_page_extent_mapped(page); } /* @@ -8355,7 +8549,12 @@ again: wait_on_page_writeback(page); lock_extent_bits(io_tree, page_start, page_end, &cached_state); - set_page_extent_mapped(page); + ret2 = set_page_extent_mapped(page); + if (ret2 < 0) { + ret = vmf_error(ret2); + unlock_extent_cached(io_tree, page_start, page_end, &cached_state); + goto out_unlock; + } /* * we can't set the delalloc bits if there are pending ordered @@ -8592,15 +8791,18 @@ out: */ int btrfs_create_subvol_root(struct btrfs_trans_handle *trans, struct btrfs_root *new_root, - struct btrfs_root *parent_root, - u64 new_dirid) + struct btrfs_root *parent_root) { struct inode *inode; int err; u64 index = 0; + u64 ino; + + err = btrfs_get_free_objectid(new_root, &ino); + if (err < 0) + return err; - inode = btrfs_new_inode(trans, new_root, NULL, "..", 2, - new_dirid, new_dirid, + inode = btrfs_new_inode(trans, new_root, NULL, "..", 2, ino, ino, S_IFDIR | (~current_umask() & S_IRWXUGO), &index); if (IS_ERR(inode)) @@ -9079,7 +9281,7 @@ static int btrfs_whiteout_for_rename(struct btrfs_trans_handle *trans, u64 objectid; u64 index; - ret = btrfs_find_free_objectid(root, &objectid); + ret = btrfs_get_free_objectid(root, &objectid); if (ret) return ret; @@ -9390,7 +9592,9 @@ static struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode * some fairly slow code that needs optimization. This walks the list * of all the inodes with pending delalloc and forces them to disk. */ -static int start_delalloc_inodes(struct btrfs_root *root, u64 *nr, bool snapshot) +static int start_delalloc_inodes(struct btrfs_root *root, + struct writeback_control *wbc, bool snapshot, + bool in_reclaim_context) { struct btrfs_inode *binode; struct inode *inode; @@ -9398,6 +9602,7 @@ static int start_delalloc_inodes(struct btrfs_root *root, u64 *nr, bool snapshot struct list_head works; struct list_head splice; int ret = 0; + bool full_flush = wbc->nr_to_write == LONG_MAX; INIT_LIST_HEAD(&works); INIT_LIST_HEAD(&splice); @@ -9411,6 +9616,11 @@ static int start_delalloc_inodes(struct btrfs_root *root, u64 *nr, bool snapshot list_move_tail(&binode->delalloc_inodes, &root->delalloc_inodes); + + if (in_reclaim_context && + test_bit(BTRFS_INODE_NO_DELALLOC_FLUSH, &binode->runtime_flags)) + continue; + inode = igrab(&binode->vfs_inode); if (!inode) { cond_resched_lock(&root->delalloc_lock); @@ -9421,18 +9631,24 @@ static int start_delalloc_inodes(struct btrfs_root *root, u64 *nr, bool snapshot if (snapshot) set_bit(BTRFS_INODE_SNAPSHOT_FLUSH, &binode->runtime_flags); - work = btrfs_alloc_delalloc_work(inode); - if (!work) { - iput(inode); - ret = -ENOMEM; - goto out; - } - list_add_tail(&work->list, &works); - btrfs_queue_work(root->fs_info->flush_workers, - &work->work); - if (*nr != U64_MAX) { - (*nr)--; - if (*nr == 0) + if (full_flush) { + work = btrfs_alloc_delalloc_work(inode); + if (!work) { + iput(inode); + ret = -ENOMEM; + goto out; + } + list_add_tail(&work->list, &works); + btrfs_queue_work(root->fs_info->flush_workers, + &work->work); + } else { + ret = sync_inode(inode, wbc); + if (!ret && + test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT, + &BTRFS_I(inode)->runtime_flags)) + ret = sync_inode(inode, wbc); + btrfs_add_delayed_iput(inode); + if (ret || wbc->nr_to_write <= 0) goto out; } cond_resched(); @@ -9458,17 +9674,29 @@ out: int btrfs_start_delalloc_snapshot(struct btrfs_root *root) { + struct writeback_control wbc = { + .nr_to_write = LONG_MAX, + .sync_mode = WB_SYNC_NONE, + .range_start = 0, + .range_end = LLONG_MAX, + }; struct btrfs_fs_info *fs_info = root->fs_info; - u64 nr = U64_MAX; if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) return -EROFS; - return start_delalloc_inodes(root, &nr, true); + return start_delalloc_inodes(root, &wbc, true, false); } -int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr) +int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, long nr, + bool in_reclaim_context) { + struct writeback_control wbc = { + .nr_to_write = nr, + .sync_mode = WB_SYNC_NONE, + .range_start = 0, + .range_end = LLONG_MAX, + }; struct btrfs_root *root; struct list_head splice; int ret; @@ -9481,7 +9709,14 @@ int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr) mutex_lock(&fs_info->delalloc_root_mutex); spin_lock(&fs_info->delalloc_root_lock); list_splice_init(&fs_info->delalloc_roots, &splice); - while (!list_empty(&splice) && nr) { + while (!list_empty(&splice)) { + /* + * Reset nr_to_write here so we know that we're doing a full + * flush. + */ + if (nr == LONG_MAX) + wbc.nr_to_write = LONG_MAX; + root = list_first_entry(&splice, struct btrfs_root, delalloc_root); root = btrfs_grab_root(root); @@ -9490,9 +9725,9 @@ int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr) &fs_info->delalloc_roots); spin_unlock(&fs_info->delalloc_root_lock); - ret = start_delalloc_inodes(root, &nr, false); + ret = start_delalloc_inodes(root, &wbc, false, in_reclaim_context); btrfs_put_root(root); - if (ret < 0) + if (ret < 0 || wbc.nr_to_write <= 0) goto out; spin_lock(&fs_info->delalloc_root_lock); } @@ -9542,7 +9777,7 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry, if (IS_ERR(trans)) return PTR_ERR(trans); - err = btrfs_find_free_objectid(root, &objectid); + err = btrfs_get_free_objectid(root, &objectid); if (err) goto out_unlock; @@ -9876,7 +10111,7 @@ static int btrfs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) if (IS_ERR(trans)) return PTR_ERR(trans); - ret = btrfs_find_free_objectid(root, &objectid); + ret = btrfs_get_free_objectid(root, &objectid); if (ret) goto out; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 703212ff50a5..a8c60d46d19c 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -528,6 +528,14 @@ static noinline int btrfs_ioctl_fitrim(struct btrfs_fs_info *fs_info, return -EPERM; /* + * btrfs_trim_block_group() depends on space cache, which is not + * available in zoned filesystem. So, disallow fitrim on a zoned + * filesystem for now. + */ + if (btrfs_is_zoned(fs_info)) + return -EOPNOTSUPP; + + /* * If the fs is mounted with nologreplay, which requires it to be * mounted in RO mode as well, we can not allow discard on free space * inside block groups, because log trees refer to extents that are not @@ -606,14 +614,13 @@ static noinline int create_subvol(struct inode *dir, int err; dev_t anon_dev = 0; u64 objectid; - u64 new_dirid = BTRFS_FIRST_FREE_OBJECTID; u64 index = 0; root_item = kzalloc(sizeof(*root_item), GFP_KERNEL); if (!root_item) return -ENOMEM; - ret = btrfs_find_free_objectid(fs_info->tree_root, &objectid); + ret = btrfs_get_free_objectid(fs_info->tree_root, &objectid); if (ret) goto fail_free; @@ -693,7 +700,7 @@ static noinline int create_subvol(struct inode *dir, free_extent_buffer(leaf); leaf = NULL; - btrfs_set_root_dirid(root_item, new_dirid); + btrfs_set_root_dirid(root_item, BTRFS_FIRST_FREE_OBJECTID); key.objectid = objectid; key.offset = 0; @@ -716,7 +723,7 @@ static noinline int create_subvol(struct inode *dir, btrfs_record_root_in_trans(trans, new_root); - ret = btrfs_create_subvol_root(trans, new_root, root, new_dirid); + ret = btrfs_create_subvol_root(trans, new_root, root); btrfs_put_root(new_root); if (ret) { /* We potentially lose an unused inode item here */ @@ -724,10 +731,6 @@ static noinline int create_subvol(struct inode *dir, goto fail; } - mutex_lock(&new_root->objectid_mutex); - new_root->highest_objectid = new_dirid; - mutex_unlock(&new_root->objectid_mutex); - /* * insert the directory item */ @@ -1319,6 +1322,13 @@ again: if (!page) break; + ret = set_page_extent_mapped(page); + if (ret < 0) { + unlock_page(page); + put_page(page); + break; + } + page_start = page_offset(page); page_end = page_start + PAGE_SIZE - 1; while (1) { @@ -1440,7 +1450,6 @@ again: for (i = 0; i < i_done; i++) { clear_page_dirty_for_io(pages[i]); ClearPageChecked(pages[i]); - set_page_extent_mapped(pages[i]); set_page_dirty(pages[i]); unlock_page(pages[i]); put_page(pages[i]); @@ -4951,7 +4960,7 @@ long btrfs_ioctl(struct file *file, unsigned int case BTRFS_IOC_SYNC: { int ret; - ret = btrfs_start_delalloc_roots(fs_info, U64_MAX); + ret = btrfs_start_delalloc_roots(fs_info, LONG_MAX, false); if (ret) return ret; ret = btrfs_sync_fs(inode->i_sb, 1); diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index 79d366a36223..985a21558437 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -199,14 +199,21 @@ static int __btrfs_add_ordered_extent(struct btrfs_inode *inode, u64 file_offset entry->compress_type = compress_type; entry->truncated_len = (u64)-1; entry->qgroup_rsv = ret; - if (type != BTRFS_ORDERED_IO_DONE && type != BTRFS_ORDERED_COMPLETE) - set_bit(type, &entry->flags); + entry->physical = (u64)-1; + entry->disk = NULL; + entry->partno = (u8)-1; - if (dio) { - percpu_counter_add_batch(&fs_info->dio_bytes, num_bytes, - fs_info->delalloc_batch); + ASSERT(type == BTRFS_ORDERED_REGULAR || + type == BTRFS_ORDERED_NOCOW || + type == BTRFS_ORDERED_PREALLOC || + type == BTRFS_ORDERED_COMPRESSED); + set_bit(type, &entry->flags); + + percpu_counter_add_batch(&fs_info->ordered_bytes, num_bytes, + fs_info->delalloc_batch); + + if (dio) set_bit(BTRFS_ORDERED_DIRECT, &entry->flags); - } /* one ref for the tree */ refcount_set(&entry->refs, 1); @@ -256,6 +263,9 @@ int btrfs_add_ordered_extent(struct btrfs_inode *inode, u64 file_offset, u64 disk_bytenr, u64 num_bytes, u64 disk_num_bytes, int type) { + ASSERT(type == BTRFS_ORDERED_REGULAR || + type == BTRFS_ORDERED_NOCOW || + type == BTRFS_ORDERED_PREALLOC); return __btrfs_add_ordered_extent(inode, file_offset, disk_bytenr, num_bytes, disk_num_bytes, type, 0, BTRFS_COMPRESS_NONE); @@ -265,6 +275,9 @@ int btrfs_add_ordered_extent_dio(struct btrfs_inode *inode, u64 file_offset, u64 disk_bytenr, u64 num_bytes, u64 disk_num_bytes, int type) { + ASSERT(type == BTRFS_ORDERED_REGULAR || + type == BTRFS_ORDERED_NOCOW || + type == BTRFS_ORDERED_PREALLOC); return __btrfs_add_ordered_extent(inode, file_offset, disk_bytenr, num_bytes, disk_num_bytes, type, 1, BTRFS_COMPRESS_NONE); @@ -272,11 +285,12 @@ int btrfs_add_ordered_extent_dio(struct btrfs_inode *inode, u64 file_offset, int btrfs_add_ordered_extent_compress(struct btrfs_inode *inode, u64 file_offset, u64 disk_bytenr, u64 num_bytes, - u64 disk_num_bytes, int type, - int compress_type) + u64 disk_num_bytes, int compress_type) { + ASSERT(compress_type != BTRFS_COMPRESS_NONE); return __btrfs_add_ordered_extent(inode, file_offset, disk_bytenr, - num_bytes, disk_num_bytes, type, 0, + num_bytes, disk_num_bytes, + BTRFS_ORDERED_COMPRESSED, 0, compress_type); } @@ -297,26 +311,33 @@ void btrfs_add_ordered_sum(struct btrfs_ordered_extent *entry, } /* - * this is used to account for finished IO across a given range - * of the file. The IO may span ordered extents. If - * a given ordered_extent is completely done, 1 is returned, otherwise - * 0. + * Finish IO for one ordered extent across a given range. The range can + * contain several ordered extents. + * + * @found_ret: Return the finished ordered extent + * @file_offset: File offset for the finished IO + * Will also be updated to one byte past the range that is + * recordered as finished. This allows caller to walk forward. + * @io_size: Length of the finish IO range + * @uptodate: If the IO finished without problem * - * test_and_set_bit on a flag in the struct btrfs_ordered_extent is used - * to make sure this function only returns 1 once for a given ordered extent. + * Return true if any ordered extent is finished in the range, and update + * @found_ret and @file_offset. + * Return false otherwise. * - * file_offset is updated to one byte past the range that is recorded as - * complete. This allows you to walk forward in the file. + * NOTE: Although The range can cross multiple ordered extents, only one + * ordered extent will be updated during one call. The caller is responsible to + * iterate all ordered extents in the range. */ -int btrfs_dec_test_first_ordered_pending(struct btrfs_inode *inode, - struct btrfs_ordered_extent **cached, +bool btrfs_dec_test_first_ordered_pending(struct btrfs_inode *inode, + struct btrfs_ordered_extent **finished_ret, u64 *file_offset, u64 io_size, int uptodate) { struct btrfs_fs_info *fs_info = inode->root->fs_info; struct btrfs_ordered_inode_tree *tree = &inode->ordered_tree; struct rb_node *node; struct btrfs_ordered_extent *entry = NULL; - int ret; + bool finished = false; unsigned long flags; u64 dec_end; u64 dec_start; @@ -324,16 +345,12 @@ int btrfs_dec_test_first_ordered_pending(struct btrfs_inode *inode, spin_lock_irqsave(&tree->lock, flags); node = tree_search(tree, *file_offset); - if (!node) { - ret = 1; + if (!node) goto out; - } entry = rb_entry(node, struct btrfs_ordered_extent, rb_node); - if (!offset_in_entry(entry, *file_offset)) { - ret = 1; + if (!offset_in_entry(entry, *file_offset)) goto out; - } dec_start = max(*file_offset, entry->file_offset); dec_end = min(*file_offset + io_size, @@ -354,39 +371,50 @@ int btrfs_dec_test_first_ordered_pending(struct btrfs_inode *inode, set_bit(BTRFS_ORDERED_IOERR, &entry->flags); if (entry->bytes_left == 0) { - ret = test_and_set_bit(BTRFS_ORDERED_IO_DONE, &entry->flags); + /* + * Ensure only one caller can set the flag and finished_ret + * accordingly + */ + finished = !test_and_set_bit(BTRFS_ORDERED_IO_DONE, &entry->flags); /* test_and_set_bit implies a barrier */ cond_wake_up_nomb(&entry->wait); - } else { - ret = 1; } out: - if (!ret && cached && entry) { - *cached = entry; + if (finished && finished_ret && entry) { + *finished_ret = entry; refcount_inc(&entry->refs); } spin_unlock_irqrestore(&tree->lock, flags); - return ret == 0; + return finished; } /* - * this is used to account for finished IO across a given range - * of the file. The IO should not span ordered extents. If - * a given ordered_extent is completely done, 1 is returned, otherwise - * 0. + * Finish IO for one ordered extent across a given range. The range can only + * contain one ordered extent. + * + * @cached: The cached ordered extent. If not NULL, we can skip the tree + * search and use the ordered extent directly. + * Will be also used to store the finished ordered extent. + * @file_offset: File offset for the finished IO + * @io_size: Length of the finish IO range + * @uptodate: If the IO finishes without problem * - * test_and_set_bit on a flag in the struct btrfs_ordered_extent is used - * to make sure this function only returns 1 once for a given ordered extent. + * Return true if the ordered extent is finished in the range, and update + * @cached. + * Return false otherwise. + * + * NOTE: The range can NOT cross multiple ordered extents. + * Thus caller should ensure the range doesn't cross ordered extents. */ -int btrfs_dec_test_ordered_pending(struct btrfs_inode *inode, - struct btrfs_ordered_extent **cached, - u64 file_offset, u64 io_size, int uptodate) +bool btrfs_dec_test_ordered_pending(struct btrfs_inode *inode, + struct btrfs_ordered_extent **cached, + u64 file_offset, u64 io_size, int uptodate) { struct btrfs_ordered_inode_tree *tree = &inode->ordered_tree; struct rb_node *node; struct btrfs_ordered_extent *entry = NULL; unsigned long flags; - int ret; + bool finished = false; spin_lock_irqsave(&tree->lock, flags); if (cached && *cached) { @@ -395,41 +423,39 @@ int btrfs_dec_test_ordered_pending(struct btrfs_inode *inode, } node = tree_search(tree, file_offset); - if (!node) { - ret = 1; + if (!node) goto out; - } entry = rb_entry(node, struct btrfs_ordered_extent, rb_node); have_entry: - if (!offset_in_entry(entry, file_offset)) { - ret = 1; + if (!offset_in_entry(entry, file_offset)) goto out; - } - if (io_size > entry->bytes_left) { + if (io_size > entry->bytes_left) btrfs_crit(inode->root->fs_info, "bad ordered accounting left %llu size %llu", entry->bytes_left, io_size); - } + entry->bytes_left -= io_size; if (!uptodate) set_bit(BTRFS_ORDERED_IOERR, &entry->flags); if (entry->bytes_left == 0) { - ret = test_and_set_bit(BTRFS_ORDERED_IO_DONE, &entry->flags); + /* + * Ensure only one caller can set the flag and finished_ret + * accordingly + */ + finished = !test_and_set_bit(BTRFS_ORDERED_IO_DONE, &entry->flags); /* test_and_set_bit implies a barrier */ cond_wake_up_nomb(&entry->wait); - } else { - ret = 1; } out: - if (!ret && cached && entry) { + if (finished && cached && entry) { *cached = entry; refcount_inc(&entry->refs); } spin_unlock_irqrestore(&tree->lock, flags); - return ret == 0; + return finished; } /* @@ -480,9 +506,8 @@ void btrfs_remove_ordered_extent(struct btrfs_inode *btrfs_inode, btrfs_delalloc_release_metadata(btrfs_inode, entry->num_bytes, false); - if (test_bit(BTRFS_ORDERED_DIRECT, &entry->flags)) - percpu_counter_add_batch(&fs_info->dio_bytes, -entry->num_bytes, - fs_info->delalloc_batch); + percpu_counter_add_batch(&fs_info->ordered_bytes, -entry->num_bytes, + fs_info->delalloc_batch); tree = &btrfs_inode->ordered_tree; spin_lock_irq(&tree->lock); @@ -745,9 +770,10 @@ struct btrfs_ordered_extent *btrfs_lookup_ordered_extent(struct btrfs_inode *ino struct btrfs_ordered_inode_tree *tree; struct rb_node *node; struct btrfs_ordered_extent *entry = NULL; + unsigned long flags; tree = &inode->ordered_tree; - spin_lock_irq(&tree->lock); + spin_lock_irqsave(&tree->lock, flags); node = tree_search(tree, file_offset); if (!node) goto out; @@ -758,7 +784,7 @@ struct btrfs_ordered_extent *btrfs_lookup_ordered_extent(struct btrfs_inode *ino if (entry) refcount_inc(&entry->refs); out: - spin_unlock_irq(&tree->lock); + spin_unlock_irqrestore(&tree->lock, flags); return entry; } @@ -898,6 +924,84 @@ void btrfs_lock_and_flush_ordered_range(struct btrfs_inode *inode, u64 start, } } +static int clone_ordered_extent(struct btrfs_ordered_extent *ordered, u64 pos, + u64 len) +{ + struct inode *inode = ordered->inode; + u64 file_offset = ordered->file_offset + pos; + u64 disk_bytenr = ordered->disk_bytenr + pos; + u64 num_bytes = len; + u64 disk_num_bytes = len; + int type; + unsigned long flags_masked = ordered->flags & ~(1 << BTRFS_ORDERED_DIRECT); + int compress_type = ordered->compress_type; + unsigned long weight; + int ret; + + weight = hweight_long(flags_masked); + WARN_ON_ONCE(weight > 1); + if (!weight) + type = 0; + else + type = __ffs(flags_masked); + + if (test_bit(BTRFS_ORDERED_COMPRESSED, &ordered->flags)) { + WARN_ON_ONCE(1); + ret = btrfs_add_ordered_extent_compress(BTRFS_I(inode), + file_offset, disk_bytenr, num_bytes, + disk_num_bytes, compress_type); + } else if (test_bit(BTRFS_ORDERED_DIRECT, &ordered->flags)) { + ret = btrfs_add_ordered_extent_dio(BTRFS_I(inode), file_offset, + disk_bytenr, num_bytes, disk_num_bytes, type); + } else { + ret = btrfs_add_ordered_extent(BTRFS_I(inode), file_offset, + disk_bytenr, num_bytes, disk_num_bytes, type); + } + + return ret; +} + +int btrfs_split_ordered_extent(struct btrfs_ordered_extent *ordered, u64 pre, + u64 post) +{ + struct inode *inode = ordered->inode; + struct btrfs_ordered_inode_tree *tree = &BTRFS_I(inode)->ordered_tree; + struct rb_node *node; + struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + int ret = 0; + + spin_lock_irq(&tree->lock); + /* Remove from tree once */ + node = &ordered->rb_node; + rb_erase(node, &tree->tree); + RB_CLEAR_NODE(node); + if (tree->last == node) + tree->last = NULL; + + ordered->file_offset += pre; + ordered->disk_bytenr += pre; + ordered->num_bytes -= (pre + post); + ordered->disk_num_bytes -= (pre + post); + ordered->bytes_left -= (pre + post); + + /* Re-insert the node */ + node = tree_insert(&tree->tree, ordered->file_offset, &ordered->rb_node); + if (node) + btrfs_panic(fs_info, -EEXIST, + "zoned: inconsistency in ordered tree at offset %llu", + ordered->file_offset); + + spin_unlock_irq(&tree->lock); + + if (pre) + ret = clone_ordered_extent(ordered, 0, pre); + if (post) + ret = clone_ordered_extent(ordered, pre + ordered->disk_num_bytes, + post); + + return ret; +} + int __init ordered_data_init(void) { btrfs_ordered_extent_cache = kmem_cache_create("btrfs_ordered_extent", diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h index 0bfa82b58e23..99e0853e4d3b 100644 --- a/fs/btrfs/ordered-data.h +++ b/fs/btrfs/ordered-data.h @@ -27,7 +27,7 @@ struct btrfs_ordered_sum { }; /* - * bits for the flags field: + * Bits for btrfs_ordered_extent::flags. * * BTRFS_ORDERED_IO_DONE is set when all of the blocks are written. * It is used to make sure metadata is inserted into the tree only once @@ -38,24 +38,36 @@ struct btrfs_ordered_sum { * IO is done and any metadata is inserted into the tree. */ enum { + /* + * Different types for direct io, one and only one of the 4 type can + * be set when creating ordered extent. + * + * REGULAR: For regular non-compressed COW write + * NOCOW: For NOCOW write into existing non-hole extent + * PREALLOC: For NOCOW write into preallocated extent + * COMPRESSED: For compressed COW write + */ + BTRFS_ORDERED_REGULAR, + BTRFS_ORDERED_NOCOW, + BTRFS_ORDERED_PREALLOC, + BTRFS_ORDERED_COMPRESSED, + + /* + * Extra bit for direct io, can only be set for + * REGULAR/NOCOW/PREALLOC. No direct io for compressed extent. + */ + BTRFS_ORDERED_DIRECT, + + /* Extra status bits for ordered extents */ + /* set when all the pages are written */ BTRFS_ORDERED_IO_DONE, /* set when removed from the tree */ BTRFS_ORDERED_COMPLETE, - /* set when we want to write in place */ - BTRFS_ORDERED_NOCOW, - /* writing a zlib compressed extent */ - BTRFS_ORDERED_COMPRESSED, - /* set when writing to preallocated extent */ - BTRFS_ORDERED_PREALLOC, - /* set when we're doing DIO with this extent */ - BTRFS_ORDERED_DIRECT, /* We had an io error when writing this out */ BTRFS_ORDERED_IOERR, /* Set when we have to truncate an extent */ BTRFS_ORDERED_TRUNCATED, - /* Regular IO for COW */ - BTRFS_ORDERED_REGULAR, /* Used during fsync to track already logged extents */ BTRFS_ORDERED_LOGGED, /* We have already logged all the csums of the ordered extent */ @@ -127,6 +139,14 @@ struct btrfs_ordered_extent { struct completion completion; struct btrfs_work flush_work; struct list_head work_list; + + /* + * Used to reverse-map physical address returned from ZONE_APPEND write + * command in a workqueue context + */ + u64 physical; + struct gendisk *disk; + u8 partno; }; /* @@ -152,11 +172,11 @@ btrfs_ordered_inode_tree_init(struct btrfs_ordered_inode_tree *t) void btrfs_put_ordered_extent(struct btrfs_ordered_extent *entry); void btrfs_remove_ordered_extent(struct btrfs_inode *btrfs_inode, struct btrfs_ordered_extent *entry); -int btrfs_dec_test_ordered_pending(struct btrfs_inode *inode, - struct btrfs_ordered_extent **cached, - u64 file_offset, u64 io_size, int uptodate); -int btrfs_dec_test_first_ordered_pending(struct btrfs_inode *inode, - struct btrfs_ordered_extent **cached, +bool btrfs_dec_test_ordered_pending(struct btrfs_inode *inode, + struct btrfs_ordered_extent **cached, + u64 file_offset, u64 io_size, int uptodate); +bool btrfs_dec_test_first_ordered_pending(struct btrfs_inode *inode, + struct btrfs_ordered_extent **finished_ret, u64 *file_offset, u64 io_size, int uptodate); int btrfs_add_ordered_extent(struct btrfs_inode *inode, u64 file_offset, @@ -167,8 +187,7 @@ int btrfs_add_ordered_extent_dio(struct btrfs_inode *inode, u64 file_offset, u64 disk_num_bytes, int type); int btrfs_add_ordered_extent_compress(struct btrfs_inode *inode, u64 file_offset, u64 disk_bytenr, u64 num_bytes, - u64 disk_num_bytes, int type, - int compress_type); + u64 disk_num_bytes, int compress_type); void btrfs_add_ordered_sum(struct btrfs_ordered_extent *entry, struct btrfs_ordered_sum *sum); struct btrfs_ordered_extent *btrfs_lookup_ordered_extent(struct btrfs_inode *inode, @@ -190,6 +209,8 @@ void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, u64 nr, void btrfs_lock_and_flush_ordered_range(struct btrfs_inode *inode, u64 start, u64 end, struct extent_state **cached_state); +int btrfs_split_ordered_extent(struct btrfs_ordered_extent *ordered, u64 pre, + u64 post); int __init ordered_data_init(void); void __cold ordered_data_exit(void); diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c index fe5e0026129d..aae1027bd76a 100644 --- a/fs/btrfs/print-tree.c +++ b/fs/btrfs/print-tree.c @@ -26,22 +26,22 @@ static const struct root_name_map root_map[] = { { BTRFS_DATA_RELOC_TREE_OBJECTID, "DATA_RELOC_TREE" }, }; -const char *btrfs_root_name(u64 objectid, char *buf) +const char *btrfs_root_name(const struct btrfs_key *key, char *buf) { int i; - if (objectid == BTRFS_TREE_RELOC_OBJECTID) { + if (key->objectid == BTRFS_TREE_RELOC_OBJECTID) { snprintf(buf, BTRFS_ROOT_NAME_BUF_LEN, - "TREE_RELOC offset=%llu", objectid); + "TREE_RELOC offset=%llu", key->offset); return buf; } for (i = 0; i < ARRAY_SIZE(root_map); i++) { - if (root_map[i].id == objectid) + if (root_map[i].id == key->objectid) return root_map[i].name; } - snprintf(buf, BTRFS_ROOT_NAME_BUF_LEN, "%llu", objectid); + snprintf(buf, BTRFS_ROOT_NAME_BUF_LEN, "%llu", key->objectid); return buf; } diff --git a/fs/btrfs/print-tree.h b/fs/btrfs/print-tree.h index 78b99385a503..8c3e9319ec4e 100644 --- a/fs/btrfs/print-tree.h +++ b/fs/btrfs/print-tree.h @@ -11,6 +11,6 @@ void btrfs_print_leaf(struct extent_buffer *l); void btrfs_print_tree(struct extent_buffer *c, bool follow); -const char *btrfs_root_name(u64 objectid, char *buf); +const char *btrfs_root_name(const struct btrfs_key *key, char *buf); #endif diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index fe3046007f52..808370ada888 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -3190,6 +3190,12 @@ out: return ret; } +static bool rescan_should_stop(struct btrfs_fs_info *fs_info) +{ + return btrfs_fs_closing(fs_info) || + test_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state); +} + static void btrfs_qgroup_rescan_worker(struct btrfs_work *work) { struct btrfs_fs_info *fs_info = container_of(work, struct btrfs_fs_info, @@ -3198,6 +3204,7 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work) struct btrfs_trans_handle *trans = NULL; int err = -ENOMEM; int ret = 0; + bool stopped = false; path = btrfs_alloc_path(); if (!path) @@ -3210,7 +3217,7 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work) path->skip_locking = 1; err = 0; - while (!err && !btrfs_fs_closing(fs_info)) { + while (!err && !(stopped = rescan_should_stop(fs_info))) { trans = btrfs_start_transaction(fs_info->fs_root, 0); if (IS_ERR(trans)) { err = PTR_ERR(trans); @@ -3253,7 +3260,7 @@ out: } mutex_lock(&fs_info->qgroup_rescan_lock); - if (!btrfs_fs_closing(fs_info)) + if (!stopped) fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_RESCAN; if (trans) { ret = update_qgroup_status_item(trans); @@ -3272,7 +3279,7 @@ out: btrfs_end_transaction(trans); - if (btrfs_fs_closing(fs_info)) { + if (stopped) { btrfs_info(fs_info, "qgroup scan paused"); } else if (err >= 0) { btrfs_info(fs_info, "qgroup scan completed%s", @@ -3531,16 +3538,6 @@ static int try_flush_qgroup(struct btrfs_root *root) bool can_commit = true; /* - * We don't want to run flush again and again, so if there is a running - * one, we won't try to start a new flush, but exit directly. - */ - if (test_and_set_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state)) { - wait_event(root->qgroup_flush_wait, - !test_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state)); - return 0; - } - - /* * If current process holds a transaction, we shouldn't flush, as we * assume all space reservation happens before a transaction handle is * held. @@ -3554,6 +3551,26 @@ static int try_flush_qgroup(struct btrfs_root *root) current->journal_info != BTRFS_SEND_TRANS_STUB) can_commit = false; + /* + * We don't want to run flush again and again, so if there is a running + * one, we won't try to start a new flush, but exit directly. + */ + if (test_and_set_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state)) { + /* + * We are already holding a transaction, thus we can block other + * threads from flushing. So exit right now. This increases + * the chance of EDQUOT for heavy load and near limit cases. + * But we can argue that if we're already near limit, EDQUOT is + * unavoidable anyway. + */ + if (!can_commit) + return 0; + + wait_event(root->qgroup_flush_wait, + !test_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state)); + return 0; + } + ret = btrfs_start_delalloc_snapshot(root); if (ret < 0) goto out; diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index 93fbf87bdc8d..8ec34ecb6d68 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -233,8 +233,7 @@ int btrfs_alloc_stripe_hash_table(struct btrfs_fs_info *info) } x = cmpxchg(&info->stripe_hash_table, NULL, table); - if (x) - kvfree(x); + kvfree(x); return 0; } @@ -1105,8 +1104,7 @@ static int rbio_add_io_page(struct btrfs_raid_bio *rbio, * devices or if they are not contiguous */ if (last_end == disk_start && !last->bi_status && - last->bi_disk == stripe->dev->bdev->bd_disk && - last->bi_partno == stripe->dev->bdev->bd_partno) { + last->bi_bdev == stripe->dev->bdev) { ret = bio_add_page(last, page, PAGE_SIZE, 0); if (ret == PAGE_SIZE) return 0; @@ -1357,9 +1355,7 @@ static int find_bio_stripe(struct btrfs_raid_bio *rbio, for (i = 0; i < rbio->bbio->num_stripes; i++) { stripe = &rbio->bbio->stripes[i]; if (in_range(physical, stripe->physical, rbio->stripe_len) && - stripe->dev->bdev && - bio->bi_disk == stripe->dev->bdev->bd_disk && - bio->bi_partno == stripe->dev->bdev->bd_partno) { + stripe->dev->bdev && bio->bi_bdev == stripe->dev->bdev) { return i; } } diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c index 4b9b6c52a83b..2b490becbe67 100644 --- a/fs/btrfs/ref-verify.c +++ b/fs/btrfs/ref-verify.c @@ -495,14 +495,15 @@ static int process_extent_item(struct btrfs_fs_info *fs_info, } static int process_leaf(struct btrfs_root *root, - struct btrfs_path *path, u64 *bytenr, u64 *num_bytes) + struct btrfs_path *path, u64 *bytenr, u64 *num_bytes, + int *tree_block_level) { struct btrfs_fs_info *fs_info = root->fs_info; struct extent_buffer *leaf = path->nodes[0]; struct btrfs_extent_data_ref *dref; struct btrfs_shared_data_ref *sref; u32 count; - int i = 0, tree_block_level = 0, ret = 0; + int i = 0, ret = 0; struct btrfs_key key; int nritems = btrfs_header_nritems(leaf); @@ -515,15 +516,15 @@ static int process_leaf(struct btrfs_root *root, case BTRFS_METADATA_ITEM_KEY: *bytenr = key.objectid; ret = process_extent_item(fs_info, path, &key, i, - &tree_block_level); + tree_block_level); break; case BTRFS_TREE_BLOCK_REF_KEY: ret = add_tree_block(fs_info, key.offset, 0, - key.objectid, tree_block_level); + key.objectid, *tree_block_level); break; case BTRFS_SHARED_BLOCK_REF_KEY: ret = add_tree_block(fs_info, 0, key.offset, - key.objectid, tree_block_level); + key.objectid, *tree_block_level); break; case BTRFS_EXTENT_DATA_REF_KEY: dref = btrfs_item_ptr(leaf, i, @@ -549,7 +550,8 @@ static int process_leaf(struct btrfs_root *root, /* Walk down to the leaf from the given level */ static int walk_down_tree(struct btrfs_root *root, struct btrfs_path *path, - int level, u64 *bytenr, u64 *num_bytes) + int level, u64 *bytenr, u64 *num_bytes, + int *tree_block_level) { struct extent_buffer *eb; int ret = 0; @@ -565,7 +567,8 @@ static int walk_down_tree(struct btrfs_root *root, struct btrfs_path *path, path->slots[level-1] = 0; path->locks[level-1] = BTRFS_READ_LOCK; } else { - ret = process_leaf(root, path, bytenr, num_bytes); + ret = process_leaf(root, path, bytenr, num_bytes, + tree_block_level); if (ret) break; } @@ -666,18 +669,18 @@ int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info, u64 bytenr = generic_ref->bytenr; u64 num_bytes = generic_ref->len; u64 parent = generic_ref->parent; - u64 ref_root; - u64 owner; - u64 offset; + u64 ref_root = 0; + u64 owner = 0; + u64 offset = 0; if (!btrfs_test_opt(fs_info, REF_VERIFY)) return 0; if (generic_ref->type == BTRFS_REF_METADATA) { - ref_root = generic_ref->tree_ref.root; + if (!parent) + ref_root = generic_ref->tree_ref.root; owner = generic_ref->tree_ref.level; - offset = 0; - } else { + } else if (!parent) { ref_root = generic_ref->data_ref.ref_root; owner = generic_ref->data_ref.ino; offset = generic_ref->data_ref.offset; @@ -693,13 +696,10 @@ int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info, goto out; } - if (parent) { - ref->parent = parent; - } else { - ref->root_objectid = ref_root; - ref->owner = owner; - ref->offset = offset; - } + ref->parent = parent; + ref->owner = owner; + ref->root_objectid = ref_root; + ref->offset = offset; ref->num_refs = (action == BTRFS_DROP_DELAYED_REF) ? -1 : 1; memcpy(&ra->ref, ref, sizeof(struct ref_entry)); @@ -974,6 +974,7 @@ int btrfs_build_ref_tree(struct btrfs_fs_info *fs_info) { struct btrfs_path *path; struct extent_buffer *eb; + int tree_block_level = 0; u64 bytenr = 0, num_bytes = 0; int ret, level; @@ -998,7 +999,7 @@ int btrfs_build_ref_tree(struct btrfs_fs_info *fs_info) * different leaf from the original extent item. */ ret = walk_down_tree(fs_info->extent_root, path, level, - &bytenr, &num_bytes); + &bytenr, &num_bytes, &tree_block_level); if (ret) break; ret = walk_up_tree(path, &level); diff --git a/fs/btrfs/reflink.c b/fs/btrfs/reflink.c index ab80896315be..b24396cf2f99 100644 --- a/fs/btrfs/reflink.c +++ b/fs/btrfs/reflink.c @@ -81,7 +81,10 @@ static int copy_inline_to_page(struct btrfs_inode *inode, goto out_unlock; } - set_page_extent_mapped(page); + ret = set_page_extent_mapped(page); + if (ret < 0) + goto out_unlock; + clear_extent_bit(&inode->io_tree, file_offset, range_end, EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, 0, 0, NULL); @@ -89,6 +92,19 @@ static int copy_inline_to_page(struct btrfs_inode *inode, if (ret) goto out_unlock; + /* + * After dirtying the page our caller will need to start a transaction, + * and if we are low on metadata free space, that can cause flushing of + * delalloc for all inodes in order to get metadata space released. + * However we are holding the range locked for the whole duration of + * the clone/dedupe operation, so we may deadlock if that happens and no + * other task releases enough space. So mark this inode as not being + * possible to flush to avoid such deadlock. We will clear that flag + * when we finish cloning all extents, since a transaction is started + * after finding each extent to clone. + */ + set_bit(BTRFS_INODE_NO_DELALLOC_FLUSH, &inode->runtime_flags); + if (comp_type == BTRFS_COMPRESS_NONE) { char *map; @@ -549,6 +565,8 @@ process_slot: out: btrfs_free_path(path); kvfree(buf); + clear_bit(BTRFS_INODE_NO_DELALLOC_FLUSH, &BTRFS_I(inode)->runtime_flags); + return ret; } diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 19b7db8b2117..232d5da7b7be 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -97,6 +97,7 @@ struct tree_block { struct rb_node rb_node; u64 bytenr; }; /* Use rb_simple_node for search/insert */ + u64 owner; struct btrfs_key key; unsigned int level:8; unsigned int key_ready:1; @@ -668,9 +669,7 @@ static void __del_reloc_root(struct btrfs_root *root) RB_CLEAR_NODE(&node->rb_node); } spin_unlock(&rc->reloc_root_tree.lock); - if (!node) - return; - BUG_ON((struct btrfs_root *)node->data != root); + ASSERT(!node || (struct btrfs_root *)node->data == root); } /* @@ -2393,8 +2392,8 @@ static int get_tree_block_key(struct btrfs_fs_info *fs_info, { struct extent_buffer *eb; - eb = read_tree_block(fs_info, block->bytenr, 0, block->key.offset, - block->level, NULL); + eb = read_tree_block(fs_info, block->bytenr, block->owner, + block->key.offset, block->level, NULL); if (IS_ERR(eb)) { return PTR_ERR(eb); } else if (!extent_buffer_uptodate(eb)) { @@ -2493,7 +2492,8 @@ int relocate_tree_blocks(struct btrfs_trans_handle *trans, /* Kick in readahead for tree blocks with missing keys */ rbtree_postorder_for_each_entry_safe(block, next, blocks, rb_node) { if (!block->key_ready) - btrfs_readahead_tree_block(fs_info, block->bytenr, 0, 0, + btrfs_readahead_tree_block(fs_info, block->bytenr, + block->owner, 0, block->level); } @@ -2553,6 +2553,31 @@ static noinline_for_stack int prealloc_file_extent_cluster( if (ret) return ret; + /* + * On a zoned filesystem, we cannot preallocate the file region. + * Instead, we dirty and fiemap_write the region. + */ + if (btrfs_is_zoned(inode->root->fs_info)) { + struct btrfs_root *root = inode->root; + struct btrfs_trans_handle *trans; + + end = cluster->end - offset + 1; + trans = btrfs_start_transaction(root, 1); + if (IS_ERR(trans)) + return PTR_ERR(trans); + + inode->vfs_inode.i_ctime = current_time(&inode->vfs_inode); + i_size_write(&inode->vfs_inode, end); + ret = btrfs_update_inode(trans, root, inode); + if (ret) { + btrfs_abort_transaction(trans, ret); + btrfs_end_transaction(trans); + return ret; + } + + return btrfs_end_transaction(trans); + } + inode_lock(&inode->vfs_inode); for (nr = 0; nr < cluster->nr; nr++) { start = cluster->boundary[nr] - offset; @@ -2615,7 +2640,7 @@ int setup_extent_mapping(struct inode *inode, u64 start, u64 end, /* * Allow error injection to test balance cancellation */ -int btrfs_should_cancel_balance(struct btrfs_fs_info *fs_info) +noinline int btrfs_should_cancel_balance(struct btrfs_fs_info *fs_info) { return atomic_read(&fs_info->balance_cancel_req) || fatal_signal_pending(current); @@ -2679,6 +2704,15 @@ static int relocate_file_extent_cluster(struct inode *inode, goto out; } } + ret = set_page_extent_mapped(page); + if (ret < 0) { + btrfs_delalloc_release_metadata(BTRFS_I(inode), + PAGE_SIZE, true); + btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE); + unlock_page(page); + put_page(page); + goto out; + } if (PageReadahead(page)) { page_cache_async_readahead(inode->i_mapping, @@ -2706,8 +2740,6 @@ static int relocate_file_extent_cluster(struct inode *inode, lock_extent(&BTRFS_I(inode)->io_tree, page_start, page_end); - set_page_extent_mapped(page); - if (nr < cluster->nr && page_start + offset == cluster->boundary[nr]) { set_extent_bits(&BTRFS_I(inode)->io_tree, @@ -2749,6 +2781,8 @@ static int relocate_file_extent_cluster(struct inode *inode, } } WARN_ON(nr != cluster->nr); + if (btrfs_is_zoned(fs_info) && !ret) + ret = btrfs_wait_ordered_range(inode, 0, (u64)-1); out: kfree(ra); return ret; @@ -2801,21 +2835,58 @@ static int add_tree_block(struct reloc_control *rc, u32 item_size; int level = -1; u64 generation; + u64 owner = 0; eb = path->nodes[0]; item_size = btrfs_item_size_nr(eb, path->slots[0]); if (extent_key->type == BTRFS_METADATA_ITEM_KEY || item_size >= sizeof(*ei) + sizeof(*bi)) { + unsigned long ptr = 0, end; + ei = btrfs_item_ptr(eb, path->slots[0], struct btrfs_extent_item); + end = (unsigned long)ei + item_size; if (extent_key->type == BTRFS_EXTENT_ITEM_KEY) { bi = (struct btrfs_tree_block_info *)(ei + 1); level = btrfs_tree_block_level(eb, bi); + ptr = (unsigned long)(bi + 1); } else { level = (int)extent_key->offset; + ptr = (unsigned long)(ei + 1); } generation = btrfs_extent_generation(eb, ei); + + /* + * We're reading random blocks without knowing their owner ahead + * of time. This is ok most of the time, as all reloc roots and + * fs roots have the same lock type. However normal trees do + * not, and the only way to know ahead of time is to read the + * inline ref offset. We know it's an fs root if + * + * 1. There's more than one ref. + * 2. There's a SHARED_DATA_REF_KEY set. + * 3. FULL_BACKREF is set on the flags. + * + * Otherwise it's safe to assume that the ref offset == the + * owner of this block, so we can use that when calling + * read_tree_block. + */ + if (btrfs_extent_refs(eb, ei) == 1 && + !(btrfs_extent_flags(eb, ei) & + BTRFS_BLOCK_FLAG_FULL_BACKREF) && + ptr < end) { + struct btrfs_extent_inline_ref *iref; + int type; + + iref = (struct btrfs_extent_inline_ref *)ptr; + type = btrfs_get_extent_inline_ref_type(eb, iref, + BTRFS_REF_TYPE_BLOCK); + if (type == BTRFS_REF_TYPE_INVALID) + return -EINVAL; + if (type == BTRFS_TREE_BLOCK_REF_KEY) + owner = btrfs_extent_inline_ref_offset(eb, iref); + } } else if (unlikely(item_size == sizeof(struct btrfs_extent_item_v0))) { btrfs_print_v0_err(eb->fs_info); btrfs_handle_fs_error(eb->fs_info, -EINVAL, NULL); @@ -2837,6 +2908,7 @@ static int add_tree_block(struct reloc_control *rc, block->key.offset = generation; block->level = level; block->key_ready = 0; + block->owner = owner; rb_node = rb_simple_insert(blocks, block->bytenr, &block->rb_node); if (rb_node) @@ -2975,11 +3047,16 @@ static int delete_v1_space_cache(struct extent_buffer *leaf, return 0; for (i = 0; i < btrfs_header_nritems(leaf); i++) { + u8 type; + btrfs_item_key_to_cpu(leaf, &key, i); if (key.type != BTRFS_EXTENT_DATA_KEY) continue; ei = btrfs_item_ptr(leaf, i, struct btrfs_file_extent_item); - if (btrfs_file_extent_type(leaf, ei) == BTRFS_FILE_EXTENT_REG && + type = btrfs_file_extent_type(leaf, ei); + + if ((type == BTRFS_FILE_EXTENT_REG || + type == BTRFS_FILE_EXTENT_PREALLOC) && btrfs_file_extent_disk_bytenr(leaf, ei) == data_bytenr) { found = true; space_cache_ino = key.objectid; @@ -3384,8 +3461,12 @@ static int __insert_orphan_inode(struct btrfs_trans_handle *trans, struct btrfs_path *path; struct btrfs_inode_item *item; struct extent_buffer *leaf; + u64 flags = BTRFS_INODE_NOCOMPRESS | BTRFS_INODE_PREALLOC; int ret; + if (btrfs_is_zoned(trans->fs_info)) + flags &= ~BTRFS_INODE_PREALLOC; + path = btrfs_alloc_path(); if (!path) return -ENOMEM; @@ -3400,8 +3481,7 @@ static int __insert_orphan_inode(struct btrfs_trans_handle *trans, btrfs_set_inode_generation(leaf, item, 1); btrfs_set_inode_size(leaf, item, 0); btrfs_set_inode_mode(leaf, item, S_IFREG | 0600); - btrfs_set_inode_flags(leaf, item, BTRFS_INODE_NOCOMPRESS | - BTRFS_INODE_PREALLOC); + btrfs_set_inode_flags(leaf, item, flags); btrfs_mark_buffer_dirty(leaf); out: btrfs_free_path(path); @@ -3429,7 +3509,7 @@ struct inode *create_reloc_inode(struct btrfs_fs_info *fs_info, return ERR_CAST(trans); } - err = btrfs_find_free_objectid(root, &objectid); + err = btrfs_get_free_objectid(root, &objectid); if (err) goto out; diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 5f4f88a4d2c8..582df11d298a 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -166,6 +166,7 @@ struct scrub_ctx { int pages_per_rd_bio; int is_dev_replace; + u64 write_pointer; struct scrub_bio *wr_curr_bio; struct mutex wr_lock; @@ -856,6 +857,9 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check) have_csum = sblock_to_check->pagev[0]->have_csum; dev = sblock_to_check->pagev[0]->dev; + if (btrfs_is_zoned(fs_info) && !sctx->is_dev_replace) + return btrfs_repair_one_zone(fs_info, logical); + /* * We must use GFP_NOFS because the scrub task might be waiting for a * worker task executing this function and in turn a transaction commit @@ -1619,6 +1623,28 @@ static int scrub_write_page_to_dev_replace(struct scrub_block *sblock, return scrub_add_page_to_wr_bio(sblock->sctx, spage); } +static int fill_writer_pointer_gap(struct scrub_ctx *sctx, u64 physical) +{ + int ret = 0; + u64 length; + + if (!btrfs_is_zoned(sctx->fs_info)) + return 0; + + if (!btrfs_dev_is_sequential(sctx->wr_tgtdev, physical)) + return 0; + + if (sctx->write_pointer < physical) { + length = physical - sctx->write_pointer; + + ret = btrfs_zoned_issue_zeroout(sctx->wr_tgtdev, + sctx->write_pointer, length); + if (!ret) + sctx->write_pointer = physical; + } + return ret; +} + static int scrub_add_page_to_wr_bio(struct scrub_ctx *sctx, struct scrub_page *spage) { @@ -1641,6 +1667,13 @@ again: if (sbio->page_count == 0) { struct bio *bio; + ret = fill_writer_pointer_gap(sctx, + spage->physical_for_dev_replace); + if (ret) { + mutex_unlock(&sctx->wr_lock); + return ret; + } + sbio->physical = spage->physical_for_dev_replace; sbio->logical = spage->logical; sbio->dev = sctx->wr_tgtdev; @@ -1695,13 +1728,16 @@ static void scrub_wr_submit(struct scrub_ctx *sctx) sbio = sctx->wr_curr_bio; sctx->wr_curr_bio = NULL; - WARN_ON(!sbio->bio->bi_disk); + WARN_ON(!sbio->bio->bi_bdev); scrub_pending_bio_inc(sctx); /* process all writes in a single worker thread. Then the block layer * orders the requests before sending them to the driver which * doubled the write performance on spinning disks when measured * with Linux 3.5 */ btrfsic_submit_bio(sbio->bio); + + if (btrfs_is_zoned(sctx->fs_info)) + sctx->write_pointer = sbio->physical + sbio->page_count * PAGE_SIZE; } static void scrub_wr_bio_end_io(struct bio *bio) @@ -3025,6 +3061,46 @@ out: return ret < 0 ? ret : 0; } +static void sync_replace_for_zoned(struct scrub_ctx *sctx) +{ + if (!btrfs_is_zoned(sctx->fs_info)) + return; + + sctx->flush_all_writes = true; + scrub_submit(sctx); + mutex_lock(&sctx->wr_lock); + scrub_wr_submit(sctx); + mutex_unlock(&sctx->wr_lock); + + wait_event(sctx->list_wait, atomic_read(&sctx->bios_in_flight) == 0); +} + +static int sync_write_pointer_for_zoned(struct scrub_ctx *sctx, u64 logical, + u64 physical, u64 physical_end) +{ + struct btrfs_fs_info *fs_info = sctx->fs_info; + int ret = 0; + + if (!btrfs_is_zoned(fs_info)) + return 0; + + wait_event(sctx->list_wait, atomic_read(&sctx->bios_in_flight) == 0); + + mutex_lock(&sctx->wr_lock); + if (sctx->write_pointer < physical_end) { + ret = btrfs_sync_zone_write_pointer(sctx->wr_tgtdev, logical, + physical, + sctx->write_pointer); + if (ret) + btrfs_err(fs_info, + "zoned: failed to recover write pointer"); + } + mutex_unlock(&sctx->wr_lock); + btrfs_dev_clear_zone_empty(sctx->wr_tgtdev, physical); + + return ret; +} + static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx, struct map_lookup *map, struct btrfs_device *scrub_dev, @@ -3165,6 +3241,14 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx, */ blk_start_plug(&plug); + if (sctx->is_dev_replace && + btrfs_dev_is_sequential(sctx->wr_tgtdev, physical)) { + mutex_lock(&sctx->wr_lock); + sctx->write_pointer = physical; + mutex_unlock(&sctx->wr_lock); + sctx->flush_all_writes = true; + } + /* * now find all extents for each stripe and scrub them */ @@ -3353,6 +3437,9 @@ again: if (ret) goto out; + if (sctx->is_dev_replace) + sync_replace_for_zoned(sctx); + if (extent_logical + extent_len < key.objectid + bytes) { if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) { @@ -3420,6 +3507,17 @@ out: blk_finish_plug(&plug); btrfs_free_path(path); btrfs_free_path(ppath); + + if (sctx->is_dev_replace && ret >= 0) { + int ret2; + + ret2 = sync_write_pointer_for_zoned(sctx, base + offset, + map->stripes[num].physical, + physical_end); + if (ret2) + ret = ret2; + } + return ret < 0 ? ret : 0; } @@ -3475,6 +3573,25 @@ out: return ret; } +static int finish_extent_writes_for_zoned(struct btrfs_root *root, + struct btrfs_block_group *cache) +{ + struct btrfs_fs_info *fs_info = cache->fs_info; + struct btrfs_trans_handle *trans; + + if (!btrfs_is_zoned(fs_info)) + return 0; + + btrfs_wait_block_group_reservations(cache); + btrfs_wait_nocow_writers(cache); + btrfs_wait_ordered_roots(fs_info, U64_MAX, cache->start, cache->length); + + trans = btrfs_join_transaction(root); + if (IS_ERR(trans)) + return PTR_ERR(trans); + return btrfs_commit_transaction(trans); +} + static noinline_for_stack int scrub_enumerate_chunks(struct scrub_ctx *sctx, struct btrfs_device *scrub_dev, u64 start, u64 end) @@ -3561,6 +3678,16 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, if (!cache) goto skip; + if (sctx->is_dev_replace && btrfs_is_zoned(fs_info)) { + spin_lock(&cache->lock); + if (!cache->to_copy) { + spin_unlock(&cache->lock); + ro_set = 0; + goto done; + } + spin_unlock(&cache->lock); + } + /* * Make sure that while we are scrubbing the corresponding block * group doesn't get its logical address and its device extents @@ -3619,6 +3746,16 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, * group is not RO. */ ret = btrfs_inc_block_group_ro(cache, sctx->is_dev_replace); + if (!ret && sctx->is_dev_replace) { + ret = finish_extent_writes_for_zoned(root, cache); + if (ret) { + btrfs_dec_block_group_ro(cache); + scrub_pause_off(fs_info); + btrfs_put_block_group(cache); + break; + } + } + if (ret == 0) { ro_set = 1; } else if (ret == -ENOSPC && !sctx->is_dev_replace) { @@ -3692,6 +3829,12 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, scrub_pause_off(fs_info); + if (sctx->is_dev_replace && + !btrfs_finish_block_group_to_copy(dev_replace->srcdev, + cache, found_key.offset)) + ro_set = 0; + +done: down_write(&dev_replace->rwsem); dev_replace->cursor_left = dev_replace->cursor_right; dev_replace->item_needs_writeback = 1; diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index d719a2755a40..f87878274e9f 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -236,6 +236,7 @@ struct waiting_dir_move { * after this directory is moved, we can try to rmdir the ino rmdir_ino. */ u64 rmdir_ino; + u64 rmdir_gen; bool orphanized; }; @@ -316,7 +317,7 @@ static int is_waiting_for_move(struct send_ctx *sctx, u64 ino); static struct waiting_dir_move * get_waiting_dir_move(struct send_ctx *sctx, u64 ino); -static int is_waiting_for_rm(struct send_ctx *sctx, u64 dir_ino); +static int is_waiting_for_rm(struct send_ctx *sctx, u64 dir_ino, u64 gen); static int need_send_hole(struct send_ctx *sctx) { @@ -1190,9 +1191,6 @@ struct backref_ctx { /* may be truncated in case it's the last extent in a file */ u64 extent_len; - /* data offset in the file extent item */ - u64 data_offset; - /* Just to check for bugs in backref resolving */ int found_itself; }; @@ -1400,19 +1398,6 @@ static int find_extent_clone(struct send_ctx *sctx, backref_ctx->cur_offset = data_offset; backref_ctx->found_itself = 0; backref_ctx->extent_len = num_bytes; - /* - * For non-compressed extents iterate_extent_inodes() gives us extent - * offsets that already take into account the data offset, but not for - * compressed extents, since the offset is logical and not relative to - * the physical extent locations. We must take this into account to - * avoid sending clone offsets that go beyond the source file's size, - * which would result in the clone ioctl failing with -EINVAL on the - * receiving end. - */ - if (compressed == BTRFS_COMPRESS_NONE) - backref_ctx->data_offset = 0; - else - backref_ctx->data_offset = btrfs_file_extent_offset(eb, fi); /* * The last extent of a file may be too large due to page alignment. @@ -2299,7 +2284,7 @@ static int get_cur_path(struct send_ctx *sctx, u64 ino, u64 gen, fs_path_reset(name); - if (is_waiting_for_rm(sctx, ino)) { + if (is_waiting_for_rm(sctx, ino, gen)) { ret = gen_unique_name(sctx, ino, gen, name); if (ret < 0) goto out; @@ -2858,8 +2843,8 @@ out: return ret; } -static struct orphan_dir_info * -add_orphan_dir_info(struct send_ctx *sctx, u64 dir_ino) +static struct orphan_dir_info *add_orphan_dir_info(struct send_ctx *sctx, + u64 dir_ino, u64 dir_gen) { struct rb_node **p = &sctx->orphan_dirs.rb_node; struct rb_node *parent = NULL; @@ -2868,20 +2853,23 @@ add_orphan_dir_info(struct send_ctx *sctx, u64 dir_ino) while (*p) { parent = *p; entry = rb_entry(parent, struct orphan_dir_info, node); - if (dir_ino < entry->ino) { + if (dir_ino < entry->ino) p = &(*p)->rb_left; - } else if (dir_ino > entry->ino) { + else if (dir_ino > entry->ino) p = &(*p)->rb_right; - } else { + else if (dir_gen < entry->gen) + p = &(*p)->rb_left; + else if (dir_gen > entry->gen) + p = &(*p)->rb_right; + else return entry; - } } odi = kmalloc(sizeof(*odi), GFP_KERNEL); if (!odi) return ERR_PTR(-ENOMEM); odi->ino = dir_ino; - odi->gen = 0; + odi->gen = dir_gen; odi->last_dir_index_offset = 0; rb_link_node(&odi->node, parent, p); @@ -2889,8 +2877,8 @@ add_orphan_dir_info(struct send_ctx *sctx, u64 dir_ino) return odi; } -static struct orphan_dir_info * -get_orphan_dir_info(struct send_ctx *sctx, u64 dir_ino) +static struct orphan_dir_info *get_orphan_dir_info(struct send_ctx *sctx, + u64 dir_ino, u64 gen) { struct rb_node *n = sctx->orphan_dirs.rb_node; struct orphan_dir_info *entry; @@ -2901,15 +2889,19 @@ get_orphan_dir_info(struct send_ctx *sctx, u64 dir_ino) n = n->rb_left; else if (dir_ino > entry->ino) n = n->rb_right; + else if (gen < entry->gen) + n = n->rb_left; + else if (gen > entry->gen) + n = n->rb_right; else return entry; } return NULL; } -static int is_waiting_for_rm(struct send_ctx *sctx, u64 dir_ino) +static int is_waiting_for_rm(struct send_ctx *sctx, u64 dir_ino, u64 gen) { - struct orphan_dir_info *odi = get_orphan_dir_info(sctx, dir_ino); + struct orphan_dir_info *odi = get_orphan_dir_info(sctx, dir_ino, gen); return odi != NULL; } @@ -2954,7 +2946,7 @@ static int can_rmdir(struct send_ctx *sctx, u64 dir, u64 dir_gen, key.type = BTRFS_DIR_INDEX_KEY; key.offset = 0; - odi = get_orphan_dir_info(sctx, dir); + odi = get_orphan_dir_info(sctx, dir, dir_gen); if (odi) key.offset = odi->last_dir_index_offset; @@ -2985,7 +2977,7 @@ static int can_rmdir(struct send_ctx *sctx, u64 dir, u64 dir_gen, dm = get_waiting_dir_move(sctx, loc.objectid); if (dm) { - odi = add_orphan_dir_info(sctx, dir); + odi = add_orphan_dir_info(sctx, dir, dir_gen); if (IS_ERR(odi)) { ret = PTR_ERR(odi); goto out; @@ -2993,12 +2985,13 @@ static int can_rmdir(struct send_ctx *sctx, u64 dir, u64 dir_gen, odi->gen = dir_gen; odi->last_dir_index_offset = found_key.offset; dm->rmdir_ino = dir; + dm->rmdir_gen = dir_gen; ret = 0; goto out; } if (loc.objectid > send_progress) { - odi = add_orphan_dir_info(sctx, dir); + odi = add_orphan_dir_info(sctx, dir, dir_gen); if (IS_ERR(odi)) { ret = PTR_ERR(odi); goto out; @@ -3038,6 +3031,7 @@ static int add_waiting_dir_move(struct send_ctx *sctx, u64 ino, bool orphanized) return -ENOMEM; dm->ino = ino; dm->rmdir_ino = 0; + dm->rmdir_gen = 0; dm->orphanized = orphanized; while (*p) { @@ -3183,7 +3177,7 @@ static int path_loop(struct send_ctx *sctx, struct fs_path *name, while (ino != BTRFS_FIRST_FREE_OBJECTID) { fs_path_reset(name); - if (is_waiting_for_rm(sctx, ino)) + if (is_waiting_for_rm(sctx, ino, gen)) break; if (is_waiting_for_move(sctx, ino)) { if (*ancestor_ino == 0) @@ -3223,6 +3217,7 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm) u64 parent_ino, parent_gen; struct waiting_dir_move *dm = NULL; u64 rmdir_ino = 0; + u64 rmdir_gen; u64 ancestor; bool is_orphan; int ret; @@ -3237,6 +3232,7 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm) dm = get_waiting_dir_move(sctx, pm->ino); ASSERT(dm); rmdir_ino = dm->rmdir_ino; + rmdir_gen = dm->rmdir_gen; is_orphan = dm->orphanized; free_waiting_dir_move(sctx, dm); @@ -3273,6 +3269,7 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm) dm = get_waiting_dir_move(sctx, pm->ino); ASSERT(dm); dm->rmdir_ino = rmdir_ino; + dm->rmdir_gen = rmdir_gen; } goto out; } @@ -3291,7 +3288,7 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm) struct orphan_dir_info *odi; u64 gen; - odi = get_orphan_dir_info(sctx, rmdir_ino); + odi = get_orphan_dir_info(sctx, rmdir_ino, rmdir_gen); if (!odi) { /* already deleted */ goto finish; @@ -5499,6 +5496,21 @@ static int clone_range(struct send_ctx *sctx, break; offset += clone_len; clone_root->offset += clone_len; + + /* + * If we are cloning from the file we are currently processing, + * and using the send root as the clone root, we must stop once + * the current clone offset reaches the current eof of the file + * at the receiver, otherwise we would issue an invalid clone + * operation (source range going beyond eof) and cause the + * receiver to fail. So if we reach the current eof, bail out + * and fallback to a regular write. + */ + if (clone_root->root == sctx->send_root && + clone_root->ino == sctx->cur_ino && + clone_root->offset >= sctx->cur_inode_next_write_offset) + break; + data_offset += clone_len; next: path->slots[0]++; @@ -6579,10 +6591,9 @@ static int changed_cb(struct btrfs_path *left_path, struct btrfs_path *right_path, struct btrfs_key *key, enum btrfs_compare_tree_result result, - void *ctx) + struct send_ctx *sctx) { int ret = 0; - struct send_ctx *sctx = ctx; if (result == BTRFS_COMPARE_TREE_SAME) { if (key->type == BTRFS_INODE_REF_KEY || @@ -6787,7 +6798,7 @@ static int tree_compare_item(struct btrfs_path *left_path, * If it detects a change, it aborts immediately. */ static int btrfs_compare_trees(struct btrfs_root *left_root, - struct btrfs_root *right_root, void *ctx) + struct btrfs_root *right_root, struct send_ctx *sctx) { struct btrfs_fs_info *fs_info = left_root->fs_info; int ret; @@ -6939,7 +6950,7 @@ static int btrfs_compare_trees(struct btrfs_root *left_root, ret = changed_cb(left_path, right_path, &right_key, BTRFS_COMPARE_TREE_DELETED, - ctx); + sctx); if (ret < 0) goto out; } @@ -6950,7 +6961,7 @@ static int btrfs_compare_trees(struct btrfs_root *left_root, ret = changed_cb(left_path, right_path, &left_key, BTRFS_COMPARE_TREE_NEW, - ctx); + sctx); if (ret < 0) goto out; } @@ -6964,7 +6975,7 @@ static int btrfs_compare_trees(struct btrfs_root *left_root, ret = changed_cb(left_path, right_path, &left_key, BTRFS_COMPARE_TREE_NEW, - ctx); + sctx); if (ret < 0) goto out; advance_left = ADVANCE; @@ -6972,7 +6983,7 @@ static int btrfs_compare_trees(struct btrfs_root *left_root, ret = changed_cb(left_path, right_path, &right_key, BTRFS_COMPARE_TREE_DELETED, - ctx); + sctx); if (ret < 0) goto out; advance_right = ADVANCE; @@ -6987,7 +6998,7 @@ static int btrfs_compare_trees(struct btrfs_root *left_root, else result = BTRFS_COMPARE_TREE_SAME; ret = changed_cb(left_path, right_path, - &left_key, result, ctx); + &left_key, result, sctx); if (ret < 0) goto out; advance_left = ADVANCE; diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c index 64099565ab8f..2da6177f4b0b 100644 --- a/fs/btrfs/space-info.c +++ b/fs/btrfs/space-info.c @@ -140,6 +140,12 @@ * be freed, plus any delayed work we may not have gotten rid of in the case * of metadata. * + * FORCE_COMMIT_TRANS + * For use by the preemptive flusher. We use this to bypass the ticketing + * checks in may_commit_transaction, as we have more information about the + * overall state of the system and may want to commit the transaction ahead + * of actual ENOSPC conditions. + * * OVERCOMMIT * * Because we hold so many reservations for metadata we will allow you to @@ -163,6 +169,7 @@ u64 __pure btrfs_space_info_used(struct btrfs_space_info *s_info, ASSERT(s_info); return s_info->bytes_used + s_info->bytes_reserved + s_info->bytes_pinned + s_info->bytes_readonly + + s_info->bytes_zone_unusable + (may_use_included ? s_info->bytes_may_use : 0); } @@ -206,6 +213,7 @@ static int create_space_info(struct btrfs_fs_info *info, u64 flags) INIT_LIST_HEAD(&space_info->ro_bgs); INIT_LIST_HEAD(&space_info->tickets); INIT_LIST_HEAD(&space_info->priority_tickets); + space_info->clamp = 1; ret = btrfs_sysfs_add_space_info_type(info, space_info); if (ret) @@ -257,7 +265,7 @@ out: void btrfs_update_space_info(struct btrfs_fs_info *info, u64 flags, u64 total_bytes, u64 bytes_used, - u64 bytes_readonly, + u64 bytes_readonly, u64 bytes_zone_unusable, struct btrfs_space_info **space_info) { struct btrfs_space_info *found; @@ -273,6 +281,7 @@ void btrfs_update_space_info(struct btrfs_fs_info *info, u64 flags, found->bytes_used += bytes_used; found->disk_used += bytes_used * factor; found->bytes_readonly += bytes_readonly; + found->bytes_zone_unusable += bytes_zone_unusable; if (total_bytes > 0) found->full = 0; btrfs_try_granting_tickets(info, found); @@ -422,10 +431,10 @@ static void __btrfs_dump_space_info(struct btrfs_fs_info *fs_info, info->total_bytes - btrfs_space_info_used(info, true), info->full ? "" : "not "); btrfs_info(fs_info, - "space_info total=%llu, used=%llu, pinned=%llu, reserved=%llu, may_use=%llu, readonly=%llu", + "space_info total=%llu, used=%llu, pinned=%llu, reserved=%llu, may_use=%llu, readonly=%llu zone_unusable=%llu", info->total_bytes, info->bytes_used, info->bytes_pinned, info->bytes_reserved, info->bytes_may_use, - info->bytes_readonly); + info->bytes_readonly, info->bytes_zone_unusable); DUMP_BLOCK_RSV(fs_info, global_block_rsv); DUMP_BLOCK_RSV(fs_info, trans_block_rsv); @@ -454,9 +463,10 @@ again: list_for_each_entry(cache, &info->block_groups[index], list) { spin_lock(&cache->lock); btrfs_info(fs_info, - "block group %llu has %llu bytes, %llu used %llu pinned %llu reserved %s", + "block group %llu has %llu bytes, %llu used %llu pinned %llu reserved %llu zone_unusable %s", cache->start, cache->length, cache->used, cache->pinned, - cache->reserved, cache->ro ? "[readonly]" : ""); + cache->reserved, cache->zone_unusable, + cache->ro ? "[readonly]" : ""); spin_unlock(&cache->lock); btrfs_dump_free_space(cache, bytes); } @@ -489,7 +499,7 @@ static void shrink_delalloc(struct btrfs_fs_info *fs_info, { struct btrfs_trans_handle *trans; u64 delalloc_bytes; - u64 dio_bytes; + u64 ordered_bytes; u64 items; long time_left; int loops; @@ -513,26 +523,24 @@ static void shrink_delalloc(struct btrfs_fs_info *fs_info, delalloc_bytes = percpu_counter_sum_positive( &fs_info->delalloc_bytes); - dio_bytes = percpu_counter_sum_positive(&fs_info->dio_bytes); - if (delalloc_bytes == 0 && dio_bytes == 0) { - if (trans) - return; - if (wait_ordered) - btrfs_wait_ordered_roots(fs_info, items, 0, (u64)-1); + ordered_bytes = percpu_counter_sum_positive(&fs_info->ordered_bytes); + if (delalloc_bytes == 0 && ordered_bytes == 0) return; - } /* * If we are doing more ordered than delalloc we need to just wait on * ordered extents, otherwise we'll waste time trying to flush delalloc * that likely won't give us the space back we need. */ - if (dio_bytes > delalloc_bytes) + if (ordered_bytes > delalloc_bytes) wait_ordered = true; loops = 0; - while ((delalloc_bytes || dio_bytes) && loops < 3) { - btrfs_start_delalloc_roots(fs_info, items); + while ((delalloc_bytes || ordered_bytes) && loops < 3) { + u64 temp = min(delalloc_bytes, to_reclaim) >> PAGE_SHIFT; + long nr_pages = min_t(u64, temp, LONG_MAX); + + btrfs_start_delalloc_roots(fs_info, nr_pages, true); loops++; if (wait_ordered && !trans) { @@ -553,15 +561,16 @@ static void shrink_delalloc(struct btrfs_fs_info *fs_info, delalloc_bytes = percpu_counter_sum_positive( &fs_info->delalloc_bytes); - dio_bytes = percpu_counter_sum_positive(&fs_info->dio_bytes); + ordered_bytes = percpu_counter_sum_positive( + &fs_info->ordered_bytes); } } /** - * maybe_commit_transaction - possibly commit the transaction if its ok to - * @root - the root we're allocating for - * @bytes - the number of bytes we want to reserve - * @force - force the commit + * Possibly commit the transaction if its ok to + * + * @fs_info: the filesystem + * @space_info: space_info we are checking for commit, either data or metadata * * This will check to make sure that committing the transaction will actually * get us somewhere and then commit the transaction if it does. Otherwise it @@ -667,7 +676,7 @@ enospc: */ static void flush_space(struct btrfs_fs_info *fs_info, struct btrfs_space_info *space_info, u64 num_bytes, - int state) + enum btrfs_flush_state state, bool for_preempt) { struct btrfs_root *root = fs_info->extent_root; struct btrfs_trans_handle *trans; @@ -736,13 +745,21 @@ static void flush_space(struct btrfs_fs_info *fs_info, case COMMIT_TRANS: ret = may_commit_transaction(fs_info, space_info); break; + case FORCE_COMMIT_TRANS: + trans = btrfs_join_transaction(root); + if (IS_ERR(trans)) { + ret = PTR_ERR(trans); + break; + } + ret = btrfs_commit_transaction(trans); + break; default: ret = -ENOSPC; break; } trace_btrfs_flush_space(fs_info, space_info->flags, num_bytes, state, - ret); + ret, for_preempt); return; } @@ -752,7 +769,6 @@ btrfs_calc_reclaim_metadata_size(struct btrfs_fs_info *fs_info, { u64 used; u64 avail; - u64 expected; u64 to_reclaim = space_info->reclaim_size; lockdep_assert_held(&space_info->lock); @@ -770,43 +786,88 @@ btrfs_calc_reclaim_metadata_size(struct btrfs_fs_info *fs_info, if (space_info->total_bytes + avail < used) to_reclaim += used - (space_info->total_bytes + avail); - if (to_reclaim) - return to_reclaim; - - to_reclaim = min_t(u64, num_online_cpus() * SZ_1M, SZ_16M); - if (btrfs_can_overcommit(fs_info, space_info, to_reclaim, - BTRFS_RESERVE_FLUSH_ALL)) - return 0; - - used = btrfs_space_info_used(space_info, true); - - if (btrfs_can_overcommit(fs_info, space_info, SZ_1M, - BTRFS_RESERVE_FLUSH_ALL)) - expected = div_factor_fine(space_info->total_bytes, 95); - else - expected = div_factor_fine(space_info->total_bytes, 90); - - if (used > expected) - to_reclaim = used - expected; - else - to_reclaim = 0; - to_reclaim = min(to_reclaim, space_info->bytes_may_use + - space_info->bytes_reserved); return to_reclaim; } -static inline int need_do_async_reclaim(struct btrfs_fs_info *fs_info, - struct btrfs_space_info *space_info, - u64 used) +static bool need_preemptive_reclaim(struct btrfs_fs_info *fs_info, + struct btrfs_space_info *space_info) { + u64 ordered, delalloc; u64 thresh = div_factor_fine(space_info->total_bytes, 98); + u64 used; /* If we're just plain full then async reclaim just slows us down. */ if ((space_info->bytes_used + space_info->bytes_reserved) >= thresh) - return 0; + return false; - if (!btrfs_calc_reclaim_metadata_size(fs_info, space_info)) - return 0; + /* + * We have tickets queued, bail so we don't compete with the async + * flushers. + */ + if (space_info->reclaim_size) + return false; + + /* + * If we have over half of the free space occupied by reservations or + * pinned then we want to start flushing. + * + * We do not do the traditional thing here, which is to say + * + * if (used >= ((total_bytes + avail) / 2)) + * return 1; + * + * because this doesn't quite work how we want. If we had more than 50% + * of the space_info used by bytes_used and we had 0 available we'd just + * constantly run the background flusher. Instead we want it to kick in + * if our reclaimable space exceeds our clamped free space. + * + * Our clamping range is 2^1 -> 2^8. Practically speaking that means + * the following: + * + * Amount of RAM Minimum threshold Maximum threshold + * + * 256GiB 1GiB 128GiB + * 128GiB 512MiB 64GiB + * 64GiB 256MiB 32GiB + * 32GiB 128MiB 16GiB + * 16GiB 64MiB 8GiB + * + * These are the range our thresholds will fall in, corresponding to how + * much delalloc we need for the background flusher to kick in. + */ + + thresh = calc_available_free_space(fs_info, space_info, + BTRFS_RESERVE_FLUSH_ALL); + thresh += (space_info->total_bytes - space_info->bytes_used - + space_info->bytes_reserved - space_info->bytes_readonly); + thresh >>= space_info->clamp; + + used = space_info->bytes_pinned; + + /* + * If we have more ordered bytes than delalloc bytes then we're either + * doing a lot of DIO, or we simply don't have a lot of delalloc waiting + * around. Preemptive flushing is only useful in that it can free up + * space before tickets need to wait for things to finish. In the case + * of ordered extents, preemptively waiting on ordered extents gets us + * nothing, if our reservations are tied up in ordered extents we'll + * simply have to slow down writers by forcing them to wait on ordered + * extents. + * + * In the case that ordered is larger than delalloc, only include the + * block reserves that we would actually be able to directly reclaim + * from. In this case if we're heavy on metadata operations this will + * clearly be heavy enough to warrant preemptive flushing. In the case + * of heavy DIO or ordered reservations, preemptive flushing will just + * waste time and cause us to slow down. + */ + ordered = percpu_counter_sum_positive(&fs_info->ordered_bytes); + delalloc = percpu_counter_sum_positive(&fs_info->delalloc_bytes); + if (ordered >= delalloc) + used += fs_info->delayed_refs_rsv.reserved + + fs_info->delayed_block_rsv.reserved; + else + used += space_info->bytes_may_use; return (used >= thresh && !btrfs_fs_closing(fs_info) && !test_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state)); @@ -920,7 +981,7 @@ static void btrfs_async_reclaim_metadata_space(struct work_struct *work) struct btrfs_fs_info *fs_info; struct btrfs_space_info *space_info; u64 to_reclaim; - int flush_state; + enum btrfs_flush_state flush_state; int commit_cycles = 0; u64 last_tickets_id; @@ -939,7 +1000,7 @@ static void btrfs_async_reclaim_metadata_space(struct work_struct *work) flush_state = FLUSH_DELAYED_ITEMS_NR; do { - flush_space(fs_info, space_info, to_reclaim, flush_state); + flush_space(fs_info, space_info, to_reclaim, flush_state, false); spin_lock(&space_info->lock); if (list_empty(&space_info->tickets)) { space_info->flush = 0; @@ -988,6 +1049,105 @@ static void btrfs_async_reclaim_metadata_space(struct work_struct *work) } /* + * This handles pre-flushing of metadata space before we get to the point that + * we need to start blocking threads on tickets. The logic here is different + * from the other flush paths because it doesn't rely on tickets to tell us how + * much we need to flush, instead it attempts to keep us below the 80% full + * watermark of space by flushing whichever reservation pool is currently the + * largest. + */ +static void btrfs_preempt_reclaim_metadata_space(struct work_struct *work) +{ + struct btrfs_fs_info *fs_info; + struct btrfs_space_info *space_info; + struct btrfs_block_rsv *delayed_block_rsv; + struct btrfs_block_rsv *delayed_refs_rsv; + struct btrfs_block_rsv *global_rsv; + struct btrfs_block_rsv *trans_rsv; + int loops = 0; + + fs_info = container_of(work, struct btrfs_fs_info, + preempt_reclaim_work); + space_info = btrfs_find_space_info(fs_info, BTRFS_BLOCK_GROUP_METADATA); + delayed_block_rsv = &fs_info->delayed_block_rsv; + delayed_refs_rsv = &fs_info->delayed_refs_rsv; + global_rsv = &fs_info->global_block_rsv; + trans_rsv = &fs_info->trans_block_rsv; + + spin_lock(&space_info->lock); + while (need_preemptive_reclaim(fs_info, space_info)) { + enum btrfs_flush_state flush; + u64 delalloc_size = 0; + u64 to_reclaim, block_rsv_size; + u64 global_rsv_size = global_rsv->reserved; + + loops++; + + /* + * We don't have a precise counter for the metadata being + * reserved for delalloc, so we'll approximate it by subtracting + * out the block rsv's space from the bytes_may_use. If that + * amount is higher than the individual reserves, then we can + * assume it's tied up in delalloc reservations. + */ + block_rsv_size = global_rsv_size + + delayed_block_rsv->reserved + + delayed_refs_rsv->reserved + + trans_rsv->reserved; + if (block_rsv_size < space_info->bytes_may_use) + delalloc_size = space_info->bytes_may_use - block_rsv_size; + spin_unlock(&space_info->lock); + + /* + * We don't want to include the global_rsv in our calculation, + * because that's space we can't touch. Subtract it from the + * block_rsv_size for the next checks. + */ + block_rsv_size -= global_rsv_size; + + /* + * We really want to avoid flushing delalloc too much, as it + * could result in poor allocation patterns, so only flush it if + * it's larger than the rest of the pools combined. + */ + if (delalloc_size > block_rsv_size) { + to_reclaim = delalloc_size; + flush = FLUSH_DELALLOC; + } else if (space_info->bytes_pinned > + (delayed_block_rsv->reserved + + delayed_refs_rsv->reserved)) { + to_reclaim = space_info->bytes_pinned; + flush = FORCE_COMMIT_TRANS; + } else if (delayed_block_rsv->reserved > + delayed_refs_rsv->reserved) { + to_reclaim = delayed_block_rsv->reserved; + flush = FLUSH_DELAYED_ITEMS_NR; + } else { + to_reclaim = delayed_refs_rsv->reserved; + flush = FLUSH_DELAYED_REFS_NR; + } + + /* + * We don't want to reclaim everything, just a portion, so scale + * down the to_reclaim by 1/4. If it takes us down to 0, + * reclaim 1 items worth. + */ + to_reclaim >>= 2; + if (!to_reclaim) + to_reclaim = btrfs_calc_insert_metadata_size(fs_info, 1); + flush_space(fs_info, space_info, to_reclaim, flush, true); + cond_resched(); + spin_lock(&space_info->lock); + } + + /* We only went through once, back off our clamping. */ + if (loops == 1 && !space_info->reclaim_size) + space_info->clamp = max(1, space_info->clamp - 1); + trace_btrfs_done_preemptive_reclaim(fs_info, space_info); + spin_unlock(&space_info->lock); +} + +/* * FLUSH_DELALLOC_WAIT: * Space is freed from flushing delalloc in one of two ways. * @@ -1052,7 +1212,7 @@ static void btrfs_async_reclaim_data_space(struct work_struct *work) struct btrfs_fs_info *fs_info; struct btrfs_space_info *space_info; u64 last_tickets_id; - int flush_state = 0; + enum btrfs_flush_state flush_state = 0; fs_info = container_of(work, struct btrfs_fs_info, async_data_reclaim_work); space_info = fs_info->data_sinfo; @@ -1067,7 +1227,7 @@ static void btrfs_async_reclaim_data_space(struct work_struct *work) spin_unlock(&space_info->lock); while (!space_info->full) { - flush_space(fs_info, space_info, U64_MAX, ALLOC_CHUNK_FORCE); + flush_space(fs_info, space_info, U64_MAX, ALLOC_CHUNK_FORCE, false); spin_lock(&space_info->lock); if (list_empty(&space_info->tickets)) { space_info->flush = 0; @@ -1080,7 +1240,7 @@ static void btrfs_async_reclaim_data_space(struct work_struct *work) while (flush_state < ARRAY_SIZE(data_flush_states)) { flush_space(fs_info, space_info, U64_MAX, - data_flush_states[flush_state]); + data_flush_states[flush_state], false); spin_lock(&space_info->lock); if (list_empty(&space_info->tickets)) { space_info->flush = 0; @@ -1113,6 +1273,8 @@ void btrfs_init_async_reclaim_work(struct btrfs_fs_info *fs_info) { INIT_WORK(&fs_info->async_reclaim_work, btrfs_async_reclaim_metadata_space); INIT_WORK(&fs_info->async_data_reclaim_work, btrfs_async_reclaim_data_space); + INIT_WORK(&fs_info->preempt_reclaim_work, + btrfs_preempt_reclaim_metadata_space); } static const enum btrfs_flush_state priority_flush_states[] = { @@ -1151,7 +1313,8 @@ static void priority_reclaim_metadata_space(struct btrfs_fs_info *fs_info, flush_state = 0; do { - flush_space(fs_info, space_info, to_reclaim, states[flush_state]); + flush_space(fs_info, space_info, to_reclaim, states[flush_state], + false); flush_state++; spin_lock(&space_info->lock); if (ticket->bytes == 0) { @@ -1167,7 +1330,7 @@ static void priority_reclaim_data_space(struct btrfs_fs_info *fs_info, struct reserve_ticket *ticket) { while (!space_info->full) { - flush_space(fs_info, space_info, U64_MAX, ALLOC_CHUNK_FORCE); + flush_space(fs_info, space_info, U64_MAX, ALLOC_CHUNK_FORCE, false); spin_lock(&space_info->lock); if (ticket->bytes == 0) { spin_unlock(&space_info->lock); @@ -1212,11 +1375,14 @@ static void wait_reserve_ticket(struct btrfs_fs_info *fs_info, } /** - * handle_reserve_ticket - do the appropriate flushing and waiting for a ticket - * @fs_info - the fs - * @space_info - the space_info for the reservation - * @ticket - the ticket for the reservation - * @flush - how much we can flush + * Do the appropriate flushing and waiting for a ticket + * + * @fs_info: the filesystem + * @space_info: space info for the reservation + * @ticket: ticket for the reservation + * @start_ns: timestamp when the reservation started + * @orig_bytes: amount of bytes originally reserved + * @flush: how much we can flush * * This does the work of figuring out how to flush for the ticket, waiting for * the reservation, and returning the appropriate error if there is one. @@ -1224,6 +1390,7 @@ static void wait_reserve_ticket(struct btrfs_fs_info *fs_info, static int handle_reserve_ticket(struct btrfs_fs_info *fs_info, struct btrfs_space_info *space_info, struct reserve_ticket *ticket, + u64 start_ns, u64 orig_bytes, enum btrfs_reserve_flush_enum flush) { int ret; @@ -1279,6 +1446,8 @@ static int handle_reserve_ticket(struct btrfs_fs_info *fs_info, * space wasn't reserved at all). */ ASSERT(!(ticket->bytes == 0 && ticket->error)); + trace_btrfs_reserve_ticket(fs_info, space_info->flags, orig_bytes, + start_ns, flush, ticket->error); return ret; } @@ -1292,12 +1461,31 @@ static inline bool is_normal_flushing(enum btrfs_reserve_flush_enum flush) (flush == BTRFS_RESERVE_FLUSH_ALL_STEAL); } +static inline void maybe_clamp_preempt(struct btrfs_fs_info *fs_info, + struct btrfs_space_info *space_info) +{ + u64 ordered = percpu_counter_sum_positive(&fs_info->ordered_bytes); + u64 delalloc = percpu_counter_sum_positive(&fs_info->delalloc_bytes); + + /* + * If we're heavy on ordered operations then clamping won't help us. We + * need to clamp specifically to keep up with dirty'ing buffered + * writers, because there's not a 1:1 correlation of writing delalloc + * and freeing space, like there is with flushing delayed refs or + * delayed nodes. If we're already more ordered than delalloc then + * we're keeping up, otherwise we aren't and should probably clamp. + */ + if (ordered < delalloc) + space_info->clamp = min(space_info->clamp + 1, 8); +} + /** - * reserve_metadata_bytes - try to reserve bytes from the block_rsv's space - * @root - the root we're allocating for - * @space_info - the space info we want to allocate from - * @orig_bytes - the number of bytes we want - * @flush - whether or not we can flush to make our reservation + * Try to reserve bytes from the block_rsv's space + * + * @fs_info: the filesystem + * @space_info: space info we want to allocate from + * @orig_bytes: number of bytes we want + * @flush: whether or not we can flush to make our reservation * * This will reserve orig_bytes number of bytes from the space info associated * with the block_rsv. If there is not enough space it will make an attempt to @@ -1312,6 +1500,7 @@ static int __reserve_bytes(struct btrfs_fs_info *fs_info, { struct work_struct *async_work; struct reserve_ticket ticket; + u64 start_ns = 0; u64 used; int ret = 0; bool pending_tickets; @@ -1364,6 +1553,9 @@ static int __reserve_bytes(struct btrfs_fs_info *fs_info, space_info->reclaim_size += ticket.bytes; init_waitqueue_head(&ticket.wait); ticket.steal = (flush == BTRFS_RESERVE_FLUSH_ALL_STEAL); + if (trace_btrfs_reserve_ticket_enabled()) + start_ns = ktime_get_ns(); + if (flush == BTRFS_RESERVE_FLUSH_ALL || flush == BTRFS_RESERVE_FLUSH_ALL_STEAL || flush == BTRFS_RESERVE_FLUSH_DATA) { @@ -1380,6 +1572,14 @@ static int __reserve_bytes(struct btrfs_fs_info *fs_info, list_add_tail(&ticket.list, &space_info->priority_tickets); } + + /* + * We were forced to add a reserve ticket, so our preemptive + * flushing is unable to keep up. Clamp down on the threshold + * for the preemptive flushing in order to keep up with the + * workload. + */ + maybe_clamp_preempt(fs_info, space_info); } else if (!ret && space_info->flags & BTRFS_BLOCK_GROUP_METADATA) { used += orig_bytes; /* @@ -1388,27 +1588,29 @@ static int __reserve_bytes(struct btrfs_fs_info *fs_info, * the async reclaim as we will panic. */ if (!test_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags) && - need_do_async_reclaim(fs_info, space_info, used) && - !work_busy(&fs_info->async_reclaim_work)) { + need_preemptive_reclaim(fs_info, space_info) && + !work_busy(&fs_info->preempt_reclaim_work)) { trace_btrfs_trigger_flush(fs_info, space_info->flags, orig_bytes, flush, "preempt"); queue_work(system_unbound_wq, - &fs_info->async_reclaim_work); + &fs_info->preempt_reclaim_work); } } spin_unlock(&space_info->lock); if (!ret || flush == BTRFS_RESERVE_NO_FLUSH) return ret; - return handle_reserve_ticket(fs_info, space_info, &ticket, flush); + return handle_reserve_ticket(fs_info, space_info, &ticket, start_ns, + orig_bytes, flush); } /** - * reserve_metadata_bytes - try to reserve bytes from the block_rsv's space - * @root - the root we're allocating for - * @block_rsv - the block_rsv we're allocating for - * @orig_bytes - the number of bytes we want - * @flush - whether or not we can flush to make our reservation + * Trye to reserve metadata bytes from the block_rsv's space + * + * @root: the root we're allocating for + * @block_rsv: block_rsv we're allocating for + * @orig_bytes: number of bytes we want + * @flush: whether or not we can flush to make our reservation * * This will reserve orig_bytes number of bytes from the space info associated * with the block_rsv. If there is not enough space it will make an attempt to @@ -1446,10 +1648,11 @@ int btrfs_reserve_metadata_bytes(struct btrfs_root *root, } /** - * btrfs_reserve_data_bytes - try to reserve data bytes for an allocation - * @fs_info - the filesystem - * @bytes - the number of bytes we need - * @flush - how we are allowed to flush + * Try to reserve data bytes for an allocation + * + * @fs_info: the filesystem + * @bytes: number of bytes we need + * @flush: how we are allowed to flush * * This will reserve bytes from the data space info. If there is not enough * space then we will attempt to flush space as specified by flush. diff --git a/fs/btrfs/space-info.h b/fs/btrfs/space-info.h index 5646393b928c..b1a8ffb03b3e 100644 --- a/fs/btrfs/space-info.h +++ b/fs/btrfs/space-info.h @@ -17,11 +17,17 @@ struct btrfs_space_info { u64 bytes_may_use; /* number of bytes that may be used for delalloc/allocations */ u64 bytes_readonly; /* total bytes that are read only */ + u64 bytes_zone_unusable; /* total bytes that are unusable until + resetting the device zone */ u64 max_extent_size; /* This will hold the maximum extent size of the space info if we had an ENOSPC in the allocator. */ + int clamp; /* Used to scale our threshold for preemptive + flushing. The value is >> clamp, so turns + out to be a 2^clamp divisor. */ + unsigned int full:1; /* indicates that we cannot allocate any more chunks for this space */ unsigned int chunk_alloc:1; /* set if we are allocating a chunk */ @@ -119,7 +125,7 @@ DECLARE_SPACE_INFO_UPDATE(bytes_pinned, "pinned"); int btrfs_init_space_info(struct btrfs_fs_info *fs_info); void btrfs_update_space_info(struct btrfs_fs_info *info, u64 flags, u64 total_bytes, u64 bytes_used, - u64 bytes_readonly, + u64 bytes_readonly, u64 bytes_zone_unusable, struct btrfs_space_info **space_info); struct btrfs_space_info *btrfs_find_space_info(struct btrfs_fs_info *info, u64 flags); @@ -152,4 +158,21 @@ static inline void btrfs_space_info_free_bytes_may_use( int btrfs_reserve_data_bytes(struct btrfs_fs_info *fs_info, u64 bytes, enum btrfs_reserve_flush_enum flush); +static inline void __btrfs_mod_total_bytes_pinned( + struct btrfs_space_info *space_info, + s64 mod) +{ + percpu_counter_add_batch(&space_info->total_bytes_pinned, mod, + BTRFS_TOTAL_BYTES_PINNED_BATCH); +} + +static inline void btrfs_mod_total_bytes_pinned(struct btrfs_fs_info *fs_info, + u64 flags, s64 mod) +{ + struct btrfs_space_info *space_info = btrfs_find_space_info(fs_info, flags); + + ASSERT(space_info); + __btrfs_mod_total_bytes_pinned(space_info, mod); +} + #endif /* BTRFS_SPACE_INFO_H */ diff --git a/fs/btrfs/subpage.c b/fs/btrfs/subpage.c new file mode 100644 index 000000000000..c69049e7daa9 --- /dev/null +++ b/fs/btrfs/subpage.c @@ -0,0 +1,278 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/slab.h> +#include "ctree.h" +#include "subpage.h" + +int btrfs_attach_subpage(const struct btrfs_fs_info *fs_info, + struct page *page, enum btrfs_subpage_type type) +{ + struct btrfs_subpage *subpage = NULL; + int ret; + + /* + * We have cases like a dummy extent buffer page, which is not mappped + * and doesn't need to be locked. + */ + if (page->mapping) + ASSERT(PageLocked(page)); + /* Either not subpage, or the page already has private attached */ + if (fs_info->sectorsize == PAGE_SIZE || PagePrivate(page)) + return 0; + + ret = btrfs_alloc_subpage(fs_info, &subpage, type); + if (ret < 0) + return ret; + attach_page_private(page, subpage); + return 0; +} + +void btrfs_detach_subpage(const struct btrfs_fs_info *fs_info, + struct page *page) +{ + struct btrfs_subpage *subpage; + + /* Either not subpage, or already detached */ + if (fs_info->sectorsize == PAGE_SIZE || !PagePrivate(page)) + return; + + subpage = (struct btrfs_subpage *)detach_page_private(page); + ASSERT(subpage); + btrfs_free_subpage(subpage); +} + +int btrfs_alloc_subpage(const struct btrfs_fs_info *fs_info, + struct btrfs_subpage **ret, + enum btrfs_subpage_type type) +{ + if (fs_info->sectorsize == PAGE_SIZE) + return 0; + + *ret = kzalloc(sizeof(struct btrfs_subpage), GFP_NOFS); + if (!*ret) + return -ENOMEM; + spin_lock_init(&(*ret)->lock); + if (type == BTRFS_SUBPAGE_METADATA) + atomic_set(&(*ret)->eb_refs, 0); + else + atomic_set(&(*ret)->readers, 0); + return 0; +} + +void btrfs_free_subpage(struct btrfs_subpage *subpage) +{ + kfree(subpage); +} + +/* + * Increase the eb_refs of current subpage. + * + * This is important for eb allocation, to prevent race with last eb freeing + * of the same page. + * With the eb_refs increased before the eb inserted into radix tree, + * detach_extent_buffer_page() won't detach the page private while we're still + * allocating the extent buffer. + */ +void btrfs_page_inc_eb_refs(const struct btrfs_fs_info *fs_info, + struct page *page) +{ + struct btrfs_subpage *subpage; + + if (fs_info->sectorsize == PAGE_SIZE) + return; + + ASSERT(PagePrivate(page) && page->mapping); + lockdep_assert_held(&page->mapping->private_lock); + + subpage = (struct btrfs_subpage *)page->private; + atomic_inc(&subpage->eb_refs); +} + +void btrfs_page_dec_eb_refs(const struct btrfs_fs_info *fs_info, + struct page *page) +{ + struct btrfs_subpage *subpage; + + if (fs_info->sectorsize == PAGE_SIZE) + return; + + ASSERT(PagePrivate(page) && page->mapping); + lockdep_assert_held(&page->mapping->private_lock); + + subpage = (struct btrfs_subpage *)page->private; + ASSERT(atomic_read(&subpage->eb_refs)); + atomic_dec(&subpage->eb_refs); +} + +static void btrfs_subpage_assert(const struct btrfs_fs_info *fs_info, + struct page *page, u64 start, u32 len) +{ + /* Basic checks */ + ASSERT(PagePrivate(page) && page->private); + ASSERT(IS_ALIGNED(start, fs_info->sectorsize) && + IS_ALIGNED(len, fs_info->sectorsize)); + /* + * The range check only works for mapped page, we can still have + * unmapped page like dummy extent buffer pages. + */ + if (page->mapping) + ASSERT(page_offset(page) <= start && + start + len <= page_offset(page) + PAGE_SIZE); +} + +void btrfs_subpage_start_reader(const struct btrfs_fs_info *fs_info, + struct page *page, u64 start, u32 len) +{ + struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private; + const int nbits = len >> fs_info->sectorsize_bits; + int ret; + + btrfs_subpage_assert(fs_info, page, start, len); + + ret = atomic_add_return(nbits, &subpage->readers); + ASSERT(ret == nbits); +} + +void btrfs_subpage_end_reader(const struct btrfs_fs_info *fs_info, + struct page *page, u64 start, u32 len) +{ + struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private; + const int nbits = len >> fs_info->sectorsize_bits; + + btrfs_subpage_assert(fs_info, page, start, len); + ASSERT(atomic_read(&subpage->readers) >= nbits); + if (atomic_sub_and_test(nbits, &subpage->readers)) + unlock_page(page); +} + +/* + * Convert the [start, start + len) range into a u16 bitmap + * + * For example: if start == page_offset() + 16K, len = 16K, we get 0x00f0. + */ +static u16 btrfs_subpage_calc_bitmap(const struct btrfs_fs_info *fs_info, + struct page *page, u64 start, u32 len) +{ + const int bit_start = offset_in_page(start) >> fs_info->sectorsize_bits; + const int nbits = len >> fs_info->sectorsize_bits; + + btrfs_subpage_assert(fs_info, page, start, len); + + /* + * Here nbits can be 16, thus can go beyond u16 range. We make the + * first left shift to be calculate in unsigned long (at least u32), + * then truncate the result to u16. + */ + return (u16)(((1UL << nbits) - 1) << bit_start); +} + +void btrfs_subpage_set_uptodate(const struct btrfs_fs_info *fs_info, + struct page *page, u64 start, u32 len) +{ + struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private; + const u16 tmp = btrfs_subpage_calc_bitmap(fs_info, page, start, len); + unsigned long flags; + + spin_lock_irqsave(&subpage->lock, flags); + subpage->uptodate_bitmap |= tmp; + if (subpage->uptodate_bitmap == U16_MAX) + SetPageUptodate(page); + spin_unlock_irqrestore(&subpage->lock, flags); +} + +void btrfs_subpage_clear_uptodate(const struct btrfs_fs_info *fs_info, + struct page *page, u64 start, u32 len) +{ + struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private; + const u16 tmp = btrfs_subpage_calc_bitmap(fs_info, page, start, len); + unsigned long flags; + + spin_lock_irqsave(&subpage->lock, flags); + subpage->uptodate_bitmap &= ~tmp; + ClearPageUptodate(page); + spin_unlock_irqrestore(&subpage->lock, flags); +} + +void btrfs_subpage_set_error(const struct btrfs_fs_info *fs_info, + struct page *page, u64 start, u32 len) +{ + struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private; + const u16 tmp = btrfs_subpage_calc_bitmap(fs_info, page, start, len); + unsigned long flags; + + spin_lock_irqsave(&subpage->lock, flags); + subpage->error_bitmap |= tmp; + SetPageError(page); + spin_unlock_irqrestore(&subpage->lock, flags); +} + +void btrfs_subpage_clear_error(const struct btrfs_fs_info *fs_info, + struct page *page, u64 start, u32 len) +{ + struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private; + const u16 tmp = btrfs_subpage_calc_bitmap(fs_info, page, start, len); + unsigned long flags; + + spin_lock_irqsave(&subpage->lock, flags); + subpage->error_bitmap &= ~tmp; + if (subpage->error_bitmap == 0) + ClearPageError(page); + spin_unlock_irqrestore(&subpage->lock, flags); +} + +/* + * Unlike set/clear which is dependent on each page status, for test all bits + * are tested in the same way. + */ +#define IMPLEMENT_BTRFS_SUBPAGE_TEST_OP(name) \ +bool btrfs_subpage_test_##name(const struct btrfs_fs_info *fs_info, \ + struct page *page, u64 start, u32 len) \ +{ \ + struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private; \ + const u16 tmp = btrfs_subpage_calc_bitmap(fs_info, page, start, len); \ + unsigned long flags; \ + bool ret; \ + \ + spin_lock_irqsave(&subpage->lock, flags); \ + ret = ((subpage->name##_bitmap & tmp) == tmp); \ + spin_unlock_irqrestore(&subpage->lock, flags); \ + return ret; \ +} +IMPLEMENT_BTRFS_SUBPAGE_TEST_OP(uptodate); +IMPLEMENT_BTRFS_SUBPAGE_TEST_OP(error); + +/* + * Note that, in selftests (extent-io-tests), we can have empty fs_info passed + * in. We only test sectorsize == PAGE_SIZE cases so far, thus we can fall + * back to regular sectorsize branch. + */ +#define IMPLEMENT_BTRFS_PAGE_OPS(name, set_page_func, clear_page_func, \ + test_page_func) \ +void btrfs_page_set_##name(const struct btrfs_fs_info *fs_info, \ + struct page *page, u64 start, u32 len) \ +{ \ + if (unlikely(!fs_info) || fs_info->sectorsize == PAGE_SIZE) { \ + set_page_func(page); \ + return; \ + } \ + btrfs_subpage_set_##name(fs_info, page, start, len); \ +} \ +void btrfs_page_clear_##name(const struct btrfs_fs_info *fs_info, \ + struct page *page, u64 start, u32 len) \ +{ \ + if (unlikely(!fs_info) || fs_info->sectorsize == PAGE_SIZE) { \ + clear_page_func(page); \ + return; \ + } \ + btrfs_subpage_clear_##name(fs_info, page, start, len); \ +} \ +bool btrfs_page_test_##name(const struct btrfs_fs_info *fs_info, \ + struct page *page, u64 start, u32 len) \ +{ \ + if (unlikely(!fs_info) || fs_info->sectorsize == PAGE_SIZE) \ + return test_page_func(page); \ + return btrfs_subpage_test_##name(fs_info, page, start, len); \ +} +IMPLEMENT_BTRFS_PAGE_OPS(uptodate, SetPageUptodate, ClearPageUptodate, + PageUptodate); +IMPLEMENT_BTRFS_PAGE_OPS(error, SetPageError, ClearPageError, PageError); diff --git a/fs/btrfs/subpage.h b/fs/btrfs/subpage.h new file mode 100644 index 000000000000..b86a4881475d --- /dev/null +++ b/fs/btrfs/subpage.h @@ -0,0 +1,91 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef BTRFS_SUBPAGE_H +#define BTRFS_SUBPAGE_H + +#include <linux/spinlock.h> + +/* + * Maximum page size we support is 64K, minimum sector size is 4K, u16 bitmap + * is sufficient. Regular bitmap_* is not used due to size reasons. + */ +#define BTRFS_SUBPAGE_BITMAP_SIZE 16 + +/* + * Structure to trace status of each sector inside a page, attached to + * page::private for both data and metadata inodes. + */ +struct btrfs_subpage { + /* Common members for both data and metadata pages */ + spinlock_t lock; + u16 uptodate_bitmap; + u16 error_bitmap; + union { + /* + * Structures only used by metadata + * + * @eb_refs should only be operated under private_lock, as it + * manages whether the subpage can be detached. + */ + atomic_t eb_refs; + /* Structures only used by data */ + struct { + atomic_t readers; + }; + }; +}; + +enum btrfs_subpage_type { + BTRFS_SUBPAGE_METADATA, + BTRFS_SUBPAGE_DATA, +}; + +int btrfs_attach_subpage(const struct btrfs_fs_info *fs_info, + struct page *page, enum btrfs_subpage_type type); +void btrfs_detach_subpage(const struct btrfs_fs_info *fs_info, + struct page *page); + +/* Allocate additional data where page represents more than one sector */ +int btrfs_alloc_subpage(const struct btrfs_fs_info *fs_info, + struct btrfs_subpage **ret, + enum btrfs_subpage_type type); +void btrfs_free_subpage(struct btrfs_subpage *subpage); + +void btrfs_page_inc_eb_refs(const struct btrfs_fs_info *fs_info, + struct page *page); +void btrfs_page_dec_eb_refs(const struct btrfs_fs_info *fs_info, + struct page *page); + +void btrfs_subpage_start_reader(const struct btrfs_fs_info *fs_info, + struct page *page, u64 start, u32 len); +void btrfs_subpage_end_reader(const struct btrfs_fs_info *fs_info, + struct page *page, u64 start, u32 len); + +/* + * Template for subpage related operations. + * + * btrfs_subpage_*() are for call sites where the page has subpage attached and + * the range is ensured to be inside the page. + * + * btrfs_page_*() are for call sites where the page can either be subpage + * specific or regular page. The function will handle both cases. + * But the range still needs to be inside the page. + */ +#define DECLARE_BTRFS_SUBPAGE_OPS(name) \ +void btrfs_subpage_set_##name(const struct btrfs_fs_info *fs_info, \ + struct page *page, u64 start, u32 len); \ +void btrfs_subpage_clear_##name(const struct btrfs_fs_info *fs_info, \ + struct page *page, u64 start, u32 len); \ +bool btrfs_subpage_test_##name(const struct btrfs_fs_info *fs_info, \ + struct page *page, u64 start, u32 len); \ +void btrfs_page_set_##name(const struct btrfs_fs_info *fs_info, \ + struct page *page, u64 start, u32 len); \ +void btrfs_page_clear_##name(const struct btrfs_fs_info *fs_info, \ + struct page *page, u64 start, u32 len); \ +bool btrfs_page_test_##name(const struct btrfs_fs_info *fs_info, \ + struct page *page, u64 start, u32 len); + +DECLARE_BTRFS_SUBPAGE_OPS(uptodate); +DECLARE_BTRFS_SUBPAGE_OPS(error); + +#endif diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 022f20810089..f8435641b912 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -48,7 +48,6 @@ #include "tests/btrfs-tests.h" #include "block-group.h" #include "discard.h" - #include "qgroup.h" #define CREATE_TRACE_POINTS #include <trace/events/btrfs.h> @@ -175,7 +174,7 @@ void __btrfs_handle_fs_error(struct btrfs_fs_info *fs_info, const char *function btrfs_discard_stop(fs_info); /* btrfs handle error by forcing the filesystem readonly */ - sb->s_flags |= SB_RDONLY; + btrfs_set_sb_rdonly(sb); btrfs_info(fs_info, "forced readonly"); /* * Note that a running device replace operation is not canceled here @@ -1953,7 +1952,7 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) /* avoid complains from lockdep et al. */ up(&fs_info->uuid_tree_rescan_sem); - sb->s_flags |= SB_RDONLY; + btrfs_set_sb_rdonly(sb); /* * Setting SB_RDONLY will put the cleaner thread to @@ -1964,10 +1963,42 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) */ btrfs_delete_unused_bgs(fs_info); + /* + * The cleaner task could be already running before we set the + * flag BTRFS_FS_STATE_RO (and SB_RDONLY in the superblock). + * We must make sure that after we finish the remount, i.e. after + * we call btrfs_commit_super(), the cleaner can no longer start + * a transaction - either because it was dropping a dead root, + * running delayed iputs or deleting an unused block group (the + * cleaner picked a block group from the list of unused block + * groups before we were able to in the previous call to + * btrfs_delete_unused_bgs()). + */ + wait_on_bit(&fs_info->flags, BTRFS_FS_CLEANER_RUNNING, + TASK_UNINTERRUPTIBLE); + + /* + * We've set the superblock to RO mode, so we might have made + * the cleaner task sleep without running all pending delayed + * iputs. Go through all the delayed iputs here, so that if an + * unmount happens without remounting RW we don't end up at + * finishing close_ctree() with a non-empty list of delayed + * iputs. + */ + btrfs_run_delayed_iputs(fs_info); + btrfs_dev_replace_suspend_for_unmount(fs_info); btrfs_scrub_cancel(fs_info); btrfs_pause_balance(fs_info); + /* + * Pause the qgroup rescan worker if it is running. We don't want + * it to be still running after we are in RO mode, as after that, + * by the time we unmount, it might have left a transaction open, + * so we would leak the transaction and/or crash. + */ + btrfs_qgroup_wait_for_completion(fs_info, false); + ret = btrfs_commit_super(fs_info); if (ret) goto restore; @@ -1996,6 +2027,13 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) ret = -EINVAL; goto restore; } + if (fs_info->sectorsize < PAGE_SIZE) { + btrfs_warn(fs_info, + "read-write mount is not yet allowed for sectorsize %u page size %lu", + fs_info->sectorsize, PAGE_SIZE); + ret = -EINVAL; + goto restore; + } /* * NOTE: when remounting with a change that does writes, don't @@ -2006,7 +2044,7 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) if (ret) goto restore; - sb->s_flags &= ~SB_RDONLY; + btrfs_clear_sb_rdonly(sb); set_bit(BTRFS_FS_OPEN, &fs_info->flags); } @@ -2028,6 +2066,8 @@ restore: /* We've hit an error - don't reset SB_RDONLY */ if (sb_rdonly(sb)) old_flags |= SB_RDONLY; + if (!(old_flags & SB_RDONLY)) + clear_bit(BTRFS_FS_STATE_RO, &fs_info->fs_state); sb->s_flags = old_flags; fs_info->mount_opt = old_opts; fs_info->compress_type = old_compress_type; diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index 19b9fffa2c9c..6eb1c50fa98c 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -666,6 +666,7 @@ SPACE_INFO_ATTR(bytes_pinned); SPACE_INFO_ATTR(bytes_reserved); SPACE_INFO_ATTR(bytes_may_use); SPACE_INFO_ATTR(bytes_readonly); +SPACE_INFO_ATTR(bytes_zone_unusable); SPACE_INFO_ATTR(disk_used); SPACE_INFO_ATTR(disk_total); BTRFS_ATTR(space_info, total_bytes_pinned, @@ -679,6 +680,7 @@ static struct attribute *space_info_attrs[] = { BTRFS_ATTR_PTR(space_info, bytes_reserved), BTRFS_ATTR_PTR(space_info, bytes_may_use), BTRFS_ATTR_PTR(space_info, bytes_readonly), + BTRFS_ATTR_PTR(space_info, bytes_zone_unusable), BTRFS_ATTR_PTR(space_info, disk_used), BTRFS_ATTR_PTR(space_info, disk_total), BTRFS_ATTR_PTR(space_info, total_bytes_pinned), diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c index 8ca334d554af..6bd97bd4cb37 100644 --- a/fs/btrfs/tests/btrfs-tests.c +++ b/fs/btrfs/tests/btrfs-tests.c @@ -55,8 +55,14 @@ struct inode *btrfs_new_test_inode(void) struct inode *inode; inode = new_inode(test_mnt->mnt_sb); - if (inode) - inode_init_owner(inode, NULL, S_IFREG); + if (!inode) + return NULL; + + inode->i_mode = S_IFREG; + BTRFS_I(inode)->location.type = BTRFS_INODE_ITEM_KEY; + BTRFS_I(inode)->location.objectid = BTRFS_FIRST_FREE_OBJECTID; + BTRFS_I(inode)->location.offset = 0; + inode_init_owner(inode, NULL, S_IFREG); return inode; } diff --git a/fs/btrfs/tests/extent-map-tests.c b/fs/btrfs/tests/extent-map-tests.c index 57379e96ccc9..c0aefe6dee0b 100644 --- a/fs/btrfs/tests/extent-map-tests.c +++ b/fs/btrfs/tests/extent-map-tests.c @@ -507,7 +507,7 @@ static int test_rmap_block(struct btrfs_fs_info *fs_info, goto out_free; } - ret = btrfs_rmap_block(fs_info, em->start, btrfs_sb_offset(1), + ret = btrfs_rmap_block(fs_info, em->start, NULL, btrfs_sb_offset(1), &logical, &out_ndaddrs, &out_stripe_len); if (ret || (out_ndaddrs == 0 && test->expected_mapped_addr)) { test_err("didn't rmap anything but expected %d", diff --git a/fs/btrfs/tests/inode-tests.c b/fs/btrfs/tests/inode-tests.c index 04022069761d..c9874b12d337 100644 --- a/fs/btrfs/tests/inode-tests.c +++ b/fs/btrfs/tests/inode-tests.c @@ -232,11 +232,6 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize) return ret; } - inode->i_mode = S_IFREG; - BTRFS_I(inode)->location.type = BTRFS_INODE_ITEM_KEY; - BTRFS_I(inode)->location.objectid = BTRFS_FIRST_FREE_OBJECTID; - BTRFS_I(inode)->location.offset = 0; - fs_info = btrfs_alloc_dummy_fs_info(nodesize, sectorsize); if (!fs_info) { test_std_err(TEST_ALLOC_FS_INFO); @@ -835,10 +830,6 @@ static int test_hole_first(u32 sectorsize, u32 nodesize) return ret; } - BTRFS_I(inode)->location.type = BTRFS_INODE_ITEM_KEY; - BTRFS_I(inode)->location.objectid = BTRFS_FIRST_FREE_OBJECTID; - BTRFS_I(inode)->location.offset = 0; - fs_info = btrfs_alloc_dummy_fs_info(nodesize, sectorsize); if (!fs_info) { test_std_err(TEST_ALLOC_FS_INFO); diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 8e0f7a1029c6..acff6bb49a97 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -21,6 +21,7 @@ #include "qgroup.h" #include "block-group.h" #include "space-info.h" +#include "zoned.h" #define BTRFS_ROOT_TRANS_TAG 0 @@ -107,6 +108,11 @@ static const unsigned int btrfs_blocked_trans_types[TRANS_STATE_MAX] = { __TRANS_JOIN | __TRANS_JOIN_NOLOCK | __TRANS_JOIN_NOSTART), + [TRANS_STATE_SUPER_COMMITTED] = (__TRANS_START | + __TRANS_ATTACH | + __TRANS_JOIN | + __TRANS_JOIN_NOLOCK | + __TRANS_JOIN_NOSTART), [TRANS_STATE_COMPLETED] = (__TRANS_START | __TRANS_ATTACH | __TRANS_JOIN | @@ -375,6 +381,8 @@ loop: spin_lock_init(&cur_trans->dirty_bgs_lock); INIT_LIST_HEAD(&cur_trans->deleted_bgs); spin_lock_init(&cur_trans->dropped_roots_lock); + INIT_LIST_HEAD(&cur_trans->releasing_ebs); + spin_lock_init(&cur_trans->releasing_ebs_lock); list_add_tail(&cur_trans->list, &fs_info->trans_list); extent_io_tree_init(fs_info, &cur_trans->dirty_pages, IO_TREE_TRANS_DIRTY_PAGES, fs_info->btree_inode); @@ -826,10 +834,11 @@ btrfs_attach_transaction_barrier(struct btrfs_root *root) return trans; } -/* wait for a transaction commit to be fully complete */ -static noinline void wait_for_commit(struct btrfs_transaction *commit) +/* Wait for a transaction commit to reach at least the given state. */ +static noinline void wait_for_commit(struct btrfs_transaction *commit, + const enum btrfs_trans_state min_state) { - wait_event(commit->commit_wait, commit->state == TRANS_STATE_COMPLETED); + wait_event(commit->commit_wait, commit->state >= min_state); } int btrfs_wait_for_commit(struct btrfs_fs_info *fs_info, u64 transid) @@ -884,7 +893,7 @@ int btrfs_wait_for_commit(struct btrfs_fs_info *fs_info, u64 transid) goto out; /* nothing committing|committed */ } - wait_for_commit(cur_trans); + wait_for_commit(cur_trans, TRANS_STATE_COMPLETED); btrfs_put_transaction(cur_trans); out: return ret; @@ -909,9 +918,8 @@ bool btrfs_should_end_transaction(struct btrfs_trans_handle *trans) { struct btrfs_transaction *cur_trans = trans->transaction; - smp_mb(); if (cur_trans->state >= TRANS_STATE_COMMIT_START || - cur_trans->delayed_refs.flushing) + test_bit(BTRFS_DELAYED_REFS_FLUSHING, &cur_trans->delayed_refs.flags)) return true; return should_end_transaction(trans); @@ -1230,10 +1238,6 @@ static noinline int commit_cowonly_roots(struct btrfs_trans_handle *trans) if (ret) return ret; - ret = btrfs_run_delayed_refs(trans, (unsigned long)-1); - if (ret) - return ret; - ret = btrfs_run_dev_stats(trans); if (ret) return ret; @@ -1248,10 +1252,6 @@ static noinline int commit_cowonly_roots(struct btrfs_trans_handle *trans) if (ret) return ret; - /* run_qgroups might have added some more refs */ - ret = btrfs_run_delayed_refs(trans, (unsigned long)-1); - if (ret) - return ret; again: while (!list_empty(&fs_info->dirty_cowonly_roots)) { struct btrfs_root *root; @@ -1266,15 +1266,24 @@ again: ret = update_cowonly_root(trans, root); if (ret) return ret; - ret = btrfs_run_delayed_refs(trans, (unsigned long)-1); - if (ret) - return ret; } + /* Now flush any delayed refs generated by updating all of the roots */ + ret = btrfs_run_delayed_refs(trans, (unsigned long)-1); + if (ret) + return ret; + while (!list_empty(dirty_bgs) || !list_empty(io_bgs)) { ret = btrfs_write_dirty_block_groups(trans); if (ret) return ret; + + /* + * We're writing the dirty block groups, which could generate + * delayed refs, which could generate more dirty block groups, + * so we want to keep this flushing in this loop to make sure + * everything gets run. + */ ret = btrfs_run_delayed_refs(trans, (unsigned long)-1); if (ret) return ret; @@ -1319,7 +1328,6 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans) struct btrfs_root *gang[8]; int i; int ret; - int err = 0; spin_lock(&fs_info->fs_roots_radix_lock); while (1) { @@ -1331,6 +1339,8 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans) break; for (i = 0; i < ret; i++) { struct btrfs_root *root = gang[i]; + int ret2; + radix_tree_tag_clear(&fs_info->fs_roots_radix, (unsigned long)root->root_key.objectid, BTRFS_ROOT_TRANS_TAG); @@ -1350,17 +1360,17 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans) root->node); } - err = btrfs_update_root(trans, fs_info->tree_root, + ret2 = btrfs_update_root(trans, fs_info->tree_root, &root->root_key, &root->root_item); + if (ret2) + return ret2; spin_lock(&fs_info->fs_roots_radix_lock); - if (err) - break; btrfs_qgroup_free_meta_all_pertrans(root); } } spin_unlock(&fs_info->fs_roots_radix_lock); - return err; + return 0; } /* @@ -1433,6 +1443,23 @@ static int qgroup_account_snapshot(struct btrfs_trans_handle *trans, record_root_in_trans(trans, src, 1); /* + * btrfs_qgroup_inherit relies on a consistent view of the usage for the + * src root, so we must run the delayed refs here. + * + * However this isn't particularly fool proof, because there's no + * synchronization keeping us from changing the tree after this point + * before we do the qgroup_inherit, or even from making changes while + * we're doing the qgroup_inherit. But that's a problem for the future, + * for now flush the delayed refs to narrow the race window where the + * qgroup counters could end up wrong. + */ + ret = btrfs_run_delayed_refs(trans, (unsigned long)-1); + if (ret) { + btrfs_abort_transaction(trans, ret); + goto out; + } + + /* * We are going to commit transaction, see btrfs_commit_transaction() * comment for reason locking tree_log_mutex */ @@ -1525,7 +1552,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, ASSERT(pending->root_item); new_root_item = pending->root_item; - pending->error = btrfs_find_free_objectid(tree_root, &objectid); + pending->error = btrfs_get_free_objectid(tree_root, &objectid); if (pending->error) goto no_free_objectid; @@ -1685,12 +1712,6 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, goto fail; } - ret = btrfs_run_delayed_refs(trans, (unsigned long)-1); - if (ret) { - btrfs_abort_transaction(trans, ret); - goto fail; - } - /* * Do special qgroup accounting for snapshot, as we do some qgroup * snapshot hack to do fast snapshot. @@ -1738,12 +1759,6 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, } } - ret = btrfs_run_delayed_refs(trans, (unsigned long)-1); - if (ret) { - btrfs_abort_transaction(trans, ret); - goto fail; - } - fail: pending->error = ret; dir_item_existed: @@ -2042,32 +2057,25 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) btrfs_trans_release_metadata(trans); trans->block_rsv = NULL; - /* make a pass through all the delayed refs we have so far - * any runnings procs may add more while we are here - */ - ret = btrfs_run_delayed_refs(trans, 0); - if (ret) { - btrfs_end_transaction(trans); - return ret; - } - - cur_trans = trans->transaction; - /* - * set the flushing flag so procs in this transaction have to - * start sending their work down. + * We only want one transaction commit doing the flushing so we do not + * waste a bunch of time on lock contention on the extent root node. */ - cur_trans->delayed_refs.flushing = 1; - smp_wmb(); + if (!test_and_set_bit(BTRFS_DELAYED_REFS_FLUSHING, + &cur_trans->delayed_refs.flags)) { + /* + * Make a pass through all the delayed refs we have so far. + * Any running threads may add more while we are here. + */ + ret = btrfs_run_delayed_refs(trans, 0); + if (ret) { + btrfs_end_transaction(trans); + return ret; + } + } btrfs_create_pending_block_groups(trans); - ret = btrfs_run_delayed_refs(trans, 0); - if (ret) { - btrfs_end_transaction(trans); - return ret; - } - if (!test_bit(BTRFS_TRANS_DIRTY_BG_RUN, &cur_trans->flags)) { int run_it = 0; @@ -2101,11 +2109,15 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) spin_lock(&fs_info->trans_lock); if (cur_trans->state >= TRANS_STATE_COMMIT_START) { + enum btrfs_trans_state want_state = TRANS_STATE_COMPLETED; + spin_unlock(&fs_info->trans_lock); refcount_inc(&cur_trans->use_count); - ret = btrfs_end_transaction(trans); - wait_for_commit(cur_trans); + if (trans->in_fsync) + want_state = TRANS_STATE_SUPER_COMMITTED; + ret = btrfs_end_transaction(trans); + wait_for_commit(cur_trans, want_state); if (TRANS_ABORTED(cur_trans)) ret = cur_trans->aborted; @@ -2119,13 +2131,19 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) wake_up(&fs_info->transaction_blocked_wait); if (cur_trans->list.prev != &fs_info->trans_list) { + enum btrfs_trans_state want_state = TRANS_STATE_COMPLETED; + + if (trans->in_fsync) + want_state = TRANS_STATE_SUPER_COMMITTED; + prev_trans = list_entry(cur_trans->list.prev, struct btrfs_transaction, list); - if (prev_trans->state != TRANS_STATE_COMPLETED) { + if (prev_trans->state < want_state) { refcount_inc(&prev_trans->use_count); spin_unlock(&fs_info->trans_lock); - wait_for_commit(prev_trans); + wait_for_commit(prev_trans, want_state); + ret = READ_ONCE(prev_trans->aborted); btrfs_put_transaction(prev_trans); @@ -2265,14 +2283,6 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) btrfs_free_log_root_tree(trans, fs_info); /* - * commit_fs_roots() can call btrfs_save_ino_cache(), which generates - * new delayed refs. Must handle them or qgroup can be wrong. - */ - ret = btrfs_run_delayed_refs(trans, (unsigned long)-1); - if (ret) - goto unlock_tree_log; - - /* * Since fs roots are all committed, we can get a quite accurate * new_roots. So let's do quota accounting. */ @@ -2343,6 +2353,13 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) goto scrub_continue; } + /* + * At this point, we should have written all the tree blocks allocated + * in this transaction. So it's now safe to free the redirtyied extent + * buffers. + */ + btrfs_free_redirty_list(cur_trans); + ret = write_all_supers(fs_info, 0); /* * the super is written, we can safely allow the tree-loggers @@ -2352,6 +2369,13 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) if (ret) goto scrub_continue; + /* + * We needn't acquire the lock here because there is no other task + * which can change it. + */ + cur_trans->state = TRANS_STATE_SUPER_COMMITTED; + wake_up(&cur_trans->commit_wait); + btrfs_finish_extent_commit(trans); if (test_bit(BTRFS_TRANS_HAVE_FREE_BGS, &cur_trans->flags)) diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index 31ca81bad822..6335716e513f 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -16,6 +16,7 @@ enum btrfs_trans_state { TRANS_STATE_COMMIT_START, TRANS_STATE_COMMIT_DOING, TRANS_STATE_UNBLOCKED, + TRANS_STATE_SUPER_COMMITTED, TRANS_STATE_COMPLETED, TRANS_STATE_MAX, }; @@ -92,6 +93,9 @@ struct btrfs_transaction { */ atomic_t pending_ordered; wait_queue_head_t pending_wait; + + spinlock_t releasing_ebs_lock; + struct list_head releasing_ebs; }; #define __TRANS_FREEZABLE (1U << 0) @@ -133,6 +137,7 @@ struct btrfs_trans_handle { bool can_flush_pending_bgs; bool reloc_reserved; bool dirty; + bool in_fsync; struct btrfs_root *root; struct btrfs_fs_info *fs_info; struct list_head new_bgs; diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 028e733e42f3..582061c7b547 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -760,6 +760,7 @@ int btrfs_check_chunk_valid(struct extent_buffer *leaf, { struct btrfs_fs_info *fs_info = leaf->fs_info; u64 length; + u64 chunk_end; u64 stripe_len; u16 num_stripes; u16 sub_stripes; @@ -814,6 +815,12 @@ int btrfs_check_chunk_valid(struct extent_buffer *leaf, "invalid chunk length, have %llu", length); return -EUCLEAN; } + if (unlikely(check_add_overflow(logical, length, &chunk_end))) { + chunk_err(leaf, chunk, logical, +"invalid chunk logical start and length, have logical start %llu length %llu", + logical, length); + return -EUCLEAN; + } if (unlikely(!is_power_of_2(stripe_len) || stripe_len != BTRFS_STRIPE_LEN)) { chunk_err(leaf, chunk, logical, "invalid chunk stripe length: %llu", diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 254c2ee43aae..d90695c1ab6c 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -19,6 +19,7 @@ #include "qgroup.h" #include "block-group.h" #include "space-info.h" +#include "zoned.h" /* magic values for the inode_only field in btrfs_log_inode: * @@ -104,6 +105,7 @@ static noinline int replay_dir_deletes(struct btrfs_trans_handle *trans, struct btrfs_root *log, struct btrfs_path *path, u64 dirid, int del_all); +static void wait_log_commit(struct btrfs_root *root, int transid); /* * tree logging is a special write ahead log used to make sure that @@ -139,7 +141,9 @@ static int start_log_trans(struct btrfs_trans_handle *trans, { struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_root *tree_root = fs_info->tree_root; + const bool zoned = btrfs_is_zoned(fs_info); int ret = 0; + bool created = false; /* * First check if the log root tree was already created. If not, create @@ -149,8 +153,10 @@ static int start_log_trans(struct btrfs_trans_handle *trans, mutex_lock(&tree_root->log_mutex); if (!fs_info->log_root_tree) { ret = btrfs_init_log_root_tree(trans, fs_info); - if (!ret) + if (!ret) { set_bit(BTRFS_ROOT_HAS_LOG_TREE, &tree_root->state); + created = true; + } } mutex_unlock(&tree_root->log_mutex); if (ret) @@ -159,12 +165,20 @@ static int start_log_trans(struct btrfs_trans_handle *trans, mutex_lock(&root->log_mutex); +again: if (root->log_root) { + int index = (root->log_transid + 1) % 2; + if (btrfs_need_log_full_commit(trans)) { ret = -EAGAIN; goto out; } + if (zoned && atomic_read(&root->log_commit[index])) { + wait_log_commit(root, root->log_transid - 1); + goto again; + } + if (!root->log_start_pid) { clear_bit(BTRFS_ROOT_MULTI_LOG_TASKS, &root->state); root->log_start_pid = current->pid; @@ -172,6 +186,17 @@ static int start_log_trans(struct btrfs_trans_handle *trans, set_bit(BTRFS_ROOT_MULTI_LOG_TASKS, &root->state); } } else { + /* + * This means fs_info->log_root_tree was already created + * for some other FS trees. Do the full commit not to mix + * nodes from multiple log transactions to do sequential + * writing. + */ + if (zoned && !created) { + ret = -EAGAIN; + goto out; + } + ret = btrfs_add_log_tree(trans, root); if (ret) goto out; @@ -200,14 +225,22 @@ out: */ static int join_running_log_trans(struct btrfs_root *root) { + const bool zoned = btrfs_is_zoned(root->fs_info); int ret = -ENOENT; if (!test_bit(BTRFS_ROOT_HAS_LOG_TREE, &root->state)) return ret; mutex_lock(&root->log_mutex); +again: if (root->log_root) { + int index = (root->log_transid + 1) % 2; + ret = 0; + if (zoned && atomic_read(&root->log_commit[index])) { + wait_log_commit(root, root->log_transid - 1); + goto again; + } atomic_inc(&root->log_writers); } mutex_unlock(&root->log_mutex); @@ -2752,6 +2785,8 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans, free_extent_buffer(next); return ret; } + btrfs_redirty_list_add( + trans->transaction, next); } else { if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &next->bflags)) clear_extent_buffer_dirty(next); @@ -3085,6 +3120,17 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, */ blk_start_plug(&plug); ret = btrfs_write_marked_extents(fs_info, &log->dirty_log_pages, mark); + /* + * -EAGAIN happens when someone, e.g., a concurrent transaction + * commit, writes a dirty extent in this tree-log commit. This + * concurrent write will create a hole writing out the extents, + * and we cannot proceed on a zoned filesystem, requiring + * sequential writing. While we can bail out to a full commit + * here, but we can continue hoping the concurrent writing fills + * the hole. + */ + if (ret == -EAGAIN && btrfs_is_zoned(fs_info)) + ret = 0; if (ret) { blk_finish_plug(&plug); btrfs_abort_transaction(trans, ret); @@ -3127,6 +3173,19 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, list_add_tail(&root_log_ctx.list, &log_root_tree->log_ctxs[index2]); root_log_ctx.log_transid = log_root_tree->log_transid; + if (btrfs_is_zoned(fs_info)) { + mutex_lock(&fs_info->tree_root->log_mutex); + if (!log_root_tree->node) { + ret = btrfs_alloc_log_tree_node(trans, log_root_tree); + if (ret) { + mutex_unlock(&fs_info->tree_log_mutex); + mutex_unlock(&log_root_tree->log_mutex); + goto out; + } + } + mutex_unlock(&fs_info->tree_root->log_mutex); + } + /* * Now we are safe to update the log_root_tree because we're under the * log_mutex, and we're a current writer so we're holding the commit @@ -3194,7 +3253,17 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, &log_root_tree->dirty_log_pages, EXTENT_DIRTY | EXTENT_NEW); blk_finish_plug(&plug); - if (ret) { + /* + * As described above, -EAGAIN indicates a hole in the extents. We + * cannot wait for these write outs since the waiting cause a + * deadlock. Bail out to the full commit instead. + */ + if (ret == -EAGAIN && btrfs_is_zoned(fs_info)) { + btrfs_set_log_full_commit(trans); + btrfs_wait_tree_log_extents(log, mark); + mutex_unlock(&log_root_tree->log_mutex); + goto out_wake_log_root; + } else if (ret) { btrfs_set_log_full_commit(trans); btrfs_abort_transaction(trans, ret); mutex_unlock(&log_root_tree->log_mutex); @@ -3285,17 +3354,22 @@ static void free_log_tree(struct btrfs_trans_handle *trans, .process_func = process_one_buffer }; - ret = walk_log_tree(trans, log, &wc); - if (ret) { - if (trans) - btrfs_abort_transaction(trans, ret); - else - btrfs_handle_fs_error(log->fs_info, ret, NULL); + if (log->node) { + ret = walk_log_tree(trans, log, &wc); + if (ret) { + if (trans) + btrfs_abort_transaction(trans, ret); + else + btrfs_handle_fs_error(log->fs_info, ret, NULL); + } } clear_extent_bits(&log->dirty_log_pages, 0, (u64)-1, EXTENT_DIRTY | EXTENT_NEW | EXTENT_NEED_WAIT); extent_io_tree_release(&log->log_csum_range); + + if (trans && log->node) + btrfs_redirty_list_add(trans->transaction, log->node); btrfs_put_root(log); } @@ -3379,7 +3453,6 @@ int btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans, struct btrfs_path *path; int ret; int err = 0; - int bytes_del = 0; u64 dir_ino = btrfs_ino(dir); if (!inode_logged(trans, dir)) @@ -3406,7 +3479,6 @@ int btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans, } if (di) { ret = btrfs_delete_one_dir_name(trans, log, path, di); - bytes_del += name_len; if (ret) { err = ret; goto fail; @@ -3421,46 +3493,17 @@ int btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans, } if (di) { ret = btrfs_delete_one_dir_name(trans, log, path, di); - bytes_del += name_len; if (ret) { err = ret; goto fail; } } - /* update the directory size in the log to reflect the names - * we have removed + /* + * We do not need to update the size field of the directory's inode item + * because on log replay we update the field to reflect all existing + * entries in the directory (see overwrite_item()). */ - if (bytes_del) { - struct btrfs_key key; - - key.objectid = dir_ino; - key.offset = 0; - key.type = BTRFS_INODE_ITEM_KEY; - btrfs_release_path(path); - - ret = btrfs_search_slot(trans, log, &key, path, 0, 1); - if (ret < 0) { - err = ret; - goto fail; - } - if (ret == 0) { - struct btrfs_inode_item *item; - u64 i_size; - - item = btrfs_item_ptr(path->nodes[0], path->slots[0], - struct btrfs_inode_item); - i_size = btrfs_inode_size(path->nodes[0], item); - if (i_size > bytes_del) - i_size -= bytes_del; - else - i_size = 0; - btrfs_set_inode_size(path->nodes[0], item, i_size); - btrfs_mark_buffer_dirty(path->nodes[0]); - } else - ret = 0; - btrfs_release_path(path); - } fail: btrfs_free_path(path); out_unlock: @@ -3889,7 +3932,14 @@ static void fill_inode_item(struct btrfs_trans_handle *trans, btrfs_set_token_timespec_nsec(&token, &item->ctime, inode->i_ctime.tv_nsec); - btrfs_set_token_inode_nbytes(&token, item, inode_get_bytes(inode)); + /* + * We do not need to set the nbytes field, in fact during a fast fsync + * its value may not even be correct, since a fast fsync does not wait + * for ordered extent completion, which is where we update nbytes, it + * only waits for writeback to complete. During log replay as we find + * file extent items and replay them, we adjust the nbytes field of the + * inode item in subvolume tree as needed (see overwrite_item()). + */ btrfs_set_token_inode_sequence(&token, item, inode_peek_iversion(inode)); btrfs_set_token_inode_transid(&token, item, trans->transid); @@ -5290,12 +5340,28 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, } /* + * This is for cases where logging a directory could result in losing a + * a file after replaying the log. For example, if we move a file from a + * directory A to a directory B, then fsync directory A, we have no way + * to known the file was moved from A to B, so logging just A would + * result in losing the file after a log replay. + */ + if (S_ISDIR(inode->vfs_inode.i_mode) && + inode_only == LOG_INODE_ALL && + inode->last_unlink_trans >= trans->transid) { + btrfs_set_log_full_commit(trans); + err = 1; + goto out_unlock; + } + + /* * a brute force approach to making sure we get the most uptodate * copies of everything. */ if (S_ISDIR(inode->vfs_inode.i_mode)) { int max_key_type = BTRFS_DIR_LOG_INDEX_KEY; + clear_bit(BTRFS_INODE_COPY_EVERYTHING, &inode->runtime_flags); if (inode_only == LOG_INODE_EXISTS) max_key_type = BTRFS_XATTR_ITEM_KEY; ret = drop_objectid_items(trans, log, path, ino, max_key_type); @@ -5452,96 +5518,31 @@ out_unlock: } /* - * Check if we must fallback to a transaction commit when logging an inode. - * This must be called after logging the inode and is used only in the context - * when fsyncing an inode requires the need to log some other inode - in which - * case we can't lock the i_mutex of each other inode we need to log as that - * can lead to deadlocks with concurrent fsync against other inodes (as we can - * log inodes up or down in the hierarchy) or rename operations for example. So - * we take the log_mutex of the inode after we have logged it and then check for - * its last_unlink_trans value - this is safe because any task setting - * last_unlink_trans must take the log_mutex and it must do this before it does - * the actual unlink operation, so if we do this check before a concurrent task - * sets last_unlink_trans it means we've logged a consistent version/state of - * all the inode items, otherwise we are not sure and must do a transaction - * commit (the concurrent task might have only updated last_unlink_trans before - * we logged the inode or it might have also done the unlink). + * Check if we need to log an inode. This is used in contexts where while + * logging an inode we need to log another inode (either that it exists or in + * full mode). This is used instead of btrfs_inode_in_log() because the later + * requires the inode to be in the log and have the log transaction committed, + * while here we do not care if the log transaction was already committed - our + * caller will commit the log later - and we want to avoid logging an inode + * multiple times when multiple tasks have joined the same log transaction. */ -static bool btrfs_must_commit_transaction(struct btrfs_trans_handle *trans, - struct btrfs_inode *inode) +static bool need_log_inode(struct btrfs_trans_handle *trans, + struct btrfs_inode *inode) { - bool ret = false; - - mutex_lock(&inode->log_mutex); - if (inode->last_unlink_trans >= trans->transid) { - /* - * Make sure any commits to the log are forced to be full - * commits. - */ - btrfs_set_log_full_commit(trans); - ret = true; - } - mutex_unlock(&inode->log_mutex); - - return ret; -} - -/* - * follow the dentry parent pointers up the chain and see if any - * of the directories in it require a full commit before they can - * be logged. Returns zero if nothing special needs to be done or 1 if - * a full commit is required. - */ -static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans, - struct btrfs_inode *inode, - struct dentry *parent, - struct super_block *sb) -{ - int ret = 0; - struct dentry *old_parent = NULL; - /* - * for regular files, if its inode is already on disk, we don't - * have to worry about the parents at all. This is because - * we can use the last_unlink_trans field to record renames - * and other fun in this file. + * If this inode does not have new/updated/deleted xattrs since the last + * time it was logged and is flagged as logged in the current transaction, + * we can skip logging it. As for new/deleted names, those are updated in + * the log by link/unlink/rename operations. + * In case the inode was logged and then evicted and reloaded, its + * logged_trans will be 0, in which case we have to fully log it since + * logged_trans is a transient field, not persisted. */ - if (S_ISREG(inode->vfs_inode.i_mode) && - inode->generation < trans->transid && - inode->last_unlink_trans < trans->transid) - goto out; - - if (!S_ISDIR(inode->vfs_inode.i_mode)) { - if (!parent || d_really_is_negative(parent) || sb != parent->d_sb) - goto out; - inode = BTRFS_I(d_inode(parent)); - } - - while (1) { - if (btrfs_must_commit_transaction(trans, inode)) { - ret = 1; - break; - } - - if (!parent || d_really_is_negative(parent) || sb != parent->d_sb) - break; - - if (IS_ROOT(parent)) { - inode = BTRFS_I(d_inode(parent)); - if (btrfs_must_commit_transaction(trans, inode)) - ret = 1; - break; - } - - parent = dget_parent(parent); - dput(old_parent); - old_parent = parent; - inode = BTRFS_I(d_inode(parent)); + if (inode->logged_trans == trans->transid && + !test_bit(BTRFS_INODE_COPY_EVERYTHING, &inode->runtime_flags)) + return false; - } - dput(old_parent); -out: - return ret; + return true; } struct btrfs_dir_list { @@ -5671,7 +5672,7 @@ process_leaf: goto next_dir_inode; } - if (btrfs_inode_in_log(BTRFS_I(di_inode), trans->transid)) { + if (!need_log_inode(trans, BTRFS_I(di_inode))) { btrfs_add_delayed_iput(di_inode); break; } @@ -5681,9 +5682,6 @@ process_leaf: log_mode = LOG_INODE_ALL; ret = btrfs_log_inode(trans, root, BTRFS_I(di_inode), log_mode, ctx); - if (!ret && - btrfs_must_commit_transaction(trans, BTRFS_I(di_inode))) - ret = 1; btrfs_add_delayed_iput(di_inode); if (ret) goto next_dir_inode; @@ -5821,13 +5819,15 @@ static int btrfs_log_all_parents(struct btrfs_trans_handle *trans, goto out; } + if (!need_log_inode(trans, BTRFS_I(dir_inode))) { + btrfs_add_delayed_iput(dir_inode); + continue; + } + if (ctx) ctx->log_new_dentries = false; ret = btrfs_log_inode(trans, root, BTRFS_I(dir_inode), LOG_INODE_ALL, ctx); - if (!ret && - btrfs_must_commit_transaction(trans, BTRFS_I(dir_inode))) - ret = 1; if (!ret && ctx && ctx->log_new_dentries) ret = log_new_dir_dentries(trans, root, BTRFS_I(dir_inode), ctx); @@ -5872,7 +5872,8 @@ static int log_new_ancestors(struct btrfs_trans_handle *trans, if (IS_ERR(inode)) return PTR_ERR(inode); - if (BTRFS_I(inode)->generation >= trans->transid) + if (BTRFS_I(inode)->generation >= trans->transid && + need_log_inode(trans, BTRFS_I(inode))) ret = btrfs_log_inode(trans, root, BTRFS_I(inode), LOG_INODE_EXISTS, ctx); btrfs_add_delayed_iput(inode); @@ -5926,7 +5927,8 @@ static int log_new_ancestors_fast(struct btrfs_trans_handle *trans, if (root != inode->root) break; - if (inode->generation >= trans->transid) { + if (inode->generation >= trans->transid && + need_log_inode(trans, inode)) { ret = btrfs_log_inode(trans, root, inode, LOG_INODE_EXISTS, ctx); if (ret) @@ -6041,12 +6043,9 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans, { struct btrfs_root *root = inode->root; struct btrfs_fs_info *fs_info = root->fs_info; - struct super_block *sb; int ret = 0; bool log_dentries = false; - sb = inode->vfs_inode.i_sb; - if (btrfs_test_opt(fs_info, NOTREELOG)) { ret = 1; goto end_no_trans; @@ -6057,10 +6056,6 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans, goto end_no_trans; } - ret = check_parent_dirs_for_sync(trans, inode, parent, sb); - if (ret) - goto end_no_trans; - /* * Skip already logged inodes or inodes corresponding to tmpfiles * (since logging them is pointless, a link count of 0 means they @@ -6307,8 +6302,7 @@ again: * root->objectid_mutex is not acquired as log replay * could only happen during mount. */ - ret = btrfs_find_highest_objectid(root, - &root->highest_objectid); + ret = btrfs_init_root_free_objectid(root); } wc.replay_dest->log_root = NULL; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index ee086fc56c30..bc3b33efddc5 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -421,7 +421,7 @@ static struct btrfs_device *__alloc_device(struct btrfs_fs_info *fs_info) * Preallocate a bio that's always going to be used for flushing device * barriers and matches the device lifespan */ - dev->flush_bio = bio_alloc_bioset(GFP_KERNEL, 0, NULL); + dev->flush_bio = bio_kmalloc(GFP_KERNEL, 0); if (!dev->flush_bio) { kfree(dev); return ERR_PTR(-ENOMEM); @@ -433,7 +433,7 @@ static struct btrfs_device *__alloc_device(struct btrfs_fs_info *fs_info) atomic_set(&dev->reada_in_flight, 0); atomic_set(&dev->dev_stats_ccnt, 0); - btrfs_device_data_ordered_init(dev, fs_info); + btrfs_device_data_ordered_init(dev); INIT_RADIX_TREE(&dev->reada_zones, GFP_NOFS & ~__GFP_DIRECT_RECLAIM); INIT_RADIX_TREE(&dev->reada_extents, GFP_NOFS & ~__GFP_DIRECT_RECLAIM); extent_io_tree_init(fs_info, &dev->alloc_state, @@ -669,10 +669,6 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices, clear_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state); device->mode = flags; - ret = btrfs_get_dev_zone_info(device); - if (ret != 0) - goto error_free_page; - fs_devices->open_devices++; if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state) && device->devid != BTRFS_DEV_REPLACE_DEVID) { @@ -1418,11 +1414,62 @@ static u64 dev_extent_search_start(struct btrfs_device *device, u64 start) * make sure to start at an offset of at least 1MB. */ return max_t(u64, start, SZ_1M); + case BTRFS_CHUNK_ALLOC_ZONED: + /* + * We don't care about the starting region like regular + * allocator, because we anyway use/reserve the first two zones + * for superblock logging. + */ + return ALIGN(start, device->zone_info->zone_size); default: BUG(); } } +static bool dev_extent_hole_check_zoned(struct btrfs_device *device, + u64 *hole_start, u64 *hole_size, + u64 num_bytes) +{ + u64 zone_size = device->zone_info->zone_size; + u64 pos; + int ret; + bool changed = false; + + ASSERT(IS_ALIGNED(*hole_start, zone_size)); + + while (*hole_size > 0) { + pos = btrfs_find_allocatable_zones(device, *hole_start, + *hole_start + *hole_size, + num_bytes); + if (pos != *hole_start) { + *hole_size = *hole_start + *hole_size - pos; + *hole_start = pos; + changed = true; + if (*hole_size < num_bytes) + break; + } + + ret = btrfs_ensure_empty_zones(device, pos, num_bytes); + + /* Range is ensured to be empty */ + if (!ret) + return changed; + + /* Given hole range was invalid (outside of device) */ + if (ret == -ERANGE) { + *hole_start += *hole_size; + *hole_size = 0; + return 1; + } + + *hole_start += zone_size; + *hole_size -= zone_size; + changed = true; + } + + return changed; +} + /** * dev_extent_hole_check - check if specified hole is suitable for allocation * @device: the device which we have the hole @@ -1430,7 +1477,7 @@ static u64 dev_extent_search_start(struct btrfs_device *device, u64 start) * @hole_size: the size of the hole * @num_bytes: the size of the free space that we need * - * This function may modify @hole_start and @hole_end to reflect the suitable + * This function may modify @hole_start and @hole_size to reflect the suitable * position for allocation. Returns 1 if hole position is updated, 0 otherwise. */ static bool dev_extent_hole_check(struct btrfs_device *device, u64 *hole_start, @@ -1439,24 +1486,39 @@ static bool dev_extent_hole_check(struct btrfs_device *device, u64 *hole_start, bool changed = false; u64 hole_end = *hole_start + *hole_size; - /* - * Check before we set max_hole_start, otherwise we could end up - * sending back this offset anyway. - */ - if (contains_pending_extent(device, hole_start, *hole_size)) { - if (hole_end >= *hole_start) - *hole_size = hole_end - *hole_start; - else - *hole_size = 0; - changed = true; - } + for (;;) { + /* + * Check before we set max_hole_start, otherwise we could end up + * sending back this offset anyway. + */ + if (contains_pending_extent(device, hole_start, *hole_size)) { + if (hole_end >= *hole_start) + *hole_size = hole_end - *hole_start; + else + *hole_size = 0; + changed = true; + } + + switch (device->fs_devices->chunk_alloc_policy) { + case BTRFS_CHUNK_ALLOC_REGULAR: + /* No extra check */ + break; + case BTRFS_CHUNK_ALLOC_ZONED: + if (dev_extent_hole_check_zoned(device, hole_start, + hole_size, num_bytes)) { + changed = true; + /* + * The changed hole can contain pending extent. + * Loop again to check that. + */ + continue; + } + break; + default: + BUG(); + } - switch (device->fs_devices->chunk_alloc_policy) { - case BTRFS_CHUNK_ALLOC_REGULAR: - /* No extra check */ break; - default: - BUG(); } return changed; @@ -1509,6 +1571,9 @@ static int find_free_dev_extent_start(struct btrfs_device *device, search_start = dev_extent_search_start(device, search_start); + WARN_ON(device->zone_info && + !IS_ALIGNED(num_bytes, device->zone_info->zone_size)); + path = btrfs_alloc_path(); if (!path) return -ENOMEM; @@ -2592,7 +2657,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path set_blocksize(device->bdev, BTRFS_BDEV_BLOCKSIZE); if (seeding_dev) { - sb->s_flags &= ~SB_RDONLY; + btrfs_clear_sb_rdonly(sb); ret = btrfs_prepare_sprout(fs_info); if (ret) { btrfs_abort_transaction(trans, ret); @@ -2728,7 +2793,7 @@ error_sysfs: mutex_unlock(&fs_info->fs_devices->device_list_mutex); error_trans: if (seeding_dev) - sb->s_flags |= SB_RDONLY; + btrfs_set_sb_rdonly(sb); if (trans) btrfs_end_transaction(trans); error_free_zone: @@ -4317,6 +4382,8 @@ int btrfs_recover_balance(struct btrfs_fs_info *fs_info) btrfs_warn(fs_info, "balance: cannot set exclusive op status, resume manually"); + btrfs_release_path(path); + mutex_lock(&fs_info->balance_mutex); BUG_ON(fs_info->balance_ctl); spin_lock(&fs_info->balance_lock); @@ -4666,11 +4733,10 @@ again: } ret = btrfs_previous_item(root, path, 0, key.type); - if (ret) - mutex_unlock(&fs_info->delete_unused_bgs_mutex); - if (ret < 0) - goto done; if (ret) { + mutex_unlock(&fs_info->delete_unused_bgs_mutex); + if (ret < 0) + goto done; ret = 0; btrfs_release_path(path); break; @@ -4902,6 +4968,37 @@ static void init_alloc_chunk_ctl_policy_regular( ctl->dev_extent_min = BTRFS_STRIPE_LEN * ctl->dev_stripes; } +static void init_alloc_chunk_ctl_policy_zoned( + struct btrfs_fs_devices *fs_devices, + struct alloc_chunk_ctl *ctl) +{ + u64 zone_size = fs_devices->fs_info->zone_size; + u64 limit; + int min_num_stripes = ctl->devs_min * ctl->dev_stripes; + int min_data_stripes = (min_num_stripes - ctl->nparity) / ctl->ncopies; + u64 min_chunk_size = min_data_stripes * zone_size; + u64 type = ctl->type; + + ctl->max_stripe_size = zone_size; + if (type & BTRFS_BLOCK_GROUP_DATA) { + ctl->max_chunk_size = round_down(BTRFS_MAX_DATA_CHUNK_SIZE, + zone_size); + } else if (type & BTRFS_BLOCK_GROUP_METADATA) { + ctl->max_chunk_size = ctl->max_stripe_size; + } else if (type & BTRFS_BLOCK_GROUP_SYSTEM) { + ctl->max_chunk_size = 2 * ctl->max_stripe_size; + ctl->devs_max = min_t(int, ctl->devs_max, + BTRFS_MAX_DEVS_SYS_CHUNK); + } + + /* We don't want a chunk larger than 10% of writable space */ + limit = max(round_down(div_factor(fs_devices->total_rw_bytes, 1), + zone_size), + min_chunk_size); + ctl->max_chunk_size = min(limit, ctl->max_chunk_size); + ctl->dev_extent_min = zone_size * ctl->dev_stripes; +} + static void init_alloc_chunk_ctl(struct btrfs_fs_devices *fs_devices, struct alloc_chunk_ctl *ctl) { @@ -4922,6 +5019,9 @@ static void init_alloc_chunk_ctl(struct btrfs_fs_devices *fs_devices, case BTRFS_CHUNK_ALLOC_REGULAR: init_alloc_chunk_ctl_policy_regular(fs_devices, ctl); break; + case BTRFS_CHUNK_ALLOC_ZONED: + init_alloc_chunk_ctl_policy_zoned(fs_devices, ctl); + break; default: BUG(); } @@ -5048,6 +5148,38 @@ static int decide_stripe_size_regular(struct alloc_chunk_ctl *ctl, return 0; } +static int decide_stripe_size_zoned(struct alloc_chunk_ctl *ctl, + struct btrfs_device_info *devices_info) +{ + u64 zone_size = devices_info[0].dev->zone_info->zone_size; + /* Number of stripes that count for block group size */ + int data_stripes; + + /* + * It should hold because: + * dev_extent_min == dev_extent_want == zone_size * dev_stripes + */ + ASSERT(devices_info[ctl->ndevs - 1].max_avail == ctl->dev_extent_min); + + ctl->stripe_size = zone_size; + ctl->num_stripes = ctl->ndevs * ctl->dev_stripes; + data_stripes = (ctl->num_stripes - ctl->nparity) / ctl->ncopies; + + /* stripe_size is fixed in zoned filesysmte. Reduce ndevs instead. */ + if (ctl->stripe_size * data_stripes > ctl->max_chunk_size) { + ctl->ndevs = div_u64(div_u64(ctl->max_chunk_size * ctl->ncopies, + ctl->stripe_size) + ctl->nparity, + ctl->dev_stripes); + ctl->num_stripes = ctl->ndevs * ctl->dev_stripes; + data_stripes = (ctl->num_stripes - ctl->nparity) / ctl->ncopies; + ASSERT(ctl->stripe_size * data_stripes <= ctl->max_chunk_size); + } + + ctl->chunk_size = ctl->stripe_size * data_stripes; + + return 0; +} + static int decide_stripe_size(struct btrfs_fs_devices *fs_devices, struct alloc_chunk_ctl *ctl, struct btrfs_device_info *devices_info) @@ -5075,6 +5207,8 @@ static int decide_stripe_size(struct btrfs_fs_devices *fs_devices, switch (fs_devices->chunk_alloc_policy) { case BTRFS_CHUNK_ALLOC_REGULAR: return decide_stripe_size_regular(ctl, devices_info); + case BTRFS_CHUNK_ALLOC_ZONED: + return decide_stripe_size_zoned(ctl, devices_info); default: BUG(); } @@ -5839,9 +5973,29 @@ static int get_extra_mirror_from_replace(struct btrfs_fs_info *fs_info, return ret; } +static bool is_block_group_to_copy(struct btrfs_fs_info *fs_info, u64 logical) +{ + struct btrfs_block_group *cache; + bool ret; + + /* Non zoned filesystem does not use "to_copy" flag */ + if (!btrfs_is_zoned(fs_info)) + return false; + + cache = btrfs_lookup_block_group(fs_info, logical); + + spin_lock(&cache->lock); + ret = cache->to_copy; + spin_unlock(&cache->lock); + + btrfs_put_block_group(cache); + return ret; +} + static void handle_ops_on_dev_replace(enum btrfs_map_op op, struct btrfs_bio **bbio_ret, struct btrfs_dev_replace *dev_replace, + u64 logical, int *num_stripes_ret, int *max_errors_ret) { struct btrfs_bio *bbio = *bbio_ret; @@ -5855,6 +6009,13 @@ static void handle_ops_on_dev_replace(enum btrfs_map_op op, int index_where_to_add; /* + * A block group which have "to_copy" set will eventually + * copied by dev-replace process. We can avoid cloning IO here. + */ + if (is_block_group_to_copy(dev_replace->srcdev->fs_info, logical)) + return; + + /* * duplicate the write operations while the dev replace * procedure is running. Since the copying of the old disk to * the new disk takes place at run time while the filesystem is @@ -5939,23 +6100,24 @@ static bool need_full_stripe(enum btrfs_map_op op) } /* - * btrfs_get_io_geometry - calculates the geomery of a particular (address, len) - * tuple. This information is used to calculate how big a - * particular bio can get before it straddles a stripe. + * Calculate the geometry of a particular (address, len) tuple. This + * information is used to calculate how big a particular bio can get before it + * straddles a stripe. * - * @fs_info - the filesystem - * @logical - address that we want to figure out the geometry of - * @len - the length of IO we are going to perform, starting at @logical - * @op - type of operation - write or read - * @io_geom - pointer used to return values + * @fs_info: the filesystem + * @em: mapping containing the logical extent + * @op: type of operation - write or read + * @logical: address that we want to figure out the geometry of + * @len: the length of IO we are going to perform, starting at @logical + * @io_geom: pointer used to return values * * Returns < 0 in case a chunk for the given logical address cannot be found, * usually shouldn't happen unless @logical is corrupted, 0 otherwise. */ -int btrfs_get_io_geometry(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, - u64 logical, u64 len, struct btrfs_io_geometry *io_geom) +int btrfs_get_io_geometry(struct btrfs_fs_info *fs_info, struct extent_map *em, + enum btrfs_map_op op, u64 logical, u64 len, + struct btrfs_io_geometry *io_geom) { - struct extent_map *em; struct map_lookup *map; u64 offset; u64 stripe_offset; @@ -5963,14 +6125,9 @@ int btrfs_get_io_geometry(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, u64 stripe_len; u64 raid56_full_stripe_start = (u64)-1; int data_stripes; - int ret = 0; ASSERT(op != BTRFS_MAP_DISCARD); - em = btrfs_get_chunk_map(fs_info, logical, len); - if (IS_ERR(em)) - return PTR_ERR(em); - map = em->map_lookup; /* Offset of this logical address in the chunk */ offset = logical - em->start; @@ -5984,8 +6141,7 @@ int btrfs_get_io_geometry(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, btrfs_crit(fs_info, "stripe math has gone wrong, stripe_offset=%llu offset=%llu start=%llu logical=%llu stripe_len=%llu", stripe_offset, offset, em->start, logical, stripe_len); - ret = -EINVAL; - goto out; + return -EINVAL; } /* stripe_offset is the offset of this block in its stripe */ @@ -6032,10 +6188,7 @@ int btrfs_get_io_geometry(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, io_geom->stripe_offset = stripe_offset; io_geom->raid56_stripe_offset = raid56_full_stripe_start; -out: - /* once for us */ - free_extent_map(em); - return ret; + return 0; } static int __btrfs_map_block(struct btrfs_fs_info *fs_info, @@ -6068,12 +6221,13 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, ASSERT(bbio_ret); ASSERT(op != BTRFS_MAP_DISCARD); - ret = btrfs_get_io_geometry(fs_info, op, logical, *length, &geom); + em = btrfs_get_chunk_map(fs_info, logical, *length); + ASSERT(!IS_ERR(em)); + + ret = btrfs_get_io_geometry(fs_info, em, op, logical, *length, &geom); if (ret < 0) return ret; - em = btrfs_get_chunk_map(fs_info, logical, *length); - ASSERT(!IS_ERR(em)); map = em->map_lookup; *length = geom.len; @@ -6249,8 +6403,8 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, if (dev_replace_is_ongoing && dev_replace->tgtdev != NULL && need_full_stripe(op)) { - handle_ops_on_dev_replace(op, &bbio, dev_replace, &num_stripes, - &max_errors); + handle_ops_on_dev_replace(op, &bbio, dev_replace, logical, + &num_stripes, &max_errors); } *bbio_ret = bbio; @@ -6321,7 +6475,7 @@ static void btrfs_end_bio(struct bio *bio) struct btrfs_device *dev = btrfs_io_bio(bio)->device; ASSERT(dev->bdev); - if (bio_op(bio) == REQ_OP_WRITE) + if (btrfs_op(bio) == BTRFS_MAP_WRITE) btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_WRITE_ERRS); else if (!(bio->bi_opf & REQ_RAHEAD)) @@ -6373,6 +6527,20 @@ static void submit_stripe_bio(struct btrfs_bio *bbio, struct bio *bio, btrfs_io_bio(bio)->device = dev; bio->bi_end_io = btrfs_end_bio; bio->bi_iter.bi_sector = physical >> 9; + /* + * For zone append writing, bi_sector must point the beginning of the + * zone + */ + if (bio_op(bio) == REQ_OP_ZONE_APPEND) { + if (btrfs_dev_is_sequential(dev, physical)) { + u64 zone_start = round_down(physical, fs_info->zone_size); + + bio->bi_iter.bi_sector = zone_start >> SECTOR_SHIFT; + } else { + bio->bi_opf &= ~REQ_OP_ZONE_APPEND; + bio->bi_opf |= REQ_OP_WRITE; + } + } btrfs_debug_in_rcu(fs_info, "btrfs_map_bio: rw %d 0x%x, sector=%llu, dev=%lu (%s id %llu), size=%u", bio_op(bio), bio->bi_opf, bio->bi_iter.bi_sector, @@ -6434,10 +6602,10 @@ blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio, atomic_set(&bbio->stripes_pending, bbio->num_stripes); if ((bbio->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK) && - ((bio_op(bio) == REQ_OP_WRITE) || (mirror_num > 1))) { + ((btrfs_op(bio) == BTRFS_MAP_WRITE) || (mirror_num > 1))) { /* In this case, map_length has been set to the length of a single stripe; not the whole write */ - if (bio_op(bio) == REQ_OP_WRITE) { + if (btrfs_op(bio) == BTRFS_MAP_WRITE) { ret = raid56_parity_write(fs_info, bio, bbio, map_length); } else { @@ -6460,7 +6628,7 @@ blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio, dev = bbio->stripes[dev_nr].dev; if (!dev || !dev->bdev || test_bit(BTRFS_DEV_STATE_MISSING, &dev->dev_state) || - (bio_op(first_bio) == REQ_OP_WRITE && + (btrfs_op(first_bio) == BTRFS_MAP_WRITE && !test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state))) { bbio_error(bbio, first_bio, logical); continue; @@ -7642,6 +7810,20 @@ static int verify_one_dev_extent(struct btrfs_fs_info *fs_info, ret = -EUCLEAN; goto out; } + + if (dev->zone_info) { + u64 zone_size = dev->zone_info->zone_size; + + if (!IS_ALIGNED(physical_offset, zone_size) || + !IS_ALIGNED(physical_len, zone_size)) { + btrfs_err(fs_info, +"zoned: dev extent devid %llu physical offset %llu len %llu is not aligned to device zone", + devid, physical_offset, physical_len); + ret = -EUCLEAN; + goto out; + } + } + out: free_extent_map(em); return ret; @@ -7798,3 +7980,75 @@ bool btrfs_pinned_by_swapfile(struct btrfs_fs_info *fs_info, void *ptr) spin_unlock(&fs_info->swapfile_pins_lock); return node != NULL; } + +static int relocating_repair_kthread(void *data) +{ + struct btrfs_block_group *cache = (struct btrfs_block_group *)data; + struct btrfs_fs_info *fs_info = cache->fs_info; + u64 target; + int ret = 0; + + target = cache->start; + btrfs_put_block_group(cache); + + if (!btrfs_exclop_start(fs_info, BTRFS_EXCLOP_BALANCE)) { + btrfs_info(fs_info, + "zoned: skip relocating block group %llu to repair: EBUSY", + target); + return -EBUSY; + } + + mutex_lock(&fs_info->delete_unused_bgs_mutex); + + /* Ensure block group still exists */ + cache = btrfs_lookup_block_group(fs_info, target); + if (!cache) + goto out; + + if (!cache->relocating_repair) + goto out; + + ret = btrfs_may_alloc_data_chunk(fs_info, target); + if (ret < 0) + goto out; + + btrfs_info(fs_info, + "zoned: relocating block group %llu to repair IO failure", + target); + ret = btrfs_relocate_chunk(fs_info, target); + +out: + if (cache) + btrfs_put_block_group(cache); + mutex_unlock(&fs_info->delete_unused_bgs_mutex); + btrfs_exclop_finish(fs_info); + + return ret; +} + +int btrfs_repair_one_zone(struct btrfs_fs_info *fs_info, u64 logical) +{ + struct btrfs_block_group *cache; + + /* Do not attempt to repair in degraded state */ + if (btrfs_test_opt(fs_info, DEGRADED)) + return 0; + + cache = btrfs_lookup_block_group(fs_info, logical); + if (!cache) + return 0; + + spin_lock(&cache->lock); + if (cache->relocating_repair) { + spin_unlock(&cache->lock); + btrfs_put_block_group(cache); + return 0; + } + cache->relocating_repair = 1; + spin_unlock(&cache->lock); + + kthread_run(relocating_repair_kthread, cache, + "btrfs-relocating-repair"); + + return 0; +} diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 1997a4649a66..d4c3e0dd32b8 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -39,10 +39,10 @@ struct btrfs_io_geometry { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) #include <linux/seqlock.h> #define __BTRFS_NEED_DEVICE_DATA_ORDERED -#define btrfs_device_data_ordered_init(device, info) \ - seqcount_mutex_init(&device->data_seqcount, &info->chunk_mutex) +#define btrfs_device_data_ordered_init(device) \ + seqcount_init(&device->data_seqcount) #else -#define btrfs_device_data_ordered_init(device, info) do { } while (0) +#define btrfs_device_data_ordered_init(device) do { } while (0) #endif #define BTRFS_DEV_STATE_WRITEABLE (0) @@ -76,8 +76,7 @@ struct btrfs_device { blk_status_t last_flush_error; #ifdef __BTRFS_NEED_DEVICE_DATA_ORDERED - /* A seqcount_t with associated chunk_mutex (for lockdep) */ - seqcount_mutex_t data_seqcount; + seqcount_t data_seqcount; #endif /* the internal btrfs device id */ @@ -168,9 +167,11 @@ btrfs_device_get_##name(const struct btrfs_device *dev) \ static inline void \ btrfs_device_set_##name(struct btrfs_device *dev, u64 size) \ { \ + preempt_disable(); \ write_seqcount_begin(&dev->data_seqcount); \ dev->name = size; \ write_seqcount_end(&dev->data_seqcount); \ + preempt_enable(); \ } #elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) #define BTRFS_DEVICE_GETSET_FUNCS(name) \ @@ -213,6 +214,7 @@ BTRFS_DEVICE_GETSET_FUNCS(bytes_used); enum btrfs_chunk_allocation_policy { BTRFS_CHUNK_ALLOC_REGULAR, + BTRFS_CHUNK_ALLOC_ZONED, }; /* @@ -422,6 +424,7 @@ static inline enum btrfs_map_op btrfs_op(struct bio *bio) case REQ_OP_DISCARD: return BTRFS_MAP_DISCARD; case REQ_OP_WRITE: + case REQ_OP_ZONE_APPEND: return BTRFS_MAP_WRITE; default: WARN_ON_ONCE(1); @@ -439,8 +442,9 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, int btrfs_map_sblock(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, u64 logical, u64 *length, struct btrfs_bio **bbio_ret); -int btrfs_get_io_geometry(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, - u64 logical, u64 len, struct btrfs_io_geometry *io_geom); +int btrfs_get_io_geometry(struct btrfs_fs_info *fs_info, struct extent_map *map, + enum btrfs_map_op op, u64 logical, u64 len, + struct btrfs_io_geometry *io_geom); int btrfs_read_sys_array(struct btrfs_fs_info *fs_info); int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info); int btrfs_alloc_chunk(struct btrfs_trans_handle *trans, u64 type); @@ -595,5 +599,6 @@ void btrfs_scratch_superblocks(struct btrfs_fs_info *fs_info, int btrfs_bg_type_to_factor(u64 flags); const char *btrfs_bg_type_to_raid_name(u64 flags); int btrfs_verify_dev_extents(struct btrfs_fs_info *fs_info); +int btrfs_repair_one_zone(struct btrfs_fs_info *fs_info, u64 logical); #endif diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index c38846659019..d0eb0c8d6269 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -1,14 +1,25 @@ // SPDX-License-Identifier: GPL-2.0 +#include <linux/bitops.h> #include <linux/slab.h> #include <linux/blkdev.h> +#include <linux/sched/mm.h> #include "ctree.h" #include "volumes.h" #include "zoned.h" #include "rcu-string.h" +#include "disk-io.h" +#include "block-group.h" +#include "transaction.h" +#include "dev-replace.h" +#include "space-info.h" /* Maximum number of zones to report per blkdev_report_zones() call */ #define BTRFS_REPORT_NR_ZONES 4096 +/* Invalid allocation pointer value for missing devices */ +#define WP_MISSING_DEV ((u64)-1) +/* Pseudo write pointer value for conventional zone */ +#define WP_CONVENTIONAL ((u64)-2) /* Number of superblock log zones */ #define BTRFS_NR_SB_LOG_ZONES 2 @@ -119,6 +130,36 @@ static inline u32 sb_zone_number(int shift, int mirror) return 0; } +/* + * Emulate blkdev_report_zones() for a non-zoned device. It slices up the block + * device into static sized chunks and fake a conventional zone on each of + * them. + */ +static int emulate_report_zones(struct btrfs_device *device, u64 pos, + struct blk_zone *zones, unsigned int nr_zones) +{ + const sector_t zone_sectors = device->fs_info->zone_size >> SECTOR_SHIFT; + sector_t bdev_size = bdev_nr_sectors(device->bdev); + unsigned int i; + + pos >>= SECTOR_SHIFT; + for (i = 0; i < nr_zones; i++) { + zones[i].start = i * zone_sectors + pos; + zones[i].len = zone_sectors; + zones[i].capacity = zone_sectors; + zones[i].wp = zones[i].start + zone_sectors; + zones[i].type = BLK_ZONE_TYPE_CONVENTIONAL; + zones[i].cond = BLK_ZONE_COND_NOT_WP; + + if (zones[i].wp >= bdev_size) { + i++; + break; + } + } + + return i; +} + static int btrfs_get_dev_zones(struct btrfs_device *device, u64 pos, struct blk_zone *zones, unsigned int *nr_zones) { @@ -127,6 +168,12 @@ static int btrfs_get_dev_zones(struct btrfs_device *device, u64 pos, if (!*nr_zones) return 0; + if (!bdev_is_zoned(device->bdev)) { + ret = emulate_report_zones(device, pos, zones, *nr_zones); + *nr_zones = ret; + return 0; + } + ret = blkdev_report_zones(device->bdev, pos >> SECTOR_SHIFT, *nr_zones, copy_zone_info_cb, zones); if (ret < 0) { @@ -143,8 +190,78 @@ static int btrfs_get_dev_zones(struct btrfs_device *device, u64 pos, return 0; } +/* The emulated zone size is determined from the size of device extent */ +static int calculate_emulated_zone_size(struct btrfs_fs_info *fs_info) +{ + struct btrfs_path *path; + struct btrfs_root *root = fs_info->dev_root; + struct btrfs_key key; + struct extent_buffer *leaf; + struct btrfs_dev_extent *dext; + int ret = 0; + + key.objectid = 1; + key.type = BTRFS_DEV_EXTENT_KEY; + key.offset = 0; + + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + + ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); + if (ret < 0) + goto out; + + if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) { + ret = btrfs_next_item(root, path); + if (ret < 0) + goto out; + /* No dev extents at all? Not good */ + if (ret > 0) { + ret = -EUCLEAN; + goto out; + } + } + + leaf = path->nodes[0]; + dext = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_dev_extent); + fs_info->zone_size = btrfs_dev_extent_length(leaf, dext); + ret = 0; + +out: + btrfs_free_path(path); + + return ret; +} + +int btrfs_get_dev_zone_info_all_devices(struct btrfs_fs_info *fs_info) +{ + struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; + struct btrfs_device *device; + int ret = 0; + + /* fs_info->zone_size might not set yet. Use the incomapt flag here. */ + if (!btrfs_fs_incompat(fs_info, ZONED)) + return 0; + + mutex_lock(&fs_devices->device_list_mutex); + list_for_each_entry(device, &fs_devices->devices, dev_list) { + /* We can skip reading of zone info for missing devices */ + if (!device->bdev) + continue; + + ret = btrfs_get_dev_zone_info(device); + if (ret) + break; + } + mutex_unlock(&fs_devices->device_list_mutex); + + return ret; +} + int btrfs_get_dev_zone_info(struct btrfs_device *device) { + struct btrfs_fs_info *fs_info = device->fs_info; struct btrfs_zoned_device_info *zone_info = NULL; struct block_device *bdev = device->bdev; struct request_queue *queue = bdev_get_queue(bdev); @@ -153,9 +270,14 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device) struct blk_zone *zones = NULL; unsigned int i, nreported = 0, nr_zones; unsigned int zone_sectors; + char *model, *emulated; int ret; - if (!bdev_is_zoned(bdev)) + /* + * Cannot use btrfs_is_zoned here, since fs_info::zone_size might not + * yet be set. + */ + if (!btrfs_fs_incompat(fs_info, ZONED)) return 0; if (device->zone_info) @@ -165,8 +287,20 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device) if (!zone_info) return -ENOMEM; + if (!bdev_is_zoned(bdev)) { + if (!fs_info->zone_size) { + ret = calculate_emulated_zone_size(fs_info); + if (ret) + goto out; + } + + ASSERT(fs_info->zone_size); + zone_sectors = fs_info->zone_size >> SECTOR_SHIFT; + } else { + zone_sectors = bdev_zone_sectors(bdev); + } + nr_sectors = bdev_nr_sectors(bdev); - zone_sectors = bdev_zone_sectors(bdev); /* Check if it's power of 2 (see is_power_of_2) */ ASSERT(zone_sectors != 0 && (zone_sectors & (zone_sectors - 1)) == 0); zone_info->zone_size = zone_sectors << SECTOR_SHIFT; @@ -272,20 +406,42 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device) device->zone_info = zone_info; - /* device->fs_info is not safe to use for printing messages */ - btrfs_info_in_rcu(NULL, - "host-%s zoned block device %s, %u zones of %llu bytes", - bdev_zoned_model(bdev) == BLK_ZONED_HM ? "managed" : "aware", - rcu_str_deref(device->name), zone_info->nr_zones, - zone_info->zone_size); + switch (bdev_zoned_model(bdev)) { + case BLK_ZONED_HM: + model = "host-managed zoned"; + emulated = ""; + break; + case BLK_ZONED_HA: + model = "host-aware zoned"; + emulated = ""; + break; + case BLK_ZONED_NONE: + model = "regular"; + emulated = "emulated "; + break; + default: + /* Just in case */ + btrfs_err_in_rcu(fs_info, "zoned: unsupported model %d on %s", + bdev_zoned_model(bdev), + rcu_str_deref(device->name)); + ret = -EOPNOTSUPP; + goto out_free_zone_info; + } + + btrfs_info_in_rcu(fs_info, + "%s block device %s, %u %szones of %llu bytes", + model, rcu_str_deref(device->name), zone_info->nr_zones, + emulated, zone_info->zone_size); return 0; out: kfree(zones); +out_free_zone_info: bitmap_free(zone_info->empty_zones); bitmap_free(zone_info->seq_zones); kfree(zone_info); + device->zone_info = NULL; return ret; } @@ -324,7 +480,7 @@ int btrfs_check_zoned_mode(struct btrfs_fs_info *fs_info) u64 nr_devices = 0; u64 zone_size = 0; u64 max_zone_append_size = 0; - const bool incompat_zoned = btrfs_is_zoned(fs_info); + const bool incompat_zoned = btrfs_fs_incompat(fs_info, ZONED); int ret = 0; /* Count zoned devices */ @@ -335,9 +491,17 @@ int btrfs_check_zoned_mode(struct btrfs_fs_info *fs_info) continue; model = bdev_zoned_model(device->bdev); + /* + * A Host-Managed zoned device must be used as a zoned device. + * A Host-Aware zoned device and a non-zoned devices can be + * treated as a zoned device, if ZONED flag is enabled in the + * superblock. + */ if (model == BLK_ZONED_HM || - (model == BLK_ZONED_HA && incompat_zoned)) { - struct btrfs_zoned_device_info *zone_info; + (model == BLK_ZONED_HA && incompat_zoned) || + (model == BLK_ZONED_NONE && incompat_zoned)) { + struct btrfs_zoned_device_info *zone_info = + device->zone_info; zone_info = device->zone_info; zoned_devices++; @@ -406,6 +570,15 @@ int btrfs_check_zoned_mode(struct btrfs_fs_info *fs_info) fs_info->zone_size = zone_size; fs_info->max_zone_append_size = max_zone_append_size; + fs_info->fs_devices->chunk_alloc_policy = BTRFS_CHUNK_ALLOC_ZONED; + + /* + * Check mount options here, because we might change fs_info->zoned + * from fs_info->zone_size. + */ + ret = btrfs_check_mountopts_zoned(fs_info); + if (ret) + goto out; btrfs_info(fs_info, "zoned mode enabled with zone size %llu", zone_size); out: @@ -488,7 +661,6 @@ int btrfs_sb_log_location_bdev(struct block_device *bdev, int mirror, int rw, unsigned int zone_sectors; u32 sb_zone; int ret; - u64 zone_size; u8 zone_sectors_shift; sector_t nr_sectors; u32 nr_zones; @@ -503,7 +675,6 @@ int btrfs_sb_log_location_bdev(struct block_device *bdev, int mirror, int rw, zone_sectors = bdev_zone_sectors(bdev); if (!is_power_of_2(zone_sectors)) return -EINVAL; - zone_size = zone_sectors << SECTOR_SHIFT; zone_sectors_shift = ilog2(zone_sectors); nr_sectors = bdev_nr_sectors(bdev); nr_zones = nr_sectors >> zone_sectors_shift; @@ -529,7 +700,13 @@ int btrfs_sb_log_location(struct btrfs_device *device, int mirror, int rw, struct btrfs_zoned_device_info *zinfo = device->zone_info; u32 zone_num; - if (!zinfo) { + /* + * For a zoned filesystem on a non-zoned block device, use the same + * super block locations as regular filesystem. Doing so, the super + * block can always be retrieved and the zoned flag of the volume + * detected from the super block information. + */ + if (!bdev_is_zoned(device->bdev)) { *bytenr_ret = btrfs_sb_offset(mirror); return 0; } @@ -614,3 +791,671 @@ int btrfs_reset_sb_log_zones(struct block_device *bdev, int mirror) sb_zone << zone_sectors_shift, zone_sectors * BTRFS_NR_SB_LOG_ZONES, GFP_NOFS); } + +/** + * btrfs_find_allocatable_zones - find allocatable zones within a given region + * + * @device: the device to allocate a region on + * @hole_start: the position of the hole to allocate the region + * @num_bytes: size of wanted region + * @hole_end: the end of the hole + * @return: position of allocatable zones + * + * Allocatable region should not contain any superblock locations. + */ +u64 btrfs_find_allocatable_zones(struct btrfs_device *device, u64 hole_start, + u64 hole_end, u64 num_bytes) +{ + struct btrfs_zoned_device_info *zinfo = device->zone_info; + const u8 shift = zinfo->zone_size_shift; + u64 nzones = num_bytes >> shift; + u64 pos = hole_start; + u64 begin, end; + bool have_sb; + int i; + + ASSERT(IS_ALIGNED(hole_start, zinfo->zone_size)); + ASSERT(IS_ALIGNED(num_bytes, zinfo->zone_size)); + + while (pos < hole_end) { + begin = pos >> shift; + end = begin + nzones; + + if (end > zinfo->nr_zones) + return hole_end; + + /* Check if zones in the region are all empty */ + if (btrfs_dev_is_sequential(device, pos) && + find_next_zero_bit(zinfo->empty_zones, end, begin) != end) { + pos += zinfo->zone_size; + continue; + } + + have_sb = false; + for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) { + u32 sb_zone; + u64 sb_pos; + + sb_zone = sb_zone_number(shift, i); + if (!(end <= sb_zone || + sb_zone + BTRFS_NR_SB_LOG_ZONES <= begin)) { + have_sb = true; + pos = ((u64)sb_zone + BTRFS_NR_SB_LOG_ZONES) << shift; + break; + } + + /* We also need to exclude regular superblock positions */ + sb_pos = btrfs_sb_offset(i); + if (!(pos + num_bytes <= sb_pos || + sb_pos + BTRFS_SUPER_INFO_SIZE <= pos)) { + have_sb = true; + pos = ALIGN(sb_pos + BTRFS_SUPER_INFO_SIZE, + zinfo->zone_size); + break; + } + } + if (!have_sb) + break; + } + + return pos; +} + +int btrfs_reset_device_zone(struct btrfs_device *device, u64 physical, + u64 length, u64 *bytes) +{ + int ret; + + *bytes = 0; + ret = blkdev_zone_mgmt(device->bdev, REQ_OP_ZONE_RESET, + physical >> SECTOR_SHIFT, length >> SECTOR_SHIFT, + GFP_NOFS); + if (ret) + return ret; + + *bytes = length; + while (length) { + btrfs_dev_set_zone_empty(device, physical); + physical += device->zone_info->zone_size; + length -= device->zone_info->zone_size; + } + + return 0; +} + +int btrfs_ensure_empty_zones(struct btrfs_device *device, u64 start, u64 size) +{ + struct btrfs_zoned_device_info *zinfo = device->zone_info; + const u8 shift = zinfo->zone_size_shift; + unsigned long begin = start >> shift; + unsigned long end = (start + size) >> shift; + u64 pos; + int ret; + + ASSERT(IS_ALIGNED(start, zinfo->zone_size)); + ASSERT(IS_ALIGNED(size, zinfo->zone_size)); + + if (end > zinfo->nr_zones) + return -ERANGE; + + /* All the zones are conventional */ + if (find_next_bit(zinfo->seq_zones, begin, end) == end) + return 0; + + /* All the zones are sequential and empty */ + if (find_next_zero_bit(zinfo->seq_zones, begin, end) == end && + find_next_zero_bit(zinfo->empty_zones, begin, end) == end) + return 0; + + for (pos = start; pos < start + size; pos += zinfo->zone_size) { + u64 reset_bytes; + + if (!btrfs_dev_is_sequential(device, pos) || + btrfs_dev_is_empty_zone(device, pos)) + continue; + + /* Free regions should be empty */ + btrfs_warn_in_rcu( + device->fs_info, + "zoned: resetting device %s (devid %llu) zone %llu for allocation", + rcu_str_deref(device->name), device->devid, pos >> shift); + WARN_ON_ONCE(1); + + ret = btrfs_reset_device_zone(device, pos, zinfo->zone_size, + &reset_bytes); + if (ret) + return ret; + } + + return 0; +} + +/* + * Calculate an allocation pointer from the extent allocation information + * for a block group consist of conventional zones. It is pointed to the + * end of the highest addressed extent in the block group as an allocation + * offset. + */ +static int calculate_alloc_pointer(struct btrfs_block_group *cache, + u64 *offset_ret) +{ + struct btrfs_fs_info *fs_info = cache->fs_info; + struct btrfs_root *root = fs_info->extent_root; + struct btrfs_path *path; + struct btrfs_key key; + struct btrfs_key found_key; + int ret; + u64 length; + + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + + key.objectid = cache->start + cache->length; + key.type = 0; + key.offset = 0; + + ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); + /* We should not find the exact match */ + if (!ret) + ret = -EUCLEAN; + if (ret < 0) + goto out; + + ret = btrfs_previous_extent_item(root, path, cache->start); + if (ret) { + if (ret == 1) { + ret = 0; + *offset_ret = 0; + } + goto out; + } + + btrfs_item_key_to_cpu(path->nodes[0], &found_key, path->slots[0]); + + if (found_key.type == BTRFS_EXTENT_ITEM_KEY) + length = found_key.offset; + else + length = fs_info->nodesize; + + if (!(found_key.objectid >= cache->start && + found_key.objectid + length <= cache->start + cache->length)) { + ret = -EUCLEAN; + goto out; + } + *offset_ret = found_key.objectid + length - cache->start; + ret = 0; + +out: + btrfs_free_path(path); + return ret; +} + +int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new) +{ + struct btrfs_fs_info *fs_info = cache->fs_info; + struct extent_map_tree *em_tree = &fs_info->mapping_tree; + struct extent_map *em; + struct map_lookup *map; + struct btrfs_device *device; + u64 logical = cache->start; + u64 length = cache->length; + u64 physical = 0; + int ret; + int i; + unsigned int nofs_flag; + u64 *alloc_offsets = NULL; + u64 last_alloc = 0; + u32 num_sequential = 0, num_conventional = 0; + + if (!btrfs_is_zoned(fs_info)) + return 0; + + /* Sanity check */ + if (!IS_ALIGNED(length, fs_info->zone_size)) { + btrfs_err(fs_info, + "zoned: block group %llu len %llu unaligned to zone size %llu", + logical, length, fs_info->zone_size); + return -EIO; + } + + /* Get the chunk mapping */ + read_lock(&em_tree->lock); + em = lookup_extent_mapping(em_tree, logical, length); + read_unlock(&em_tree->lock); + + if (!em) + return -EINVAL; + + map = em->map_lookup; + + alloc_offsets = kcalloc(map->num_stripes, sizeof(*alloc_offsets), GFP_NOFS); + if (!alloc_offsets) { + free_extent_map(em); + return -ENOMEM; + } + + for (i = 0; i < map->num_stripes; i++) { + bool is_sequential; + struct blk_zone zone; + struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace; + int dev_replace_is_ongoing = 0; + + device = map->stripes[i].dev; + physical = map->stripes[i].physical; + + if (device->bdev == NULL) { + alloc_offsets[i] = WP_MISSING_DEV; + continue; + } + + is_sequential = btrfs_dev_is_sequential(device, physical); + if (is_sequential) + num_sequential++; + else + num_conventional++; + + if (!is_sequential) { + alloc_offsets[i] = WP_CONVENTIONAL; + continue; + } + + /* + * This zone will be used for allocation, so mark this zone + * non-empty. + */ + btrfs_dev_clear_zone_empty(device, physical); + + down_read(&dev_replace->rwsem); + dev_replace_is_ongoing = btrfs_dev_replace_is_ongoing(dev_replace); + if (dev_replace_is_ongoing && dev_replace->tgtdev != NULL) + btrfs_dev_clear_zone_empty(dev_replace->tgtdev, physical); + up_read(&dev_replace->rwsem); + + /* + * The group is mapped to a sequential zone. Get the zone write + * pointer to determine the allocation offset within the zone. + */ + WARN_ON(!IS_ALIGNED(physical, fs_info->zone_size)); + nofs_flag = memalloc_nofs_save(); + ret = btrfs_get_dev_zone(device, physical, &zone); + memalloc_nofs_restore(nofs_flag); + if (ret == -EIO || ret == -EOPNOTSUPP) { + ret = 0; + alloc_offsets[i] = WP_MISSING_DEV; + continue; + } else if (ret) { + goto out; + } + + switch (zone.cond) { + case BLK_ZONE_COND_OFFLINE: + case BLK_ZONE_COND_READONLY: + btrfs_err(fs_info, + "zoned: offline/readonly zone %llu on device %s (devid %llu)", + physical >> device->zone_info->zone_size_shift, + rcu_str_deref(device->name), device->devid); + alloc_offsets[i] = WP_MISSING_DEV; + break; + case BLK_ZONE_COND_EMPTY: + alloc_offsets[i] = 0; + break; + case BLK_ZONE_COND_FULL: + alloc_offsets[i] = fs_info->zone_size; + break; + default: + /* Partially used zone */ + alloc_offsets[i] = + ((zone.wp - zone.start) << SECTOR_SHIFT); + break; + } + } + + if (num_sequential > 0) + cache->seq_zone = true; + + if (num_conventional > 0) { + /* + * Avoid calling calculate_alloc_pointer() for new BG. It + * is no use for new BG. It must be always 0. + * + * Also, we have a lock chain of extent buffer lock -> + * chunk mutex. For new BG, this function is called from + * btrfs_make_block_group() which is already taking the + * chunk mutex. Thus, we cannot call + * calculate_alloc_pointer() which takes extent buffer + * locks to avoid deadlock. + */ + if (new) { + cache->alloc_offset = 0; + goto out; + } + ret = calculate_alloc_pointer(cache, &last_alloc); + if (ret || map->num_stripes == num_conventional) { + if (!ret) + cache->alloc_offset = last_alloc; + else + btrfs_err(fs_info, + "zoned: failed to determine allocation offset of bg %llu", + cache->start); + goto out; + } + } + + switch (map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK) { + case 0: /* single */ + cache->alloc_offset = alloc_offsets[0]; + break; + case BTRFS_BLOCK_GROUP_DUP: + case BTRFS_BLOCK_GROUP_RAID1: + case BTRFS_BLOCK_GROUP_RAID0: + case BTRFS_BLOCK_GROUP_RAID10: + case BTRFS_BLOCK_GROUP_RAID5: + case BTRFS_BLOCK_GROUP_RAID6: + /* non-single profiles are not supported yet */ + default: + btrfs_err(fs_info, "zoned: profile %s not yet supported", + btrfs_bg_type_to_raid_name(map->type)); + ret = -EINVAL; + goto out; + } + +out: + /* An extent is allocated after the write pointer */ + if (!ret && num_conventional && last_alloc > cache->alloc_offset) { + btrfs_err(fs_info, + "zoned: got wrong write pointer in BG %llu: %llu > %llu", + logical, last_alloc, cache->alloc_offset); + ret = -EIO; + } + + if (!ret) + cache->meta_write_pointer = cache->alloc_offset + cache->start; + + kfree(alloc_offsets); + free_extent_map(em); + + return ret; +} + +void btrfs_calc_zone_unusable(struct btrfs_block_group *cache) +{ + u64 unusable, free; + + if (!btrfs_is_zoned(cache->fs_info)) + return; + + WARN_ON(cache->bytes_super != 0); + unusable = cache->alloc_offset - cache->used; + free = cache->length - cache->alloc_offset; + + /* We only need ->free_space in ALLOC_SEQ block groups */ + cache->last_byte_to_unpin = (u64)-1; + cache->cached = BTRFS_CACHE_FINISHED; + cache->free_space_ctl->free_space = free; + cache->zone_unusable = unusable; + + /* Should not have any excluded extents. Just in case, though */ + btrfs_free_excluded_extents(cache); +} + +void btrfs_redirty_list_add(struct btrfs_transaction *trans, + struct extent_buffer *eb) +{ + struct btrfs_fs_info *fs_info = eb->fs_info; + + if (!btrfs_is_zoned(fs_info) || + btrfs_header_flag(eb, BTRFS_HEADER_FLAG_WRITTEN) || + !list_empty(&eb->release_list)) + return; + + set_extent_buffer_dirty(eb); + set_extent_bits_nowait(&trans->dirty_pages, eb->start, + eb->start + eb->len - 1, EXTENT_DIRTY); + memzero_extent_buffer(eb, 0, eb->len); + set_bit(EXTENT_BUFFER_NO_CHECK, &eb->bflags); + + spin_lock(&trans->releasing_ebs_lock); + list_add_tail(&eb->release_list, &trans->releasing_ebs); + spin_unlock(&trans->releasing_ebs_lock); + atomic_inc(&eb->refs); +} + +void btrfs_free_redirty_list(struct btrfs_transaction *trans) +{ + spin_lock(&trans->releasing_ebs_lock); + while (!list_empty(&trans->releasing_ebs)) { + struct extent_buffer *eb; + + eb = list_first_entry(&trans->releasing_ebs, + struct extent_buffer, release_list); + list_del_init(&eb->release_list); + free_extent_buffer(eb); + } + spin_unlock(&trans->releasing_ebs_lock); +} + +bool btrfs_use_zone_append(struct btrfs_inode *inode, struct extent_map *em) +{ + struct btrfs_fs_info *fs_info = inode->root->fs_info; + struct btrfs_block_group *cache; + bool ret = false; + + if (!btrfs_is_zoned(fs_info)) + return false; + + if (!fs_info->max_zone_append_size) + return false; + + if (!is_data_inode(&inode->vfs_inode)) + return false; + + cache = btrfs_lookup_block_group(fs_info, em->block_start); + ASSERT(cache); + if (!cache) + return false; + + ret = cache->seq_zone; + btrfs_put_block_group(cache); + + return ret; +} + +void btrfs_record_physical_zoned(struct inode *inode, u64 file_offset, + struct bio *bio) +{ + struct btrfs_ordered_extent *ordered; + const u64 physical = bio->bi_iter.bi_sector << SECTOR_SHIFT; + + if (bio_op(bio) != REQ_OP_ZONE_APPEND) + return; + + ordered = btrfs_lookup_ordered_extent(BTRFS_I(inode), file_offset); + if (WARN_ON(!ordered)) + return; + + ordered->physical = physical; + ordered->disk = bio->bi_bdev->bd_disk; + ordered->partno = bio->bi_bdev->bd_partno; + + btrfs_put_ordered_extent(ordered); +} + +void btrfs_rewrite_logical_zoned(struct btrfs_ordered_extent *ordered) +{ + struct btrfs_inode *inode = BTRFS_I(ordered->inode); + struct btrfs_fs_info *fs_info = inode->root->fs_info; + struct extent_map_tree *em_tree; + struct extent_map *em; + struct btrfs_ordered_sum *sum; + struct block_device *bdev; + u64 orig_logical = ordered->disk_bytenr; + u64 *logical = NULL; + int nr, stripe_len; + + /* Zoned devices should not have partitions. So, we can assume it is 0 */ + ASSERT(ordered->partno == 0); + bdev = bdgrab(ordered->disk->part0); + if (WARN_ON(!bdev)) + return; + + if (WARN_ON(btrfs_rmap_block(fs_info, orig_logical, bdev, + ordered->physical, &logical, &nr, + &stripe_len))) + goto out; + + WARN_ON(nr != 1); + + if (orig_logical == *logical) + goto out; + + ordered->disk_bytenr = *logical; + + em_tree = &inode->extent_tree; + write_lock(&em_tree->lock); + em = search_extent_mapping(em_tree, ordered->file_offset, + ordered->num_bytes); + em->block_start = *logical; + free_extent_map(em); + write_unlock(&em_tree->lock); + + list_for_each_entry(sum, &ordered->list, list) { + if (*logical < orig_logical) + sum->bytenr -= orig_logical - *logical; + else + sum->bytenr += *logical - orig_logical; + } + +out: + kfree(logical); + bdput(bdev); +} + +bool btrfs_check_meta_write_pointer(struct btrfs_fs_info *fs_info, + struct extent_buffer *eb, + struct btrfs_block_group **cache_ret) +{ + struct btrfs_block_group *cache; + bool ret = true; + + if (!btrfs_is_zoned(fs_info)) + return true; + + cache = *cache_ret; + + if (cache && (eb->start < cache->start || + cache->start + cache->length <= eb->start)) { + btrfs_put_block_group(cache); + cache = NULL; + *cache_ret = NULL; + } + + if (!cache) + cache = btrfs_lookup_block_group(fs_info, eb->start); + + if (cache) { + if (cache->meta_write_pointer != eb->start) { + btrfs_put_block_group(cache); + cache = NULL; + ret = false; + } else { + cache->meta_write_pointer = eb->start + eb->len; + } + + *cache_ret = cache; + } + + return ret; +} + +void btrfs_revert_meta_write_pointer(struct btrfs_block_group *cache, + struct extent_buffer *eb) +{ + if (!btrfs_is_zoned(eb->fs_info) || !cache) + return; + + ASSERT(cache->meta_write_pointer == eb->start + eb->len); + cache->meta_write_pointer = eb->start; +} + +int btrfs_zoned_issue_zeroout(struct btrfs_device *device, u64 physical, u64 length) +{ + if (!btrfs_dev_is_sequential(device, physical)) + return -EOPNOTSUPP; + + return blkdev_issue_zeroout(device->bdev, physical >> SECTOR_SHIFT, + length >> SECTOR_SHIFT, GFP_NOFS, 0); +} + +static int read_zone_info(struct btrfs_fs_info *fs_info, u64 logical, + struct blk_zone *zone) +{ + struct btrfs_bio *bbio = NULL; + u64 mapped_length = PAGE_SIZE; + unsigned int nofs_flag; + int nmirrors; + int i, ret; + + ret = btrfs_map_sblock(fs_info, BTRFS_MAP_GET_READ_MIRRORS, logical, + &mapped_length, &bbio); + if (ret || !bbio || mapped_length < PAGE_SIZE) { + btrfs_put_bbio(bbio); + return -EIO; + } + + if (bbio->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK) + return -EINVAL; + + nofs_flag = memalloc_nofs_save(); + nmirrors = (int)bbio->num_stripes; + for (i = 0; i < nmirrors; i++) { + u64 physical = bbio->stripes[i].physical; + struct btrfs_device *dev = bbio->stripes[i].dev; + + /* Missing device */ + if (!dev->bdev) + continue; + + ret = btrfs_get_dev_zone(dev, physical, zone); + /* Failing device */ + if (ret == -EIO || ret == -EOPNOTSUPP) + continue; + break; + } + memalloc_nofs_restore(nofs_flag); + + return ret; +} + +/* + * Synchronize write pointer in a zone at @physical_start on @tgt_dev, by + * filling zeros between @physical_pos to a write pointer of dev-replace + * source device. + */ +int btrfs_sync_zone_write_pointer(struct btrfs_device *tgt_dev, u64 logical, + u64 physical_start, u64 physical_pos) +{ + struct btrfs_fs_info *fs_info = tgt_dev->fs_info; + struct blk_zone zone; + u64 length; + u64 wp; + int ret; + + if (!btrfs_dev_is_sequential(tgt_dev, physical_pos)) + return 0; + + ret = read_zone_info(fs_info, logical, &zone); + if (ret) + return ret; + + wp = physical_start + ((zone.wp - zone.start) << SECTOR_SHIFT); + + if (physical_pos == wp) + return 0; + + if (physical_pos > wp) + return -EUCLEAN; + + length = wp - physical_pos; + return btrfs_zoned_issue_zeroout(tgt_dev, physical_pos, length); +} diff --git a/fs/btrfs/zoned.h b/fs/btrfs/zoned.h index 8abe2f83272b..61e969652fe1 100644 --- a/fs/btrfs/zoned.h +++ b/fs/btrfs/zoned.h @@ -7,6 +7,7 @@ #include <linux/blkdev.h> #include "volumes.h" #include "disk-io.h" +#include "block-group.h" struct btrfs_zoned_device_info { /* @@ -25,6 +26,7 @@ struct btrfs_zoned_device_info { #ifdef CONFIG_BLK_DEV_ZONED int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos, struct blk_zone *zone); +int btrfs_get_dev_zone_info_all_devices(struct btrfs_fs_info *fs_info); int btrfs_get_dev_zone_info(struct btrfs_device *device); void btrfs_destroy_dev_zone_info(struct btrfs_device *device); int btrfs_check_zoned_mode(struct btrfs_fs_info *fs_info); @@ -35,6 +37,28 @@ int btrfs_sb_log_location(struct btrfs_device *device, int mirror, int rw, u64 *bytenr_ret); void btrfs_advance_sb_log(struct btrfs_device *device, int mirror); int btrfs_reset_sb_log_zones(struct block_device *bdev, int mirror); +u64 btrfs_find_allocatable_zones(struct btrfs_device *device, u64 hole_start, + u64 hole_end, u64 num_bytes); +int btrfs_reset_device_zone(struct btrfs_device *device, u64 physical, + u64 length, u64 *bytes); +int btrfs_ensure_empty_zones(struct btrfs_device *device, u64 start, u64 size); +int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new); +void btrfs_calc_zone_unusable(struct btrfs_block_group *cache); +void btrfs_redirty_list_add(struct btrfs_transaction *trans, + struct extent_buffer *eb); +void btrfs_free_redirty_list(struct btrfs_transaction *trans); +bool btrfs_use_zone_append(struct btrfs_inode *inode, struct extent_map *em); +void btrfs_record_physical_zoned(struct inode *inode, u64 file_offset, + struct bio *bio); +void btrfs_rewrite_logical_zoned(struct btrfs_ordered_extent *ordered); +bool btrfs_check_meta_write_pointer(struct btrfs_fs_info *fs_info, + struct extent_buffer *eb, + struct btrfs_block_group **cache_ret); +void btrfs_revert_meta_write_pointer(struct btrfs_block_group *cache, + struct extent_buffer *eb); +int btrfs_zoned_issue_zeroout(struct btrfs_device *device, u64 physical, u64 length); +int btrfs_sync_zone_write_pointer(struct btrfs_device *tgt_dev, u64 logical, + u64 physical_start, u64 physical_pos); #else /* CONFIG_BLK_DEV_ZONED */ static inline int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos, struct blk_zone *zone) @@ -42,6 +66,11 @@ static inline int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos, return 0; } +static inline int btrfs_get_dev_zone_info_all_devices(struct btrfs_fs_info *fs_info) +{ + return 0; +} + static inline int btrfs_get_dev_zone_info(struct btrfs_device *device) { return 0; @@ -85,6 +114,78 @@ static inline int btrfs_reset_sb_log_zones(struct block_device *bdev, int mirror return 0; } +static inline u64 btrfs_find_allocatable_zones(struct btrfs_device *device, + u64 hole_start, u64 hole_end, + u64 num_bytes) +{ + return hole_start; +} + +static inline int btrfs_reset_device_zone(struct btrfs_device *device, + u64 physical, u64 length, u64 *bytes) +{ + *bytes = 0; + return 0; +} + +static inline int btrfs_ensure_empty_zones(struct btrfs_device *device, + u64 start, u64 size) +{ + return 0; +} + +static inline int btrfs_load_block_group_zone_info( + struct btrfs_block_group *cache, bool new) +{ + return 0; +} + +static inline void btrfs_calc_zone_unusable(struct btrfs_block_group *cache) { } + +static inline void btrfs_redirty_list_add(struct btrfs_transaction *trans, + struct extent_buffer *eb) { } +static inline void btrfs_free_redirty_list(struct btrfs_transaction *trans) { } + +static inline bool btrfs_use_zone_append(struct btrfs_inode *inode, + struct extent_map *em) +{ + return false; +} + +static inline void btrfs_record_physical_zoned(struct inode *inode, + u64 file_offset, struct bio *bio) +{ +} + +static inline void btrfs_rewrite_logical_zoned( + struct btrfs_ordered_extent *ordered) { } + +static inline bool btrfs_check_meta_write_pointer(struct btrfs_fs_info *fs_info, + struct extent_buffer *eb, + struct btrfs_block_group **cache_ret) +{ + return true; +} + +static inline void btrfs_revert_meta_write_pointer( + struct btrfs_block_group *cache, + struct extent_buffer *eb) +{ +} + +static inline int btrfs_zoned_issue_zeroout(struct btrfs_device *device, + u64 physical, u64 length) +{ + return -EOPNOTSUPP; +} + +static inline int btrfs_sync_zone_write_pointer(struct btrfs_device *tgt_dev, + u64 logical, u64 physical_start, + u64 physical_pos) +{ + return -EOPNOTSUPP; +} + #endif static inline bool btrfs_dev_is_sequential(struct btrfs_device *device, u64 pos) @@ -136,12 +237,16 @@ static inline void btrfs_dev_clear_zone_empty(struct btrfs_device *device, u64 p static inline bool btrfs_check_device_zone_type(const struct btrfs_fs_info *fs_info, struct block_device *bdev) { - u64 zone_size; - if (btrfs_is_zoned(fs_info)) { - zone_size = bdev_zone_sectors(bdev) << SECTOR_SHIFT; - /* Do not allow non-zoned device */ - return bdev_is_zoned(bdev) && fs_info->zone_size == zone_size; + /* + * We can allow a regular device on a zoned filesystem, because + * we will emulate the zoned capabilities. + */ + if (!bdev_is_zoned(bdev)) + return true; + + return fs_info->zone_size == + (bdev_zone_sectors(bdev) << SECTOR_SHIFT); } /* Do not allow Host Manged zoned device */ @@ -157,4 +262,46 @@ static inline bool btrfs_check_super_location(struct btrfs_device *device, u64 p return device->zone_info == NULL || !btrfs_dev_is_sequential(device, pos); } +static inline bool btrfs_can_zone_reset(struct btrfs_device *device, + u64 physical, u64 length) +{ + u64 zone_size; + + if (!btrfs_dev_is_sequential(device, physical)) + return false; + + zone_size = device->zone_info->zone_size; + if (!IS_ALIGNED(physical, zone_size) || !IS_ALIGNED(length, zone_size)) + return false; + + return true; +} + +static inline void btrfs_zoned_meta_io_lock(struct btrfs_fs_info *fs_info) +{ + if (!btrfs_is_zoned(fs_info)) + return; + mutex_lock(&fs_info->zoned_meta_io_lock); +} + +static inline void btrfs_zoned_meta_io_unlock(struct btrfs_fs_info *fs_info) +{ + if (!btrfs_is_zoned(fs_info)) + return; + mutex_unlock(&fs_info->zoned_meta_io_lock); +} + +static inline void btrfs_clear_treelog_bg(struct btrfs_block_group *bg) +{ + struct btrfs_fs_info *fs_info = bg->fs_info; + + if (!btrfs_is_zoned(fs_info)) + return; + + spin_lock(&fs_info->treelog_bg_lock); + if (fs_info->treelog_bg == bg->start) + fs_info->treelog_bg = 0; + spin_unlock(&fs_info->treelog_bg_lock); +} + #endif diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c index 8bda092e60c5..e027c718ca01 100644 --- a/fs/cachefiles/rdwr.c +++ b/fs/cachefiles/rdwr.c @@ -413,7 +413,6 @@ int cachefiles_read_or_alloc_page(struct fscache_retrieval *op, inode = d_backing_inode(object->backer); ASSERT(S_ISREG(inode->i_mode)); - ASSERT(inode->i_mapping->a_ops->readpages); /* calculate the shift required to use bmap */ shift = PAGE_SHIFT - inode->i_sb->s_blocksize_bits; @@ -713,7 +712,6 @@ int cachefiles_read_or_alloc_pages(struct fscache_retrieval *op, inode = d_backing_inode(object->backer); ASSERT(S_ISREG(inode->i_mode)); - ASSERT(inode->i_mapping->a_ops->readpages); /* calculate the shift required to use bmap */ shift = PAGE_SHIFT - inode->i_sb->s_blocksize_bits; diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 840587037b59..d87bd852ed96 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -5038,7 +5038,7 @@ bad: return; } -static struct ceph_connection *con_get(struct ceph_connection *con) +static struct ceph_connection *mds_get_con(struct ceph_connection *con) { struct ceph_mds_session *s = con->private; @@ -5047,7 +5047,7 @@ static struct ceph_connection *con_get(struct ceph_connection *con) return NULL; } -static void con_put(struct ceph_connection *con) +static void mds_put_con(struct ceph_connection *con) { struct ceph_mds_session *s = con->private; @@ -5058,7 +5058,7 @@ static void con_put(struct ceph_connection *con) * if the client is unresponsive for long enough, the mds will kill * the session entirely. */ -static void peer_reset(struct ceph_connection *con) +static void mds_peer_reset(struct ceph_connection *con) { struct ceph_mds_session *s = con->private; struct ceph_mds_client *mdsc = s->s_mdsc; @@ -5067,7 +5067,7 @@ static void peer_reset(struct ceph_connection *con) send_mds_reconnect(mdsc, s); } -static void dispatch(struct ceph_connection *con, struct ceph_msg *msg) +static void mds_dispatch(struct ceph_connection *con, struct ceph_msg *msg) { struct ceph_mds_session *s = con->private; struct ceph_mds_client *mdsc = s->s_mdsc; @@ -5125,8 +5125,8 @@ out: * Note: returned pointer is the address of a structure that's * managed separately. Caller must *not* attempt to free it. */ -static struct ceph_auth_handshake *get_authorizer(struct ceph_connection *con, - int *proto, int force_new) +static struct ceph_auth_handshake * +mds_get_authorizer(struct ceph_connection *con, int *proto, int force_new) { struct ceph_mds_session *s = con->private; struct ceph_mds_client *mdsc = s->s_mdsc; @@ -5142,7 +5142,7 @@ static struct ceph_auth_handshake *get_authorizer(struct ceph_connection *con, return auth; } -static int add_authorizer_challenge(struct ceph_connection *con, +static int mds_add_authorizer_challenge(struct ceph_connection *con, void *challenge_buf, int challenge_buf_len) { struct ceph_mds_session *s = con->private; @@ -5153,7 +5153,7 @@ static int add_authorizer_challenge(struct ceph_connection *con, challenge_buf, challenge_buf_len); } -static int verify_authorizer_reply(struct ceph_connection *con) +static int mds_verify_authorizer_reply(struct ceph_connection *con) { struct ceph_mds_session *s = con->private; struct ceph_mds_client *mdsc = s->s_mdsc; @@ -5165,7 +5165,7 @@ static int verify_authorizer_reply(struct ceph_connection *con) NULL, NULL, NULL, NULL); } -static int invalidate_authorizer(struct ceph_connection *con) +static int mds_invalidate_authorizer(struct ceph_connection *con) { struct ceph_mds_session *s = con->private; struct ceph_mds_client *mdsc = s->s_mdsc; @@ -5288,15 +5288,15 @@ static int mds_check_message_signature(struct ceph_msg *msg) } static const struct ceph_connection_operations mds_con_ops = { - .get = con_get, - .put = con_put, - .dispatch = dispatch, - .get_authorizer = get_authorizer, - .add_authorizer_challenge = add_authorizer_challenge, - .verify_authorizer_reply = verify_authorizer_reply, - .invalidate_authorizer = invalidate_authorizer, - .peer_reset = peer_reset, + .get = mds_get_con, + .put = mds_put_con, .alloc_msg = mds_alloc_msg, + .dispatch = mds_dispatch, + .peer_reset = mds_peer_reset, + .get_authorizer = mds_get_authorizer, + .add_authorizer_challenge = mds_add_authorizer_challenge, + .verify_authorizer_reply = mds_verify_authorizer_reply, + .invalidate_authorizer = mds_invalidate_authorizer, .sign_message = mds_sign_message, .check_message_signature = mds_check_message_signature, .get_auth_request = mds_get_auth_request, diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c index e4c6ae47a796..6b1ce4efb591 100644 --- a/fs/cifs/cifs_dfs_ref.c +++ b/fs/cifs/cifs_dfs_ref.c @@ -133,8 +133,9 @@ cifs_build_devname(char *nodename, const char *prepath) * Caller is responsible for freeing returned value if it is not error. */ char *cifs_compose_mount_options(const char *sb_mountdata, - const char *fullpath, - const struct dfs_info3_param *ref) + const char *fullpath, + const struct dfs_info3_param *ref, + char **devname) { int rc; char *name; @@ -231,7 +232,10 @@ char *cifs_compose_mount_options(const char *sb_mountdata, strcat(mountdata, "ip="); strcat(mountdata, srvIP); - kfree(name); + if (devname) + *devname = name; + else + kfree(name); /*cifs_dbg(FYI, "%s: parent mountdata: %s\n", __func__, sb_mountdata);*/ /*cifs_dbg(FYI, "%s: submount mountdata: %s\n", __func__, mountdata );*/ @@ -278,7 +282,7 @@ static struct vfsmount *cifs_dfs_do_mount(struct dentry *mntpt, /* strip first '\' from fullpath */ mountdata = cifs_compose_mount_options(cifs_sb->ctx->mount_options, - fullpath + 1, NULL); + fullpath + 1, NULL, NULL); if (IS_ERR(mountdata)) { kfree(devname); return (struct vfsmount *)mountdata; diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index ce0d0037fd0a..ab883e84e116 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -469,7 +469,7 @@ cifs_show_cache_flavor(struct seq_file *s, struct cifs_sb_info *cifs_sb) static int cifs_show_devname(struct seq_file *m, struct dentry *root) { struct cifs_sb_info *cifs_sb = CIFS_SB(root->d_sb); - char *devname = kstrdup(cifs_sb->ctx->UNC, GFP_KERNEL); + char *devname = kstrdup(cifs_sb->ctx->source, GFP_KERNEL); if (devname == NULL) seq_puts(m, "none"); @@ -822,7 +822,7 @@ cifs_smb3_do_mount(struct file_system_type *fs_type, goto out; } - rc = cifs_setup_volume_info(cifs_sb->ctx); + rc = cifs_setup_volume_info(cifs_sb->ctx, NULL, old_ctx->UNC); if (rc) { root = ERR_PTR(rc); goto out; diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index 340ff81ee87b..32f7a013402e 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -78,7 +78,8 @@ extern char *cifs_build_path_to_root(struct smb3_fs_context *ctx, int add_treename); extern char *build_wildcard_path_from_dentry(struct dentry *direntry); extern char *cifs_compose_mount_options(const char *sb_mountdata, - const char *fullpath, const struct dfs_info3_param *ref); + const char *fullpath, const struct dfs_info3_param *ref, + char **devname); /* extern void renew_parental_timestamps(struct dentry *direntry);*/ extern struct mid_q_entry *AllocMidQEntry(const struct smb_hdr *smb_buffer, struct TCP_Server_Info *server); @@ -89,6 +90,7 @@ extern void cifs_wake_up_task(struct mid_q_entry *mid); extern int cifs_handle_standard(struct TCP_Server_Info *server, struct mid_q_entry *mid); extern int smb3_parse_devname(const char *devname, struct smb3_fs_context *ctx); +extern int smb3_parse_opt(const char *options, const char *key, char **val); extern bool cifs_match_ipaddr(struct sockaddr *srcaddr, struct sockaddr *rhs); extern int cifs_discard_remaining_data(struct TCP_Server_Info *server); extern int cifs_call_async(struct TCP_Server_Info *server, @@ -549,7 +551,7 @@ extern int SMBencrypt(unsigned char *passwd, const unsigned char *c8, unsigned char *p24); extern int -cifs_setup_volume_info(struct smb3_fs_context *ctx); +cifs_setup_volume_info(struct smb3_fs_context *ctx, const char *mntopts, const char *devname); extern struct TCP_Server_Info * cifs_find_tcp_session(struct smb3_fs_context *ctx); diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index b9df85506938..4bb9decbbf27 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -2195,7 +2195,7 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx) if (ses->server->capabilities & SMB2_GLOBAL_CAP_DIRECTORY_LEASING) tcon->nohandlecache = ctx->nohandlecache; else - tcon->nohandlecache = 1; + tcon->nohandlecache = true; tcon->nodelete = ctx->nodelete; tcon->local_lease = ctx->local_lease; INIT_LIST_HEAD(&tcon->pending_opens); @@ -2628,7 +2628,7 @@ void reset_cifs_unix_caps(unsigned int xid, struct cifs_tcon *tcon, } else if (ctx) tcon->unix_ext = 1; /* Unix Extensions supported */ - if (tcon->unix_ext == 0) { + if (!tcon->unix_ext) { cifs_dbg(FYI, "Unix extensions disabled so not set on reconnect\n"); return; } @@ -2756,6 +2756,7 @@ int cifs_setup_cifs_sb(struct cifs_sb_info *cifs_sb) cifs_sb->prepath = kstrdup(ctx->prepath, GFP_KERNEL); if (cifs_sb->prepath == NULL) return -ENOMEM; + cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_USE_PREFIX_PATH; } return 0; @@ -2972,17 +2973,28 @@ expand_dfs_referral(const unsigned int xid, struct cifs_ses *ses, rc = dfs_cache_find(xid, ses, cifs_sb->local_nls, cifs_remap(cifs_sb), ref_path, &referral, NULL); if (!rc) { + char *fake_devname = NULL; + mdata = cifs_compose_mount_options(cifs_sb->ctx->mount_options, - full_path + 1, &referral); + full_path + 1, &referral, + &fake_devname); free_dfs_info_param(&referral); if (IS_ERR(mdata)) { rc = PTR_ERR(mdata); mdata = NULL; } else { - smb3_cleanup_fs_context_contents(ctx); - rc = cifs_setup_volume_info(ctx); + /* + * We can not clear out the whole structure since we + * no longer have an explicit function to parse + * a mount-string. Instead we need to clear out the + * individual fields that are no longer valid. + */ + kfree(ctx->prepath); + ctx->prepath = NULL; + rc = cifs_setup_volume_info(ctx, mdata, fake_devname); } + kfree(fake_devname); kfree(cifs_sb->ctx->mount_options); cifs_sb->ctx->mount_options = mdata; } @@ -3036,6 +3048,7 @@ static int setup_dfs_tgt_conn(const char *path, const char *full_path, struct dfs_info3_param ref = {0}; char *mdata = NULL; struct smb3_fs_context fake_ctx = {NULL}; + char *fake_devname = NULL; cifs_dbg(FYI, "%s: dfs path: %s\n", __func__, path); @@ -3044,16 +3057,18 @@ static int setup_dfs_tgt_conn(const char *path, const char *full_path, return rc; mdata = cifs_compose_mount_options(cifs_sb->ctx->mount_options, - full_path + 1, &ref); + full_path + 1, &ref, + &fake_devname); free_dfs_info_param(&ref); if (IS_ERR(mdata)) { rc = PTR_ERR(mdata); mdata = NULL; } else - rc = cifs_setup_volume_info(&fake_ctx); + rc = cifs_setup_volume_info(&fake_ctx, mdata, fake_devname); kfree(mdata); + kfree(fake_devname); if (!rc) { /* @@ -3122,10 +3137,24 @@ static int do_dfs_failover(const char *path, const char *full_path, struct cifs_ * we should pass a clone of the original context? */ int -cifs_setup_volume_info(struct smb3_fs_context *ctx) +cifs_setup_volume_info(struct smb3_fs_context *ctx, const char *mntopts, const char *devname) { int rc = 0; + smb3_parse_devname(devname, ctx); + + if (mntopts) { + char *ip; + + cifs_dbg(FYI, "%s: mntopts=%s\n", __func__, mntopts); + rc = smb3_parse_opt(mntopts, "ip", &ip); + if (!rc && !cifs_convert_address((struct sockaddr *)&ctx->dstaddr, ip, + strlen(ip))) { + cifs_dbg(VFS, "%s: failed to convert ip address\n", __func__); + return -EINVAL; + } + } + if (ctx->nullauth) { cifs_dbg(FYI, "Anonymous login\n"); kfree(ctx->username); @@ -3740,7 +3769,7 @@ cifs_setup_session(const unsigned int xid, struct cifs_ses *ses, if (!ses->binding) { ses->capabilities = server->capabilities; - if (linuxExtEnabled == 0) + if (!linuxExtEnabled) ses->capabilities &= (~server->vals->cap_unix); if (ses->auth_key.response) { diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c index 6ad6ba5f6ebe..4950ab0486ae 100644 --- a/fs/cifs/dfs_cache.c +++ b/fs/cifs/dfs_cache.c @@ -1260,7 +1260,8 @@ void dfs_cache_del_vol(const char *fullpath) vi = find_vol(fullpath); spin_unlock(&vol_list_lock); - kref_put(&vi->refcnt, vol_release); + if (!IS_ERR(vi)) + kref_put(&vi->refcnt, vol_release); } /** @@ -1416,7 +1417,7 @@ static struct cifs_ses *find_root_ses(struct vol_info *vi, int rc; struct cache_entry *ce; struct dfs_info3_param ref = {0}; - char *mdata = NULL; + char *mdata = NULL, *devname = NULL; struct TCP_Server_Info *server; struct cifs_ses *ses; struct smb3_fs_context ctx = {NULL}; @@ -1443,7 +1444,8 @@ static struct cifs_ses *find_root_ses(struct vol_info *vi, up_read(&htable_rw_lock); - mdata = cifs_compose_mount_options(vi->mntdata, rpath, &ref); + mdata = cifs_compose_mount_options(vi->mntdata, rpath, &ref, + &devname); free_dfs_info_param(&ref); if (IS_ERR(mdata)) { @@ -1452,7 +1454,7 @@ static struct cifs_ses *find_root_ses(struct vol_info *vi, goto out; } - rc = cifs_setup_volume_info(&ctx); + rc = cifs_setup_volume_info(&ctx, NULL, devname); if (rc) { ses = ERR_PTR(rc); @@ -1471,6 +1473,7 @@ out: smb3_cleanup_fs_context_contents(&ctx); kfree(mdata); kfree(rpath); + kfree(devname); return ses; } diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index 68900f1629bf..97ac363b5df1 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -737,6 +737,7 @@ static int cifs_d_revalidate(struct dentry *direntry, unsigned int flags) { struct inode *inode; + int rc; if (flags & LOOKUP_RCU) return -ECHILD; @@ -746,8 +747,25 @@ cifs_d_revalidate(struct dentry *direntry, unsigned int flags) if ((flags & LOOKUP_REVAL) && !CIFS_CACHE_READ(CIFS_I(inode))) CIFS_I(inode)->time = 0; /* force reval */ - if (cifs_revalidate_dentry(direntry)) - return 0; + rc = cifs_revalidate_dentry(direntry); + if (rc) { + cifs_dbg(FYI, "cifs_revalidate_dentry failed with rc=%d", rc); + switch (rc) { + case -ENOENT: + case -ESTALE: + /* + * Those errors mean the dentry is invalid + * (file was deleted or recreated) + */ + return 0; + default: + /* + * Otherwise some unexpected error happened + * report it as-is to VFS layer + */ + return rc; + } + } else { /* * If the inode wasn't known to be a dfs entry when diff --git a/fs/cifs/fs_context.c b/fs/cifs/fs_context.c index 0afccbbed2e6..12a5da0230b5 100644 --- a/fs/cifs/fs_context.c +++ b/fs/cifs/fs_context.c @@ -148,7 +148,6 @@ const struct fs_parameter_spec smb3_fs_parameters[] = { /* Mount options which take string value */ fsparam_string("source", Opt_source), - fsparam_string("unc", Opt_source), fsparam_string("user", Opt_user), fsparam_string("username", Opt_user), fsparam_string("pass", Opt_pass), @@ -175,8 +174,15 @@ const struct fs_parameter_spec smb3_fs_parameters[] = { fsparam_flag_no("exec", Opt_ignore), fsparam_flag_no("dev", Opt_ignore), fsparam_flag_no("mand", Opt_ignore), + fsparam_flag_no("auto", Opt_ignore), fsparam_string("cred", Opt_ignore), fsparam_string("credentials", Opt_ignore), + /* + * UNC and prefixpath is now extracted from Opt_source + * in the new mount API so we can just ignore them going forward. + */ + fsparam_string("unc", Opt_ignore), + fsparam_string("prefixpath", Opt_ignore), {} }; @@ -303,8 +309,6 @@ do { \ int smb3_fs_context_dup(struct smb3_fs_context *new_ctx, struct smb3_fs_context *ctx) { - int rc = 0; - memcpy(new_ctx, ctx, sizeof(*ctx)); new_ctx->prepath = NULL; new_ctx->mount_options = NULL; @@ -313,6 +317,7 @@ smb3_fs_context_dup(struct smb3_fs_context *new_ctx, struct smb3_fs_context *ctx new_ctx->password = NULL; new_ctx->domainname = NULL; new_ctx->UNC = NULL; + new_ctx->source = NULL; new_ctx->iocharset = NULL; /* @@ -323,11 +328,12 @@ smb3_fs_context_dup(struct smb3_fs_context *new_ctx, struct smb3_fs_context *ctx DUP_CTX_STR(username); DUP_CTX_STR(password); DUP_CTX_STR(UNC); + DUP_CTX_STR(source); DUP_CTX_STR(domainname); DUP_CTX_STR(nodename); DUP_CTX_STR(iocharset); - return rc; + return 0; } static int @@ -401,6 +407,37 @@ cifs_parse_smb_version(char *value, struct smb3_fs_context *ctx, bool is_smb3) return 0; } +int smb3_parse_opt(const char *options, const char *key, char **val) +{ + int rc = -ENOENT; + char *opts, *orig, *p; + + orig = opts = kstrdup(options, GFP_KERNEL); + if (!opts) + return -ENOMEM; + + while ((p = strsep(&opts, ","))) { + char *nval; + + if (!*p) + continue; + if (strncasecmp(p, key, strlen(key))) + continue; + nval = strchr(p, '='); + if (nval) { + if (nval == p) + continue; + *nval++ = 0; + *val = kstrndup(nval, strlen(nval), GFP_KERNEL); + rc = !*val ? -ENOMEM : 0; + goto out; + } + } +out: + kfree(orig); + return rc; +} + /* * Parse a devname into substrings and populate the ctx->UNC and ctx->prepath * fields with the result. Returns 0 on success and an error otherwise @@ -533,7 +570,7 @@ static int smb3_fs_context_validate(struct fs_context *fc) if (ctx->rdma && ctx->vals->protocol_id < SMB30_PROT_ID) { cifs_dbg(VFS, "SMB Direct requires Version >=3.0\n"); - return -1; + return -EOPNOTSUPP; } #ifndef CONFIG_KEYS @@ -556,7 +593,7 @@ static int smb3_fs_context_validate(struct fs_context *fc) /* make sure UNC has a share name */ if (strlen(ctx->UNC) < 3 || !strchr(ctx->UNC + 3, '\\')) { cifs_dbg(VFS, "Malformed UNC. Unable to find share name.\n"); - return -1; + return -ENOENT; } if (!ctx->got_ip) { @@ -570,7 +607,7 @@ static int smb3_fs_context_validate(struct fs_context *fc) if (!cifs_convert_address((struct sockaddr *)&ctx->dstaddr, &ctx->UNC[2], len)) { pr_err("Unable to determine destination address\n"); - return -1; + return -EHOSTUNREACH; } } @@ -701,6 +738,7 @@ static int smb3_reconfigure(struct fs_context *fc) * just use what we already have in cifs_sb->ctx. */ STEAL_STRING(cifs_sb, ctx, UNC); + STEAL_STRING(cifs_sb, ctx, source); STEAL_STRING(cifs_sb, ctx, username); STEAL_STRING(cifs_sb, ctx, password); STEAL_STRING(cifs_sb, ctx, domainname); @@ -943,6 +981,11 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, cifs_dbg(VFS, "Unknown error parsing devname\n"); goto cifs_parse_mount_err; } + ctx->source = kstrdup(param->string, GFP_KERNEL); + if (ctx->source == NULL) { + cifs_dbg(VFS, "OOM when copying UNC string\n"); + goto cifs_parse_mount_err; + } fc->source = kstrdup(param->string, GFP_KERNEL); if (fc->source == NULL) { cifs_dbg(VFS, "OOM when copying UNC string\n"); @@ -1265,7 +1308,7 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, return 0; cifs_parse_mount_err: - return 1; + return -EINVAL; } int smb3_init_fs_context(struct fs_context *fc) @@ -1365,6 +1408,8 @@ smb3_cleanup_fs_context_contents(struct smb3_fs_context *ctx) ctx->password = NULL; kfree(ctx->UNC); ctx->UNC = NULL; + kfree(ctx->source); + ctx->source = NULL; kfree(ctx->domainname); ctx->domainname = NULL; kfree(ctx->nodename); @@ -1502,8 +1547,8 @@ void smb3_update_mnt_flags(struct cifs_sb_info *cifs_sb) cifs_sb->mnt_cifs_flags |= (CIFS_MOUNT_MULTIUSER | CIFS_MOUNT_NO_PERM); else - cifs_sb->mnt_cifs_flags &= ~(CIFS_MOUNT_MULTIUSER | - CIFS_MOUNT_NO_PERM); + cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_MULTIUSER; + if (ctx->strict_io) cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_STRICT_IO; diff --git a/fs/cifs/fs_context.h b/fs/cifs/fs_context.h index 3358b33abcd0..1c44a460e2c0 100644 --- a/fs/cifs/fs_context.h +++ b/fs/cifs/fs_context.h @@ -159,6 +159,7 @@ struct smb3_fs_context { char *username; char *password; char *domainname; + char *source; char *UNC; char *nodename; char *iocharset; /* local code page for mapping to and from Unicode */ diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 067eb44c7baa..794fc3b68b4f 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -3248,7 +3248,7 @@ close_exit: free_rsp_buf(resp_buftype, rsp); /* retry close in a worker thread if this one is interrupted */ - if (rc == -EINTR) { + if (is_interrupt_error(rc)) { int tmp_rc; tmp_rc = smb2_handle_cancelled_close(tcon, persistent_fid, diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index 204a622b89ed..a5a9e33c0d73 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -286,7 +286,7 @@ struct smb2_negotiate_req { __le32 NegotiateContextOffset; /* SMB3.1.1 only. MBZ earlier */ __le16 NegotiateContextCount; /* SMB3.1.1 only. MBZ earlier */ __le16 Reserved2; - __le16 Dialects[1]; /* One dialect (vers=) at a time for now */ + __le16 Dialects[4]; /* BB expand this if autonegotiate > 4 dialects */ } __packed; /* Dialects */ @@ -424,7 +424,7 @@ struct smb2_rdma_transform_capabilities_context { __le16 TransformCount; __u16 Reserved1; __u32 Reserved2; - __le16 RDMATransformIds[1]; + __le16 RDMATransformIds[]; } __packed; /* Signing algorithms */ diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index e9abb41aa89b..4a2b836eb017 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -338,7 +338,7 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst, if (ssocket == NULL) return -EAGAIN; - if (signal_pending(current)) { + if (fatal_signal_pending(current)) { cifs_dbg(FYI, "signal pending before send request\n"); return -ERESTARTSYS; } @@ -429,7 +429,7 @@ unmask: if (signal_pending(current) && (total_len != send_length)) { cifs_dbg(FYI, "signal is pending after attempt to send\n"); - rc = -EINTR; + rc = -ERESTARTSYS; } /* uncork it */ @@ -666,10 +666,22 @@ wait_for_compound_request(struct TCP_Server_Info *server, int num, if (*credits < num) { /* - * Return immediately if not too many requests in flight since - * we will likely be stuck on waiting for credits. + * If the server is tight on resources or just gives us less + * credits for other reasons (e.g. requests are coming out of + * order and the server delays granting more credits until it + * processes a missing mid) and we exhausted most available + * credits there may be situations when we try to send + * a compound request but we don't have enough credits. At this + * point the client needs to decide if it should wait for + * additional credits or fail the request. If at least one + * request is in flight there is a high probability that the + * server will return enough credits to satisfy this compound + * request. + * + * Return immediately if no requests in flight since we will be + * stuck on waiting for credits. */ - if (server->in_flight < num - *credits) { + if (server->in_flight == 0) { spin_unlock(&server->req_lock); trace_smb3_insufficient_credits(server->CurrentMid, server->hostname, scredits, sin_flight); diff --git a/fs/compat_binfmt_elf.c b/fs/compat_binfmt_elf.c index 2c557229696a..95e72d271b95 100644 --- a/fs/compat_binfmt_elf.c +++ b/fs/compat_binfmt_elf.c @@ -50,6 +50,7 @@ * which requires asm/elf.h to define compat_elf_gregset_t et al. */ #define elf_prstatus compat_elf_prstatus +#define elf_prstatus_common compat_elf_prstatus_common #define elf_prpsinfo compat_elf_prpsinfo #undef ns_to_kernel_old_timeval @@ -61,7 +62,6 @@ * differ from the native ones, or omitted when they match. */ -#undef ELF_ARCH #undef elf_check_arch #define elf_check_arch compat_elf_check_arch @@ -90,11 +90,6 @@ #define ELF_ET_DYN_BASE COMPAT_ELF_ET_DYN_BASE #endif -#ifdef COMPAT_ELF_EXEC_PAGESIZE -#undef ELF_EXEC_PAGESIZE -#define ELF_EXEC_PAGESIZE COMPAT_ELF_EXEC_PAGESIZE -#endif - #ifdef COMPAT_ELF_PLAT_INIT #undef ELF_PLAT_INIT #define ELF_PLAT_INIT COMPAT_ELF_PLAT_INIT @@ -810,11 +810,12 @@ static void dax_entry_mkclean(struct address_space *mapping, pgoff_t index, address = pgoff_address(index, vma); /* - * Note because we provide range to follow_pte it will call + * follow_invalidate_pte() will use the range to call * mmu_notifier_invalidate_range_start() on our behalf before * taking any lock. */ - if (follow_pte(vma->vm_mm, address, &range, &ptep, &pmdp, &ptl)) + if (follow_invalidate_pte(vma->vm_mm, address, &range, &ptep, + &pmdp, &ptl)) continue; /* diff --git a/fs/dcookies.c b/fs/dcookies.c deleted file mode 100644 index 6eeb61100a09..000000000000 --- a/fs/dcookies.c +++ /dev/null @@ -1,356 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * dcookies.c - * - * Copyright 2002 John Levon <levon@movementarian.org> - * - * Persistent cookie-path mappings. These are used by - * profilers to convert a per-task EIP value into something - * non-transitory that can be processed at a later date. - * This is done by locking the dentry/vfsmnt pair in the - * kernel until released by the tasks needing the persistent - * objects. The tag is simply an unsigned long that refers - * to the pair and can be looked up from userspace. - */ - -#include <linux/syscalls.h> -#include <linux/export.h> -#include <linux/slab.h> -#include <linux/list.h> -#include <linux/mount.h> -#include <linux/capability.h> -#include <linux/dcache.h> -#include <linux/mm.h> -#include <linux/err.h> -#include <linux/errno.h> -#include <linux/dcookies.h> -#include <linux/mutex.h> -#include <linux/path.h> -#include <linux/compat.h> -#include <linux/uaccess.h> - -/* The dcookies are allocated from a kmem_cache and - * hashed onto a small number of lists. None of the - * code here is particularly performance critical - */ -struct dcookie_struct { - struct path path; - struct list_head hash_list; -}; - -static LIST_HEAD(dcookie_users); -static DEFINE_MUTEX(dcookie_mutex); -static struct kmem_cache *dcookie_cache __read_mostly; -static struct list_head *dcookie_hashtable __read_mostly; -static size_t hash_size __read_mostly; - -static inline int is_live(void) -{ - return !(list_empty(&dcookie_users)); -} - - -/* The dentry is locked, its address will do for the cookie */ -static inline unsigned long dcookie_value(struct dcookie_struct * dcs) -{ - return (unsigned long)dcs->path.dentry; -} - - -static size_t dcookie_hash(unsigned long dcookie) -{ - return (dcookie >> L1_CACHE_SHIFT) & (hash_size - 1); -} - - -static struct dcookie_struct * find_dcookie(unsigned long dcookie) -{ - struct dcookie_struct *found = NULL; - struct dcookie_struct * dcs; - struct list_head * pos; - struct list_head * list; - - list = dcookie_hashtable + dcookie_hash(dcookie); - - list_for_each(pos, list) { - dcs = list_entry(pos, struct dcookie_struct, hash_list); - if (dcookie_value(dcs) == dcookie) { - found = dcs; - break; - } - } - - return found; -} - - -static void hash_dcookie(struct dcookie_struct * dcs) -{ - struct list_head * list = dcookie_hashtable + dcookie_hash(dcookie_value(dcs)); - list_add(&dcs->hash_list, list); -} - - -static struct dcookie_struct *alloc_dcookie(const struct path *path) -{ - struct dcookie_struct *dcs = kmem_cache_alloc(dcookie_cache, - GFP_KERNEL); - struct dentry *d; - if (!dcs) - return NULL; - - d = path->dentry; - spin_lock(&d->d_lock); - d->d_flags |= DCACHE_COOKIE; - spin_unlock(&d->d_lock); - - dcs->path = *path; - path_get(path); - hash_dcookie(dcs); - return dcs; -} - - -/* This is the main kernel-side routine that retrieves the cookie - * value for a dentry/vfsmnt pair. - */ -int get_dcookie(const struct path *path, unsigned long *cookie) -{ - int err = 0; - struct dcookie_struct * dcs; - - mutex_lock(&dcookie_mutex); - - if (!is_live()) { - err = -EINVAL; - goto out; - } - - if (path->dentry->d_flags & DCACHE_COOKIE) { - dcs = find_dcookie((unsigned long)path->dentry); - } else { - dcs = alloc_dcookie(path); - if (!dcs) { - err = -ENOMEM; - goto out; - } - } - - *cookie = dcookie_value(dcs); - -out: - mutex_unlock(&dcookie_mutex); - return err; -} - - -/* And here is where the userspace process can look up the cookie value - * to retrieve the path. - */ -static int do_lookup_dcookie(u64 cookie64, char __user *buf, size_t len) -{ - unsigned long cookie = (unsigned long)cookie64; - int err = -EINVAL; - char * kbuf; - char * path; - size_t pathlen; - struct dcookie_struct * dcs; - - /* we could leak path information to users - * without dir read permission without this - */ - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; - - mutex_lock(&dcookie_mutex); - - if (!is_live()) { - err = -EINVAL; - goto out; - } - - if (!(dcs = find_dcookie(cookie))) - goto out; - - err = -ENOMEM; - kbuf = kmalloc(PAGE_SIZE, GFP_KERNEL); - if (!kbuf) - goto out; - - /* FIXME: (deleted) ? */ - path = d_path(&dcs->path, kbuf, PAGE_SIZE); - - mutex_unlock(&dcookie_mutex); - - if (IS_ERR(path)) { - err = PTR_ERR(path); - goto out_free; - } - - err = -ERANGE; - - pathlen = kbuf + PAGE_SIZE - path; - if (pathlen <= len) { - err = pathlen; - if (copy_to_user(buf, path, pathlen)) - err = -EFAULT; - } - -out_free: - kfree(kbuf); - return err; -out: - mutex_unlock(&dcookie_mutex); - return err; -} - -SYSCALL_DEFINE3(lookup_dcookie, u64, cookie64, char __user *, buf, size_t, len) -{ - return do_lookup_dcookie(cookie64, buf, len); -} - -#ifdef CONFIG_COMPAT -COMPAT_SYSCALL_DEFINE4(lookup_dcookie, u32, w0, u32, w1, char __user *, buf, compat_size_t, len) -{ -#ifdef __BIG_ENDIAN - return do_lookup_dcookie(((u64)w0 << 32) | w1, buf, len); -#else - return do_lookup_dcookie(((u64)w1 << 32) | w0, buf, len); -#endif -} -#endif - -static int dcookie_init(void) -{ - struct list_head * d; - unsigned int i, hash_bits; - int err = -ENOMEM; - - dcookie_cache = kmem_cache_create("dcookie_cache", - sizeof(struct dcookie_struct), - 0, 0, NULL); - - if (!dcookie_cache) - goto out; - - dcookie_hashtable = kmalloc(PAGE_SIZE, GFP_KERNEL); - if (!dcookie_hashtable) - goto out_kmem; - - err = 0; - - /* - * Find the power-of-two list-heads that can fit into the allocation.. - * We don't guarantee that "sizeof(struct list_head)" is necessarily - * a power-of-two. - */ - hash_size = PAGE_SIZE / sizeof(struct list_head); - hash_bits = 0; - do { - hash_bits++; - } while ((hash_size >> hash_bits) != 0); - hash_bits--; - - /* - * Re-calculate the actual number of entries and the mask - * from the number of bits we can fit. - */ - hash_size = 1UL << hash_bits; - - /* And initialize the newly allocated array */ - d = dcookie_hashtable; - i = hash_size; - do { - INIT_LIST_HEAD(d); - d++; - i--; - } while (i); - -out: - return err; -out_kmem: - kmem_cache_destroy(dcookie_cache); - goto out; -} - - -static void free_dcookie(struct dcookie_struct * dcs) -{ - struct dentry *d = dcs->path.dentry; - - spin_lock(&d->d_lock); - d->d_flags &= ~DCACHE_COOKIE; - spin_unlock(&d->d_lock); - - path_put(&dcs->path); - kmem_cache_free(dcookie_cache, dcs); -} - - -static void dcookie_exit(void) -{ - struct list_head * list; - struct list_head * pos; - struct list_head * pos2; - struct dcookie_struct * dcs; - size_t i; - - for (i = 0; i < hash_size; ++i) { - list = dcookie_hashtable + i; - list_for_each_safe(pos, pos2, list) { - dcs = list_entry(pos, struct dcookie_struct, hash_list); - list_del(&dcs->hash_list); - free_dcookie(dcs); - } - } - - kfree(dcookie_hashtable); - kmem_cache_destroy(dcookie_cache); -} - - -struct dcookie_user { - struct list_head next; -}; - -struct dcookie_user * dcookie_register(void) -{ - struct dcookie_user * user; - - mutex_lock(&dcookie_mutex); - - user = kmalloc(sizeof(struct dcookie_user), GFP_KERNEL); - if (!user) - goto out; - - if (!is_live() && dcookie_init()) - goto out_free; - - list_add(&user->next, &dcookie_users); - -out: - mutex_unlock(&dcookie_mutex); - return user; -out_free: - kfree(user); - user = NULL; - goto out; -} - - -void dcookie_unregister(struct dcookie_user * user) -{ - mutex_lock(&dcookie_mutex); - - list_del(&user->next); - kfree(user); - - if (!is_live()) - dcookie_exit(); - - mutex_unlock(&dcookie_mutex); -} - -EXPORT_SYMBOL_GPL(dcookie_register); -EXPORT_SYMBOL_GPL(dcookie_unregister); -EXPORT_SYMBOL_GPL(get_dcookie); diff --git a/fs/direct-io.c b/fs/direct-io.c index d53fa92a1ab6..aa1083ecd623 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -426,6 +426,8 @@ static inline void dio_bio_submit(struct dio *dio, struct dio_submit *sdio) unsigned long flags; bio->bi_private = dio; + /* don't account direct I/O as memory stall */ + bio_clear_flag(bio, BIO_WORKINGSET); spin_lock_irqsave(&dio->bio_lock, flags); dio->refcount++; @@ -434,7 +436,7 @@ static inline void dio_bio_submit(struct dio *dio, struct dio_submit *sdio) if (dio->is_async && dio->op == REQ_OP_READ && dio->should_dirty) bio_set_pages_dirty(bio); - dio->bio_disk = bio->bi_disk; + dio->bio_disk = bio->bi_bdev->bd_disk; if (sdio->submit_io) { sdio->submit_io(bio, dio->inode, sdio->logical_offset_in_bio); diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index e23752d9a79f..58d0f7187997 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -1016,15 +1016,19 @@ ecryptfs_setxattr(struct dentry *dentry, struct inode *inode, { int rc; struct dentry *lower_dentry; + struct inode *lower_inode; lower_dentry = ecryptfs_dentry_to_lower(dentry); - if (!(d_inode(lower_dentry)->i_opflags & IOP_XATTR)) { + lower_inode = d_inode(lower_dentry); + if (!(lower_inode->i_opflags & IOP_XATTR)) { rc = -EOPNOTSUPP; goto out; } - rc = vfs_setxattr(lower_dentry, name, value, size, flags); + inode_lock(lower_inode); + rc = __vfs_setxattr_locked(lower_dentry, name, value, size, flags, NULL); + inode_unlock(lower_inode); if (!rc && inode) - fsstack_copy_attr_all(inode, d_inode(lower_dentry)); + fsstack_copy_attr_all(inode, lower_inode); out: return rc; } diff --git a/fs/erofs/super.c b/fs/erofs/super.c index be10b16ea66e..d5a6b9b888a5 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -158,8 +158,8 @@ static int erofs_read_superblock(struct super_block *sb) blkszbits = dsb->blkszbits; /* 9(512 bytes) + LOG_SECTORS_PER_BLOCK == LOG_BLOCK_SIZE */ if (blkszbits != LOG_BLOCK_SIZE) { - erofs_err(sb, "blksize %u isn't supported on this platform", - 1 << blkszbits); + erofs_err(sb, "blkszbits %u isn't supported on this platform", + blkszbits); goto out; } diff --git a/fs/erofs/xattr.c b/fs/erofs/xattr.c index 5bde77d70852..47314a26767a 100644 --- a/fs/erofs/xattr.c +++ b/fs/erofs/xattr.c @@ -48,8 +48,14 @@ static int init_inode_xattrs(struct inode *inode) int ret = 0; /* the most case is that xattrs of this inode are initialized. */ - if (test_bit(EROFS_I_EA_INITED_BIT, &vi->flags)) + if (test_bit(EROFS_I_EA_INITED_BIT, &vi->flags)) { + /* + * paired with smp_mb() at the end of the function to ensure + * fields will only be observed after the bit is set. + */ + smp_mb(); return 0; + } if (wait_on_bit_lock(&vi->flags, EROFS_I_BL_XATTR_BIT, TASK_KILLABLE)) return -ERESTARTSYS; @@ -137,6 +143,8 @@ static int init_inode_xattrs(struct inode *inode) } xattr_iter_end(&it, atomic_map); + /* paired with smp_mb() at the beginning of the function. */ + smp_mb(); set_bit(EROFS_I_EA_INITED_BIT, &vi->flags); out_unlock: diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c index ae325541884e..14d2de35110c 100644 --- a/fs/erofs/zmap.c +++ b/fs/erofs/zmap.c @@ -36,8 +36,14 @@ static int z_erofs_fill_inode_lazy(struct inode *inode) void *kaddr; struct z_erofs_map_header *h; - if (test_bit(EROFS_I_Z_INITED_BIT, &vi->flags)) + if (test_bit(EROFS_I_Z_INITED_BIT, &vi->flags)) { + /* + * paired with smp_mb() at the end of the function to ensure + * fields will only be observed after the bit is set. + */ + smp_mb(); return 0; + } if (wait_on_bit_lock(&vi->flags, EROFS_I_BL_Z_BIT, TASK_KILLABLE)) return -ERESTARTSYS; @@ -83,6 +89,8 @@ static int z_erofs_fill_inode_lazy(struct inode *inode) vi->z_physical_clusterbits[1] = vi->z_logical_clusterbits + ((h->h_clusterbits >> 5) & 7); + /* paired with smp_mb() at the beginning of the function */ + smp_mb(); set_bit(EROFS_I_Z_INITED_BIT, &vi->flags); unmap_done: kunmap_atomic(kaddr); diff --git a/fs/exec.c b/fs/exec.c index 5d4d52039105..5a853f03c233 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -708,7 +708,7 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift) return -ENOMEM; lru_add_drain(); - tlb_gather_mmu(&tlb, mm, old_start, old_end); + tlb_gather_mmu(&tlb, mm); if (new_end > old_start) { /* * when the old and new regions overlap clear from new_end. @@ -725,7 +725,7 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift) free_pgd_range(&tlb, old_start, old_end, new_end, vma->vm_next ? vma->vm_next->vm_start : USER_PGTABLES_CEILING); } - tlb_finish_mmu(&tlb, old_start, old_end); + tlb_finish_mmu(&tlb); /* * Shrink the vma to just the new range. Always succeeds. diff --git a/fs/exfat/file.c b/fs/exfat/file.c index a92478eabfa4..183ffdf4d43c 100644 --- a/fs/exfat/file.c +++ b/fs/exfat/file.c @@ -361,7 +361,7 @@ int exfat_file_fsync(struct file *filp, loff_t start, loff_t end, int datasync) if (err) return err; - return blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL); + return blkdev_issue_flush(inode->i_sb->s_bdev); } const struct file_operations exfat_file_operations = { diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c index 1a0a827a7f34..be799040a415 100644 --- a/fs/ext4/ext4_jbd2.c +++ b/fs/ext4/ext4_jbd2.c @@ -372,20 +372,3 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line, } return err; } - -int __ext4_handle_dirty_super(const char *where, unsigned int line, - handle_t *handle, struct super_block *sb) -{ - struct buffer_head *bh = EXT4_SB(sb)->s_sbh; - int err = 0; - - ext4_superblock_csum_set(sb); - if (ext4_handle_valid(handle)) { - err = jbd2_journal_dirty_metadata(handle, bh); - if (err) - ext4_journal_abort_handle(where, line, __func__, - bh, handle, err); - } else - mark_buffer_dirty(bh); - return err; -} diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h index a124c68b0c75..0d2fa423b7ad 100644 --- a/fs/ext4/ext4_jbd2.h +++ b/fs/ext4/ext4_jbd2.h @@ -244,9 +244,6 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line, handle_t *handle, struct inode *inode, struct buffer_head *bh); -int __ext4_handle_dirty_super(const char *where, unsigned int line, - handle_t *handle, struct super_block *sb); - #define ext4_journal_get_write_access(handle, bh) \ __ext4_journal_get_write_access(__func__, __LINE__, (handle), (bh)) #define ext4_forget(handle, is_metadata, inode, bh, block_nr) \ @@ -257,8 +254,6 @@ int __ext4_handle_dirty_super(const char *where, unsigned int line, #define ext4_handle_dirty_metadata(handle, inode, bh) \ __ext4_handle_dirty_metadata(__func__, __LINE__, (handle), (inode), \ (bh)) -#define ext4_handle_dirty_super(handle, sb) \ - __ext4_handle_dirty_super(__func__, __LINE__, (handle), (sb)) handle_t *__ext4_journal_start_sb(struct super_block *sb, unsigned int line, int type, int blocks, int rsv_blocks, diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c index 4fcc21c25e79..6e8208acfc62 100644 --- a/fs/ext4/fast_commit.c +++ b/fs/ext4/fast_commit.c @@ -604,13 +604,13 @@ void ext4_fc_track_range(handle_t *handle, struct inode *inode, ext4_lblk_t star trace_ext4_fc_track_range(inode, start, end, ret); } -static void ext4_fc_submit_bh(struct super_block *sb) +static void ext4_fc_submit_bh(struct super_block *sb, bool is_tail) { int write_flags = REQ_SYNC; struct buffer_head *bh = EXT4_SB(sb)->s_fc_bh; - /* TODO: REQ_FUA | REQ_PREFLUSH is unnecessarily expensive. */ - if (test_opt(sb, BARRIER)) + /* Add REQ_FUA | REQ_PREFLUSH only its tail */ + if (test_opt(sb, BARRIER) && is_tail) write_flags |= REQ_FUA | REQ_PREFLUSH; lock_buffer(bh); set_buffer_dirty(bh); @@ -684,7 +684,7 @@ static u8 *ext4_fc_reserve_space(struct super_block *sb, int len, u32 *crc) *crc = ext4_chksum(sbi, *crc, tl, sizeof(*tl)); if (pad_len > 0) ext4_fc_memzero(sb, tl + 1, pad_len, crc); - ext4_fc_submit_bh(sb); + ext4_fc_submit_bh(sb, false); ret = jbd2_fc_get_buf(EXT4_SB(sb)->s_journal, &bh); if (ret) @@ -741,7 +741,7 @@ static int ext4_fc_write_tail(struct super_block *sb, u32 crc) tail.fc_crc = cpu_to_le32(crc); ext4_fc_memcpy(sb, dst, &tail.fc_crc, sizeof(tail.fc_crc), NULL); - ext4_fc_submit_bh(sb); + ext4_fc_submit_bh(sb, true); return 0; } @@ -1076,7 +1076,7 @@ static int ext4_fc_perform_commit(journal_t *journal) * flush before we start writing fast commit blocks. */ if (journal->j_fs_dev != journal->j_dev) - blkdev_issue_flush(journal->j_fs_dev, GFP_NOFS); + blkdev_issue_flush(journal->j_fs_dev); blk_start_plug(&plug); if (sbi->s_fc_bytes == 0) { @@ -1268,7 +1268,7 @@ static void ext4_fc_cleanup(journal_t *journal, int full) list_splice_init(&sbi->s_fc_dentry_q[FC_Q_STAGING], &sbi->s_fc_dentry_q[FC_Q_MAIN]); list_splice_init(&sbi->s_fc_q[FC_Q_STAGING], - &sbi->s_fc_q[FC_Q_STAGING]); + &sbi->s_fc_q[FC_Q_MAIN]); ext4_clear_mount_flag(sb, EXT4_MF_FC_COMMITTING); ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE); @@ -1318,14 +1318,14 @@ static int ext4_fc_replay_unlink(struct super_block *sb, struct ext4_fc_tl *tl) entry.len = darg.dname_len; inode = ext4_iget(sb, darg.ino, EXT4_IGET_NORMAL); - if (IS_ERR_OR_NULL(inode)) { + if (IS_ERR(inode)) { jbd_debug(1, "Inode %d not found", darg.ino); return 0; } old_parent = ext4_iget(sb, darg.parent_ino, EXT4_IGET_NORMAL); - if (IS_ERR_OR_NULL(old_parent)) { + if (IS_ERR(old_parent)) { jbd_debug(1, "Dir with inode %d not found", darg.parent_ino); iput(inode); return 0; @@ -1410,7 +1410,7 @@ static int ext4_fc_replay_link(struct super_block *sb, struct ext4_fc_tl *tl) darg.parent_ino, darg.dname_len); inode = ext4_iget(sb, darg.ino, EXT4_IGET_NORMAL); - if (IS_ERR_OR_NULL(inode)) { + if (IS_ERR(inode)) { jbd_debug(1, "Inode not found."); return 0; } @@ -1466,10 +1466,11 @@ static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl) trace_ext4_fc_replay(sb, tag, ino, 0, 0); inode = ext4_iget(sb, ino, EXT4_IGET_NORMAL); - if (!IS_ERR_OR_NULL(inode)) { + if (!IS_ERR(inode)) { ext4_ext_clear_bb(inode); iput(inode); } + inode = NULL; ext4_fc_record_modified_inode(sb, ino); @@ -1512,7 +1513,7 @@ static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl) /* Given that we just wrote the inode on disk, this SHOULD succeed. */ inode = ext4_iget(sb, ino, EXT4_IGET_NORMAL); - if (IS_ERR_OR_NULL(inode)) { + if (IS_ERR(inode)) { jbd_debug(1, "Inode not found."); return -EFSCORRUPTED; } @@ -1534,7 +1535,7 @@ static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl) out: iput(inode); if (!ret) - blkdev_issue_flush(sb->s_bdev, GFP_KERNEL); + blkdev_issue_flush(sb->s_bdev); return 0; } @@ -1564,7 +1565,7 @@ static int ext4_fc_replay_create(struct super_block *sb, struct ext4_fc_tl *tl) goto out; inode = ext4_iget(sb, darg.ino, EXT4_IGET_NORMAL); - if (IS_ERR_OR_NULL(inode)) { + if (IS_ERR(inode)) { jbd_debug(1, "inode %d not found.", darg.ino); inode = NULL; ret = -EINVAL; @@ -1577,7 +1578,7 @@ static int ext4_fc_replay_create(struct super_block *sb, struct ext4_fc_tl *tl) * dot and dot dot dirents are setup properly. */ dir = ext4_iget(sb, darg.parent_ino, EXT4_IGET_NORMAL); - if (IS_ERR_OR_NULL(dir)) { + if (IS_ERR(dir)) { jbd_debug(1, "Dir %d not found.", darg.ino); goto out; } @@ -1653,7 +1654,7 @@ static int ext4_fc_replay_add_range(struct super_block *sb, inode = ext4_iget(sb, le32_to_cpu(fc_add_ex->fc_ino), EXT4_IGET_NORMAL); - if (IS_ERR_OR_NULL(inode)) { + if (IS_ERR(inode)) { jbd_debug(1, "Inode not found."); return 0; } @@ -1777,7 +1778,7 @@ ext4_fc_replay_del_range(struct super_block *sb, struct ext4_fc_tl *tl) le32_to_cpu(lrange->fc_ino), cur, remaining); inode = ext4_iget(sb, le32_to_cpu(lrange->fc_ino), EXT4_IGET_NORMAL); - if (IS_ERR_OR_NULL(inode)) { + if (IS_ERR(inode)) { jbd_debug(1, "Inode %d not found", le32_to_cpu(lrange->fc_ino)); return 0; } @@ -1832,7 +1833,7 @@ static void ext4_fc_set_bitmaps_and_counters(struct super_block *sb) for (i = 0; i < state->fc_modified_inodes_used; i++) { inode = ext4_iget(sb, state->fc_modified_inodes[i], EXT4_IGET_NORMAL); - if (IS_ERR_OR_NULL(inode)) { + if (IS_ERR(inode)) { jbd_debug(1, "Inode %d not found.", state->fc_modified_inodes[i]); continue; @@ -1849,7 +1850,7 @@ static void ext4_fc_set_bitmaps_and_counters(struct super_block *sb) if (ret > 0) { path = ext4_find_extent(inode, map.m_lblk, NULL, 0); - if (!IS_ERR_OR_NULL(path)) { + if (!IS_ERR(path)) { for (j = 0; j < path->p_depth; j++) ext4_mb_mark_bb(inode->i_sb, path[j].p_block, 1, 1); diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 3ed8c048fb12..194f5d00fa32 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -74,8 +74,7 @@ static ssize_t ext4_dio_read_iter(struct kiocb *iocb, struct iov_iter *to) return generic_file_read_iter(iocb, to); } - ret = iomap_dio_rw(iocb, to, &ext4_iomap_ops, NULL, - is_sync_kiocb(iocb)); + ret = iomap_dio_rw(iocb, to, &ext4_iomap_ops, NULL, 0); inode_unlock_shared(inode); file_accessed(iocb->ki_filp); @@ -550,7 +549,7 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from) if (ilock_shared) iomap_ops = &ext4_iomap_overwrite_ops; ret = iomap_dio_rw(iocb, from, iomap_ops, &ext4_dio_write_ops, - is_sync_kiocb(iocb) || unaligned_io || extend); + (unaligned_io || extend) ? IOMAP_DIO_FORCE_WAIT : 0); if (ret == -ENOTBLK) ret = 0; @@ -809,9 +808,12 @@ static int ext4_sample_last_mounted(struct super_block *sb, err = ext4_journal_get_write_access(handle, sbi->s_sbh); if (err) goto out_journal; - strlcpy(sbi->s_es->s_last_mounted, cp, + lock_buffer(sbi->s_sbh); + strncpy(sbi->s_es->s_last_mounted, cp, sizeof(sbi->s_es->s_last_mounted)); - ext4_handle_dirty_super(handle, sb); + ext4_superblock_csum_set(sb); + unlock_buffer(sbi->s_sbh); + ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh); out_journal: ext4_journal_stop(handle); out: diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index 113bfb023a4a..027a7d7037a0 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -174,7 +174,7 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync) ret = ext4_fsync_journal(inode, datasync, &needs_barrier); if (needs_barrier) { - err = blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL); + err = blkdev_issue_flush(inode->i_sb->s_bdev); if (!ret) ret = err; } diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index b215c564bc31..20f2fcb799f5 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -1583,7 +1583,7 @@ int ext4_init_inode_table(struct super_block *sb, ext4_group_t group, if (ret < 0) goto err_out; if (barrier) - blkdev_issue_flush(sb->s_bdev, GFP_NOFS); + blkdev_issue_flush(sb->s_bdev); skip_zeroout: ext4_lock_group(sb, group); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 27946882d4ce..c173c8405856 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -5150,9 +5150,13 @@ static int ext4_do_update_inode(handle_t *handle, err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh); if (err) goto out_brelse; + lock_buffer(EXT4_SB(sb)->s_sbh); ext4_set_feature_large_file(sb); + ext4_superblock_csum_set(sb); + unlock_buffer(EXT4_SB(sb)->s_sbh); ext4_handle_sync(handle); - err = ext4_handle_dirty_super(handle, sb); + err = ext4_handle_dirty_metadata(handle, NULL, + EXT4_SB(sb)->s_sbh); } ext4_update_inode_fsync_trans(handle, inode, need_datasync); out_brelse: diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 524e13432447..713b1ae44c1a 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -1157,7 +1157,10 @@ resizefs_out: err = ext4_journal_get_write_access(handle, sbi->s_sbh); if (err) goto pwsalt_err_journal; + lock_buffer(sbi->s_sbh); generate_random_uuid(sbi->s_es->s_encrypt_pw_salt); + ext4_superblock_csum_set(sb); + unlock_buffer(sbi->s_sbh); err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh); pwsalt_err_journal: @@ -1306,6 +1309,12 @@ out: return -EOPNOTSUPP; return fsverity_ioctl_measure(filp, (void __user *)arg); + case FS_IOC_READ_VERITY_METADATA: + if (!ext4_has_feature_verity(sb)) + return -EOPNOTSUPP; + return fsverity_ioctl_read_metadata(filp, + (const void __user *)arg); + default: return -ENOTTY; } @@ -1388,6 +1397,7 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case FS_IOC_GETFSMAP: case FS_IOC_ENABLE_VERITY: case FS_IOC_MEASURE_VERITY: + case FS_IOC_READ_VERITY_METADATA: case EXT4_IOC_CLEAR_ES_CACHE: case EXT4_IOC_GETSTATE: case EXT4_IOC_GET_ES_CACHE: diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index b17a082b7db1..cf652ba3e74d 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2976,14 +2976,17 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode) (le32_to_cpu(sbi->s_es->s_inodes_count))) { /* Insert this inode at the head of the on-disk orphan list */ NEXT_ORPHAN(inode) = le32_to_cpu(sbi->s_es->s_last_orphan); + lock_buffer(sbi->s_sbh); sbi->s_es->s_last_orphan = cpu_to_le32(inode->i_ino); + ext4_superblock_csum_set(sb); + unlock_buffer(sbi->s_sbh); dirty = true; } list_add(&EXT4_I(inode)->i_orphan, &sbi->s_orphan); mutex_unlock(&sbi->s_orphan_lock); if (dirty) { - err = ext4_handle_dirty_super(handle, sb); + err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh); rc = ext4_mark_iloc_dirty(handle, inode, &iloc); if (!err) err = rc; @@ -3059,9 +3062,12 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode) mutex_unlock(&sbi->s_orphan_lock); goto out_brelse; } + lock_buffer(sbi->s_sbh); sbi->s_es->s_last_orphan = cpu_to_le32(ino_next); + ext4_superblock_csum_set(inode->i_sb); + unlock_buffer(sbi->s_sbh); mutex_unlock(&sbi->s_orphan_lock); - err = ext4_handle_dirty_super(handle, inode->i_sb); + err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh); } else { struct ext4_iloc iloc2; struct inode *i_prev = @@ -3593,9 +3599,6 @@ static int ext4_setent(handle_t *handle, struct ext4_renament *ent, return retval2; } } - brelse(ent->bh); - ent->bh = NULL; - return retval; } @@ -3794,6 +3797,7 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, } } + old_file_type = old.de->file_type; if (IS_DIRSYNC(old.dir) || IS_DIRSYNC(new.dir)) ext4_handle_sync(handle); @@ -3821,7 +3825,6 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, force_reread = (new.dir->i_ino == old.dir->i_ino && ext4_test_inode_flag(new.dir, EXT4_INODE_INLINE_DATA)); - old_file_type = old.de->file_type; if (whiteout) { /* * Do this before adding a new entry, so the old entry is sure @@ -3919,15 +3922,19 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, retval = 0; end_rename: - brelse(old.dir_bh); - brelse(old.bh); - brelse(new.bh); if (whiteout) { - if (retval) + if (retval) { + ext4_setent(handle, &old, + old.inode->i_ino, old_file_type); drop_nlink(whiteout); + } unlock_new_inode(whiteout); iput(whiteout); + } + brelse(old.dir_bh); + brelse(old.bh); + brelse(new.bh); if (handle) ext4_journal_stop(handle); return retval; diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 928700d57eb6..bd0d185654f3 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -899,8 +899,11 @@ static int add_new_gdb(handle_t *handle, struct inode *inode, EXT4_SB(sb)->s_gdb_count++; ext4_kvfree_array_rcu(o_group_desc); + lock_buffer(EXT4_SB(sb)->s_sbh); le16_add_cpu(&es->s_reserved_gdt_blocks, -1); - err = ext4_handle_dirty_super(handle, sb); + ext4_superblock_csum_set(sb); + unlock_buffer(EXT4_SB(sb)->s_sbh); + err = ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh); if (err) ext4_std_error(sb, err); return err; @@ -1384,6 +1387,7 @@ static void ext4_update_super(struct super_block *sb, reserved_blocks *= blocks_count; do_div(reserved_blocks, 100); + lock_buffer(sbi->s_sbh); ext4_blocks_count_set(es, ext4_blocks_count(es) + blocks_count); ext4_free_blocks_count_set(es, ext4_free_blocks_count(es) + free_blocks); le32_add_cpu(&es->s_inodes_count, EXT4_INODES_PER_GROUP(sb) * @@ -1421,6 +1425,8 @@ static void ext4_update_super(struct super_block *sb, * active. */ ext4_r_blocks_count_set(es, ext4_r_blocks_count(es) + reserved_blocks); + ext4_superblock_csum_set(sb); + unlock_buffer(sbi->s_sbh); /* Update the free space counts */ percpu_counter_add(&sbi->s_freeclusters_counter, @@ -1515,7 +1521,7 @@ static int ext4_flex_group_add(struct super_block *sb, ext4_update_super(sb, flex_gd); - err = ext4_handle_dirty_super(handle, sb); + err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh); exit_journal: err2 = ext4_journal_stop(handle); @@ -1717,15 +1723,18 @@ static int ext4_group_extend_no_check(struct super_block *sb, goto errout; } + lock_buffer(EXT4_SB(sb)->s_sbh); ext4_blocks_count_set(es, o_blocks_count + add); ext4_free_blocks_count_set(es, ext4_free_blocks_count(es) + add); + ext4_superblock_csum_set(sb); + unlock_buffer(EXT4_SB(sb)->s_sbh); ext4_debug("freeing blocks %llu through %llu\n", o_blocks_count, o_blocks_count + add); /* We add the blocks to the bitmap and set the group need init bit */ err = ext4_group_add_blocks(handle, sb, o_blocks_count, add); if (err) goto errout; - ext4_handle_dirty_super(handle, sb); + ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh); ext4_debug("freed blocks %llu through %llu\n", o_blocks_count, o_blocks_count + add); errout: @@ -1874,12 +1883,15 @@ static int ext4_convert_meta_bg(struct super_block *sb, struct inode *inode) if (err) goto errout; + lock_buffer(sbi->s_sbh); ext4_clear_feature_resize_inode(sb); ext4_set_feature_meta_bg(sb); sbi->s_es->s_first_meta_bg = cpu_to_le32(num_desc_blocks(sb, sbi->s_groups_count)); + ext4_superblock_csum_set(sb); + unlock_buffer(sbi->s_sbh); - err = ext4_handle_dirty_super(handle, sb); + err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh); if (err) { ext4_std_error(sb, err); goto errout; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 21121787c874..fb5985102c1d 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -65,7 +65,8 @@ static struct ratelimit_state ext4_mount_msg_ratelimit; static int ext4_load_journal(struct super_block *, struct ext4_super_block *, unsigned long journal_devnum); static int ext4_show_options(struct seq_file *seq, struct dentry *root); -static int ext4_commit_super(struct super_block *sb, int sync); +static void ext4_update_super(struct super_block *sb); +static int ext4_commit_super(struct super_block *sb); static int ext4_mark_recovery_complete(struct super_block *sb, struct ext4_super_block *es); static int ext4_clear_journal_err(struct super_block *sb, @@ -586,15 +587,12 @@ static int ext4_errno_to_code(int errno) return EXT4_ERR_UNKNOWN; } -static void __save_error_info(struct super_block *sb, int error, - __u32 ino, __u64 block, - const char *func, unsigned int line) +static void save_error_info(struct super_block *sb, int error, + __u32 ino, __u64 block, + const char *func, unsigned int line) { struct ext4_sb_info *sbi = EXT4_SB(sb); - EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; - if (bdev_read_only(sb->s_bdev)) - return; /* We default to EFSCORRUPTED error... */ if (error == 0) error = EFSCORRUPTED; @@ -618,15 +616,6 @@ static void __save_error_info(struct super_block *sb, int error, spin_unlock(&sbi->s_error_lock); } -static void save_error_info(struct super_block *sb, int error, - __u32 ino, __u64 block, - const char *func, unsigned int line) -{ - __save_error_info(sb, error, ino, block, func, line); - if (!bdev_read_only(sb->s_bdev)) - ext4_commit_super(sb, 1); -} - /* Deal with the reporting of failure conditions on a filesystem such as * inconsistencies detected or read IO failures. * @@ -647,19 +636,40 @@ static void save_error_info(struct super_block *sb, int error, * used to deal with unrecoverable failures such as journal IO errors or ENOMEM * at a critical moment in log management. */ -static void ext4_handle_error(struct super_block *sb, bool force_ro) +static void ext4_handle_error(struct super_block *sb, bool force_ro, int error, + __u32 ino, __u64 block, + const char *func, unsigned int line) { journal_t *journal = EXT4_SB(sb)->s_journal; + bool continue_fs = !force_ro && test_opt(sb, ERRORS_CONT); + EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; if (test_opt(sb, WARN_ON_ERROR)) WARN_ON_ONCE(1); - if (sb_rdonly(sb) || (!force_ro && test_opt(sb, ERRORS_CONT))) + if (!continue_fs && !sb_rdonly(sb)) { + ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED); + if (journal) + jbd2_journal_abort(journal, -EIO); + } + + if (!bdev_read_only(sb->s_bdev)) { + save_error_info(sb, error, ino, block, func, line); + /* + * In case the fs should keep running, we need to writeout + * superblock through the journal. Due to lock ordering + * constraints, it may not be safe to do it right here so we + * defer superblock flushing to a workqueue. + */ + if (continue_fs) + schedule_work(&EXT4_SB(sb)->s_error_work); + else + ext4_commit_super(sb); + } + + if (sb_rdonly(sb) || continue_fs) return; - ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED); - if (journal) - jbd2_journal_abort(journal, -EIO); /* * We force ERRORS_RO behavior when system is rebooting. Otherwise we * could panic during 'reboot -f' as the underlying device got already @@ -682,8 +692,39 @@ static void flush_stashed_error_work(struct work_struct *work) { struct ext4_sb_info *sbi = container_of(work, struct ext4_sb_info, s_error_work); + journal_t *journal = sbi->s_journal; + handle_t *handle; - ext4_commit_super(sbi->s_sb, 1); + /* + * If the journal is still running, we have to write out superblock + * through the journal to avoid collisions of other journalled sb + * updates. + * + * We use directly jbd2 functions here to avoid recursing back into + * ext4 error handling code during handling of previous errors. + */ + if (!sb_rdonly(sbi->s_sb) && journal) { + handle = jbd2_journal_start(journal, 1); + if (IS_ERR(handle)) + goto write_directly; + if (jbd2_journal_get_write_access(handle, sbi->s_sbh)) { + jbd2_journal_stop(handle); + goto write_directly; + } + ext4_update_super(sbi->s_sb); + if (jbd2_journal_dirty_metadata(handle, sbi->s_sbh)) { + jbd2_journal_stop(handle); + goto write_directly; + } + jbd2_journal_stop(handle); + return; + } +write_directly: + /* + * Write through journal failed. Write sb directly to get error info + * out and hope for the best. + */ + ext4_commit_super(sbi->s_sb); } #define ext4_error_ratelimit(sb) \ @@ -710,8 +751,7 @@ void __ext4_error(struct super_block *sb, const char *function, sb->s_id, function, line, current->comm, &vaf); va_end(args); } - save_error_info(sb, error, 0, block, function, line); - ext4_handle_error(sb, force_ro); + ext4_handle_error(sb, force_ro, error, 0, block, function, line); } void __ext4_error_inode(struct inode *inode, const char *function, @@ -741,9 +781,8 @@ void __ext4_error_inode(struct inode *inode, const char *function, current->comm, &vaf); va_end(args); } - save_error_info(inode->i_sb, error, inode->i_ino, block, - function, line); - ext4_handle_error(inode->i_sb, false); + ext4_handle_error(inode->i_sb, false, error, inode->i_ino, block, + function, line); } void __ext4_error_file(struct file *file, const char *function, @@ -780,9 +819,8 @@ void __ext4_error_file(struct file *file, const char *function, current->comm, path, &vaf); va_end(args); } - save_error_info(inode->i_sb, EFSCORRUPTED, inode->i_ino, block, - function, line); - ext4_handle_error(inode->i_sb, false); + ext4_handle_error(inode->i_sb, false, EFSCORRUPTED, inode->i_ino, block, + function, line); } const char *ext4_decode_error(struct super_block *sb, int errno, @@ -849,8 +887,7 @@ void __ext4_std_error(struct super_block *sb, const char *function, sb->s_id, function, line, errstr); } - save_error_info(sb, -errno, 0, 0, function, line); - ext4_handle_error(sb, false); + ext4_handle_error(sb, false, -errno, 0, 0, function, line); } void __ext4_msg(struct super_block *sb, @@ -944,13 +981,16 @@ __acquires(bitlock) if (test_opt(sb, ERRORS_CONT)) { if (test_opt(sb, WARN_ON_ERROR)) WARN_ON_ONCE(1); - __save_error_info(sb, EFSCORRUPTED, ino, block, function, line); - schedule_work(&EXT4_SB(sb)->s_error_work); + EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; + if (!bdev_read_only(sb->s_bdev)) { + save_error_info(sb, EFSCORRUPTED, ino, block, function, + line); + schedule_work(&EXT4_SB(sb)->s_error_work); + } return; } ext4_unlock_group(sb, grp); - save_error_info(sb, EFSCORRUPTED, ino, block, function, line); - ext4_handle_error(sb, false); + ext4_handle_error(sb, false, EFSCORRUPTED, ino, block, function, line); /* * We only get here in the ERRORS_RO case; relocking the group * may be dangerous, but nothing bad will happen since the @@ -1152,7 +1192,7 @@ static void ext4_put_super(struct super_block *sb) es->s_state = cpu_to_le16(sbi->s_mount_state); } if (!sb_rdonly(sb)) - ext4_commit_super(sb, 1); + ext4_commit_super(sb); rcu_read_lock(); group_desc = rcu_dereference(sbi->s_group_desc); @@ -2642,7 +2682,7 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es, if (sbi->s_journal) ext4_set_feature_journal_needs_recovery(sb); - err = ext4_commit_super(sb, 1); + err = ext4_commit_super(sb); done: if (test_opt(sb, DEBUG)) printk(KERN_INFO "[EXT4 FS bs=%lu, gc=%u, " @@ -4868,7 +4908,7 @@ no_journal: if (DUMMY_ENCRYPTION_ENABLED(sbi) && !sb_rdonly(sb) && !ext4_has_feature_encrypt(sb)) { ext4_set_feature_encrypt(sb); - ext4_commit_super(sb, 1); + ext4_commit_super(sb); } /* @@ -5418,7 +5458,7 @@ static int ext4_load_journal(struct super_block *sb, es->s_journal_dev = cpu_to_le32(journal_devnum); /* Make sure we flush the recovery flag to disk. */ - ext4_commit_super(sb, 1); + ext4_commit_super(sb); } return 0; @@ -5428,16 +5468,14 @@ err_out: return err; } -static int ext4_commit_super(struct super_block *sb, int sync) +/* Copy state of EXT4_SB(sb) into buffer for on-disk superblock */ +static void ext4_update_super(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); - struct ext4_super_block *es = EXT4_SB(sb)->s_es; - struct buffer_head *sbh = EXT4_SB(sb)->s_sbh; - int error = 0; - - if (!sbh || block_device_ejected(sb)) - return error; + struct ext4_super_block *es = sbi->s_es; + struct buffer_head *sbh = sbi->s_sbh; + lock_buffer(sbh); /* * If the file system is mounted read-only, don't update the * superblock write time. This avoids updating the superblock @@ -5451,17 +5489,17 @@ static int ext4_commit_super(struct super_block *sb, int sync) if (!(sb->s_flags & SB_RDONLY)) ext4_update_tstamp(es, s_wtime); es->s_kbytes_written = - cpu_to_le64(EXT4_SB(sb)->s_kbytes_written + + cpu_to_le64(sbi->s_kbytes_written + ((part_stat_read(sb->s_bdev, sectors[STAT_WRITE]) - - EXT4_SB(sb)->s_sectors_written_start) >> 1)); - if (percpu_counter_initialized(&EXT4_SB(sb)->s_freeclusters_counter)) + sbi->s_sectors_written_start) >> 1)); + if (percpu_counter_initialized(&sbi->s_freeclusters_counter)) ext4_free_blocks_count_set(es, - EXT4_C2B(EXT4_SB(sb), percpu_counter_sum_positive( - &EXT4_SB(sb)->s_freeclusters_counter))); - if (percpu_counter_initialized(&EXT4_SB(sb)->s_freeinodes_counter)) + EXT4_C2B(sbi, percpu_counter_sum_positive( + &sbi->s_freeclusters_counter))); + if (percpu_counter_initialized(&sbi->s_freeinodes_counter)) es->s_free_inodes_count = cpu_to_le32(percpu_counter_sum_positive( - &EXT4_SB(sb)->s_freeinodes_counter)); + &sbi->s_freeinodes_counter)); /* Copy error information to the on-disk superblock */ spin_lock(&sbi->s_error_lock); if (sbi->s_add_error_count > 0) { @@ -5502,10 +5540,20 @@ static int ext4_commit_super(struct super_block *sb, int sync) } spin_unlock(&sbi->s_error_lock); - BUFFER_TRACE(sbh, "marking dirty"); ext4_superblock_csum_set(sb); - if (sync) - lock_buffer(sbh); + unlock_buffer(sbh); +} + +static int ext4_commit_super(struct super_block *sb) +{ + struct buffer_head *sbh = EXT4_SB(sb)->s_sbh; + int error = 0; + + if (!sbh || block_device_ejected(sb)) + return error; + + ext4_update_super(sb); + if (buffer_write_io_error(sbh) || !buffer_uptodate(sbh)) { /* * Oh, dear. A previous attempt to write the @@ -5520,17 +5568,15 @@ static int ext4_commit_super(struct super_block *sb, int sync) clear_buffer_write_io_error(sbh); set_buffer_uptodate(sbh); } + BUFFER_TRACE(sbh, "marking dirty"); mark_buffer_dirty(sbh); - if (sync) { - unlock_buffer(sbh); - error = __sync_dirty_buffer(sbh, - REQ_SYNC | (test_opt(sb, BARRIER) ? REQ_FUA : 0)); - if (buffer_write_io_error(sbh)) { - ext4_msg(sb, KERN_ERR, "I/O error while writing " - "superblock"); - clear_buffer_write_io_error(sbh); - set_buffer_uptodate(sbh); - } + error = __sync_dirty_buffer(sbh, + REQ_SYNC | (test_opt(sb, BARRIER) ? REQ_FUA : 0)); + if (buffer_write_io_error(sbh)) { + ext4_msg(sb, KERN_ERR, "I/O error while writing " + "superblock"); + clear_buffer_write_io_error(sbh); + set_buffer_uptodate(sbh); } return error; } @@ -5561,7 +5607,7 @@ static int ext4_mark_recovery_complete(struct super_block *sb, if (ext4_has_feature_journal_needs_recovery(sb) && sb_rdonly(sb)) { ext4_clear_feature_journal_needs_recovery(sb); - ext4_commit_super(sb, 1); + ext4_commit_super(sb); } out: jbd2_journal_unlock_updates(journal); @@ -5603,7 +5649,7 @@ static int ext4_clear_journal_err(struct super_block *sb, EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; es->s_state |= cpu_to_le16(EXT4_ERROR_FS); - ext4_commit_super(sb, 1); + ext4_commit_super(sb); jbd2_journal_clear_err(journal); jbd2_journal_update_sb_errno(journal); @@ -5663,7 +5709,7 @@ static int ext4_sync_fs(struct super_block *sb, int wait) needs_barrier = true; if (needs_barrier) { int err; - err = blkdev_issue_flush(sb->s_bdev, GFP_KERNEL); + err = blkdev_issue_flush(sb->s_bdev); if (!ret) ret = err; } @@ -5705,7 +5751,7 @@ static int ext4_freeze(struct super_block *sb) ext4_clear_feature_journal_needs_recovery(sb); } - error = ext4_commit_super(sb, 1); + error = ext4_commit_super(sb); out: if (journal) /* we rely on upper layer to stop further updates */ @@ -5727,7 +5773,7 @@ static int ext4_unfreeze(struct super_block *sb) ext4_set_feature_journal_needs_recovery(sb); } - ext4_commit_super(sb, 1); + ext4_commit_super(sb); return 0; } @@ -5987,7 +6033,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) } if (sbi->s_journal == NULL && !(old_sb_flags & SB_RDONLY)) { - err = ext4_commit_super(sb, 1); + err = ext4_commit_super(sb); if (err) goto restore_opts; } diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 4e3b1f8c2e81..372208500f4e 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -792,8 +792,11 @@ static void ext4_xattr_update_super_block(handle_t *handle, BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get_write_access"); if (ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh) == 0) { + lock_buffer(EXT4_SB(sb)->s_sbh); ext4_set_feature_xattr(sb); - ext4_handle_dirty_super(handle, sb); + ext4_superblock_csum_set(sb); + unlock_buffer(EXT4_SB(sb)->s_sbh); + ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh); } } diff --git a/fs/f2fs/Kconfig b/fs/f2fs/Kconfig index d13c5c6a9787..62e638a49bbf 100644 --- a/fs/f2fs/Kconfig +++ b/fs/f2fs/Kconfig @@ -76,16 +76,6 @@ config F2FS_CHECK_FS If you want to improve the performance, say N. -config F2FS_IO_TRACE - bool "F2FS IO tracer" - depends on F2FS_FS - depends on FUNCTION_TRACER - help - F2FS IO trace is based on a function trace, which gathers process - information and block IO patterns in the filesystem level. - - If unsure, say N. - config F2FS_FAULT_INJECTION bool "F2FS fault injection facility" depends on F2FS_FS @@ -119,6 +109,16 @@ config F2FS_FS_LZ4 help Support LZ4 compress algorithm, if unsure, say Y. +config F2FS_FS_LZ4HC + bool "LZ4HC compression support" + depends on F2FS_FS_COMPRESSION + depends on F2FS_FS_LZ4 + select LZ4HC_COMPRESS + default y + help + Support LZ4HC compress algorithm, LZ4HC has compatible on-disk + layout with LZ4, if unsure, say Y. + config F2FS_FS_ZSTD bool "ZSTD compression support" depends on F2FS_FS_COMPRESSION diff --git a/fs/f2fs/Makefile b/fs/f2fs/Makefile index ee7316b42f69..e5295746208b 100644 --- a/fs/f2fs/Makefile +++ b/fs/f2fs/Makefile @@ -7,6 +7,5 @@ f2fs-y += shrinker.o extent_cache.o sysfs.o f2fs-$(CONFIG_F2FS_STAT_FS) += debug.o f2fs-$(CONFIG_F2FS_FS_XATTR) += xattr.o f2fs-$(CONFIG_F2FS_FS_POSIX_ACL) += acl.o -f2fs-$(CONFIG_F2FS_IO_TRACE) += trace.o f2fs-$(CONFIG_FS_VERITY) += verity.o f2fs-$(CONFIG_F2FS_FS_COMPRESSION) += compress.o diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c index 1e5e9b1136ee..732ec10e7890 100644 --- a/fs/f2fs/acl.c +++ b/fs/f2fs/acl.c @@ -200,6 +200,27 @@ struct posix_acl *f2fs_get_acl(struct inode *inode, int type) return __f2fs_get_acl(inode, type, NULL); } +static int f2fs_acl_update_mode(struct inode *inode, umode_t *mode_p, + struct posix_acl **acl) +{ + umode_t mode = inode->i_mode; + int error; + + if (is_inode_flag_set(inode, FI_ACL_MODE)) + mode = F2FS_I(inode)->i_acl_mode; + + error = posix_acl_equiv_mode(*acl, &mode); + if (error < 0) + return error; + if (error == 0) + *acl = NULL; + if (!in_group_p(inode->i_gid) && + !capable_wrt_inode_uidgid(inode, CAP_FSETID)) + mode &= ~S_ISGID; + *mode_p = mode; + return 0; +} + static int __f2fs_set_acl(struct inode *inode, int type, struct posix_acl *acl, struct page *ipage) { @@ -213,7 +234,7 @@ static int __f2fs_set_acl(struct inode *inode, int type, case ACL_TYPE_ACCESS: name_index = F2FS_XATTR_INDEX_POSIX_ACL_ACCESS; if (acl && !ipage) { - error = posix_acl_update_mode(inode, &mode, &acl); + error = f2fs_acl_update_mode(inode, &mode, &acl); if (error) return error; set_acl_inode(inode, mode); diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index 897edb7c951a..174a0819ad96 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -13,13 +13,15 @@ #include <linux/f2fs_fs.h> #include <linux/pagevec.h> #include <linux/swap.h> +#include <linux/kthread.h> #include "f2fs.h" #include "node.h" #include "segment.h" -#include "trace.h" #include <trace/events/f2fs.h> +#define DEFAULT_CHECKPOINT_IOPRIO (IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, 3)) + static struct kmem_cache *ino_entry_slab; struct kmem_cache *f2fs_inode_entry_slab; @@ -443,7 +445,6 @@ static int f2fs_set_meta_page_dirty(struct page *page) __set_page_dirty_nobuffers(page); inc_page_count(F2FS_P_SB(page), F2FS_DIRTY_META); f2fs_set_page_private(page, 0); - f2fs_trace_pid(page); return 1; } return 0; @@ -1017,7 +1018,6 @@ void f2fs_update_dirty_page(struct inode *inode, struct page *page) spin_unlock(&sbi->inode_lock[type]); f2fs_set_page_private(page, 0); - f2fs_trace_pid(page); } void f2fs_remove_dirty_inode(struct inode *inode) @@ -1707,3 +1707,174 @@ void f2fs_destroy_checkpoint_caches(void) kmem_cache_destroy(ino_entry_slab); kmem_cache_destroy(f2fs_inode_entry_slab); } + +static int __write_checkpoint_sync(struct f2fs_sb_info *sbi) +{ + struct cp_control cpc = { .reason = CP_SYNC, }; + int err; + + down_write(&sbi->gc_lock); + err = f2fs_write_checkpoint(sbi, &cpc); + up_write(&sbi->gc_lock); + + return err; +} + +static void __checkpoint_and_complete_reqs(struct f2fs_sb_info *sbi) +{ + struct ckpt_req_control *cprc = &sbi->cprc_info; + struct ckpt_req *req, *next; + struct llist_node *dispatch_list; + u64 sum_diff = 0, diff, count = 0; + int ret; + + dispatch_list = llist_del_all(&cprc->issue_list); + if (!dispatch_list) + return; + dispatch_list = llist_reverse_order(dispatch_list); + + ret = __write_checkpoint_sync(sbi); + atomic_inc(&cprc->issued_ckpt); + + llist_for_each_entry_safe(req, next, dispatch_list, llnode) { + diff = (u64)ktime_ms_delta(ktime_get(), req->queue_time); + req->ret = ret; + complete(&req->wait); + + sum_diff += diff; + count++; + } + atomic_sub(count, &cprc->queued_ckpt); + atomic_add(count, &cprc->total_ckpt); + + spin_lock(&cprc->stat_lock); + cprc->cur_time = (unsigned int)div64_u64(sum_diff, count); + if (cprc->peak_time < cprc->cur_time) + cprc->peak_time = cprc->cur_time; + spin_unlock(&cprc->stat_lock); +} + +static int issue_checkpoint_thread(void *data) +{ + struct f2fs_sb_info *sbi = data; + struct ckpt_req_control *cprc = &sbi->cprc_info; + wait_queue_head_t *q = &cprc->ckpt_wait_queue; +repeat: + if (kthread_should_stop()) + return 0; + + if (!llist_empty(&cprc->issue_list)) + __checkpoint_and_complete_reqs(sbi); + + wait_event_interruptible(*q, + kthread_should_stop() || !llist_empty(&cprc->issue_list)); + goto repeat; +} + +static void flush_remained_ckpt_reqs(struct f2fs_sb_info *sbi, + struct ckpt_req *wait_req) +{ + struct ckpt_req_control *cprc = &sbi->cprc_info; + + if (!llist_empty(&cprc->issue_list)) { + __checkpoint_and_complete_reqs(sbi); + } else { + /* already dispatched by issue_checkpoint_thread */ + if (wait_req) + wait_for_completion(&wait_req->wait); + } +} + +static void init_ckpt_req(struct ckpt_req *req) +{ + memset(req, 0, sizeof(struct ckpt_req)); + + init_completion(&req->wait); + req->queue_time = ktime_get(); +} + +int f2fs_issue_checkpoint(struct f2fs_sb_info *sbi) +{ + struct ckpt_req_control *cprc = &sbi->cprc_info; + struct ckpt_req req; + struct cp_control cpc; + + cpc.reason = __get_cp_reason(sbi); + if (!test_opt(sbi, MERGE_CHECKPOINT) || cpc.reason != CP_SYNC) { + int ret; + + down_write(&sbi->gc_lock); + ret = f2fs_write_checkpoint(sbi, &cpc); + up_write(&sbi->gc_lock); + + return ret; + } + + if (!cprc->f2fs_issue_ckpt) + return __write_checkpoint_sync(sbi); + + init_ckpt_req(&req); + + llist_add(&req.llnode, &cprc->issue_list); + atomic_inc(&cprc->queued_ckpt); + + /* update issue_list before we wake up issue_checkpoint thread */ + smp_mb(); + + if (waitqueue_active(&cprc->ckpt_wait_queue)) + wake_up(&cprc->ckpt_wait_queue); + + if (cprc->f2fs_issue_ckpt) + wait_for_completion(&req.wait); + else + flush_remained_ckpt_reqs(sbi, &req); + + return req.ret; +} + +int f2fs_start_ckpt_thread(struct f2fs_sb_info *sbi) +{ + dev_t dev = sbi->sb->s_bdev->bd_dev; + struct ckpt_req_control *cprc = &sbi->cprc_info; + + if (cprc->f2fs_issue_ckpt) + return 0; + + cprc->f2fs_issue_ckpt = kthread_run(issue_checkpoint_thread, sbi, + "f2fs_ckpt-%u:%u", MAJOR(dev), MINOR(dev)); + if (IS_ERR(cprc->f2fs_issue_ckpt)) { + cprc->f2fs_issue_ckpt = NULL; + return -ENOMEM; + } + + set_task_ioprio(cprc->f2fs_issue_ckpt, cprc->ckpt_thread_ioprio); + + return 0; +} + +void f2fs_stop_ckpt_thread(struct f2fs_sb_info *sbi) +{ + struct ckpt_req_control *cprc = &sbi->cprc_info; + + if (cprc->f2fs_issue_ckpt) { + struct task_struct *ckpt_task = cprc->f2fs_issue_ckpt; + + cprc->f2fs_issue_ckpt = NULL; + kthread_stop(ckpt_task); + + flush_remained_ckpt_reqs(sbi, NULL); + } +} + +void f2fs_init_ckpt_req_control(struct f2fs_sb_info *sbi) +{ + struct ckpt_req_control *cprc = &sbi->cprc_info; + + atomic_set(&cprc->issued_ckpt, 0); + atomic_set(&cprc->total_ckpt, 0); + atomic_set(&cprc->queued_ckpt, 0); + cprc->ckpt_thread_ioprio = DEFAULT_CHECKPOINT_IOPRIO; + init_waitqueue_head(&cprc->ckpt_wait_queue); + init_llist_head(&cprc->issue_list); + spin_lock_init(&cprc->stat_lock); +} diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c index 4bcbacfe3325..77fa342de38f 100644 --- a/fs/f2fs/compress.c +++ b/fs/f2fs/compress.c @@ -252,8 +252,14 @@ static const struct f2fs_compress_ops f2fs_lzo_ops = { #ifdef CONFIG_F2FS_FS_LZ4 static int lz4_init_compress_ctx(struct compress_ctx *cc) { - cc->private = f2fs_kvmalloc(F2FS_I_SB(cc->inode), - LZ4_MEM_COMPRESS, GFP_NOFS); + unsigned int size = LZ4_MEM_COMPRESS; + +#ifdef CONFIG_F2FS_FS_LZ4HC + if (F2FS_I(cc->inode)->i_compress_flag >> COMPRESS_LEVEL_OFFSET) + size = LZ4HC_MEM_COMPRESS; +#endif + + cc->private = f2fs_kvmalloc(F2FS_I_SB(cc->inode), size, GFP_NOFS); if (!cc->private) return -ENOMEM; @@ -272,10 +278,34 @@ static void lz4_destroy_compress_ctx(struct compress_ctx *cc) cc->private = NULL; } +#ifdef CONFIG_F2FS_FS_LZ4HC +static int lz4hc_compress_pages(struct compress_ctx *cc) +{ + unsigned char level = F2FS_I(cc->inode)->i_compress_flag >> + COMPRESS_LEVEL_OFFSET; + int len; + + if (level) + len = LZ4_compress_HC(cc->rbuf, cc->cbuf->cdata, cc->rlen, + cc->clen, level, cc->private); + else + len = LZ4_compress_default(cc->rbuf, cc->cbuf->cdata, cc->rlen, + cc->clen, cc->private); + if (!len) + return -EAGAIN; + + cc->clen = len; + return 0; +} +#endif + static int lz4_compress_pages(struct compress_ctx *cc) { int len; +#ifdef CONFIG_F2FS_FS_LZ4HC + return lz4hc_compress_pages(cc); +#endif len = LZ4_compress_default(cc->rbuf, cc->cbuf->cdata, cc->rlen, cc->clen, cc->private); if (!len) @@ -325,8 +355,13 @@ static int zstd_init_compress_ctx(struct compress_ctx *cc) ZSTD_CStream *stream; void *workspace; unsigned int workspace_size; + unsigned char level = F2FS_I(cc->inode)->i_compress_flag >> + COMPRESS_LEVEL_OFFSET; - params = ZSTD_getParams(F2FS_ZSTD_DEFAULT_CLEVEL, cc->rlen, 0); + if (!level) + level = F2FS_ZSTD_DEFAULT_CLEVEL; + + params = ZSTD_getParams(level, cc->rlen, 0); workspace_size = ZSTD_CStreamWorkspaceBound(params.cParams); workspace = f2fs_kvmalloc(F2FS_I_SB(cc->inode), @@ -721,38 +756,27 @@ out: return ret; } -void f2fs_decompress_pages(struct bio *bio, struct page *page, bool verity) +static void f2fs_decompress_cluster(struct decompress_io_ctx *dic) { - struct decompress_io_ctx *dic = - (struct decompress_io_ctx *)page_private(page); struct f2fs_sb_info *sbi = F2FS_I_SB(dic->inode); - struct f2fs_inode_info *fi= F2FS_I(dic->inode); + struct f2fs_inode_info *fi = F2FS_I(dic->inode); const struct f2fs_compress_ops *cops = f2fs_cops[fi->i_compress_algorithm]; int ret; int i; - dec_page_count(sbi, F2FS_RD_DATA); - - if (bio->bi_status || PageError(page)) - dic->failed = true; - - if (atomic_dec_return(&dic->pending_pages)) - return; - trace_f2fs_decompress_pages_start(dic->inode, dic->cluster_idx, dic->cluster_size, fi->i_compress_algorithm); - /* submit partial compressed pages */ if (dic->failed) { ret = -EIO; - goto out_free_dic; + goto out_end_io; } dic->tpages = page_array_alloc(dic->inode, dic->cluster_size); if (!dic->tpages) { ret = -ENOMEM; - goto out_free_dic; + goto out_end_io; } for (i = 0; i < dic->cluster_size; i++) { @@ -764,20 +788,20 @@ void f2fs_decompress_pages(struct bio *bio, struct page *page, bool verity) dic->tpages[i] = f2fs_compress_alloc_page(); if (!dic->tpages[i]) { ret = -ENOMEM; - goto out_free_dic; + goto out_end_io; } } if (cops->init_decompress_ctx) { ret = cops->init_decompress_ctx(dic); if (ret) - goto out_free_dic; + goto out_end_io; } dic->rbuf = f2fs_vmap(dic->tpages, dic->cluster_size); if (!dic->rbuf) { ret = -ENOMEM; - goto destroy_decompress_ctx; + goto out_destroy_decompress_ctx; } dic->cbuf = f2fs_vmap(dic->cpages, dic->nr_cpages); @@ -816,18 +840,34 @@ out_vunmap_cbuf: vm_unmap_ram(dic->cbuf, dic->nr_cpages); out_vunmap_rbuf: vm_unmap_ram(dic->rbuf, dic->cluster_size); -destroy_decompress_ctx: +out_destroy_decompress_ctx: if (cops->destroy_decompress_ctx) cops->destroy_decompress_ctx(dic); -out_free_dic: - if (!verity) - f2fs_decompress_end_io(dic->rpages, dic->cluster_size, - ret, false); - +out_end_io: trace_f2fs_decompress_pages_end(dic->inode, dic->cluster_idx, dic->clen, ret); - if (!verity) - f2fs_free_dic(dic); + f2fs_decompress_end_io(dic, ret); +} + +/* + * This is called when a page of a compressed cluster has been read from disk + * (or failed to be read from disk). It checks whether this page was the last + * page being waited on in the cluster, and if so, it decompresses the cluster + * (or in the case of a failure, cleans up without actually decompressing). + */ +void f2fs_end_read_compressed_page(struct page *page, bool failed) +{ + struct decompress_io_ctx *dic = + (struct decompress_io_ctx *)page_private(page); + struct f2fs_sb_info *sbi = F2FS_I_SB(dic->inode); + + dec_page_count(sbi, F2FS_RD_DATA); + + if (failed) + WRITE_ONCE(dic->failed, true); + + if (atomic_dec_and_test(&dic->remaining_pages)) + f2fs_decompress_cluster(dic); } static bool is_page_in_cluster(struct compress_ctx *cc, pgoff_t index) @@ -1415,7 +1455,7 @@ retry_write: ret = f2fs_write_single_data_page(cc->rpages[i], &_submitted, NULL, NULL, wbc, io_type, - compr_blocks); + compr_blocks, false); if (ret) { if (ret == AOP_WRITEPAGE_ACTIVATE) { unlock_page(cc->rpages[i]); @@ -1450,6 +1490,9 @@ retry_write: *submitted += _submitted; } + + f2fs_balance_fs(F2FS_M_SB(mapping), true); + return 0; out_err: for (++i; i < cc->cluster_size; i++) { @@ -1494,6 +1537,8 @@ destroy_out: return err; } +static void f2fs_free_dic(struct decompress_io_ctx *dic); + struct decompress_io_ctx *f2fs_alloc_dic(struct compress_ctx *cc) { struct decompress_io_ctx *dic; @@ -1512,12 +1557,14 @@ struct decompress_io_ctx *f2fs_alloc_dic(struct compress_ctx *cc) dic->magic = F2FS_COMPRESSED_PAGE_MAGIC; dic->inode = cc->inode; - atomic_set(&dic->pending_pages, cc->nr_cpages); + atomic_set(&dic->remaining_pages, cc->nr_cpages); dic->cluster_idx = cc->cluster_idx; dic->cluster_size = cc->cluster_size; dic->log_cluster_size = cc->log_cluster_size; dic->nr_cpages = cc->nr_cpages; + refcount_set(&dic->refcnt, 1); dic->failed = false; + dic->need_verity = f2fs_need_verity(cc->inode, start_idx); for (i = 0; i < dic->cluster_size; i++) dic->rpages[i] = cc->rpages[i]; @@ -1546,7 +1593,7 @@ out_free: return ERR_PTR(-ENOMEM); } -void f2fs_free_dic(struct decompress_io_ctx *dic) +static void f2fs_free_dic(struct decompress_io_ctx *dic) { int i; @@ -1574,30 +1621,88 @@ void f2fs_free_dic(struct decompress_io_ctx *dic) kmem_cache_free(dic_entry_slab, dic); } -void f2fs_decompress_end_io(struct page **rpages, - unsigned int cluster_size, bool err, bool verity) +static void f2fs_put_dic(struct decompress_io_ctx *dic) +{ + if (refcount_dec_and_test(&dic->refcnt)) + f2fs_free_dic(dic); +} + +/* + * Update and unlock the cluster's pagecache pages, and release the reference to + * the decompress_io_ctx that was being held for I/O completion. + */ +static void __f2fs_decompress_end_io(struct decompress_io_ctx *dic, bool failed) { int i; - for (i = 0; i < cluster_size; i++) { - struct page *rpage = rpages[i]; + for (i = 0; i < dic->cluster_size; i++) { + struct page *rpage = dic->rpages[i]; if (!rpage) continue; - if (err || PageError(rpage)) - goto clear_uptodate; - - if (!verity || fsverity_verify_page(rpage)) { + /* PG_error was set if verity failed. */ + if (failed || PageError(rpage)) { + ClearPageUptodate(rpage); + /* will re-read again later */ + ClearPageError(rpage); + } else { SetPageUptodate(rpage); - goto unlock; } -clear_uptodate: - ClearPageUptodate(rpage); - ClearPageError(rpage); -unlock: unlock_page(rpage); } + + f2fs_put_dic(dic); +} + +static void f2fs_verify_cluster(struct work_struct *work) +{ + struct decompress_io_ctx *dic = + container_of(work, struct decompress_io_ctx, verity_work); + int i; + + /* Verify the cluster's decompressed pages with fs-verity. */ + for (i = 0; i < dic->cluster_size; i++) { + struct page *rpage = dic->rpages[i]; + + if (rpage && !fsverity_verify_page(rpage)) + SetPageError(rpage); + } + + __f2fs_decompress_end_io(dic, false); +} + +/* + * This is called when a compressed cluster has been decompressed + * (or failed to be read and/or decompressed). + */ +void f2fs_decompress_end_io(struct decompress_io_ctx *dic, bool failed) +{ + if (!failed && dic->need_verity) { + /* + * Note that to avoid deadlocks, the verity work can't be done + * on the decompression workqueue. This is because verifying + * the data pages can involve reading metadata pages from the + * file, and these metadata pages may be compressed. + */ + INIT_WORK(&dic->verity_work, f2fs_verify_cluster); + fsverity_enqueue_verify_work(&dic->verity_work); + } else { + __f2fs_decompress_end_io(dic, failed); + } +} + +/* + * Put a reference to a compressed page's decompress_io_ctx. + * + * This is called when the page is no longer needed and can be freed. + */ +void f2fs_put_page_dic(struct page *page) +{ + struct decompress_io_ctx *dic = + (struct decompress_io_ctx *)page_private(page); + + f2fs_put_dic(dic); } int f2fs_init_page_array_cache(struct f2fs_sb_info *sbi) diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index aa34d620bec9..b9721c8f116c 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -25,7 +25,6 @@ #include "f2fs.h" #include "node.h" #include "segment.h" -#include "trace.h" #include <trace/events/f2fs.h> #define NUM_PREALLOC_POST_READ_CTXS 128 @@ -50,27 +49,6 @@ void f2fs_destroy_bioset(void) bioset_exit(&f2fs_bioset); } -static inline struct bio *__f2fs_bio_alloc(gfp_t gfp_mask, - unsigned int nr_iovecs) -{ - return bio_alloc_bioset(gfp_mask, nr_iovecs, &f2fs_bioset); -} - -struct bio *f2fs_bio_alloc(struct f2fs_sb_info *sbi, int npages, bool noio) -{ - if (noio) { - /* No failure on bio allocation */ - return __f2fs_bio_alloc(GFP_NOIO, npages); - } - - if (time_to_inject(sbi, FAULT_ALLOC_BIO)) { - f2fs_show_injection_info(sbi, FAULT_ALLOC_BIO); - return NULL; - } - - return __f2fs_bio_alloc(GFP_KERNEL, npages); -} - static bool __is_cp_guaranteed(struct page *page) { struct address_space *mapping = page->mapping; @@ -115,10 +93,21 @@ static enum count_type __read_io_type(struct page *page) /* postprocessing steps for read bios */ enum bio_post_read_step { - STEP_DECRYPT, - STEP_DECOMPRESS_NOWQ, /* handle normal cluster data inplace */ - STEP_DECOMPRESS, /* handle compressed cluster data in workqueue */ - STEP_VERITY, +#ifdef CONFIG_FS_ENCRYPTION + STEP_DECRYPT = 1 << 0, +#else + STEP_DECRYPT = 0, /* compile out the decryption-related code */ +#endif +#ifdef CONFIG_F2FS_FS_COMPRESSION + STEP_DECOMPRESS = 1 << 1, +#else + STEP_DECOMPRESS = 0, /* compile out the decompression-related code */ +#endif +#ifdef CONFIG_FS_VERITY + STEP_VERITY = 1 << 2, +#else + STEP_VERITY = 0, /* compile out the verity-related code */ +#endif }; struct bio_post_read_ctx { @@ -128,25 +117,26 @@ struct bio_post_read_ctx { unsigned int enabled_steps; }; -static void __read_end_io(struct bio *bio, bool compr, bool verity) +static void f2fs_finish_read_bio(struct bio *bio) { - struct page *page; struct bio_vec *bv; struct bvec_iter_all iter_all; + /* + * Update and unlock the bio's pagecache pages, and put the + * decompression context for any compressed pages. + */ bio_for_each_segment_all(bv, bio, iter_all) { - page = bv->bv_page; + struct page *page = bv->bv_page; -#ifdef CONFIG_F2FS_FS_COMPRESSION - if (compr && f2fs_is_compressed_page(page)) { - f2fs_decompress_pages(bio, page, verity); + if (f2fs_is_compressed_page(page)) { + if (bio->bi_status) + f2fs_end_read_compressed_page(page, true); + f2fs_put_page_dic(page); continue; } - if (verity) - continue; -#endif - /* PG_error was set if any post_read step failed */ + /* PG_error was set if decryption or verity failed. */ if (bio->bi_status || PageError(page)) { ClearPageUptodate(page); /* will re-read again later */ @@ -157,181 +147,141 @@ static void __read_end_io(struct bio *bio, bool compr, bool verity) dec_page_count(F2FS_P_SB(page), __read_io_type(page)); unlock_page(page); } -} - -static void f2fs_release_read_bio(struct bio *bio); -static void __f2fs_read_end_io(struct bio *bio, bool compr, bool verity) -{ - if (!compr) - __read_end_io(bio, false, verity); - f2fs_release_read_bio(bio); -} - -static void f2fs_decompress_bio(struct bio *bio, bool verity) -{ - __read_end_io(bio, true, verity); -} - -static void bio_post_read_processing(struct bio_post_read_ctx *ctx); - -static void f2fs_decrypt_work(struct bio_post_read_ctx *ctx) -{ - fscrypt_decrypt_bio(ctx->bio); -} - -static void f2fs_decompress_work(struct bio_post_read_ctx *ctx) -{ - f2fs_decompress_bio(ctx->bio, ctx->enabled_steps & (1 << STEP_VERITY)); -} - -#ifdef CONFIG_F2FS_FS_COMPRESSION -static void f2fs_verify_pages(struct page **rpages, unsigned int cluster_size) -{ - f2fs_decompress_end_io(rpages, cluster_size, false, true); -} - -static void f2fs_verify_bio(struct bio *bio) -{ - struct bio_vec *bv; - struct bvec_iter_all iter_all; - bio_for_each_segment_all(bv, bio, iter_all) { - struct page *page = bv->bv_page; - struct decompress_io_ctx *dic; - - dic = (struct decompress_io_ctx *)page_private(page); - - if (dic) { - if (atomic_dec_return(&dic->verity_pages)) - continue; - f2fs_verify_pages(dic->rpages, - dic->cluster_size); - f2fs_free_dic(dic); - continue; - } - - if (bio->bi_status || PageError(page)) - goto clear_uptodate; - - if (fsverity_verify_page(page)) { - SetPageUptodate(page); - goto unlock; - } -clear_uptodate: - ClearPageUptodate(page); - ClearPageError(page); -unlock: - dec_page_count(F2FS_P_SB(page), __read_io_type(page)); - unlock_page(page); - } + if (bio->bi_private) + mempool_free(bio->bi_private, bio_post_read_ctx_pool); + bio_put(bio); } -#endif -static void f2fs_verity_work(struct work_struct *work) +static void f2fs_verify_bio(struct work_struct *work) { struct bio_post_read_ctx *ctx = container_of(work, struct bio_post_read_ctx, work); struct bio *bio = ctx->bio; -#ifdef CONFIG_F2FS_FS_COMPRESSION - unsigned int enabled_steps = ctx->enabled_steps; -#endif + bool may_have_compressed_pages = (ctx->enabled_steps & STEP_DECOMPRESS); /* * fsverity_verify_bio() may call readpages() again, and while verity - * will be disabled for this, decryption may still be needed, resulting - * in another bio_post_read_ctx being allocated. So to prevent - * deadlocks we need to release the current ctx to the mempool first. - * This assumes that verity is the last post-read step. + * will be disabled for this, decryption and/or decompression may still + * be needed, resulting in another bio_post_read_ctx being allocated. + * So to prevent deadlocks we need to release the current ctx to the + * mempool first. This assumes that verity is the last post-read step. */ mempool_free(ctx, bio_post_read_ctx_pool); bio->bi_private = NULL; -#ifdef CONFIG_F2FS_FS_COMPRESSION - /* previous step is decompression */ - if (enabled_steps & (1 << STEP_DECOMPRESS)) { - f2fs_verify_bio(bio); - f2fs_release_read_bio(bio); - return; + /* + * Verify the bio's pages with fs-verity. Exclude compressed pages, + * as those were handled separately by f2fs_end_read_compressed_page(). + */ + if (may_have_compressed_pages) { + struct bio_vec *bv; + struct bvec_iter_all iter_all; + + bio_for_each_segment_all(bv, bio, iter_all) { + struct page *page = bv->bv_page; + + if (!f2fs_is_compressed_page(page) && + !PageError(page) && !fsverity_verify_page(page)) + SetPageError(page); + } + } else { + fsverity_verify_bio(bio); } -#endif - fsverity_verify_bio(bio); - __f2fs_read_end_io(bio, false, false); + f2fs_finish_read_bio(bio); } -static void f2fs_post_read_work(struct work_struct *work) +/* + * If the bio's data needs to be verified with fs-verity, then enqueue the + * verity work for the bio. Otherwise finish the bio now. + * + * Note that to avoid deadlocks, the verity work can't be done on the + * decryption/decompression workqueue. This is because verifying the data pages + * can involve reading verity metadata pages from the file, and these verity + * metadata pages may be encrypted and/or compressed. + */ +static void f2fs_verify_and_finish_bio(struct bio *bio) { - struct bio_post_read_ctx *ctx = - container_of(work, struct bio_post_read_ctx, work); + struct bio_post_read_ctx *ctx = bio->bi_private; - if (ctx->enabled_steps & (1 << STEP_DECRYPT)) - f2fs_decrypt_work(ctx); - - if (ctx->enabled_steps & (1 << STEP_DECOMPRESS)) - f2fs_decompress_work(ctx); - - if (ctx->enabled_steps & (1 << STEP_VERITY)) { - INIT_WORK(&ctx->work, f2fs_verity_work); + if (ctx && (ctx->enabled_steps & STEP_VERITY)) { + INIT_WORK(&ctx->work, f2fs_verify_bio); fsverity_enqueue_verify_work(&ctx->work); - return; + } else { + f2fs_finish_read_bio(bio); } - - __f2fs_read_end_io(ctx->bio, - ctx->enabled_steps & (1 << STEP_DECOMPRESS), false); } -static void f2fs_enqueue_post_read_work(struct f2fs_sb_info *sbi, - struct work_struct *work) -{ - queue_work(sbi->post_read_wq, work); -} - -static void bio_post_read_processing(struct bio_post_read_ctx *ctx) +/* + * Handle STEP_DECOMPRESS by decompressing any compressed clusters whose last + * remaining page was read by @ctx->bio. + * + * Note that a bio may span clusters (even a mix of compressed and uncompressed + * clusters) or be for just part of a cluster. STEP_DECOMPRESS just indicates + * that the bio includes at least one compressed page. The actual decompression + * is done on a per-cluster basis, not a per-bio basis. + */ +static void f2fs_handle_step_decompress(struct bio_post_read_ctx *ctx) { - /* - * We use different work queues for decryption and for verity because - * verity may require reading metadata pages that need decryption, and - * we shouldn't recurse to the same workqueue. - */ + struct bio_vec *bv; + struct bvec_iter_all iter_all; + bool all_compressed = true; - if (ctx->enabled_steps & (1 << STEP_DECRYPT) || - ctx->enabled_steps & (1 << STEP_DECOMPRESS)) { - INIT_WORK(&ctx->work, f2fs_post_read_work); - f2fs_enqueue_post_read_work(ctx->sbi, &ctx->work); - return; - } + bio_for_each_segment_all(bv, ctx->bio, iter_all) { + struct page *page = bv->bv_page; - if (ctx->enabled_steps & (1 << STEP_VERITY)) { - INIT_WORK(&ctx->work, f2fs_verity_work); - fsverity_enqueue_verify_work(&ctx->work); - return; + /* PG_error was set if decryption failed. */ + if (f2fs_is_compressed_page(page)) + f2fs_end_read_compressed_page(page, PageError(page)); + else + all_compressed = false; } - __f2fs_read_end_io(ctx->bio, false, false); + /* + * Optimization: if all the bio's pages are compressed, then scheduling + * the per-bio verity work is unnecessary, as verity will be fully + * handled at the compression cluster level. + */ + if (all_compressed) + ctx->enabled_steps &= ~STEP_VERITY; } -static bool f2fs_bio_post_read_required(struct bio *bio) +static void f2fs_post_read_work(struct work_struct *work) { - return bio->bi_private; + struct bio_post_read_ctx *ctx = + container_of(work, struct bio_post_read_ctx, work); + + if (ctx->enabled_steps & STEP_DECRYPT) + fscrypt_decrypt_bio(ctx->bio); + + if (ctx->enabled_steps & STEP_DECOMPRESS) + f2fs_handle_step_decompress(ctx); + + f2fs_verify_and_finish_bio(ctx->bio); } 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 = bio->bi_private; if (time_to_inject(sbi, FAULT_READ_IO)) { f2fs_show_injection_info(sbi, FAULT_READ_IO); bio->bi_status = BLK_STS_IOERR; } - if (f2fs_bio_post_read_required(bio)) { - struct bio_post_read_ctx *ctx = bio->bi_private; - - bio_post_read_processing(ctx); + if (bio->bi_status) { + f2fs_finish_read_bio(bio); return; } - __f2fs_read_end_io(bio, false, false); + if (ctx && (ctx->enabled_steps & (STEP_DECRYPT | STEP_DECOMPRESS))) { + INIT_WORK(&ctx->work, f2fs_post_read_work); + queue_work(ctx->sbi->post_read_wq, &ctx->work); + } else { + f2fs_verify_and_finish_bio(bio); + } } static void f2fs_write_end_io(struct bio *bio) @@ -427,22 +377,12 @@ int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr) return 0; } -/* - * Return true, if pre_bio's bdev is same as its target device. - */ -static bool __same_bdev(struct f2fs_sb_info *sbi, - block_t blk_addr, struct bio *bio) -{ - struct block_device *b = f2fs_target_device(sbi, blk_addr, NULL); - return bio->bi_disk == b->bd_disk && bio->bi_partno == b->bd_partno; -} - static struct bio *__bio_alloc(struct f2fs_io_info *fio, int npages) { struct f2fs_sb_info *sbi = fio->sbi; struct bio *bio; - bio = f2fs_bio_alloc(sbi, npages, true); + bio = bio_alloc_bioset(GFP_NOIO, npages, &f2fs_bioset); f2fs_target_device(sbi, fio->new_blkaddr, bio); if (is_read_io(fio->op)) { @@ -499,7 +439,7 @@ static inline void __submit_bio(struct f2fs_sb_info *sbi, if (f2fs_lfs_mode(sbi) && current->plug) blk_finish_plug(current->plug); - if (F2FS_IO_ALIGNED(sbi)) + if (!F2FS_IO_ALIGNED(sbi)) goto submit_io; start = bio->bi_iter.bi_size >> F2FS_BLKSIZE_BITS; @@ -707,7 +647,6 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio) return -EFSCORRUPTED; trace_f2fs_submit_page_bio(page, fio); - f2fs_trace_ios(fio, 0); /* Allocate a new bio */ bio = __bio_alloc(fio, 1); @@ -741,7 +680,7 @@ static bool page_is_mergeable(struct f2fs_sb_info *sbi, struct bio *bio, return false; if (last_blkaddr + 1 != cur_blkaddr) return false; - return __same_bdev(sbi, cur_blkaddr, bio); + return bio->bi_bdev == f2fs_target_device(sbi, cur_blkaddr, NULL); } static bool io_type_is_mergeable(struct f2fs_bio_info *io, @@ -912,7 +851,6 @@ int f2fs_merge_page_bio(struct f2fs_io_info *fio) return -EFSCORRUPTED; trace_f2fs_submit_page_bio(page, fio); - f2fs_trace_ios(fio, 0); if (bio && !page_is_mergeable(fio->sbi, bio, *fio->last_block, fio->new_blkaddr)) @@ -1009,7 +947,6 @@ alloc_new: wbc_account_cgroup_owner(fio->io_wbc, bio_page, PAGE_SIZE); io->last_block_in_bio = fio->new_blkaddr; - f2fs_trace_ios(fio, 0); trace_f2fs_submit_page_write(fio->page, fio); skip: @@ -1022,24 +959,18 @@ out: up_write(&io->io_rwsem); } -static inline bool f2fs_need_verity(const struct inode *inode, pgoff_t idx) -{ - return fsverity_active(inode) && - idx < DIV_ROUND_UP(inode->i_size, PAGE_SIZE); -} - static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr, unsigned nr_pages, unsigned op_flag, - pgoff_t first_idx, bool for_write, - bool for_verity) + pgoff_t first_idx, bool for_write) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct bio *bio; struct bio_post_read_ctx *ctx; unsigned int post_read_steps = 0; - bio = f2fs_bio_alloc(sbi, min_t(int, nr_pages, BIO_MAX_PAGES), - for_write); + bio = bio_alloc_bioset(for_write ? GFP_NOIO : GFP_KERNEL, + min_t(int, nr_pages, BIO_MAX_PAGES), + &f2fs_bioset); if (!bio) return ERR_PTR(-ENOMEM); @@ -1050,13 +981,19 @@ static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr, bio_set_op_attrs(bio, REQ_OP_READ, op_flag); if (fscrypt_inode_uses_fs_layer_crypto(inode)) - post_read_steps |= 1 << STEP_DECRYPT; - if (f2fs_compressed_file(inode)) - post_read_steps |= 1 << STEP_DECOMPRESS_NOWQ; - if (for_verity && f2fs_need_verity(inode, first_idx)) - post_read_steps |= 1 << STEP_VERITY; + post_read_steps |= STEP_DECRYPT; + + if (f2fs_need_verity(inode, first_idx)) + post_read_steps |= STEP_VERITY; + + /* + * STEP_DECOMPRESS is handled specially, since a compressed file might + * contain both compressed and uncompressed clusters. We'll allocate a + * bio_post_read_ctx if the file is compressed, but the caller is + * responsible for enabling STEP_DECOMPRESS if it's actually needed. + */ - if (post_read_steps) { + if (post_read_steps || f2fs_compressed_file(inode)) { /* Due to the mempool, this never fails. */ ctx = mempool_alloc(bio_post_read_ctx_pool, GFP_NOFS); ctx->bio = bio; @@ -1068,13 +1005,6 @@ static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr, return bio; } -static void f2fs_release_read_bio(struct bio *bio) -{ - if (bio->bi_private) - mempool_free(bio->bi_private, bio_post_read_ctx_pool); - bio_put(bio); -} - /* This can handle encryption stuffs */ static int f2fs_submit_page_read(struct inode *inode, struct page *page, block_t blkaddr, int op_flags, bool for_write) @@ -1083,7 +1013,7 @@ static int f2fs_submit_page_read(struct inode *inode, struct page *page, struct bio *bio; bio = f2fs_grab_read_bio(inode, blkaddr, 1, op_flags, - page->index, for_write, true); + page->index, for_write); if (IS_ERR(bio)) return PTR_ERR(bio); @@ -1964,6 +1894,7 @@ next: } if (size) { + flags |= FIEMAP_EXTENT_MERGED; if (IS_ENCRYPTED(inode)) flags |= FIEMAP_EXTENT_DATA_ENCRYPTED; @@ -2121,7 +2052,7 @@ submit_and_realloc: if (bio == NULL) { bio = f2fs_grab_read_bio(inode, block_nr, nr_pages, is_readahead ? REQ_RAHEAD : 0, page->index, - false, true); + false); if (IS_ERR(bio)) { ret = PTR_ERR(bio); bio = NULL; @@ -2167,8 +2098,6 @@ int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret, sector_t last_block_in_file; const unsigned blocksize = blks_to_bytes(inode, 1); struct decompress_io_ctx *dic = NULL; - struct bio_post_read_ctx *ctx; - bool for_verity = false; int i; int ret = 0; @@ -2234,29 +2163,10 @@ int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret, goto out_put_dnode; } - /* - * It's possible to enable fsverity on the fly when handling a cluster, - * which requires complicated error handling. Instead of adding more - * complexity, let's give a rule where end_io post-processes fsverity - * per cluster. In order to do that, we need to submit bio, if previous - * bio sets a different post-process policy. - */ - if (fsverity_active(cc->inode)) { - atomic_set(&dic->verity_pages, cc->nr_cpages); - for_verity = true; - - if (bio) { - ctx = bio->bi_private; - if (!(ctx->enabled_steps & (1 << STEP_VERITY))) { - __submit_bio(sbi, bio, DATA); - bio = NULL; - } - } - } - for (i = 0; i < dic->nr_cpages; i++) { struct page *page = dic->cpages[i]; block_t blkaddr; + struct bio_post_read_ctx *ctx; blkaddr = data_blkaddr(dn.inode, dn.node_page, dn.ofs_in_node + i + 1); @@ -2272,31 +2182,10 @@ submit_and_realloc: if (!bio) { bio = f2fs_grab_read_bio(inode, blkaddr, nr_pages, is_readahead ? REQ_RAHEAD : 0, - page->index, for_write, for_verity); + page->index, for_write); if (IS_ERR(bio)) { - unsigned int remained = dic->nr_cpages - i; - bool release = false; - ret = PTR_ERR(bio); - dic->failed = true; - - if (for_verity) { - if (!atomic_sub_return(remained, - &dic->verity_pages)) - release = true; - } else { - if (!atomic_sub_return(remained, - &dic->pending_pages)) - release = true; - } - - if (release) { - f2fs_decompress_end_io(dic->rpages, - cc->cluster_size, true, - false); - f2fs_free_dic(dic); - } - + f2fs_decompress_end_io(dic, ret); f2fs_put_dnode(&dn); *bio_ret = NULL; return ret; @@ -2308,10 +2197,9 @@ submit_and_realloc: if (bio_add_page(bio, page, blocksize, 0) < blocksize) goto submit_and_realloc; - /* tag STEP_DECOMPRESS to handle IO in wq */ ctx = bio->bi_private; - if (!(ctx->enabled_steps & (1 << STEP_DECOMPRESS))) - ctx->enabled_steps |= 1 << STEP_DECOMPRESS; + ctx->enabled_steps |= STEP_DECOMPRESS; + refcount_inc(&dic->refcnt); inc_page_count(sbi, F2FS_RD_DATA); f2fs_update_iostat(sbi, FS_DATA_READ_IO, F2FS_BLKSIZE); @@ -2328,7 +2216,13 @@ submit_and_realloc: out_put_dnode: f2fs_put_dnode(&dn); out: - f2fs_decompress_end_io(cc->rpages, cc->cluster_size, true, false); + for (i = 0; i < cc->cluster_size; i++) { + if (cc->rpages[i]) { + ClearPageUptodate(cc->rpages[i]); + ClearPageError(cc->rpages[i]); + unlock_page(cc->rpages[i]); + } + } *bio_ret = bio; return ret; } @@ -2337,11 +2231,6 @@ out: /* * This function was originally taken from fs/mpage.c, and customized for f2fs. * Major change was from block_size == page_size in f2fs by default. - * - * Note that the aops->readpages() function is ONLY used for read-ahead. If - * this function ever deviates from doing just read-ahead, it should either - * use ->readpage() or do the necessary surgery to decouple ->readpages() - * from read-ahead. */ static int f2fs_mpage_readpages(struct inode *inode, struct readahead_control *rac, struct page *page) @@ -2364,7 +2253,6 @@ static int f2fs_mpage_readpages(struct inode *inode, unsigned nr_pages = rac ? readahead_count(rac) : 1; unsigned max_nr_pages = nr_pages; int ret = 0; - bool drop_ra = false; map.m_pblk = 0; map.m_lblk = 0; @@ -2375,26 +2263,10 @@ static int f2fs_mpage_readpages(struct inode *inode, map.m_seg_type = NO_CHECK_TYPE; map.m_may_create = false; - /* - * Two readahead threads for same address range can cause race condition - * which fragments sequential read IOs. So let's avoid each other. - */ - if (rac && readahead_count(rac)) { - if (READ_ONCE(F2FS_I(inode)->ra_offset) == readahead_index(rac)) - drop_ra = true; - else - WRITE_ONCE(F2FS_I(inode)->ra_offset, - readahead_index(rac)); - } - for (; nr_pages; nr_pages--) { if (rac) { page = readahead_page(rac); prefetchw(&page->flags); - if (drop_ra) { - f2fs_put_page(page, 1); - continue; - } } #ifdef CONFIG_F2FS_FS_COMPRESSION @@ -2457,9 +2329,6 @@ next_page: } if (bio) __submit_bio(F2FS_I_SB(inode), bio, DATA); - - if (rac && readahead_count(rac) && !drop_ra) - WRITE_ONCE(F2FS_I(inode)->ra_offset, -1); return ret; } @@ -2743,7 +2612,8 @@ int f2fs_write_single_data_page(struct page *page, int *submitted, sector_t *last_block, struct writeback_control *wbc, enum iostat_type io_type, - int compr_blocks) + int compr_blocks, + bool allow_balance) { struct inode *inode = page->mapping->host; struct f2fs_sb_info *sbi = F2FS_I_SB(inode); @@ -2881,7 +2751,7 @@ out: } unlock_page(page); if (!S_ISDIR(inode->i_mode) && !IS_NOQUOTA(inode) && - !F2FS_I(inode)->cp_task) + !F2FS_I(inode)->cp_task && allow_balance) f2fs_balance_fs(sbi, need_balance_fs); if (unlikely(f2fs_cp_error(sbi))) { @@ -2928,7 +2798,7 @@ out: #endif return f2fs_write_single_data_page(page, NULL, NULL, NULL, - wbc, FS_DATA_IO, 0); + wbc, FS_DATA_IO, 0, true); } /* @@ -3096,7 +2966,8 @@ continue_unlock: } #endif ret = f2fs_write_single_data_page(page, &submitted, - &bio, &last_block, wbc, io_type, 0); + &bio, &last_block, wbc, io_type, + 0, true); if (ret == AOP_WRITEPAGE_ACTIVATE) unlock_page(page); #ifdef CONFIG_F2FS_FS_COMPRESSION @@ -3831,7 +3702,7 @@ static sector_t f2fs_bmap(struct address_space *mapping, sector_t block) filemap_write_and_wait(mapping); /* Block number less than F2FS MAX BLOCKS */ - if (unlikely(block >= F2FS_I_SB(inode)->max_file_blocks)) + if (unlikely(block >= max_file_blocks(inode))) goto out; if (f2fs_compressed_file(inode)) { @@ -4108,12 +3979,13 @@ static int f2fs_swap_activate(struct swap_info_struct *sis, struct file *file, if (!f2fs_disable_compressed_file(inode)) return -EINVAL; + f2fs_precache_extents(inode); + ret = check_swap_activate(sis, file, span); if (ret < 0) return ret; set_inode_flag(inode, FI_PIN_FILE); - f2fs_precache_extents(inode); f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); return ret; } diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c index 197c914119da..91855d5721cd 100644 --- a/fs/f2fs/debug.c +++ b/fs/f2fs/debug.c @@ -120,6 +120,13 @@ static void update_general_status(struct f2fs_sb_info *sbi) atomic_read(&SM_I(sbi)->dcc_info->discard_cmd_cnt); si->undiscard_blks = SM_I(sbi)->dcc_info->undiscard_blks; } + si->nr_issued_ckpt = atomic_read(&sbi->cprc_info.issued_ckpt); + si->nr_total_ckpt = atomic_read(&sbi->cprc_info.total_ckpt); + si->nr_queued_ckpt = atomic_read(&sbi->cprc_info.queued_ckpt); + spin_lock(&sbi->cprc_info.stat_lock); + si->cur_ckpt_time = sbi->cprc_info.cur_time; + si->peak_ckpt_time = sbi->cprc_info.peak_time; + spin_unlock(&sbi->cprc_info.stat_lock); si->total_count = (int)sbi->user_block_count / sbi->blocks_per_seg; si->rsvd_segs = reserved_segments(sbi); si->overp_segs = overprovision_segments(sbi); @@ -417,6 +424,11 @@ static int stat_show(struct seq_file *s, void *v) si->meta_count[META_NAT]); seq_printf(s, " - ssa blocks : %u\n", si->meta_count[META_SSA]); + seq_printf(s, "CP merge (Queued: %4d, Issued: %4d, Total: %4d, " + "Cur time: %4d(ms), Peak time: %4d(ms))\n", + si->nr_queued_ckpt, si->nr_issued_ckpt, + si->nr_total_ckpt, si->cur_ckpt_time, + si->peak_ckpt_time); seq_printf(s, "GC calls: %d (BG: %d)\n", si->call_count, si->bg_gc); seq_printf(s, " - data segments : %d (%d)\n", diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index bb11759191dc..506c801880f3 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -43,7 +43,6 @@ enum { FAULT_KVMALLOC, FAULT_PAGE_ALLOC, FAULT_PAGE_GET, - FAULT_ALLOC_BIO, FAULT_ALLOC_NID, FAULT_ORPHAN, FAULT_BLOCK, @@ -97,6 +96,7 @@ extern const char *f2fs_fault_name[FAULT_MAX]; #define F2FS_MOUNT_DISABLE_CHECKPOINT 0x02000000 #define F2FS_MOUNT_NORECOVERY 0x04000000 #define F2FS_MOUNT_ATGC 0x08000000 +#define F2FS_MOUNT_MERGE_CHECKPOINT 0x10000000 #define F2FS_OPTION(sbi) ((sbi)->mount_opt) #define clear_opt(sbi, option) (F2FS_OPTION(sbi).opt &= ~F2FS_MOUNT_##option) @@ -146,6 +146,7 @@ struct f2fs_mount_info { /* For compression */ unsigned char compress_algorithm; /* algorithm type */ unsigned char compress_log_size; /* cluster log size */ + unsigned char compress_level; /* compress level */ bool compress_chksum; /* compressed data chksum */ unsigned char compress_ext_cnt; /* extension count */ int compress_mode; /* compression mode */ @@ -266,6 +267,26 @@ struct fsync_node_entry { unsigned int seq_id; /* sequence id */ }; +struct ckpt_req { + struct completion wait; /* completion for checkpoint done */ + struct llist_node llnode; /* llist_node to be linked in wait queue */ + int ret; /* return code of checkpoint */ + ktime_t queue_time; /* request queued time */ +}; + +struct ckpt_req_control { + struct task_struct *f2fs_issue_ckpt; /* checkpoint task */ + int ckpt_thread_ioprio; /* checkpoint merge thread ioprio */ + wait_queue_head_t ckpt_wait_queue; /* waiting queue for wake-up */ + atomic_t issued_ckpt; /* # of actually issued ckpts */ + atomic_t total_ckpt; /* # of total ckpts */ + atomic_t queued_ckpt; /* # of queued ckpts */ + struct llist_head issue_list; /* list for command issue */ + spinlock_t stat_lock; /* lock for below checkpoint time stats */ + unsigned int cur_time; /* cur wait time in msec for currently issued checkpoint */ + unsigned int peak_time; /* peak wait time in msec until now */ +}; + /* for the bitmap indicate blocks to be discarded */ struct discard_entry { struct list_head list; /* list head */ @@ -717,7 +738,6 @@ struct f2fs_inode_info { struct list_head inmem_pages; /* inmemory pages managed by f2fs */ struct task_struct *inmem_task; /* store inmemory task */ struct mutex inmem_lock; /* lock for inmemory pages */ - pgoff_t ra_offset; /* ongoing readahead offset */ struct extent_tree *extent_tree; /* cached extent_tree entry */ /* avoid racing between foreground op and gc */ @@ -735,6 +755,7 @@ struct f2fs_inode_info { atomic_t i_compr_blocks; /* # of compressed blocks */ unsigned char i_compress_algorithm; /* algorithm type */ unsigned char i_log_cluster_size; /* log of cluster size */ + unsigned char i_compress_level; /* compress level (lz4hc,zstd) */ unsigned short i_compress_flag; /* compress flag */ unsigned int i_cluster_size; /* cluster size */ }; @@ -1310,6 +1331,8 @@ struct compress_data { #define F2FS_COMPRESSED_PAGE_MAGIC 0xF5F2C000 +#define COMPRESS_LEVEL_OFFSET 8 + /* compress context */ struct compress_ctx { struct inode *inode; /* inode the context belong to */ @@ -1337,7 +1360,7 @@ struct compress_io_ctx { atomic_t pending_pages; /* in-flight compressed page count */ }; -/* decompress io context for read IO path */ +/* Context for decompressing one cluster on the read IO path */ struct decompress_io_ctx { u32 magic; /* magic number to indicate page is compressed */ struct inode *inode; /* inode the context belong to */ @@ -1353,11 +1376,37 @@ struct decompress_io_ctx { struct compress_data *cbuf; /* virtual mapped address on cpages */ size_t rlen; /* valid data length in rbuf */ size_t clen; /* valid data length in cbuf */ - atomic_t pending_pages; /* in-flight compressed page count */ - atomic_t verity_pages; /* in-flight page count for verity */ - bool failed; /* indicate IO error during decompression */ + + /* + * The number of compressed pages remaining to be read in this cluster. + * This is initially nr_cpages. It is decremented by 1 each time a page + * has been read (or failed to be read). When it reaches 0, the cluster + * is decompressed (or an error is reported). + * + * If an error occurs before all the pages have been submitted for I/O, + * then this will never reach 0. In this case the I/O submitter is + * responsible for calling f2fs_decompress_end_io() instead. + */ + atomic_t remaining_pages; + + /* + * Number of references to this decompress_io_ctx. + * + * One reference is held for I/O completion. This reference is dropped + * after the pagecache pages are updated and unlocked -- either after + * decompression (and verity if enabled), or after an error. + * + * In addition, each compressed page holds a reference while it is in a + * bio. These references are necessary prevent compressed pages from + * being freed while they are still in a bio. + */ + refcount_t refcnt; + + bool failed; /* IO error occurred before decompression? */ + bool need_verity; /* need fs-verity verification after decompression? */ void *private; /* payload buffer for specified decompression algorithm */ void *private2; /* extra payload buffer */ + struct work_struct verity_work; /* work to verify the decompressed pages */ }; #define NULL_CLUSTER ((unsigned int)(~0)) @@ -1404,6 +1453,7 @@ struct f2fs_sb_info { wait_queue_head_t cp_wait; unsigned long last_time[MAX_TIME]; /* to store time in jiffies */ long interval_time[MAX_TIME]; /* to store thresholds */ + struct ckpt_req_control cprc_info; /* for checkpoint request control */ struct inode_management im[MAX_INO_ENTRY]; /* manage inode cache */ @@ -1444,7 +1494,6 @@ struct f2fs_sb_info { unsigned int total_sections; /* total section count */ unsigned int total_node_count; /* total node block count */ unsigned int total_valid_node_count; /* valid node block count */ - loff_t max_file_blocks; /* max block index of file */ int dir_level; /* directory level */ int readdir_ra; /* readahead inode in readdir */ u64 max_io_bytes; /* max io bytes to merge IOs */ @@ -1541,9 +1590,12 @@ struct f2fs_sb_info { unsigned int node_io_flag; /* For sysfs suppport */ - struct kobject s_kobj; + struct kobject s_kobj; /* /sys/fs/f2fs/<devname> */ struct completion s_kobj_unregister; + struct kobject s_stat_kobj; /* /sys/fs/f2fs/<devname>/stat */ + struct completion s_stat_kobj_unregister; + /* For shrinker support */ struct list_head s_list; int s_ndevs; /* number of devices */ @@ -3232,6 +3284,7 @@ int f2fs_inode_dirtied(struct inode *inode, bool sync); void f2fs_inode_synced(struct inode *inode); int f2fs_enable_quota_files(struct f2fs_sb_info *sbi, bool rdonly); int f2fs_quota_sync(struct super_block *sb, int type); +loff_t max_file_blocks(struct inode *inode); void f2fs_quota_off_umount(struct super_block *sb); int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover); int f2fs_sync_fs(struct super_block *sb, int sync); @@ -3418,13 +3471,16 @@ int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc); void f2fs_init_ino_entry_info(struct f2fs_sb_info *sbi); int __init f2fs_create_checkpoint_caches(void); void f2fs_destroy_checkpoint_caches(void); +int f2fs_issue_checkpoint(struct f2fs_sb_info *sbi); +int f2fs_start_ckpt_thread(struct f2fs_sb_info *sbi); +void f2fs_stop_ckpt_thread(struct f2fs_sb_info *sbi); +void f2fs_init_ckpt_req_control(struct f2fs_sb_info *sbi); /* * data.c */ int __init f2fs_init_bioset(void); void f2fs_destroy_bioset(void); -struct bio *f2fs_bio_alloc(struct f2fs_sb_info *sbi, int npages, bool noio); int f2fs_init_bio_entry_cache(void); void f2fs_destroy_bio_entry_cache(void); void f2fs_submit_bio(struct f2fs_sb_info *sbi, @@ -3469,7 +3525,7 @@ int f2fs_write_single_data_page(struct page *page, int *submitted, struct bio **bio, sector_t *last_block, struct writeback_control *wbc, enum iostat_type io_type, - int compr_blocks); + int compr_blocks, bool allow_balance); void f2fs_invalidate_page(struct page *page, unsigned int offset, unsigned int length); int f2fs_release_page(struct page *page, gfp_t wait); @@ -3530,6 +3586,8 @@ struct f2fs_stat_info { int nr_discarding, nr_discarded; int nr_discard_cmd; unsigned int undiscard_blks; + int nr_issued_ckpt, nr_total_ckpt, nr_queued_ckpt; + unsigned int cur_ckpt_time, peak_ckpt_time; int inline_xattr, inline_inode, inline_dir, append, update, orphans; int compr_inode; unsigned long long compr_blocks; @@ -3715,8 +3773,6 @@ void f2fs_update_sit_info(struct f2fs_sb_info *sbi); #define stat_dec_compr_inode(inode) do { } while (0) #define stat_add_compr_blocks(inode, blocks) do { } while (0) #define stat_sub_compr_blocks(inode, blocks) do { } while (0) -#define stat_inc_atomic_write(inode) do { } while (0) -#define stat_dec_atomic_write(inode) do { } while (0) #define stat_update_max_atomic_write(inode) do { } while (0) #define stat_inc_volatile_write(inode) do { } while (0) #define stat_dec_volatile_write(inode) do { } while (0) @@ -3876,7 +3932,7 @@ void f2fs_compress_write_end_io(struct bio *bio, struct page *page); bool f2fs_is_compress_backend_ready(struct inode *inode); int f2fs_init_compress_mempool(void); void f2fs_destroy_compress_mempool(void); -void f2fs_decompress_pages(struct bio *bio, struct page *page, bool verity); +void f2fs_end_read_compressed_page(struct page *page, bool failed); bool f2fs_cluster_is_empty(struct compress_ctx *cc); bool f2fs_cluster_can_merge_page(struct compress_ctx *cc, pgoff_t index); void f2fs_compress_ctx_add_page(struct compress_ctx *cc, struct page *page); @@ -3889,9 +3945,8 @@ int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret, unsigned nr_pages, sector_t *last_block_in_bio, bool is_readahead, bool for_write); struct decompress_io_ctx *f2fs_alloc_dic(struct compress_ctx *cc); -void f2fs_free_dic(struct decompress_io_ctx *dic); -void f2fs_decompress_end_io(struct page **rpages, - unsigned int cluster_size, bool err, bool verity); +void f2fs_decompress_end_io(struct decompress_io_ctx *dic, bool failed); +void f2fs_put_page_dic(struct page *page); int f2fs_init_compress_ctx(struct compress_ctx *cc); void f2fs_destroy_compress_ctx(struct compress_ctx *cc); void f2fs_init_compress_info(struct f2fs_sb_info *sbi); @@ -3915,6 +3970,14 @@ static inline struct page *f2fs_compress_control_page(struct page *page) } static inline int f2fs_init_compress_mempool(void) { return 0; } static inline void f2fs_destroy_compress_mempool(void) { } +static inline void f2fs_end_read_compressed_page(struct page *page, bool failed) +{ + WARN_ON_ONCE(1); +} +static inline void f2fs_put_page_dic(struct page *page) +{ + WARN_ON_ONCE(1); +} static inline int f2fs_init_page_array_cache(struct f2fs_sb_info *sbi) { return 0; } static inline void f2fs_destroy_page_array_cache(struct f2fs_sb_info *sbi) { } static inline int __init f2fs_init_compress_cache(void) { return 0; } @@ -3934,6 +3997,11 @@ static inline void set_compress_context(struct inode *inode) 1 << COMPRESS_CHKSUM : 0; F2FS_I(inode)->i_cluster_size = 1 << F2FS_I(inode)->i_log_cluster_size; + if (F2FS_I(inode)->i_compress_algorithm == COMPRESS_LZ4 && + F2FS_OPTION(sbi).compress_level) + F2FS_I(inode)->i_compress_flag |= + F2FS_OPTION(sbi).compress_level << + COMPRESS_LEVEL_OFFSET; F2FS_I(inode)->i_flags |= F2FS_COMPR_FL; set_inode_flag(inode, FI_COMPRESSED_FILE); stat_inc_compr_inode(inode); @@ -4114,6 +4182,12 @@ static inline bool f2fs_force_buffered_io(struct inode *inode, return false; } +static inline bool f2fs_need_verity(const struct inode *inode, pgoff_t idx) +{ + return fsverity_active(inode) && + idx < DIV_ROUND_UP(inode->i_size, PAGE_SIZE); +} + #ifdef CONFIG_F2FS_FAULT_INJECTION extern void f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned int rate, unsigned int type); diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index f585545277d7..471a6ff0c937 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -29,7 +29,6 @@ #include "xattr.h" #include "acl.h" #include "gc.h" -#include "trace.h" #include <trace/events/f2fs.h> #include <uapi/linux/f2fs.h> @@ -60,6 +59,9 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf) bool need_alloc = true; int err = 0; + if (unlikely(IS_IMMUTABLE(inode))) + return VM_FAULT_SIGBUS; + if (unlikely(f2fs_cp_error(sbi))) { err = -EIO; goto err; @@ -70,6 +72,10 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf) goto err; } + err = f2fs_convert_inline_inode(inode); + if (err) + goto err; + #ifdef CONFIG_F2FS_FS_COMPRESSION if (f2fs_compressed_file(inode)) { int ret = f2fs_is_compressed_cluster(inode, page->index); @@ -366,7 +372,6 @@ flush_out: f2fs_update_time(sbi, REQ_TIME); out: trace_f2fs_sync_file_exit(inode, cp_reason, datasync, ret); - f2fs_trace_ios(NULL, 1); return ret; } @@ -483,6 +488,9 @@ static loff_t f2fs_llseek(struct file *file, loff_t offset, int whence) struct inode *inode = file->f_mapping->host; loff_t maxbytes = inode->i_sb->s_maxbytes; + if (f2fs_compressed_file(inode)) + maxbytes = max_file_blocks(inode) << F2FS_BLKSIZE_BITS; + switch (whence) { case SEEK_SET: case SEEK_CUR: @@ -502,7 +510,6 @@ static loff_t f2fs_llseek(struct file *file, loff_t offset, int whence) static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma) { struct inode *inode = file_inode(file); - int err; if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) return -EIO; @@ -510,11 +517,6 @@ static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma) if (!f2fs_is_compress_backend_ready(inode)) return -EOPNOTSUPP; - /* we don't need to use inline_data strictly */ - err = f2fs_convert_inline_inode(inode); - if (err) - return err; - file_accessed(file); vma->vm_ops = &f2fs_file_vm_ops; set_inode_flag(inode, FI_MMAP_FILE); @@ -667,7 +669,7 @@ int f2fs_do_truncate_blocks(struct inode *inode, u64 from, bool lock) free_from = (pgoff_t)F2FS_BLK_ALIGN(from); - if (free_from >= sbi->max_file_blocks) + if (free_from >= max_file_blocks(inode)) goto free_partial; if (lock) @@ -767,6 +769,10 @@ int f2fs_truncate(struct inode *inode) return -EIO; } + err = dquot_initialize(inode); + if (err) + return err; + /* we should check inline_data size */ if (!f2fs_may_inline_data(inode)) { err = f2fs_convert_inline_inode(inode); @@ -848,7 +854,8 @@ static void __setattr_copy(struct inode *inode, const struct iattr *attr) if (ia_valid & ATTR_MODE) { umode_t mode = attr->ia_mode; - if (!in_group_p(inode->i_gid) && !capable(CAP_FSETID)) + if (!in_group_p(inode->i_gid) && + !capable_wrt_inode_uidgid(inode, CAP_FSETID)) mode &= ~S_ISGID; set_acl_inode(inode, mode); } @@ -865,6 +872,14 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr) if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) return -EIO; + if (unlikely(IS_IMMUTABLE(inode))) + return -EPERM; + + if (unlikely(IS_APPEND(inode) && + (attr->ia_valid & (ATTR_MODE | ATTR_UID | + ATTR_GID | ATTR_TIMES_SET)))) + return -EPERM; + if ((attr->ia_valid & ATTR_SIZE) && !f2fs_is_compress_backend_ready(inode)) return -EOPNOTSUPP; @@ -949,8 +964,10 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr) if (attr->ia_valid & ATTR_MODE) { err = posix_acl_chmod(inode, f2fs_get_inode_mode(inode)); - if (err || is_inode_flag_set(inode, FI_ACL_MODE)) { - inode->i_mode = F2FS_I(inode)->i_acl_mode; + + if (is_inode_flag_set(inode, FI_ACL_MODE)) { + if (!err) + inode->i_mode = F2FS_I(inode)->i_acl_mode; clear_inode_flag(inode, FI_ACL_MODE); } } @@ -2730,7 +2747,7 @@ static int f2fs_ioc_defragment(struct file *filp, unsigned long arg) return -EINVAL; if (unlikely((range.start + range.len) >> PAGE_SHIFT > - sbi->max_file_blocks)) + max_file_blocks(inode))) return -EINVAL; err = mnt_want_write_file(filp); @@ -3293,7 +3310,7 @@ int f2fs_precache_extents(struct inode *inode) map.m_next_extent = &m_next_extent; map.m_seg_type = NO_CHECK_TYPE; map.m_may_create = false; - end = F2FS_I_SB(inode)->max_file_blocks; + end = max_file_blocks(inode); while (map.m_lblk < end) { map.m_len = end - map.m_lblk; @@ -3357,6 +3374,14 @@ static int f2fs_ioc_measure_verity(struct file *filp, unsigned long arg) return fsverity_ioctl_measure(filp, (void __user *)arg); } +static int f2fs_ioc_read_verity_metadata(struct file *filp, unsigned long arg) +{ + if (!f2fs_sb_has_verity(F2FS_I_SB(file_inode(filp)))) + return -EOPNOTSUPP; + + return fsverity_ioctl_read_metadata(filp, (const void __user *)arg); +} + static int f2fs_ioc_getfslabel(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); @@ -4043,8 +4068,10 @@ static int redirty_blocks(struct inode *inode, pgoff_t page_idx, int len) for (i = 0; i < page_len; i++, redirty_idx++) { page = find_lock_page(mapping, redirty_idx); - if (!page) - ret = -ENOENT; + if (!page) { + ret = -ENOMEM; + break; + } set_page_dirty(page); f2fs_put_page(page, 1); f2fs_put_page(page, 0); @@ -4272,6 +4299,8 @@ static long __f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) return f2fs_ioc_enable_verity(filp, arg); case FS_IOC_MEASURE_VERITY: return f2fs_ioc_measure_verity(filp, arg); + case FS_IOC_READ_VERITY_METADATA: + return f2fs_ioc_read_verity_metadata(filp, arg); case FS_IOC_GETFSLABEL: return f2fs_ioc_getfslabel(filp, arg); case FS_IOC_SETFSLABEL: @@ -4349,6 +4378,11 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) inode_lock(inode); } + if (unlikely(IS_IMMUTABLE(inode))) { + ret = -EPERM; + goto unlock; + } + ret = generic_write_checks(iocb, from); if (ret > 0) { bool preallocated = false; @@ -4413,6 +4447,7 @@ write: if (ret > 0) f2fs_update_iostat(F2FS_I_SB(inode), APP_WRITE_IO, ret); } +unlock: inode_unlock(inode); out: trace_f2fs_file_write_iter(inode, iocb->ki_pos, @@ -4523,6 +4558,7 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case F2FS_IOC_RESIZE_FS: case FS_IOC_ENABLE_VERITY: case FS_IOC_MEASURE_VERITY: + case FS_IOC_READ_VERITY_METADATA: case FS_IOC_GETFSLABEL: case FS_IOC_SETFSLABEL: case F2FS_IOC_GET_COMPRESS_BLOCKS: diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 3ef84e6ded41..39330ad3c44e 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -1169,8 +1169,6 @@ static int move_data_block(struct inode *inode, block_t bidx, if (err) goto put_out; - set_summary(&sum, dn.nid, dn.ofs_in_node, ni.version); - /* read page */ fio.page = page; fio.new_blkaddr = fio.old_blkaddr = dn.data_blkaddr; @@ -1207,6 +1205,9 @@ static int move_data_block(struct inode *inode, block_t bidx, } } + set_summary(&sum, dn.nid, dn.ofs_in_node, ni.version); + + /* allocate block address */ f2fs_allocate_data_block(fio.sbi, NULL, fio.old_blkaddr, &newaddr, &sum, type, NULL); @@ -1233,9 +1234,6 @@ static int move_data_block(struct inode *inode, block_t bidx, set_page_writeback(fio.encrypted_page); ClearPageError(page); - /* allocate block address */ - f2fs_wait_on_page_writeback(dn.node_page, NODE, true, true); - fio.op = REQ_OP_WRITE; fio.op_flags = REQ_SYNC; fio.new_blkaddr = newaddr; diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c index 806ebabf5870..993caefcd2bb 100644 --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -192,6 +192,10 @@ int f2fs_convert_inline_inode(struct inode *inode) f2fs_hw_is_readonly(sbi) || f2fs_readonly(sbi->sb)) return 0; + err = dquot_initialize(inode); + if (err) + return err; + page = f2fs_grab_cache_page(inode->i_mapping, 0, false); if (!page) return -ENOMEM; diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index 6edb1ab579a1..887804968576 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -855,7 +855,11 @@ static int __f2fs_tmpfile(struct inode *dir, struct dentry *dentry, if (whiteout) { f2fs_i_links_write(inode, false); + + spin_lock(&inode->i_lock); inode->i_state |= I_LINKABLE; + spin_unlock(&inode->i_lock); + *whiteout = inode; } else { d_tmpfile(dentry, inode); @@ -1041,7 +1045,11 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, err = f2fs_add_link(old_dentry, whiteout); if (err) goto put_out_dir; + + spin_lock(&whiteout->i_lock); whiteout->i_state &= ~I_LINKABLE; + spin_unlock(&whiteout->i_lock); + iput(whiteout); } diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 3a24423ac65f..a8a0fb890e8d 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -17,7 +17,6 @@ #include "node.h" #include "segment.h" #include "xattr.h" -#include "trace.h" #include <trace/events/f2fs.h> #define on_f2fs_build_free_nids(nmi) mutex_is_locked(&(nm_i)->build_lock) @@ -2089,7 +2088,6 @@ static int f2fs_set_node_page_dirty(struct page *page) __set_page_dirty_nobuffers(page); inc_page_count(F2FS_P_SB(page), F2FS_DIRTY_NODES); f2fs_set_page_private(page, 0); - f2fs_trace_pid(page); return 1; } return 0; @@ -2696,7 +2694,7 @@ retry: src = F2FS_INODE(page); dst = F2FS_INODE(ipage); - memcpy(dst, src, (unsigned long)&src->i_ext - (unsigned long)src); + memcpy(dst, src, offsetof(struct f2fs_inode, i_ext)); dst->i_size = 0; dst->i_blocks = cpu_to_le64(1); dst->i_links = cpu_to_le32(1); diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index deca74cb17df..993004f06a77 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -20,7 +20,6 @@ #include "segment.h" #include "node.h" #include "gc.h" -#include "trace.h" #include <trace/events/f2fs.h> #define __reverse_ffz(x) __reverse_ffs(~(x)) @@ -187,8 +186,6 @@ void f2fs_register_inmem_page(struct inode *inode, struct page *page) { struct inmem_pages *new; - f2fs_trace_pid(page); - f2fs_set_page_private(page, ATOMIC_WRITTEN_PAGE); new = f2fs_kmem_cache_alloc(inmem_entry_slab, GFP_NOFS); @@ -566,17 +563,7 @@ do_sync: static int __submit_flush_wait(struct f2fs_sb_info *sbi, struct block_device *bdev) { - struct bio *bio; - int ret; - - bio = f2fs_bio_alloc(sbi, 0, false); - if (!bio) - return -ENOMEM; - - bio->bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH; - bio_set_dev(bio, bdev); - ret = submit_bio_wait(bio); - bio_put(bio); + int ret = blkdev_issue_flush(bdev); trace_f2fs_issue_flush(bdev, test_opt(sbi, NOBARRIER), test_opt(sbi, FLUSH_MERGE), ret); @@ -610,8 +597,6 @@ repeat: if (kthread_should_stop()) return 0; - sb_start_intwrite(sbi->sb); - if (!llist_empty(&fcc->issue_list)) { struct flush_cmd *cmd, *next; int ret; @@ -632,8 +617,6 @@ repeat: fcc->dispatch_list = NULL; } - sb_end_intwrite(sbi->sb); - wait_event_interruptible(*q, kthread_should_stop() || !llist_empty(&fcc->issue_list)); goto repeat; diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h index e81eb0748e2a..229814b4f4a6 100644 --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -101,11 +101,11 @@ static inline void sanity_check_seg_type(struct f2fs_sb_info *sbi, #define BLKS_PER_SEC(sbi) \ ((sbi)->segs_per_sec * (sbi)->blocks_per_seg) #define GET_SEC_FROM_SEG(sbi, segno) \ - ((segno) / (sbi)->segs_per_sec) + (((segno) == -1) ? -1: (segno) / (sbi)->segs_per_sec) #define GET_SEG_FROM_SEC(sbi, secno) \ ((secno) * (sbi)->segs_per_sec) #define GET_ZONE_FROM_SEC(sbi, secno) \ - ((secno) / (sbi)->secs_per_zone) + (((secno) == -1) ? -1: (secno) / (sbi)->secs_per_zone) #define GET_ZONE_FROM_SEG(sbi, segno) \ GET_ZONE_FROM_SEC(sbi, GET_SEC_FROM_SEG(sbi, segno)) diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index b4a07fe62d1a..4acfa7d36731 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -25,13 +25,14 @@ #include <linux/quota.h> #include <linux/unicode.h> #include <linux/part_stat.h> +#include <linux/zstd.h> +#include <linux/lz4.h> #include "f2fs.h" #include "node.h" #include "segment.h" #include "xattr.h" #include "gc.h" -#include "trace.h" #define CREATE_TRACE_POINTS #include <trace/events/f2fs.h> @@ -45,7 +46,6 @@ const char *f2fs_fault_name[FAULT_MAX] = { [FAULT_KVMALLOC] = "kvmalloc", [FAULT_PAGE_ALLOC] = "page alloc", [FAULT_PAGE_GET] = "page get", - [FAULT_ALLOC_BIO] = "alloc bio", [FAULT_ALLOC_NID] = "alloc nid", [FAULT_ORPHAN] = "orphan", [FAULT_BLOCK] = "no more block", @@ -143,6 +143,8 @@ enum { Opt_checkpoint_disable_cap, Opt_checkpoint_disable_cap_perc, Opt_checkpoint_enable, + Opt_checkpoint_merge, + Opt_nocheckpoint_merge, Opt_compress_algorithm, Opt_compress_log_size, Opt_compress_extension, @@ -213,6 +215,8 @@ static match_table_t f2fs_tokens = { {Opt_checkpoint_disable_cap, "checkpoint=disable:%u"}, {Opt_checkpoint_disable_cap_perc, "checkpoint=disable:%u%%"}, {Opt_checkpoint_enable, "checkpoint=enable"}, + {Opt_checkpoint_merge, "checkpoint_merge"}, + {Opt_nocheckpoint_merge, "nocheckpoint_merge"}, {Opt_compress_algorithm, "compress_algorithm=%s"}, {Opt_compress_log_size, "compress_log_size=%u"}, {Opt_compress_extension, "compress_extension=%s"}, @@ -464,6 +468,74 @@ static int f2fs_set_test_dummy_encryption(struct super_block *sb, return 0; } +#ifdef CONFIG_F2FS_FS_COMPRESSION +#ifdef CONFIG_F2FS_FS_LZ4 +static int f2fs_set_lz4hc_level(struct f2fs_sb_info *sbi, const char *str) +{ +#ifdef CONFIG_F2FS_FS_LZ4HC + unsigned int level; +#endif + + if (strlen(str) == 3) { + F2FS_OPTION(sbi).compress_level = 0; + return 0; + } + +#ifdef CONFIG_F2FS_FS_LZ4HC + str += 3; + + if (str[0] != ':') { + f2fs_info(sbi, "wrong format, e.g. <alg_name>:<compr_level>"); + return -EINVAL; + } + if (kstrtouint(str + 1, 10, &level)) + return -EINVAL; + + if (level < LZ4HC_MIN_CLEVEL || level > LZ4HC_MAX_CLEVEL) { + f2fs_info(sbi, "invalid lz4hc compress level: %d", level); + return -EINVAL; + } + + F2FS_OPTION(sbi).compress_level = level; + return 0; +#else + f2fs_info(sbi, "kernel doesn't support lz4hc compression"); + return -EINVAL; +#endif +} +#endif + +#ifdef CONFIG_F2FS_FS_ZSTD +static int f2fs_set_zstd_level(struct f2fs_sb_info *sbi, const char *str) +{ + unsigned int level; + int len = 4; + + if (strlen(str) == len) { + F2FS_OPTION(sbi).compress_level = 0; + return 0; + } + + str += len; + + if (str[0] != ':') { + f2fs_info(sbi, "wrong format, e.g. <alg_name>:<compr_level>"); + return -EINVAL; + } + if (kstrtouint(str + 1, 10, &level)) + return -EINVAL; + + if (!level || level > ZSTD_maxCLevel()) { + f2fs_info(sbi, "invalid zstd compress level: %d", level); + return -EINVAL; + } + + F2FS_OPTION(sbi).compress_level = level; + return 0; +} +#endif +#endif + static int parse_options(struct super_block *sb, char *options, bool is_remount) { struct f2fs_sb_info *sbi = F2FS_SB(sb); @@ -872,6 +944,12 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount) case Opt_checkpoint_enable: clear_opt(sbi, DISABLE_CHECKPOINT); break; + case Opt_checkpoint_merge: + set_opt(sbi, MERGE_CHECKPOINT); + break; + case Opt_nocheckpoint_merge: + clear_opt(sbi, MERGE_CHECKPOINT); + break; #ifdef CONFIG_F2FS_FS_COMPRESSION case Opt_compress_algorithm: if (!f2fs_sb_has_compression(sbi)) { @@ -882,17 +960,45 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount) if (!name) return -ENOMEM; if (!strcmp(name, "lzo")) { +#ifdef CONFIG_F2FS_FS_LZO + F2FS_OPTION(sbi).compress_level = 0; F2FS_OPTION(sbi).compress_algorithm = COMPRESS_LZO; - } else if (!strcmp(name, "lz4")) { +#else + f2fs_info(sbi, "kernel doesn't support lzo compression"); +#endif + } else if (!strncmp(name, "lz4", 3)) { +#ifdef CONFIG_F2FS_FS_LZ4 + ret = f2fs_set_lz4hc_level(sbi, name); + if (ret) { + kfree(name); + return -EINVAL; + } F2FS_OPTION(sbi).compress_algorithm = COMPRESS_LZ4; - } else if (!strcmp(name, "zstd")) { +#else + f2fs_info(sbi, "kernel doesn't support lz4 compression"); +#endif + } else if (!strncmp(name, "zstd", 4)) { +#ifdef CONFIG_F2FS_FS_ZSTD + ret = f2fs_set_zstd_level(sbi, name); + if (ret) { + kfree(name); + return -EINVAL; + } F2FS_OPTION(sbi).compress_algorithm = COMPRESS_ZSTD; +#else + f2fs_info(sbi, "kernel doesn't support zstd compression"); +#endif } else if (!strcmp(name, "lzo-rle")) { +#ifdef CONFIG_F2FS_FS_LZORLE + F2FS_OPTION(sbi).compress_level = 0; F2FS_OPTION(sbi).compress_algorithm = COMPRESS_LZORLE; +#else + f2fs_info(sbi, "kernel doesn't support lzorle compression"); +#endif } else { kfree(name); return -EINVAL; @@ -1076,8 +1182,6 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb) /* Will be used by directory only */ fi->i_dir_level = F2FS_SB(sb)->dir_level; - fi->ra_offset = -1; - return &fi->vfs_inode; } @@ -1246,6 +1350,12 @@ static void f2fs_put_super(struct super_block *sb) mutex_lock(&sbi->umount_mutex); /* + * flush all issued checkpoints and stop checkpoint issue thread. + * after then, all checkpoints should be done by each process context. + */ + f2fs_stop_ckpt_thread(sbi); + + /* * We don't need to do checkpoint when superblock is clean. * But, the previous checkpoint was not done by umount, it needs to do * clean checkpoint again. @@ -1343,16 +1453,8 @@ int f2fs_sync_fs(struct super_block *sb, int sync) if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) return -EAGAIN; - if (sync) { - struct cp_control cpc; - - cpc.reason = __get_cp_reason(sbi); - - down_write(&sbi->gc_lock); - err = f2fs_write_checkpoint(sbi, &cpc); - up_write(&sbi->gc_lock); - } - f2fs_trace_ios(NULL, 1); + if (sync) + err = f2fs_issue_checkpoint(sbi); return err; } @@ -1369,6 +1471,10 @@ static int f2fs_freeze(struct super_block *sb) /* must be clean, since sync_filesystem() was already called */ if (is_sbi_flag_set(F2FS_SB(sb), SBI_IS_DIRTY)) return -EINVAL; + + /* ensure no checkpoint required */ + if (!llist_empty(&F2FS_SB(sb)->cprc_info.issue_list)) + return -EINVAL; return 0; } @@ -1539,6 +1645,9 @@ static inline void f2fs_show_compress_options(struct seq_file *seq, } seq_printf(seq, ",compress_algorithm=%s", algtype); + if (F2FS_OPTION(sbi).compress_level) + seq_printf(seq, ":%d", F2FS_OPTION(sbi).compress_level); + seq_printf(seq, ",compress_log_size=%u", F2FS_OPTION(sbi).compress_log_size); @@ -1674,6 +1783,10 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) if (test_opt(sbi, DISABLE_CHECKPOINT)) seq_printf(seq, ",checkpoint=disable:%u", F2FS_OPTION(sbi).unusable_cap); + if (test_opt(sbi, MERGE_CHECKPOINT)) + seq_puts(seq, ",checkpoint_merge"); + else + seq_puts(seq, ",nocheckpoint_merge"); if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_POSIX) seq_printf(seq, ",fsync_mode=%s", "posix"); else if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_STRICT) @@ -1796,6 +1909,9 @@ restore_flag: static void f2fs_enable_checkpoint(struct f2fs_sb_info *sbi) { + /* we should flush all the data to keep data consistency */ + sync_inodes_sb(sbi->sb); + down_write(&sbi->gc_lock); f2fs_dirty_to_prefree(sbi); @@ -1954,6 +2070,19 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) } } + if (!test_opt(sbi, DISABLE_CHECKPOINT) && + test_opt(sbi, MERGE_CHECKPOINT)) { + err = f2fs_start_ckpt_thread(sbi); + if (err) { + f2fs_err(sbi, + "Failed to start F2FS issue_checkpoint_thread (%d)", + err); + goto restore_gc; + } + } else { + f2fs_stop_ckpt_thread(sbi); + } + /* * We stop issue flush thread if FS is mounted as RO * or if flush_merge is not passed in mount option. @@ -2638,10 +2767,10 @@ static const struct export_operations f2fs_export_ops = { .get_parent = f2fs_get_parent, }; -static loff_t max_file_blocks(void) +loff_t max_file_blocks(struct inode *inode) { loff_t result = 0; - loff_t leaf_count = DEF_ADDRS_PER_BLOCK; + loff_t leaf_count; /* * note: previously, result is equal to (DEF_ADDRS_PER_INODE - @@ -2650,6 +2779,11 @@ static loff_t max_file_blocks(void) * result as zero. */ + if (inode && f2fs_compressed_file(inode)) + leaf_count = ADDRS_PER_BLOCK(inode); + else + leaf_count = DEF_ADDRS_PER_BLOCK; + /* two direct node blocks */ result += (leaf_count * 2); @@ -3533,8 +3667,7 @@ try_onemore: if (err) goto free_options; - sbi->max_file_blocks = max_file_blocks(); - sb->s_maxbytes = sbi->max_file_blocks << + sb->s_maxbytes = max_file_blocks(NULL) << le32_to_cpu(raw_super->log_blocksize); sb->s_max_links = F2FS_LINK_MAX; @@ -3701,6 +3834,19 @@ try_onemore: f2fs_init_fsync_node_info(sbi); + /* setup checkpoint request control and start checkpoint issue thread */ + f2fs_init_ckpt_req_control(sbi); + if (!test_opt(sbi, DISABLE_CHECKPOINT) && + test_opt(sbi, MERGE_CHECKPOINT)) { + err = f2fs_start_ckpt_thread(sbi); + if (err) { + f2fs_err(sbi, + "Failed to start F2FS issue_checkpoint_thread (%d)", + err); + goto stop_ckpt_thread; + } + } + /* setup f2fs internal modules */ err = f2fs_build_segment_manager(sbi); if (err) { @@ -3786,12 +3932,10 @@ try_onemore: * previous checkpoint was not done by clean system shutdown. */ if (f2fs_hw_is_readonly(sbi)) { - if (!is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG)) { - err = -EROFS; + if (!is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG)) f2fs_err(sbi, "Need to recover fsync data, but write access unavailable"); - goto free_meta; - } - f2fs_info(sbi, "write access unavailable, skipping recovery"); + else + f2fs_info(sbi, "write access unavailable, skipping recovery"); goto reset_checkpoint; } @@ -3910,6 +4054,8 @@ free_nm: free_sm: f2fs_destroy_segment_manager(sbi); f2fs_destroy_post_read_wq(sbi); +stop_ckpt_thread: + f2fs_stop_ckpt_thread(sbi); free_devices: destroy_device_list(sbi); kvfree(sbi->ckpt); @@ -4024,8 +4170,6 @@ static int __init init_f2fs_fs(void) return -EINVAL; } - f2fs_build_trace_ios(); - err = init_inodecache(); if (err) goto fail; @@ -4118,7 +4262,6 @@ static void __exit exit_f2fs_fs(void) f2fs_destroy_segment_manager_caches(); f2fs_destroy_node_manager_caches(); destroy_inodecache(); - f2fs_destroy_trace_ios(); } module_init(init_f2fs_fs) diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index 30bae57428d1..e38a7f6921dd 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -11,6 +11,7 @@ #include <linux/f2fs_fs.h> #include <linux/seq_file.h> #include <linux/unicode.h> +#include <linux/ioprio.h> #include "f2fs.h" #include "segment.h" @@ -34,6 +35,7 @@ enum { FAULT_INFO_TYPE, /* struct f2fs_fault_info */ #endif RESERVED_BLOCKS, /* struct f2fs_sb_info */ + CPRC_INFO, /* struct ckpt_req_control */ }; struct f2fs_attr { @@ -70,6 +72,8 @@ static unsigned char *__struct_ptr(struct f2fs_sb_info *sbi, int struct_type) else if (struct_type == STAT_INFO) return (unsigned char *)F2FS_STAT(sbi); #endif + else if (struct_type == CPRC_INFO) + return (unsigned char *)&sbi->cprc_info; return NULL; } @@ -96,6 +100,12 @@ static ssize_t lifetime_write_kbytes_show(struct f2fs_attr *a, sbi->sectors_written_start) >> 1))); } +static ssize_t sb_status_show(struct f2fs_attr *a, + struct f2fs_sb_info *sbi, char *buf) +{ + return sprintf(buf, "%lx\n", sbi->s_flag); +} + static ssize_t features_show(struct f2fs_attr *a, struct f2fs_sb_info *sbi, char *buf) { @@ -255,6 +265,23 @@ static ssize_t f2fs_sbi_show(struct f2fs_attr *a, return len; } + if (!strcmp(a->attr.name, "ckpt_thread_ioprio")) { + struct ckpt_req_control *cprc = &sbi->cprc_info; + int len = 0; + int class = IOPRIO_PRIO_CLASS(cprc->ckpt_thread_ioprio); + int data = IOPRIO_PRIO_DATA(cprc->ckpt_thread_ioprio); + + if (class == IOPRIO_CLASS_RT) + len += scnprintf(buf + len, PAGE_SIZE - len, "rt,"); + else if (class == IOPRIO_CLASS_BE) + len += scnprintf(buf + len, PAGE_SIZE - len, "be,"); + else + return -EINVAL; + + len += scnprintf(buf + len, PAGE_SIZE - len, "%d\n", data); + return len; + } + ui = (unsigned int *)(ptr + a->offset); return sprintf(buf, "%u\n", *ui); @@ -308,6 +335,38 @@ out: return ret ? ret : count; } + if (!strcmp(a->attr.name, "ckpt_thread_ioprio")) { + const char *name = strim((char *)buf); + struct ckpt_req_control *cprc = &sbi->cprc_info; + int class; + long data; + int ret; + + if (!strncmp(name, "rt,", 3)) + class = IOPRIO_CLASS_RT; + else if (!strncmp(name, "be,", 3)) + class = IOPRIO_CLASS_BE; + else + return -EINVAL; + + name += 3; + ret = kstrtol(name, 10, &data); + if (ret) + return ret; + if (data >= IOPRIO_BE_NR || data < 0) + return -EINVAL; + + cprc->ckpt_thread_ioprio = IOPRIO_PRIO_VALUE(class, data); + if (test_opt(sbi, MERGE_CHECKPOINT)) { + ret = set_task_ioprio(cprc->f2fs_issue_ckpt, + cprc->ckpt_thread_ioprio); + if (ret) + return ret; + } + + return count; + } + ui = (unsigned int *)(ptr + a->offset); ret = kstrtoul(skip_spaces(buf), 0, &t); @@ -567,6 +626,7 @@ F2FS_RW_ATTR(FAULT_INFO_TYPE, f2fs_fault_info, inject_type, inject_type); #endif F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, data_io_flag, data_io_flag); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, node_io_flag, node_io_flag); +F2FS_RW_ATTR(CPRC_INFO, ckpt_req_control, ckpt_thread_ioprio, ckpt_thread_ioprio); F2FS_GENERAL_RO_ATTR(dirty_segments); F2FS_GENERAL_RO_ATTR(free_segments); F2FS_GENERAL_RO_ATTR(lifetime_write_kbytes); @@ -652,6 +712,7 @@ static struct attribute *f2fs_attrs[] = { #endif ATTR_LIST(data_io_flag), ATTR_LIST(node_io_flag), + ATTR_LIST(ckpt_thread_ioprio), ATTR_LIST(dirty_segments), ATTR_LIST(free_segments), ATTR_LIST(unusable), @@ -702,6 +763,13 @@ static struct attribute *f2fs_feat_attrs[] = { }; ATTRIBUTE_GROUPS(f2fs_feat); +F2FS_GENERAL_RO_ATTR(sb_status); +static struct attribute *f2fs_stat_attrs[] = { + ATTR_LIST(sb_status), + NULL, +}; +ATTRIBUTE_GROUPS(f2fs_stat); + static const struct sysfs_ops f2fs_attr_ops = { .show = f2fs_attr_show, .store = f2fs_attr_store, @@ -730,6 +798,44 @@ static struct kobject f2fs_feat = { .kset = &f2fs_kset, }; +static ssize_t f2fs_stat_attr_show(struct kobject *kobj, + struct attribute *attr, char *buf) +{ + struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info, + s_stat_kobj); + struct f2fs_attr *a = container_of(attr, struct f2fs_attr, attr); + + return a->show ? a->show(a, sbi, buf) : 0; +} + +static ssize_t f2fs_stat_attr_store(struct kobject *kobj, struct attribute *attr, + const char *buf, size_t len) +{ + struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info, + s_stat_kobj); + struct f2fs_attr *a = container_of(attr, struct f2fs_attr, attr); + + return a->store ? a->store(a, sbi, buf, len) : 0; +} + +static void f2fs_stat_kobj_release(struct kobject *kobj) +{ + struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info, + s_stat_kobj); + complete(&sbi->s_stat_kobj_unregister); +} + +static const struct sysfs_ops f2fs_stat_attr_ops = { + .show = f2fs_stat_attr_show, + .store = f2fs_stat_attr_store, +}; + +static struct kobj_type f2fs_stat_ktype = { + .default_groups = f2fs_stat_groups, + .sysfs_ops = &f2fs_stat_attr_ops, + .release = f2fs_stat_kobj_release, +}; + static int __maybe_unused segment_info_seq_show(struct seq_file *seq, void *offset) { @@ -936,11 +1042,15 @@ int f2fs_register_sysfs(struct f2fs_sb_info *sbi) init_completion(&sbi->s_kobj_unregister); err = kobject_init_and_add(&sbi->s_kobj, &f2fs_sb_ktype, NULL, "%s", sb->s_id); - if (err) { - kobject_put(&sbi->s_kobj); - wait_for_completion(&sbi->s_kobj_unregister); - return err; - } + if (err) + goto put_sb_kobj; + + sbi->s_stat_kobj.kset = &f2fs_kset; + init_completion(&sbi->s_stat_kobj_unregister); + err = kobject_init_and_add(&sbi->s_stat_kobj, &f2fs_stat_ktype, + &sbi->s_kobj, "stat"); + if (err) + goto put_stat_kobj; if (f2fs_proc_root) sbi->s_proc = proc_mkdir(sb->s_id, f2fs_proc_root); @@ -956,6 +1066,13 @@ int f2fs_register_sysfs(struct f2fs_sb_info *sbi) victim_bits_seq_show, sb); } return 0; +put_stat_kobj: + kobject_put(&sbi->s_stat_kobj); + wait_for_completion(&sbi->s_stat_kobj_unregister); +put_sb_kobj: + kobject_put(&sbi->s_kobj); + wait_for_completion(&sbi->s_kobj_unregister); + return err; } void f2fs_unregister_sysfs(struct f2fs_sb_info *sbi) @@ -967,6 +1084,11 @@ void f2fs_unregister_sysfs(struct f2fs_sb_info *sbi) remove_proc_entry("victim_bits", sbi->s_proc); remove_proc_entry(sbi->sb->s_id, f2fs_proc_root); } + + kobject_del(&sbi->s_stat_kobj); + kobject_put(&sbi->s_stat_kobj); + wait_for_completion(&sbi->s_stat_kobj_unregister); + kobject_del(&sbi->s_kobj); kobject_put(&sbi->s_kobj); wait_for_completion(&sbi->s_kobj_unregister); diff --git a/fs/f2fs/trace.c b/fs/f2fs/trace.c deleted file mode 100644 index d0ab533a9ce8..000000000000 --- a/fs/f2fs/trace.c +++ /dev/null @@ -1,165 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * f2fs IO tracer - * - * Copyright (c) 2014 Motorola Mobility - * Copyright (c) 2014 Jaegeuk Kim <jaegeuk@kernel.org> - */ -#include <linux/fs.h> -#include <linux/f2fs_fs.h> -#include <linux/sched.h> -#include <linux/radix-tree.h> - -#include "f2fs.h" -#include "trace.h" - -static RADIX_TREE(pids, GFP_ATOMIC); -static spinlock_t pids_lock; -static struct last_io_info last_io; - -static inline void __print_last_io(void) -{ - if (!last_io.len) - return; - - trace_printk("%3x:%3x %4x %-16s %2x %5x %5x %12x %4x\n", - last_io.major, last_io.minor, - last_io.pid, "----------------", - last_io.type, - last_io.fio.op, last_io.fio.op_flags, - last_io.fio.new_blkaddr, - last_io.len); - memset(&last_io, 0, sizeof(last_io)); -} - -static int __file_type(struct inode *inode, pid_t pid) -{ - if (f2fs_is_atomic_file(inode)) - return __ATOMIC_FILE; - else if (f2fs_is_volatile_file(inode)) - return __VOLATILE_FILE; - else if (S_ISDIR(inode->i_mode)) - return __DIR_FILE; - else if (inode->i_ino == F2FS_NODE_INO(F2FS_I_SB(inode))) - return __NODE_FILE; - else if (inode->i_ino == F2FS_META_INO(F2FS_I_SB(inode))) - return __META_FILE; - else if (pid) - return __NORMAL_FILE; - else - return __MISC_FILE; -} - -void f2fs_trace_pid(struct page *page) -{ - struct inode *inode = page->mapping->host; - pid_t pid = task_pid_nr(current); - void *p; - - set_page_private(page, (unsigned long)pid); - -retry: - if (radix_tree_preload(GFP_NOFS)) - return; - - spin_lock(&pids_lock); - p = radix_tree_lookup(&pids, pid); - if (p == current) - goto out; - if (p) - radix_tree_delete(&pids, pid); - - if (radix_tree_insert(&pids, pid, current)) { - spin_unlock(&pids_lock); - radix_tree_preload_end(); - cond_resched(); - goto retry; - } - - trace_printk("%3x:%3x %4x %-16s\n", - MAJOR(inode->i_sb->s_dev), MINOR(inode->i_sb->s_dev), - pid, current->comm); -out: - spin_unlock(&pids_lock); - radix_tree_preload_end(); -} - -void f2fs_trace_ios(struct f2fs_io_info *fio, int flush) -{ - struct inode *inode; - pid_t pid; - int major, minor; - - if (flush) { - __print_last_io(); - return; - } - - inode = fio->page->mapping->host; - pid = page_private(fio->page); - - major = MAJOR(inode->i_sb->s_dev); - minor = MINOR(inode->i_sb->s_dev); - - if (last_io.major == major && last_io.minor == minor && - last_io.pid == pid && - last_io.type == __file_type(inode, pid) && - last_io.fio.op == fio->op && - last_io.fio.op_flags == fio->op_flags && - last_io.fio.new_blkaddr + last_io.len == - fio->new_blkaddr) { - last_io.len++; - return; - } - - __print_last_io(); - - last_io.major = major; - last_io.minor = minor; - last_io.pid = pid; - last_io.type = __file_type(inode, pid); - last_io.fio = *fio; - last_io.len = 1; - return; -} - -void f2fs_build_trace_ios(void) -{ - spin_lock_init(&pids_lock); -} - -#define PIDVEC_SIZE 128 -static unsigned int gang_lookup_pids(pid_t *results, unsigned long first_index, - unsigned int max_items) -{ - struct radix_tree_iter iter; - void **slot; - unsigned int ret = 0; - - if (unlikely(!max_items)) - return 0; - - radix_tree_for_each_slot(slot, &pids, &iter, first_index) { - results[ret] = iter.index; - if (++ret == max_items) - break; - } - return ret; -} - -void f2fs_destroy_trace_ios(void) -{ - pid_t pid[PIDVEC_SIZE]; - pid_t next_pid = 0; - unsigned int found; - - spin_lock(&pids_lock); - while ((found = gang_lookup_pids(pid, next_pid, PIDVEC_SIZE))) { - unsigned idx; - - next_pid = pid[found - 1] + 1; - for (idx = 0; idx < found; idx++) - radix_tree_delete(&pids, pid[idx]); - } - spin_unlock(&pids_lock); -} diff --git a/fs/f2fs/trace.h b/fs/f2fs/trace.h deleted file mode 100644 index 789f6aa727fc..000000000000 --- a/fs/f2fs/trace.h +++ /dev/null @@ -1,43 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * f2fs IO tracer - * - * Copyright (c) 2014 Motorola Mobility - * Copyright (c) 2014 Jaegeuk Kim <jaegeuk@kernel.org> - */ -#ifndef __F2FS_TRACE_H__ -#define __F2FS_TRACE_H__ - -#ifdef CONFIG_F2FS_IO_TRACE -#include <trace/events/f2fs.h> - -enum file_type { - __NORMAL_FILE, - __DIR_FILE, - __NODE_FILE, - __META_FILE, - __ATOMIC_FILE, - __VOLATILE_FILE, - __MISC_FILE, -}; - -struct last_io_info { - int major, minor; - pid_t pid; - enum file_type type; - struct f2fs_io_info fio; - block_t len; -}; - -extern void f2fs_trace_pid(struct page *); -extern void f2fs_trace_ios(struct f2fs_io_info *, int); -extern void f2fs_build_trace_ios(void); -extern void f2fs_destroy_trace_ios(void); -#else -#define f2fs_trace_pid(p) -#define f2fs_trace_ios(i, n) -#define f2fs_build_trace_ios() -#define f2fs_destroy_trace_ios() - -#endif -#endif /* __F2FS_TRACE_H__ */ diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c index 65afcc3cc68a..8159fae74b9a 100644 --- a/fs/f2fs/xattr.c +++ b/fs/f2fs/xattr.c @@ -327,7 +327,7 @@ static int lookup_all_xattrs(struct inode *inode, struct page *ipage, void *last_addr = NULL; nid_t xnid = F2FS_I(inode)->i_xattr_nid; unsigned int inline_size = inline_xattr_size(inode); - int err = 0; + int err; if (!xnid && !inline_size) return -ENODATA; @@ -515,7 +515,7 @@ int f2fs_getxattr(struct inode *inode, int index, const char *name, void *buffer, size_t buffer_size, struct page *ipage) { struct f2fs_xattr_entry *entry = NULL; - int error = 0; + int error; unsigned int size, len; void *base_addr = NULL; int base_size; @@ -562,7 +562,7 @@ ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) struct inode *inode = d_inode(dentry); struct f2fs_xattr_entry *entry; void *base_addr, *last_base_addr; - int error = 0; + int error; size_t rest = buffer_size; down_read(&F2FS_I(inode)->i_xattr_sem); @@ -632,7 +632,7 @@ static int __f2fs_setxattr(struct inode *inode, int index, int found, newsize; size_t len; __u32 new_hsize; - int error = 0; + int error; if (name == NULL) return -EINVAL; @@ -673,7 +673,7 @@ static int __f2fs_setxattr(struct inode *inode, int index, } if (value && f2fs_xattr_value_same(here, value, size)) - goto exit; + goto same; } else if ((flags & XATTR_REPLACE)) { error = -ENODATA; goto exit; @@ -738,17 +738,20 @@ static int __f2fs_setxattr(struct inode *inode, int index, if (error) goto exit; - if (is_inode_flag_set(inode, FI_ACL_MODE)) { - inode->i_mode = F2FS_I(inode)->i_acl_mode; - inode->i_ctime = current_time(inode); - clear_inode_flag(inode, FI_ACL_MODE); - } if (index == F2FS_XATTR_INDEX_ENCRYPTION && !strcmp(name, F2FS_XATTR_NAME_ENCRYPTION_CONTEXT)) f2fs_set_encrypted_inode(inode); f2fs_mark_inode_dirty_sync(inode, true); if (!error && S_ISDIR(inode->i_mode)) set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_CP); + +same: + if (is_inode_flag_set(inode, FI_ACL_MODE)) { + inode->i_mode = F2FS_I(inode)->i_acl_mode; + inode->i_ctime = current_time(inode); + clear_inode_flag(inode, FI_ACL_MODE); + } + exit: kfree(base_addr); return error; diff --git a/fs/fat/file.c b/fs/fat/file.c index f9ee27cf4d7c..5fee74f1ad61 100644 --- a/fs/fat/file.c +++ b/fs/fat/file.c @@ -195,7 +195,7 @@ int fat_file_fsync(struct file *filp, loff_t start, loff_t end, int datasync) if (err) return err; - return blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL); + return blkdev_issue_flush(inode->i_sb->s_bdev); } diff --git a/fs/fcntl.c b/fs/fcntl.c index 05b36b28f2e8..483ef8861376 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -148,11 +148,15 @@ void f_delown(struct file *filp) pid_t f_getown(struct file *filp) { - pid_t pid; + pid_t pid = 0; read_lock(&filp->f_owner.lock); - pid = pid_vnr(filp->f_owner.pid); - if (filp->f_owner.pid_type == PIDTYPE_PGID) - pid = -pid; + rcu_read_lock(); + if (pid_task(filp->f_owner.pid, filp->f_owner.pid_type)) { + pid = pid_vnr(filp->f_owner.pid); + if (filp->f_owner.pid_type == PIDTYPE_PGID) + pid = -pid; + } + rcu_read_unlock(); read_unlock(&filp->f_owner.lock); return pid; } @@ -200,11 +204,14 @@ static int f_setown_ex(struct file *filp, unsigned long arg) static int f_getown_ex(struct file *filp, unsigned long arg) { struct f_owner_ex __user *owner_p = (void __user *)arg; - struct f_owner_ex owner; + struct f_owner_ex owner = {}; int ret = 0; read_lock(&filp->f_owner.lock); - owner.pid = pid_vnr(filp->f_owner.pid); + rcu_read_lock(); + if (pid_task(filp->f_owner.pid, filp->f_owner.pid_type)) + owner.pid = pid_vnr(filp->f_owner.pid); + rcu_read_unlock(); switch (filp->f_owner.pid_type) { case PIDTYPE_PID: owner.type = F_OWNER_TID; diff --git a/fs/file.c b/fs/file.c index dab120b71e44..f3a4bac2cbe9 100644 --- a/fs/file.c +++ b/fs/file.c @@ -22,6 +22,8 @@ #include <linux/close_range.h> #include <net/sock.h> +#include "internal.h" + unsigned int sysctl_nr_open __read_mostly = 1024*1024; unsigned int sysctl_nr_open_min = BITS_PER_LONG; /* our min() is unusable in constant expressions ;-/ */ @@ -732,36 +734,48 @@ int __close_range(unsigned fd, unsigned max_fd, unsigned int flags) } /* - * variant of close_fd that gets a ref on the file for later fput. - * The caller must ensure that filp_close() called on the file, and then - * an fput(). + * See close_fd_get_file() below, this variant assumes current->files->file_lock + * is held. */ -int close_fd_get_file(unsigned int fd, struct file **res) +int __close_fd_get_file(unsigned int fd, struct file **res) { struct files_struct *files = current->files; struct file *file; struct fdtable *fdt; - spin_lock(&files->file_lock); fdt = files_fdtable(files); if (fd >= fdt->max_fds) - goto out_unlock; + goto out_err; file = fdt->fd[fd]; if (!file) - goto out_unlock; + goto out_err; rcu_assign_pointer(fdt->fd[fd], NULL); __put_unused_fd(files, fd); - spin_unlock(&files->file_lock); get_file(file); *res = file; return 0; - -out_unlock: - spin_unlock(&files->file_lock); +out_err: *res = NULL; return -ENOENT; } +/* + * variant of close_fd that gets a ref on the file for later fput. + * The caller must ensure that filp_close() called on the file, and then + * an fput(). + */ +int close_fd_get_file(unsigned int fd, struct file **res) +{ + struct files_struct *files = current->files; + int ret; + + spin_lock(&files->file_lock); + ret = __close_fd_get_file(fd, res); + spin_unlock(&files->file_lock); + + return ret; +} + void do_close_on_exec(struct files_struct *files) { unsigned i; diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index acfb55834af2..c41cb887eb7d 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -1474,21 +1474,25 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) } /* - * Some filesystems may redirty the inode during the writeback - * due to delalloc, clear dirty metadata flags right before - * write_inode() + * If the inode has dirty timestamps and we need to write them, call + * mark_inode_dirty_sync() to notify the filesystem about it and to + * change I_DIRTY_TIME into I_DIRTY_SYNC. */ - spin_lock(&inode->i_lock); - - dirty = inode->i_state & I_DIRTY; if ((inode->i_state & I_DIRTY_TIME) && - ((dirty & I_DIRTY_INODE) || - wbc->sync_mode == WB_SYNC_ALL || wbc->for_sync || + (wbc->sync_mode == WB_SYNC_ALL || wbc->for_sync || time_after(jiffies, inode->dirtied_time_when + dirtytime_expire_interval * HZ))) { - dirty |= I_DIRTY_TIME; trace_writeback_lazytime(inode); + mark_inode_dirty_sync(inode); } + + /* + * Some filesystems may redirty the inode during the writeback + * due to delalloc, clear dirty metadata flags right before + * write_inode() + */ + spin_lock(&inode->i_lock); + dirty = inode->i_state & I_DIRTY; inode->i_state &= ~dirty; /* @@ -1509,8 +1513,6 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) spin_unlock(&inode->i_lock); - if (dirty & I_DIRTY_TIME) - mark_inode_dirty_sync(inode); /* Don't write the inode if only I_DIRTY_PAGES was set */ if (dirty & ~I_DIRTY_PAGES) { int err = write_inode(inode, wbc); diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index b39b339feddc..89609c299717 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -797,9 +797,7 @@ static ssize_t gfs2_file_direct_read(struct kiocb *iocb, struct iov_iter *to, if (ret) goto out_uninit; - ret = iomap_dio_rw(iocb, to, &gfs2_iomap_ops, NULL, - is_sync_kiocb(iocb)); - + ret = iomap_dio_rw(iocb, to, &gfs2_iomap_ops, NULL, 0); gfs2_glock_dq(gh); out_uninit: gfs2_holder_uninit(gh); @@ -833,8 +831,7 @@ static ssize_t gfs2_file_direct_write(struct kiocb *iocb, struct iov_iter *from, if (offset + len > i_size_read(&ip->i_inode)) goto out; - ret = iomap_dio_rw(iocb, from, &gfs2_iomap_ops, NULL, - is_sync_kiocb(iocb)); + ret = iomap_dio_rw(iocb, from, &gfs2_iomap_ops, NULL, 0); if (ret == -ENOTBLK) ret = 0; out: diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index e3da9e96b835..ca464328b79c 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -340,7 +340,7 @@ int hfsplus_file_fsync(struct file *file, loff_t start, loff_t end, } if (!test_bit(HFSPLUS_SB_NOBARRIER, &sbi->flags)) - blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL); + blkdev_issue_flush(inode->i_sb->s_bdev); inode_unlock(inode); diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c index 807119ae5adf..b9e3db3f855f 100644 --- a/fs/hfsplus/super.c +++ b/fs/hfsplus/super.c @@ -239,7 +239,7 @@ out: mutex_unlock(&sbi->vh_mutex); if (!test_bit(HFSPLUS_SB_NOBARRIER, &sbi->flags)) - blkdev_issue_flush(sb->s_bdev, GFP_KERNEL); + blkdev_issue_flush(sb->s_bdev); return error; } diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index aea35459d390..4a5beca6eaa8 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -34,6 +34,8 @@ static inline struct hostfs_inode_info *HOSTFS_I(struct inode *inode) #define FILE_HOSTFS_I(file) HOSTFS_I(file_inode(file)) +static struct kmem_cache *hostfs_inode_cache; + /* Changed in hostfs_args before the kernel starts running */ static char *root_ino = ""; static int append = 0; @@ -221,7 +223,7 @@ static struct inode *hostfs_alloc_inode(struct super_block *sb) { struct hostfs_inode_info *hi; - hi = kmalloc(sizeof(*hi), GFP_KERNEL_ACCOUNT); + hi = kmem_cache_alloc(hostfs_inode_cache, GFP_KERNEL_ACCOUNT); if (hi == NULL) return NULL; hi->fd = -1; @@ -243,7 +245,7 @@ static void hostfs_evict_inode(struct inode *inode) static void hostfs_free_inode(struct inode *inode) { - kfree(HOSTFS_I(inode)); + kmem_cache_free(hostfs_inode_cache, HOSTFS_I(inode)); } static int hostfs_show_options(struct seq_file *seq, struct dentry *root) @@ -986,12 +988,16 @@ MODULE_ALIAS_FS("hostfs"); static int __init init_hostfs(void) { + hostfs_inode_cache = KMEM_CACHE(hostfs_inode_info, 0); + if (!hostfs_inode_cache) + return -ENOMEM; return register_filesystem(&hostfs_type); } static void __exit exit_hostfs(void) { unregister_filesystem(&hostfs_type); + kmem_cache_destroy(hostfs_inode_cache); } module_init(init_hostfs) diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index b5c109703daa..21c20fd5f9ee 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -735,9 +735,10 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset, mutex_unlock(&hugetlb_fault_mutex_table[hash]); + set_page_huge_active(page); /* * unlock_page because locked by add_to_page_cache() - * page_put due to reference from alloc_huge_page() + * put_page() due to reference from alloc_huge_page() */ unlock_page(page); put_page(page); diff --git a/fs/internal.h b/fs/internal.h index 77c50befbfbe..49bfb3750b22 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -15,6 +15,7 @@ struct mount; struct shrink_control; struct fs_context; struct user_namespace; +struct pipe_inode_info; /* * block_dev.c @@ -132,6 +133,7 @@ extern struct file *do_file_open_root(struct dentry *, struct vfsmount *, const char *, const struct open_flags *); extern struct open_how build_open_how(int flags, umode_t mode); extern int build_open_flags(const struct open_how *how, struct open_flags *op); +extern int __close_fd_get_file(unsigned int fd, struct file **res); long do_sys_ftruncate(unsigned int fd, loff_t length, int small); int chmod_common(const struct path *path, umode_t mode); @@ -193,3 +195,11 @@ int sb_init_dio_done_wq(struct super_block *sb); */ int do_statx(int dfd, const char __user *filename, unsigned flags, unsigned int mask, struct statx __user *buffer); + +/* + * fs/splice.c: + */ +long splice_file_to_pipe(struct file *in, + struct pipe_inode_info *opipe, + loff_t *offset, + size_t len, unsigned int flags); diff --git a/fs/io-wq.c b/fs/io-wq.c index a564f36e260c..c36bbcd823ce 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -64,9 +64,7 @@ struct io_worker { #endif const struct cred *cur_creds; const struct cred *saved_creds; - struct files_struct *restore_files; struct nsproxy *restore_nsproxy; - struct fs_struct *restore_fs; }; #if BITS_PER_LONG == 64 @@ -156,19 +154,19 @@ static bool __io_worker_unuse(struct io_wqe *wqe, struct io_worker *worker) worker->cur_creds = worker->saved_creds = NULL; } - if (current->files != worker->restore_files) { + if (current->files) { __acquire(&wqe->lock); raw_spin_unlock_irq(&wqe->lock); dropped_lock = true; task_lock(current); - current->files = worker->restore_files; + current->files = NULL; current->nsproxy = worker->restore_nsproxy; task_unlock(current); } - if (current->fs != worker->restore_fs) - current->fs = worker->restore_fs; + if (current->fs) + current->fs = NULL; /* * If we have an active mm, we need to drop the wq lock before unusing @@ -329,11 +327,11 @@ static void io_worker_start(struct io_wqe *wqe, struct io_worker *worker) allow_kernel_signal(SIGINT); current->flags |= PF_IO_WORKER; + current->fs = NULL; + current->files = NULL; worker->flags |= (IO_WORKER_F_UP | IO_WORKER_F_RUNNING); - worker->restore_files = current->files; worker->restore_nsproxy = current->nsproxy; - worker->restore_fs = current->fs; io_wqe_inc_running(wqe, worker); } @@ -555,23 +553,21 @@ get_next: /* handle a whole dependent link */ do { - struct io_wq_work *old_work, *next_hashed, *linked; + struct io_wq_work *next_hashed, *linked; unsigned int hash = io_get_work_hash(work); next_hashed = wq_next_work(work); io_impersonate_work(worker, work); + wq->do_work(work); + io_assign_current_work(worker, NULL); - old_work = work; - linked = wq->do_work(work); - + linked = wq->free_work(work); work = next_hashed; if (!work && linked && !io_wq_is_hashed(linked)) { work = linked; linked = NULL; } io_assign_current_work(worker, work); - wq->free_work(old_work); - if (linked) io_wqe_enqueue(wqe, linked); @@ -850,11 +846,9 @@ static void io_run_cancel(struct io_wq_work *work, struct io_wqe *wqe) struct io_wq *wq = wqe->wq; do { - struct io_wq_work *old_work = work; - work->flags |= IO_WQ_WORK_CANCEL; - work = wq->do_work(work); - wq->free_work(old_work); + wq->do_work(work); + work = wq->free_work(work); } while (work); } @@ -944,7 +938,6 @@ static bool io_wq_worker_cancel(struct io_worker *worker, void *data) */ spin_lock_irqsave(&worker->lock, flags); if (worker->cur_work && - !(worker->cur_work->flags & IO_WQ_WORK_NO_CANCEL) && match->fn(worker->cur_work, match->data)) { send_sig(SIGINT, worker->task, 1); match->nr_running++; diff --git a/fs/io-wq.h b/fs/io-wq.h index b158f8addcf3..096f1021018e 100644 --- a/fs/io-wq.h +++ b/fs/io-wq.h @@ -9,7 +9,6 @@ enum { IO_WQ_WORK_CANCEL = 1, IO_WQ_WORK_HASHED = 2, IO_WQ_WORK_UNBOUND = 4, - IO_WQ_WORK_NO_CANCEL = 8, IO_WQ_WORK_CONCURRENT = 16, IO_WQ_WORK_FILES = 32, @@ -28,15 +27,6 @@ enum io_wq_cancel { IO_WQ_CANCEL_NOTFOUND, /* work not found */ }; -struct io_wq_work_node { - struct io_wq_work_node *next; -}; - -struct io_wq_work_list { - struct io_wq_work_node *first; - struct io_wq_work_node *last; -}; - static inline void wq_list_add_after(struct io_wq_work_node *node, struct io_wq_work_node *pos, struct io_wq_work_list *list) @@ -107,8 +97,8 @@ static inline struct io_wq_work *wq_next_work(struct io_wq_work *work) return container_of(work->list.next, struct io_wq_work, list); } -typedef void (free_work_fn)(struct io_wq_work *); -typedef struct io_wq_work *(io_wq_work_fn)(struct io_wq_work *); +typedef struct io_wq_work *(free_work_fn)(struct io_wq_work *); +typedef void (io_wq_work_fn)(struct io_wq_work *); struct io_wq_data { struct user_struct *user; diff --git a/fs/io_uring.c b/fs/io_uring.c index ca46f314640b..14ce789927e4 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -187,6 +187,11 @@ struct io_rings { struct io_uring_cqe cqes[] ____cacheline_aligned_in_smp; }; +enum io_uring_cmd_flags { + IO_URING_F_NONBLOCK = 1, + IO_URING_F_COMPLETE_DEFER = 2, +}; + struct io_mapped_ubuf { u64 ubuf; size_t len; @@ -195,28 +200,38 @@ struct io_mapped_ubuf { unsigned long acct_pages; }; -struct fixed_file_table { +struct io_ring_ctx; + +struct io_rsrc_put { + struct list_head list; + union { + void *rsrc; + struct file *file; + }; +}; + +struct fixed_rsrc_table { struct file **files; }; -struct fixed_file_ref_node { +struct fixed_rsrc_ref_node { struct percpu_ref refs; struct list_head node; - struct list_head file_list; - struct fixed_file_data *file_data; + struct list_head rsrc_list; + struct fixed_rsrc_data *rsrc_data; + void (*rsrc_put)(struct io_ring_ctx *ctx, + struct io_rsrc_put *prsrc); struct llist_node llist; bool done; }; -struct fixed_file_data { - struct fixed_file_table *table; +struct fixed_rsrc_data { + struct fixed_rsrc_table *table; struct io_ring_ctx *ctx; - struct fixed_file_ref_node *node; + struct fixed_rsrc_ref_node *node; struct percpu_ref refs; struct completion done; - struct list_head ref_list; - spinlock_t lock; }; struct io_buffer { @@ -249,6 +264,46 @@ struct io_sq_data { unsigned sq_thread_idle; }; +#define IO_IOPOLL_BATCH 8 +#define IO_COMPL_BATCH 32 +#define IO_REQ_CACHE_SIZE 32 +#define IO_REQ_ALLOC_BATCH 8 + +struct io_comp_state { + struct io_kiocb *reqs[IO_COMPL_BATCH]; + unsigned int nr; + unsigned int locked_free_nr; + /* inline/task_work completion list, under ->uring_lock */ + struct list_head free_list; + /* IRQ completion list, under ->completion_lock */ + struct list_head locked_free_list; +}; + +struct io_submit_state { + struct blk_plug plug; + + /* + * io_kiocb alloc cache + */ + void *reqs[IO_REQ_CACHE_SIZE]; + unsigned int free_reqs; + + bool plug_started; + + /* + * Batch completion logic + */ + struct io_comp_state comp; + + /* + * File reference cache + */ + struct file *file; + unsigned int fd; + unsigned int file_refs; + unsigned int ios_left; +}; + struct io_ring_ctx { struct { struct percpu_ref refs; @@ -262,6 +317,7 @@ struct io_ring_ctx { unsigned int drain_next: 1; unsigned int eventfd_async: 1; unsigned int restricted: 1; + unsigned int sqo_dead: 1; /* * Ring buffer of indices into array of io_uring_sqe, which is @@ -290,6 +346,13 @@ struct io_ring_ctx { struct io_uring_sqe *sq_sqes; } ____cacheline_aligned_in_smp; + struct { + struct mutex uring_lock; + wait_queue_head_t wait; + } ____cacheline_aligned_in_smp; + + struct io_submit_state submit_state; + struct io_rings *rings; /* IO offload */ @@ -318,7 +381,7 @@ struct io_ring_ctx { * readers must ensure that ->refs is alive as long as the file* is * used. Only updated through io_uring_register(2). */ - struct fixed_file_data *file_data; + struct fixed_rsrc_data *file_data; unsigned nr_user_files; /* if used, fixed mapped user buffers */ @@ -337,9 +400,6 @@ struct io_ring_ctx { struct completion ref_comp; struct completion sq_thread_comp; - /* if all else fails... */ - struct io_kiocb *fallback_req; - #if defined(CONFIG_UNIX) struct socket *ring_sock; #endif @@ -353,6 +413,7 @@ struct io_ring_ctx { unsigned cq_entries; unsigned cq_mask; atomic_t cq_timeouts; + unsigned cq_last_tm_flush; unsigned long cq_check_overflow; struct wait_queue_head cq_wait; struct fasync_struct *cq_fasync; @@ -360,11 +421,6 @@ struct io_ring_ctx { } ____cacheline_aligned_in_smp; struct { - struct mutex uring_lock; - wait_queue_head_t wait; - } ____cacheline_aligned_in_smp; - - struct { spinlock_t completion_lock; /* @@ -382,11 +438,15 @@ struct io_ring_ctx { struct list_head inflight_list; } ____cacheline_aligned_in_smp; - struct delayed_work file_put_work; - struct llist_head file_put_llist; + struct delayed_work rsrc_put_work; + struct llist_head rsrc_put_llist; + struct list_head rsrc_ref_list; + spinlock_t rsrc_ref_lock; - struct work_struct exit_work; struct io_restriction restrictions; + + /* Keep this last, we don't need it for the fast path */ + struct work_struct exit_work; }; /* @@ -409,7 +469,6 @@ struct io_poll_remove { struct io_close { struct file *file; - struct file *put_file; int fd; }; @@ -487,13 +546,12 @@ struct io_sr_msg { struct io_open { struct file *file; int dfd; - bool ignore_nonblock; struct filename *filename; struct open_how how; unsigned long nofile; }; -struct io_files_update { +struct io_rsrc_update { struct file *file; u64 arg; u32 nr_args; @@ -582,7 +640,8 @@ struct io_async_connect { struct io_async_msghdr { struct iovec fast_iov[UIO_FASTIOV]; - struct iovec *iov; + /* points to an allocated iov, if NULL we use fast_iov instead */ + struct iovec *free_iov; struct sockaddr __user *uaddr; struct msghdr msg; struct sockaddr_storage addr; @@ -616,6 +675,7 @@ enum { REQ_F_NO_FILE_TABLE_BIT, REQ_F_WORK_INITIALIZED_BIT, REQ_F_LTIMEOUT_ACTIVE_BIT, + REQ_F_COMPLETE_INLINE_BIT, /* not a real bit, just to check we're not overflowing the space */ __REQ_F_LAST_BIT, @@ -659,6 +719,8 @@ enum { REQ_F_WORK_INITIALIZED = BIT(REQ_F_WORK_INITIALIZED_BIT), /* linked timeout is active, i.e. prepared by link's head */ REQ_F_LTIMEOUT_ACTIVE = BIT(REQ_F_LTIMEOUT_ACTIVE_BIT), + /* completion is deferred through io_comp_state */ + REQ_F_COMPLETE_INLINE = BIT(REQ_F_COMPLETE_INLINE_BIT), }; struct async_poll { @@ -666,6 +728,11 @@ struct async_poll { struct io_poll_iocb *double_poll; }; +struct io_task_work { + struct io_wq_work_node node; + task_work_func_t func; +}; + /* * NOTE! Each of the iocb union members has the file pointer * as the first entry in their struct definition. So you can @@ -687,7 +754,7 @@ struct io_kiocb { struct io_sr_msg sr_msg; struct io_open open; struct io_close close; - struct io_files_update files_update; + struct io_rsrc_update rsrc_update; struct io_fadvise fadvise; struct io_madvise madvise; struct io_epoll epoll; @@ -717,14 +784,17 @@ struct io_kiocb { u64 user_data; struct io_kiocb *link; - struct percpu_ref *fixed_file_refs; + struct percpu_ref *fixed_rsrc_refs; /* * 1. used with ctx->iopoll_list with reads/writes * 2. to track reqs with ->files (see io_op_def::file_table) */ struct list_head inflight_entry; - struct callback_head task_work; + union { + struct io_task_work io_task_work; + struct callback_head task_work; + }; /* for polled requests, i.e. IORING_OP_POLL_ADD and async armed poll */ struct hlist_node hash_node; struct async_poll *apoll; @@ -737,44 +807,9 @@ struct io_defer_entry { u32 seq; }; -#define IO_IOPOLL_BATCH 8 - -struct io_comp_state { - unsigned int nr; - struct list_head list; - struct io_ring_ctx *ctx; -}; - -struct io_submit_state { - struct blk_plug plug; - - /* - * io_kiocb alloc cache - */ - void *reqs[IO_IOPOLL_BATCH]; - unsigned int free_reqs; - - bool plug_started; - - /* - * Batch completion logic - */ - struct io_comp_state comp; - - /* - * File reference cache - */ - struct file *file; - unsigned int fd; - unsigned int file_refs; - unsigned int ios_left; -}; - struct io_op_def { /* needs req->file assigned */ unsigned needs_file : 1; - /* don't fail if file grab fails */ - unsigned needs_file_no_error : 1; /* hash wq insertion if file is a regular file */ unsigned hash_reg_file : 1; /* unbound wq insertion if file is a non-regular file */ @@ -855,7 +890,8 @@ static const struct io_op_def io_op_defs[] = { .pollout = 1, .needs_async_data = 1, .async_size = sizeof(struct io_async_msghdr), - .work_flags = IO_WQ_WORK_MM | IO_WQ_WORK_BLKCG, + .work_flags = IO_WQ_WORK_MM | IO_WQ_WORK_BLKCG | + IO_WQ_WORK_FS, }, [IORING_OP_RECVMSG] = { .needs_file = 1, @@ -864,7 +900,8 @@ static const struct io_op_def io_op_defs[] = { .buffer_select = 1, .needs_async_data = 1, .async_size = sizeof(struct io_async_msghdr), - .work_flags = IO_WQ_WORK_MM | IO_WQ_WORK_BLKCG, + .work_flags = IO_WQ_WORK_MM | IO_WQ_WORK_BLKCG | + IO_WQ_WORK_FS, }, [IORING_OP_TIMEOUT] = { .needs_async_data = 1, @@ -904,8 +941,6 @@ static const struct io_op_def io_op_defs[] = { IO_WQ_WORK_FS | IO_WQ_WORK_MM, }, [IORING_OP_CLOSE] = { - .needs_file = 1, - .needs_file_no_error = 1, .work_flags = IO_WQ_WORK_FILES | IO_WQ_WORK_BLKCG, }, [IORING_OP_FILES_UPDATE] = { @@ -987,39 +1022,43 @@ static const struct io_op_def io_op_defs[] = { }, }; -enum io_mem_account { - ACCT_LOCKED, - ACCT_PINNED, -}; - -static void destroy_fixed_file_ref_node(struct fixed_file_ref_node *ref_node); -static struct fixed_file_ref_node *alloc_fixed_file_ref_node( +static void io_uring_try_cancel_requests(struct io_ring_ctx *ctx, + struct task_struct *task, + struct files_struct *files); +static void destroy_fixed_rsrc_ref_node(struct fixed_rsrc_ref_node *ref_node); +static struct fixed_rsrc_ref_node *alloc_fixed_rsrc_ref_node( struct io_ring_ctx *ctx); +static void init_fixed_file_ref_node(struct io_ring_ctx *ctx, + struct fixed_rsrc_ref_node *ref_node); -static void __io_complete_rw(struct io_kiocb *req, long res, long res2, - struct io_comp_state *cs); +static bool io_rw_reissue(struct io_kiocb *req); static void io_cqring_fill_event(struct io_kiocb *req, long res); static void io_put_req(struct io_kiocb *req); static void io_put_req_deferred(struct io_kiocb *req, int nr); static void io_double_put_req(struct io_kiocb *req); +static void io_dismantle_req(struct io_kiocb *req); +static void io_put_task(struct task_struct *task, int nr); +static void io_queue_next(struct io_kiocb *req); static struct io_kiocb *io_prep_linked_timeout(struct io_kiocb *req); static void __io_queue_linked_timeout(struct io_kiocb *req); static void io_queue_linked_timeout(struct io_kiocb *req); static int __io_sqe_files_update(struct io_ring_ctx *ctx, - struct io_uring_files_update *ip, + struct io_uring_rsrc_update *ip, unsigned nr_args); static void __io_clean_op(struct io_kiocb *req); static struct file *io_file_get(struct io_submit_state *state, struct io_kiocb *req, int fd, bool fixed); -static void __io_queue_sqe(struct io_kiocb *req, struct io_comp_state *cs); -static void io_file_put_work(struct work_struct *work); +static void __io_queue_sqe(struct io_kiocb *req); +static void io_rsrc_put_work(struct work_struct *work); -static ssize_t io_import_iovec(int rw, struct io_kiocb *req, - struct iovec **iovec, struct iov_iter *iter, - bool needs_lock); +static int io_import_iovec(int rw, struct io_kiocb *req, struct iovec **iovec, + struct iov_iter *iter, bool needs_lock); static int io_setup_async_rw(struct io_kiocb *req, const struct iovec *iovec, const struct iovec *fast_iov, struct iov_iter *iter, bool force); +static void io_req_task_queue(struct io_kiocb *req); +static void io_submit_flush_completions(struct io_comp_state *cs, + struct io_ring_ctx *ctx); static struct kmem_cache *req_cachep; @@ -1043,8 +1082,7 @@ EXPORT_SYMBOL(io_uring_get_socket); static inline void io_clean_op(struct io_kiocb *req) { - if (req->flags & (REQ_F_NEED_CLEANUP | REQ_F_BUFFER_SELECTED | - REQ_F_INFLIGHT)) + if (req->flags & (REQ_F_NEED_CLEANUP | REQ_F_BUFFER_SELECTED)) __io_clean_op(req); } @@ -1052,9 +1090,9 @@ static inline void io_set_resource_node(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; - if (!req->fixed_file_refs) { - req->fixed_file_refs = &ctx->file_data->node->refs; - percpu_ref_get(req->fixed_file_refs); + if (!req->fixed_rsrc_refs) { + req->fixed_rsrc_refs = &ctx->file_data->node->refs; + percpu_ref_get(req->fixed_rsrc_refs); } } @@ -1064,14 +1102,21 @@ static bool io_match_task(struct io_kiocb *head, { struct io_kiocb *req; - if (task && head->task != task) + if (task && head->task != task) { + /* in terms of cancelation, always match if req task is dead */ + if (head->task->flags & PF_EXITING) + return true; return false; + } if (!files) return true; io_for_each_link(req, head) { - if ((req->flags & REQ_F_WORK_INITIALIZED) && - (req->work.flags & IO_WQ_WORK_FILES) && + if (!(req->flags & REQ_F_WORK_INITIALIZED)) + continue; + if (req->file && req->file->f_op == &io_uring_fops) + return true; + if ((req->work.flags & IO_WQ_WORK_FILES) && req->work.identity->files == files) return true; } @@ -1132,10 +1177,6 @@ static int __io_sq_thread_acquire_mm(struct io_ring_ctx *ctx) if (current->mm) return 0; - /* Should never happen */ - if (unlikely(!(ctx->flags & IORING_SETUP_SQPOLL))) - return -EFAULT; - task_lock(ctx->sqo_task); mm = ctx->sqo_task->mm; if (unlikely(!mm || !mmget_not_zero(mm))) @@ -1150,8 +1191,8 @@ static int __io_sq_thread_acquire_mm(struct io_ring_ctx *ctx) return -EFAULT; } -static int io_sq_thread_acquire_mm_files(struct io_ring_ctx *ctx, - struct io_kiocb *req) +static int __io_sq_thread_acquire_mm_files(struct io_ring_ctx *ctx, + struct io_kiocb *req) { const struct io_op_def *def = &io_op_defs[req->opcode]; int ret; @@ -1171,6 +1212,14 @@ static int io_sq_thread_acquire_mm_files(struct io_ring_ctx *ctx, return 0; } +static inline int io_sq_thread_acquire_mm_files(struct io_ring_ctx *ctx, + struct io_kiocb *req) +{ + if (!(ctx->flags & IORING_SETUP_SQPOLL)) + return 0; + return __io_sq_thread_acquire_mm_files(ctx, req); +} + static void io_sq_thread_associate_blkcg(struct io_ring_ctx *ctx, struct cgroup_subsys_state **cur_css) @@ -1247,11 +1296,6 @@ static inline void io_req_init_async(struct io_kiocb *req) refcount_inc(&req->work.identity->count); } -static inline bool io_async_submit(struct io_ring_ctx *ctx) -{ - return ctx->flags & IORING_SETUP_SQPOLL; -} - static void io_ring_ctx_ref_free(struct percpu_ref *ref) { struct io_ring_ctx *ctx = container_of(ref, struct io_ring_ctx, refs); @@ -1273,10 +1317,6 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) if (!ctx) return NULL; - ctx->fallback_req = kmem_cache_alloc(req_cachep, GFP_KERNEL); - if (!ctx->fallback_req) - goto err; - /* * Use 5 bits less than the max cq entries, that should give us around * 32 entries per hash list if totally full and uniformly spread. @@ -1313,12 +1353,14 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) INIT_LIST_HEAD(&ctx->timeout_list); spin_lock_init(&ctx->inflight_lock); INIT_LIST_HEAD(&ctx->inflight_list); - INIT_DELAYED_WORK(&ctx->file_put_work, io_file_put_work); - init_llist_head(&ctx->file_put_llist); + spin_lock_init(&ctx->rsrc_ref_lock); + INIT_LIST_HEAD(&ctx->rsrc_ref_list); + INIT_DELAYED_WORK(&ctx->rsrc_put_work, io_rsrc_put_work); + init_llist_head(&ctx->rsrc_put_llist); + INIT_LIST_HEAD(&ctx->submit_state.comp.free_list); + INIT_LIST_HEAD(&ctx->submit_state.comp.locked_free_list); return ctx; err: - if (ctx->fallback_req) - kmem_cache_free(req_cachep, ctx->fallback_req); kfree(ctx->cancel_hash); kfree(ctx); return NULL; @@ -1336,19 +1378,6 @@ static bool req_need_defer(struct io_kiocb *req, u32 seq) return false; } -static void __io_commit_cqring(struct io_ring_ctx *ctx) -{ - struct io_rings *rings = ctx->rings; - - /* order cqe stores with ring update */ - smp_store_release(&rings->cq.tail, ctx->cached_cq_tail); - - if (wq_has_sleeper(&ctx->cq_wait)) { - wake_up_interruptible(&ctx->cq_wait); - kill_fasync(&ctx->cq_fasync, SIGIO, POLL_IN); - } -} - static void io_put_identity(struct io_uring_task *tctx, struct io_kiocb *req) { if (req->work.identity == &tctx->__identity) @@ -1362,22 +1391,14 @@ static void io_req_clean_work(struct io_kiocb *req) if (!(req->flags & REQ_F_WORK_INITIALIZED)) return; - req->flags &= ~REQ_F_WORK_INITIALIZED; - - if (req->work.flags & IO_WQ_WORK_MM) { + if (req->work.flags & IO_WQ_WORK_MM) mmdrop(req->work.identity->mm); - req->work.flags &= ~IO_WQ_WORK_MM; - } #ifdef CONFIG_BLK_CGROUP - if (req->work.flags & IO_WQ_WORK_BLKCG) { + if (req->work.flags & IO_WQ_WORK_BLKCG) css_put(req->work.identity->blkcg_css); - req->work.flags &= ~IO_WQ_WORK_BLKCG; - } #endif - if (req->work.flags & IO_WQ_WORK_CREDS) { + if (req->work.flags & IO_WQ_WORK_CREDS) put_cred(req->work.identity->creds); - req->work.flags &= ~IO_WQ_WORK_CREDS; - } if (req->work.flags & IO_WQ_WORK_FS) { struct fs_struct *fs = req->work.identity->fs; @@ -1387,9 +1408,27 @@ static void io_req_clean_work(struct io_kiocb *req) spin_unlock(&req->work.identity->fs->lock); if (fs) free_fs_struct(fs); - req->work.flags &= ~IO_WQ_WORK_FS; } + if (req->work.flags & IO_WQ_WORK_FILES) { + put_files_struct(req->work.identity->files); + put_nsproxy(req->work.identity->nsproxy); + } + if (req->flags & REQ_F_INFLIGHT) { + struct io_ring_ctx *ctx = req->ctx; + struct io_uring_task *tctx = req->task->io_uring; + unsigned long flags; + spin_lock_irqsave(&ctx->inflight_lock, flags); + list_del(&req->inflight_entry); + spin_unlock_irqrestore(&ctx->inflight_lock, flags); + req->flags &= ~REQ_F_INFLIGHT; + if (atomic_read(&tctx->in_idle)) + wake_up(&tctx->wait); + } + + req->flags &= ~REQ_F_WORK_INITIALIZED; + req->work.flags &= ~(IO_WQ_WORK_MM | IO_WQ_WORK_BLKCG | IO_WQ_WORK_FS | + IO_WQ_WORK_CREDS | IO_WQ_WORK_FILES); io_put_identity(req->task->io_uring, req); } @@ -1438,11 +1477,24 @@ static bool io_identity_cow(struct io_kiocb *req) return true; } +static void io_req_track_inflight(struct io_kiocb *req) +{ + struct io_ring_ctx *ctx = req->ctx; + + if (!(req->flags & REQ_F_INFLIGHT)) { + io_req_init_async(req); + req->flags |= REQ_F_INFLIGHT; + + spin_lock_irq(&ctx->inflight_lock); + list_add(&req->inflight_entry, &ctx->inflight_list); + spin_unlock_irq(&ctx->inflight_lock); + } +} + static bool io_grab_identity(struct io_kiocb *req) { const struct io_op_def *def = &io_op_defs[req->opcode]; struct io_identity *id = req->work.identity; - struct io_ring_ctx *ctx = req->ctx; if (def->work_flags & IO_WQ_WORK_FSIZE) { if (id->fsize != rlimit(RLIMIT_FSIZE)) @@ -1498,12 +1550,8 @@ static bool io_grab_identity(struct io_kiocb *req) return false; atomic_inc(&id->files->count); get_nsproxy(id->nsproxy); - req->flags |= REQ_F_INFLIGHT; - - spin_lock_irq(&ctx->inflight_lock); - list_add(&req->inflight_entry, &ctx->inflight_list); - spin_unlock_irq(&ctx->inflight_lock); req->work.flags |= IO_WQ_WORK_FILES; + io_req_track_inflight(req); } if (!(req->work.flags & IO_WQ_WORK_MM) && (def->work_flags & IO_WQ_WORK_MM)) { @@ -1520,10 +1568,8 @@ static void io_prep_async_work(struct io_kiocb *req) { const struct io_op_def *def = &io_op_defs[req->opcode]; struct io_ring_ctx *ctx = req->ctx; - struct io_identity *id; io_req_init_async(req); - id = req->work.identity; if (req->flags & REQ_F_FORCE_ASYNC) req->work.flags |= IO_WQ_WORK_CONCURRENT; @@ -1619,43 +1665,57 @@ static void __io_queue_deferred(struct io_ring_ctx *ctx) do { struct io_defer_entry *de = list_first_entry(&ctx->defer_list, struct io_defer_entry, list); - struct io_kiocb *link; if (req_need_defer(de->req, de->seq)) break; list_del_init(&de->list); - /* punt-init is done before queueing for defer */ - link = __io_queue_async_work(de->req); - if (link) { - __io_queue_linked_timeout(link); - /* drop submission reference */ - io_put_req_deferred(link, 1); - } + io_req_task_queue(de->req); kfree(de); } while (!list_empty(&ctx->defer_list)); } static void io_flush_timeouts(struct io_ring_ctx *ctx) { - while (!list_empty(&ctx->timeout_list)) { + u32 seq; + + if (list_empty(&ctx->timeout_list)) + return; + + seq = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts); + + do { + u32 events_needed, events_got; struct io_kiocb *req = list_first_entry(&ctx->timeout_list, struct io_kiocb, timeout.list); if (io_is_timeout_noseq(req)) break; - if (req->timeout.target_seq != ctx->cached_cq_tail - - atomic_read(&ctx->cq_timeouts)) + + /* + * Since seq can easily wrap around over time, subtract + * the last seq at which timeouts were flushed before comparing. + * Assuming not more than 2^31-1 events have happened since, + * these subtractions won't have wrapped, so we can check if + * target is in [last_seq, current_seq] by comparing the two. + */ + events_needed = req->timeout.target_seq - ctx->cq_last_tm_flush; + events_got = seq - ctx->cq_last_tm_flush; + if (events_got < events_needed) break; list_del_init(&req->timeout.list); io_kill_timeout(req); - } + } while (!list_empty(&ctx->timeout_list)); + + ctx->cq_last_tm_flush = seq; } static void io_commit_cqring(struct io_ring_ctx *ctx) { io_flush_timeouts(ctx); - __io_commit_cqring(ctx); + + /* order cqe stores with ring update */ + smp_store_release(&ctx->rings->cq.tail, ctx->cached_cq_tail); if (unlikely(!list_empty(&ctx->defer_list))) __io_queue_deferred(ctx); @@ -1668,21 +1728,25 @@ static inline bool io_sqring_full(struct io_ring_ctx *ctx) return READ_ONCE(r->sq.tail) - ctx->cached_sq_head == r->sq_ring_entries; } +static inline unsigned int __io_cqring_events(struct io_ring_ctx *ctx) +{ + return ctx->cached_cq_tail - READ_ONCE(ctx->rings->cq.head); +} + static struct io_uring_cqe *io_get_cqring(struct io_ring_ctx *ctx) { struct io_rings *rings = ctx->rings; unsigned tail; - tail = ctx->cached_cq_tail; /* * writes to the cq entry need to come after reading head; the * control dependency is enough as we're using WRITE_ONCE to * fill the cq entry */ - if (tail - READ_ONCE(rings->cq.head) == rings->cq_ring_entries) + if (__io_cqring_events(ctx) == rings->cq_ring_entries) return NULL; - ctx->cached_cq_tail++; + tail = ctx->cached_cq_tail++; return &rings->cqes[tail & ctx->cq_mask]; } @@ -1697,36 +1761,56 @@ static inline bool io_should_trigger_evfd(struct io_ring_ctx *ctx) return io_wq_current_is_worker(); } -static inline unsigned __io_cqring_events(struct io_ring_ctx *ctx) -{ - return ctx->cached_cq_tail - READ_ONCE(ctx->rings->cq.head); -} - static void io_cqring_ev_posted(struct io_ring_ctx *ctx) { + /* see waitqueue_active() comment */ + smp_mb(); + if (waitqueue_active(&ctx->wait)) wake_up(&ctx->wait); if (ctx->sq_data && waitqueue_active(&ctx->sq_data->wait)) wake_up(&ctx->sq_data->wait); if (io_should_trigger_evfd(ctx)) eventfd_signal(ctx->cq_ev_fd, 1); + if (waitqueue_active(&ctx->cq_wait)) { + wake_up_interruptible(&ctx->cq_wait); + kill_fasync(&ctx->cq_fasync, SIGIO, POLL_IN); + } +} + +static void io_cqring_ev_posted_iopoll(struct io_ring_ctx *ctx) +{ + /* see waitqueue_active() comment */ + smp_mb(); + + if (ctx->flags & IORING_SETUP_SQPOLL) { + if (waitqueue_active(&ctx->wait)) + wake_up(&ctx->wait); + } + if (io_should_trigger_evfd(ctx)) + eventfd_signal(ctx->cq_ev_fd, 1); + if (waitqueue_active(&ctx->cq_wait)) { + wake_up_interruptible(&ctx->cq_wait); + kill_fasync(&ctx->cq_fasync, SIGIO, POLL_IN); + } } /* Returns true if there are no backlogged entries after the flush */ -static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force, - struct task_struct *tsk, - struct files_struct *files) +static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force, + struct task_struct *tsk, + struct files_struct *files) { struct io_rings *rings = ctx->rings; struct io_kiocb *req, *tmp; struct io_uring_cqe *cqe; unsigned long flags; - bool all_flushed; + bool all_flushed, posted; LIST_HEAD(list); if (!force && __io_cqring_events(ctx) == rings->cq_ring_entries) return false; + posted = false; spin_lock_irqsave(&ctx->completion_lock, flags); list_for_each_entry_safe(req, tmp, &ctx->cq_overflow_list, compl.list) { if (!io_match_task(req, tsk, files)) @@ -1746,6 +1830,7 @@ static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force, WRITE_ONCE(ctx->rings->cq_overflow, ctx->cached_cq_overflow); } + posted = true; } all_flushed = list_empty(&ctx->cq_overflow_list); @@ -1755,9 +1840,11 @@ static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force, ctx->rings->sq_flags &= ~IORING_SQ_CQ_OVERFLOW; } - io_commit_cqring(ctx); + if (posted) + io_commit_cqring(ctx); spin_unlock_irqrestore(&ctx->completion_lock, flags); - io_cqring_ev_posted(ctx); + if (posted) + io_cqring_ev_posted(ctx); while (!list_empty(&list)) { req = list_first_entry(&list, struct io_kiocb, compl.list); @@ -1768,6 +1855,20 @@ static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force, return all_flushed; } +static void io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force, + struct task_struct *tsk, + struct files_struct *files) +{ + if (test_bit(0, &ctx->cq_check_overflow)) { + /* iopoll syncs against uring_lock, not completion_lock */ + if (ctx->flags & IORING_SETUP_IOPOLL) + mutex_lock(&ctx->uring_lock); + __io_cqring_overflow_flush(ctx, force, tsk, files); + if (ctx->flags & IORING_SETUP_IOPOLL) + mutex_unlock(&ctx->uring_lock); + } +} + static void __io_cqring_fill_event(struct io_kiocb *req, long res, long cflags) { struct io_ring_ctx *ctx = req->ctx; @@ -1813,7 +1914,8 @@ static void io_cqring_fill_event(struct io_kiocb *req, long res) __io_cqring_fill_event(req, res, 0); } -static void io_cqring_add_event(struct io_kiocb *req, long res, long cflags) +static inline void io_req_complete_post(struct io_kiocb *req, long res, + unsigned int cflags) { struct io_ring_ctx *ctx = req->ctx; unsigned long flags; @@ -1821,92 +1923,96 @@ static void io_cqring_add_event(struct io_kiocb *req, long res, long cflags) spin_lock_irqsave(&ctx->completion_lock, flags); __io_cqring_fill_event(req, res, cflags); io_commit_cqring(ctx); + /* + * If we're the last reference to this request, add to our locked + * free_list cache. + */ + if (refcount_dec_and_test(&req->refs)) { + struct io_comp_state *cs = &ctx->submit_state.comp; + + io_dismantle_req(req); + io_put_task(req->task, 1); + list_add(&req->compl.list, &cs->locked_free_list); + cs->locked_free_nr++; + } else + req = NULL; spin_unlock_irqrestore(&ctx->completion_lock, flags); io_cqring_ev_posted(ctx); -} - -static void io_submit_flush_completions(struct io_comp_state *cs) -{ - struct io_ring_ctx *ctx = cs->ctx; - - spin_lock_irq(&ctx->completion_lock); - while (!list_empty(&cs->list)) { - struct io_kiocb *req; - - req = list_first_entry(&cs->list, struct io_kiocb, compl.list); - list_del(&req->compl.list); - __io_cqring_fill_event(req, req->result, req->compl.cflags); - - /* - * io_free_req() doesn't care about completion_lock unless one - * of these flags is set. REQ_F_WORK_INITIALIZED is in the list - * because of a potential deadlock with req->work.fs->lock - */ - if (req->flags & (REQ_F_FAIL_LINK|REQ_F_LINK_TIMEOUT - |REQ_F_WORK_INITIALIZED)) { - spin_unlock_irq(&ctx->completion_lock); - io_put_req(req); - spin_lock_irq(&ctx->completion_lock); - } else { - io_put_req(req); - } + if (req) { + io_queue_next(req); + percpu_ref_put(&ctx->refs); } - io_commit_cqring(ctx); - spin_unlock_irq(&ctx->completion_lock); - - io_cqring_ev_posted(ctx); - cs->nr = 0; } -static void __io_req_complete(struct io_kiocb *req, long res, unsigned cflags, - struct io_comp_state *cs) +static void io_req_complete_state(struct io_kiocb *req, long res, + unsigned int cflags) { - if (!cs) { - io_cqring_add_event(req, res, cflags); - io_put_req(req); - } else { - io_clean_op(req); - req->result = res; - req->compl.cflags = cflags; - list_add_tail(&req->compl.list, &cs->list); - if (++cs->nr >= 32) - io_submit_flush_completions(cs); - } + io_clean_op(req); + req->result = res; + req->compl.cflags = cflags; + req->flags |= REQ_F_COMPLETE_INLINE; } -static void io_req_complete(struct io_kiocb *req, long res) +static inline void __io_req_complete(struct io_kiocb *req, unsigned issue_flags, + long res, unsigned cflags) { - __io_req_complete(req, res, 0, NULL); + if (issue_flags & IO_URING_F_COMPLETE_DEFER) + io_req_complete_state(req, res, cflags); + else + io_req_complete_post(req, res, cflags); } -static inline bool io_is_fallback_req(struct io_kiocb *req) +static inline void io_req_complete(struct io_kiocb *req, long res) { - return req == (struct io_kiocb *) - ((unsigned long) req->ctx->fallback_req & ~1UL); + __io_req_complete(req, 0, res, 0); } -static struct io_kiocb *io_get_fallback_req(struct io_ring_ctx *ctx) +static bool io_flush_cached_reqs(struct io_ring_ctx *ctx) { - struct io_kiocb *req; + struct io_submit_state *state = &ctx->submit_state; + struct io_comp_state *cs = &state->comp; + struct io_kiocb *req = NULL; - req = ctx->fallback_req; - if (!test_and_set_bit_lock(0, (unsigned long *) &ctx->fallback_req)) - return req; + /* + * If we have more than a batch's worth of requests in our IRQ side + * locked cache, grab the lock and move them over to our submission + * side cache. + */ + if (READ_ONCE(cs->locked_free_nr) > IO_COMPL_BATCH) { + spin_lock_irq(&ctx->completion_lock); + list_splice_init(&cs->locked_free_list, &cs->free_list); + cs->locked_free_nr = 0; + spin_unlock_irq(&ctx->completion_lock); + } - return NULL; + while (!list_empty(&cs->free_list)) { + req = list_first_entry(&cs->free_list, struct io_kiocb, + compl.list); + list_del(&req->compl.list); + state->reqs[state->free_reqs++] = req; + if (state->free_reqs == ARRAY_SIZE(state->reqs)) + break; + } + + return req != NULL; } -static struct io_kiocb *io_alloc_req(struct io_ring_ctx *ctx, - struct io_submit_state *state) +static struct io_kiocb *io_alloc_req(struct io_ring_ctx *ctx) { + struct io_submit_state *state = &ctx->submit_state; + + BUILD_BUG_ON(IO_REQ_ALLOC_BATCH > ARRAY_SIZE(state->reqs)); + if (!state->free_reqs) { gfp_t gfp = GFP_KERNEL | __GFP_NOWARN; - size_t sz; int ret; - sz = min_t(size_t, state->ios_left, ARRAY_SIZE(state->reqs)); - ret = kmem_cache_alloc_bulk(req_cachep, gfp, sz, state->reqs); + if (io_flush_cached_reqs(ctx)) + goto got_req; + + ret = kmem_cache_alloc_bulk(req_cachep, gfp, IO_REQ_ALLOC_BATCH, + state->reqs); /* * Bulk alloc is all-or-nothing. If we fail to get a batch, @@ -1915,16 +2021,14 @@ static struct io_kiocb *io_alloc_req(struct io_ring_ctx *ctx, if (unlikely(ret <= 0)) { state->reqs[0] = kmem_cache_alloc(req_cachep, gfp); if (!state->reqs[0]) - goto fallback; + return NULL; ret = 1; } state->free_reqs = ret; } - +got_req: state->free_reqs--; return state->reqs[state->free_reqs]; -fallback: - return io_get_fallback_req(ctx); } static inline void io_put_file(struct io_kiocb *req, struct file *file, @@ -1942,27 +2046,29 @@ static void io_dismantle_req(struct io_kiocb *req) kfree(req->async_data); if (req->file) io_put_file(req, req->file, (req->flags & REQ_F_FIXED_FILE)); - if (req->fixed_file_refs) - percpu_ref_put(req->fixed_file_refs); + if (req->fixed_rsrc_refs) + percpu_ref_put(req->fixed_rsrc_refs); io_req_clean_work(req); } +static inline void io_put_task(struct task_struct *task, int nr) +{ + struct io_uring_task *tctx = task->io_uring; + + percpu_counter_sub(&tctx->inflight, nr); + if (unlikely(atomic_read(&tctx->in_idle))) + wake_up(&tctx->wait); + put_task_struct_many(task, nr); +} + static void __io_free_req(struct io_kiocb *req) { - struct io_uring_task *tctx = req->task->io_uring; struct io_ring_ctx *ctx = req->ctx; io_dismantle_req(req); + io_put_task(req->task, 1); - percpu_counter_dec(&tctx->inflight); - if (atomic_read(&tctx->in_idle)) - wake_up(&tctx->wait); - put_task_struct(req->task); - - if (likely(!io_is_fallback_req(req))) - kmem_cache_free(req_cachep, req); - else - clear_bit_unlock(0, (unsigned long *) &ctx->fallback_req); + kmem_cache_free(req_cachep, req); percpu_ref_put(&ctx->refs); } @@ -2068,11 +2174,105 @@ static struct io_kiocb *__io_req_find_next(struct io_kiocb *req) static inline struct io_kiocb *io_req_find_next(struct io_kiocb *req) { - if (likely(!(req->link) && !(req->flags & REQ_F_LINK_TIMEOUT))) + if (likely(!(req->flags & (REQ_F_LINK|REQ_F_HARDLINK)))) return NULL; return __io_req_find_next(req); } +static bool __tctx_task_work(struct io_uring_task *tctx) +{ + struct io_ring_ctx *ctx = NULL; + struct io_wq_work_list list; + struct io_wq_work_node *node; + + if (wq_list_empty(&tctx->task_list)) + return false; + + spin_lock_irq(&tctx->task_lock); + list = tctx->task_list; + INIT_WQ_LIST(&tctx->task_list); + spin_unlock_irq(&tctx->task_lock); + + node = list.first; + while (node) { + struct io_wq_work_node *next = node->next; + struct io_ring_ctx *this_ctx; + struct io_kiocb *req; + + req = container_of(node, struct io_kiocb, io_task_work.node); + this_ctx = req->ctx; + req->task_work.func(&req->task_work); + node = next; + + if (!ctx) { + ctx = this_ctx; + } else if (ctx != this_ctx) { + mutex_lock(&ctx->uring_lock); + io_submit_flush_completions(&ctx->submit_state.comp, ctx); + mutex_unlock(&ctx->uring_lock); + ctx = this_ctx; + } + } + + if (ctx && ctx->submit_state.comp.nr) { + mutex_lock(&ctx->uring_lock); + io_submit_flush_completions(&ctx->submit_state.comp, ctx); + mutex_unlock(&ctx->uring_lock); + } + + return list.first != NULL; +} + +static void tctx_task_work(struct callback_head *cb) +{ + struct io_uring_task *tctx = container_of(cb, struct io_uring_task, task_work); + + while (__tctx_task_work(tctx)) + cond_resched(); + + clear_bit(0, &tctx->task_state); +} + +static int io_task_work_add(struct task_struct *tsk, struct io_kiocb *req, + enum task_work_notify_mode notify) +{ + struct io_uring_task *tctx = tsk->io_uring; + struct io_wq_work_node *node, *prev; + unsigned long flags; + int ret; + + WARN_ON_ONCE(!tctx); + + spin_lock_irqsave(&tctx->task_lock, flags); + wq_list_add_tail(&req->io_task_work.node, &tctx->task_list); + spin_unlock_irqrestore(&tctx->task_lock, flags); + + /* task_work already pending, we're done */ + if (test_bit(0, &tctx->task_state) || + test_and_set_bit(0, &tctx->task_state)) + return 0; + + if (!task_work_add(tsk, &tctx->task_work, notify)) + return 0; + + /* + * Slow path - we failed, find and delete work. if the work is not + * in the list, it got run and we're fine. + */ + ret = 0; + spin_lock_irqsave(&tctx->task_lock, flags); + wq_list_for_each(node, prev, &tctx->task_list) { + if (&req->io_task_work.node == node) { + wq_list_del(&tctx->task_list, node, prev); + ret = 1; + break; + } + } + spin_unlock_irqrestore(&tctx->task_lock, flags); + clear_bit(0, &tctx->task_state); + return ret; +} + static int io_req_task_work_add(struct io_kiocb *req) { struct task_struct *tsk = req->task; @@ -2093,13 +2293,23 @@ static int io_req_task_work_add(struct io_kiocb *req) if (!(ctx->flags & IORING_SETUP_SQPOLL)) notify = TWA_SIGNAL; - ret = task_work_add(tsk, &req->task_work, notify); + ret = io_task_work_add(tsk, req, notify); if (!ret) wake_up_process(tsk); return ret; } +static void io_req_task_work_add_fallback(struct io_kiocb *req, + task_work_func_t cb) +{ + struct task_struct *tsk = io_wq_get_task(req->ctx->io_wq); + + init_task_work(&req->task_work, cb); + task_work_add(tsk, &req->task_work, TWA_NONE); + wake_up_process(tsk); +} + static void __io_req_task_cancel(struct io_kiocb *req, int error) { struct io_ring_ctx *ctx = req->ctx; @@ -2127,40 +2337,35 @@ static void __io_req_task_submit(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; - if (!__io_sq_thread_acquire_mm(ctx) && - !__io_sq_thread_acquire_files(ctx)) { - mutex_lock(&ctx->uring_lock); - __io_queue_sqe(req, NULL); - mutex_unlock(&ctx->uring_lock); - } else { + /* ctx stays valid until unlock, even if we drop all ours ctx->refs */ + mutex_lock(&ctx->uring_lock); + if (!ctx->sqo_dead && !(current->flags & PF_EXITING) && + !io_sq_thread_acquire_mm_files(ctx, req)) + __io_queue_sqe(req); + else __io_req_task_cancel(req, -EFAULT); - } + mutex_unlock(&ctx->uring_lock); + + if (ctx->flags & IORING_SETUP_SQPOLL) + io_sq_thread_drop_mm_files(); } static void io_req_task_submit(struct callback_head *cb) { struct io_kiocb *req = container_of(cb, struct io_kiocb, task_work); - struct io_ring_ctx *ctx = req->ctx; __io_req_task_submit(req); - percpu_ref_put(&ctx->refs); } static void io_req_task_queue(struct io_kiocb *req) { int ret; - init_task_work(&req->task_work, io_req_task_submit); - percpu_ref_get(&req->ctx->refs); - + req->task_work.func = io_req_task_submit; ret = io_req_task_work_add(req); if (unlikely(ret)) { - struct task_struct *tsk; - - init_task_work(&req->task_work, io_req_task_cancel); - tsk = io_wq_get_task(req->ctx->io_wq); - task_work_add(tsk, &req->task_work, TWA_NONE); - wake_up_process(tsk); + percpu_ref_get(&req->ctx->refs); + io_req_task_work_add_fallback(req, io_req_task_cancel); } } @@ -2179,66 +2384,75 @@ static void io_free_req(struct io_kiocb *req) } struct req_batch { - void *reqs[IO_IOPOLL_BATCH]; - int to_free; - struct task_struct *task; int task_refs; + int ctx_refs; }; static inline void io_init_req_batch(struct req_batch *rb) { - rb->to_free = 0; rb->task_refs = 0; + rb->ctx_refs = 0; rb->task = NULL; } -static void __io_req_free_batch_flush(struct io_ring_ctx *ctx, - struct req_batch *rb) -{ - kmem_cache_free_bulk(req_cachep, rb->to_free, rb->reqs); - percpu_ref_put_many(&ctx->refs, rb->to_free); - rb->to_free = 0; -} - static void io_req_free_batch_finish(struct io_ring_ctx *ctx, struct req_batch *rb) { - if (rb->to_free) - __io_req_free_batch_flush(ctx, rb); - if (rb->task) { - struct io_uring_task *tctx = rb->task->io_uring; - - percpu_counter_sub(&tctx->inflight, rb->task_refs); - put_task_struct_many(rb->task, rb->task_refs); - rb->task = NULL; - } + if (rb->task) + io_put_task(rb->task, rb->task_refs); + if (rb->ctx_refs) + percpu_ref_put_many(&ctx->refs, rb->ctx_refs); } -static void io_req_free_batch(struct req_batch *rb, struct io_kiocb *req) +static void io_req_free_batch(struct req_batch *rb, struct io_kiocb *req, + struct io_submit_state *state) { - if (unlikely(io_is_fallback_req(req))) { - io_free_req(req); - return; - } io_queue_next(req); if (req->task != rb->task) { - if (rb->task) { - struct io_uring_task *tctx = rb->task->io_uring; - - percpu_counter_sub(&tctx->inflight, rb->task_refs); - put_task_struct_many(rb->task, rb->task_refs); - } + if (rb->task) + io_put_task(rb->task, rb->task_refs); rb->task = req->task; rb->task_refs = 0; } rb->task_refs++; + rb->ctx_refs++; io_dismantle_req(req); - rb->reqs[rb->to_free++] = req; - if (unlikely(rb->to_free == ARRAY_SIZE(rb->reqs))) - __io_req_free_batch_flush(req->ctx, rb); + if (state->free_reqs != ARRAY_SIZE(state->reqs)) + state->reqs[state->free_reqs++] = req; + else + list_add(&req->compl.list, &state->comp.free_list); +} + +static void io_submit_flush_completions(struct io_comp_state *cs, + struct io_ring_ctx *ctx) +{ + int i, nr = cs->nr; + struct io_kiocb *req; + struct req_batch rb; + + io_init_req_batch(&rb); + spin_lock_irq(&ctx->completion_lock); + for (i = 0; i < nr; i++) { + req = cs->reqs[i]; + __io_cqring_fill_event(req, req->result, req->compl.cflags); + } + io_commit_cqring(ctx); + spin_unlock_irq(&ctx->completion_lock); + + io_cqring_ev_posted(ctx); + for (i = 0; i < nr; i++) { + req = cs->reqs[i]; + + /* submission and completion refs */ + if (refcount_sub_and_test(2, &req->refs)) + io_req_free_batch(&rb, req, &ctx->submit_state); + } + + io_req_free_batch_finish(ctx, &rb); + cs->nr = 0; } /* @@ -2273,15 +2487,10 @@ static void io_free_req_deferred(struct io_kiocb *req) { int ret; - init_task_work(&req->task_work, io_put_req_deferred_cb); + req->task_work.func = io_put_req_deferred_cb; ret = io_req_task_work_add(req); - if (unlikely(ret)) { - struct task_struct *tsk; - - tsk = io_wq_get_task(req->ctx->io_wq); - task_work_add(tsk, &req->task_work, TWA_NONE); - wake_up_process(tsk); - } + if (unlikely(ret)) + io_req_task_work_add_fallback(req, io_put_req_deferred_cb); } static inline void io_put_req_deferred(struct io_kiocb *req, int refs) @@ -2290,22 +2499,6 @@ static inline void io_put_req_deferred(struct io_kiocb *req, int refs) io_free_req_deferred(req); } -static struct io_wq_work *io_steal_work(struct io_kiocb *req) -{ - struct io_kiocb *nxt; - - /* - * A ref is owned by io-wq in which context we're. So, if that's the - * last one, it's safe to steal next work. False negatives are Ok, - * it just will be re-punted async in io_put_work() - */ - if (refcount_read(&req->refs) != 1) - return NULL; - - nxt = io_req_find_next(req); - return nxt ? &nxt->work : NULL; -} - static void io_double_put_req(struct io_kiocb *req) { /* drop both submit and complete references */ @@ -2313,20 +2506,8 @@ static void io_double_put_req(struct io_kiocb *req) io_free_req(req); } -static unsigned io_cqring_events(struct io_ring_ctx *ctx, bool noflush) +static unsigned io_cqring_events(struct io_ring_ctx *ctx) { - if (test_bit(0, &ctx->cq_check_overflow)) { - /* - * noflush == true is from the waitqueue handler, just ensure - * we wake up the task, and the next invocation will flush the - * entries. We cannot safely to it from here. - */ - if (noflush) - return -1U; - - io_cqring_overflow_flush(ctx, false, NULL, NULL); - } - /* See comment at the top of this file */ smp_rmb(); return __io_cqring_events(ctx); @@ -2376,17 +2557,6 @@ static inline bool io_run_task_work(void) return false; } -static void io_iopoll_queue(struct list_head *again) -{ - struct io_kiocb *req; - - do { - req = list_first_entry(again, struct io_kiocb, inflight_entry); - list_del(&req->inflight_entry); - __io_complete_rw(req, -EAGAIN, 0, NULL); - } while (!list_empty(again)); -} - /* * Find and free completed poll iocbs */ @@ -2395,7 +2565,6 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events, { struct req_batch rb; struct io_kiocb *req; - LIST_HEAD(again); /* order with ->result store in io_complete_rw_iopoll() */ smp_rmb(); @@ -2405,13 +2574,13 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events, int cflags = 0; req = list_first_entry(done, struct io_kiocb, inflight_entry); + list_del(&req->inflight_entry); + if (READ_ONCE(req->result) == -EAGAIN) { - req->result = 0; req->iopoll_completed = 0; - list_move_tail(&req->inflight_entry, &again); - continue; + if (io_rw_reissue(req)) + continue; } - list_del(&req->inflight_entry); if (req->flags & REQ_F_BUFFER_SELECTED) cflags = io_put_rw_kbuf(req); @@ -2420,16 +2589,12 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events, (*nr_events)++; if (refcount_dec_and_test(&req->refs)) - io_req_free_batch(&rb, req); + io_req_free_batch(&rb, req, &ctx->submit_state); } io_commit_cqring(ctx); - if (ctx->flags & IORING_SETUP_SQPOLL) - io_cqring_ev_posted(ctx); + io_cqring_ev_posted_iopoll(ctx); io_req_free_batch_finish(ctx, &rb); - - if (!list_empty(&again)) - io_iopoll_queue(&again); } static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events, @@ -2551,7 +2716,9 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, long min) * If we do, we can potentially be spinning for commands that * already triggered a CQE (eg in error). */ - if (io_cqring_events(ctx, false)) + if (test_bit(0, &ctx->cq_check_overflow)) + __io_cqring_overflow_flush(ctx, false, NULL, NULL); + if (io_cqring_events(ctx)) break; /* @@ -2594,34 +2761,16 @@ static void kiocb_end_write(struct io_kiocb *req) file_end_write(req->file); } -static void io_complete_rw_common(struct kiocb *kiocb, long res, - struct io_comp_state *cs) -{ - struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb); - int cflags = 0; - - if (kiocb->ki_flags & IOCB_WRITE) - kiocb_end_write(req); - - if (res != req->result) - req_set_fail_links(req); - if (req->flags & REQ_F_BUFFER_SELECTED) - cflags = io_put_rw_kbuf(req); - __io_req_complete(req, res, cflags, cs); -} - #ifdef CONFIG_BLOCK -static bool io_resubmit_prep(struct io_kiocb *req, int error) +static bool io_resubmit_prep(struct io_kiocb *req) { struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; - ssize_t ret = -ECANCELED; + int rw, ret; struct iov_iter iter; - int rw; - if (error) { - ret = error; - goto end_req; - } + /* already prepared */ + if (req->async_data) + return true; switch (req->opcode) { case IORING_OP_READV: @@ -2637,27 +2786,17 @@ static bool io_resubmit_prep(struct io_kiocb *req, int error) default: printk_once(KERN_WARNING "io_uring: bad opcode in resubmit %d\n", req->opcode); - goto end_req; + return false; } - if (!req->async_data) { - ret = io_import_iovec(rw, req, &iovec, &iter, false); - if (ret < 0) - goto end_req; - ret = io_setup_async_rw(req, iovec, inline_vecs, &iter, false); - if (!ret) - return true; - kfree(iovec); - } else { - return true; - } -end_req: - req_set_fail_links(req); - return false; + ret = io_import_iovec(rw, req, &iovec, &iter, false); + if (ret < 0) + return false; + return !io_setup_async_rw(req, iovec, inline_vecs, &iter, false); } #endif -static bool io_rw_reissue(struct io_kiocb *req, long res) +static bool io_rw_reissue(struct io_kiocb *req) { #ifdef CONFIG_BLOCK umode_t mode = file_inode(req->file)->i_mode; @@ -2665,33 +2804,45 @@ static bool io_rw_reissue(struct io_kiocb *req, long res) if (!S_ISBLK(mode) && !S_ISREG(mode)) return false; - if ((res != -EAGAIN && res != -EOPNOTSUPP) || io_wq_current_is_worker()) + if ((req->flags & REQ_F_NOWAIT) || io_wq_current_is_worker()) return false; + lockdep_assert_held(&req->ctx->uring_lock); + ret = io_sq_thread_acquire_mm_files(req->ctx, req); - if (io_resubmit_prep(req, ret)) { + if (!ret && io_resubmit_prep(req)) { refcount_inc(&req->refs); io_queue_async_work(req); return true; } - + req_set_fail_links(req); #endif return false; } static void __io_complete_rw(struct io_kiocb *req, long res, long res2, - struct io_comp_state *cs) + unsigned int issue_flags) { - if (!io_rw_reissue(req, res)) - io_complete_rw_common(&req->rw.kiocb, res, cs); + int cflags = 0; + + if ((res == -EAGAIN || res == -EOPNOTSUPP) && io_rw_reissue(req)) + return; + if (res != req->result) + req_set_fail_links(req); + + if (req->rw.kiocb.ki_flags & IOCB_WRITE) + kiocb_end_write(req); + if (req->flags & REQ_F_BUFFER_SELECTED) + cflags = io_put_rw_kbuf(req); + __io_req_complete(req, issue_flags, res, cflags); } static void io_complete_rw(struct kiocb *kiocb, long res, long res2) { struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb); - __io_complete_rw(req, res, res2, NULL); + __io_complete_rw(req, res, res2, 0); } static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2) @@ -2755,16 +2906,12 @@ static void io_iopoll_req_issued(struct io_kiocb *req, bool in_async) wake_up(&ctx->sq_data->wait); } -static inline void __io_state_file_put(struct io_submit_state *state) -{ - fput_many(state->file, state->file_refs); - state->file_refs = 0; -} - static inline void io_state_file_put(struct io_submit_state *state) { - if (state->file_refs) - __io_state_file_put(state); + if (state->file_refs) { + fput_many(state->file, state->file_refs); + state->file_refs = 0; + } } /* @@ -2782,7 +2929,7 @@ static struct file *__io_file_get(struct io_submit_state *state, int fd) state->file_refs--; return state->file; } - __io_state_file_put(state); + io_state_file_put(state); } state->file = fget_many(fd, state->ios_left); if (unlikely(!state->file)) @@ -2840,16 +2987,17 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_ring_ctx *ctx = req->ctx; struct kiocb *kiocb = &req->rw.kiocb; + struct file *file = req->file; unsigned ioprio; int ret; - if (S_ISREG(file_inode(req->file)->i_mode)) + if (S_ISREG(file_inode(file)->i_mode)) req->flags |= REQ_F_ISREG; kiocb->ki_pos = READ_ONCE(sqe->off); - if (kiocb->ki_pos == -1 && !(req->file->f_mode & FMODE_STREAM)) { + if (kiocb->ki_pos == -1 && !(file->f_mode & FMODE_STREAM)) { req->flags |= REQ_F_CUR_POS; - kiocb->ki_pos = req->file->f_pos; + kiocb->ki_pos = file->f_pos; } kiocb->ki_hint = ki_hint_validate(file_write_hint(kiocb->ki_filp)); kiocb->ki_flags = iocb_flags(kiocb->ki_filp); @@ -2857,6 +3005,10 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (unlikely(ret)) return ret; + /* don't allow async punt for O_NONBLOCK or RWF_NOWAIT */ + if ((kiocb->ki_flags & IOCB_NOWAIT) || (file->f_flags & O_NONBLOCK)) + req->flags |= REQ_F_NOWAIT; + ioprio = READ_ONCE(sqe->ioprio); if (ioprio) { ret = ioprio_check_cap(ioprio); @@ -2867,10 +3019,6 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe) } else kiocb->ki_ioprio = get_current_ioprio(); - /* don't allow async punt if RWF_NOWAIT was requested */ - if (kiocb->ki_flags & IOCB_NOWAIT) - req->flags |= REQ_F_NOWAIT; - if (ctx->flags & IORING_SETUP_IOPOLL) { if (!(kiocb->ki_flags & IOCB_DIRECT) || !kiocb->ki_filp->f_op->iopoll) @@ -2913,7 +3061,7 @@ static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret) } static void kiocb_done(struct kiocb *kiocb, ssize_t ret, - struct io_comp_state *cs) + unsigned int issue_flags) { struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb); struct io_async_rw *io = req->async_data; @@ -2929,13 +3077,12 @@ static void kiocb_done(struct kiocb *kiocb, ssize_t ret, if (req->flags & REQ_F_CUR_POS) req->file->f_pos = kiocb->ki_pos; if (ret >= 0 && kiocb->ki_complete == io_complete_rw) - __io_complete_rw(req, ret, 0, cs); + __io_complete_rw(req, ret, 0, issue_flags); else io_rw_done(kiocb, ret); } -static ssize_t io_import_fixed(struct io_kiocb *req, int rw, - struct iov_iter *iter) +static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter) { struct io_ring_ctx *ctx = req->ctx; size_t len = req->rw.len; @@ -2999,7 +3146,7 @@ static ssize_t io_import_fixed(struct io_kiocb *req, int rw, } } - return len; + return 0; } static void io_ring_submit_unlock(struct io_ring_ctx *ctx, bool needs_lock) @@ -3140,16 +3287,14 @@ static ssize_t io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov, return __io_iov_buffer_select(req, iov, needs_lock); } -static ssize_t io_import_iovec(int rw, struct io_kiocb *req, - struct iovec **iovec, struct iov_iter *iter, - bool needs_lock) +static int io_import_iovec(int rw, struct io_kiocb *req, struct iovec **iovec, + struct iov_iter *iter, bool needs_lock) { void __user *buf = u64_to_user_ptr(req->rw.addr); size_t sqe_len = req->rw.len; + u8 opcode = req->opcode; ssize_t ret; - u8 opcode; - opcode = req->opcode; if (opcode == IORING_OP_READ_FIXED || opcode == IORING_OP_WRITE_FIXED) { *iovec = NULL; return io_import_fixed(req, rw, iter); @@ -3174,10 +3319,8 @@ static ssize_t io_import_iovec(int rw, struct io_kiocb *req, if (req->flags & REQ_F_BUFFER_SELECT) { ret = io_iov_buffer_select(req, *iovec, needs_lock); - if (!ret) { - ret = (*iovec)->iov_len; - iov_iter_init(iter, rw, *iovec, 1, ret); - } + if (!ret) + iov_iter_init(iter, rw, *iovec, 1, (*iovec)->iov_len); *iovec = NULL; return ret; } @@ -3295,8 +3438,10 @@ static int io_setup_async_rw(struct io_kiocb *req, const struct iovec *iovec, if (!force && !io_op_defs[req->opcode].needs_async_data) return 0; if (!req->async_data) { - if (__io_alloc_async_data(req)) + if (__io_alloc_async_data(req)) { + kfree(iovec); return -ENOMEM; + } io_req_map_rw(req, iovec, fast_iov, iter); } @@ -3307,7 +3452,7 @@ static inline int io_rw_prep_async(struct io_kiocb *req, int rw) { struct io_async_rw *iorw = req->async_data; struct iovec *iov = iorw->fast_iov; - ssize_t ret; + int ret; ret = io_import_iovec(rw, req, &iov, &iorw->iter, false); if (unlikely(ret < 0)) @@ -3353,7 +3498,6 @@ static int io_async_buf_func(struct wait_queue_entry *wait, unsigned mode, struct wait_page_queue *wpq; struct io_kiocb *req = wait->private; struct wait_page_key *key = arg; - int ret; wpq = container_of(wait, struct wait_page_queue, wait); @@ -3363,21 +3507,9 @@ static int io_async_buf_func(struct wait_queue_entry *wait, unsigned mode, req->rw.kiocb.ki_flags &= ~IOCB_WAITQ; list_del_init(&wait->entry); - init_task_work(&req->task_work, io_req_task_submit); - percpu_ref_get(&req->ctx->refs); - /* submit ref gets dropped, acquire a new one */ refcount_inc(&req->refs); - ret = io_req_task_work_add(req); - if (unlikely(ret)) { - struct task_struct *tsk; - - /* queue just for cancelation */ - init_task_work(&req->task_work, io_req_task_cancel); - tsk = io_wq_get_task(req->ctx->io_wq); - task_work_add(tsk, &req->task_work, TWA_NONE); - wake_up_process(tsk); - } + io_req_task_queue(req); return 1; } @@ -3434,15 +3566,14 @@ static int io_iter_do_read(struct io_kiocb *req, struct iov_iter *iter) return -EINVAL; } -static int io_read(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static int io_read(struct io_kiocb *req, unsigned int issue_flags) { struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; struct kiocb *kiocb = &req->rw.kiocb; struct iov_iter __iter, *iter = &__iter; struct io_async_rw *rw = req->async_data; ssize_t io_size, ret, ret2; - bool no_async; + bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; if (rw) { iter = &rw->iter; @@ -3454,7 +3585,6 @@ static int io_read(struct io_kiocb *req, bool force_nonblock, } io_size = iov_iter_count(iter); req->result = io_size; - ret = 0; /* Ensure we clear previously set non-block flag */ if (!force_nonblock) @@ -3462,88 +3592,72 @@ static int io_read(struct io_kiocb *req, bool force_nonblock, else kiocb->ki_flags |= IOCB_NOWAIT; - /* If the file doesn't support async, just async punt */ - no_async = force_nonblock && !io_file_supports_async(req->file, READ); - if (no_async) - goto copy_iov; + if (force_nonblock && !io_file_supports_async(req->file, READ)) { + ret = io_setup_async_rw(req, iovec, inline_vecs, iter, true); + return ret ?: -EAGAIN; + } ret = rw_verify_area(READ, req->file, io_kiocb_ppos(kiocb), io_size); - if (unlikely(ret)) - goto out_free; + if (unlikely(ret)) { + kfree(iovec); + return ret; + } ret = io_iter_do_read(req, iter); - if (!ret) { - goto done; - } else if (ret == -EIOCBQUEUED) { - ret = 0; - goto out_free; + if (ret == -EIOCBQUEUED) { + /* it's faster to check here then delegate to kfree */ + if (iovec) + kfree(iovec); + return 0; } else if (ret == -EAGAIN) { /* IOPOLL retry should happen for io-wq threads */ if (!force_nonblock && !(req->ctx->flags & IORING_SETUP_IOPOLL)) goto done; - /* no retry on NONBLOCK marked file */ - if (req->file->f_flags & O_NONBLOCK) + /* no retry on NONBLOCK nor RWF_NOWAIT */ + if (req->flags & REQ_F_NOWAIT) goto done; /* some cases will consume bytes even on error returns */ iov_iter_revert(iter, io_size - iov_iter_count(iter)); ret = 0; - goto copy_iov; - } else if (ret < 0) { - /* make sure -ERESTARTSYS -> -EINTR is done */ + } else if (ret <= 0 || ret == io_size || !force_nonblock || + (req->flags & REQ_F_NOWAIT) || !(req->flags & REQ_F_ISREG)) { + /* read all, failed, already did sync or don't want to retry */ goto done; } - /* read it all, or we did blocking attempt. no retry. */ - if (!iov_iter_count(iter) || !force_nonblock || - (req->file->f_flags & O_NONBLOCK)) - goto done; - - io_size -= ret; -copy_iov: ret2 = io_setup_async_rw(req, iovec, inline_vecs, iter, true); - if (ret2) { - ret = ret2; - goto out_free; - } - if (no_async) - return -EAGAIN; + if (ret2) + return ret2; + rw = req->async_data; - /* it's copied and will be cleaned with ->io */ - iovec = NULL; /* now use our persistent iterator, if we aren't already */ iter = &rw->iter; -retry: - rw->bytes_done += ret; - /* if we can retry, do so with the callbacks armed */ - if (!io_rw_should_retry(req)) { - kiocb->ki_flags &= ~IOCB_WAITQ; - return -EAGAIN; - } - /* - * Now retry read with the IOCB_WAITQ parts set in the iocb. If we - * get -EIOCBQUEUED, then we'll get a notification when the desired - * page gets unlocked. We can also get a partial read here, and if we - * do, then just retry at the new offset. - */ - ret = io_iter_do_read(req, iter); - if (ret == -EIOCBQUEUED) { - ret = 0; - goto out_free; - } else if (ret > 0 && ret < io_size) { + do { + io_size -= ret; + rw->bytes_done += ret; + /* if we can retry, do so with the callbacks armed */ + if (!io_rw_should_retry(req)) { + kiocb->ki_flags &= ~IOCB_WAITQ; + return -EAGAIN; + } + + /* + * Now retry read with the IOCB_WAITQ parts set in the iocb. If + * we get -EIOCBQUEUED, then we'll get a notification when the + * desired page gets unlocked. We can also get a partial read + * here, and if we do, then just retry at the new offset. + */ + ret = io_iter_do_read(req, iter); + if (ret == -EIOCBQUEUED) + return 0; /* we got some bytes, but not all. retry. */ - goto retry; - } + } while (ret > 0 && ret < io_size); done: - kiocb_done(kiocb, ret, cs); - ret = 0; -out_free: - /* it's reportedly faster than delegating the null check to kfree() */ - if (iovec) - kfree(iovec); - return ret; + kiocb_done(kiocb, ret, issue_flags); + return 0; } static int io_write_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) @@ -3563,14 +3677,14 @@ static int io_write_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return io_rw_prep_async(req, WRITE); } -static int io_write(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static int io_write(struct io_kiocb *req, unsigned int issue_flags) { struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; struct kiocb *kiocb = &req->rw.kiocb; struct iov_iter __iter, *iter = &__iter; struct io_async_rw *rw = req->async_data; ssize_t ret, ret2, io_size; + bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; if (rw) { iter = &rw->iter; @@ -3629,22 +3743,21 @@ static int io_write(struct io_kiocb *req, bool force_nonblock, */ if (ret2 == -EOPNOTSUPP && (kiocb->ki_flags & IOCB_NOWAIT)) ret2 = -EAGAIN; - /* no retry on NONBLOCK marked file */ - if (ret2 == -EAGAIN && (req->file->f_flags & O_NONBLOCK)) + /* no retry on NONBLOCK nor RWF_NOWAIT */ + if (ret2 == -EAGAIN && (req->flags & REQ_F_NOWAIT)) goto done; if (!force_nonblock || ret2 != -EAGAIN) { /* IOPOLL retry should happen for io-wq threads */ if ((req->ctx->flags & IORING_SETUP_IOPOLL) && ret2 == -EAGAIN) goto copy_iov; done: - kiocb_done(kiocb, ret2, cs); + kiocb_done(kiocb, ret2, issue_flags); } else { copy_iov: /* some cases will consume bytes even on error returns */ iov_iter_revert(iter, io_size - iov_iter_count(iter)); ret = io_setup_async_rw(req, iovec, inline_vecs, iter, false); - if (!ret) - return -EAGAIN; + return ret ?: -EAGAIN; } out_free: /* it's reportedly faster than delegating the null check to kfree() */ @@ -3682,12 +3795,12 @@ static int io_renameat_prep(struct io_kiocb *req, return 0; } -static int io_renameat(struct io_kiocb *req, bool force_nonblock) +static int io_renameat(struct io_kiocb *req, unsigned int issue_flags) { struct io_rename *ren = &req->rename; int ret; - if (force_nonblock) + if (issue_flags & IO_URING_F_NONBLOCK) return -EAGAIN; ret = do_renameat2(ren->old_dfd, ren->oldpath, ren->new_dfd, @@ -3724,12 +3837,12 @@ static int io_unlinkat_prep(struct io_kiocb *req, return 0; } -static int io_unlinkat(struct io_kiocb *req, bool force_nonblock) +static int io_unlinkat(struct io_kiocb *req, unsigned int issue_flags) { struct io_unlink *un = &req->unlink; int ret; - if (force_nonblock) + if (issue_flags & IO_URING_F_NONBLOCK) return -EAGAIN; if (un->flags & AT_REMOVEDIR) @@ -3761,13 +3874,13 @@ static int io_shutdown_prep(struct io_kiocb *req, #endif } -static int io_shutdown(struct io_kiocb *req, bool force_nonblock) +static int io_shutdown(struct io_kiocb *req, unsigned int issue_flags) { #if defined(CONFIG_NET) struct socket *sock; int ret; - if (force_nonblock) + if (issue_flags & IO_URING_F_NONBLOCK) return -EAGAIN; sock = sock_from_file(req->file); @@ -3826,7 +3939,7 @@ static int io_tee_prep(struct io_kiocb *req, return __io_splice_prep(req, sqe); } -static int io_tee(struct io_kiocb *req, bool force_nonblock) +static int io_tee(struct io_kiocb *req, unsigned int issue_flags) { struct io_splice *sp = &req->splice; struct file *in = sp->file_in; @@ -3834,7 +3947,7 @@ static int io_tee(struct io_kiocb *req, bool force_nonblock) unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED; long ret = 0; - if (force_nonblock) + if (issue_flags & IO_URING_F_NONBLOCK) return -EAGAIN; if (sp->len) ret = do_tee(in, out, sp->len, flags); @@ -3857,7 +3970,7 @@ static int io_splice_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return __io_splice_prep(req, sqe); } -static int io_splice(struct io_kiocb *req, bool force_nonblock) +static int io_splice(struct io_kiocb *req, unsigned int issue_flags) { struct io_splice *sp = &req->splice; struct file *in = sp->file_in; @@ -3866,7 +3979,7 @@ static int io_splice(struct io_kiocb *req, bool force_nonblock) loff_t *poff_in, *poff_out; long ret = 0; - if (force_nonblock) + if (issue_flags & IO_URING_F_NONBLOCK) return -EAGAIN; poff_in = (sp->off_in == -1) ? NULL : &sp->off_in; @@ -3887,14 +4000,14 @@ static int io_splice(struct io_kiocb *req, bool force_nonblock) /* * IORING_OP_NOP just posts a completion event, nothing else. */ -static int io_nop(struct io_kiocb *req, struct io_comp_state *cs) +static int io_nop(struct io_kiocb *req, unsigned int issue_flags) { struct io_ring_ctx *ctx = req->ctx; if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; - __io_req_complete(req, 0, 0, cs); + __io_req_complete(req, issue_flags, 0, 0); return 0; } @@ -3919,13 +4032,13 @@ static int io_prep_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe) return 0; } -static int io_fsync(struct io_kiocb *req, bool force_nonblock) +static int io_fsync(struct io_kiocb *req, unsigned int issue_flags) { loff_t end = req->sync.off + req->sync.len; int ret; /* fsync always requires a blocking context */ - if (force_nonblock) + if (issue_flags & IO_URING_F_NONBLOCK) return -EAGAIN; ret = vfs_fsync_range(req->file, req->sync.off, @@ -3951,12 +4064,12 @@ static int io_fallocate_prep(struct io_kiocb *req, return 0; } -static int io_fallocate(struct io_kiocb *req, bool force_nonblock) +static int io_fallocate(struct io_kiocb *req, unsigned int issue_flags) { int ret; /* fallocate always requiring blocking context */ - if (force_nonblock) + if (issue_flags & IO_URING_F_NONBLOCK) return -EAGAIN; ret = vfs_fallocate(req->file, req->sync.mode, req->sync.off, req->sync.len); @@ -3989,7 +4102,6 @@ static int __io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe return ret; } req->open.nofile = rlimit(RLIMIT_NOFILE); - req->open.ignore_nonblock = false; req->flags |= REQ_F_NEED_CLEANUP; return 0; } @@ -4027,43 +4139,53 @@ static int io_openat2_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return __io_openat_prep(req, sqe); } -static int io_openat2(struct io_kiocb *req, bool force_nonblock) +static int io_openat2(struct io_kiocb *req, unsigned int issue_flags) { struct open_flags op; struct file *file; + bool nonblock_set; + bool resolve_nonblock; int ret; - if (force_nonblock && !req->open.ignore_nonblock) - return -EAGAIN; - ret = build_open_flags(&req->open.how, &op); if (ret) goto err; + nonblock_set = op.open_flag & O_NONBLOCK; + resolve_nonblock = req->open.how.resolve & RESOLVE_CACHED; + if (issue_flags & IO_URING_F_NONBLOCK) { + /* + * Don't bother trying for O_TRUNC, O_CREAT, or O_TMPFILE open, + * it'll always -EAGAIN + */ + if (req->open.how.flags & (O_TRUNC | O_CREAT | O_TMPFILE)) + return -EAGAIN; + op.lookup_flags |= LOOKUP_CACHED; + op.open_flag |= O_NONBLOCK; + } ret = __get_unused_fd_flags(req->open.how.flags, req->open.nofile); if (ret < 0) goto err; file = do_filp_open(req->open.dfd, req->open.filename, &op); + /* only retry if RESOLVE_CACHED wasn't already set by application */ + if ((!resolve_nonblock && (issue_flags & IO_URING_F_NONBLOCK)) && + file == ERR_PTR(-EAGAIN)) { + /* + * We could hang on to this 'fd', but seems like marginal + * gain for something that is now known to be a slower path. + * So just put it, and we'll get a new one when we retry. + */ + put_unused_fd(ret); + return -EAGAIN; + } + if (IS_ERR(file)) { put_unused_fd(ret); ret = PTR_ERR(file); - /* - * A work-around to ensure that /proc/self works that way - * that it should - if we get -EOPNOTSUPP back, then assume - * that proc_self_get_link() failed us because we're in async - * context. We should be safe to retry this from the task - * itself with force_nonblock == false set, as it should not - * block on lookup. Would be nice to know this upfront and - * avoid the async dance, but doesn't seem feasible. - */ - if (ret == -EOPNOTSUPP && io_wq_current_is_worker()) { - req->open.ignore_nonblock = true; - refcount_inc(&req->refs); - io_req_task_queue(req); - return 0; - } } else { + if ((issue_flags & IO_URING_F_NONBLOCK) && !nonblock_set) + file->f_flags &= ~O_NONBLOCK; fsnotify_open(file); fd_install(ret, file); } @@ -4076,9 +4198,9 @@ err: return 0; } -static int io_openat(struct io_kiocb *req, bool force_nonblock) +static int io_openat(struct io_kiocb *req, unsigned int issue_flags) { - return io_openat2(req, force_nonblock); + return io_openat2(req, issue_flags & IO_URING_F_NONBLOCK); } static int io_remove_buffers_prep(struct io_kiocb *req, @@ -4126,13 +4248,13 @@ static int __io_remove_buffers(struct io_ring_ctx *ctx, struct io_buffer *buf, return i; } -static int io_remove_buffers(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static int io_remove_buffers(struct io_kiocb *req, unsigned int issue_flags) { struct io_provide_buf *p = &req->pbuf; struct io_ring_ctx *ctx = req->ctx; struct io_buffer *head; int ret = 0; + bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; io_ring_submit_lock(ctx, !force_nonblock); @@ -4147,11 +4269,11 @@ static int io_remove_buffers(struct io_kiocb *req, bool force_nonblock, /* need to hold the lock to complete IOPOLL requests */ if (ctx->flags & IORING_SETUP_IOPOLL) { - __io_req_complete(req, ret, 0, cs); + __io_req_complete(req, issue_flags, ret, 0); io_ring_submit_unlock(ctx, !force_nonblock); } else { io_ring_submit_unlock(ctx, !force_nonblock); - __io_req_complete(req, ret, 0, cs); + __io_req_complete(req, issue_flags, ret, 0); } return 0; } @@ -4210,13 +4332,13 @@ static int io_add_buffers(struct io_provide_buf *pbuf, struct io_buffer **head) return i ? i : -ENOMEM; } -static int io_provide_buffers(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static int io_provide_buffers(struct io_kiocb *req, unsigned int issue_flags) { struct io_provide_buf *p = &req->pbuf; struct io_ring_ctx *ctx = req->ctx; struct io_buffer *head, *list; int ret = 0; + bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; io_ring_submit_lock(ctx, !force_nonblock); @@ -4242,11 +4364,11 @@ out: /* need to hold the lock to complete IOPOLL requests */ if (ctx->flags & IORING_SETUP_IOPOLL) { - __io_req_complete(req, ret, 0, cs); + __io_req_complete(req, issue_flags, ret, 0); io_ring_submit_unlock(ctx, !force_nonblock); } else { io_ring_submit_unlock(ctx, !force_nonblock); - __io_req_complete(req, ret, 0, cs); + __io_req_complete(req, issue_flags, ret, 0); } return 0; } @@ -4278,12 +4400,12 @@ static int io_epoll_ctl_prep(struct io_kiocb *req, #endif } -static int io_epoll_ctl(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static int io_epoll_ctl(struct io_kiocb *req, unsigned int issue_flags) { #if defined(CONFIG_EPOLL) struct io_epoll *ie = &req->epoll; int ret; + bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; ret = do_epoll_ctl(ie->epfd, ie->op, ie->fd, &ie->event, force_nonblock); if (force_nonblock && ret == -EAGAIN) @@ -4291,7 +4413,7 @@ static int io_epoll_ctl(struct io_kiocb *req, bool force_nonblock, if (ret < 0) req_set_fail_links(req); - __io_req_complete(req, ret, 0, cs); + __io_req_complete(req, issue_flags, ret, 0); return 0; #else return -EOPNOTSUPP; @@ -4315,13 +4437,13 @@ static int io_madvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) #endif } -static int io_madvise(struct io_kiocb *req, bool force_nonblock) +static int io_madvise(struct io_kiocb *req, unsigned int issue_flags) { #if defined(CONFIG_ADVISE_SYSCALLS) && defined(CONFIG_MMU) struct io_madvise *ma = &req->madvise; int ret; - if (force_nonblock) + if (issue_flags & IO_URING_F_NONBLOCK) return -EAGAIN; ret = do_madvise(current->mm, ma->addr, ma->len, ma->advice); @@ -4347,12 +4469,12 @@ static int io_fadvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return 0; } -static int io_fadvise(struct io_kiocb *req, bool force_nonblock) +static int io_fadvise(struct io_kiocb *req, unsigned int issue_flags) { struct io_fadvise *fa = &req->fadvise; int ret; - if (force_nonblock) { + if (issue_flags & IO_URING_F_NONBLOCK) { switch (fa->advice) { case POSIX_FADV_NORMAL: case POSIX_FADV_RANDOM: @@ -4388,12 +4510,12 @@ static int io_statx_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return 0; } -static int io_statx(struct io_kiocb *req, bool force_nonblock) +static int io_statx(struct io_kiocb *req, unsigned int issue_flags) { struct io_statx *ctx = &req->statx; int ret; - if (force_nonblock) { + if (issue_flags & IO_URING_F_NONBLOCK) { /* only need file table for an actual valid fd */ if (ctx->dfd == -1 || ctx->dfd == AT_FDCWD) req->flags |= REQ_F_NO_FILE_TABLE; @@ -4411,14 +4533,6 @@ static int io_statx(struct io_kiocb *req, bool force_nonblock) static int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - /* - * If we queue this for async, it must not be cancellable. That would - * leave the 'file' in an undeterminate state, and here need to modify - * io_wq_work.flags, so initialize io_wq_work firstly. - */ - io_req_init_async(req); - req->work.flags |= IO_WQ_WORK_NO_CANCEL; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (sqe->ioprio || sqe->off || sqe->addr || sqe->len || @@ -4428,42 +4542,59 @@ static int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return -EBADF; req->close.fd = READ_ONCE(sqe->fd); - if ((req->file && req->file->f_op == &io_uring_fops)) - return -EBADF; - - req->close.put_file = NULL; return 0; } -static int io_close(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static int io_close(struct io_kiocb *req, unsigned int issue_flags) { + struct files_struct *files = current->files; struct io_close *close = &req->close; + struct fdtable *fdt; + struct file *file; int ret; - /* might be already done during nonblock submission */ - if (!close->put_file) { - ret = close_fd_get_file(close->fd, &close->put_file); - if (ret < 0) - return (ret == -ENOENT) ? -EBADF : ret; + file = NULL; + ret = -EBADF; + spin_lock(&files->file_lock); + fdt = files_fdtable(files); + if (close->fd >= fdt->max_fds) { + spin_unlock(&files->file_lock); + goto err; + } + file = fdt->fd[close->fd]; + if (!file) { + spin_unlock(&files->file_lock); + goto err; + } + + if (file->f_op == &io_uring_fops) { + spin_unlock(&files->file_lock); + file = NULL; + goto err; } /* if the file has a flush method, be safe and punt to async */ - if (close->put_file->f_op->flush && force_nonblock) { - /* was never set, but play safe */ - req->flags &= ~REQ_F_NOWAIT; - /* avoid grabbing files - we don't need the files */ - req->flags |= REQ_F_NO_FILE_TABLE; + if (file->f_op->flush && (issue_flags & IO_URING_F_NONBLOCK)) { + spin_unlock(&files->file_lock); return -EAGAIN; } + ret = __close_fd_get_file(close->fd, &file); + spin_unlock(&files->file_lock); + if (ret < 0) { + if (ret == -ENOENT) + ret = -EBADF; + goto err; + } + /* No ->flush() or already async, safely close from here */ - ret = filp_close(close->put_file, req->work.identity->files); + ret = filp_close(file, current->files); +err: if (ret < 0) req_set_fail_links(req); - fput(close->put_file); - close->put_file = NULL; - __io_req_complete(req, ret, 0, cs); + if (file) + fput(file); + __io_req_complete(req, issue_flags, ret, 0); return 0; } @@ -4485,12 +4616,12 @@ static int io_prep_sfr(struct io_kiocb *req, const struct io_uring_sqe *sqe) return 0; } -static int io_sync_file_range(struct io_kiocb *req, bool force_nonblock) +static int io_sync_file_range(struct io_kiocb *req, unsigned int issue_flags) { int ret; /* sync_file_range always requires a blocking context */ - if (force_nonblock) + if (issue_flags & IO_URING_F_NONBLOCK) return -EAGAIN; ret = sync_file_range(req->file, req->sync.off, req->sync.len, @@ -4510,23 +4641,27 @@ static int io_setup_async_msg(struct io_kiocb *req, if (async_msg) return -EAGAIN; if (io_alloc_async_data(req)) { - if (kmsg->iov != kmsg->fast_iov) - kfree(kmsg->iov); + kfree(kmsg->free_iov); return -ENOMEM; } async_msg = req->async_data; req->flags |= REQ_F_NEED_CLEANUP; memcpy(async_msg, kmsg, sizeof(*kmsg)); + async_msg->msg.msg_name = &async_msg->addr; + /* if were using fast_iov, set it to the new one */ + if (!async_msg->free_iov) + async_msg->msg.msg_iter.iov = async_msg->fast_iov; + return -EAGAIN; } static int io_sendmsg_copy_hdr(struct io_kiocb *req, struct io_async_msghdr *iomsg) { - iomsg->iov = iomsg->fast_iov; iomsg->msg.msg_name = &iomsg->addr; + iomsg->free_iov = iomsg->fast_iov; return sendmsg_copy_msghdr(&iomsg->msg, req->sr_msg.umsg, - req->sr_msg.msg_flags, &iomsg->iov); + req->sr_msg.msg_flags, &iomsg->free_iov); } static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) @@ -4555,8 +4690,7 @@ static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return ret; } -static int io_sendmsg(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags) { struct io_async_msghdr iomsg, *kmsg; struct socket *sock; @@ -4567,14 +4701,8 @@ static int io_sendmsg(struct io_kiocb *req, bool force_nonblock, if (unlikely(!sock)) return -ENOTSOCK; - if (req->async_data) { - kmsg = req->async_data; - kmsg->msg.msg_name = &kmsg->addr; - /* if iov is set, it's allocated already */ - if (!kmsg->iov) - kmsg->iov = kmsg->fast_iov; - kmsg->msg.msg_iter.iov = kmsg->iov; - } else { + kmsg = req->async_data; + if (!kmsg) { ret = io_sendmsg_copy_hdr(req, &iomsg); if (ret) return ret; @@ -4584,26 +4712,26 @@ static int io_sendmsg(struct io_kiocb *req, bool force_nonblock, flags = req->sr_msg.msg_flags; if (flags & MSG_DONTWAIT) req->flags |= REQ_F_NOWAIT; - else if (force_nonblock) + else if (issue_flags & IO_URING_F_NONBLOCK) flags |= MSG_DONTWAIT; ret = __sys_sendmsg_sock(sock, &kmsg->msg, flags); - if (force_nonblock && ret == -EAGAIN) + if ((issue_flags & IO_URING_F_NONBLOCK) && ret == -EAGAIN) return io_setup_async_msg(req, kmsg); if (ret == -ERESTARTSYS) ret = -EINTR; - if (kmsg->iov != kmsg->fast_iov) - kfree(kmsg->iov); + /* fast path, check for non-NULL to avoid function call */ + if (kmsg->free_iov) + kfree(kmsg->free_iov); req->flags &= ~REQ_F_NEED_CLEANUP; if (ret < 0) req_set_fail_links(req); - __io_req_complete(req, ret, 0, cs); + __io_req_complete(req, issue_flags, ret, 0); return 0; } -static int io_send(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static int io_send(struct io_kiocb *req, unsigned int issue_flags) { struct io_sr_msg *sr = &req->sr_msg; struct msghdr msg; @@ -4628,19 +4756,19 @@ static int io_send(struct io_kiocb *req, bool force_nonblock, flags = req->sr_msg.msg_flags; if (flags & MSG_DONTWAIT) req->flags |= REQ_F_NOWAIT; - else if (force_nonblock) + else if (issue_flags & IO_URING_F_NONBLOCK) flags |= MSG_DONTWAIT; msg.msg_flags = flags; ret = sock_sendmsg(sock, &msg); - if (force_nonblock && ret == -EAGAIN) + if ((issue_flags & IO_URING_F_NONBLOCK) && ret == -EAGAIN) return -EAGAIN; if (ret == -ERESTARTSYS) ret = -EINTR; if (ret < 0) req_set_fail_links(req); - __io_req_complete(req, ret, 0, cs); + __io_req_complete(req, issue_flags, ret, 0); return 0; } @@ -4660,15 +4788,14 @@ static int __io_recvmsg_copy_hdr(struct io_kiocb *req, if (req->flags & REQ_F_BUFFER_SELECT) { if (iov_len > 1) return -EINVAL; - if (copy_from_user(iomsg->iov, uiov, sizeof(*uiov))) + if (copy_from_user(iomsg->fast_iov, uiov, sizeof(*uiov))) return -EFAULT; - sr->len = iomsg->iov[0].iov_len; - iov_iter_init(&iomsg->msg.msg_iter, READ, iomsg->iov, 1, - sr->len); - iomsg->iov = NULL; + sr->len = iomsg->fast_iov[0].iov_len; + iomsg->free_iov = NULL; } else { + iomsg->free_iov = iomsg->fast_iov; ret = __import_iovec(READ, uiov, iov_len, UIO_FASTIOV, - &iomsg->iov, &iomsg->msg.msg_iter, + &iomsg->free_iov, &iomsg->msg.msg_iter, false); if (ret > 0) ret = 0; @@ -4707,11 +4834,11 @@ static int __io_compat_recvmsg_copy_hdr(struct io_kiocb *req, if (clen < 0) return -EINVAL; sr->len = clen; - iomsg->iov[0].iov_len = clen; - iomsg->iov = NULL; + iomsg->free_iov = NULL; } else { + iomsg->free_iov = iomsg->fast_iov; ret = __import_iovec(READ, (struct iovec __user *)uiov, len, - UIO_FASTIOV, &iomsg->iov, + UIO_FASTIOV, &iomsg->free_iov, &iomsg->msg.msg_iter, true); if (ret < 0) return ret; @@ -4725,7 +4852,6 @@ static int io_recvmsg_copy_hdr(struct io_kiocb *req, struct io_async_msghdr *iomsg) { iomsg->msg.msg_name = &iomsg->addr; - iomsg->iov = iomsg->fast_iov; #ifdef CONFIG_COMPAT if (req->ctx->compat) @@ -4783,27 +4909,21 @@ static int io_recvmsg_prep(struct io_kiocb *req, return ret; } -static int io_recvmsg(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) { struct io_async_msghdr iomsg, *kmsg; struct socket *sock; struct io_buffer *kbuf; unsigned flags; int ret, cflags = 0; + bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; sock = sock_from_file(req->file); if (unlikely(!sock)) return -ENOTSOCK; - if (req->async_data) { - kmsg = req->async_data; - kmsg->msg.msg_name = &kmsg->addr; - /* if iov is set, it's allocated already */ - if (!kmsg->iov) - kmsg->iov = kmsg->fast_iov; - kmsg->msg.msg_iter.iov = kmsg->iov; - } else { + kmsg = req->async_data; + if (!kmsg) { ret = io_recvmsg_copy_hdr(req, &iomsg); if (ret) return ret; @@ -4815,7 +4935,8 @@ static int io_recvmsg(struct io_kiocb *req, bool force_nonblock, if (IS_ERR(kbuf)) return PTR_ERR(kbuf); kmsg->fast_iov[0].iov_base = u64_to_user_ptr(kbuf->addr); - iov_iter_init(&kmsg->msg.msg_iter, READ, kmsg->iov, + kmsg->fast_iov[0].iov_len = req->sr_msg.len; + iov_iter_init(&kmsg->msg.msg_iter, READ, kmsg->fast_iov, 1, req->sr_msg.len); } @@ -4834,17 +4955,17 @@ static int io_recvmsg(struct io_kiocb *req, bool force_nonblock, if (req->flags & REQ_F_BUFFER_SELECTED) cflags = io_put_recv_kbuf(req); - if (kmsg->iov != kmsg->fast_iov) - kfree(kmsg->iov); + /* fast path, check for non-NULL to avoid function call */ + if (kmsg->free_iov) + kfree(kmsg->free_iov); req->flags &= ~REQ_F_NEED_CLEANUP; if (ret < 0) req_set_fail_links(req); - __io_req_complete(req, ret, cflags, cs); + __io_req_complete(req, issue_flags, ret, cflags); return 0; } -static int io_recv(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static int io_recv(struct io_kiocb *req, unsigned int issue_flags) { struct io_buffer *kbuf; struct io_sr_msg *sr = &req->sr_msg; @@ -4854,6 +4975,7 @@ static int io_recv(struct io_kiocb *req, bool force_nonblock, struct iovec iov; unsigned flags; int ret, cflags = 0; + bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; sock = sock_from_file(req->file); if (unlikely(!sock)) @@ -4893,7 +5015,7 @@ out_free: cflags = io_put_recv_kbuf(req); if (ret < 0) req_set_fail_links(req); - __io_req_complete(req, ret, cflags, cs); + __io_req_complete(req, issue_flags, ret, cflags); return 0; } @@ -4913,10 +5035,10 @@ static int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return 0; } -static int io_accept(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static int io_accept(struct io_kiocb *req, unsigned int issue_flags) { struct io_accept *accept = &req->accept; + bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; unsigned int file_flags = force_nonblock ? O_NONBLOCK : 0; int ret; @@ -4933,7 +5055,7 @@ static int io_accept(struct io_kiocb *req, bool force_nonblock, ret = -EINTR; req_set_fail_links(req); } - __io_req_complete(req, ret, 0, cs); + __io_req_complete(req, issue_flags, ret, 0); return 0; } @@ -4957,12 +5079,12 @@ static int io_connect_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) &io->address); } -static int io_connect(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static int io_connect(struct io_kiocb *req, unsigned int issue_flags) { struct io_async_connect __io, *io; unsigned file_flags; int ret; + bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; if (req->async_data) { io = req->async_data; @@ -4995,7 +5117,7 @@ static int io_connect(struct io_kiocb *req, bool force_nonblock, out: if (ret < 0) req_set_fail_links(req); - __io_req_complete(req, ret, 0, cs); + __io_req_complete(req, issue_flags, ret, 0); return 0; } #else /* !CONFIG_NET */ @@ -5004,14 +5126,12 @@ static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return -EOPNOTSUPP; } -static int io_sendmsg(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags) { return -EOPNOTSUPP; } -static int io_send(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static int io_send(struct io_kiocb *req, unsigned int issue_flags) { return -EOPNOTSUPP; } @@ -5022,14 +5142,12 @@ static int io_recvmsg_prep(struct io_kiocb *req, return -EOPNOTSUPP; } -static int io_recvmsg(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) { return -EOPNOTSUPP; } -static int io_recv(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static int io_recv(struct io_kiocb *req, unsigned int issue_flags) { return -EOPNOTSUPP; } @@ -5039,8 +5157,7 @@ static int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return -EOPNOTSUPP; } -static int io_accept(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static int io_accept(struct io_kiocb *req, unsigned int issue_flags) { return -EOPNOTSUPP; } @@ -5050,8 +5167,7 @@ static int io_connect_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return -EOPNOTSUPP; } -static int io_connect(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static int io_connect(struct io_kiocb *req, unsigned int issue_flags) { return -EOPNOTSUPP; } @@ -5077,7 +5193,7 @@ static int __io_async_wake(struct io_kiocb *req, struct io_poll_iocb *poll, list_del_init(&poll->wait.entry); req->result = mask; - init_task_work(&req->task_work, func); + req->task_work.func = func; percpu_ref_get(&req->ctx->refs); /* @@ -5088,12 +5204,8 @@ static int __io_async_wake(struct io_kiocb *req, struct io_poll_iocb *poll, */ ret = io_req_task_work_add(req); if (unlikely(ret)) { - struct task_struct *tsk; - WRITE_ONCE(poll->canceled, true); - tsk = io_wq_get_task(req->ctx->io_wq); - task_work_add(tsk, &req->task_work, TWA_NONE); - wake_up_process(tsk); + io_req_task_work_add_fallback(req, func); } return 1; } @@ -5536,7 +5648,7 @@ static int io_poll_remove_prep(struct io_kiocb *req, * Find a running poll command that matches one specified in sqe->addr, * and remove it if found. */ -static int io_poll_remove(struct io_kiocb *req) +static int io_poll_remove(struct io_kiocb *req, unsigned int issue_flags) { struct io_ring_ctx *ctx = req->ctx; int ret; @@ -5587,7 +5699,7 @@ static int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe return 0; } -static int io_poll_add(struct io_kiocb *req) +static int io_poll_add(struct io_kiocb *req, unsigned int issue_flags) { struct io_poll_iocb *poll = &req->poll; struct io_ring_ctx *ctx = req->ctx; @@ -5718,24 +5830,27 @@ static int io_timeout_remove_prep(struct io_kiocb *req, return 0; } +static inline enum hrtimer_mode io_translate_timeout_mode(unsigned int flags) +{ + return (flags & IORING_TIMEOUT_ABS) ? HRTIMER_MODE_ABS + : HRTIMER_MODE_REL; +} + /* * Remove or update an existing timeout command */ -static int io_timeout_remove(struct io_kiocb *req) +static int io_timeout_remove(struct io_kiocb *req, unsigned int issue_flags) { struct io_timeout_rem *tr = &req->timeout_rem; struct io_ring_ctx *ctx = req->ctx; int ret; spin_lock_irq(&ctx->completion_lock); - if (req->timeout_rem.flags & IORING_TIMEOUT_UPDATE) { - enum hrtimer_mode mode = (tr->flags & IORING_TIMEOUT_ABS) - ? HRTIMER_MODE_ABS : HRTIMER_MODE_REL; - - ret = io_timeout_update(ctx, tr->addr, &tr->ts, mode); - } else { + if (!(req->timeout_rem.flags & IORING_TIMEOUT_UPDATE)) ret = io_timeout_cancel(ctx, tr->addr); - } + else + ret = io_timeout_update(ctx, tr->addr, &tr->ts, + io_translate_timeout_mode(tr->flags)); io_cqring_fill_event(req, ret); io_commit_cqring(ctx); @@ -5775,16 +5890,12 @@ static int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe, if (get_timespec64(&data->ts, u64_to_user_ptr(sqe->addr))) return -EFAULT; - if (flags & IORING_TIMEOUT_ABS) - data->mode = HRTIMER_MODE_ABS; - else - data->mode = HRTIMER_MODE_REL; - + data->mode = io_translate_timeout_mode(flags); hrtimer_init(&data->timer, CLOCK_MONOTONIC, data->mode); return 0; } -static int io_timeout(struct io_kiocb *req) +static int io_timeout(struct io_kiocb *req, unsigned int issue_flags) { struct io_ring_ctx *ctx = req->ctx; struct io_timeout_data *data = req->async_data; @@ -5806,6 +5917,12 @@ static int io_timeout(struct io_kiocb *req) tail = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts); req->timeout.target_seq = tail + off; + /* Update the last seq here in case io_flush_timeouts() hasn't. + * This is safe because ->completion_lock is held, and submissions + * and completions are never mixed in the same ->completion_lock section. + */ + ctx->cq_last_tm_flush = tail; + /* * Insertion sort, ensuring the first entry in the list is always * the one we need first. @@ -5901,7 +6018,7 @@ static int io_async_cancel_prep(struct io_kiocb *req, return 0; } -static int io_async_cancel(struct io_kiocb *req) +static int io_async_cancel(struct io_kiocb *req, unsigned int issue_flags) { struct io_ring_ctx *ctx = req->ctx; @@ -5909,7 +6026,7 @@ static int io_async_cancel(struct io_kiocb *req) return 0; } -static int io_files_update_prep(struct io_kiocb *req, +static int io_rsrc_update_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { if (unlikely(req->ctx->flags & IORING_SETUP_SQPOLL)) @@ -5919,34 +6036,33 @@ static int io_files_update_prep(struct io_kiocb *req, if (sqe->ioprio || sqe->rw_flags) return -EINVAL; - req->files_update.offset = READ_ONCE(sqe->off); - req->files_update.nr_args = READ_ONCE(sqe->len); - if (!req->files_update.nr_args) + req->rsrc_update.offset = READ_ONCE(sqe->off); + req->rsrc_update.nr_args = READ_ONCE(sqe->len); + if (!req->rsrc_update.nr_args) return -EINVAL; - req->files_update.arg = READ_ONCE(sqe->addr); + req->rsrc_update.arg = READ_ONCE(sqe->addr); return 0; } -static int io_files_update(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static int io_files_update(struct io_kiocb *req, unsigned int issue_flags) { struct io_ring_ctx *ctx = req->ctx; - struct io_uring_files_update up; + struct io_uring_rsrc_update up; int ret; - if (force_nonblock) + if (issue_flags & IO_URING_F_NONBLOCK) return -EAGAIN; - up.offset = req->files_update.offset; - up.fds = req->files_update.arg; + up.offset = req->rsrc_update.offset; + up.data = req->rsrc_update.arg; mutex_lock(&ctx->uring_lock); - ret = __io_sqe_files_update(ctx, &up, req->files_update.nr_args); + ret = __io_sqe_files_update(ctx, &up, req->rsrc_update.nr_args); mutex_unlock(&ctx->uring_lock); if (ret < 0) req_set_fail_links(req); - __io_req_complete(req, ret, 0, cs); + __io_req_complete(req, issue_flags, ret, 0); return 0; } @@ -5996,7 +6112,7 @@ static int io_req_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) case IORING_OP_CLOSE: return io_close_prep(req, sqe); case IORING_OP_FILES_UPDATE: - return io_files_update_prep(req, sqe); + return io_rsrc_update_prep(req, sqe); case IORING_OP_STATX: return io_statx_prep(req, sqe); case IORING_OP_FADVISE: @@ -6094,23 +6210,6 @@ static int io_req_defer(struct io_kiocb *req, const struct io_uring_sqe *sqe) return -EIOCBQUEUED; } -static void io_req_drop_files(struct io_kiocb *req) -{ - struct io_ring_ctx *ctx = req->ctx; - struct io_uring_task *tctx = req->task->io_uring; - unsigned long flags; - - put_files_struct(req->work.identity->files); - put_nsproxy(req->work.identity->nsproxy); - spin_lock_irqsave(&ctx->inflight_lock, flags); - list_del(&req->inflight_entry); - spin_unlock_irqrestore(&ctx->inflight_lock, flags); - req->flags &= ~REQ_F_INFLIGHT; - req->work.flags &= ~IO_WQ_WORK_FILES; - if (atomic_read(&tctx->in_idle)) - wake_up(&tctx->wait); -} - static void __io_clean_op(struct io_kiocb *req) { if (req->flags & REQ_F_BUFFER_SELECTED) { @@ -6144,8 +6243,8 @@ static void __io_clean_op(struct io_kiocb *req) case IORING_OP_RECVMSG: case IORING_OP_SENDMSG: { struct io_async_msghdr *io = req->async_data; - if (io->iov != io->fast_iov) - kfree(io->iov); + + kfree(io->free_iov); break; } case IORING_OP_SPLICE: @@ -6168,117 +6267,113 @@ static void __io_clean_op(struct io_kiocb *req) } req->flags &= ~REQ_F_NEED_CLEANUP; } - - if (req->flags & REQ_F_INFLIGHT) - io_req_drop_files(req); } -static int io_issue_sqe(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags) { struct io_ring_ctx *ctx = req->ctx; int ret; switch (req->opcode) { case IORING_OP_NOP: - ret = io_nop(req, cs); + ret = io_nop(req, issue_flags); break; case IORING_OP_READV: case IORING_OP_READ_FIXED: case IORING_OP_READ: - ret = io_read(req, force_nonblock, cs); + ret = io_read(req, issue_flags); break; case IORING_OP_WRITEV: case IORING_OP_WRITE_FIXED: case IORING_OP_WRITE: - ret = io_write(req, force_nonblock, cs); + ret = io_write(req, issue_flags); break; case IORING_OP_FSYNC: - ret = io_fsync(req, force_nonblock); + ret = io_fsync(req, issue_flags); break; case IORING_OP_POLL_ADD: - ret = io_poll_add(req); + ret = io_poll_add(req, issue_flags); break; case IORING_OP_POLL_REMOVE: - ret = io_poll_remove(req); + ret = io_poll_remove(req, issue_flags); break; case IORING_OP_SYNC_FILE_RANGE: - ret = io_sync_file_range(req, force_nonblock); + ret = io_sync_file_range(req, issue_flags); break; case IORING_OP_SENDMSG: - ret = io_sendmsg(req, force_nonblock, cs); + ret = io_sendmsg(req, issue_flags); break; case IORING_OP_SEND: - ret = io_send(req, force_nonblock, cs); + ret = io_send(req, issue_flags); break; case IORING_OP_RECVMSG: - ret = io_recvmsg(req, force_nonblock, cs); + ret = io_recvmsg(req, issue_flags); break; case IORING_OP_RECV: - ret = io_recv(req, force_nonblock, cs); + ret = io_recv(req, issue_flags); break; case IORING_OP_TIMEOUT: - ret = io_timeout(req); + ret = io_timeout(req, issue_flags); break; case IORING_OP_TIMEOUT_REMOVE: - ret = io_timeout_remove(req); + ret = io_timeout_remove(req, issue_flags); break; case IORING_OP_ACCEPT: - ret = io_accept(req, force_nonblock, cs); + ret = io_accept(req, issue_flags); break; case IORING_OP_CONNECT: - ret = io_connect(req, force_nonblock, cs); + ret = io_connect(req, issue_flags); break; case IORING_OP_ASYNC_CANCEL: - ret = io_async_cancel(req); + ret = io_async_cancel(req, issue_flags); break; case IORING_OP_FALLOCATE: - ret = io_fallocate(req, force_nonblock); + ret = io_fallocate(req, issue_flags); break; case IORING_OP_OPENAT: - ret = io_openat(req, force_nonblock); + ret = io_openat(req, issue_flags); break; case IORING_OP_CLOSE: - ret = io_close(req, force_nonblock, cs); + ret = io_close(req, issue_flags); break; case IORING_OP_FILES_UPDATE: - ret = io_files_update(req, force_nonblock, cs); + ret = io_files_update(req, issue_flags); break; case IORING_OP_STATX: - ret = io_statx(req, force_nonblock); + ret = io_statx(req, issue_flags); break; case IORING_OP_FADVISE: - ret = io_fadvise(req, force_nonblock); + ret = io_fadvise(req, issue_flags); break; case IORING_OP_MADVISE: - ret = io_madvise(req, force_nonblock); + ret = io_madvise(req, issue_flags); break; case IORING_OP_OPENAT2: - ret = io_openat2(req, force_nonblock); + ret = io_openat2(req, issue_flags); break; case IORING_OP_EPOLL_CTL: - ret = io_epoll_ctl(req, force_nonblock, cs); + ret = io_epoll_ctl(req, issue_flags); break; case IORING_OP_SPLICE: - ret = io_splice(req, force_nonblock); + ret = io_splice(req, issue_flags); break; case IORING_OP_PROVIDE_BUFFERS: - ret = io_provide_buffers(req, force_nonblock, cs); + ret = io_provide_buffers(req, issue_flags); break; case IORING_OP_REMOVE_BUFFERS: - ret = io_remove_buffers(req, force_nonblock, cs); + ret = io_remove_buffers(req, issue_flags); break; case IORING_OP_TEE: - ret = io_tee(req, force_nonblock); + ret = io_tee(req, issue_flags); break; case IORING_OP_SHUTDOWN: - ret = io_shutdown(req, force_nonblock); + ret = io_shutdown(req, issue_flags); break; case IORING_OP_RENAMEAT: - ret = io_renameat(req, force_nonblock); + ret = io_renameat(req, issue_flags); break; case IORING_OP_UNLINKAT: - ret = io_unlinkat(req, force_nonblock); + ret = io_unlinkat(req, issue_flags); break; default: ret = -EINVAL; @@ -6305,7 +6400,7 @@ static int io_issue_sqe(struct io_kiocb *req, bool force_nonblock, return 0; } -static struct io_wq_work *io_wq_submit_work(struct io_wq_work *work) +static void io_wq_submit_work(struct io_wq_work *work) { struct io_kiocb *req = container_of(work, struct io_kiocb, work); struct io_kiocb *timeout; @@ -6315,15 +6410,12 @@ static struct io_wq_work *io_wq_submit_work(struct io_wq_work *work) if (timeout) io_queue_linked_timeout(timeout); - /* if NO_CANCEL is set, we must still run the work */ - if ((work->flags & (IO_WQ_WORK_CANCEL|IO_WQ_WORK_NO_CANCEL)) == - IO_WQ_WORK_CANCEL) { + if (work->flags & IO_WQ_WORK_CANCEL) ret = -ECANCELED; - } if (!ret) { do { - ret = io_issue_sqe(req, false, NULL); + ret = io_issue_sqe(req, 0); /* * We can get EAGAIN for polled IO even though we're * forcing a sync submission from here, since we can't @@ -6359,14 +6451,12 @@ static struct io_wq_work *io_wq_submit_work(struct io_wq_work *work) if (lock_ctx) mutex_unlock(&lock_ctx->uring_lock); } - - return io_steal_work(req); } static inline struct file *io_file_from_index(struct io_ring_ctx *ctx, int index) { - struct fixed_file_table *table; + struct fixed_rsrc_table *table; table = &ctx->file_data->table[index >> IORING_FILE_TABLE_SHIFT]; return table->files[index & IORING_FILE_TABLE_MASK]; @@ -6389,6 +6479,8 @@ static struct file *io_file_get(struct io_submit_state *state, file = __io_file_get(state, fd); } + if (file && unlikely(file->f_op == &io_uring_fops)) + io_req_track_inflight(req); return file; } @@ -6417,9 +6509,10 @@ static enum hrtimer_restart io_link_timeout_fn(struct hrtimer *timer) if (prev) { req_set_fail_links(prev); io_async_find_and_cancel(ctx, req, prev->user_data, -ETIME); - io_put_req(prev); + io_put_req_deferred(prev, 1); } else { - io_req_complete(req, -ETIME); + io_req_complete_post(req, -ETIME, 0); + io_put_req_deferred(req, 1); } return HRTIMER_NORESTART; } @@ -6465,27 +6558,21 @@ static struct io_kiocb *io_prep_linked_timeout(struct io_kiocb *req) return nxt; } -static void __io_queue_sqe(struct io_kiocb *req, struct io_comp_state *cs) +static void __io_queue_sqe(struct io_kiocb *req) { - struct io_kiocb *linked_timeout; + struct io_kiocb *linked_timeout = io_prep_linked_timeout(req); const struct cred *old_creds = NULL; int ret; -again: - linked_timeout = io_prep_linked_timeout(req); - if ((req->flags & REQ_F_WORK_INITIALIZED) && (req->work.flags & IO_WQ_WORK_CREDS) && - req->work.identity->creds != current_cred()) { - if (old_creds) - revert_creds(old_creds); - if (old_creds == req->work.identity->creds) - old_creds = NULL; /* restored original creds */ - else - old_creds = override_creds(req->work.identity->creds); - } + req->work.identity->creds != current_cred()) + old_creds = override_creds(req->work.identity->creds); - ret = io_issue_sqe(req, true, cs); + ret = io_issue_sqe(req, IO_URING_F_NONBLOCK|IO_URING_F_COMPLETE_DEFER); + + if (old_creds) + revert_creds(old_creds); /* * We async punt it if the file wasn't marked NOWAIT, or if the file @@ -6499,34 +6586,28 @@ again: */ io_queue_async_work(req); } - - if (linked_timeout) - io_queue_linked_timeout(linked_timeout); } else if (likely(!ret)) { /* drop submission reference */ - req = io_put_req_find_next(req); - if (linked_timeout) - io_queue_linked_timeout(linked_timeout); + if (req->flags & REQ_F_COMPLETE_INLINE) { + struct io_ring_ctx *ctx = req->ctx; + struct io_comp_state *cs = &ctx->submit_state.comp; - if (req) { - if (!(req->flags & REQ_F_FORCE_ASYNC)) - goto again; - io_queue_async_work(req); + cs->reqs[cs->nr++] = req; + if (cs->nr == ARRAY_SIZE(cs->reqs)) + io_submit_flush_completions(cs, ctx); + } else { + io_put_req(req); } } else { - /* un-prep timeout, so it'll be killed as any other linked */ - req->flags &= ~REQ_F_LINK_TIMEOUT; req_set_fail_links(req); io_put_req(req); io_req_complete(req, ret); } - - if (old_creds) - revert_creds(old_creds); + if (linked_timeout) + io_queue_linked_timeout(linked_timeout); } -static void io_queue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe, - struct io_comp_state *cs) +static void io_queue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe) { int ret; @@ -6551,18 +6632,17 @@ fail_req: if (unlikely(ret)) goto fail_req; } - __io_queue_sqe(req, cs); + __io_queue_sqe(req); } } -static inline void io_queue_link_head(struct io_kiocb *req, - struct io_comp_state *cs) +static inline void io_queue_link_head(struct io_kiocb *req) { if (unlikely(req->flags & REQ_F_FAIL_LINK)) { io_put_req(req); io_req_complete(req, -ECANCELED); } else - io_queue_sqe(req, NULL, cs); + io_queue_sqe(req, NULL); } struct io_submit_link { @@ -6571,7 +6651,7 @@ struct io_submit_link { }; static int io_submit_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe, - struct io_submit_link *link, struct io_comp_state *cs) + struct io_submit_link *link) { struct io_ring_ctx *ctx = req->ctx; int ret; @@ -6609,7 +6689,7 @@ static int io_submit_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe, /* last request of a link, enqueue the link */ if (!(req->flags & (REQ_F_LINK | REQ_F_HARDLINK))) { - io_queue_link_head(head, cs); + io_queue_link_head(head); link->head = NULL; } } else { @@ -6624,7 +6704,7 @@ static int io_submit_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe, link->head = req; link->last = req; } else { - io_queue_sqe(req, sqe, cs); + io_queue_sqe(req, sqe); } } @@ -6634,29 +6714,23 @@ static int io_submit_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe, /* * Batched submission is done, ensure local IO is flushed out. */ -static void io_submit_state_end(struct io_submit_state *state) +static void io_submit_state_end(struct io_submit_state *state, + struct io_ring_ctx *ctx) { - if (!list_empty(&state->comp.list)) - io_submit_flush_completions(&state->comp); + if (state->comp.nr) + io_submit_flush_completions(&state->comp, ctx); if (state->plug_started) blk_finish_plug(&state->plug); io_state_file_put(state); - if (state->free_reqs) - kmem_cache_free_bulk(req_cachep, state->free_reqs, state->reqs); } /* * Start submission side cache. */ static void io_submit_state_start(struct io_submit_state *state, - struct io_ring_ctx *ctx, unsigned int max_ios) + unsigned int max_ios) { state->plug_started = false; - state->comp.nr = 0; - INIT_LIST_HEAD(&state->comp.list); - state->comp.ctx = ctx; - state->free_reqs = 0; - state->file_refs = 0; state->ios_left = max_ios; } @@ -6693,7 +6767,7 @@ static const struct io_uring_sqe *io_get_sqe(struct io_ring_ctx *ctx) * 2) allows the kernel side to track the head on its own, even * though the application is the one updating it. */ - head = READ_ONCE(sq_array[ctx->cached_sq_head & ctx->sq_mask]); + head = READ_ONCE(sq_array[ctx->cached_sq_head++ & ctx->sq_mask]); if (likely(head < ctx->sq_entries)) return &ctx->sq_sqes[head]; @@ -6703,11 +6777,6 @@ static const struct io_uring_sqe *io_get_sqe(struct io_ring_ctx *ctx) return NULL; } -static inline void io_consume_sqe(struct io_ring_ctx *ctx) -{ - ctx->cached_sq_head++; -} - /* * Check SQE restrictions (opcode and flags). * @@ -6739,36 +6808,36 @@ static inline bool io_check_restriction(struct io_ring_ctx *ctx, IOSQE_BUFFER_SELECT) static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, - const struct io_uring_sqe *sqe, - struct io_submit_state *state) + const struct io_uring_sqe *sqe) { + struct io_submit_state *state; unsigned int sqe_flags; - int id, ret; + int id, ret = 0; req->opcode = READ_ONCE(sqe->opcode); + /* same numerical values with corresponding REQ_F_*, safe to copy */ + req->flags = sqe_flags = READ_ONCE(sqe->flags); req->user_data = READ_ONCE(sqe->user_data); req->async_data = NULL; req->file = NULL; req->ctx = ctx; - req->flags = 0; req->link = NULL; - req->fixed_file_refs = NULL; + req->fixed_rsrc_refs = NULL; /* one is dropped after submission, the other at completion */ refcount_set(&req->refs, 2); req->task = current; req->result = 0; + /* enforce forwards compatibility on users */ + if (unlikely(sqe_flags & ~SQE_VALID_FLAGS)) + return -EINVAL; + if (unlikely(req->opcode >= IORING_OP_LAST)) return -EINVAL; if (unlikely(io_sq_thread_acquire_mm_files(ctx, req))) return -EFAULT; - sqe_flags = READ_ONCE(sqe->flags); - /* enforce forwards compatibility on users */ - if (unlikely(sqe_flags & ~SQE_VALID_FLAGS)) - return -EINVAL; - if (unlikely(!io_check_restriction(ctx, req, sqe_flags))) return -EACCES; @@ -6791,8 +6860,7 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, req->work.flags |= IO_WQ_WORK_CREDS; } - /* same numerical values with corresponding REQ_F_*, safe to copy */ - req->flags |= sqe_flags; + state = &ctx->submit_state; /* * Plug now if we have more than 1 IO left after this, and the target @@ -6804,13 +6872,11 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, state->plug_started = true; } - ret = 0; if (io_op_defs[req->opcode].needs_file) { bool fixed = req->flags & REQ_F_FIXED_FILE; req->file = io_file_get(state, req, READ_ONCE(sqe->fd), fixed); - if (unlikely(!req->file && - !io_op_defs[req->opcode].needs_file_no_error)) + if (unlikely(!req->file)) ret = -EBADF; } @@ -6820,13 +6886,12 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr) { - struct io_submit_state state; struct io_submit_link link; int i, submitted = 0; /* if we have a backlog and couldn't flush it all, return BUSY */ if (test_bit(0, &ctx->sq_check_overflow)) { - if (!io_cqring_overflow_flush(ctx, false, NULL, NULL)) + if (!__io_cqring_overflow_flush(ctx, false, NULL, NULL)) return -EBUSY; } @@ -6839,7 +6904,7 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr) percpu_counter_add(¤t->io_uring->inflight, nr); refcount_add(nr, ¤t->usage); - io_submit_state_start(&state, ctx, nr); + io_submit_state_start(&ctx->submit_state, nr); link.head = NULL; for (i = 0; i < nr; i++) { @@ -6847,22 +6912,21 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr) struct io_kiocb *req; int err; - sqe = io_get_sqe(ctx); - if (unlikely(!sqe)) { - io_consume_sqe(ctx); - break; - } - req = io_alloc_req(ctx, &state); + req = io_alloc_req(ctx); if (unlikely(!req)) { if (!submitted) submitted = -EAGAIN; break; } - io_consume_sqe(ctx); + sqe = io_get_sqe(ctx); + if (unlikely(!sqe)) { + kmem_cache_free(req_cachep, req); + break; + } /* will complete beyond this point, count as submitted */ submitted++; - err = io_init_req(ctx, req, sqe, &state); + err = io_init_req(ctx, req, sqe); if (unlikely(err)) { fail_req: io_put_req(req); @@ -6871,8 +6935,8 @@ fail_req: } trace_io_uring_submit_sqe(ctx, req->opcode, req->user_data, - true, io_async_submit(ctx)); - err = io_submit_sqe(req, sqe, &link, &state.comp); + true, ctx->flags & IORING_SETUP_SQPOLL); + err = io_submit_sqe(req, sqe, &link); if (err) goto fail_req; } @@ -6887,8 +6951,8 @@ fail_req: put_task_struct_many(current, unused); } if (link.head) - io_queue_link_head(link.head, &state.comp); - io_submit_state_end(&state); + io_queue_link_head(link.head); + io_submit_state_end(&ctx->submit_state, ctx); /* Commit SQ ring head once we've consumed and submitted all SQEs */ io_commit_sqring(ctx); @@ -6928,7 +6992,8 @@ static int __io_sq_thread(struct io_ring_ctx *ctx, bool cap_entries) if (!list_empty(&ctx->iopoll_list)) io_do_iopoll(ctx, &nr_events, 0); - if (to_submit && likely(!percpu_ref_is_dying(&ctx->refs))) + if (to_submit && !ctx->sqo_dead && + likely(!percpu_ref_is_dying(&ctx->refs))) ret = io_submit_sqes(ctx, to_submit); mutex_unlock(&ctx->uring_lock); } @@ -7029,15 +7094,13 @@ static int io_sq_thread(void *data) if (sqt_spin || !time_after(jiffies, timeout)) { io_run_task_work(); + io_sq_thread_drop_mm_files(); cond_resched(); if (sqt_spin) timeout = jiffies + sqd->sq_thread_idle; continue; } - if (kthread_should_park()) - continue; - needs_sched = true; prepare_to_wait(&sqd->wait, &wait, TASK_INTERRUPTIBLE); list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) { @@ -7052,7 +7115,7 @@ static int io_sq_thread(void *data) } } - if (needs_sched) { + if (needs_sched && !kthread_should_park()) { list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) io_ring_set_wakeup_flag(ctx); @@ -7066,6 +7129,7 @@ static int io_sq_thread(void *data) } io_run_task_work(); + io_sq_thread_drop_mm_files(); if (cur_css) io_sq_thread_unassociate_blkcg(); @@ -7089,7 +7153,7 @@ struct io_wait_queue { unsigned nr_timeouts; }; -static inline bool io_should_wake(struct io_wait_queue *iowq, bool noflush) +static inline bool io_should_wake(struct io_wait_queue *iowq) { struct io_ring_ctx *ctx = iowq->ctx; @@ -7098,7 +7162,7 @@ static inline bool io_should_wake(struct io_wait_queue *iowq, bool noflush) * started waiting. For timeouts, we always want to return to userspace, * regardless of event count. */ - return io_cqring_events(ctx, noflush) >= iowq->to_wait || + return io_cqring_events(ctx) >= iowq->to_wait || atomic_read(&ctx->cq_timeouts) != iowq->nr_timeouts; } @@ -7108,11 +7172,13 @@ static int io_wake_function(struct wait_queue_entry *curr, unsigned int mode, struct io_wait_queue *iowq = container_of(curr, struct io_wait_queue, wq); - /* use noflush == true, as we can't safely rely on locking context */ - if (!io_should_wake(iowq, true)) - return -1; - - return autoremove_wake_function(curr, mode, wake_flags, key); + /* + * Cannot safely flush overflowed CQEs from here, ensure we wake up + * the task, and the next invocation will do it. + */ + if (io_should_wake(iowq) || test_bit(0, &iowq->ctx->cq_check_overflow)) + return autoremove_wake_function(curr, mode, wake_flags, key); + return -1; } static int io_run_task_work_sig(void) @@ -7126,6 +7192,25 @@ static int io_run_task_work_sig(void) return -EINTR; } +/* when returns >0, the caller should retry */ +static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx, + struct io_wait_queue *iowq, + signed long *timeout) +{ + int ret; + + /* make sure we run task_work before checking for signals */ + ret = io_run_task_work_sig(); + if (ret || io_should_wake(iowq)) + return ret; + /* let the caller flush overflows, retry */ + if (test_bit(0, &ctx->cq_check_overflow)) + return 1; + + *timeout = schedule_timeout(*timeout); + return !*timeout ? -ETIME : 1; +} + /* * Wait until events become available, if we don't already have some. The * application must reap them itself, as they reside on the shared cq ring. @@ -7144,12 +7229,12 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, .to_wait = min_events, }; struct io_rings *rings = ctx->rings; - struct timespec64 ts; - signed long timeout = 0; - int ret = 0; + signed long timeout = MAX_SCHEDULE_TIMEOUT; + int ret; do { - if (io_cqring_events(ctx, false) >= min_events) + io_cqring_overflow_flush(ctx, false, NULL, NULL); + if (io_cqring_events(ctx) >= min_events) return 0; if (!io_run_task_work()) break; @@ -7169,6 +7254,8 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, } if (uts) { + struct timespec64 ts; + if (get_timespec64(&ts, uts)) return -EFAULT; timeout = timespec64_to_jiffies(&ts); @@ -7177,27 +7264,12 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, iowq.nr_timeouts = atomic_read(&ctx->cq_timeouts); trace_io_uring_cqring_wait(ctx, min_events); do { + io_cqring_overflow_flush(ctx, false, NULL, NULL); prepare_to_wait_exclusive(&ctx->wait, &iowq.wq, TASK_INTERRUPTIBLE); - /* make sure we run task_work before checking for signals */ - ret = io_run_task_work_sig(); - if (ret > 0) - continue; - else if (ret < 0) - break; - if (io_should_wake(&iowq, false)) - break; - if (uts) { - timeout = schedule_timeout(timeout); - if (timeout == 0) { - ret = -ETIME; - break; - } - } else { - schedule(); - } - } while (1); - finish_wait(&ctx->wait, &iowq.wq); + ret = io_cqring_wait_schedule(ctx, &iowq, &timeout); + finish_wait(&ctx->wait, &iowq.wq); + } while (ret > 0); restore_saved_sigmask_unless(ret == -EINTR); @@ -7227,47 +7299,52 @@ static void __io_sqe_files_unregister(struct io_ring_ctx *ctx) #endif } -static void io_file_ref_kill(struct percpu_ref *ref) +static void io_rsrc_data_ref_zero(struct percpu_ref *ref) { - struct fixed_file_data *data; + struct fixed_rsrc_data *data; - data = container_of(ref, struct fixed_file_data, refs); + data = container_of(ref, struct fixed_rsrc_data, refs); complete(&data->done); } -static void io_sqe_files_set_node(struct fixed_file_data *file_data, - struct fixed_file_ref_node *ref_node) +static inline void io_rsrc_ref_lock(struct io_ring_ctx *ctx) { - spin_lock_bh(&file_data->lock); - file_data->node = ref_node; - list_add_tail(&ref_node->node, &file_data->ref_list); - spin_unlock_bh(&file_data->lock); - percpu_ref_get(&file_data->refs); + spin_lock_bh(&ctx->rsrc_ref_lock); } -static int io_sqe_files_unregister(struct io_ring_ctx *ctx) +static inline void io_rsrc_ref_unlock(struct io_ring_ctx *ctx) { - struct fixed_file_data *data = ctx->file_data; - struct fixed_file_ref_node *backup_node, *ref_node = NULL; - unsigned nr_tables, i; - int ret; + spin_unlock_bh(&ctx->rsrc_ref_lock); +} - if (!data) - return -ENXIO; - backup_node = alloc_fixed_file_ref_node(ctx); - if (!backup_node) - return -ENOMEM; +static void io_sqe_rsrc_set_node(struct io_ring_ctx *ctx, + struct fixed_rsrc_data *rsrc_data, + struct fixed_rsrc_ref_node *ref_node) +{ + io_rsrc_ref_lock(ctx); + rsrc_data->node = ref_node; + list_add_tail(&ref_node->node, &ctx->rsrc_ref_list); + io_rsrc_ref_unlock(ctx); + percpu_ref_get(&rsrc_data->refs); +} - spin_lock_bh(&data->lock); +static int io_rsrc_ref_quiesce(struct fixed_rsrc_data *data, + struct io_ring_ctx *ctx, + struct fixed_rsrc_ref_node *backup_node) +{ + struct fixed_rsrc_ref_node *ref_node; + int ret; + + io_rsrc_ref_lock(ctx); ref_node = data->node; - spin_unlock_bh(&data->lock); + io_rsrc_ref_unlock(ctx); if (ref_node) percpu_ref_kill(&ref_node->refs); percpu_ref_kill(&data->refs); /* wait for all refs nodes to complete */ - flush_delayed_work(&ctx->file_put_work); + flush_delayed_work(&ctx->rsrc_put_work); do { ret = wait_for_completion_interruptible(&data->done); if (!ret) @@ -7276,21 +7353,65 @@ static int io_sqe_files_unregister(struct io_ring_ctx *ctx) if (ret < 0) { percpu_ref_resurrect(&data->refs); reinit_completion(&data->done); - io_sqe_files_set_node(data, backup_node); + io_sqe_rsrc_set_node(ctx, data, backup_node); return ret; } } while (1); + destroy_fixed_rsrc_ref_node(backup_node); + return 0; +} + +static struct fixed_rsrc_data *alloc_fixed_rsrc_data(struct io_ring_ctx *ctx) +{ + struct fixed_rsrc_data *data; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return NULL; + + if (percpu_ref_init(&data->refs, io_rsrc_data_ref_zero, + PERCPU_REF_ALLOW_REINIT, GFP_KERNEL)) { + kfree(data); + return NULL; + } + data->ctx = ctx; + init_completion(&data->done); + return data; +} + +static void free_fixed_rsrc_data(struct fixed_rsrc_data *data) +{ + percpu_ref_exit(&data->refs); + kfree(data->table); + kfree(data); +} + +static int io_sqe_files_unregister(struct io_ring_ctx *ctx) +{ + struct fixed_rsrc_data *data = ctx->file_data; + struct fixed_rsrc_ref_node *backup_node; + unsigned nr_tables, i; + int ret; + + if (!data) + return -ENXIO; + backup_node = alloc_fixed_rsrc_ref_node(ctx); + if (!backup_node) + return -ENOMEM; + init_fixed_file_ref_node(ctx, backup_node); + + ret = io_rsrc_ref_quiesce(data, ctx, backup_node); + if (ret) + return ret; + __io_sqe_files_unregister(ctx); nr_tables = DIV_ROUND_UP(ctx->nr_user_files, IORING_MAX_FILES_TABLE); for (i = 0; i < nr_tables; i++) kfree(data->table[i].files); - kfree(data->table); - percpu_ref_exit(&data->refs); - kfree(data); + free_fixed_rsrc_data(data); ctx->file_data = NULL; ctx->nr_user_files = 0; - destroy_fixed_file_ref_node(backup_node); return 0; } @@ -7513,13 +7634,13 @@ static int io_sqe_files_scm(struct io_ring_ctx *ctx) } #endif -static int io_sqe_alloc_file_tables(struct fixed_file_data *file_data, +static int io_sqe_alloc_file_tables(struct fixed_rsrc_data *file_data, unsigned nr_tables, unsigned nr_files) { int i; for (i = 0; i < nr_tables; i++) { - struct fixed_file_table *table = &file_data->table[i]; + struct fixed_rsrc_table *table = &file_data->table[i]; unsigned this_files; this_files = min(nr_files, IORING_MAX_FILES_TABLE); @@ -7534,14 +7655,15 @@ static int io_sqe_alloc_file_tables(struct fixed_file_data *file_data, return 0; for (i = 0; i < nr_tables; i++) { - struct fixed_file_table *table = &file_data->table[i]; + struct fixed_rsrc_table *table = &file_data->table[i]; kfree(table->files); } return 1; } -static void io_ring_file_put(struct io_ring_ctx *ctx, struct file *file) +static void io_ring_file_put(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc) { + struct file *file = prsrc->file; #if defined(CONFIG_UNIX) struct sock *sock = ctx->ring_sock->sk; struct sk_buff_head list, *head = &sock->sk_receive_queue; @@ -7602,108 +7724,119 @@ static void io_ring_file_put(struct io_ring_ctx *ctx, struct file *file) #endif } -struct io_file_put { - struct list_head list; - struct file *file; -}; - -static void __io_file_put_work(struct fixed_file_ref_node *ref_node) +static void __io_rsrc_put_work(struct fixed_rsrc_ref_node *ref_node) { - struct fixed_file_data *file_data = ref_node->file_data; - struct io_ring_ctx *ctx = file_data->ctx; - struct io_file_put *pfile, *tmp; + struct fixed_rsrc_data *rsrc_data = ref_node->rsrc_data; + struct io_ring_ctx *ctx = rsrc_data->ctx; + struct io_rsrc_put *prsrc, *tmp; - list_for_each_entry_safe(pfile, tmp, &ref_node->file_list, list) { - list_del(&pfile->list); - io_ring_file_put(ctx, pfile->file); - kfree(pfile); + list_for_each_entry_safe(prsrc, tmp, &ref_node->rsrc_list, list) { + list_del(&prsrc->list); + ref_node->rsrc_put(ctx, prsrc); + kfree(prsrc); } percpu_ref_exit(&ref_node->refs); kfree(ref_node); - percpu_ref_put(&file_data->refs); + percpu_ref_put(&rsrc_data->refs); } -static void io_file_put_work(struct work_struct *work) +static void io_rsrc_put_work(struct work_struct *work) { struct io_ring_ctx *ctx; struct llist_node *node; - ctx = container_of(work, struct io_ring_ctx, file_put_work.work); - node = llist_del_all(&ctx->file_put_llist); + ctx = container_of(work, struct io_ring_ctx, rsrc_put_work.work); + node = llist_del_all(&ctx->rsrc_put_llist); while (node) { - struct fixed_file_ref_node *ref_node; + struct fixed_rsrc_ref_node *ref_node; struct llist_node *next = node->next; - ref_node = llist_entry(node, struct fixed_file_ref_node, llist); - __io_file_put_work(ref_node); + ref_node = llist_entry(node, struct fixed_rsrc_ref_node, llist); + __io_rsrc_put_work(ref_node); node = next; } } -static void io_file_data_ref_zero(struct percpu_ref *ref) +static struct file **io_fixed_file_slot(struct fixed_rsrc_data *file_data, + unsigned i) { - struct fixed_file_ref_node *ref_node; - struct fixed_file_data *data; + struct fixed_rsrc_table *table; + + table = &file_data->table[i >> IORING_FILE_TABLE_SHIFT]; + return &table->files[i & IORING_FILE_TABLE_MASK]; +} + +static void io_rsrc_node_ref_zero(struct percpu_ref *ref) +{ + struct fixed_rsrc_ref_node *ref_node; + struct fixed_rsrc_data *data; struct io_ring_ctx *ctx; bool first_add = false; int delay = HZ; - ref_node = container_of(ref, struct fixed_file_ref_node, refs); - data = ref_node->file_data; + ref_node = container_of(ref, struct fixed_rsrc_ref_node, refs); + data = ref_node->rsrc_data; ctx = data->ctx; - spin_lock_bh(&data->lock); + io_rsrc_ref_lock(ctx); ref_node->done = true; - while (!list_empty(&data->ref_list)) { - ref_node = list_first_entry(&data->ref_list, - struct fixed_file_ref_node, node); + while (!list_empty(&ctx->rsrc_ref_list)) { + ref_node = list_first_entry(&ctx->rsrc_ref_list, + struct fixed_rsrc_ref_node, node); /* recycle ref nodes in order */ if (!ref_node->done) break; list_del(&ref_node->node); - first_add |= llist_add(&ref_node->llist, &ctx->file_put_llist); + first_add |= llist_add(&ref_node->llist, &ctx->rsrc_put_llist); } - spin_unlock_bh(&data->lock); + io_rsrc_ref_unlock(ctx); if (percpu_ref_is_dying(&data->refs)) delay = 0; if (!delay) - mod_delayed_work(system_wq, &ctx->file_put_work, 0); + mod_delayed_work(system_wq, &ctx->rsrc_put_work, 0); else if (first_add) - queue_delayed_work(system_wq, &ctx->file_put_work, delay); + queue_delayed_work(system_wq, &ctx->rsrc_put_work, delay); } -static struct fixed_file_ref_node *alloc_fixed_file_ref_node( +static struct fixed_rsrc_ref_node *alloc_fixed_rsrc_ref_node( struct io_ring_ctx *ctx) { - struct fixed_file_ref_node *ref_node; + struct fixed_rsrc_ref_node *ref_node; ref_node = kzalloc(sizeof(*ref_node), GFP_KERNEL); if (!ref_node) - return ERR_PTR(-ENOMEM); + return NULL; - if (percpu_ref_init(&ref_node->refs, io_file_data_ref_zero, + if (percpu_ref_init(&ref_node->refs, io_rsrc_node_ref_zero, 0, GFP_KERNEL)) { kfree(ref_node); - return ERR_PTR(-ENOMEM); + return NULL; } INIT_LIST_HEAD(&ref_node->node); - INIT_LIST_HEAD(&ref_node->file_list); - ref_node->file_data = ctx->file_data; + INIT_LIST_HEAD(&ref_node->rsrc_list); ref_node->done = false; return ref_node; } -static void destroy_fixed_file_ref_node(struct fixed_file_ref_node *ref_node) +static void init_fixed_file_ref_node(struct io_ring_ctx *ctx, + struct fixed_rsrc_ref_node *ref_node) +{ + ref_node->rsrc_data = ctx->file_data; + ref_node->rsrc_put = io_ring_file_put; +} + +static void destroy_fixed_rsrc_ref_node(struct fixed_rsrc_ref_node *ref_node) { percpu_ref_exit(&ref_node->refs); kfree(ref_node); } + static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, unsigned nr_args) { @@ -7711,8 +7844,8 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, unsigned nr_tables, i; struct file *file; int fd, ret = -ENOMEM; - struct fixed_file_ref_node *ref_node; - struct fixed_file_data *file_data; + struct fixed_rsrc_ref_node *ref_node; + struct fixed_rsrc_data *file_data; if (ctx->file_data) return -EBUSY; @@ -7721,13 +7854,10 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, if (nr_args > IORING_MAX_FIXED_FILES) return -EMFILE; - file_data = kzalloc(sizeof(*ctx->file_data), GFP_KERNEL); + file_data = alloc_fixed_rsrc_data(ctx); if (!file_data) return -ENOMEM; - file_data->ctx = ctx; - init_completion(&file_data->done); - INIT_LIST_HEAD(&file_data->ref_list); - spin_lock_init(&file_data->lock); + ctx->file_data = file_data; nr_tables = DIV_ROUND_UP(nr_args, IORING_MAX_FILES_TABLE); file_data->table = kcalloc(nr_tables, sizeof(*file_data->table), @@ -7735,18 +7865,10 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, if (!file_data->table) goto out_free; - if (percpu_ref_init(&file_data->refs, io_file_ref_kill, - PERCPU_REF_ALLOW_REINIT, GFP_KERNEL)) - goto out_free; - if (io_sqe_alloc_file_tables(file_data, nr_tables, nr_args)) - goto out_ref; - ctx->file_data = file_data; + goto out_free; for (i = 0; i < nr_args; i++, ctx->nr_user_files++) { - struct fixed_file_table *table; - unsigned index; - if (copy_from_user(&fd, &fds[i], sizeof(fd))) { ret = -EFAULT; goto out_fput; @@ -7771,9 +7893,7 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, fput(file); goto out_fput; } - table = &file_data->table[i >> IORING_FILE_TABLE_SHIFT]; - index = i & IORING_FILE_TABLE_MASK; - table->files[index] = file; + *io_fixed_file_slot(file_data, i) = file; } ret = io_sqe_files_scm(ctx); @@ -7782,13 +7902,14 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, return ret; } - ref_node = alloc_fixed_file_ref_node(ctx); - if (IS_ERR(ref_node)) { + ref_node = alloc_fixed_rsrc_ref_node(ctx); + if (!ref_node) { io_sqe_files_unregister(ctx); - return PTR_ERR(ref_node); + return -ENOMEM; } + init_fixed_file_ref_node(ctx, ref_node); - io_sqe_files_set_node(file_data, ref_node); + io_sqe_rsrc_set_node(ctx, file_data, ref_node); return ret; out_fput: for (i = 0; i < ctx->nr_user_files; i++) { @@ -7799,11 +7920,8 @@ out_fput: for (i = 0; i < nr_tables; i++) kfree(file_data->table[i].files); ctx->nr_user_files = 0; -out_ref: - percpu_ref_exit(&file_data->refs); out_free: - kfree(file_data->table); - kfree(file_data); + free_fixed_rsrc_data(ctx->file_data); ctx->file_data = NULL; return ret; } @@ -7851,29 +7969,34 @@ static int io_sqe_file_register(struct io_ring_ctx *ctx, struct file *file, #endif } -static int io_queue_file_removal(struct fixed_file_data *data, - struct file *file) +static int io_queue_rsrc_removal(struct fixed_rsrc_data *data, void *rsrc) { - struct io_file_put *pfile; - struct fixed_file_ref_node *ref_node = data->node; + struct io_rsrc_put *prsrc; + struct fixed_rsrc_ref_node *ref_node = data->node; - pfile = kzalloc(sizeof(*pfile), GFP_KERNEL); - if (!pfile) + prsrc = kzalloc(sizeof(*prsrc), GFP_KERNEL); + if (!prsrc) return -ENOMEM; - pfile->file = file; - list_add(&pfile->list, &ref_node->file_list); + prsrc->rsrc = rsrc; + list_add(&prsrc->list, &ref_node->rsrc_list); return 0; } +static inline int io_queue_file_removal(struct fixed_rsrc_data *data, + struct file *file) +{ + return io_queue_rsrc_removal(data, (void *)file); +} + static int __io_sqe_files_update(struct io_ring_ctx *ctx, - struct io_uring_files_update *up, + struct io_uring_rsrc_update *up, unsigned nr_args) { - struct fixed_file_data *data = ctx->file_data; - struct fixed_file_ref_node *ref_node; - struct file *file; + struct fixed_rsrc_data *data = ctx->file_data; + struct fixed_rsrc_ref_node *ref_node; + struct file *file, **file_slot; __s32 __user *fds; int fd, i, err; __u32 done; @@ -7884,30 +8007,29 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, if (done > ctx->nr_user_files) return -EINVAL; - ref_node = alloc_fixed_file_ref_node(ctx); - if (IS_ERR(ref_node)) - return PTR_ERR(ref_node); - - done = 0; - fds = u64_to_user_ptr(up->fds); - while (nr_args) { - struct fixed_file_table *table; - unsigned index; + ref_node = alloc_fixed_rsrc_ref_node(ctx); + if (!ref_node) + return -ENOMEM; + init_fixed_file_ref_node(ctx, ref_node); + fds = u64_to_user_ptr(up->data); + for (done = 0; done < nr_args; done++) { err = 0; if (copy_from_user(&fd, &fds[done], sizeof(fd))) { err = -EFAULT; break; } - i = array_index_nospec(up->offset, ctx->nr_user_files); - table = &ctx->file_data->table[i >> IORING_FILE_TABLE_SHIFT]; - index = i & IORING_FILE_TABLE_MASK; - if (table->files[index]) { - file = table->files[index]; - err = io_queue_file_removal(data, file); + if (fd == IORING_REGISTER_FILES_SKIP) + continue; + + i = array_index_nospec(up->offset + done, ctx->nr_user_files); + file_slot = io_fixed_file_slot(ctx->file_data, i); + + if (*file_slot) { + err = io_queue_file_removal(data, *file_slot); if (err) break; - table->files[index] = NULL; + *file_slot = NULL; needs_switch = true; } if (fd != -1) { @@ -7929,24 +8051,21 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, err = -EBADF; break; } - table->files[index] = file; + *file_slot = file; err = io_sqe_file_register(ctx, file, i); if (err) { - table->files[index] = NULL; + *file_slot = NULL; fput(file); break; } } - nr_args--; - done++; - up->offset++; } if (needs_switch) { percpu_ref_kill(&data->node->refs); - io_sqe_files_set_node(data, ref_node); + io_sqe_rsrc_set_node(ctx, data, ref_node); } else - destroy_fixed_file_ref_node(ref_node); + destroy_fixed_rsrc_ref_node(ref_node); return done ? done : err; } @@ -7954,7 +8073,7 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, static int io_sqe_files_update(struct io_ring_ctx *ctx, void __user *arg, unsigned nr_args) { - struct io_uring_files_update up; + struct io_uring_rsrc_update up; if (!ctx->file_data) return -ENXIO; @@ -7968,12 +8087,12 @@ static int io_sqe_files_update(struct io_ring_ctx *ctx, void __user *arg, return __io_sqe_files_update(ctx, &up, nr_args); } -static void io_free_work(struct io_wq_work *work) +static struct io_wq_work *io_free_work(struct io_wq_work *work) { struct io_kiocb *req = container_of(work, struct io_kiocb, work); - /* Consider that io_steal_work() relies on this ref */ - io_put_req(req); + req = io_put_req_find_next(req); + return req ? &req->work : NULL; } static int io_init_wq_offload(struct io_ring_ctx *ctx, @@ -8046,6 +8165,10 @@ static int io_uring_alloc_task_context(struct task_struct *task) io_init_identity(&tctx->__identity); tctx->identity = &tctx->__identity; task->io_uring = tctx; + spin_lock_init(&tctx->task_lock); + INIT_WQ_LIST(&tctx->task_list); + tctx->task_state = 0; + init_task_work(&tctx->task_work, tctx_task_work); return 0; } @@ -8167,25 +8290,16 @@ static inline int __io_account_mem(struct user_struct *user, return 0; } -static void io_unaccount_mem(struct io_ring_ctx *ctx, unsigned long nr_pages, - enum io_mem_account acct) +static void io_unaccount_mem(struct io_ring_ctx *ctx, unsigned long nr_pages) { if (ctx->limit_mem) __io_unaccount_mem(ctx->user, nr_pages); - if (ctx->mm_account) { - if (acct == ACCT_LOCKED) { - mmap_write_lock(ctx->mm_account); - ctx->mm_account->locked_vm -= nr_pages; - mmap_write_unlock(ctx->mm_account); - }else if (acct == ACCT_PINNED) { - atomic64_sub(nr_pages, &ctx->mm_account->pinned_vm); - } - } + if (ctx->mm_account) + atomic64_sub(nr_pages, &ctx->mm_account->pinned_vm); } -static int io_account_mem(struct io_ring_ctx *ctx, unsigned long nr_pages, - enum io_mem_account acct) +static int io_account_mem(struct io_ring_ctx *ctx, unsigned long nr_pages) { int ret; @@ -8195,15 +8309,8 @@ static int io_account_mem(struct io_ring_ctx *ctx, unsigned long nr_pages, return ret; } - if (ctx->mm_account) { - if (acct == ACCT_LOCKED) { - mmap_write_lock(ctx->mm_account); - ctx->mm_account->locked_vm += nr_pages; - mmap_write_unlock(ctx->mm_account); - } else if (acct == ACCT_PINNED) { - atomic64_add(nr_pages, &ctx->mm_account->pinned_vm); - } - } + if (ctx->mm_account) + atomic64_add(nr_pages, &ctx->mm_account->pinned_vm); return 0; } @@ -8223,7 +8330,7 @@ static void io_mem_free(void *ptr) static void *io_mem_alloc(size_t size) { gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN | __GFP_COMP | - __GFP_NORETRY; + __GFP_NORETRY | __GFP_ACCOUNT; return (void *) __get_free_pages(gfp_flags, get_order(size)); } @@ -8257,19 +8364,7 @@ static unsigned long rings_size(unsigned sq_entries, unsigned cq_entries, return off; } -static unsigned long ring_pages(unsigned sq_entries, unsigned cq_entries) -{ - size_t pages; - - pages = (size_t)1 << get_order( - rings_size(sq_entries, cq_entries, NULL)); - pages += (size_t)1 << get_order( - array_size(sizeof(struct io_uring_sqe), sq_entries)); - - return pages; -} - -static int io_sqe_buffer_unregister(struct io_ring_ctx *ctx) +static int io_sqe_buffers_unregister(struct io_ring_ctx *ctx) { int i, j; @@ -8283,7 +8378,7 @@ static int io_sqe_buffer_unregister(struct io_ring_ctx *ctx) unpin_user_page(imu->bvec[j].bv_page); if (imu->acct_pages) - io_unaccount_mem(ctx, imu->acct_pages, ACCT_PINNED); + io_unaccount_mem(ctx, imu->acct_pages); kvfree(imu->bvec); imu->nr_bvecs = 0; } @@ -8381,21 +8476,105 @@ static int io_buffer_account_pin(struct io_ring_ctx *ctx, struct page **pages, if (!imu->acct_pages) return 0; - ret = io_account_mem(ctx, imu->acct_pages, ACCT_PINNED); + ret = io_account_mem(ctx, imu->acct_pages); if (ret) imu->acct_pages = 0; return ret; } -static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg, - unsigned nr_args) +static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov, + struct io_mapped_ubuf *imu, + struct page **last_hpage) { struct vm_area_struct **vmas = NULL; struct page **pages = NULL; - struct page *last_hpage = NULL; - int i, j, got_pages = 0; - int ret = -EINVAL; + unsigned long off, start, end, ubuf; + size_t size; + int ret, pret, nr_pages, i; + + ubuf = (unsigned long) iov->iov_base; + end = (ubuf + iov->iov_len + PAGE_SIZE - 1) >> PAGE_SHIFT; + start = ubuf >> PAGE_SHIFT; + nr_pages = end - start; + + ret = -ENOMEM; + + pages = kvmalloc_array(nr_pages, sizeof(struct page *), GFP_KERNEL); + if (!pages) + goto done; + + vmas = kvmalloc_array(nr_pages, sizeof(struct vm_area_struct *), + GFP_KERNEL); + if (!vmas) + goto done; + + imu->bvec = kvmalloc_array(nr_pages, sizeof(struct bio_vec), + GFP_KERNEL); + if (!imu->bvec) + goto done; + + ret = 0; + mmap_read_lock(current->mm); + pret = pin_user_pages(ubuf, nr_pages, FOLL_WRITE | FOLL_LONGTERM, + pages, vmas); + if (pret == nr_pages) { + /* don't support file backed memory */ + for (i = 0; i < nr_pages; i++) { + struct vm_area_struct *vma = vmas[i]; + + if (vma->vm_file && + !is_file_hugepages(vma->vm_file)) { + ret = -EOPNOTSUPP; + break; + } + } + } else { + ret = pret < 0 ? pret : -EFAULT; + } + mmap_read_unlock(current->mm); + if (ret) { + /* + * if we did partial map, or found file backed vmas, + * release any pages we did get + */ + if (pret > 0) + unpin_user_pages(pages, pret); + kvfree(imu->bvec); + goto done; + } + ret = io_buffer_account_pin(ctx, pages, pret, imu, last_hpage); + if (ret) { + unpin_user_pages(pages, pret); + kvfree(imu->bvec); + goto done; + } + + off = ubuf & ~PAGE_MASK; + size = iov->iov_len; + for (i = 0; i < nr_pages; i++) { + size_t vec_len; + + vec_len = min_t(size_t, size, PAGE_SIZE - off); + imu->bvec[i].bv_page = pages[i]; + imu->bvec[i].bv_len = vec_len; + imu->bvec[i].bv_offset = off; + off = 0; + size -= vec_len; + } + /* store original address for later verification */ + imu->ubuf = ubuf; + imu->len = iov->iov_len; + imu->nr_bvecs = nr_pages; + ret = 0; +done: + kvfree(pages); + kvfree(vmas); + return ret; +} + +static int io_buffers_map_alloc(struct io_ring_ctx *ctx, unsigned int nr_args) +{ if (ctx->user_bufs) return -EBUSY; if (!nr_args || nr_args > UIO_MAXIOV) @@ -8406,121 +8585,58 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg, if (!ctx->user_bufs) return -ENOMEM; - for (i = 0; i < nr_args; i++) { - struct io_mapped_ubuf *imu = &ctx->user_bufs[i]; - unsigned long off, start, end, ubuf; - int pret, nr_pages; - struct iovec iov; - size_t size; + return 0; +} - ret = io_copy_iov(ctx, &iov, arg, i); - if (ret) - goto err; +static int io_buffer_validate(struct iovec *iov) +{ + /* + * Don't impose further limits on the size and buffer + * constraints here, we'll -EINVAL later when IO is + * submitted if they are wrong. + */ + if (!iov->iov_base || !iov->iov_len) + return -EFAULT; - /* - * Don't impose further limits on the size and buffer - * constraints here, we'll -EINVAL later when IO is - * submitted if they are wrong. - */ - ret = -EFAULT; - if (!iov.iov_base || !iov.iov_len) - goto err; + /* arbitrary limit, but we need something */ + if (iov->iov_len > SZ_1G) + return -EFAULT; - /* arbitrary limit, but we need something */ - if (iov.iov_len > SZ_1G) - goto err; + return 0; +} - ubuf = (unsigned long) iov.iov_base; - end = (ubuf + iov.iov_len + PAGE_SIZE - 1) >> PAGE_SHIFT; - start = ubuf >> PAGE_SHIFT; - nr_pages = end - start; +static int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg, + unsigned int nr_args) +{ + int i, ret; + struct iovec iov; + struct page *last_hpage = NULL; - ret = 0; - if (!pages || nr_pages > got_pages) { - kvfree(vmas); - kvfree(pages); - pages = kvmalloc_array(nr_pages, sizeof(struct page *), - GFP_KERNEL); - vmas = kvmalloc_array(nr_pages, - sizeof(struct vm_area_struct *), - GFP_KERNEL); - if (!pages || !vmas) { - ret = -ENOMEM; - goto err; - } - got_pages = nr_pages; - } + ret = io_buffers_map_alloc(ctx, nr_args); + if (ret) + return ret; - imu->bvec = kvmalloc_array(nr_pages, sizeof(struct bio_vec), - GFP_KERNEL); - ret = -ENOMEM; - if (!imu->bvec) - goto err; + for (i = 0; i < nr_args; i++) { + struct io_mapped_ubuf *imu = &ctx->user_bufs[i]; - ret = 0; - mmap_read_lock(current->mm); - pret = pin_user_pages(ubuf, nr_pages, - FOLL_WRITE | FOLL_LONGTERM, - pages, vmas); - if (pret == nr_pages) { - /* don't support file backed memory */ - for (j = 0; j < nr_pages; j++) { - struct vm_area_struct *vma = vmas[j]; - - if (vma->vm_file && - !is_file_hugepages(vma->vm_file)) { - ret = -EOPNOTSUPP; - break; - } - } - } else { - ret = pret < 0 ? pret : -EFAULT; - } - mmap_read_unlock(current->mm); - if (ret) { - /* - * if we did partial map, or found file backed vmas, - * release any pages we did get - */ - if (pret > 0) - unpin_user_pages(pages, pret); - kvfree(imu->bvec); - goto err; - } + ret = io_copy_iov(ctx, &iov, arg, i); + if (ret) + break; - ret = io_buffer_account_pin(ctx, pages, pret, imu, &last_hpage); - if (ret) { - unpin_user_pages(pages, pret); - kvfree(imu->bvec); - goto err; - } + ret = io_buffer_validate(&iov); + if (ret) + break; - off = ubuf & ~PAGE_MASK; - size = iov.iov_len; - for (j = 0; j < nr_pages; j++) { - size_t vec_len; - - vec_len = min_t(size_t, size, PAGE_SIZE - off); - imu->bvec[j].bv_page = pages[j]; - imu->bvec[j].bv_len = vec_len; - imu->bvec[j].bv_offset = off; - off = 0; - size -= vec_len; - } - /* store original address for later verification */ - imu->ubuf = ubuf; - imu->len = iov.iov_len; - imu->nr_bvecs = nr_pages; + ret = io_sqe_buffer_register(ctx, &iov, imu, &last_hpage); + if (ret) + break; ctx->nr_user_bufs++; } - kvfree(pages); - kvfree(vmas); - return 0; -err: - kvfree(pages); - kvfree(vmas); - io_sqe_buffer_unregister(ctx); + + if (ret) + io_sqe_buffers_unregister(ctx); + return ret; } @@ -8571,10 +8687,49 @@ static void io_destroy_buffers(struct io_ring_ctx *ctx) idr_destroy(&ctx->io_buffer_idr); } +static void io_req_cache_free(struct list_head *list, struct task_struct *tsk) +{ + struct io_kiocb *req, *nxt; + + list_for_each_entry_safe(req, nxt, list, compl.list) { + if (tsk && req->task != tsk) + continue; + list_del(&req->compl.list); + kmem_cache_free(req_cachep, req); + } +} + +static void io_req_caches_free(struct io_ring_ctx *ctx, struct task_struct *tsk) +{ + struct io_submit_state *submit_state = &ctx->submit_state; + + mutex_lock(&ctx->uring_lock); + + if (submit_state->free_reqs) + kmem_cache_free_bulk(req_cachep, submit_state->free_reqs, + submit_state->reqs); + + io_req_cache_free(&submit_state->comp.free_list, NULL); + + spin_lock_irq(&ctx->completion_lock); + io_req_cache_free(&submit_state->comp.locked_free_list, NULL); + spin_unlock_irq(&ctx->completion_lock); + + mutex_unlock(&ctx->uring_lock); +} + static void io_ring_ctx_free(struct io_ring_ctx *ctx) { + /* + * Some may use context even when all refs and requests have been put, + * and they are free to do so while still holding uring_lock, see + * __io_req_task_submit(). Wait for them to finish. + */ + mutex_lock(&ctx->uring_lock); + mutex_unlock(&ctx->uring_lock); + io_finish_async(ctx); - io_sqe_buffer_unregister(ctx); + io_sqe_buffers_unregister(ctx); if (ctx->sqo_task) { put_task_struct(ctx->sqo_task); @@ -8606,8 +8761,8 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx) percpu_ref_exit(&ctx->refs); free_uid(ctx->user); put_cred(ctx->creds); + io_req_caches_free(ctx, NULL); kfree(ctx->cancel_hash); - kmem_cache_free(req_cachep, ctx->fallback_req); kfree(ctx); } @@ -8624,7 +8779,21 @@ static __poll_t io_uring_poll(struct file *file, poll_table *wait) smp_rmb(); if (!io_sqring_full(ctx)) mask |= EPOLLOUT | EPOLLWRNORM; - if (io_cqring_events(ctx, false)) + + /* + * Don't flush cqring overflow list here, just do a simple check. + * Otherwise there could possible be ABBA deadlock: + * CPU0 CPU1 + * ---- ---- + * lock(&ctx->uring_lock); + * lock(&ep->mtx); + * lock(&ctx->uring_lock); + * lock(&ep->mtx); + * + * Users may get EPOLLIN meanwhile seeing nothing in cqring, this + * pushs them to do the flush. + */ + if (io_cqring_events(ctx) || test_bit(0, &ctx->cq_check_overflow)) mask |= EPOLLIN | EPOLLRDNORM; return mask; @@ -8637,9 +8806,8 @@ static int io_uring_fasync(int fd, struct file *file, int on) return fasync_helper(fd, file, on, &ctx->cq_fasync); } -static int io_remove_personalities(int id, void *p, void *data) +static int io_unregister_personality(struct io_ring_ctx *ctx, unsigned id) { - struct io_ring_ctx *ctx = data; struct io_identity *iod; iod = idr_remove(&ctx->personality_idr, id); @@ -8647,7 +8815,17 @@ static int io_remove_personalities(int id, void *p, void *data) put_cred(iod->creds); if (refcount_dec_and_test(&iod->count)) kfree(iod); + return 0; } + + return -EINVAL; +} + +static int io_remove_personalities(int id, void *p, void *data) +{ + struct io_ring_ctx *ctx = data; + + io_unregister_personality(ctx, id); return 0; } @@ -8663,7 +8841,7 @@ static void io_ring_exit_work(struct work_struct *work) * as nobody else will be looking for them. */ do { - io_iopoll_try_reap_events(ctx); + io_uring_try_cancel_requests(ctx, NULL, NULL); } while (!wait_for_completion_timeout(&ctx->ref_comp, HZ/20)); io_ring_ctx_free(ctx); } @@ -8679,10 +8857,15 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) { mutex_lock(&ctx->uring_lock); percpu_ref_kill(&ctx->refs); + + if (WARN_ON_ONCE((ctx->flags & IORING_SETUP_SQPOLL) && !ctx->sqo_dead)) + ctx->sqo_dead = 1; + /* if force is set, the ring is going away. always drop after that */ ctx->cq_overflow_flushed = 1; if (ctx->rings) - io_cqring_overflow_flush(ctx, true, NULL, NULL); + __io_cqring_overflow_flush(ctx, true, NULL, NULL); + idr_for_each(&ctx->personality_idr, io_remove_personalities, ctx); mutex_unlock(&ctx->uring_lock); io_kill_timeouts(ctx, NULL, NULL); @@ -8693,15 +8876,6 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) /* if we failed setting up the ctx, we might not have any rings */ io_iopoll_try_reap_events(ctx); - idr_for_each(&ctx->personality_idr, io_remove_personalities, ctx); - - /* - * Do this upfront, so we won't have a grace period where the ring - * is closed but resources aren't reaped yet. This can cause - * spurious failure in setting up a new ring. - */ - io_unaccount_mem(ctx, ring_pages(ctx->sq_entries, ctx->cq_entries), - ACCT_LOCKED); INIT_WORK(&ctx->exit_work, io_ring_exit_work); /* @@ -8773,72 +8947,91 @@ static void io_cancel_defer_files(struct io_ring_ctx *ctx, } } -static void io_uring_cancel_files(struct io_ring_ctx *ctx, - struct task_struct *task, - struct files_struct *files) +static void io_uring_try_cancel_requests(struct io_ring_ctx *ctx, + struct task_struct *task, + struct files_struct *files) { - while (!list_empty_careful(&ctx->inflight_list)) { - struct io_task_cancel cancel = { .task = task, .files = files }; - struct io_kiocb *req; - DEFINE_WAIT(wait); - bool found = false; + struct io_task_cancel cancel = { .task = task, .files = files, }; - spin_lock_irq(&ctx->inflight_lock); - list_for_each_entry(req, &ctx->inflight_list, inflight_entry) { - if (req->task != task || - req->work.identity->files != files) - continue; - found = true; - break; - } - if (found) - prepare_to_wait(&task->io_uring->wait, &wait, - TASK_UNINTERRUPTIBLE); - spin_unlock_irq(&ctx->inflight_lock); - - /* We need to keep going until we don't find a matching req */ - if (!found) - break; - - io_wq_cancel_cb(ctx->io_wq, io_cancel_task_cb, &cancel, true); - io_poll_remove_all(ctx, task, files); - io_kill_timeouts(ctx, task, files); - /* cancellations _may_ trigger task work */ - io_run_task_work(); - schedule(); - finish_wait(&task->io_uring->wait, &wait); - } -} - -static void __io_uring_cancel_task_requests(struct io_ring_ctx *ctx, - struct task_struct *task) -{ while (1) { - struct io_task_cancel cancel = { .task = task, .files = NULL, }; enum io_wq_cancel cret; bool ret = false; - cret = io_wq_cancel_cb(ctx->io_wq, io_cancel_task_cb, &cancel, true); - if (cret != IO_WQ_CANCEL_NOTFOUND) - ret = true; + if (ctx->io_wq) { + cret = io_wq_cancel_cb(ctx->io_wq, io_cancel_task_cb, + &cancel, true); + ret |= (cret != IO_WQ_CANCEL_NOTFOUND); + } /* SQPOLL thread does its own polling */ - if (!(ctx->flags & IORING_SETUP_SQPOLL)) { + if (!(ctx->flags & IORING_SETUP_SQPOLL) && !files) { while (!list_empty_careful(&ctx->iopoll_list)) { io_iopoll_try_reap_events(ctx); ret = true; } } - ret |= io_poll_remove_all(ctx, task, NULL); - ret |= io_kill_timeouts(ctx, task, NULL); + ret |= io_poll_remove_all(ctx, task, files); + ret |= io_kill_timeouts(ctx, task, files); ret |= io_run_task_work(); + io_cqring_overflow_flush(ctx, true, task, files); if (!ret) break; cond_resched(); } } +static int io_uring_count_inflight(struct io_ring_ctx *ctx, + struct task_struct *task, + struct files_struct *files) +{ + struct io_kiocb *req; + int cnt = 0; + + spin_lock_irq(&ctx->inflight_lock); + list_for_each_entry(req, &ctx->inflight_list, inflight_entry) + cnt += io_match_task(req, task, files); + spin_unlock_irq(&ctx->inflight_lock); + return cnt; +} + +static void io_uring_cancel_files(struct io_ring_ctx *ctx, + struct task_struct *task, + struct files_struct *files) +{ + while (!list_empty_careful(&ctx->inflight_list)) { + DEFINE_WAIT(wait); + int inflight; + + inflight = io_uring_count_inflight(ctx, task, files); + if (!inflight) + break; + + io_uring_try_cancel_requests(ctx, task, files); + + if (ctx->sq_data) + io_sq_thread_unpark(ctx->sq_data); + prepare_to_wait(&task->io_uring->wait, &wait, + TASK_UNINTERRUPTIBLE); + if (inflight == io_uring_count_inflight(ctx, task, files)) + schedule(); + finish_wait(&task->io_uring->wait, &wait); + if (ctx->sq_data) + io_sq_thread_park(ctx->sq_data); + } +} + +static void io_disable_sqo_submit(struct io_ring_ctx *ctx) +{ + mutex_lock(&ctx->uring_lock); + ctx->sqo_dead = 1; + mutex_unlock(&ctx->uring_lock); + + /* make sure callers enter the ring to get error */ + if (ctx->rings) + io_ring_set_wakeup_flag(ctx); +} + /* * We need to iteratively cancel requests, in case a request has dependent * hard links. These persist even for failure of cancelations, hence keep @@ -8850,29 +9043,20 @@ static void io_uring_cancel_task_requests(struct io_ring_ctx *ctx, struct task_struct *task = current; if ((ctx->flags & IORING_SETUP_SQPOLL) && ctx->sq_data) { + io_disable_sqo_submit(ctx); task = ctx->sq_data->thread; atomic_inc(&task->io_uring->in_idle); io_sq_thread_park(ctx->sq_data); } io_cancel_defer_files(ctx, task, files); - io_ring_submit_lock(ctx, (ctx->flags & IORING_SETUP_IOPOLL)); - io_cqring_overflow_flush(ctx, true, task, files); - io_ring_submit_unlock(ctx, (ctx->flags & IORING_SETUP_IOPOLL)); + io_uring_cancel_files(ctx, task, files); if (!files) - __io_uring_cancel_task_requests(ctx, task); - else - io_uring_cancel_files(ctx, task, files); + io_uring_try_cancel_requests(ctx, task, NULL); if ((ctx->flags & IORING_SETUP_SQPOLL) && ctx->sq_data) { atomic_dec(&task->io_uring->in_idle); - /* - * If the files that are going away are the ones in the thread - * identity, clear them out. - */ - if (task->io_uring->identity->files == files) - task->io_uring->identity->files = NULL; io_sq_thread_unpark(ctx->sq_data); } } @@ -8902,6 +9086,10 @@ static int io_uring_add_task_file(struct io_ring_ctx *ctx, struct file *file) fput(file); return ret; } + + /* one and only SQPOLL file note, held by sqo_task */ + WARN_ON_ONCE((ctx->flags & IORING_SETUP_SQPOLL) && + current != ctx->sqo_task); } tctx->last = file; } @@ -8931,20 +9119,12 @@ static void io_uring_del_task_file(struct file *file) fput(file); } -/* - * Drop task note for this file if we're the only ones that hold it after - * pending fput() - */ -static void io_uring_attempt_task_drop(struct file *file) +static void io_uring_remove_task_files(struct io_uring_task *tctx) { - if (!current->io_uring) - return; - /* - * fput() is pending, will be 2 if the only other ref is our potential - * task file note. If the task is exiting, drop regardless of count. - */ - if (fatal_signal_pending(current) || (current->flags & PF_EXITING) || - atomic_long_read(&file->f_count) == 2) + struct file *file; + unsigned long index; + + xa_for_each(&tctx->xa, index, file) io_uring_del_task_file(file); } @@ -8956,43 +9136,49 @@ void __io_uring_files_cancel(struct files_struct *files) /* make sure overflow events are dropped */ atomic_inc(&tctx->in_idle); - - xa_for_each(&tctx->xa, index, file) { - struct io_ring_ctx *ctx = file->private_data; - - io_uring_cancel_task_requests(ctx, files); - if (files) - io_uring_del_task_file(file); - } - + xa_for_each(&tctx->xa, index, file) + io_uring_cancel_task_requests(file->private_data, files); atomic_dec(&tctx->in_idle); + + if (files) + io_uring_remove_task_files(tctx); } static s64 tctx_inflight(struct io_uring_task *tctx) { - unsigned long index; - struct file *file; - s64 inflight; - - inflight = percpu_counter_sum(&tctx->inflight); - if (!tctx->sqpoll) - return inflight; + return percpu_counter_sum(&tctx->inflight); +} - /* - * If we have SQPOLL rings, then we need to iterate and find them, and - * add the pending count for those. - */ - xa_for_each(&tctx->xa, index, file) { - struct io_ring_ctx *ctx = file->private_data; +static void io_uring_cancel_sqpoll(struct io_ring_ctx *ctx) +{ + struct io_uring_task *tctx; + s64 inflight; + DEFINE_WAIT(wait); - if (ctx->flags & IORING_SETUP_SQPOLL) { - struct io_uring_task *__tctx = ctx->sqo_task->io_uring; + if (!ctx->sq_data) + return; + tctx = ctx->sq_data->thread->io_uring; + io_disable_sqo_submit(ctx); - inflight += percpu_counter_sum(&__tctx->inflight); - } - } + atomic_inc(&tctx->in_idle); + do { + /* read completions before cancelations */ + inflight = tctx_inflight(tctx); + if (!inflight) + break; + io_uring_cancel_task_requests(ctx, NULL); - return inflight; + prepare_to_wait(&tctx->wait, &wait, TASK_UNINTERRUPTIBLE); + /* + * If we've seen completions, retry without waiting. This + * avoids a race where a completion comes in before we did + * prepare_to_wait(). + */ + if (inflight == tctx_inflight(tctx)) + schedule(); + finish_wait(&tctx->wait, &wait); + } while (1); + atomic_dec(&tctx->in_idle); } /* @@ -9008,6 +9194,15 @@ void __io_uring_task_cancel(void) /* make sure overflow events are dropped */ atomic_inc(&tctx->in_idle); + /* trigger io_disable_sqo_submit() */ + if (tctx->sqpoll) { + struct file *file; + unsigned long index; + + xa_for_each(&tctx->xa, index, file) + io_uring_cancel_sqpoll(file->private_data); + } + do { /* read completions before cancelations */ inflight = tctx_inflight(tctx); @@ -9018,21 +9213,57 @@ void __io_uring_task_cancel(void) prepare_to_wait(&tctx->wait, &wait, TASK_UNINTERRUPTIBLE); /* - * If we've seen completions, retry. This avoids a race where - * a completion comes in before we did prepare_to_wait(). + * If we've seen completions, retry without waiting. This + * avoids a race where a completion comes in before we did + * prepare_to_wait(). */ - if (inflight != tctx_inflight(tctx)) - continue; - schedule(); + if (inflight == tctx_inflight(tctx)) + schedule(); finish_wait(&tctx->wait, &wait); } while (1); atomic_dec(&tctx->in_idle); + + io_uring_remove_task_files(tctx); } static int io_uring_flush(struct file *file, void *data) { - io_uring_attempt_task_drop(file); + struct io_uring_task *tctx = current->io_uring; + struct io_ring_ctx *ctx = file->private_data; + + if (fatal_signal_pending(current) || (current->flags & PF_EXITING)) { + io_uring_cancel_task_requests(ctx, NULL); + io_req_caches_free(ctx, current); + } + + if (!tctx) + return 0; + + /* we should have cancelled and erased it before PF_EXITING */ + WARN_ON_ONCE((current->flags & PF_EXITING) && + xa_load(&tctx->xa, (unsigned long)file)); + + /* + * fput() is pending, will be 2 if the only other ref is our potential + * task file note. If the task is exiting, drop regardless of count. + */ + if (atomic_long_read(&file->f_count) != 2) + return 0; + + if (ctx->flags & IORING_SETUP_SQPOLL) { + /* there is only one file note, which is owned by sqo_task */ + WARN_ON_ONCE(ctx->sqo_task != current && + xa_load(&tctx->xa, (unsigned long)file)); + /* sqo_dead check is for when this happens after cancellation */ + WARN_ON_ONCE(ctx->sqo_task == current && !ctx->sqo_dead && + !xa_load(&tctx->xa, (unsigned long)file)); + + io_disable_sqo_submit(ctx); + } + + if (!(ctx->flags & IORING_SETUP_SQPOLL) || ctx->sqo_task == current) + io_uring_del_task_file(file); return 0; } @@ -9106,8 +9337,9 @@ static unsigned long io_uring_nommu_get_unmapped_area(struct file *file, #endif /* !CONFIG_MMU */ -static void io_sqpoll_wait_sq(struct io_ring_ctx *ctx) +static int io_sqpoll_wait_sq(struct io_ring_ctx *ctx) { + int ret = 0; DEFINE_WAIT(wait); do { @@ -9116,6 +9348,11 @@ static void io_sqpoll_wait_sq(struct io_ring_ctx *ctx) prepare_to_wait(&ctx->sqo_sq_wait, &wait, TASK_INTERRUPTIBLE); + if (unlikely(ctx->sqo_dead)) { + ret = -EOWNERDEAD; + goto out; + } + if (!io_sqring_full(ctx)) break; @@ -9123,6 +9360,8 @@ static void io_sqpoll_wait_sq(struct io_ring_ctx *ctx) } while (!signal_pending(current)); finish_wait(&ctx->sqo_sq_wait, &wait); +out: + return ret; } static int io_get_ext_arg(unsigned flags, const void __user *argp, size_t *argsz, @@ -9194,17 +9433,18 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, */ ret = 0; if (ctx->flags & IORING_SETUP_SQPOLL) { - if (!list_empty_careful(&ctx->cq_overflow_list)) { - bool needs_lock = ctx->flags & IORING_SETUP_IOPOLL; + io_cqring_overflow_flush(ctx, false, NULL, NULL); - io_ring_submit_lock(ctx, needs_lock); - io_cqring_overflow_flush(ctx, false, NULL, NULL); - io_ring_submit_unlock(ctx, needs_lock); - } + ret = -EOWNERDEAD; + if (unlikely(ctx->sqo_dead)) + goto out; if (flags & IORING_ENTER_SQ_WAKEUP) wake_up(&ctx->sq_data->wait); - if (flags & IORING_ENTER_SQ_WAIT) - io_sqpoll_wait_sq(ctx); + if (flags & IORING_ENTER_SQ_WAIT) { + ret = io_sqpoll_wait_sq(ctx); + if (ret) + goto out; + } submitted = to_submit; } else if (to_submit) { ret = io_uring_add_task_file(ctx, f.file); @@ -9304,11 +9544,8 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m) seq_printf(m, "SqThreadCpu:\t%d\n", sq ? task_cpu(sq->thread) : -1); seq_printf(m, "UserFiles:\t%u\n", ctx->nr_user_files); for (i = 0; has_lock && i < ctx->nr_user_files; i++) { - struct fixed_file_table *table; - struct file *f; + struct file *f = *io_fixed_file_slot(ctx->file_data, i); - table = &ctx->file_data->table[i >> IORING_FILE_TABLE_SHIFT]; - f = table->files[i & IORING_FILE_TABLE_MASK]; if (f) seq_printf(m, "%5u: %s\n", i, file_dentry(f)->d_iname); else @@ -9464,7 +9701,6 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p, struct user_struct *user = NULL; struct io_ring_ctx *ctx; struct file *file; - bool limit_mem; int ret; if (!entries) @@ -9505,26 +9741,14 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p, } user = get_uid(current_user()); - limit_mem = !capable(CAP_IPC_LOCK); - - if (limit_mem) { - ret = __io_account_mem(user, - ring_pages(p->sq_entries, p->cq_entries)); - if (ret) { - free_uid(user); - return ret; - } - } ctx = io_ring_ctx_alloc(p); if (!ctx) { - if (limit_mem) - __io_unaccount_mem(user, ring_pages(p->sq_entries, - p->cq_entries)); free_uid(user); return -ENOMEM; } ctx->compat = in_compat_syscall(); + ctx->limit_mem = !capable(CAP_IPC_LOCK); ctx->user = user; ctx->creds = get_current_cred(); #ifdef CONFIG_AUDIT @@ -9560,17 +9784,6 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p, goto err; } #endif - - /* - * Account memory _before_ installing the file descriptor. Once - * the descriptor is installed, it can get closed at any time. Also - * do this before hitting the general error path, as ring freeing - * will un-account as well. - */ - io_account_mem(ctx, ring_pages(p->sq_entries, p->cq_entries), - ACCT_LOCKED); - ctx->limit_mem = limit_mem; - ret = io_allocate_scq_urings(ctx, p); if (ret) goto err; @@ -9623,6 +9836,7 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p, */ ret = io_uring_install_fd(ctx, file); if (ret < 0) { + io_disable_sqo_submit(ctx); /* fput will clean it up */ fput(file); return ret; @@ -9631,6 +9845,7 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p, trace_io_uring_create(ret, ctx, p->sq_entries, p->cq_entries, p->flags); return ret; err: + io_disable_sqo_submit(ctx); io_ring_ctx_wait_and_kill(ctx); return ret; } @@ -9726,21 +9941,6 @@ static int io_register_personality(struct io_ring_ctx *ctx) return ret; } -static int io_unregister_personality(struct io_ring_ctx *ctx, unsigned id) -{ - struct io_identity *iod; - - iod = idr_remove(&ctx->personality_idr, id); - if (iod) { - put_cred(iod->creds); - if (refcount_dec_and_test(&iod->count)) - kfree(iod); - return 0; - } - - return -EINVAL; -} - static int io_register_restrictions(struct io_ring_ctx *ctx, void __user *arg, unsigned int nr_args) { @@ -9898,13 +10098,13 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, switch (opcode) { case IORING_REGISTER_BUFFERS: - ret = io_sqe_buffer_register(ctx, arg, nr_args); + ret = io_sqe_buffers_register(ctx, arg, nr_args); break; case IORING_UNREGISTER_BUFFERS: ret = -EINVAL; if (arg || nr_args) break; - ret = io_sqe_buffer_unregister(ctx); + ret = io_sqe_buffers_unregister(ctx); break; case IORING_REGISTER_FILES: ret = io_sqe_files_register(ctx, arg, nr_args); @@ -10047,7 +10247,8 @@ static int __init io_uring_init(void) BUILD_BUG_ON(ARRAY_SIZE(io_op_defs) != IORING_OP_LAST); BUILD_BUG_ON(__REQ_F_LAST_BIT >= 8 * sizeof(int)); - req_cachep = KMEM_CACHE(io_kiocb, SLAB_HWCACHE_ALIGN | SLAB_PANIC); + req_cachep = KMEM_CACHE(io_kiocb, SLAB_HWCACHE_ALIGN | SLAB_PANIC | + SLAB_ACCOUNT); return 0; }; __initcall(io_uring_init); diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index 933f234d5bec..e2c4991833b8 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -201,6 +201,34 @@ iomap_dio_zero(struct iomap_dio *dio, struct iomap *iomap, loff_t pos, iomap_dio_submit_bio(dio, iomap, bio, pos); } +/* + * Figure out the bio's operation flags from the dio request, the + * mapping, and whether or not we want FUA. Note that we can end up + * clearing the WRITE_FUA flag in the dio request. + */ +static inline unsigned int +iomap_dio_bio_opflags(struct iomap_dio *dio, struct iomap *iomap, bool use_fua) +{ + unsigned int opflags = REQ_SYNC | REQ_IDLE; + + if (!(dio->flags & IOMAP_DIO_WRITE)) { + WARN_ON_ONCE(iomap->flags & IOMAP_F_ZONE_APPEND); + return REQ_OP_READ; + } + + if (iomap->flags & IOMAP_F_ZONE_APPEND) + opflags |= REQ_OP_ZONE_APPEND; + else + opflags |= REQ_OP_WRITE; + + if (use_fua) + opflags |= REQ_FUA; + else + dio->flags &= ~IOMAP_DIO_WRITE_FUA; + + return opflags; +} + static loff_t iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length, struct iomap_dio *dio, struct iomap *iomap) @@ -208,6 +236,7 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length, unsigned int blkbits = blksize_bits(bdev_logical_block_size(iomap->bdev)); unsigned int fs_block_size = i_blocksize(inode), pad; unsigned int align = iov_iter_alignment(dio->submit.iter); + unsigned int bio_opf; struct bio *bio; bool need_zeroout = false; bool use_fua = false; @@ -250,11 +279,8 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length, orig_count = iov_iter_count(dio->submit.iter); iov_iter_truncate(dio->submit.iter, length); - nr_pages = iov_iter_npages(dio->submit.iter, BIO_MAX_PAGES); - if (nr_pages <= 0) { - ret = nr_pages; + if (!iov_iter_count(dio->submit.iter)) goto out; - } if (need_zeroout) { /* zero out from the start of the block to the write offset */ @@ -263,6 +289,14 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length, iomap_dio_zero(dio, iomap, pos - pad, pad); } + /* + * Set the operation flags early so that bio_iov_iter_get_pages + * can set up the page vector appropriately for a ZONE_APPEND + * operation. + */ + bio_opf = iomap_dio_bio_opflags(dio, iomap, use_fua); + + nr_pages = bio_iov_vecs_to_alloc(dio->submit.iter, BIO_MAX_PAGES); do { size_t n; if (dio->error) { @@ -278,6 +312,7 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length, bio->bi_ioprio = dio->iocb->ki_ioprio; bio->bi_private = dio; bio->bi_end_io = iomap_dio_bio_end_io; + bio->bi_opf = bio_opf; ret = bio_iov_iter_get_pages(bio, dio->submit.iter); if (unlikely(ret)) { @@ -293,14 +328,8 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length, n = bio->bi_iter.bi_size; if (dio->flags & IOMAP_DIO_WRITE) { - bio->bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_IDLE; - if (use_fua) - bio->bi_opf |= REQ_FUA; - else - dio->flags &= ~IOMAP_DIO_WRITE_FUA; task_io_account_write(n); } else { - bio->bi_opf = REQ_OP_READ; if (dio->flags & IOMAP_DIO_DIRTY) bio_set_pages_dirty(bio); } @@ -308,7 +337,8 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length, dio->size += n; copied += n; - nr_pages = iov_iter_npages(dio->submit.iter, BIO_MAX_PAGES); + nr_pages = bio_iov_vecs_to_alloc(dio->submit.iter, + BIO_MAX_PAGES); iomap_dio_submit_bio(dio, iomap, bio, pos); pos += n; } while (nr_pages); @@ -420,23 +450,22 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length, struct iomap_dio * __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops, const struct iomap_dio_ops *dops, - bool wait_for_completion) + unsigned int dio_flags) { struct address_space *mapping = iocb->ki_filp->f_mapping; struct inode *inode = file_inode(iocb->ki_filp); size_t count = iov_iter_count(iter); loff_t pos = iocb->ki_pos; loff_t end = iocb->ki_pos + count - 1, ret = 0; - unsigned int flags = IOMAP_DIRECT; + bool wait_for_completion = + is_sync_kiocb(iocb) || (dio_flags & IOMAP_DIO_FORCE_WAIT); + unsigned int iomap_flags = IOMAP_DIRECT; struct blk_plug plug; struct iomap_dio *dio; if (!count) return NULL; - if (WARN_ON(is_sync_kiocb(iocb) && !wait_for_completion)) - return ERR_PTR(-EIO); - dio = kmalloc(sizeof(*dio), GFP_KERNEL); if (!dio) return ERR_PTR(-ENOMEM); @@ -461,7 +490,7 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, if (iter_is_iovec(iter)) dio->flags |= IOMAP_DIO_DIRTY; } else { - flags |= IOMAP_WRITE; + iomap_flags |= IOMAP_WRITE; dio->flags |= IOMAP_DIO_WRITE; /* for data sync or sync, we need sync completion processing */ @@ -483,7 +512,14 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, ret = -EAGAIN; goto out_free_dio; } - flags |= IOMAP_NOWAIT; + iomap_flags |= IOMAP_NOWAIT; + } + + if (dio_flags & IOMAP_DIO_OVERWRITE_ONLY) { + ret = -EAGAIN; + if (pos >= dio->i_size || pos + count > dio->i_size) + goto out_free_dio; + iomap_flags |= IOMAP_OVERWRITE_ONLY; } ret = filemap_write_and_wait_range(mapping, pos, end); @@ -514,7 +550,7 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, blk_start_plug(&plug); do { - ret = iomap_apply(inode, pos, count, flags, ops, dio, + ret = iomap_apply(inode, pos, count, iomap_flags, ops, dio, iomap_dio_actor); if (ret <= 0) { /* magic error code to fall back to buffered I/O */ @@ -598,11 +634,11 @@ EXPORT_SYMBOL_GPL(__iomap_dio_rw); ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops, const struct iomap_dio_ops *dops, - bool wait_for_completion) + unsigned int dio_flags) { struct iomap_dio *dio; - dio = __iomap_dio_rw(iocb, iter, ops, dops, wait_for_completion); + dio = __iomap_dio_rw(iocb, iter, ops, dops, dio_flags); if (IS_ERR_OR_NULL(dio)) return PTR_ERR_OR_ZERO(dio); return iomap_dio_complete(dio); diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index 472932b9e6bc..63b526d44886 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -416,7 +416,7 @@ int jbd2_cleanup_journal_tail(journal_t *journal) * jbd2_cleanup_journal_tail() doesn't get called all that often. */ if (journal->j_flags & JBD2_BARRIER) - blkdev_issue_flush(journal->j_fs_dev, GFP_NOFS); + blkdev_issue_flush(journal->j_fs_dev); return __jbd2_update_log_tail(journal, first_tid, blocknr); } diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index b121d7d434c6..3cc4ab2ba7f4 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -825,7 +825,7 @@ start_journal_io: if (commit_transaction->t_need_data_flush && (journal->j_fs_dev != journal->j_dev) && (journal->j_flags & JBD2_BARRIER)) - blkdev_issue_flush(journal->j_fs_dev, GFP_NOFS); + blkdev_issue_flush(journal->j_fs_dev); /* Done it all: now write the commit record asynchronously. */ if (jbd2_has_feature_async_commit(journal)) { @@ -932,7 +932,7 @@ start_journal_io: stats.run.rs_blocks_logged++; if (jbd2_has_feature_async_commit(journal) && journal->j_flags & JBD2_BARRIER) { - blkdev_issue_flush(journal->j_dev, GFP_NOFS); + blkdev_issue_flush(journal->j_dev); } if (err) diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c index dc0694fcfcd1..69f18fe20923 100644 --- a/fs/jbd2/recovery.c +++ b/fs/jbd2/recovery.c @@ -326,7 +326,7 @@ int jbd2_journal_recover(journal_t *journal) err = err2; /* Make sure all replayed data is on permanent storage */ if (journal->j_flags & JBD2_BARRIER) { - err2 = blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL); + err2 = blkdev_issue_flush(journal->j_fs_dev); if (!err) err = err2; } diff --git a/fs/jffs2/compr_rtime.c b/fs/jffs2/compr_rtime.c index 406d9cc84ba8..79e771ab624f 100644 --- a/fs/jffs2/compr_rtime.c +++ b/fs/jffs2/compr_rtime.c @@ -37,6 +37,9 @@ static int jffs2_rtime_compress(unsigned char *data_in, int outpos = 0; int pos=0; + if (*dstlen <= 3) + return -1; + memset(positions,0,sizeof(positions)); while (pos < (*sourcelen) && outpos <= (*dstlen)-2) { diff --git a/fs/jffs2/summary.c b/fs/jffs2/summary.c index be7c8a6a5748..4fe64519870f 100644 --- a/fs/jffs2/summary.c +++ b/fs/jffs2/summary.c @@ -783,6 +783,8 @@ static int jffs2_sum_write_data(struct jffs2_sb_info *c, struct jffs2_eraseblock dbg_summary("Writing unknown RWCOMPAT_COPY node type %x\n", je16_to_cpu(temp->u.nodetype)); jffs2_sum_disable_collecting(c->summary); + /* The above call removes the list, nothing more to do */ + goto bail_rwcompat; } else { BUG(); /* unknown node in summary information */ } @@ -794,6 +796,7 @@ static int jffs2_sum_write_data(struct jffs2_sb_info *c, struct jffs2_eraseblock c->summary->sum_num--; } + bail_rwcompat: jffs2_sum_reset_collected(c->summary); diff --git a/fs/jfs/jfs_dmap.c b/fs/jfs/jfs_dmap.c index 94b7c1cb5ceb..7aee15608619 100644 --- a/fs/jfs/jfs_dmap.c +++ b/fs/jfs/jfs_dmap.c @@ -1656,7 +1656,7 @@ s64 dbDiscardAG(struct inode *ip, int agno, s64 minlen) } else if (rc == -ENOSPC) { /* search for next smaller log2 block */ l2nb = BLKSTOL2(nblocks) - 1; - nblocks = 1 << l2nb; + nblocks = 1LL << l2nb; } else { /* Trim any already allocated blocks */ jfs_error(bmp->db_ipbmap->i_sb, "-EIO\n"); diff --git a/fs/jfs/jfs_filsys.h b/fs/jfs/jfs_filsys.h index 1e899298f7f0..b5d702df7111 100644 --- a/fs/jfs/jfs_filsys.h +++ b/fs/jfs/jfs_filsys.h @@ -268,5 +268,6 @@ * fsck() must be run to repair */ #define FM_EXTENDFS 0x00000008 /* file system extendfs() in progress */ +#define FM_STATE_MAX 0x0000000f /* max value of s_state */ #endif /* _H_JFS_FILSYS */ diff --git a/fs/jfs/jfs_mount.c b/fs/jfs/jfs_mount.c index 2935d4c776ec..5d7d7170c03c 100644 --- a/fs/jfs/jfs_mount.c +++ b/fs/jfs/jfs_mount.c @@ -37,6 +37,7 @@ #include <linux/fs.h> #include <linux/buffer_head.h> #include <linux/blkdev.h> +#include <linux/log2.h> #include "jfs_incore.h" #include "jfs_filsys.h" @@ -366,6 +367,15 @@ static int chkSuper(struct super_block *sb) sbi->bsize = bsize; sbi->l2bsize = le16_to_cpu(j_sb->s_l2bsize); + /* check some fields for possible corruption */ + if (sbi->l2bsize != ilog2((u32)bsize) || + j_sb->pad != 0 || + le32_to_cpu(j_sb->s_state) > FM_STATE_MAX) { + rc = -EINVAL; + jfs_err("jfs_mount: Mount Failure: superblock is corrupt!"); + goto out; + } + /* * For now, ignore s_pbsize, l2bfactor. All I/O going through buffer * cache. diff --git a/fs/jfs/jfs_txnmgr.c b/fs/jfs/jfs_txnmgr.c index dca8edd2378c..053295cd7bc6 100644 --- a/fs/jfs/jfs_txnmgr.c +++ b/fs/jfs/jfs_txnmgr.c @@ -148,10 +148,10 @@ static struct { /* * forward references */ -static int diLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, - struct tlock * tlck, struct commit * cd); -static int dataLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, - struct tlock * tlck); +static void diLog(struct jfs_log *log, struct tblock *tblk, struct lrd *lrd, + struct tlock *tlck, struct commit *cd); +static void dataLog(struct jfs_log *log, struct tblock *tblk, struct lrd *lrd, + struct tlock *tlck); static void dtLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, struct tlock * tlck); static void mapLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, @@ -159,8 +159,8 @@ static void mapLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, static void txAllocPMap(struct inode *ip, struct maplock * maplock, struct tblock * tblk); static void txForce(struct tblock * tblk); -static int txLog(struct jfs_log * log, struct tblock * tblk, - struct commit * cd); +static void txLog(struct jfs_log *log, struct tblock *tblk, + struct commit *cd); static void txUpdateMap(struct tblock * tblk); static void txRelease(struct tblock * tblk); static void xtLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, @@ -1256,8 +1256,7 @@ int txCommit(tid_t tid, /* transaction identifier */ * * txUpdateMap() resets XAD_NEW in XAD. */ - if ((rc = txLog(log, tblk, &cd))) - goto TheEnd; + txLog(log, tblk, &cd); /* * Ensure that inode isn't reused before @@ -1365,9 +1364,8 @@ int txCommit(tid_t tid, /* transaction identifier */ * * RETURN : */ -static int txLog(struct jfs_log * log, struct tblock * tblk, struct commit * cd) +static void txLog(struct jfs_log *log, struct tblock *tblk, struct commit *cd) { - int rc = 0; struct inode *ip; lid_t lid; struct tlock *tlck; @@ -1414,7 +1412,7 @@ static int txLog(struct jfs_log * log, struct tblock * tblk, struct commit * cd) } } - return rc; + return; } /* @@ -1422,10 +1420,9 @@ static int txLog(struct jfs_log * log, struct tblock * tblk, struct commit * cd) * * function: log inode tlock and format maplock to update bmap; */ -static int diLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, - struct tlock * tlck, struct commit * cd) +static void diLog(struct jfs_log *log, struct tblock *tblk, struct lrd *lrd, + struct tlock *tlck, struct commit *cd) { - int rc = 0; struct metapage *mp; pxd_t *pxd; struct pxd_lock *pxdlock; @@ -1527,7 +1524,7 @@ static int diLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, } #endif /* _JFS_WIP */ - return rc; + return; } /* @@ -1535,8 +1532,8 @@ static int diLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, * * function: log data tlock */ -static int dataLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, - struct tlock * tlck) +static void dataLog(struct jfs_log *log, struct tblock *tblk, struct lrd *lrd, + struct tlock *tlck) { struct metapage *mp; pxd_t *pxd; @@ -1562,7 +1559,7 @@ static int dataLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, metapage_homeok(mp); discard_metapage(mp); tlck->mp = NULL; - return 0; + return; } PXDaddress(pxd, mp->index); @@ -1573,7 +1570,7 @@ static int dataLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, /* mark page as homeward bound */ tlck->flag |= tlckWRITEPAGE; - return 0; + return; } /* diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index f277d023ebcd..c75719312147 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -14,6 +14,7 @@ #include <linux/pagemap.h> #include <linux/sched/mm.h> #include <linux/fsnotify.h> +#include <linux/uio.h> #include "kernfs-internal.h" @@ -180,11 +181,10 @@ static const struct seq_operations kernfs_seq_ops = { * it difficult to use seq_file. Implement simplistic custom buffering for * bin files. */ -static ssize_t kernfs_file_direct_read(struct kernfs_open_file *of, - char __user *user_buf, size_t count, - loff_t *ppos) +static ssize_t kernfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) { - ssize_t len = min_t(size_t, count, PAGE_SIZE); + struct kernfs_open_file *of = kernfs_of(iocb->ki_filp); + ssize_t len = min_t(size_t, iov_iter_count(iter), PAGE_SIZE); const struct kernfs_ops *ops; char *buf; @@ -210,7 +210,7 @@ static ssize_t kernfs_file_direct_read(struct kernfs_open_file *of, of->event = atomic_read(&of->kn->attr.open->event); ops = kernfs_ops(of->kn); if (ops->read) - len = ops->read(of, buf, len, *ppos); + len = ops->read(of, buf, len, iocb->ki_pos); else len = -EINVAL; @@ -220,12 +220,12 @@ static ssize_t kernfs_file_direct_read(struct kernfs_open_file *of, if (len < 0) goto out_free; - if (copy_to_user(user_buf, buf, len)) { + if (copy_to_iter(buf, len, iter) != len) { len = -EFAULT; goto out_free; } - *ppos += len; + iocb->ki_pos += len; out_free: if (buf == of->prealloc_buf) @@ -235,31 +235,14 @@ static ssize_t kernfs_file_direct_read(struct kernfs_open_file *of, return len; } -/** - * kernfs_fop_read - kernfs vfs read callback - * @file: file pointer - * @user_buf: data to write - * @count: number of bytes - * @ppos: starting offset - */ -static ssize_t kernfs_fop_read(struct file *file, char __user *user_buf, - size_t count, loff_t *ppos) +static ssize_t kernfs_fop_read_iter(struct kiocb *iocb, struct iov_iter *iter) { - struct kernfs_open_file *of = kernfs_of(file); - - if (of->kn->flags & KERNFS_HAS_SEQ_SHOW) - return seq_read(file, user_buf, count, ppos); - else - return kernfs_file_direct_read(of, user_buf, count, ppos); + if (kernfs_of(iocb->ki_filp)->kn->flags & KERNFS_HAS_SEQ_SHOW) + return seq_read_iter(iocb, iter); + return kernfs_file_read_iter(iocb, iter); } -/** - * kernfs_fop_write - kernfs vfs write callback - * @file: file pointer - * @user_buf: data to write - * @count: number of bytes - * @ppos: starting offset - * +/* * Copy data in from userland and pass it to the matching kernfs write * operation. * @@ -269,20 +252,18 @@ static ssize_t kernfs_fop_read(struct file *file, char __user *user_buf, * modify only the the value you're changing, then write entire buffer * back. */ -static ssize_t kernfs_fop_write(struct file *file, const char __user *user_buf, - size_t count, loff_t *ppos) +static ssize_t kernfs_fop_write_iter(struct kiocb *iocb, struct iov_iter *iter) { - struct kernfs_open_file *of = kernfs_of(file); + struct kernfs_open_file *of = kernfs_of(iocb->ki_filp); + ssize_t len = iov_iter_count(iter); const struct kernfs_ops *ops; - ssize_t len; char *buf; if (of->atomic_write_len) { - len = count; if (len > of->atomic_write_len) return -E2BIG; } else { - len = min_t(size_t, count, PAGE_SIZE); + len = min_t(size_t, len, PAGE_SIZE); } buf = of->prealloc_buf; @@ -293,7 +274,7 @@ static ssize_t kernfs_fop_write(struct file *file, const char __user *user_buf, if (!buf) return -ENOMEM; - if (copy_from_user(buf, user_buf, len)) { + if (copy_from_iter(buf, len, iter) != len) { len = -EFAULT; goto out_free; } @@ -312,7 +293,7 @@ static ssize_t kernfs_fop_write(struct file *file, const char __user *user_buf, ops = kernfs_ops(of->kn); if (ops->write) - len = ops->write(of, buf, len, *ppos); + len = ops->write(of, buf, len, iocb->ki_pos); else len = -EINVAL; @@ -320,7 +301,7 @@ static ssize_t kernfs_fop_write(struct file *file, const char __user *user_buf, mutex_unlock(&of->mutex); if (len > 0) - *ppos += len; + iocb->ki_pos += len; out_free: if (buf == of->prealloc_buf) @@ -673,7 +654,7 @@ static int kernfs_fop_open(struct inode *inode, struct file *file) /* * Write path needs to atomic_write_len outside active reference. - * Cache it in open_file. See kernfs_fop_write() for details. + * Cache it in open_file. See kernfs_fop_write_iter() for details. */ of->atomic_write_len = ops->atomic_write_len; @@ -960,14 +941,16 @@ void kernfs_notify(struct kernfs_node *kn) EXPORT_SYMBOL_GPL(kernfs_notify); const struct file_operations kernfs_file_fops = { - .read = kernfs_fop_read, - .write = kernfs_fop_write, + .read_iter = kernfs_fop_read_iter, + .write_iter = kernfs_fop_write_iter, .llseek = generic_file_llseek, .mmap = kernfs_fop_mmap, .open = kernfs_fop_open, .release = kernfs_fop_release, .poll = kernfs_fop_poll, .fsync = noop_fsync, + .splice_read = generic_file_splice_read, + .splice_write = iter_file_splice_write, }; /** diff --git a/fs/libfs.c b/fs/libfs.c index e52818fb276a..1e551766bc52 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -1117,7 +1117,7 @@ int generic_file_fsync(struct file *file, loff_t start, loff_t end, err = __generic_file_fsync(file, start, end, datasync); if (err) return err; - return blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL); + return blkdev_issue_flush(inode->i_sb->s_bdev); } EXPORT_SYMBOL(generic_file_fsync); @@ -1383,8 +1383,8 @@ static bool needs_casefold(const struct inode *dir) * * Return: 0 if names match, 1 if mismatch, or -ERRNO */ -int generic_ci_d_compare(const struct dentry *dentry, unsigned int len, - const char *str, const struct qstr *name) +static int generic_ci_d_compare(const struct dentry *dentry, unsigned int len, + const char *str, const struct qstr *name) { const struct dentry *parent = READ_ONCE(dentry->d_parent); const struct inode *dir = READ_ONCE(parent->d_inode); @@ -1421,7 +1421,6 @@ fallback: return 1; return !!memcmp(str, name->name, len); } -EXPORT_SYMBOL(generic_ci_d_compare); /** * generic_ci_d_hash - generic d_hash implementation for casefolding filesystems @@ -1430,7 +1429,7 @@ EXPORT_SYMBOL(generic_ci_d_compare); * * Return: 0 if hash was successful or unchanged, and -EINVAL on error */ -int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str) +static int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str) { const struct inode *dir = READ_ONCE(dentry->d_inode); struct super_block *sb = dentry->d_sb; @@ -1445,7 +1444,6 @@ int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str) return -EINVAL; return 0; } -EXPORT_SYMBOL(generic_ci_d_hash); static const struct dentry_operations generic_ci_dentry_ops = { .d_hash = generic_ci_d_hash, diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c index fa41dda39925..4c10fb5138f1 100644 --- a/fs/lockd/svc4proc.c +++ b/fs/lockd/svc4proc.c @@ -512,6 +512,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = { .pc_argsize = sizeof(struct nlm_void), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, + .pc_name = "NULL", }, [NLMPROC_TEST] = { .pc_func = nlm4svc_proc_test, @@ -520,6 +521,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = { .pc_argsize = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_res), .pc_xdrressize = Ck+St+2+No+Rg, + .pc_name = "TEST", }, [NLMPROC_LOCK] = { .pc_func = nlm4svc_proc_lock, @@ -528,6 +530,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = { .pc_argsize = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_res), .pc_xdrressize = Ck+St, + .pc_name = "LOCK", }, [NLMPROC_CANCEL] = { .pc_func = nlm4svc_proc_cancel, @@ -536,6 +539,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = { .pc_argsize = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_res), .pc_xdrressize = Ck+St, + .pc_name = "CANCEL", }, [NLMPROC_UNLOCK] = { .pc_func = nlm4svc_proc_unlock, @@ -544,6 +548,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = { .pc_argsize = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_res), .pc_xdrressize = Ck+St, + .pc_name = "UNLOCK", }, [NLMPROC_GRANTED] = { .pc_func = nlm4svc_proc_granted, @@ -552,6 +557,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = { .pc_argsize = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_res), .pc_xdrressize = Ck+St, + .pc_name = "GRANTED", }, [NLMPROC_TEST_MSG] = { .pc_func = nlm4svc_proc_test_msg, @@ -560,6 +566,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = { .pc_argsize = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, + .pc_name = "TEST_MSG", }, [NLMPROC_LOCK_MSG] = { .pc_func = nlm4svc_proc_lock_msg, @@ -568,6 +575,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = { .pc_argsize = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, + .pc_name = "LOCK_MSG", }, [NLMPROC_CANCEL_MSG] = { .pc_func = nlm4svc_proc_cancel_msg, @@ -576,6 +584,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = { .pc_argsize = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, + .pc_name = "CANCEL_MSG", }, [NLMPROC_UNLOCK_MSG] = { .pc_func = nlm4svc_proc_unlock_msg, @@ -584,6 +593,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = { .pc_argsize = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, + .pc_name = "UNLOCK_MSG", }, [NLMPROC_GRANTED_MSG] = { .pc_func = nlm4svc_proc_granted_msg, @@ -592,6 +602,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = { .pc_argsize = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, + .pc_name = "GRANTED_MSG", }, [NLMPROC_TEST_RES] = { .pc_func = nlm4svc_proc_null, @@ -600,6 +611,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = { .pc_argsize = sizeof(struct nlm_res), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, + .pc_name = "TEST_RES", }, [NLMPROC_LOCK_RES] = { .pc_func = nlm4svc_proc_null, @@ -608,6 +620,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = { .pc_argsize = sizeof(struct nlm_res), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, + .pc_name = "LOCK_RES", }, [NLMPROC_CANCEL_RES] = { .pc_func = nlm4svc_proc_null, @@ -616,6 +629,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = { .pc_argsize = sizeof(struct nlm_res), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, + .pc_name = "CANCEL_RES", }, [NLMPROC_UNLOCK_RES] = { .pc_func = nlm4svc_proc_null, @@ -624,6 +638,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = { .pc_argsize = sizeof(struct nlm_res), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, + .pc_name = "UNLOCK_RES", }, [NLMPROC_GRANTED_RES] = { .pc_func = nlm4svc_proc_granted_res, @@ -632,6 +647,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = { .pc_argsize = sizeof(struct nlm_res), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, + .pc_name = "GRANTED_RES", }, [NLMPROC_NSM_NOTIFY] = { .pc_func = nlm4svc_proc_sm_notify, @@ -640,6 +656,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = { .pc_argsize = sizeof(struct nlm_reboot), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, + .pc_name = "SM_NOTIFY", }, [17] = { .pc_func = nlm4svc_proc_unused, @@ -648,6 +665,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = { .pc_argsize = sizeof(struct nlm_void), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = 0, + .pc_name = "UNUSED", }, [18] = { .pc_func = nlm4svc_proc_unused, @@ -656,6 +674,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = { .pc_argsize = sizeof(struct nlm_void), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = 0, + .pc_name = "UNUSED", }, [19] = { .pc_func = nlm4svc_proc_unused, @@ -664,6 +683,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = { .pc_argsize = sizeof(struct nlm_void), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = 0, + .pc_name = "UNUSED", }, [NLMPROC_SHARE] = { .pc_func = nlm4svc_proc_share, @@ -672,6 +692,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = { .pc_argsize = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_res), .pc_xdrressize = Ck+St+1, + .pc_name = "SHARE", }, [NLMPROC_UNSHARE] = { .pc_func = nlm4svc_proc_unshare, @@ -680,6 +701,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = { .pc_argsize = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_res), .pc_xdrressize = Ck+St+1, + .pc_name = "UNSHARE", }, [NLMPROC_NM_LOCK] = { .pc_func = nlm4svc_proc_nm_lock, @@ -688,6 +710,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = { .pc_argsize = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_res), .pc_xdrressize = Ck+St, + .pc_name = "NM_LOCK", }, [NLMPROC_FREE_ALL] = { .pc_func = nlm4svc_proc_free_all, @@ -696,5 +719,6 @@ const struct svc_procedure nlmsvc_procedures4[24] = { .pc_argsize = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, + .pc_name = "FREE_ALL", }, }; diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c index 50855f2c1f4b..4ae4b63b5392 100644 --- a/fs/lockd/svcproc.c +++ b/fs/lockd/svcproc.c @@ -554,6 +554,7 @@ const struct svc_procedure nlmsvc_procedures[24] = { .pc_argsize = sizeof(struct nlm_void), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, + .pc_name = "NULL", }, [NLMPROC_TEST] = { .pc_func = nlmsvc_proc_test, @@ -562,6 +563,7 @@ const struct svc_procedure nlmsvc_procedures[24] = { .pc_argsize = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_res), .pc_xdrressize = Ck+St+2+No+Rg, + .pc_name = "TEST", }, [NLMPROC_LOCK] = { .pc_func = nlmsvc_proc_lock, @@ -570,6 +572,7 @@ const struct svc_procedure nlmsvc_procedures[24] = { .pc_argsize = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_res), .pc_xdrressize = Ck+St, + .pc_name = "LOCK", }, [NLMPROC_CANCEL] = { .pc_func = nlmsvc_proc_cancel, @@ -578,6 +581,7 @@ const struct svc_procedure nlmsvc_procedures[24] = { .pc_argsize = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_res), .pc_xdrressize = Ck+St, + .pc_name = "CANCEL", }, [NLMPROC_UNLOCK] = { .pc_func = nlmsvc_proc_unlock, @@ -586,6 +590,7 @@ const struct svc_procedure nlmsvc_procedures[24] = { .pc_argsize = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_res), .pc_xdrressize = Ck+St, + .pc_name = "UNLOCK", }, [NLMPROC_GRANTED] = { .pc_func = nlmsvc_proc_granted, @@ -594,6 +599,7 @@ const struct svc_procedure nlmsvc_procedures[24] = { .pc_argsize = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_res), .pc_xdrressize = Ck+St, + .pc_name = "GRANTED", }, [NLMPROC_TEST_MSG] = { .pc_func = nlmsvc_proc_test_msg, @@ -602,6 +608,7 @@ const struct svc_procedure nlmsvc_procedures[24] = { .pc_argsize = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, + .pc_name = "TEST_MSG", }, [NLMPROC_LOCK_MSG] = { .pc_func = nlmsvc_proc_lock_msg, @@ -610,6 +617,7 @@ const struct svc_procedure nlmsvc_procedures[24] = { .pc_argsize = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, + .pc_name = "LOCK_MSG", }, [NLMPROC_CANCEL_MSG] = { .pc_func = nlmsvc_proc_cancel_msg, @@ -618,6 +626,7 @@ const struct svc_procedure nlmsvc_procedures[24] = { .pc_argsize = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, + .pc_name = "CANCEL_MSG", }, [NLMPROC_UNLOCK_MSG] = { .pc_func = nlmsvc_proc_unlock_msg, @@ -626,6 +635,7 @@ const struct svc_procedure nlmsvc_procedures[24] = { .pc_argsize = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, + .pc_name = "UNLOCK_MSG", }, [NLMPROC_GRANTED_MSG] = { .pc_func = nlmsvc_proc_granted_msg, @@ -634,6 +644,7 @@ const struct svc_procedure nlmsvc_procedures[24] = { .pc_argsize = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, + .pc_name = "GRANTED_MSG", }, [NLMPROC_TEST_RES] = { .pc_func = nlmsvc_proc_null, @@ -642,6 +653,7 @@ const struct svc_procedure nlmsvc_procedures[24] = { .pc_argsize = sizeof(struct nlm_res), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, + .pc_name = "TEST_RES", }, [NLMPROC_LOCK_RES] = { .pc_func = nlmsvc_proc_null, @@ -650,6 +662,7 @@ const struct svc_procedure nlmsvc_procedures[24] = { .pc_argsize = sizeof(struct nlm_res), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, + .pc_name = "LOCK_RES", }, [NLMPROC_CANCEL_RES] = { .pc_func = nlmsvc_proc_null, @@ -658,6 +671,7 @@ const struct svc_procedure nlmsvc_procedures[24] = { .pc_argsize = sizeof(struct nlm_res), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, + .pc_name = "CANCEL_RES", }, [NLMPROC_UNLOCK_RES] = { .pc_func = nlmsvc_proc_null, @@ -666,6 +680,7 @@ const struct svc_procedure nlmsvc_procedures[24] = { .pc_argsize = sizeof(struct nlm_res), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, + .pc_name = "UNLOCK_RES", }, [NLMPROC_GRANTED_RES] = { .pc_func = nlmsvc_proc_granted_res, @@ -674,6 +689,7 @@ const struct svc_procedure nlmsvc_procedures[24] = { .pc_argsize = sizeof(struct nlm_res), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, + .pc_name = "GRANTED_RES", }, [NLMPROC_NSM_NOTIFY] = { .pc_func = nlmsvc_proc_sm_notify, @@ -682,6 +698,7 @@ const struct svc_procedure nlmsvc_procedures[24] = { .pc_argsize = sizeof(struct nlm_reboot), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, + .pc_name = "SM_NOTIFY", }, [17] = { .pc_func = nlmsvc_proc_unused, @@ -690,6 +707,7 @@ const struct svc_procedure nlmsvc_procedures[24] = { .pc_argsize = sizeof(struct nlm_void), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, + .pc_name = "UNUSED", }, [18] = { .pc_func = nlmsvc_proc_unused, @@ -698,6 +716,7 @@ const struct svc_procedure nlmsvc_procedures[24] = { .pc_argsize = sizeof(struct nlm_void), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, + .pc_name = "UNUSED", }, [19] = { .pc_func = nlmsvc_proc_unused, @@ -706,6 +725,7 @@ const struct svc_procedure nlmsvc_procedures[24] = { .pc_argsize = sizeof(struct nlm_void), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = St, + .pc_name = "UNUSED", }, [NLMPROC_SHARE] = { .pc_func = nlmsvc_proc_share, @@ -714,6 +734,7 @@ const struct svc_procedure nlmsvc_procedures[24] = { .pc_argsize = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_res), .pc_xdrressize = Ck+St+1, + .pc_name = "SHARE", }, [NLMPROC_UNSHARE] = { .pc_func = nlmsvc_proc_unshare, @@ -722,6 +743,7 @@ const struct svc_procedure nlmsvc_procedures[24] = { .pc_argsize = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_res), .pc_xdrressize = Ck+St+1, + .pc_name = "UNSHARE", }, [NLMPROC_NM_LOCK] = { .pc_func = nlmsvc_proc_nm_lock, @@ -730,6 +752,7 @@ const struct svc_procedure nlmsvc_procedures[24] = { .pc_argsize = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_res), .pc_xdrressize = Ck+St, + .pc_name = "NM_LOCK", }, [NLMPROC_FREE_ALL] = { .pc_func = nlmsvc_proc_free_all, @@ -738,5 +761,6 @@ const struct svc_procedure nlmsvc_procedures[24] = { .pc_argsize = sizeof(struct nlm_args), .pc_ressize = sizeof(struct nlm_void), .pc_xdrressize = 0, + .pc_name = "FREE_ALL", }, }; diff --git a/fs/namei.c b/fs/namei.c index 78443a85480a..de74ad2bc6e2 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -630,6 +630,11 @@ static inline bool legitimize_path(struct nameidata *nd, static bool legitimize_links(struct nameidata *nd) { int i; + if (unlikely(nd->flags & LOOKUP_CACHED)) { + drop_links(nd); + nd->depth = 0; + return false; + } for (i = 0; i < nd->depth; i++) { struct saved *last = nd->stack + i; if (unlikely(!legitimize_path(nd, &last->link, last->seq))) { @@ -669,17 +674,17 @@ static bool legitimize_root(struct nameidata *nd) */ /** - * unlazy_walk - try to switch to ref-walk mode. + * try_to_unlazy - try to switch to ref-walk mode. * @nd: nameidata pathwalk data - * Returns: 0 on success, -ECHILD on failure + * Returns: true on success, false on failure * - * unlazy_walk attempts to legitimize the current nd->path and nd->root + * try_to_unlazy attempts to legitimize the current nd->path and nd->root * for ref-walk mode. * Must be called from rcu-walk context. - * Nothing should touch nameidata between unlazy_walk() failure and + * Nothing should touch nameidata between try_to_unlazy() failure and * terminate_walk(). */ -static int unlazy_walk(struct nameidata *nd) +static bool try_to_unlazy(struct nameidata *nd) { struct dentry *parent = nd->path.dentry; @@ -694,30 +699,30 @@ static int unlazy_walk(struct nameidata *nd) goto out; rcu_read_unlock(); BUG_ON(nd->inode != parent->d_inode); - return 0; + return true; out1: nd->path.mnt = NULL; nd->path.dentry = NULL; out: rcu_read_unlock(); - return -ECHILD; + return false; } /** - * unlazy_child - try to switch to ref-walk mode. + * try_to_unlazy_next - try to switch to ref-walk mode. * @nd: nameidata pathwalk data - * @dentry: child of nd->path.dentry - * @seq: seq number to check dentry against - * Returns: 0 on success, -ECHILD on failure + * @dentry: next dentry to step into + * @seq: seq number to check @dentry against + * Returns: true on success, false on failure * - * unlazy_child attempts to legitimize the current nd->path, nd->root and dentry - * for ref-walk mode. @dentry must be a path found by a do_lookup call on - * @nd. Must be called from rcu-walk context. - * Nothing should touch nameidata between unlazy_child() failure and + * Similar to to try_to_unlazy(), but here we have the next dentry already + * picked by rcu-walk and want to legitimize that in addition to the current + * nd->path and nd->root for ref-walk mode. Must be called from rcu-walk context. + * Nothing should touch nameidata between try_to_unlazy_next() failure and * terminate_walk(). */ -static int unlazy_child(struct nameidata *nd, struct dentry *dentry, unsigned seq) +static bool try_to_unlazy_next(struct nameidata *nd, struct dentry *dentry, unsigned seq) { BUG_ON(!(nd->flags & LOOKUP_RCU)); @@ -747,7 +752,7 @@ static int unlazy_child(struct nameidata *nd, struct dentry *dentry, unsigned se if (unlikely(!legitimize_root(nd))) goto out_dput; rcu_read_unlock(); - return 0; + return true; out2: nd->path.mnt = NULL; @@ -755,11 +760,11 @@ out1: nd->path.dentry = NULL; out: rcu_read_unlock(); - return -ECHILD; + return false; out_dput: rcu_read_unlock(); dput(dentry); - return -ECHILD; + return false; } static inline int d_revalidate(struct dentry *dentry, unsigned int flags) @@ -792,7 +797,8 @@ static int complete_walk(struct nameidata *nd) */ if (!(nd->flags & (LOOKUP_ROOT | LOOKUP_IS_SCOPED))) nd->root.mnt = NULL; - if (unlikely(unlazy_walk(nd))) + nd->flags &= ~LOOKUP_CACHED; + if (!try_to_unlazy(nd)) return -ECHILD; } @@ -1372,7 +1378,7 @@ static inline int handle_mounts(struct nameidata *nd, struct dentry *dentry, return -ENOENT; if (likely(__follow_mount_rcu(nd, path, inode, seqp))) return 0; - if (unlazy_child(nd, dentry, seq)) + if (!try_to_unlazy_next(nd, dentry, seq)) return -ECHILD; // *path might've been clobbered by __follow_mount_rcu() path->mnt = nd->path.mnt; @@ -1466,7 +1472,7 @@ static struct dentry *lookup_fast(struct nameidata *nd, unsigned seq; dentry = __d_lookup_rcu(parent, &nd->last, &seq); if (unlikely(!dentry)) { - if (unlazy_walk(nd)) + if (!try_to_unlazy(nd)) return ERR_PTR(-ECHILD); return NULL; } @@ -1493,9 +1499,9 @@ static struct dentry *lookup_fast(struct nameidata *nd, status = d_revalidate(dentry, nd->flags); if (likely(status > 0)) return dentry; - if (unlazy_child(nd, dentry, seq)) + if (!try_to_unlazy_next(nd, dentry, seq)) return ERR_PTR(-ECHILD); - if (unlikely(status == -ECHILD)) + if (status == -ECHILD) /* we'd been told to redo it in non-rcu mode */ status = d_revalidate(dentry, nd->flags); } else { @@ -1567,10 +1573,8 @@ static inline int may_lookup(struct nameidata *nd) { if (nd->flags & LOOKUP_RCU) { int err = inode_permission(nd->inode, MAY_EXEC|MAY_NOT_BLOCK); - if (err != -ECHILD) + if (err != -ECHILD || !try_to_unlazy(nd)) return err; - if (unlazy_walk(nd)) - return -ECHILD; } return inode_permission(nd->inode, MAY_EXEC); } @@ -1592,7 +1596,7 @@ static int reserve_stack(struct nameidata *nd, struct path *link, unsigned seq) // unlazy even if we fail to grab the link - cleanup needs it bool grabbed_link = legitimize_path(nd, link, seq); - if (unlazy_walk(nd) != 0 || !grabbed_link) + if (!try_to_unlazy(nd) != 0 || !grabbed_link) return -ECHILD; if (nd_alloc_stack(nd)) @@ -1634,7 +1638,7 @@ static const char *pick_link(struct nameidata *nd, struct path *link, touch_atime(&last->link); cond_resched(); } else if (atime_needs_update(&last->link, inode)) { - if (unlikely(unlazy_walk(nd))) + if (!try_to_unlazy(nd)) return ERR_PTR(-ECHILD); touch_atime(&last->link); } @@ -1651,11 +1655,8 @@ static const char *pick_link(struct nameidata *nd, struct path *link, get = inode->i_op->get_link; if (nd->flags & LOOKUP_RCU) { res = get(NULL, inode, &last->done); - if (res == ERR_PTR(-ECHILD)) { - if (unlikely(unlazy_walk(nd))) - return ERR_PTR(-ECHILD); + if (res == ERR_PTR(-ECHILD) && try_to_unlazy(nd)) res = get(link->dentry, inode, &last->done); - } } else { res = get(link->dentry, inode, &last->done); } @@ -2195,7 +2196,7 @@ OK: } if (unlikely(!d_can_lookup(nd->path.dentry))) { if (nd->flags & LOOKUP_RCU) { - if (unlazy_walk(nd)) + if (!try_to_unlazy(nd)) return -ECHILD; } return -ENOTDIR; @@ -2209,6 +2210,10 @@ static const char *path_init(struct nameidata *nd, unsigned flags) int error; const char *s = nd->name->name; + /* LOOKUP_CACHED requires RCU, ask caller to retry */ + if ((flags & (LOOKUP_RCU | LOOKUP_CACHED)) == LOOKUP_CACHED) + return ERR_PTR(-EAGAIN); + if (!*s) flags &= ~LOOKUP_RCU; if (flags & LOOKUP_RCU) @@ -3129,7 +3134,6 @@ static const char *open_last_lookups(struct nameidata *nd, struct inode *inode; struct dentry *dentry; const char *res; - int error; nd->flags |= op->intent; @@ -3153,9 +3157,8 @@ static const char *open_last_lookups(struct nameidata *nd, } else { /* create side of things */ if (nd->flags & LOOKUP_RCU) { - error = unlazy_walk(nd); - if (unlikely(error)) - return ERR_PTR(error); + if (!try_to_unlazy(nd)) + return ERR_PTR(-ECHILD); } audit_inode(nd->name, dir, AUDIT_INODE_PARENT); /* trailing slashes? */ @@ -3164,9 +3167,7 @@ static const char *open_last_lookups(struct nameidata *nd, } if (open_flag & (O_CREAT | O_TRUNC | O_WRONLY | O_RDWR)) { - error = mnt_want_write(nd->path.mnt); - if (!error) - got_write = true; + got_write = !mnt_want_write(nd->path.mnt); /* * do _not_ fail yet - we might not need that or fail with * a different error; let lookup_open() decide; we'll be @@ -3325,10 +3326,8 @@ static int do_tmpfile(struct nameidata *nd, unsigned flags, audit_inode(nd->name, child, 0); /* Don't check for other permissions, the inode was just created */ error = may_open(&path, 0, op->open_flag); - if (error) - goto out2; - file->f_path.mnt = path.mnt; - error = finish_open(file, child, NULL); + if (!error) + error = vfs_open(&path, file); out2: mnt_drop_write(path.mnt); out: diff --git a/fs/namespace.c b/fs/namespace.c index d2db7dfe232b..9d33909d0f9e 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1713,8 +1713,6 @@ static int can_umount(const struct path *path, int flags) { struct mount *mnt = real_mount(path->mnt); - if (flags & ~(MNT_FORCE | MNT_DETACH | MNT_EXPIRE | UMOUNT_NOFOLLOW)) - return -EINVAL; if (!may_mount()) return -EPERM; if (path->dentry != path->mnt->mnt_root) @@ -1728,6 +1726,7 @@ static int can_umount(const struct path *path, int flags) return 0; } +// caller is responsible for flags being sane int path_umount(struct path *path, int flags) { struct mount *mnt = real_mount(path->mnt); @@ -1749,6 +1748,10 @@ static int ksys_umount(char __user *name, int flags) struct path path; int ret; + // basic validity checks done first + if (flags & ~(MNT_FORCE | MNT_DETACH | MNT_EXPIRE | UMOUNT_NOFOLLOW)) + return -EINVAL; + if (!(flags & UMOUNT_NOFOLLOW)) lookup_flags |= LOOKUP_FOLLOW; ret = user_path_at(AT_FDCWD, name, lookup_flags, &path); diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c index 3be6836074ae..1a96ce28efb0 100644 --- a/fs/nfs/blocklayout/blocklayout.c +++ b/fs/nfs/blocklayout/blocklayout.c @@ -123,11 +123,6 @@ bl_alloc_init_bio(int npg, struct block_device *bdev, sector_t disk_sector, npg = min(npg, BIO_MAX_PAGES); bio = bio_alloc(GFP_NOIO, npg); - if (!bio && (current->flags & PF_MEMALLOC)) { - while (!bio && (npg /= 2)) - bio = bio_alloc(GFP_NOIO, npg); - } - if (bio) { bio->bi_iter.bi_sector = disk_sector; bio_set_dev(bio, bdev); diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index 79ff172eb1c8..c5348ba81129 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -1060,6 +1060,7 @@ static const struct svc_procedure nfs4_callback_procedures1[] = { .pc_decode = nfs4_decode_void, .pc_encode = nfs4_encode_void, .pc_xdrressize = 1, + .pc_name = "NULL", }, [CB_COMPOUND] = { .pc_func = nfs4_callback_compound, @@ -1067,6 +1068,7 @@ static const struct svc_procedure nfs4_callback_procedures1[] = { .pc_argsize = 256, .pc_ressize = 256, .pc_xdrressize = NFS4_CALLBACK_BUFSIZE, + .pc_name = "COMPOUND", } }; diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index 816e1427f17e..04bf8066980c 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -1011,22 +1011,24 @@ nfs_delegation_find_inode_server(struct nfs_server *server, const struct nfs_fh *fhandle) { struct nfs_delegation *delegation; - struct inode *freeme, *res = NULL; + struct super_block *freeme = NULL; + struct inode *res = NULL; list_for_each_entry_rcu(delegation, &server->delegations, super_list) { spin_lock(&delegation->lock); if (delegation->inode != NULL && !test_bit(NFS_DELEGATION_REVOKED, &delegation->flags) && nfs_compare_fh(fhandle, &NFS_I(delegation->inode)->fh) == 0) { - freeme = igrab(delegation->inode); - if (freeme && nfs_sb_active(freeme->i_sb)) - res = freeme; + if (nfs_sb_active(server->super)) { + freeme = server->super; + res = igrab(delegation->inode); + } spin_unlock(&delegation->lock); if (res != NULL) return res; if (freeme) { rcu_read_unlock(); - iput(freeme); + nfs_sb_deactive(freeme); rcu_read_lock(); } return ERR_PTR(-EAGAIN); diff --git a/fs/nfs/export.c b/fs/nfs/export.c index 7412bb164fa7..f2b34cfe286c 100644 --- a/fs/nfs/export.c +++ b/fs/nfs/export.c @@ -167,10 +167,28 @@ out: return parent; } +static u64 nfs_fetch_iversion(struct inode *inode) +{ + struct nfs_server *server = NFS_SERVER(inode); + + /* Is this the right call?: */ + nfs_revalidate_inode(server, inode); + /* + * Also, note we're ignoring any returned error. That seems to be + * the practice for cache consistency information elsewhere in + * the server, but I'm not sure why. + */ + if (server->nfs_client->rpc_ops->version >= 4) + return inode_peek_iversion_raw(inode); + else + return time_to_chattr(&inode->i_ctime); +} + const struct export_operations nfs_export_ops = { .encode_fh = nfs_encode_fh, .fh_to_dentry = nfs_fh_to_dentry, .get_parent = nfs_get_parent, + .fetch_iversion = nfs_fetch_iversion, .flags = EXPORT_OP_NOWCC|EXPORT_OP_NOSUBTREECHK| EXPORT_OP_CLOSE_BEFORE_UNLINK|EXPORT_OP_REMOTE_FS| EXPORT_OP_NOATOMIC_ATTR, diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index b840d0a91c9d..62d3189745cd 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -136,9 +136,29 @@ struct nfs_fs_context { } clone_data; }; -#define nfs_errorf(fc, fmt, ...) errorf(fc, fmt, ## __VA_ARGS__) -#define nfs_invalf(fc, fmt, ...) invalf(fc, fmt, ## __VA_ARGS__) -#define nfs_warnf(fc, fmt, ...) warnf(fc, fmt, ## __VA_ARGS__) +#define nfs_errorf(fc, fmt, ...) ((fc)->log.log ? \ + errorf(fc, fmt, ## __VA_ARGS__) : \ + ({ dprintk(fmt "\n", ## __VA_ARGS__); })) + +#define nfs_ferrorf(fc, fac, fmt, ...) ((fc)->log.log ? \ + errorf(fc, fmt, ## __VA_ARGS__) : \ + ({ dfprintk(fac, fmt "\n", ## __VA_ARGS__); })) + +#define nfs_invalf(fc, fmt, ...) ((fc)->log.log ? \ + invalf(fc, fmt, ## __VA_ARGS__) : \ + ({ dprintk(fmt "\n", ## __VA_ARGS__); -EINVAL; })) + +#define nfs_finvalf(fc, fac, fmt, ...) ((fc)->log.log ? \ + invalf(fc, fmt, ## __VA_ARGS__) : \ + ({ dfprintk(fac, fmt "\n", ## __VA_ARGS__); -EINVAL; })) + +#define nfs_warnf(fc, fmt, ...) ((fc)->log.log ? \ + warnf(fc, fmt, ## __VA_ARGS__) : \ + ({ dprintk(fmt "\n", ## __VA_ARGS__); })) + +#define nfs_fwarnf(fc, fac, fmt, ...) ((fc)->log.log ? \ + warnf(fc, fmt, ## __VA_ARGS__) : \ + ({ dfprintk(fac, fmt "\n", ## __VA_ARGS__); })) static inline struct nfs_fs_context *nfs_fc2context(const struct fs_context *fc) { @@ -579,12 +599,14 @@ extern void nfs4_test_session_trunk(struct rpc_clnt *clnt, static inline struct inode *nfs_igrab_and_active(struct inode *inode) { - inode = igrab(inode); - if (inode != NULL && !nfs_sb_active(inode->i_sb)) { - iput(inode); - inode = NULL; + struct super_block *sb = inode->i_sb; + + if (sb && nfs_sb_active(sb)) { + if (igrab(inode)) + return inode; + nfs_sb_deactive(sb); } - return inode; + return NULL; } static inline void nfs_iput_and_deactive(struct inode *inode) diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index 57b3821d975a..441a2fa073c8 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -420,7 +420,9 @@ static const struct nfs4_ssc_client_ops nfs4_ssc_clnt_ops_tbl = { */ void nfs42_ssc_register_ops(void) { +#ifdef CONFIG_NFSD_V4 nfs42_ssc_register(&nfs4_ssc_clnt_ops_tbl); +#endif } /** @@ -431,7 +433,9 @@ void nfs42_ssc_register_ops(void) */ void nfs42_ssc_unregister_ops(void) { +#ifdef CONFIG_NFSD_V4 nfs42_ssc_unregister(&nfs4_ssc_clnt_ops_tbl); +#endif } #endif /* CONFIG_NFS_V4_2 */ diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 0ce04e0e5d82..2f4679a62712 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -3536,10 +3536,8 @@ static void nfs4_close_done(struct rpc_task *task, void *data) trace_nfs4_close(state, &calldata->arg, &calldata->res, task->tk_status); /* Handle Layoutreturn errors */ - if (pnfs_roc_done(task, calldata->inode, - &calldata->arg.lr_args, - &calldata->res.lr_res, - &calldata->res.lr_ret) == -EAGAIN) + if (pnfs_roc_done(task, &calldata->arg.lr_args, &calldata->res.lr_res, + &calldata->res.lr_ret) == -EAGAIN) goto out_restart; /* hmm. we are done with the inode, and in the process of freeing @@ -6384,10 +6382,8 @@ static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata) trace_nfs4_delegreturn_exit(&data->args, &data->res, task->tk_status); /* Handle Layoutreturn errors */ - if (pnfs_roc_done(task, data->inode, - &data->args.lr_args, - &data->res.lr_res, - &data->res.lr_ret) == -EAGAIN) + if (pnfs_roc_done(task, &data->args.lr_args, &data->res.lr_res, + &data->res.lr_ret) == -EAGAIN) goto out_restart; switch (task->tk_status) { @@ -6441,10 +6437,10 @@ static void nfs4_delegreturn_release(void *calldata) struct nfs4_delegreturndata *data = calldata; struct inode *inode = data->inode; + if (data->lr.roc) + pnfs_roc_release(&data->lr.arg, &data->lr.res, + data->res.lr_ret); if (inode) { - if (data->lr.roc) - pnfs_roc_release(&data->lr.arg, &data->lr.res, - data->res.lr_ret); nfs_post_op_update_inode_force_wcc(inode, &data->fattr); nfs_iput_and_deactive(inode); } @@ -6520,16 +6516,14 @@ static int _nfs4_proc_delegreturn(struct inode *inode, const struct cred *cred, nfs_fattr_init(data->res.fattr); data->timestamp = jiffies; data->rpc_status = 0; - data->lr.roc = pnfs_roc(inode, &data->lr.arg, &data->lr.res, cred); data->inode = nfs_igrab_and_active(inode); - if (data->inode) { + if (data->inode || issync) { + data->lr.roc = pnfs_roc(inode, &data->lr.arg, &data->lr.res, + cred); if (data->lr.roc) { data->args.lr_args = &data->lr.arg; data->res.lr_res = &data->lr.res; } - } else if (data->lr.roc) { - pnfs_roc_release(&data->lr.arg, &data->lr.res, 0); - data->lr.roc = false; } task_setup_data.callback_data = data; @@ -7111,9 +7105,9 @@ static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *f data->arg.new_lock_owner, ret); } else data->cancelled = true; + trace_nfs4_set_lock(fl, state, &data->res.stateid, cmd, ret); rpc_put_task(task); dprintk("%s: done, ret = %d!\n", __func__, ret); - trace_nfs4_set_lock(fl, state, &data->res.stateid, cmd, ret); return ret; } diff --git a/fs/nfs/nfs4super.c b/fs/nfs/nfs4super.c index 984cc42ee54d..d09bcfd7db89 100644 --- a/fs/nfs/nfs4super.c +++ b/fs/nfs/nfs4super.c @@ -227,7 +227,7 @@ int nfs4_try_get_tree(struct fs_context *fc) fc, ctx->nfs_server.hostname, ctx->nfs_server.export_path); if (err) { - nfs_errorf(fc, "NFS4: Couldn't follow remote path"); + nfs_ferrorf(fc, MOUNT, "NFS4: Couldn't follow remote path"); dfprintk(MOUNT, "<-- nfs4_try_get_tree() = %d [error]\n", err); } else { dfprintk(MOUNT, "<-- nfs4_try_get_tree() = 0\n"); @@ -250,7 +250,7 @@ int nfs4_get_referral_tree(struct fs_context *fc) fc, ctx->nfs_server.hostname, ctx->nfs_server.export_path); if (err) { - nfs_errorf(fc, "NFS4: Couldn't follow remote path"); + nfs_ferrorf(fc, MOUNT, "NFS4: Couldn't follow remote path"); dfprintk(MOUNT, "<-- nfs4_get_referral_tree() = %d [error]\n", err); } else { dfprintk(MOUNT, "<-- nfs4_get_referral_tree() = 0\n"); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 07f59dc8cb2e..af64b4e6fd1f 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -324,6 +324,21 @@ pnfs_grab_inode_layout_hdr(struct pnfs_layout_hdr *lo) return NULL; } +/* + * Compare 2 layout stateid sequence ids, to see which is newer, + * taking into account wraparound issues. + */ +static bool pnfs_seqid_is_newer(u32 s1, u32 s2) +{ + return (s32)(s1 - s2) > 0; +} + +static void pnfs_barrier_update(struct pnfs_layout_hdr *lo, u32 newseq) +{ + if (pnfs_seqid_is_newer(newseq, lo->plh_barrier)) + lo->plh_barrier = newseq; +} + static void pnfs_set_plh_return_info(struct pnfs_layout_hdr *lo, enum pnfs_iomode iomode, u32 seq) @@ -335,6 +350,7 @@ pnfs_set_plh_return_info(struct pnfs_layout_hdr *lo, enum pnfs_iomode iomode, if (seq != 0) { WARN_ON_ONCE(lo->plh_return_seq != 0 && lo->plh_return_seq != seq); lo->plh_return_seq = seq; + pnfs_barrier_update(lo, seq); } } @@ -639,15 +655,6 @@ static int mark_lseg_invalid(struct pnfs_layout_segment *lseg, return rv; } -/* - * Compare 2 layout stateid sequence ids, to see which is newer, - * taking into account wraparound issues. - */ -static bool pnfs_seqid_is_newer(u32 s1, u32 s2) -{ - return (s32)(s1 - s2) > 0; -} - static bool pnfs_should_free_range(const struct pnfs_layout_range *lseg_range, const struct pnfs_layout_range *recall_range) @@ -984,8 +991,7 @@ pnfs_set_layout_stateid(struct pnfs_layout_hdr *lo, const nfs4_stateid *new, new_barrier = be32_to_cpu(new->seqid); else if (new_barrier == 0) return; - if (pnfs_seqid_is_newer(new_barrier, lo->plh_barrier)) - lo->plh_barrier = new_barrier; + pnfs_barrier_update(lo, new_barrier); } static bool @@ -994,7 +1000,7 @@ pnfs_layout_stateid_blocked(const struct pnfs_layout_hdr *lo, { u32 seqid = be32_to_cpu(stateid->seqid); - return !pnfs_seqid_is_newer(seqid, lo->plh_barrier); + return !pnfs_seqid_is_newer(seqid, lo->plh_barrier) && lo->plh_barrier; } /* lget is set to 1 if called from inside send_layoutget call chain */ @@ -1152,7 +1158,7 @@ void pnfs_layoutreturn_free_lsegs(struct pnfs_layout_hdr *lo, LIST_HEAD(freeme); spin_lock(&inode->i_lock); - if (!pnfs_layout_is_valid(lo) || !arg_stateid || + if (!pnfs_layout_is_valid(lo) || !nfs4_stateid_match_other(&lo->plh_stateid, arg_stateid)) goto out_unlock; if (stateid) { @@ -1183,20 +1189,17 @@ pnfs_prepare_layoutreturn(struct pnfs_layout_hdr *lo, return false; set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags); pnfs_get_layout_hdr(lo); + nfs4_stateid_copy(stateid, &lo->plh_stateid); + *cred = get_cred(lo->plh_lc_cred); if (test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags)) { - nfs4_stateid_copy(stateid, &lo->plh_stateid); - *cred = get_cred(lo->plh_lc_cred); if (lo->plh_return_seq != 0) stateid->seqid = cpu_to_be32(lo->plh_return_seq); if (iomode != NULL) *iomode = lo->plh_return_iomode; pnfs_clear_layoutreturn_info(lo); - return true; - } - nfs4_stateid_copy(stateid, &lo->plh_stateid); - *cred = get_cred(lo->plh_lc_cred); - if (iomode != NULL) + } else if (iomode != NULL) *iomode = IOMODE_ANY; + pnfs_barrier_update(lo, be32_to_cpu(stateid->seqid)); return true; } @@ -1509,10 +1512,8 @@ out_noroc: return false; } -int pnfs_roc_done(struct rpc_task *task, struct inode *inode, - struct nfs4_layoutreturn_args **argpp, - struct nfs4_layoutreturn_res **respp, - int *ret) +int pnfs_roc_done(struct rpc_task *task, struct nfs4_layoutreturn_args **argpp, + struct nfs4_layoutreturn_res **respp, int *ret) { struct nfs4_layoutreturn_args *arg = *argpp; int retval = -EAGAIN; @@ -1545,7 +1546,7 @@ int pnfs_roc_done(struct rpc_task *task, struct inode *inode, return 0; case -NFS4ERR_OLD_STATEID: if (!nfs4_layout_refresh_old_stateid(&arg->stateid, - &arg->range, inode)) + &arg->range, arg->inode)) break; *ret = -NFS4ERR_NOMATCHING_LAYOUT; return -EAGAIN; @@ -1560,23 +1561,28 @@ void pnfs_roc_release(struct nfs4_layoutreturn_args *args, int ret) { struct pnfs_layout_hdr *lo = args->layout; - const nfs4_stateid *arg_stateid = NULL; + struct inode *inode = args->inode; const nfs4_stateid *res_stateid = NULL; struct nfs4_xdr_opaque_data *ld_private = args->ld_private; switch (ret) { case -NFS4ERR_NOMATCHING_LAYOUT: + spin_lock(&inode->i_lock); + if (pnfs_layout_is_valid(lo) && + nfs4_stateid_match_other(&args->stateid, &lo->plh_stateid)) + pnfs_set_plh_return_info(lo, args->range.iomode, 0); + pnfs_clear_layoutreturn_waitbit(lo); + spin_unlock(&inode->i_lock); break; case 0: if (res->lrs_present) res_stateid = &res->stateid; fallthrough; default: - arg_stateid = &args->stateid; + pnfs_layoutreturn_free_lsegs(lo, &args->stateid, &args->range, + res_stateid); } trace_nfs4_layoutreturn_on_close(args->inode, &args->stateid, ret); - pnfs_layoutreturn_free_lsegs(lo, arg_stateid, &args->range, - res_stateid); if (ld_private && ld_private->ops && ld_private->ops->free) ld_private->ops->free(ld_private); pnfs_put_layout_hdr(lo); @@ -1906,6 +1912,11 @@ static void nfs_layoutget_end(struct pnfs_layout_hdr *lo) wake_up_var(&lo->plh_outstanding); } +static bool pnfs_is_first_layoutget(struct pnfs_layout_hdr *lo) +{ + return test_bit(NFS_LAYOUT_FIRST_LAYOUTGET, &lo->plh_flags); +} + static void pnfs_clear_first_layoutget(struct pnfs_layout_hdr *lo) { unsigned long *bitlock = &lo->plh_flags; @@ -2015,6 +2026,27 @@ lookup_again: goto lookup_again; } + /* + * Because we free lsegs when sending LAYOUTRETURN, we need to wait + * for LAYOUTRETURN. + */ + if (test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags)) { + spin_unlock(&ino->i_lock); + dprintk("%s wait for layoutreturn\n", __func__); + lseg = ERR_PTR(pnfs_prepare_to_retry_layoutget(lo)); + if (!IS_ERR(lseg)) { + pnfs_put_layout_hdr(lo); + dprintk("%s retrying\n", __func__); + trace_pnfs_update_layout(ino, pos, count, iomode, lo, + lseg, + PNFS_UPDATE_LAYOUT_RETRY); + goto lookup_again; + } + trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg, + PNFS_UPDATE_LAYOUT_RETURN); + goto out_put_layout_hdr; + } + lseg = pnfs_find_lseg(lo, &arg, strict_iomode); if (lseg) { trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg, @@ -2067,28 +2099,6 @@ lookup_again: nfs4_stateid_copy(&stateid, &lo->plh_stateid); } - /* - * Because we free lsegs before sending LAYOUTRETURN, we need to wait - * for LAYOUTRETURN even if first is true. - */ - if (test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags)) { - spin_unlock(&ino->i_lock); - dprintk("%s wait for layoutreturn\n", __func__); - lseg = ERR_PTR(pnfs_prepare_to_retry_layoutget(lo)); - if (!IS_ERR(lseg)) { - if (first) - pnfs_clear_first_layoutget(lo); - pnfs_put_layout_hdr(lo); - dprintk("%s retrying\n", __func__); - trace_pnfs_update_layout(ino, pos, count, iomode, lo, - lseg, PNFS_UPDATE_LAYOUT_RETRY); - goto lookup_again; - } - trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg, - PNFS_UPDATE_LAYOUT_RETURN); - goto out_put_layout_hdr; - } - if (pnfs_layoutgets_blocked(lo)) { trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg, PNFS_UPDATE_LAYOUT_BLOCKED); @@ -2242,6 +2252,7 @@ static void _lgopen_prepare_attached(struct nfs4_opendata *data, &rng, GFP_KERNEL); if (!lgp) { pnfs_clear_first_layoutget(lo); + nfs_layoutget_end(lo); pnfs_put_layout_hdr(lo); return; } @@ -2380,23 +2391,34 @@ pnfs_layout_process(struct nfs4_layoutget *lgp) goto out_forget; } - if (!pnfs_layout_is_valid(lo)) { - /* We have a completely new layout */ - pnfs_set_layout_stateid(lo, &res->stateid, lgp->cred, true); - } else if (nfs4_stateid_match_other(&lo->plh_stateid, &res->stateid)) { + if (nfs4_stateid_match_other(&lo->plh_stateid, &res->stateid)) { /* existing state ID, make sure the sequence number matches. */ if (pnfs_layout_stateid_blocked(lo, &res->stateid)) { + if (!pnfs_layout_is_valid(lo) && + pnfs_is_first_layoutget(lo)) + lo->plh_barrier = 0; dprintk("%s forget reply due to sequence\n", __func__); goto out_forget; } pnfs_set_layout_stateid(lo, &res->stateid, lgp->cred, false); - } else { + } else if (pnfs_layout_is_valid(lo)) { /* * We got an entirely new state ID. Mark all segments for the * inode invalid, and retry the layoutget */ - pnfs_mark_layout_stateid_invalid(lo, &free_me); + struct pnfs_layout_range range = { + .iomode = IOMODE_ANY, + .length = NFS4_MAX_UINT64, + }; + pnfs_set_plh_return_info(lo, IOMODE_ANY, 0); + pnfs_mark_matching_lsegs_return(lo, &lo->plh_return_segs, + &range, 0); goto out_forget; + } else { + /* We have a completely new layout */ + if (!pnfs_is_first_layoutget(lo)) + goto out_forget; + pnfs_set_layout_stateid(lo, &res->stateid, lgp->cred, true); } pnfs_get_lseg(lseg); diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index bbd3de1025f2..d810ae674f4e 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -297,10 +297,8 @@ bool pnfs_roc(struct inode *ino, struct nfs4_layoutreturn_args *args, struct nfs4_layoutreturn_res *res, const struct cred *cred); -int pnfs_roc_done(struct rpc_task *task, struct inode *inode, - struct nfs4_layoutreturn_args **argpp, - struct nfs4_layoutreturn_res **respp, - int *ret); +int pnfs_roc_done(struct rpc_task *task, struct nfs4_layoutreturn_args **argpp, + struct nfs4_layoutreturn_res **respp, int *ret); void pnfs_roc_release(struct nfs4_layoutreturn_args *args, struct nfs4_layoutreturn_res *res, int ret); @@ -772,7 +770,7 @@ pnfs_roc(struct inode *ino, } static inline int -pnfs_roc_done(struct rpc_task *task, struct inode *inode, +pnfs_roc_done(struct rpc_task *task, struct nfs4_layoutreturn_args **argpp, struct nfs4_layoutreturn_res **respp, int *ret) diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index 2efcfdd348a1..49d3389bd813 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -78,22 +78,18 @@ void pnfs_generic_clear_request_commit(struct nfs_page *req, struct nfs_commit_info *cinfo) { - struct pnfs_layout_segment *freeme = NULL; + struct pnfs_commit_bucket *bucket = NULL; if (!test_and_clear_bit(PG_COMMIT_TO_DS, &req->wb_flags)) goto out; cinfo->ds->nwritten--; - if (list_is_singular(&req->wb_list)) { - struct pnfs_commit_bucket *bucket; - + if (list_is_singular(&req->wb_list)) bucket = list_first_entry(&req->wb_list, - struct pnfs_commit_bucket, - written); - freeme = pnfs_free_bucket_lseg(bucket); - } + struct pnfs_commit_bucket, written); out: nfs_request_remove_commit_list(req, cinfo); - pnfs_put_lseg(freeme); + if (bucket) + pnfs_put_lseg(pnfs_free_bucket_lseg(bucket)); } EXPORT_SYMBOL_GPL(pnfs_generic_clear_request_commit); @@ -407,12 +403,16 @@ pnfs_bucket_get_committing(struct list_head *head, struct pnfs_commit_bucket *bucket, struct nfs_commit_info *cinfo) { + struct pnfs_layout_segment *lseg; struct list_head *pos; list_for_each(pos, &bucket->committing) cinfo->ds->ncommitting--; list_splice_init(&bucket->committing, head); - return pnfs_free_bucket_lseg(bucket); + lseg = pnfs_free_bucket_lseg(bucket); + if (!lseg) + lseg = pnfs_get_lseg(bucket->lseg); + return lseg; } static struct nfs_commit_data * @@ -424,8 +424,6 @@ pnfs_bucket_fetch_commitdata(struct pnfs_commit_bucket *bucket, if (!data) return NULL; data->lseg = pnfs_bucket_get_committing(&data->pages, bucket, cinfo); - if (!data->lseg) - data->lseg = pnfs_get_lseg(bucket->lseg); return data; } diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 4034102010f0..c7a924580eec 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -86,9 +86,11 @@ const struct super_operations nfs_sops = { }; EXPORT_SYMBOL_GPL(nfs_sops); +#ifdef CONFIG_NFS_V4_2 static const struct nfs_ssc_client_ops nfs_ssc_clnt_ops_tbl = { .sco_sb_deactive = nfs_sb_deactive, }; +#endif #if IS_ENABLED(CONFIG_NFS_V4) static int __init register_nfs4_fs(void) @@ -111,15 +113,21 @@ static void unregister_nfs4_fs(void) } #endif +#ifdef CONFIG_NFS_V4_2 static void nfs_ssc_register_ops(void) { +#ifdef CONFIG_NFSD_V4 nfs_ssc_register(&nfs_ssc_clnt_ops_tbl); +#endif } static void nfs_ssc_unregister_ops(void) { +#ifdef CONFIG_NFSD_V4 nfs_ssc_unregister(&nfs_ssc_clnt_ops_tbl); +#endif } +#endif /* CONFIG_NFS_V4_2 */ static struct shrinker acl_shrinker = { .count_objects = nfs_access_cache_count, @@ -148,7 +156,9 @@ int __init register_nfs_fs(void) ret = register_shrinker(&acl_shrinker); if (ret < 0) goto error_3; +#ifdef CONFIG_NFS_V4_2 nfs_ssc_register_ops(); +#endif return 0; error_3: nfs_unregister_sysctl(); @@ -168,7 +178,9 @@ void __exit unregister_nfs_fs(void) unregister_shrinker(&acl_shrinker); nfs_unregister_sysctl(); unregister_nfs4_fs(); +#ifdef CONFIG_NFS_V4_2 nfs_ssc_unregister_ops(); +#endif unregister_filesystem(&nfs_fs_type); } diff --git a/fs/nfs_common/Makefile b/fs/nfs_common/Makefile index fa82f5aaa6d9..119c75ab9fd0 100644 --- a/fs/nfs_common/Makefile +++ b/fs/nfs_common/Makefile @@ -7,4 +7,4 @@ obj-$(CONFIG_NFS_ACL_SUPPORT) += nfs_acl.o nfs_acl-objs := nfsacl.o obj-$(CONFIG_GRACE_PERIOD) += grace.o -obj-$(CONFIG_GRACE_PERIOD) += nfs_ssc.o +obj-$(CONFIG_NFS_V4_2_SSC_HELPER) += nfs_ssc.o diff --git a/fs/nfs_common/nfs_ssc.c b/fs/nfs_common/nfs_ssc.c index f43bbb373913..7c1509e968c8 100644 --- a/fs/nfs_common/nfs_ssc.c +++ b/fs/nfs_common/nfs_ssc.c @@ -1,7 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * fs/nfs_common/nfs_ssc_comm.c - * * Helper for knfsd's SSC to access ops in NFS client modules * * Author: Dai Ngo <dai.ngo@oracle.com> diff --git a/fs/nfs_common/nfsacl.c b/fs/nfs_common/nfsacl.c index d056ad2fdefd..79c563c1a5e8 100644 --- a/fs/nfs_common/nfsacl.c +++ b/fs/nfs_common/nfsacl.c @@ -295,3 +295,55 @@ int nfsacl_decode(struct xdr_buf *buf, unsigned int base, unsigned int *aclcnt, nfsacl_desc.desc.array_len; } EXPORT_SYMBOL_GPL(nfsacl_decode); + +/** + * nfs_stream_decode_acl - Decode an NFSv3 ACL + * + * @xdr: an xdr_stream positioned at an encoded ACL + * @aclcnt: OUT: count of ACEs in decoded posix_acl + * @pacl: OUT: a dynamically-allocated buffer containing the decoded posix_acl + * + * Return values: + * %false: The encoded ACL is not valid + * %true: @pacl contains a decoded ACL, and @xdr is advanced + * + * On a successful return, caller must release *pacl using posix_acl_release(). + */ +bool nfs_stream_decode_acl(struct xdr_stream *xdr, unsigned int *aclcnt, + struct posix_acl **pacl) +{ + const size_t elem_size = XDR_UNIT * 3; + struct nfsacl_decode_desc nfsacl_desc = { + .desc = { + .elem_size = elem_size, + .xcode = pacl ? xdr_nfsace_decode : NULL, + }, + }; + unsigned int base; + u32 entries; + + if (xdr_stream_decode_u32(xdr, &entries) < 0) + return false; + if (entries > NFS_ACL_MAX_ENTRIES) + return false; + + base = xdr_stream_pos(xdr); + if (!xdr_inline_decode(xdr, XDR_UNIT + elem_size * entries)) + return false; + nfsacl_desc.desc.array_maxlen = entries; + if (xdr_decode_array2(xdr->buf, base, &nfsacl_desc.desc)) + return false; + + if (pacl) { + if (entries != nfsacl_desc.desc.array_len || + posix_acl_from_nfsacl(nfsacl_desc.acl) != 0) { + posix_acl_release(nfsacl_desc.acl); + return false; + } + *pacl = nfsacl_desc.acl; + } + if (aclcnt) + *aclcnt = entries; + return true; +} +EXPORT_SYMBOL_GPL(nfs_stream_decode_acl); diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig index dbbc583d6273..821e5913faee 100644 --- a/fs/nfsd/Kconfig +++ b/fs/nfsd/Kconfig @@ -76,6 +76,7 @@ config NFSD_V4 select CRYPTO_MD5 select CRYPTO_SHA256 select GRACE_PERIOD + select NFS_V4_2_SSC_HELPER if NFS_V4_2 help This option enables support in your system's NFS server for version 4 of the NFS protocol (RFC 3530). diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c index a07c39c94bbd..1058659a8d31 100644 --- a/fs/nfsd/blocklayout.c +++ b/fs/nfsd/blocklayout.c @@ -254,7 +254,7 @@ again: req->cmd[4] = bufflen & 0xff; req->cmd_len = COMMAND_SIZE(INQUIRY); - blk_execute_rq(rq->q, NULL, rq, 1); + blk_execute_rq(NULL, rq, 1); if (req->result) { pr_err("pNFS: INQUIRY 0x83 failed with: %x\n", req->result); diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index 81e7bb12aca6..7c863f2c21e0 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -331,12 +331,29 @@ static void nfsd4_fslocs_free(struct nfsd4_fs_locations *fsloc) fsloc->locations = NULL; } +static int export_stats_init(struct export_stats *stats) +{ + stats->start_time = ktime_get_seconds(); + return nfsd_percpu_counters_init(stats->counter, EXP_STATS_COUNTERS_NUM); +} + +static void export_stats_reset(struct export_stats *stats) +{ + nfsd_percpu_counters_reset(stats->counter, EXP_STATS_COUNTERS_NUM); +} + +static void export_stats_destroy(struct export_stats *stats) +{ + nfsd_percpu_counters_destroy(stats->counter, EXP_STATS_COUNTERS_NUM); +} + static void svc_export_put(struct kref *ref) { struct svc_export *exp = container_of(ref, struct svc_export, h.ref); path_put(&exp->ex_path); auth_domain_put(exp->ex_client); nfsd4_fslocs_free(&exp->ex_fslocs); + export_stats_destroy(&exp->ex_stats); kfree(exp->ex_uuid); kfree_rcu(exp, ex_rcu); } @@ -692,22 +709,47 @@ static void exp_flags(struct seq_file *m, int flag, int fsid, kuid_t anonu, kgid_t anong, struct nfsd4_fs_locations *fslocs); static void show_secinfo(struct seq_file *m, struct svc_export *exp); +static int is_export_stats_file(struct seq_file *m) +{ + /* + * The export_stats file uses the same ops as the exports file. + * We use the file's name to determine the reported info per export. + * There is no rename in nsfdfs, so d_name.name is stable. + */ + return !strcmp(m->file->f_path.dentry->d_name.name, "export_stats"); +} + static int svc_export_show(struct seq_file *m, struct cache_detail *cd, struct cache_head *h) { - struct svc_export *exp ; + struct svc_export *exp; + bool export_stats = is_export_stats_file(m); - if (h ==NULL) { - seq_puts(m, "#path domain(flags)\n"); + if (h == NULL) { + if (export_stats) + seq_puts(m, "#path domain start-time\n#\tstats\n"); + else + seq_puts(m, "#path domain(flags)\n"); return 0; } exp = container_of(h, struct svc_export, h); seq_path(m, &exp->ex_path, " \t\n\\"); seq_putc(m, '\t'); seq_escape(m, exp->ex_client->name, " \t\n\\"); + if (export_stats) { + seq_printf(m, "\t%lld\n", exp->ex_stats.start_time); + seq_printf(m, "\tfh_stale: %lld\n", + percpu_counter_sum_positive(&exp->ex_stats.counter[EXP_STATS_FH_STALE])); + seq_printf(m, "\tio_read: %lld\n", + percpu_counter_sum_positive(&exp->ex_stats.counter[EXP_STATS_IO_READ])); + seq_printf(m, "\tio_write: %lld\n", + percpu_counter_sum_positive(&exp->ex_stats.counter[EXP_STATS_IO_WRITE])); + seq_putc(m, '\n'); + return 0; + } seq_putc(m, '('); - if (test_bit(CACHE_VALID, &h->flags) && + if (test_bit(CACHE_VALID, &h->flags) && !test_bit(CACHE_NEGATIVE, &h->flags)) { exp_flags(m, exp->ex_flags, exp->ex_fsid, exp->ex_anon_uid, exp->ex_anon_gid, &exp->ex_fslocs); @@ -748,6 +790,7 @@ static void svc_export_init(struct cache_head *cnew, struct cache_head *citem) new->ex_layout_types = 0; new->ex_uuid = NULL; new->cd = item->cd; + export_stats_reset(&new->ex_stats); } static void export_update(struct cache_head *cnew, struct cache_head *citem) @@ -780,10 +823,15 @@ static void export_update(struct cache_head *cnew, struct cache_head *citem) static struct cache_head *svc_export_alloc(void) { struct svc_export *i = kmalloc(sizeof(*i), GFP_KERNEL); - if (i) - return &i->h; - else + if (!i) + return NULL; + + if (export_stats_init(&i->ex_stats)) { + kfree(i); return NULL; + } + + return &i->h; } static const struct cache_detail svc_export_cache_template = { @@ -1245,10 +1293,14 @@ static int e_show(struct seq_file *m, void *p) struct cache_head *cp = p; struct svc_export *exp = container_of(cp, struct svc_export, h); struct cache_detail *cd = m->private; + bool export_stats = is_export_stats_file(m); if (p == SEQ_START_TOKEN) { seq_puts(m, "# Version 1.1\n"); - seq_puts(m, "# Path Client(Flags) # IPs\n"); + if (export_stats) + seq_puts(m, "# Path Client Start-time\n#\tStats\n"); + else + seq_puts(m, "# Path Client(Flags) # IPs\n"); return 0; } diff --git a/fs/nfsd/export.h b/fs/nfsd/export.h index e7daa1f246f0..ee0e3aba4a6e 100644 --- a/fs/nfsd/export.h +++ b/fs/nfsd/export.h @@ -6,6 +6,7 @@ #define NFSD_EXPORT_H #include <linux/sunrpc/cache.h> +#include <linux/percpu_counter.h> #include <uapi/linux/nfsd/export.h> #include <linux/nfs4.h> @@ -46,6 +47,19 @@ struct exp_flavor_info { u32 flags; }; +/* Per-export stats */ +enum { + EXP_STATS_FH_STALE, + EXP_STATS_IO_READ, + EXP_STATS_IO_WRITE, + EXP_STATS_COUNTERS_NUM +}; + +struct export_stats { + time64_t start_time; + struct percpu_counter counter[EXP_STATS_COUNTERS_NUM]; +}; + struct svc_export { struct cache_head h; struct auth_domain * ex_client; @@ -62,6 +76,7 @@ struct svc_export { struct nfsd4_deviceid_map *ex_devid_map; struct cache_detail *cd; struct rcu_head ex_rcu; + struct export_stats ex_stats; }; /* an "export key" (expkey) maps a filehandlefragement to an diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h index 7346acda9d76..c330f5bd0cf3 100644 --- a/fs/nfsd/netns.h +++ b/fs/nfsd/netns.h @@ -10,6 +10,7 @@ #include <net/net_namespace.h> #include <net/netns/generic.h> +#include <linux/percpu_counter.h> /* Hash tables for nfs4_clientid state */ #define CLIENT_HASH_BITS 4 @@ -21,6 +22,14 @@ struct cld_net; struct nfsd4_client_tracking_ops; +enum { + /* cache misses due only to checksum comparison failures */ + NFSD_NET_PAYLOAD_MISSES, + /* amount of memory (in bytes) currently consumed by the DRC */ + NFSD_NET_DRC_MEM_USAGE, + NFSD_NET_COUNTERS_NUM +}; + /* * Represents a nfsd "container". With respect to nfsv4 state tracking, the * fields of interest are the *_id_hashtbls and the *_name_tree. These track @@ -149,20 +158,16 @@ struct nfsd_net { /* * Stats and other tracking of on the duplicate reply cache. - * These fields and the "rc" fields in nfsdstats are modified - * with only the per-bucket cache lock, which isn't really safe - * and should be fixed if we want the statistics to be - * completely accurate. + * The longest_chain* fields are modified with only the per-bucket + * cache lock, which isn't really safe and should be fixed if we want + * these statistics to be completely accurate. */ /* total number of entries */ atomic_t num_drc_entries; - /* cache misses due only to checksum comparison failures */ - unsigned int payload_misses; - - /* amount of memory (in bytes) currently consumed by the DRC */ - unsigned int drc_mem_usage; + /* Per-netns stats counters */ + struct percpu_counter counter[NFSD_NET_COUNTERS_NUM]; /* longest hash chain seen */ unsigned int longest_chain; diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index b0f66604532a..7eeac5b81c20 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -188,63 +188,49 @@ out: static int nfsaclsvc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p) { + struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_getaclargs *argp = rqstp->rq_argp; - p = nfs2svc_decode_fh(p, &argp->fh); - if (!p) + if (!svcxdr_decode_fhandle(xdr, &argp->fh)) + return 0; + if (xdr_stream_decode_u32(xdr, &argp->mask) < 0) return 0; - argp->mask = ntohl(*p); p++; - return xdr_argsize_check(rqstp, p); + return 1; } - static int nfsaclsvc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p) { + struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_setaclargs *argp = rqstp->rq_argp; - struct kvec *head = rqstp->rq_arg.head; - unsigned int base; - int n; - p = nfs2svc_decode_fh(p, &argp->fh); - if (!p) + if (!svcxdr_decode_fhandle(xdr, &argp->fh)) return 0; - argp->mask = ntohl(*p++); - if (argp->mask & ~NFS_ACL_MASK || - !xdr_argsize_check(rqstp, p)) + if (xdr_stream_decode_u32(xdr, &argp->mask) < 0) return 0; - - base = (char *)p - (char *)head->iov_base; - n = nfsacl_decode(&rqstp->rq_arg, base, NULL, - (argp->mask & NFS_ACL) ? - &argp->acl_access : NULL); - if (n > 0) - n = nfsacl_decode(&rqstp->rq_arg, base + n, NULL, - (argp->mask & NFS_DFACL) ? - &argp->acl_default : NULL); - return (n > 0); -} - -static int nfsaclsvc_decode_fhandleargs(struct svc_rqst *rqstp, __be32 *p) -{ - struct nfsd_fhandle *argp = rqstp->rq_argp; - - p = nfs2svc_decode_fh(p, &argp->fh); - if (!p) + if (argp->mask & ~NFS_ACL_MASK) + return 0; + if (!nfs_stream_decode_acl(xdr, NULL, (argp->mask & NFS_ACL) ? + &argp->acl_access : NULL)) return 0; - return xdr_argsize_check(rqstp, p); + if (!nfs_stream_decode_acl(xdr, NULL, (argp->mask & NFS_DFACL) ? + &argp->acl_default : NULL)) + return 0; + + return 1; } static int nfsaclsvc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p) { - struct nfsd3_accessargs *argp = rqstp->rq_argp; + struct xdr_stream *xdr = &rqstp->rq_arg_stream; + struct nfsd3_accessargs *args = rqstp->rq_argp; - p = nfs2svc_decode_fh(p, &argp->fh); - if (!p) + if (!svcxdr_decode_fhandle(xdr, &args->fh)) + return 0; + if (xdr_stream_decode_u32(xdr, &args->access) < 0) return 0; - argp->access = ntohl(*p++); - return xdr_argsize_check(rqstp, p); + return 1; } /* @@ -371,6 +357,7 @@ static const struct svc_procedure nfsd_acl_procedures2[5] = { .pc_ressize = sizeof(struct nfsd_voidres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST, + .pc_name = "NULL", }, [ACLPROC2_GETACL] = { .pc_func = nfsacld_proc_getacl, @@ -381,6 +368,7 @@ static const struct svc_procedure nfsd_acl_procedures2[5] = { .pc_ressize = sizeof(struct nfsd3_getaclres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+1+2*(1+ACL), + .pc_name = "GETACL", }, [ACLPROC2_SETACL] = { .pc_func = nfsacld_proc_setacl, @@ -391,16 +379,18 @@ static const struct svc_procedure nfsd_acl_procedures2[5] = { .pc_ressize = sizeof(struct nfsd_attrstat), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+AT, + .pc_name = "SETACL", }, [ACLPROC2_GETATTR] = { .pc_func = nfsacld_proc_getattr, - .pc_decode = nfsaclsvc_decode_fhandleargs, + .pc_decode = nfssvc_decode_fhandleargs, .pc_encode = nfsaclsvc_encode_attrstatres, .pc_release = nfsaclsvc_release_attrstat, .pc_argsize = sizeof(struct nfsd_fhandle), .pc_ressize = sizeof(struct nfsd_attrstat), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+AT, + .pc_name = "GETATTR", }, [ACLPROC2_ACCESS] = { .pc_func = nfsacld_proc_access, @@ -411,6 +401,7 @@ static const struct svc_procedure nfsd_acl_procedures2[5] = { .pc_ressize = sizeof(struct nfsd3_accessres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+AT+1, + .pc_name = "SETATTR", }, }; diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c index 7c30876a31a1..a568b842e9eb 100644 --- a/fs/nfsd/nfs3acl.c +++ b/fs/nfsd/nfs3acl.c @@ -124,43 +124,39 @@ out: /* * XDR decode functions */ + static int nfs3svc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p) { + struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_getaclargs *args = rqstp->rq_argp; - p = nfs3svc_decode_fh(p, &args->fh); - if (!p) + if (!svcxdr_decode_nfs_fh3(xdr, &args->fh)) + return 0; + if (xdr_stream_decode_u32(xdr, &args->mask) < 0) return 0; - args->mask = ntohl(*p); p++; - return xdr_argsize_check(rqstp, p); + return 1; } - static int nfs3svc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p) { - struct nfsd3_setaclargs *args = rqstp->rq_argp; - struct kvec *head = rqstp->rq_arg.head; - unsigned int base; - int n; + struct xdr_stream *xdr = &rqstp->rq_arg_stream; + struct nfsd3_setaclargs *argp = rqstp->rq_argp; - p = nfs3svc_decode_fh(p, &args->fh); - if (!p) + if (!svcxdr_decode_nfs_fh3(xdr, &argp->fh)) return 0; - args->mask = ntohl(*p++); - if (args->mask & ~NFS_ACL_MASK || - !xdr_argsize_check(rqstp, p)) + if (xdr_stream_decode_u32(xdr, &argp->mask) < 0) + return 0; + if (argp->mask & ~NFS_ACL_MASK) + return 0; + if (!nfs_stream_decode_acl(xdr, NULL, (argp->mask & NFS_ACL) ? + &argp->acl_access : NULL)) + return 0; + if (!nfs_stream_decode_acl(xdr, NULL, (argp->mask & NFS_DFACL) ? + &argp->acl_default : NULL)) return 0; - base = (char *)p - (char *)head->iov_base; - n = nfsacl_decode(&rqstp->rq_arg, base, NULL, - (args->mask & NFS_ACL) ? - &args->acl_access : NULL); - if (n > 0) - n = nfsacl_decode(&rqstp->rq_arg, base + n, NULL, - (args->mask & NFS_DFACL) ? - &args->acl_default : NULL); - return (n > 0); + return 1; } /* @@ -251,6 +247,7 @@ static const struct svc_procedure nfsd_acl_procedures3[3] = { .pc_ressize = sizeof(struct nfsd_voidres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST, + .pc_name = "NULL", }, [ACLPROC3_GETACL] = { .pc_func = nfsd3_proc_getacl, @@ -261,6 +258,7 @@ static const struct svc_procedure nfsd_acl_procedures3[3] = { .pc_ressize = sizeof(struct nfsd3_getaclres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+1+2*(1+ACL), + .pc_name = "GETACL", }, [ACLPROC3_SETACL] = { .pc_func = nfsd3_proc_setacl, @@ -271,6 +269,7 @@ static const struct svc_procedure nfsd_acl_procedures3[3] = { .pc_ressize = sizeof(struct nfsd3_attrstat), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+pAT, + .pc_name = "SETACL", }, }; diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index 76931f4f57c3..8675851199f8 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -124,15 +124,16 @@ nfsd3_proc_access(struct svc_rqst *rqstp) static __be32 nfsd3_proc_readlink(struct svc_rqst *rqstp) { - struct nfsd3_readlinkargs *argp = rqstp->rq_argp; + struct nfsd_fhandle *argp = rqstp->rq_argp; struct nfsd3_readlinkres *resp = rqstp->rq_resp; + char *buffer = page_address(*(rqstp->rq_next_page++)); dprintk("nfsd: READLINK(3) %s\n", SVCFH_fmt(&argp->fh)); /* Read the symlink. */ fh_copy(&resp->fh, &argp->fh); resp->len = NFS3_MAXPATHLEN; - resp->status = nfsd_readlink(rqstp, &resp->fh, argp->buffer, &resp->len); + resp->status = nfsd_readlink(rqstp, &resp->fh, buffer, &resp->len); return rpc_success; } @@ -144,25 +145,38 @@ nfsd3_proc_read(struct svc_rqst *rqstp) { struct nfsd3_readargs *argp = rqstp->rq_argp; struct nfsd3_readres *resp = rqstp->rq_resp; - u32 max_blocksize = svc_max_payload(rqstp); - unsigned long cnt = min(argp->count, max_blocksize); + u32 max_blocksize = svc_max_payload(rqstp); + unsigned int len; + int v; + + argp->count = min_t(u32, argp->count, max_blocksize); dprintk("nfsd: READ(3) %s %lu bytes at %Lu\n", SVCFH_fmt(&argp->fh), (unsigned long) argp->count, (unsigned long long) argp->offset); + v = 0; + len = argp->count; + while (len > 0) { + struct page *page = *(rqstp->rq_next_page++); + + rqstp->rq_vec[v].iov_base = page_address(page); + rqstp->rq_vec[v].iov_len = min_t(unsigned int, len, PAGE_SIZE); + len -= rqstp->rq_vec[v].iov_len; + v++; + } + /* Obtain buffer pointer for payload. * 1 (status) + 22 (post_op_attr) + 1 (count) + 1 (eof) * + 1 (xdr opaque byte count) = 26 */ - resp->count = cnt; + resp->count = argp->count; svc_reserve_auth(rqstp, ((1 + NFS3_POST_OP_ATTR_WORDS + 3)<<2) + resp->count +4); fh_copy(&resp->fh, &argp->fh); resp->status = nfsd_read(rqstp, &resp->fh, argp->offset, - rqstp->rq_vec, argp->vlen, &resp->count, - &resp->eof); + rqstp->rq_vec, v, &resp->count, &resp->eof); return rpc_success; } @@ -421,6 +435,23 @@ nfsd3_proc_link(struct svc_rqst *rqstp) return rpc_success; } +static void nfsd3_init_dirlist_pages(struct svc_rqst *rqstp, + struct nfsd3_readdirres *resp, + int count) +{ + count = min_t(u32, count, svc_max_payload(rqstp)); + + /* Convert byte count to number of words (i.e. >> 2), + * and reserve room for the NULL ptr & eof flag (-2 words) */ + resp->buflen = (count >> 2) - 2; + + resp->buffer = page_address(*rqstp->rq_next_page); + while (count > 0) { + rqstp->rq_next_page++; + count -= PAGE_SIZE; + } +} + /* * Read a portion of a directory. */ @@ -430,6 +461,7 @@ nfsd3_proc_readdir(struct svc_rqst *rqstp) struct nfsd3_readdirargs *argp = rqstp->rq_argp; struct nfsd3_readdirres *resp = rqstp->rq_resp; int count = 0; + loff_t offset; struct page **p; caddr_t page_addr = NULL; @@ -437,18 +469,16 @@ nfsd3_proc_readdir(struct svc_rqst *rqstp) SVCFH_fmt(&argp->fh), argp->count, (u32) argp->cookie); - /* Make sure we've room for the NULL ptr & eof flag, and shrink to - * client read size */ - count = (argp->count >> 2) - 2; + nfsd3_init_dirlist_pages(rqstp, resp, argp->count); /* Read directory and encode entries on the fly */ fh_copy(&resp->fh, &argp->fh); - resp->buflen = count; resp->common.err = nfs_ok; - resp->buffer = argp->buffer; resp->rqstp = rqstp; - resp->status = nfsd_readdir(rqstp, &resp->fh, (loff_t *)&argp->cookie, + offset = argp->cookie; + + resp->status = nfsd_readdir(rqstp, &resp->fh, &offset, &resp->common, nfs3svc_encode_entry); memcpy(resp->verf, argp->verf, 8); count = 0; @@ -464,8 +494,6 @@ nfsd3_proc_readdir(struct svc_rqst *rqstp) } resp->count = count >> 2; if (resp->offset) { - loff_t offset = argp->cookie; - if (unlikely(resp->offset1)) { /* we ended up with offset on a page boundary */ *resp->offset = htonl(offset >> 32); @@ -498,16 +526,12 @@ nfsd3_proc_readdirplus(struct svc_rqst *rqstp) SVCFH_fmt(&argp->fh), argp->count, (u32) argp->cookie); - /* Convert byte count to number of words (i.e. >> 2), - * and reserve room for the NULL ptr & eof flag (-2 words) */ - resp->count = (argp->count >> 2) - 2; + nfsd3_init_dirlist_pages(rqstp, resp, argp->count); /* Read directory and encode entries on the fly */ fh_copy(&resp->fh, &argp->fh); resp->common.err = nfs_ok; - resp->buffer = argp->buffer; - resp->buflen = resp->count; resp->rqstp = rqstp; offset = argp->cookie; @@ -683,7 +707,6 @@ out: * NFSv3 Server procedures. * Only the results of non-idempotent operations are cached. */ -#define nfs3svc_decode_fhandleargs nfs3svc_decode_fhandle #define nfs3svc_encode_attrstatres nfs3svc_encode_attrstat #define nfs3svc_encode_wccstatres nfs3svc_encode_wccstat #define nfsd3_mkdirargs nfsd3_createargs @@ -708,16 +731,18 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_ressize = sizeof(struct nfsd_voidres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST, + .pc_name = "NULL", }, [NFS3PROC_GETATTR] = { .pc_func = nfsd3_proc_getattr, .pc_decode = nfs3svc_decode_fhandleargs, .pc_encode = nfs3svc_encode_attrstatres, .pc_release = nfs3svc_release_fhandle, - .pc_argsize = sizeof(struct nfsd3_fhandleargs), + .pc_argsize = sizeof(struct nfsd_fhandle), .pc_ressize = sizeof(struct nfsd3_attrstatres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+AT, + .pc_name = "GETATTR", }, [NFS3PROC_SETATTR] = { .pc_func = nfsd3_proc_setattr, @@ -728,6 +753,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_ressize = sizeof(struct nfsd3_wccstatres), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+WC, + .pc_name = "SETATTR", }, [NFS3PROC_LOOKUP] = { .pc_func = nfsd3_proc_lookup, @@ -738,6 +764,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_ressize = sizeof(struct nfsd3_diropres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+FH+pAT+pAT, + .pc_name = "LOOKUP", }, [NFS3PROC_ACCESS] = { .pc_func = nfsd3_proc_access, @@ -748,16 +775,18 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_ressize = sizeof(struct nfsd3_accessres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+pAT+1, + .pc_name = "ACCESS", }, [NFS3PROC_READLINK] = { .pc_func = nfsd3_proc_readlink, - .pc_decode = nfs3svc_decode_readlinkargs, + .pc_decode = nfs3svc_decode_fhandleargs, .pc_encode = nfs3svc_encode_readlinkres, .pc_release = nfs3svc_release_fhandle, - .pc_argsize = sizeof(struct nfsd3_readlinkargs), + .pc_argsize = sizeof(struct nfsd_fhandle), .pc_ressize = sizeof(struct nfsd3_readlinkres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+pAT+1+NFS3_MAXPATHLEN/4, + .pc_name = "READLINK", }, [NFS3PROC_READ] = { .pc_func = nfsd3_proc_read, @@ -768,6 +797,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_ressize = sizeof(struct nfsd3_readres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+pAT+4+NFSSVC_MAXBLKSIZE/4, + .pc_name = "READ", }, [NFS3PROC_WRITE] = { .pc_func = nfsd3_proc_write, @@ -778,6 +808,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_ressize = sizeof(struct nfsd3_writeres), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+WC+4, + .pc_name = "WRITE", }, [NFS3PROC_CREATE] = { .pc_func = nfsd3_proc_create, @@ -788,6 +819,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_ressize = sizeof(struct nfsd3_createres), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+(1+FH+pAT)+WC, + .pc_name = "CREATE", }, [NFS3PROC_MKDIR] = { .pc_func = nfsd3_proc_mkdir, @@ -798,6 +830,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_ressize = sizeof(struct nfsd3_createres), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+(1+FH+pAT)+WC, + .pc_name = "MKDIR", }, [NFS3PROC_SYMLINK] = { .pc_func = nfsd3_proc_symlink, @@ -808,6 +841,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_ressize = sizeof(struct nfsd3_createres), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+(1+FH+pAT)+WC, + .pc_name = "SYMLINK", }, [NFS3PROC_MKNOD] = { .pc_func = nfsd3_proc_mknod, @@ -818,6 +852,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_ressize = sizeof(struct nfsd3_createres), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+(1+FH+pAT)+WC, + .pc_name = "MKNOD", }, [NFS3PROC_REMOVE] = { .pc_func = nfsd3_proc_remove, @@ -828,6 +863,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_ressize = sizeof(struct nfsd3_wccstatres), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+WC, + .pc_name = "REMOVE", }, [NFS3PROC_RMDIR] = { .pc_func = nfsd3_proc_rmdir, @@ -838,6 +874,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_ressize = sizeof(struct nfsd3_wccstatres), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+WC, + .pc_name = "RMDIR", }, [NFS3PROC_RENAME] = { .pc_func = nfsd3_proc_rename, @@ -848,6 +885,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_ressize = sizeof(struct nfsd3_renameres), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+WC+WC, + .pc_name = "RENAME", }, [NFS3PROC_LINK] = { .pc_func = nfsd3_proc_link, @@ -858,6 +896,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_ressize = sizeof(struct nfsd3_linkres), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+pAT+WC, + .pc_name = "LINK", }, [NFS3PROC_READDIR] = { .pc_func = nfsd3_proc_readdir, @@ -867,6 +906,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_argsize = sizeof(struct nfsd3_readdirargs), .pc_ressize = sizeof(struct nfsd3_readdirres), .pc_cachetype = RC_NOCACHE, + .pc_name = "READDIR", }, [NFS3PROC_READDIRPLUS] = { .pc_func = nfsd3_proc_readdirplus, @@ -876,6 +916,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_argsize = sizeof(struct nfsd3_readdirplusargs), .pc_ressize = sizeof(struct nfsd3_readdirres), .pc_cachetype = RC_NOCACHE, + .pc_name = "READDIRPLUS", }, [NFS3PROC_FSSTAT] = { .pc_func = nfsd3_proc_fsstat, @@ -885,6 +926,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_ressize = sizeof(struct nfsd3_fsstatres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+pAT+2*6+1, + .pc_name = "FSSTAT", }, [NFS3PROC_FSINFO] = { .pc_func = nfsd3_proc_fsinfo, @@ -894,6 +936,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_ressize = sizeof(struct nfsd3_fsinfores), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+pAT+12, + .pc_name = "FSINFO", }, [NFS3PROC_PATHCONF] = { .pc_func = nfsd3_proc_pathconf, @@ -903,6 +946,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_ressize = sizeof(struct nfsd3_pathconfres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+pAT+6, + .pc_name = "PATHCONF", }, [NFS3PROC_COMMIT] = { .pc_func = nfsd3_proc_commit, @@ -913,6 +957,7 @@ static const struct svc_procedure nfsd_procedures3[22] = { .pc_ressize = sizeof(struct nfsd3_commitres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+WC+2, + .pc_name = "COMMIT", }, }; diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index 821db21ba072..9d9a01ce0b27 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -29,8 +29,9 @@ static u32 nfs3_ftypes[] = { /* - * XDR functions for basic NFS types + * Basic NFSv3 data types (RFC 1813 Sections 2.5 and 2.6) */ + static __be32 * encode_time3(__be32 *p, struct timespec64 *time) { @@ -38,32 +39,47 @@ encode_time3(__be32 *p, struct timespec64 *time) return p; } -static __be32 * -decode_time3(__be32 *p, struct timespec64 *time) +static bool +svcxdr_decode_nfstime3(struct xdr_stream *xdr, struct timespec64 *timep) { - time->tv_sec = ntohl(*p++); - time->tv_nsec = ntohl(*p++); - return p; + __be32 *p; + + p = xdr_inline_decode(xdr, XDR_UNIT * 2); + if (!p) + return false; + timep->tv_sec = be32_to_cpup(p++); + timep->tv_nsec = be32_to_cpup(p); + + return true; } -static __be32 * -decode_fh(__be32 *p, struct svc_fh *fhp) +/** + * svcxdr_decode_nfs_fh3 - Decode an NFSv3 file handle + * @xdr: XDR stream positioned at an undecoded NFSv3 FH + * @fhp: OUT: filled-in server file handle + * + * Return values: + * %false: The encoded file handle was not valid + * %true: @fhp has been initialized + */ +bool +svcxdr_decode_nfs_fh3(struct xdr_stream *xdr, struct svc_fh *fhp) { - unsigned int size; + __be32 *p; + u32 size; + + if (xdr_stream_decode_u32(xdr, &size) < 0) + return false; + if (size == 0 || size > NFS3_FHSIZE) + return false; + p = xdr_inline_decode(xdr, size); + if (!p) + return false; fh_init(fhp, NFS3_FHSIZE); - size = ntohl(*p++); - if (size > NFS3_FHSIZE) - return NULL; - - memcpy(&fhp->fh_handle.fh_base, p, size); fhp->fh_handle.fh_size = size; - return p + XDR_QUADLEN(size); -} + memcpy(&fhp->fh_handle.fh_base, p, size); -/* Helper function for NFSv3 ACL code */ -__be32 *nfs3svc_decode_fh(__be32 *p, struct svc_fh *fhp) -{ - return decode_fh(p, fhp); + return true; } static __be32 * @@ -76,69 +92,165 @@ encode_fh(__be32 *p, struct svc_fh *fhp) return p + XDR_QUADLEN(size); } -/* - * Decode a file name and make sure that the path contains - * no slashes or null bytes. - */ -static __be32 * -decode_filename(__be32 *p, char **namp, unsigned int *lenp) +static bool +svcxdr_decode_filename3(struct xdr_stream *xdr, char **name, unsigned int *len) { - char *name; - unsigned int i; + u32 size, i; + __be32 *p; + char *c; + + if (xdr_stream_decode_u32(xdr, &size) < 0) + return false; + if (size == 0 || size > NFS3_MAXNAMLEN) + return false; + p = xdr_inline_decode(xdr, size); + if (!p) + return false; - if ((p = xdr_decode_string_inplace(p, namp, lenp, NFS3_MAXNAMLEN)) != NULL) { - for (i = 0, name = *namp; i < *lenp; i++, name++) { - if (*name == '\0' || *name == '/') - return NULL; - } + *len = size; + *name = (char *)p; + for (i = 0, c = *name; i < size; i++, c++) { + if (*c == '\0' || *c == '/') + return false; } - return p; + return true; } -static __be32 * -decode_sattr3(__be32 *p, struct iattr *iap, struct user_namespace *userns) +static bool +svcxdr_decode_diropargs3(struct xdr_stream *xdr, struct svc_fh *fhp, + char **name, unsigned int *len) +{ + return svcxdr_decode_nfs_fh3(xdr, fhp) && + svcxdr_decode_filename3(xdr, name, len); +} + +static bool +svcxdr_decode_sattr3(struct svc_rqst *rqstp, struct xdr_stream *xdr, + struct iattr *iap) { - u32 tmp; + u32 set_it; iap->ia_valid = 0; - if (*p++) { + if (xdr_stream_decode_bool(xdr, &set_it) < 0) + return false; + if (set_it) { + u32 mode; + + if (xdr_stream_decode_u32(xdr, &mode) < 0) + return false; iap->ia_valid |= ATTR_MODE; - iap->ia_mode = ntohl(*p++); + iap->ia_mode = mode; } - if (*p++) { - iap->ia_uid = make_kuid(userns, ntohl(*p++)); + if (xdr_stream_decode_bool(xdr, &set_it) < 0) + return false; + if (set_it) { + u32 uid; + + if (xdr_stream_decode_u32(xdr, &uid) < 0) + return false; + iap->ia_uid = make_kuid(nfsd_user_namespace(rqstp), uid); if (uid_valid(iap->ia_uid)) iap->ia_valid |= ATTR_UID; } - if (*p++) { - iap->ia_gid = make_kgid(userns, ntohl(*p++)); + if (xdr_stream_decode_bool(xdr, &set_it) < 0) + return false; + if (set_it) { + u32 gid; + + if (xdr_stream_decode_u32(xdr, &gid) < 0) + return false; + iap->ia_gid = make_kgid(nfsd_user_namespace(rqstp), gid); if (gid_valid(iap->ia_gid)) iap->ia_valid |= ATTR_GID; } - if (*p++) { - u64 newsize; + if (xdr_stream_decode_bool(xdr, &set_it) < 0) + return false; + if (set_it) { + u64 newsize; + if (xdr_stream_decode_u64(xdr, &newsize) < 0) + return false; iap->ia_valid |= ATTR_SIZE; - p = xdr_decode_hyper(p, &newsize); iap->ia_size = min_t(u64, newsize, NFS_OFFSET_MAX); } - if ((tmp = ntohl(*p++)) == 1) { /* set to server time */ + if (xdr_stream_decode_u32(xdr, &set_it) < 0) + return false; + switch (set_it) { + case DONT_CHANGE: + break; + case SET_TO_SERVER_TIME: iap->ia_valid |= ATTR_ATIME; - } else if (tmp == 2) { /* set to client time */ + break; + case SET_TO_CLIENT_TIME: + if (!svcxdr_decode_nfstime3(xdr, &iap->ia_atime)) + return false; iap->ia_valid |= ATTR_ATIME | ATTR_ATIME_SET; - iap->ia_atime.tv_sec = ntohl(*p++); - iap->ia_atime.tv_nsec = ntohl(*p++); + break; + default: + return false; } - if ((tmp = ntohl(*p++)) == 1) { /* set to server time */ + if (xdr_stream_decode_u32(xdr, &set_it) < 0) + return false; + switch (set_it) { + case DONT_CHANGE: + break; + case SET_TO_SERVER_TIME: iap->ia_valid |= ATTR_MTIME; - } else if (tmp == 2) { /* set to client time */ + break; + case SET_TO_CLIENT_TIME: + if (!svcxdr_decode_nfstime3(xdr, &iap->ia_mtime)) + return false; iap->ia_valid |= ATTR_MTIME | ATTR_MTIME_SET; - iap->ia_mtime.tv_sec = ntohl(*p++); - iap->ia_mtime.tv_nsec = ntohl(*p++); + break; + default: + return false; } - return p; + + return true; +} + +static bool +svcxdr_decode_sattrguard3(struct xdr_stream *xdr, struct nfsd3_sattrargs *args) +{ + __be32 *p; + u32 check; + + if (xdr_stream_decode_bool(xdr, &check) < 0) + return false; + if (check) { + p = xdr_inline_decode(xdr, XDR_UNIT * 2); + if (!p) + return false; + args->check_guard = 1; + args->guardtime = be32_to_cpup(p); + } else + args->check_guard = 0; + + return true; +} + +static bool +svcxdr_decode_specdata3(struct xdr_stream *xdr, struct nfsd3_mknodargs *args) +{ + __be32 *p; + + p = xdr_inline_decode(xdr, XDR_UNIT * 2); + if (!p) + return false; + args->major = be32_to_cpup(p++); + args->minor = be32_to_cpup(p); + + return true; +} + +static bool +svcxdr_decode_devicedata3(struct svc_rqst *rqstp, struct xdr_stream *xdr, + struct nfsd3_mknodargs *args) +{ + return svcxdr_decode_sattr3(rqstp, xdr, &args->attrs) && + svcxdr_decode_specdata3(xdr, args); } static __be32 *encode_fsid(__be32 *p, struct svc_fh *fhp) @@ -252,6 +364,11 @@ encode_wcc_data(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp) return encode_post_op_attr(rqstp, p, fhp); } +static bool fs_supports_change_attribute(struct super_block *sb) +{ + return sb->s_flags & SB_I_VERSION || sb->s_export_op->fetch_iversion; +} + /* * Fill in the pre_op attr for the wcc data */ @@ -260,24 +377,26 @@ void fill_pre_wcc(struct svc_fh *fhp) struct inode *inode; struct kstat stat; bool v4 = (fhp->fh_maxsize == NFS4_FHSIZE); - __be32 err; if (fhp->fh_no_wcc || fhp->fh_pre_saved) return; inode = d_inode(fhp->fh_dentry); - err = fh_getattr(fhp, &stat); - if (err) { - /* Grab the times from inode anyway */ - stat.mtime = inode->i_mtime; - stat.ctime = inode->i_ctime; - stat.size = inode->i_size; + if (fs_supports_change_attribute(inode->i_sb) || !v4) { + __be32 err = fh_getattr(fhp, &stat); + + if (err) { + /* Grab the times from inode anyway */ + stat.mtime = inode->i_mtime; + stat.ctime = inode->i_ctime; + stat.size = inode->i_size; + } + fhp->fh_pre_mtime = stat.mtime; + fhp->fh_pre_ctime = stat.ctime; + fhp->fh_pre_size = stat.size; } if (v4) fhp->fh_pre_change = nfsd4_change_attribute(&stat, inode); - fhp->fh_pre_mtime = stat.mtime; - fhp->fh_pre_ctime = stat.ctime; - fhp->fh_pre_size = stat.size; fhp->fh_pre_saved = true; } @@ -288,7 +407,6 @@ void fill_post_wcc(struct svc_fh *fhp) { bool v4 = (fhp->fh_maxsize == NFS4_FHSIZE); struct inode *inode = d_inode(fhp->fh_dentry); - __be32 err; if (fhp->fh_no_wcc) return; @@ -296,12 +414,16 @@ void fill_post_wcc(struct svc_fh *fhp) if (fhp->fh_post_saved) printk("nfsd: inode locked twice during operation.\n"); - err = fh_getattr(fhp, &fhp->fh_post_attr); - if (err) { - fhp->fh_post_saved = false; - fhp->fh_post_attr.ctime = inode->i_ctime; - } else - fhp->fh_post_saved = true; + fhp->fh_post_saved = true; + + if (fs_supports_change_attribute(inode->i_sb) || !v4) { + __be32 err = fh_getattr(fhp, &fhp->fh_post_attr); + + if (err) { + fhp->fh_post_saved = false; + fhp->fh_post_attr.ctime = inode->i_ctime; + } + } if (v4) fhp->fh_post_change = nfsd4_change_attribute(&fhp->fh_post_attr, inode); @@ -312,331 +434,277 @@ void fill_post_wcc(struct svc_fh *fhp) */ int -nfs3svc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p) +nfs3svc_decode_fhandleargs(struct svc_rqst *rqstp, __be32 *p) { + struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd_fhandle *args = rqstp->rq_argp; - p = decode_fh(p, &args->fh); - if (!p) - return 0; - return xdr_argsize_check(rqstp, p); + return svcxdr_decode_nfs_fh3(xdr, &args->fh); } int nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p) { + struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_sattrargs *args = rqstp->rq_argp; - p = decode_fh(p, &args->fh); - if (!p) - return 0; - p = decode_sattr3(p, &args->attrs, nfsd_user_namespace(rqstp)); - - if ((args->check_guard = ntohl(*p++)) != 0) { - struct timespec64 time; - p = decode_time3(p, &time); - args->guardtime = time.tv_sec; - } - - return xdr_argsize_check(rqstp, p); + return svcxdr_decode_nfs_fh3(xdr, &args->fh) && + svcxdr_decode_sattr3(rqstp, xdr, &args->attrs) && + svcxdr_decode_sattrguard3(xdr, args); } int nfs3svc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p) { + struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_diropargs *args = rqstp->rq_argp; - if (!(p = decode_fh(p, &args->fh)) - || !(p = decode_filename(p, &args->name, &args->len))) - return 0; - - return xdr_argsize_check(rqstp, p); + return svcxdr_decode_diropargs3(xdr, &args->fh, &args->name, &args->len); } int nfs3svc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p) { + struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_accessargs *args = rqstp->rq_argp; - p = decode_fh(p, &args->fh); - if (!p) + if (!svcxdr_decode_nfs_fh3(xdr, &args->fh)) + return 0; + if (xdr_stream_decode_u32(xdr, &args->access) < 0) return 0; - args->access = ntohl(*p++); - return xdr_argsize_check(rqstp, p); + return 1; } int nfs3svc_decode_readargs(struct svc_rqst *rqstp, __be32 *p) { + struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_readargs *args = rqstp->rq_argp; - unsigned int len; - int v; - u32 max_blocksize = svc_max_payload(rqstp); - p = decode_fh(p, &args->fh); - if (!p) + if (!svcxdr_decode_nfs_fh3(xdr, &args->fh)) + return 0; + if (xdr_stream_decode_u64(xdr, &args->offset) < 0) + return 0; + if (xdr_stream_decode_u32(xdr, &args->count) < 0) return 0; - p = xdr_decode_hyper(p, &args->offset); - - args->count = ntohl(*p++); - len = min(args->count, max_blocksize); - - /* set up the kvec */ - v=0; - while (len > 0) { - struct page *p = *(rqstp->rq_next_page++); - rqstp->rq_vec[v].iov_base = page_address(p); - rqstp->rq_vec[v].iov_len = min_t(unsigned int, len, PAGE_SIZE); - len -= rqstp->rq_vec[v].iov_len; - v++; - } - args->vlen = v; - return xdr_argsize_check(rqstp, p); + return 1; } int nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p) { + struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_writeargs *args = rqstp->rq_argp; - unsigned int len, hdr, dlen; u32 max_blocksize = svc_max_payload(rqstp); struct kvec *head = rqstp->rq_arg.head; struct kvec *tail = rqstp->rq_arg.tail; + size_t remaining; - p = decode_fh(p, &args->fh); - if (!p) + if (!svcxdr_decode_nfs_fh3(xdr, &args->fh)) return 0; - p = xdr_decode_hyper(p, &args->offset); - - args->count = ntohl(*p++); - args->stable = ntohl(*p++); - len = args->len = ntohl(*p++); - if ((void *)p > head->iov_base + head->iov_len) + if (xdr_stream_decode_u64(xdr, &args->offset) < 0) return 0; - /* - * The count must equal the amount of data passed. - */ - if (args->count != args->len) + if (xdr_stream_decode_u32(xdr, &args->count) < 0) + return 0; + if (xdr_stream_decode_u32(xdr, &args->stable) < 0) return 0; - /* - * Check to make sure that we got the right number of - * bytes. - */ - hdr = (void*)p - head->iov_base; - dlen = head->iov_len + rqstp->rq_arg.page_len + tail->iov_len - hdr; - /* - * Round the length of the data which was specified up to - * the next multiple of XDR units and then compare that - * against the length which was actually received. - * Note that when RPCSEC/GSS (for example) is used, the - * data buffer can be padded so dlen might be larger - * than required. It must never be smaller. - */ - if (dlen < XDR_QUADLEN(len)*4) + /* opaque data */ + if (xdr_stream_decode_u32(xdr, &args->len) < 0) return 0; + /* request sanity */ + if (args->count != args->len) + return 0; + remaining = head->iov_len + rqstp->rq_arg.page_len + tail->iov_len; + remaining -= xdr_stream_pos(xdr); + if (remaining < xdr_align_size(args->len)) + return 0; if (args->count > max_blocksize) { args->count = max_blocksize; - len = args->len = max_blocksize; + args->len = max_blocksize; } - args->first.iov_base = (void *)p; - args->first.iov_len = head->iov_len - hdr; + args->first.iov_base = xdr->p; + args->first.iov_len = head->iov_len - xdr_stream_pos(xdr); + return 1; } int nfs3svc_decode_createargs(struct svc_rqst *rqstp, __be32 *p) { + struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_createargs *args = rqstp->rq_argp; - if (!(p = decode_fh(p, &args->fh)) - || !(p = decode_filename(p, &args->name, &args->len))) + if (!svcxdr_decode_diropargs3(xdr, &args->fh, &args->name, &args->len)) return 0; - - switch (args->createmode = ntohl(*p++)) { + if (xdr_stream_decode_u32(xdr, &args->createmode) < 0) + return 0; + switch (args->createmode) { case NFS3_CREATE_UNCHECKED: case NFS3_CREATE_GUARDED: - p = decode_sattr3(p, &args->attrs, nfsd_user_namespace(rqstp)); - break; + return svcxdr_decode_sattr3(rqstp, xdr, &args->attrs); case NFS3_CREATE_EXCLUSIVE: - args->verf = p; - p += 2; + args->verf = xdr_inline_decode(xdr, NFS3_CREATEVERFSIZE); + if (!args->verf) + return 0; break; default: return 0; } - - return xdr_argsize_check(rqstp, p); + return 1; } int nfs3svc_decode_mkdirargs(struct svc_rqst *rqstp, __be32 *p) { + struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_createargs *args = rqstp->rq_argp; - if (!(p = decode_fh(p, &args->fh)) || - !(p = decode_filename(p, &args->name, &args->len))) - return 0; - p = decode_sattr3(p, &args->attrs, nfsd_user_namespace(rqstp)); - - return xdr_argsize_check(rqstp, p); + return svcxdr_decode_diropargs3(xdr, &args->fh, + &args->name, &args->len) && + svcxdr_decode_sattr3(rqstp, xdr, &args->attrs); } int nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p) { + struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_symlinkargs *args = rqstp->rq_argp; - char *base = (char *)p; - size_t dlen; + struct kvec *head = rqstp->rq_arg.head; + struct kvec *tail = rqstp->rq_arg.tail; + size_t remaining; - if (!(p = decode_fh(p, &args->ffh)) || - !(p = decode_filename(p, &args->fname, &args->flen))) + if (!svcxdr_decode_diropargs3(xdr, &args->ffh, &args->fname, &args->flen)) + return 0; + if (!svcxdr_decode_sattr3(rqstp, xdr, &args->attrs)) + return 0; + if (xdr_stream_decode_u32(xdr, &args->tlen) < 0) return 0; - p = decode_sattr3(p, &args->attrs, nfsd_user_namespace(rqstp)); - args->tlen = ntohl(*p++); + /* request sanity */ + remaining = head->iov_len + rqstp->rq_arg.page_len + tail->iov_len; + remaining -= xdr_stream_pos(xdr); + if (remaining < xdr_align_size(args->tlen)) + return 0; - args->first.iov_base = p; - args->first.iov_len = rqstp->rq_arg.head[0].iov_len; - args->first.iov_len -= (char *)p - base; + args->first.iov_base = xdr->p; + args->first.iov_len = head->iov_len - xdr_stream_pos(xdr); - dlen = args->first.iov_len + rqstp->rq_arg.page_len + - rqstp->rq_arg.tail[0].iov_len; - if (dlen < XDR_QUADLEN(args->tlen) << 2) - return 0; return 1; } int nfs3svc_decode_mknodargs(struct svc_rqst *rqstp, __be32 *p) { + struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_mknodargs *args = rqstp->rq_argp; - if (!(p = decode_fh(p, &args->fh)) - || !(p = decode_filename(p, &args->name, &args->len))) + if (!svcxdr_decode_diropargs3(xdr, &args->fh, &args->name, &args->len)) + return 0; + if (xdr_stream_decode_u32(xdr, &args->ftype) < 0) + return 0; + switch (args->ftype) { + case NF3CHR: + case NF3BLK: + return svcxdr_decode_devicedata3(rqstp, xdr, args); + case NF3SOCK: + case NF3FIFO: + return svcxdr_decode_sattr3(rqstp, xdr, &args->attrs); + case NF3REG: + case NF3DIR: + case NF3LNK: + /* Valid XDR but illegal file types */ + break; + default: return 0; - - args->ftype = ntohl(*p++); - - if (args->ftype == NF3BLK || args->ftype == NF3CHR - || args->ftype == NF3SOCK || args->ftype == NF3FIFO) - p = decode_sattr3(p, &args->attrs, nfsd_user_namespace(rqstp)); - - if (args->ftype == NF3BLK || args->ftype == NF3CHR) { - args->major = ntohl(*p++); - args->minor = ntohl(*p++); } - return xdr_argsize_check(rqstp, p); + return 1; } int nfs3svc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p) { + struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_renameargs *args = rqstp->rq_argp; - if (!(p = decode_fh(p, &args->ffh)) - || !(p = decode_filename(p, &args->fname, &args->flen)) - || !(p = decode_fh(p, &args->tfh)) - || !(p = decode_filename(p, &args->tname, &args->tlen))) - return 0; - - return xdr_argsize_check(rqstp, p); -} - -int -nfs3svc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p) -{ - struct nfsd3_readlinkargs *args = rqstp->rq_argp; - - p = decode_fh(p, &args->fh); - if (!p) - return 0; - args->buffer = page_address(*(rqstp->rq_next_page++)); - - return xdr_argsize_check(rqstp, p); + return svcxdr_decode_diropargs3(xdr, &args->ffh, + &args->fname, &args->flen) && + svcxdr_decode_diropargs3(xdr, &args->tfh, + &args->tname, &args->tlen); } int nfs3svc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p) { + struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_linkargs *args = rqstp->rq_argp; - if (!(p = decode_fh(p, &args->ffh)) - || !(p = decode_fh(p, &args->tfh)) - || !(p = decode_filename(p, &args->tname, &args->tlen))) - return 0; - - return xdr_argsize_check(rqstp, p); + return svcxdr_decode_nfs_fh3(xdr, &args->ffh) && + svcxdr_decode_diropargs3(xdr, &args->tfh, + &args->tname, &args->tlen); } int nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p) { + struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_readdirargs *args = rqstp->rq_argp; - int len; - u32 max_blocksize = svc_max_payload(rqstp); - p = decode_fh(p, &args->fh); - if (!p) + if (!svcxdr_decode_nfs_fh3(xdr, &args->fh)) + return 0; + if (xdr_stream_decode_u64(xdr, &args->cookie) < 0) + return 0; + args->verf = xdr_inline_decode(xdr, NFS3_COOKIEVERFSIZE); + if (!args->verf) + return 0; + if (xdr_stream_decode_u32(xdr, &args->count) < 0) return 0; - p = xdr_decode_hyper(p, &args->cookie); - args->verf = p; p += 2; - args->dircount = ~0; - args->count = ntohl(*p++); - len = args->count = min_t(u32, args->count, max_blocksize); - - while (len > 0) { - struct page *p = *(rqstp->rq_next_page++); - if (!args->buffer) - args->buffer = page_address(p); - len -= PAGE_SIZE; - } - return xdr_argsize_check(rqstp, p); + return 1; } int nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, __be32 *p) { + struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_readdirargs *args = rqstp->rq_argp; - int len; - u32 max_blocksize = svc_max_payload(rqstp); + u32 dircount; - p = decode_fh(p, &args->fh); - if (!p) + if (!svcxdr_decode_nfs_fh3(xdr, &args->fh)) + return 0; + if (xdr_stream_decode_u64(xdr, &args->cookie) < 0) + return 0; + args->verf = xdr_inline_decode(xdr, NFS3_COOKIEVERFSIZE); + if (!args->verf) + return 0; + /* dircount is ignored */ + if (xdr_stream_decode_u32(xdr, &dircount) < 0) + return 0; + if (xdr_stream_decode_u32(xdr, &args->count) < 0) return 0; - p = xdr_decode_hyper(p, &args->cookie); - args->verf = p; p += 2; - args->dircount = ntohl(*p++); - args->count = ntohl(*p++); - - len = args->count = min(args->count, max_blocksize); - while (len > 0) { - struct page *p = *(rqstp->rq_next_page++); - if (!args->buffer) - args->buffer = page_address(p); - len -= PAGE_SIZE; - } - return xdr_argsize_check(rqstp, p); + return 1; } int nfs3svc_decode_commitargs(struct svc_rqst *rqstp, __be32 *p) { + struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_commitargs *args = rqstp->rq_argp; - p = decode_fh(p, &args->fh); - if (!p) + + if (!svcxdr_decode_nfs_fh3(xdr, &args->fh)) + return 0; + if (xdr_stream_decode_u64(xdr, &args->offset) < 0) + return 0; + if (xdr_stream_decode_u32(xdr, &args->count) < 0) return 0; - p = xdr_decode_hyper(p, &args->offset); - args->count = ntohl(*p++); - return xdr_argsize_check(rqstp, p); + return 1; } /* @@ -865,9 +933,14 @@ compose_entry_fh(struct nfsd3_readdirres *cd, struct svc_fh *fhp, if (isdotent(name, namlen)) { if (namlen == 2) { dchild = dget_parent(dparent); - /* filesystem root - cannot return filehandle for ".." */ + /* + * Don't return filehandle for ".." if we're at + * the filesystem or export root: + */ if (dchild == dparent) goto out; + if (dparent == exp->ex_path.dentry) + goto out; } else dchild = dget(dparent); } else diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 4727b7f03c5b..acdb3cd806a1 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -50,6 +50,11 @@ #include "pnfs.h" #include "trace.h" +static bool inter_copy_offload_enable; +module_param(inter_copy_offload_enable, bool, 0644); +MODULE_PARM_DESC(inter_copy_offload_enable, + "Enable inter server to server copy offload. Default: false"); + #ifdef CONFIG_NFSD_V4_SECURITY_LABEL #include <linux/security.h> @@ -373,8 +378,7 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, * Before RECLAIM_COMPLETE done, server should deny new lock */ if (nfsd4_has_session(cstate) && - !test_bit(NFSD4_CLIENT_RECLAIM_COMPLETE, - &cstate->session->se_client->cl_flags) && + !test_bit(NFSD4_CLIENT_RECLAIM_COMPLETE, &cstate->clp->cl_flags) && open->op_claim_type != NFS4_OPEN_CLAIM_PREVIOUS) return nfserr_grace; @@ -423,8 +427,7 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; break; case NFS4_OPEN_CLAIM_PREVIOUS: - status = nfs4_check_open_reclaim(&open->op_clientid, - cstate, nn); + status = nfs4_check_open_reclaim(cstate->clp); if (status) goto out; open->op_openowner->oo_flags |= NFS4_OO_CONFIRMED; @@ -1883,7 +1886,7 @@ nfsd4_getdeviceinfo(struct svc_rqst *rqstp, nfserr = nfs_ok; if (gdp->gd_maxcount != 0) { nfserr = ops->proc_getdeviceinfo(exp->ex_path.mnt->mnt_sb, - rqstp, cstate->session->se_client, gdp); + rqstp, cstate->clp, gdp); } gdp->gd_notify_types &= ops->notify_types; @@ -2169,7 +2172,7 @@ nfsd4_proc_null(struct svc_rqst *rqstp) static inline void nfsd4_increment_op_stats(u32 opnum) { if (opnum >= FIRST_NFS4_OP && opnum <= LAST_NFS4_OP) - nfsdstats.nfs4_opcount[opnum]++; + percpu_counter_inc(&nfsdstats.counter[NFSD_STATS_NFS4_OP(opnum)]); } static const struct nfsd4_operation nfsd4_ops[]; @@ -3300,6 +3303,7 @@ static const struct svc_procedure nfsd_procedures4[2] = { .pc_ressize = sizeof(struct nfsd_voidres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = 1, + .pc_name = "NULL", }, [NFSPROC4_COMPOUND] = { .pc_func = nfsd4_proc_compound, @@ -3310,6 +3314,7 @@ static const struct svc_procedure nfsd_procedures4[2] = { .pc_release = nfsd4_release_compoundargs, .pc_cachetype = RC_NOCACHE, .pc_xdrressize = NFSD_BUFSIZE/4, + .pc_name = "COMPOUND", }, }; diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 1d2cd6a88f61..423fd6683f3a 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -3891,6 +3891,7 @@ nfsd4_reclaim_complete(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_reclaim_complete *rc = &u->reclaim_complete; + struct nfs4_client *clp = cstate->clp; __be32 status = 0; if (rc->rca_one_fs) { @@ -3904,12 +3905,11 @@ nfsd4_reclaim_complete(struct svc_rqst *rqstp, } status = nfserr_complete_already; - if (test_and_set_bit(NFSD4_CLIENT_RECLAIM_COMPLETE, - &cstate->session->se_client->cl_flags)) + if (test_and_set_bit(NFSD4_CLIENT_RECLAIM_COMPLETE, &clp->cl_flags)) goto out; status = nfserr_stale_clientid; - if (is_client_expired(cstate->session->se_client)) + if (is_client_expired(clp)) /* * The following error isn't really legal. * But we only get here if the client just explicitly @@ -3920,8 +3920,8 @@ nfsd4_reclaim_complete(struct svc_rqst *rqstp, goto out; status = nfs_ok; - nfsd4_client_record_create(cstate->session->se_client); - inc_reclaim_complete(cstate->session->se_client); + nfsd4_client_record_create(clp); + inc_reclaim_complete(clp); out: return status; } @@ -4633,40 +4633,37 @@ static __be32 nfsd4_check_seqid(struct nfsd4_compound_state *cstate, struct nfs4 return nfserr_bad_seqid; } -static __be32 lookup_clientid(clientid_t *clid, - struct nfsd4_compound_state *cstate, - struct nfsd_net *nn, - bool sessions) +static struct nfs4_client *lookup_clientid(clientid_t *clid, bool sessions, + struct nfsd_net *nn) { struct nfs4_client *found; + spin_lock(&nn->client_lock); + found = find_confirmed_client(clid, sessions, nn); + if (found) + atomic_inc(&found->cl_rpc_users); + spin_unlock(&nn->client_lock); + return found; +} + +static __be32 set_client(clientid_t *clid, + struct nfsd4_compound_state *cstate, + struct nfsd_net *nn) +{ if (cstate->clp) { - found = cstate->clp; - if (!same_clid(&found->cl_clientid, clid)) + if (!same_clid(&cstate->clp->cl_clientid, clid)) return nfserr_stale_clientid; return nfs_ok; } - if (STALE_CLIENTID(clid, nn)) return nfserr_stale_clientid; - /* - * For v4.1+ we get the client in the SEQUENCE op. If we don't have one - * cached already then we know this is for is for v4.0 and "sessions" - * will be false. + * We're in the 4.0 case (otherwise the SEQUENCE op would have + * set cstate->clp), so session = false: */ - WARN_ON_ONCE(cstate->session); - spin_lock(&nn->client_lock); - found = find_confirmed_client(clid, sessions, nn); - if (!found) { - spin_unlock(&nn->client_lock); + cstate->clp = lookup_clientid(clid, false, nn); + if (!cstate->clp) return nfserr_expired; - } - atomic_inc(&found->cl_rpc_users); - spin_unlock(&nn->client_lock); - - /* Cache the nfs4_client in cstate! */ - cstate->clp = found; return nfs_ok; } @@ -4680,8 +4677,6 @@ nfsd4_process_open1(struct nfsd4_compound_state *cstate, struct nfs4_openowner *oo = NULL; __be32 status; - if (STALE_CLIENTID(&open->op_clientid, nn)) - return nfserr_stale_clientid; /* * In case we need it later, after we've already created the * file and don't want to risk a further failure: @@ -4690,7 +4685,7 @@ nfsd4_process_open1(struct nfsd4_compound_state *cstate, if (open->op_file == NULL) return nfserr_jukebox; - status = lookup_clientid(clientid, cstate, nn, false); + status = set_client(clientid, cstate, nn); if (status) return status; clp = cstate->clp; @@ -5300,17 +5295,14 @@ nfsd4_renew(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); trace_nfsd_clid_renew(clid); - status = lookup_clientid(clid, cstate, nn, false); + status = set_client(clid, cstate, nn); if (status) - goto out; + return status; clp = cstate->clp; - status = nfserr_cb_path_down; if (!list_empty(&clp->cl_delegations) && clp->cl_cb_state != NFSD4_CB_UP) - goto out; - status = nfs_ok; -out: - return status; + return nfserr_cb_path_down; + return nfs_ok; } void @@ -5686,8 +5678,7 @@ nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate, if (ZERO_STATEID(stateid) || ONE_STATEID(stateid) || CLOSE_STATEID(stateid)) return nfserr_bad_stateid; - status = lookup_clientid(&stateid->si_opaque.so_clid, cstate, nn, - false); + status = set_client(&stateid->si_opaque.so_clid, cstate, nn); if (status == nfserr_stale_clientid) { if (cstate->session) return nfserr_bad_stateid; @@ -5818,21 +5809,27 @@ static __be32 find_cpntf_state(struct nfsd_net *nn, stateid_t *st, { __be32 status; struct nfs4_cpntf_state *cps = NULL; - struct nfsd4_compound_state cstate; + struct nfs4_client *found; status = manage_cpntf_state(nn, st, NULL, &cps); if (status) return status; cps->cpntf_time = ktime_get_boottime_seconds(); - memset(&cstate, 0, sizeof(cstate)); - status = lookup_clientid(&cps->cp_p_clid, &cstate, nn, true); - if (status) + + status = nfserr_expired; + found = lookup_clientid(&cps->cp_p_clid, true, nn); + if (!found) goto out; - status = nfsd4_lookup_stateid(&cstate, &cps->cp_p_stateid, - NFS4_DELEG_STID|NFS4_OPEN_STID|NFS4_LOCK_STID, - stid, nn); - put_client_renew(cstate.clp); + + *stid = find_stateid_by_type(found, &cps->cp_p_stateid, + NFS4_DELEG_STID|NFS4_OPEN_STID|NFS4_LOCK_STID); + if (*stid) + status = nfs_ok; + else + status = nfserr_bad_stateid; + + put_client_renew(found); out: nfs4_put_cpntf_state(nn, cps); return status; @@ -5921,7 +5918,7 @@ nfsd4_test_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, { struct nfsd4_test_stateid *test_stateid = &u->test_stateid; struct nfsd4_test_stateid_id *stateid; - struct nfs4_client *cl = cstate->session->se_client; + struct nfs4_client *cl = cstate->clp; list_for_each_entry(stateid, &test_stateid->ts_stateid_list, ts_id_list) stateid->ts_id_status = @@ -5967,7 +5964,7 @@ nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, stateid_t *stateid = &free_stateid->fr_stateid; struct nfs4_stid *s; struct nfs4_delegation *dp; - struct nfs4_client *cl = cstate->session->se_client; + struct nfs4_client *cl = cstate->clp; __be32 ret = nfserr_bad_stateid; spin_lock(&cl->cl_lock); @@ -6696,13 +6693,9 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (nfsd4_has_session(cstate)) /* See rfc 5661 18.10.3: given clientid is ignored: */ memcpy(&lock->lk_new_clientid, - &cstate->session->se_client->cl_clientid, + &cstate->clp->cl_clientid, sizeof(clientid_t)); - status = nfserr_stale_clientid; - if (STALE_CLIENTID(&lock->lk_new_clientid, nn)) - goto out; - /* validate and update open stateid and open seqid */ status = nfs4_preprocess_confirmed_seqid_op(cstate, lock->lk_new_open_seqid, @@ -6909,8 +6902,7 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, return nfserr_inval; if (!nfsd4_has_session(cstate)) { - status = lookup_clientid(&lockt->lt_clientid, cstate, nn, - false); + status = set_client(&lockt->lt_clientid, cstate, nn); if (status) goto out; } @@ -7094,7 +7086,7 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp, dprintk("nfsd4_release_lockowner clientid: (%08x/%08x):\n", clid->cl_boot, clid->cl_id); - status = lookup_clientid(clid, cstate, nn, false); + status = set_client(clid, cstate, nn); if (status) return status; @@ -7230,25 +7222,13 @@ nfsd4_find_reclaim_client(struct xdr_netobj name, struct nfsd_net *nn) return NULL; } -/* -* Called from OPEN. Look for clientid in reclaim list. -*/ __be32 -nfs4_check_open_reclaim(clientid_t *clid, - struct nfsd4_compound_state *cstate, - struct nfsd_net *nn) +nfs4_check_open_reclaim(struct nfs4_client *clp) { - __be32 status; - - /* find clientid in conf_id_hashtbl */ - status = lookup_clientid(clid, cstate, nn, false); - if (status) - return nfserr_reclaim_bad; - - if (test_bit(NFSD4_CLIENT_RECLAIM_COMPLETE, &cstate->clp->cl_flags)) + if (test_bit(NFSD4_CLIENT_RECLAIM_COMPLETE, &clp->cl_flags)) return nfserr_no_grace; - if (nfsd4_client_record_check(cstate->clp)) + if (nfsd4_client_record_check(clp)) return nfserr_reclaim_bad; return nfs_ok; diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 45ee6b12ce5b..eaaa1605b5b5 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -147,6 +147,25 @@ svcxdr_dupstr(struct nfsd4_compoundargs *argp, void *buf, u32 len) return p; } +static void * +svcxdr_savemem(struct nfsd4_compoundargs *argp, __be32 *p, u32 len) +{ + __be32 *tmp; + + /* + * The location of the decoded data item is stable, + * so @p is OK to use. This is the common case. + */ + if (p != argp->xdr->scratch.iov_base) + return p; + + tmp = svcxdr_tmpalloc(argp, len); + if (!tmp) + return NULL; + memcpy(tmp, p, len); + return tmp; +} + /* * NFSv4 basic data type decoders */ @@ -183,11 +202,10 @@ nfsd4_decode_opaque(struct nfsd4_compoundargs *argp, struct xdr_netobj *o) p = xdr_inline_decode(argp->xdr, len); if (!p) return nfserr_bad_xdr; - o->data = svcxdr_tmpalloc(argp, len); + o->data = svcxdr_savemem(argp, p, len); if (!o->data) return nfserr_jukebox; o->len = len; - memcpy(o->data, p, len); return nfs_ok; } @@ -205,10 +223,9 @@ nfsd4_decode_component4(struct nfsd4_compoundargs *argp, char **namp, u32 *lenp) status = check_filename((char *)p, *lenp); if (status) return status; - *namp = svcxdr_tmpalloc(argp, *lenp); + *namp = svcxdr_savemem(argp, p, *lenp); if (!*namp) return nfserr_jukebox; - memcpy(*namp, p, *lenp); return nfs_ok; } @@ -1200,10 +1217,9 @@ nfsd4_decode_putfh(struct nfsd4_compoundargs *argp, struct nfsd4_putfh *putfh) p = xdr_inline_decode(argp->xdr, putfh->pf_fhlen); if (!p) return nfserr_bad_xdr; - putfh->pf_fhval = svcxdr_tmpalloc(argp, putfh->pf_fhlen); + putfh->pf_fhval = svcxdr_savemem(argp, p, putfh->pf_fhlen); if (!putfh->pf_fhval) return nfserr_jukebox; - memcpy(putfh->pf_fhval, p, putfh->pf_fhlen); return nfs_ok; } @@ -1318,24 +1334,20 @@ nfsd4_decode_setclientid(struct nfsd4_compoundargs *argp, struct nfsd4_setclient p = xdr_inline_decode(argp->xdr, setclientid->se_callback_netid_len); if (!p) return nfserr_bad_xdr; - setclientid->se_callback_netid_val = svcxdr_tmpalloc(argp, + setclientid->se_callback_netid_val = svcxdr_savemem(argp, p, setclientid->se_callback_netid_len); if (!setclientid->se_callback_netid_val) return nfserr_jukebox; - memcpy(setclientid->se_callback_netid_val, p, - setclientid->se_callback_netid_len); if (xdr_stream_decode_u32(argp->xdr, &setclientid->se_callback_addr_len) < 0) return nfserr_bad_xdr; p = xdr_inline_decode(argp->xdr, setclientid->se_callback_addr_len); if (!p) return nfserr_bad_xdr; - setclientid->se_callback_addr_val = svcxdr_tmpalloc(argp, + setclientid->se_callback_addr_val = svcxdr_savemem(argp, p, setclientid->se_callback_addr_len); if (!setclientid->se_callback_addr_val) return nfserr_jukebox; - memcpy(setclientid->se_callback_addr_val, p, - setclientid->se_callback_addr_len); if (xdr_stream_decode_u32(argp->xdr, &setclientid->se_callback_ident) < 0) return nfserr_bad_xdr; @@ -1375,10 +1387,9 @@ nfsd4_decode_verify(struct nfsd4_compoundargs *argp, struct nfsd4_verify *verify p = xdr_inline_decode(argp->xdr, verify->ve_attrlen); if (!p) return nfserr_bad_xdr; - verify->ve_attrval = svcxdr_tmpalloc(argp, verify->ve_attrlen); + verify->ve_attrval = svcxdr_savemem(argp, p, verify->ve_attrlen); if (!verify->ve_attrval) return nfserr_jukebox; - memcpy(verify->ve_attrval, p, verify->ve_attrlen); return nfs_ok; } @@ -2333,10 +2344,9 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) p = xdr_inline_decode(argp->xdr, argp->taglen); if (!p) return 0; - argp->tag = svcxdr_tmpalloc(argp, argp->taglen); + argp->tag = svcxdr_savemem(argp, p, argp->taglen); if (!argp->tag) return 0; - memcpy(argp->tag, p, argp->taglen); max_reply += xdr_align_size(argp->taglen); } @@ -4756,6 +4766,7 @@ nfsd4_encode_read_plus_data(struct nfsd4_compoundres *resp, resp->rqstp->rq_vec, read->rd_vlen, maxcount, eof); if (nfserr) return nfserr; + xdr_truncate_encode(xdr, starting_len + 16 + xdr_align_size(*maxcount)); tmp = htonl(NFS4_CONTENT_DATA); write_bytes_to_xdr_buf(xdr->buf, starting_len, &tmp, 4); @@ -4763,6 +4774,10 @@ nfsd4_encode_read_plus_data(struct nfsd4_compoundres *resp, write_bytes_to_xdr_buf(xdr->buf, starting_len + 4, &tmp64, 8); tmp = htonl(*maxcount); write_bytes_to_xdr_buf(xdr->buf, starting_len + 12, &tmp, 4); + + tmp = xdr_zero; + write_bytes_to_xdr_buf(xdr->buf, starting_len + 16 + *maxcount, &tmp, + xdr_pad_size(*maxcount)); return nfs_ok; } @@ -4855,14 +4870,15 @@ out: if (nfserr && segments == 0) xdr_truncate_encode(xdr, starting_len); else { - tmp = htonl(eof); - write_bytes_to_xdr_buf(xdr->buf, starting_len, &tmp, 4); - tmp = htonl(segments); - write_bytes_to_xdr_buf(xdr->buf, starting_len + 4, &tmp, 4); if (nfserr) { xdr_truncate_encode(xdr, last_segment); nfserr = nfs_ok; + eof = 0; } + tmp = htonl(eof); + write_bytes_to_xdr_buf(xdr->buf, starting_len, &tmp, 4); + tmp = htonl(segments); + write_bytes_to_xdr_buf(xdr->buf, starting_len + 4, &tmp, 4); } return nfserr; diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c index 80c90fc231a5..96cdf77925f3 100644 --- a/fs/nfsd/nfscache.c +++ b/fs/nfsd/nfscache.c @@ -121,14 +121,14 @@ nfsd_reply_cache_free_locked(struct nfsd_drc_bucket *b, struct svc_cacherep *rp, struct nfsd_net *nn) { if (rp->c_type == RC_REPLBUFF && rp->c_replvec.iov_base) { - nn->drc_mem_usage -= rp->c_replvec.iov_len; + nfsd_stats_drc_mem_usage_sub(nn, rp->c_replvec.iov_len); kfree(rp->c_replvec.iov_base); } if (rp->c_state != RC_UNUSED) { rb_erase(&rp->c_node, &b->rb_head); list_del(&rp->c_lru); atomic_dec(&nn->num_drc_entries); - nn->drc_mem_usage -= sizeof(*rp); + nfsd_stats_drc_mem_usage_sub(nn, sizeof(*rp)); } kmem_cache_free(drc_slab, rp); } @@ -154,6 +154,16 @@ void nfsd_drc_slab_free(void) kmem_cache_destroy(drc_slab); } +static int nfsd_reply_cache_stats_init(struct nfsd_net *nn) +{ + return nfsd_percpu_counters_init(nn->counter, NFSD_NET_COUNTERS_NUM); +} + +static void nfsd_reply_cache_stats_destroy(struct nfsd_net *nn) +{ + nfsd_percpu_counters_destroy(nn->counter, NFSD_NET_COUNTERS_NUM); +} + int nfsd_reply_cache_init(struct nfsd_net *nn) { unsigned int hashsize; @@ -165,12 +175,16 @@ int nfsd_reply_cache_init(struct nfsd_net *nn) hashsize = nfsd_hashsize(nn->max_drc_entries); nn->maskbits = ilog2(hashsize); + status = nfsd_reply_cache_stats_init(nn); + if (status) + goto out_nomem; + nn->nfsd_reply_cache_shrinker.scan_objects = nfsd_reply_cache_scan; nn->nfsd_reply_cache_shrinker.count_objects = nfsd_reply_cache_count; nn->nfsd_reply_cache_shrinker.seeks = 1; status = register_shrinker(&nn->nfsd_reply_cache_shrinker); if (status) - goto out_nomem; + goto out_stats_destroy; nn->drc_hashtbl = kvzalloc(array_size(hashsize, sizeof(*nn->drc_hashtbl)), GFP_KERNEL); @@ -186,6 +200,8 @@ int nfsd_reply_cache_init(struct nfsd_net *nn) return 0; out_shrinker: unregister_shrinker(&nn->nfsd_reply_cache_shrinker); +out_stats_destroy: + nfsd_reply_cache_stats_destroy(nn); out_nomem: printk(KERN_ERR "nfsd: failed to allocate reply cache\n"); return -ENOMEM; @@ -196,6 +212,7 @@ void nfsd_reply_cache_shutdown(struct nfsd_net *nn) struct svc_cacherep *rp; unsigned int i; + nfsd_reply_cache_stats_destroy(nn); unregister_shrinker(&nn->nfsd_reply_cache_shrinker); for (i = 0; i < nn->drc_hashsize; i++) { @@ -324,7 +341,7 @@ nfsd_cache_key_cmp(const struct svc_cacherep *key, { if (key->c_key.k_xid == rp->c_key.k_xid && key->c_key.k_csum != rp->c_key.k_csum) { - ++nn->payload_misses; + nfsd_stats_payload_misses_inc(nn); trace_nfsd_drc_mismatch(nn, key, rp); } @@ -407,7 +424,7 @@ int nfsd_cache_lookup(struct svc_rqst *rqstp) rqstp->rq_cacherep = NULL; if (type == RC_NOCACHE) { - nfsdstats.rcnocache++; + nfsd_stats_rc_nocache_inc(); goto out; } @@ -429,12 +446,12 @@ int nfsd_cache_lookup(struct svc_rqst *rqstp) goto found_entry; } - nfsdstats.rcmisses++; + nfsd_stats_rc_misses_inc(); rqstp->rq_cacherep = rp; rp->c_state = RC_INPROG; atomic_inc(&nn->num_drc_entries); - nn->drc_mem_usage += sizeof(*rp); + nfsd_stats_drc_mem_usage_add(nn, sizeof(*rp)); /* go ahead and prune the cache */ prune_bucket(b, nn); @@ -446,7 +463,7 @@ out: found_entry: /* We found a matching entry which is either in progress or done. */ - nfsdstats.rchits++; + nfsd_stats_rc_hits_inc(); rtn = RC_DROPIT; /* Request being processed */ @@ -548,7 +565,7 @@ void nfsd_cache_update(struct svc_rqst *rqstp, int cachetype, __be32 *statp) return; } spin_lock(&b->cache_lock); - nn->drc_mem_usage += bufsize; + nfsd_stats_drc_mem_usage_add(nn, bufsize); lru_put_end(b, rp); rp->c_secure = test_bit(RQ_SECURE, &rqstp->rq_flags); rp->c_type = cachetype; @@ -588,13 +605,18 @@ static int nfsd_reply_cache_stats_show(struct seq_file *m, void *v) seq_printf(m, "max entries: %u\n", nn->max_drc_entries); seq_printf(m, "num entries: %u\n", - atomic_read(&nn->num_drc_entries)); + atomic_read(&nn->num_drc_entries)); seq_printf(m, "hash buckets: %u\n", 1 << nn->maskbits); - seq_printf(m, "mem usage: %u\n", nn->drc_mem_usage); - seq_printf(m, "cache hits: %u\n", nfsdstats.rchits); - seq_printf(m, "cache misses: %u\n", nfsdstats.rcmisses); - seq_printf(m, "not cached: %u\n", nfsdstats.rcnocache); - seq_printf(m, "payload misses: %u\n", nn->payload_misses); + seq_printf(m, "mem usage: %lld\n", + percpu_counter_sum_positive(&nn->counter[NFSD_NET_DRC_MEM_USAGE])); + seq_printf(m, "cache hits: %lld\n", + percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_RC_HITS])); + seq_printf(m, "cache misses: %lld\n", + percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_RC_MISSES])); + seq_printf(m, "not cached: %lld\n", + percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_RC_NOCACHE])); + seq_printf(m, "payload misses: %lld\n", + percpu_counter_sum_positive(&nn->counter[NFSD_NET_PAYLOAD_MISSES])); seq_printf(m, "longest chain len: %u\n", nn->longest_chain); seq_printf(m, "cachesize at longest: %u\n", nn->longest_chain_cachesize); return 0; diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index f6d5d783f4a4..4f6e514192bd 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -32,6 +32,7 @@ enum { NFSD_Root = 1, NFSD_List, + NFSD_Export_Stats, NFSD_Export_features, NFSD_Fh, NFSD_FO_UnlockIP, @@ -1348,6 +1349,8 @@ static int nfsd_fill_super(struct super_block *sb, struct fs_context *fc) static const struct tree_descr nfsd_files[] = { [NFSD_List] = {"exports", &exports_nfsd_operations, S_IRUGO}, + /* Per-export io stats use same ops as exports file */ + [NFSD_Export_Stats] = {"export_stats", &exports_nfsd_operations, S_IRUGO}, [NFSD_Export_features] = {"export_features", &export_features_operations, S_IRUGO}, [NFSD_FO_UnlockIP] = {"unlock_ip", @@ -1534,7 +1537,9 @@ static int __init init_nfsd(void) retval = nfsd4_init_pnfs(); if (retval) goto out_free_slabs; - nfsd_stat_init(); /* Statistics */ + retval = nfsd_stat_init(); /* Statistics */ + if (retval) + goto out_free_pnfs; retval = nfsd_drc_slab_create(); if (retval) goto out_free_stat; @@ -1554,6 +1559,7 @@ out_free_lockd: nfsd_drc_slab_free(); out_free_stat: nfsd_stat_shutdown(); +out_free_pnfs: nfsd4_exit_pnfs(); out_free_slabs: nfsd4_free_slabs(); diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index d63cf8196fed..8bdc37aa2c2e 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -24,8 +24,8 @@ #include <uapi/linux/nfsd/debug.h> #include "netns.h" -#include "stats.h" #include "export.h" +#include "stats.h" #undef ifdebug #ifdef CONFIG_SUNRPC_DEBUG diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index 66f2ef67792a..4744a276058d 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -349,7 +349,7 @@ out: __be32 fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, int access) { - struct svc_export *exp; + struct svc_export *exp = NULL; struct dentry *dentry; __be32 error; @@ -422,7 +422,7 @@ skip_pseudoflavor_check: } out: if (error == nfserr_stale) - nfsdstats.fh_stale++; + nfsd_stats_fh_stale_inc(exp); return error; } diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h index cb20c2cd3469..f58933519f38 100644 --- a/fs/nfsd/nfsfh.h +++ b/fs/nfsd/nfsfh.h @@ -12,6 +12,7 @@ #include <linux/sunrpc/svc.h> #include <uapi/linux/nfsd/nfsfh.h> #include <linux/iversion.h> +#include <linux/exportfs.h> static inline __u32 ino_t_to_u32(ino_t ino) { @@ -264,7 +265,9 @@ fh_clear_wcc(struct svc_fh *fhp) static inline u64 nfsd4_change_attribute(struct kstat *stat, struct inode *inode) { - if (IS_I_VERSION(inode)) { + if (inode->i_sb->s_export_op->fetch_iversion) + return inode->i_sb->s_export_op->fetch_iversion(inode); + else if (IS_I_VERSION(inode)) { u64 chattr; chattr = stat->ctime.tv_sec; diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index 9473d048efec..b2f8035f166b 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -149,14 +149,15 @@ out: static __be32 nfsd_proc_readlink(struct svc_rqst *rqstp) { - struct nfsd_readlinkargs *argp = rqstp->rq_argp; + struct nfsd_fhandle *argp = rqstp->rq_argp; struct nfsd_readlinkres *resp = rqstp->rq_resp; + char *buffer = page_address(*(rqstp->rq_next_page++)); dprintk("nfsd: READLINK %s\n", SVCFH_fmt(&argp->fh)); /* Read the symlink. */ resp->len = NFS_MAXPATHLEN; - resp->status = nfsd_readlink(rqstp, &argp->fh, argp->buffer, &resp->len); + resp->status = nfsd_readlink(rqstp, &argp->fh, buffer, &resp->len); fh_put(&argp->fh); return rpc_success; @@ -171,32 +172,36 @@ nfsd_proc_read(struct svc_rqst *rqstp) { struct nfsd_readargs *argp = rqstp->rq_argp; struct nfsd_readres *resp = rqstp->rq_resp; + unsigned int len; u32 eof; + int v; dprintk("nfsd: READ %s %d bytes at %d\n", SVCFH_fmt(&argp->fh), argp->count, argp->offset); + argp->count = min_t(u32, argp->count, NFSSVC_MAXBLKSIZE_V2); + + v = 0; + len = argp->count; + while (len > 0) { + struct page *page = *(rqstp->rq_next_page++); + + rqstp->rq_vec[v].iov_base = page_address(page); + rqstp->rq_vec[v].iov_len = min_t(unsigned int, len, PAGE_SIZE); + len -= rqstp->rq_vec[v].iov_len; + v++; + } + /* Obtain buffer pointer for payload. 19 is 1 word for * status, 17 words for fattr, and 1 word for the byte count. */ - - if (NFSSVC_MAXBLKSIZE_V2 < argp->count) { - char buf[RPC_MAX_ADDRBUFLEN]; - printk(KERN_NOTICE - "oversized read request from %s (%d bytes)\n", - svc_print_addr(rqstp, buf, sizeof(buf)), - argp->count); - argp->count = NFSSVC_MAXBLKSIZE_V2; - } svc_reserve_auth(rqstp, (19<<2) + argp->count + 4); resp->count = argp->count; - resp->status = nfsd_read(rqstp, fh_copy(&resp->fh, &argp->fh), - argp->offset, - rqstp->rq_vec, argp->vlen, - &resp->count, - &eof); + fh_copy(&resp->fh, &argp->fh); + resp->status = nfsd_read(rqstp, &resp->fh, argp->offset, + rqstp->rq_vec, v, &resp->count, &eof); if (resp->status == nfs_ok) resp->status = fh_getattr(&resp->fh, &resp->stat); else if (resp->status == nfserr_jukebox) @@ -548,6 +553,20 @@ nfsd_proc_rmdir(struct svc_rqst *rqstp) return rpc_success; } +static void nfsd_init_dirlist_pages(struct svc_rqst *rqstp, + struct nfsd_readdirres *resp, + int count) +{ + count = min_t(u32, count, PAGE_SIZE); + + /* Convert byte count to number of words (i.e. >> 2), + * and reserve room for the NULL ptr & eof flag (-2 words) */ + resp->buflen = (count >> 2) - 2; + + resp->buffer = page_address(*rqstp->rq_next_page); + rqstp->rq_next_page++; +} + /* * Read a portion of a directory. */ @@ -556,31 +575,24 @@ nfsd_proc_readdir(struct svc_rqst *rqstp) { struct nfsd_readdirargs *argp = rqstp->rq_argp; struct nfsd_readdirres *resp = rqstp->rq_resp; - int count; loff_t offset; + __be32 *buffer; dprintk("nfsd: READDIR %s %d bytes at %d\n", SVCFH_fmt(&argp->fh), argp->count, argp->cookie); - /* Shrink to the client read size */ - count = (argp->count >> 2) - 2; - - /* Make sure we've room for the NULL ptr & eof flag */ - count -= 2; - if (count < 0) - count = 0; + nfsd_init_dirlist_pages(rqstp, resp, argp->count); + buffer = resp->buffer; - resp->buffer = argp->buffer; resp->offset = NULL; - resp->buflen = count; resp->common.err = nfs_ok; /* Read directory and encode entries on the fly */ offset = argp->cookie; resp->status = nfsd_readdir(rqstp, &argp->fh, &offset, &resp->common, nfssvc_encode_entry); - resp->count = resp->buffer - argp->buffer; + resp->count = resp->buffer - buffer; if (resp->offset) *resp->offset = htonl(offset); @@ -623,16 +635,18 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_ressize = sizeof(struct nfsd_voidres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = 0, + .pc_name = "NULL", }, [NFSPROC_GETATTR] = { .pc_func = nfsd_proc_getattr, - .pc_decode = nfssvc_decode_fhandle, + .pc_decode = nfssvc_decode_fhandleargs, .pc_encode = nfssvc_encode_attrstat, .pc_release = nfssvc_release_attrstat, .pc_argsize = sizeof(struct nfsd_fhandle), .pc_ressize = sizeof(struct nfsd_attrstat), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+AT, + .pc_name = "GETATTR", }, [NFSPROC_SETATTR] = { .pc_func = nfsd_proc_setattr, @@ -643,6 +657,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_ressize = sizeof(struct nfsd_attrstat), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+AT, + .pc_name = "SETATTR", }, [NFSPROC_ROOT] = { .pc_func = nfsd_proc_root, @@ -652,6 +667,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_ressize = sizeof(struct nfsd_voidres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = 0, + .pc_name = "ROOT", }, [NFSPROC_LOOKUP] = { .pc_func = nfsd_proc_lookup, @@ -662,15 +678,17 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_ressize = sizeof(struct nfsd_diropres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+FH+AT, + .pc_name = "LOOKUP", }, [NFSPROC_READLINK] = { .pc_func = nfsd_proc_readlink, - .pc_decode = nfssvc_decode_readlinkargs, + .pc_decode = nfssvc_decode_fhandleargs, .pc_encode = nfssvc_encode_readlinkres, - .pc_argsize = sizeof(struct nfsd_readlinkargs), + .pc_argsize = sizeof(struct nfsd_fhandle), .pc_ressize = sizeof(struct nfsd_readlinkres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+1+NFS_MAXPATHLEN/4, + .pc_name = "READLINK", }, [NFSPROC_READ] = { .pc_func = nfsd_proc_read, @@ -681,6 +699,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_ressize = sizeof(struct nfsd_readres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+AT+1+NFSSVC_MAXBLKSIZE_V2/4, + .pc_name = "READ", }, [NFSPROC_WRITECACHE] = { .pc_func = nfsd_proc_writecache, @@ -690,6 +709,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_ressize = sizeof(struct nfsd_voidres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = 0, + .pc_name = "WRITECACHE", }, [NFSPROC_WRITE] = { .pc_func = nfsd_proc_write, @@ -700,6 +720,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_ressize = sizeof(struct nfsd_attrstat), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+AT, + .pc_name = "WRITE", }, [NFSPROC_CREATE] = { .pc_func = nfsd_proc_create, @@ -710,6 +731,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_ressize = sizeof(struct nfsd_diropres), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+FH+AT, + .pc_name = "CREATE", }, [NFSPROC_REMOVE] = { .pc_func = nfsd_proc_remove, @@ -719,6 +741,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_ressize = sizeof(struct nfsd_stat), .pc_cachetype = RC_REPLSTAT, .pc_xdrressize = ST, + .pc_name = "REMOVE", }, [NFSPROC_RENAME] = { .pc_func = nfsd_proc_rename, @@ -728,6 +751,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_ressize = sizeof(struct nfsd_stat), .pc_cachetype = RC_REPLSTAT, .pc_xdrressize = ST, + .pc_name = "RENAME", }, [NFSPROC_LINK] = { .pc_func = nfsd_proc_link, @@ -737,6 +761,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_ressize = sizeof(struct nfsd_stat), .pc_cachetype = RC_REPLSTAT, .pc_xdrressize = ST, + .pc_name = "LINK", }, [NFSPROC_SYMLINK] = { .pc_func = nfsd_proc_symlink, @@ -746,6 +771,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_ressize = sizeof(struct nfsd_stat), .pc_cachetype = RC_REPLSTAT, .pc_xdrressize = ST, + .pc_name = "SYMLINK", }, [NFSPROC_MKDIR] = { .pc_func = nfsd_proc_mkdir, @@ -756,6 +782,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_ressize = sizeof(struct nfsd_diropres), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+FH+AT, + .pc_name = "MKDIR", }, [NFSPROC_RMDIR] = { .pc_func = nfsd_proc_rmdir, @@ -765,6 +792,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_ressize = sizeof(struct nfsd_stat), .pc_cachetype = RC_REPLSTAT, .pc_xdrressize = ST, + .pc_name = "RMDIR", }, [NFSPROC_READDIR] = { .pc_func = nfsd_proc_readdir, @@ -773,15 +801,17 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_argsize = sizeof(struct nfsd_readdirargs), .pc_ressize = sizeof(struct nfsd_readdirres), .pc_cachetype = RC_NOCACHE, + .pc_name = "READDIR", }, [NFSPROC_STATFS] = { .pc_func = nfsd_proc_statfs, - .pc_decode = nfssvc_decode_fhandle, + .pc_decode = nfssvc_decode_fhandleargs, .pc_encode = nfssvc_encode_statfsres, .pc_argsize = sizeof(struct nfsd_fhandle), .pc_ressize = sizeof(struct nfsd_statfsres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+5, + .pc_name = "STATFS", }, }; diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 00384c332f9b..6de406322106 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -33,12 +33,6 @@ #define NFSDDBG_FACILITY NFSDDBG_SVC -bool inter_copy_offload_enable; -EXPORT_SYMBOL_GPL(inter_copy_offload_enable); -module_param(inter_copy_offload_enable, bool, 0644); -MODULE_PARM_DESC(inter_copy_offload_enable, - "Enable inter server to server copy offload. Default: false"); - extern struct svc_program nfsd_program; static int nfsd(void *vrqstp); #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) @@ -961,37 +955,6 @@ out: return 0; } -/* - * A write procedure can have a large argument, and a read procedure can - * have a large reply, but no NFSv2 or NFSv3 procedure has argument and - * reply that can both be larger than a page. The xdr code has taken - * advantage of this assumption to be a sloppy about bounds checking in - * some cases. Pending a rewrite of the NFSv2/v3 xdr code to fix that - * problem, we enforce these assumptions here: - */ -static bool nfs_request_too_big(struct svc_rqst *rqstp, - const struct svc_procedure *proc) -{ - /* - * The ACL code has more careful bounds-checking and is not - * susceptible to this problem: - */ - if (rqstp->rq_prog != NFS_PROGRAM) - return false; - /* - * Ditto NFSv4 (which can in theory have argument and reply both - * more than a page): - */ - if (rqstp->rq_vers >= 4) - return false; - /* The reply will be small, we're OK: */ - if (proc->pc_xdrressize > 0 && - proc->pc_xdrressize < XDR_QUADLEN(PAGE_SIZE)) - return false; - - return rqstp->rq_arg.len > PAGE_SIZE; -} - /** * nfsd_dispatch - Process an NFS or NFSACL Request * @rqstp: incoming request @@ -1010,9 +973,6 @@ int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) struct kvec *resv = &rqstp->rq_res.head[0]; __be32 *p; - if (nfs_request_too_big(rqstp, proc)) - goto out_decode_err; - /* * Give the xdr decoder a chance to change this if it wants * (necessary in the NFSv4.0 compound case) diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c index 7aa6e8aca2c1..5d79ef6a0c7f 100644 --- a/fs/nfsd/nfsxdr.c +++ b/fs/nfsd/nfsxdr.c @@ -23,24 +23,31 @@ static u32 nfs_ftypes[] = { /* - * XDR functions for basic NFS types + * Basic NFSv2 data types (RFC 1094 Section 2.3) */ -static __be32 * -decode_fh(__be32 *p, struct svc_fh *fhp) + +/** + * svcxdr_decode_fhandle - Decode an NFSv2 file handle + * @xdr: XDR stream positioned at an encoded NFSv2 FH + * @fhp: OUT: filled-in server file handle + * + * Return values: + * %false: The encoded file handle was not valid + * %true: @fhp has been initialized + */ +bool +svcxdr_decode_fhandle(struct xdr_stream *xdr, struct svc_fh *fhp) { + __be32 *p; + + p = xdr_inline_decode(xdr, NFS_FHSIZE); + if (!p) + return false; fh_init(fhp, NFS_FHSIZE); memcpy(&fhp->fh_handle.fh_base, p, NFS_FHSIZE); fhp->fh_handle.fh_size = NFS_FHSIZE; - /* FIXME: Look up export pointer here and verify - * Sun Secure RPC if requested */ - return p + (NFS_FHSIZE >> 2); -} - -/* Helper function for NFSv2 ACL code */ -__be32 *nfs2svc_decode_fh(__be32 *p, struct svc_fh *fhp) -{ - return decode_fh(p, fhp); + return true; } static __be32 * @@ -50,66 +57,95 @@ encode_fh(__be32 *p, struct svc_fh *fhp) return p + (NFS_FHSIZE>> 2); } -/* - * Decode a file name and make sure that the path contains - * no slashes or null bytes. - */ -static __be32 * -decode_filename(__be32 *p, char **namp, unsigned int *lenp) +static bool +svcxdr_decode_filename(struct xdr_stream *xdr, char **name, unsigned int *len) { - char *name; - unsigned int i; - - if ((p = xdr_decode_string_inplace(p, namp, lenp, NFS_MAXNAMLEN)) != NULL) { - for (i = 0, name = *namp; i < *lenp; i++, name++) { - if (*name == '\0' || *name == '/') - return NULL; - } - } + u32 size, i; + __be32 *p; + char *c; + + if (xdr_stream_decode_u32(xdr, &size) < 0) + return false; + if (size == 0 || size > NFS_MAXNAMLEN) + return false; + p = xdr_inline_decode(xdr, size); + if (!p) + return false; - return p; + *len = size; + *name = (char *)p; + for (i = 0, c = *name; i < size; i++, c++) + if (*c == '\0' || *c == '/') + return false; + + return true; } -static __be32 * -decode_sattr(__be32 *p, struct iattr *iap, struct user_namespace *userns) +static bool +svcxdr_decode_diropargs(struct xdr_stream *xdr, struct svc_fh *fhp, + char **name, unsigned int *len) { - u32 tmp, tmp1; + return svcxdr_decode_fhandle(xdr, fhp) && + svcxdr_decode_filename(xdr, name, len); +} + +static bool +svcxdr_decode_sattr(struct svc_rqst *rqstp, struct xdr_stream *xdr, + struct iattr *iap) +{ + u32 tmp1, tmp2; + __be32 *p; + + p = xdr_inline_decode(xdr, XDR_UNIT * 8); + if (!p) + return false; iap->ia_valid = 0; - /* Sun client bug compatibility check: some sun clients seem to - * put 0xffff in the mode field when they mean 0xffffffff. - * Quoting the 4.4BSD nfs server code: Nah nah nah nah na nah. + /* + * Some Sun clients put 0xffff in the mode field when they + * mean 0xffffffff. */ - if ((tmp = ntohl(*p++)) != (u32)-1 && tmp != 0xffff) { + tmp1 = be32_to_cpup(p++); + if (tmp1 != (u32)-1 && tmp1 != 0xffff) { iap->ia_valid |= ATTR_MODE; - iap->ia_mode = tmp; + iap->ia_mode = tmp1; } - if ((tmp = ntohl(*p++)) != (u32)-1) { - iap->ia_uid = make_kuid(userns, tmp); + + tmp1 = be32_to_cpup(p++); + if (tmp1 != (u32)-1) { + iap->ia_uid = make_kuid(nfsd_user_namespace(rqstp), tmp1); if (uid_valid(iap->ia_uid)) iap->ia_valid |= ATTR_UID; } - if ((tmp = ntohl(*p++)) != (u32)-1) { - iap->ia_gid = make_kgid(userns, tmp); + + tmp1 = be32_to_cpup(p++); + if (tmp1 != (u32)-1) { + iap->ia_gid = make_kgid(nfsd_user_namespace(rqstp), tmp1); if (gid_valid(iap->ia_gid)) iap->ia_valid |= ATTR_GID; } - if ((tmp = ntohl(*p++)) != (u32)-1) { + + tmp1 = be32_to_cpup(p++); + if (tmp1 != (u32)-1) { iap->ia_valid |= ATTR_SIZE; - iap->ia_size = tmp; + iap->ia_size = tmp1; } - tmp = ntohl(*p++); tmp1 = ntohl(*p++); - if (tmp != (u32)-1 && tmp1 != (u32)-1) { + + tmp1 = be32_to_cpup(p++); + tmp2 = be32_to_cpup(p++); + if (tmp1 != (u32)-1 && tmp2 != (u32)-1) { iap->ia_valid |= ATTR_ATIME | ATTR_ATIME_SET; - iap->ia_atime.tv_sec = tmp; - iap->ia_atime.tv_nsec = tmp1 * 1000; + iap->ia_atime.tv_sec = tmp1; + iap->ia_atime.tv_nsec = tmp2 * NSEC_PER_USEC; } - tmp = ntohl(*p++); tmp1 = ntohl(*p++); - if (tmp != (u32)-1 && tmp1 != (u32)-1) { + + tmp1 = be32_to_cpup(p++); + tmp2 = be32_to_cpup(p++); + if (tmp1 != (u32)-1 && tmp2 != (u32)-1) { iap->ia_valid |= ATTR_MTIME | ATTR_MTIME_SET; - iap->ia_mtime.tv_sec = tmp; - iap->ia_mtime.tv_nsec = tmp1 * 1000; + iap->ia_mtime.tv_sec = tmp1; + iap->ia_mtime.tv_nsec = tmp2 * NSEC_PER_USEC; /* * Passing the invalid value useconds=1000000 for mtime * is a Sun convention for "set both mtime and atime to @@ -119,10 +155,11 @@ decode_sattr(__be32 *p, struct iattr *iap, struct user_namespace *userns) * sattr in section 6.1 of "NFS Illustrated" by * Brent Callaghan, Addison-Wesley, ISBN 0-201-32750-5 */ - if (tmp1 == 1000000) + if (tmp2 == 1000000) iap->ia_valid &= ~(ATTR_ATIME_SET|ATTR_MTIME_SET); } - return p; + + return true; } static __be32 * @@ -194,225 +231,158 @@ __be32 *nfs2svc_encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *f */ int -nfssvc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p) +nfssvc_decode_fhandleargs(struct svc_rqst *rqstp, __be32 *p) { + struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd_fhandle *args = rqstp->rq_argp; - p = decode_fh(p, &args->fh); - if (!p) - return 0; - return xdr_argsize_check(rqstp, p); + return svcxdr_decode_fhandle(xdr, &args->fh); } int nfssvc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p) { + struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd_sattrargs *args = rqstp->rq_argp; - p = decode_fh(p, &args->fh); - if (!p) - return 0; - p = decode_sattr(p, &args->attrs, nfsd_user_namespace(rqstp)); - - return xdr_argsize_check(rqstp, p); + return svcxdr_decode_fhandle(xdr, &args->fh) && + svcxdr_decode_sattr(rqstp, xdr, &args->attrs); } int nfssvc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p) { + struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd_diropargs *args = rqstp->rq_argp; - if (!(p = decode_fh(p, &args->fh)) - || !(p = decode_filename(p, &args->name, &args->len))) - return 0; - - return xdr_argsize_check(rqstp, p); + return svcxdr_decode_diropargs(xdr, &args->fh, &args->name, &args->len); } int nfssvc_decode_readargs(struct svc_rqst *rqstp, __be32 *p) { + struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd_readargs *args = rqstp->rq_argp; - unsigned int len; - int v; - p = decode_fh(p, &args->fh); - if (!p) - return 0; - - args->offset = ntohl(*p++); - len = args->count = ntohl(*p++); - p++; /* totalcount - unused */ + u32 totalcount; - len = min_t(unsigned int, len, NFSSVC_MAXBLKSIZE_V2); + if (!svcxdr_decode_fhandle(xdr, &args->fh)) + return 0; + if (xdr_stream_decode_u32(xdr, &args->offset) < 0) + return 0; + if (xdr_stream_decode_u32(xdr, &args->count) < 0) + return 0; + /* totalcount is ignored */ + if (xdr_stream_decode_u32(xdr, &totalcount) < 0) + return 0; - /* set up somewhere to store response. - * We take pages, put them on reslist and include in iovec - */ - v=0; - while (len > 0) { - struct page *p = *(rqstp->rq_next_page++); - - rqstp->rq_vec[v].iov_base = page_address(p); - rqstp->rq_vec[v].iov_len = min_t(unsigned int, len, PAGE_SIZE); - len -= rqstp->rq_vec[v].iov_len; - v++; - } - args->vlen = v; - return xdr_argsize_check(rqstp, p); + return 1; } int nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p) { + struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd_writeargs *args = rqstp->rq_argp; - unsigned int len, hdr, dlen; struct kvec *head = rqstp->rq_arg.head; + struct kvec *tail = rqstp->rq_arg.tail; + u32 beginoffset, totalcount; + size_t remaining; - p = decode_fh(p, &args->fh); - if (!p) + if (!svcxdr_decode_fhandle(xdr, &args->fh)) return 0; - - p++; /* beginoffset */ - args->offset = ntohl(*p++); /* offset */ - p++; /* totalcount */ - len = args->len = ntohl(*p++); - /* - * The protocol specifies a maximum of 8192 bytes. - */ - if (len > NFSSVC_MAXBLKSIZE_V2) + /* beginoffset is ignored */ + if (xdr_stream_decode_u32(xdr, &beginoffset) < 0) return 0; - - /* - * Check to make sure that we got the right number of - * bytes. - */ - hdr = (void*)p - head->iov_base; - if (hdr > head->iov_len) + if (xdr_stream_decode_u32(xdr, &args->offset) < 0) + return 0; + /* totalcount is ignored */ + if (xdr_stream_decode_u32(xdr, &totalcount) < 0) return 0; - dlen = head->iov_len + rqstp->rq_arg.page_len - hdr; - /* - * Round the length of the data which was specified up to - * the next multiple of XDR units and then compare that - * against the length which was actually received. - * Note that when RPCSEC/GSS (for example) is used, the - * data buffer can be padded so dlen might be larger - * than required. It must never be smaller. - */ - if (dlen < XDR_QUADLEN(len)*4) + /* opaque data */ + if (xdr_stream_decode_u32(xdr, &args->len) < 0) return 0; + if (args->len > NFSSVC_MAXBLKSIZE_V2) + return 0; + remaining = head->iov_len + rqstp->rq_arg.page_len + tail->iov_len; + remaining -= xdr_stream_pos(xdr); + if (remaining < xdr_align_size(args->len)) + return 0; + args->first.iov_base = xdr->p; + args->first.iov_len = head->iov_len - xdr_stream_pos(xdr); - args->first.iov_base = (void *)p; - args->first.iov_len = head->iov_len - hdr; return 1; } int nfssvc_decode_createargs(struct svc_rqst *rqstp, __be32 *p) { + struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd_createargs *args = rqstp->rq_argp; - if ( !(p = decode_fh(p, &args->fh)) - || !(p = decode_filename(p, &args->name, &args->len))) - return 0; - p = decode_sattr(p, &args->attrs, nfsd_user_namespace(rqstp)); - - return xdr_argsize_check(rqstp, p); + return svcxdr_decode_diropargs(xdr, &args->fh, + &args->name, &args->len) && + svcxdr_decode_sattr(rqstp, xdr, &args->attrs); } int nfssvc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p) { + struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd_renameargs *args = rqstp->rq_argp; - if (!(p = decode_fh(p, &args->ffh)) - || !(p = decode_filename(p, &args->fname, &args->flen)) - || !(p = decode_fh(p, &args->tfh)) - || !(p = decode_filename(p, &args->tname, &args->tlen))) - return 0; - - return xdr_argsize_check(rqstp, p); -} - -int -nfssvc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p) -{ - struct nfsd_readlinkargs *args = rqstp->rq_argp; - - p = decode_fh(p, &args->fh); - if (!p) - return 0; - args->buffer = page_address(*(rqstp->rq_next_page++)); - - return xdr_argsize_check(rqstp, p); + return svcxdr_decode_diropargs(xdr, &args->ffh, + &args->fname, &args->flen) && + svcxdr_decode_diropargs(xdr, &args->tfh, + &args->tname, &args->tlen); } int nfssvc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p) { + struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd_linkargs *args = rqstp->rq_argp; - if (!(p = decode_fh(p, &args->ffh)) - || !(p = decode_fh(p, &args->tfh)) - || !(p = decode_filename(p, &args->tname, &args->tlen))) - return 0; - - return xdr_argsize_check(rqstp, p); + return svcxdr_decode_fhandle(xdr, &args->ffh) && + svcxdr_decode_diropargs(xdr, &args->tfh, + &args->tname, &args->tlen); } int nfssvc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p) { + struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd_symlinkargs *args = rqstp->rq_argp; - char *base = (char *)p; - size_t xdrlen; + struct kvec *head = rqstp->rq_arg.head; - if ( !(p = decode_fh(p, &args->ffh)) - || !(p = decode_filename(p, &args->fname, &args->flen))) + if (!svcxdr_decode_diropargs(xdr, &args->ffh, &args->fname, &args->flen)) + return 0; + if (xdr_stream_decode_u32(xdr, &args->tlen) < 0) return 0; - - args->tlen = ntohl(*p++); if (args->tlen == 0) return 0; - args->first.iov_base = p; - args->first.iov_len = rqstp->rq_arg.head[0].iov_len; - args->first.iov_len -= (char *)p - base; - - /* This request is never larger than a page. Therefore, - * transport will deliver either: - * 1. pathname in the pagelist -> sattr is in the tail. - * 2. everything in the head buffer -> sattr is in the head. - */ - if (rqstp->rq_arg.page_len) { - if (args->tlen != rqstp->rq_arg.page_len) - return 0; - p = rqstp->rq_arg.tail[0].iov_base; - } else { - xdrlen = XDR_QUADLEN(args->tlen); - if (xdrlen > args->first.iov_len - (8 * sizeof(__be32))) - return 0; - p += xdrlen; - } - decode_sattr(p, &args->attrs, nfsd_user_namespace(rqstp)); - - return 1; + args->first.iov_len = head->iov_len - xdr_stream_pos(xdr); + args->first.iov_base = xdr_inline_decode(xdr, args->tlen); + if (!args->first.iov_base) + return 0; + return svcxdr_decode_sattr(rqstp, xdr, &args->attrs); } int nfssvc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p) { + struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd_readdirargs *args = rqstp->rq_argp; - p = decode_fh(p, &args->fh); - if (!p) + if (!svcxdr_decode_fhandle(xdr, &args->fh)) + return 0; + if (xdr_stream_decode_u32(xdr, &args->cookie) < 0) + return 0; + if (xdr_stream_decode_u32(xdr, &args->count) < 0) return 0; - args->cookie = ntohl(*p++); - args->count = ntohl(*p++); - args->count = min_t(u32, args->count, PAGE_SIZE); - args->buffer = page_address(*(rqstp->rq_next_page++)); - return xdr_argsize_check(rqstp, p); + return 1; } /* diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 9eae11a9d21c..73deea353169 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -649,8 +649,7 @@ void nfs4_remove_reclaim_record(struct nfs4_client_reclaim *, struct nfsd_net *) extern void nfs4_release_reclaim(struct nfsd_net *); extern struct nfs4_client_reclaim *nfsd4_find_reclaim_client(struct xdr_netobj name, struct nfsd_net *nn); -extern __be32 nfs4_check_open_reclaim(clientid_t *clid, - struct nfsd4_compound_state *cstate, struct nfsd_net *nn); +extern __be32 nfs4_check_open_reclaim(struct nfs4_client *); extern void nfsd4_probe_callback(struct nfs4_client *clp); extern void nfsd4_probe_callback_sync(struct nfs4_client *clp); extern void nfsd4_change_callback(struct nfs4_client *clp, struct nfs4_cb_conn *); diff --git a/fs/nfsd/stats.c b/fs/nfsd/stats.c index b1bc582b0493..1d3b881e7382 100644 --- a/fs/nfsd/stats.c +++ b/fs/nfsd/stats.c @@ -7,16 +7,14 @@ * Format: * rc <hits> <misses> <nocache> * Statistsics for the reply cache - * fh <stale> <total-lookups> <anonlookups> <dir-not-in-dcache> <nondir-not-in-dcache> + * fh <stale> <deprecated filehandle cache stats> * statistics for filehandle lookup * io <bytes-read> <bytes-written> * statistics for IO throughput - * th <threads> <fullcnt> <10%-20%> <20%-30%> ... <90%-100%> <100%> - * time (seconds) when nfsd thread usage above thresholds - * and number of times that all threads were in use - * ra cache-size <10% <20% <30% ... <100% not-found - * number of times that read-ahead entry was found that deep in - * the cache. + * th <threads> <deprecated thread usage histogram stats> + * number of threads + * ra <deprecated ra-cache stats> + * * plus generic RPC stats (see net/sunrpc/stats.c) * * Copyright (C) 1995, 1996, 1997 Olaf Kirch <okir@monad.swb.de> @@ -38,31 +36,24 @@ static int nfsd_proc_show(struct seq_file *seq, void *v) { int i; - seq_printf(seq, "rc %u %u %u\nfh %u %u %u %u %u\nio %u %u\n", - nfsdstats.rchits, - nfsdstats.rcmisses, - nfsdstats.rcnocache, - nfsdstats.fh_stale, - nfsdstats.fh_lookup, - nfsdstats.fh_anon, - nfsdstats.fh_nocache_dir, - nfsdstats.fh_nocache_nondir, - nfsdstats.io_read, - nfsdstats.io_write); + seq_printf(seq, "rc %lld %lld %lld\nfh %lld 0 0 0 0\nio %lld %lld\n", + percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_RC_HITS]), + percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_RC_MISSES]), + percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_RC_NOCACHE]), + percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_FH_STALE]), + percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_IO_READ]), + percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_IO_WRITE])); + /* thread usage: */ - seq_printf(seq, "th %u %u", nfsdstats.th_cnt, nfsdstats.th_fullcnt); - for (i=0; i<10; i++) { - unsigned int jifs = nfsdstats.th_usage[i]; - unsigned int sec = jifs / HZ, msec = (jifs % HZ)*1000/HZ; - seq_printf(seq, " %u.%03u", sec, msec); - } + seq_printf(seq, "th %u 0", nfsdstats.th_cnt); + + /* deprecated thread usage histogram stats */ + for (i = 0; i < 10; i++) + seq_puts(seq, " 0.000"); + + /* deprecated ra-cache stats */ + seq_puts(seq, "\nra 0 0 0 0 0 0 0 0 0 0 0 0\n"); - /* newline and ra-cache */ - seq_printf(seq, "\nra %u", nfsdstats.ra_size); - for (i=0; i<11; i++) - seq_printf(seq, " %u", nfsdstats.ra_depth[i]); - seq_putc(seq, '\n'); - /* show my rpc info */ svc_seq_show(seq, &nfsd_svcstats); @@ -70,8 +61,10 @@ static int nfsd_proc_show(struct seq_file *seq, void *v) /* Show count for individual nfsv4 operations */ /* Writing operation numbers 0 1 2 also for maintaining uniformity */ seq_printf(seq,"proc4ops %u", LAST_NFS4_OP + 1); - for (i = 0; i <= LAST_NFS4_OP; i++) - seq_printf(seq, " %u", nfsdstats.nfs4_opcount[i]); + for (i = 0; i <= LAST_NFS4_OP; i++) { + seq_printf(seq, " %lld", + percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_NFS4_OP(i)])); + } seq_putc(seq, '\n'); #endif @@ -91,14 +84,63 @@ static const struct proc_ops nfsd_proc_ops = { .proc_release = single_release, }; -void -nfsd_stat_init(void) +int nfsd_percpu_counters_init(struct percpu_counter counters[], int num) +{ + int i, err = 0; + + for (i = 0; !err && i < num; i++) + err = percpu_counter_init(&counters[i], 0, GFP_KERNEL); + + if (!err) + return 0; + + for (; i > 0; i--) + percpu_counter_destroy(&counters[i-1]); + + return err; +} + +void nfsd_percpu_counters_reset(struct percpu_counter counters[], int num) +{ + int i; + + for (i = 0; i < num; i++) + percpu_counter_set(&counters[i], 0); +} + +void nfsd_percpu_counters_destroy(struct percpu_counter counters[], int num) { + int i; + + for (i = 0; i < num; i++) + percpu_counter_destroy(&counters[i]); +} + +static int nfsd_stat_counters_init(void) +{ + return nfsd_percpu_counters_init(nfsdstats.counter, NFSD_STATS_COUNTERS_NUM); +} + +static void nfsd_stat_counters_destroy(void) +{ + nfsd_percpu_counters_destroy(nfsdstats.counter, NFSD_STATS_COUNTERS_NUM); +} + +int nfsd_stat_init(void) +{ + int err; + + err = nfsd_stat_counters_init(); + if (err) + return err; + svc_proc_register(&init_net, &nfsd_svcstats, &nfsd_proc_ops); + + return 0; } -void -nfsd_stat_shutdown(void) +void nfsd_stat_shutdown(void) { + nfsd_stat_counters_destroy(); svc_proc_unregister(&init_net, "nfsd"); } diff --git a/fs/nfsd/stats.h b/fs/nfsd/stats.h index b23fdac69820..51ecda852e23 100644 --- a/fs/nfsd/stats.h +++ b/fs/nfsd/stats.h @@ -8,37 +8,91 @@ #define _NFSD_STATS_H #include <uapi/linux/nfsd/stats.h> +#include <linux/percpu_counter.h> -struct nfsd_stats { - unsigned int rchits; /* repcache hits */ - unsigned int rcmisses; /* repcache hits */ - unsigned int rcnocache; /* uncached reqs */ - unsigned int fh_stale; /* FH stale error */ - unsigned int fh_lookup; /* dentry cached */ - unsigned int fh_anon; /* anon file dentry returned */ - unsigned int fh_nocache_dir; /* filehandle not found in dcache */ - unsigned int fh_nocache_nondir; /* filehandle not found in dcache */ - unsigned int io_read; /* bytes returned to read requests */ - unsigned int io_write; /* bytes passed in write requests */ - unsigned int th_cnt; /* number of available threads */ - unsigned int th_usage[10]; /* number of ticks during which n perdeciles - * of available threads were in use */ - unsigned int th_fullcnt; /* number of times last free thread was used */ - unsigned int ra_size; /* size of ra cache */ - unsigned int ra_depth[11]; /* number of times ra entry was found that deep - * in the cache (10percentiles). [10] = not found */ +enum { + NFSD_STATS_RC_HITS, /* repcache hits */ + NFSD_STATS_RC_MISSES, /* repcache misses */ + NFSD_STATS_RC_NOCACHE, /* uncached reqs */ + NFSD_STATS_FH_STALE, /* FH stale error */ + NFSD_STATS_IO_READ, /* bytes returned to read requests */ + NFSD_STATS_IO_WRITE, /* bytes passed in write requests */ #ifdef CONFIG_NFSD_V4 - unsigned int nfs4_opcount[LAST_NFS4_OP + 1]; /* count of individual nfsv4 operations */ + NFSD_STATS_FIRST_NFS4_OP, /* count of individual nfsv4 operations */ + NFSD_STATS_LAST_NFS4_OP = NFSD_STATS_FIRST_NFS4_OP + LAST_NFS4_OP, +#define NFSD_STATS_NFS4_OP(op) (NFSD_STATS_FIRST_NFS4_OP + (op)) #endif + NFSD_STATS_COUNTERS_NUM +}; + +struct nfsd_stats { + struct percpu_counter counter[NFSD_STATS_COUNTERS_NUM]; + /* Protected by nfsd_mutex */ + unsigned int th_cnt; /* number of available threads */ }; extern struct nfsd_stats nfsdstats; + extern struct svc_stat nfsd_svcstats; -void nfsd_stat_init(void); -void nfsd_stat_shutdown(void); +int nfsd_percpu_counters_init(struct percpu_counter counters[], int num); +void nfsd_percpu_counters_reset(struct percpu_counter counters[], int num); +void nfsd_percpu_counters_destroy(struct percpu_counter counters[], int num); +int nfsd_stat_init(void); +void nfsd_stat_shutdown(void); + +static inline void nfsd_stats_rc_hits_inc(void) +{ + percpu_counter_inc(&nfsdstats.counter[NFSD_STATS_RC_HITS]); +} + +static inline void nfsd_stats_rc_misses_inc(void) +{ + percpu_counter_inc(&nfsdstats.counter[NFSD_STATS_RC_MISSES]); +} + +static inline void nfsd_stats_rc_nocache_inc(void) +{ + percpu_counter_inc(&nfsdstats.counter[NFSD_STATS_RC_NOCACHE]); +} + +static inline void nfsd_stats_fh_stale_inc(struct svc_export *exp) +{ + percpu_counter_inc(&nfsdstats.counter[NFSD_STATS_FH_STALE]); + if (exp) + percpu_counter_inc(&exp->ex_stats.counter[EXP_STATS_FH_STALE]); +} + +static inline void nfsd_stats_io_read_add(struct svc_export *exp, s64 amount) +{ + percpu_counter_add(&nfsdstats.counter[NFSD_STATS_IO_READ], amount); + if (exp) + percpu_counter_add(&exp->ex_stats.counter[EXP_STATS_IO_READ], amount); +} + +static inline void nfsd_stats_io_write_add(struct svc_export *exp, s64 amount) +{ + percpu_counter_add(&nfsdstats.counter[NFSD_STATS_IO_WRITE], amount); + if (exp) + percpu_counter_add(&exp->ex_stats.counter[EXP_STATS_IO_WRITE], amount); +} + +static inline void nfsd_stats_payload_misses_inc(struct nfsd_net *nn) +{ + percpu_counter_inc(&nn->counter[NFSD_NET_PAYLOAD_MISSES]); +} + +static inline void nfsd_stats_drc_mem_usage_add(struct nfsd_net *nn, s64 amount) +{ + percpu_counter_add(&nn->counter[NFSD_NET_DRC_MEM_USAGE], amount); +} + +static inline void nfsd_stats_drc_mem_usage_sub(struct nfsd_net *nn, s64 amount) +{ + percpu_counter_sub(&nn->counter[NFSD_NET_DRC_MEM_USAGE], amount); +} #endif /* _NFSD_STATS_H */ diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 04937e51de56..d316e11923c5 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -889,7 +889,7 @@ static __be32 nfsd_finish_read(struct svc_rqst *rqstp, struct svc_fh *fhp, unsigned long *count, u32 *eof, ssize_t host_err) { if (host_err >= 0) { - nfsdstats.io_read += host_err; + nfsd_stats_io_read_add(fhp->fh_export, host_err); *eof = nfsd_eof_on_read(file, offset, host_err, *count); *count = host_err; fsnotify_access(file); @@ -1040,7 +1040,7 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf, goto out_nfserr; } *cnt = host_err; - nfsdstats.io_write += *cnt; + nfsd_stats_io_write_add(exp, *cnt); fsnotify_modify(file); if (stable && use_wgather) { diff --git a/fs/nfsd/xdr.h b/fs/nfsd/xdr.h index ad77387734cc..3018b52b6d5e 100644 --- a/fs/nfsd/xdr.h +++ b/fs/nfsd/xdr.h @@ -27,7 +27,6 @@ struct nfsd_readargs { struct svc_fh fh; __u32 offset; __u32 count; - int vlen; }; struct nfsd_writeargs { @@ -53,11 +52,6 @@ struct nfsd_renameargs { unsigned int tlen; }; -struct nfsd_readlinkargs { - struct svc_fh fh; - char * buffer; -}; - struct nfsd_linkargs { struct svc_fh ffh; struct svc_fh tfh; @@ -79,7 +73,6 @@ struct nfsd_readdirargs { struct svc_fh fh; __u32 cookie; __u32 count; - __be32 * buffer; }; struct nfsd_stat { @@ -144,14 +137,13 @@ union nfsd_xdrstore { #define NFS2_SVC_XDRSIZE sizeof(union nfsd_xdrstore) -int nfssvc_decode_fhandle(struct svc_rqst *, __be32 *); +int nfssvc_decode_fhandleargs(struct svc_rqst *, __be32 *); int nfssvc_decode_sattrargs(struct svc_rqst *, __be32 *); int nfssvc_decode_diropargs(struct svc_rqst *, __be32 *); int nfssvc_decode_readargs(struct svc_rqst *, __be32 *); int nfssvc_decode_writeargs(struct svc_rqst *, __be32 *); int nfssvc_decode_createargs(struct svc_rqst *, __be32 *); int nfssvc_decode_renameargs(struct svc_rqst *, __be32 *); -int nfssvc_decode_readlinkargs(struct svc_rqst *, __be32 *); int nfssvc_decode_linkargs(struct svc_rqst *, __be32 *); int nfssvc_decode_symlinkargs(struct svc_rqst *, __be32 *); int nfssvc_decode_readdirargs(struct svc_rqst *, __be32 *); @@ -172,6 +164,6 @@ void nfssvc_release_readres(struct svc_rqst *rqstp); /* Helper functions for NFSv2 ACL code */ __be32 *nfs2svc_encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp, struct kstat *stat); -__be32 *nfs2svc_decode_fh(__be32 *p, struct svc_fh *fhp); +bool svcxdr_decode_fhandle(struct xdr_stream *xdr, struct svc_fh *fhp); #endif /* LINUX_NFSD_H */ diff --git a/fs/nfsd/xdr3.h b/fs/nfsd/xdr3.h index 456fcd7a1038..3e1578953f54 100644 --- a/fs/nfsd/xdr3.h +++ b/fs/nfsd/xdr3.h @@ -25,14 +25,13 @@ struct nfsd3_diropargs { struct nfsd3_accessargs { struct svc_fh fh; - unsigned int access; + __u32 access; }; struct nfsd3_readargs { struct svc_fh fh; __u64 offset; __u32 count; - int vlen; }; struct nfsd3_writeargs { @@ -71,11 +70,6 @@ struct nfsd3_renameargs { unsigned int tlen; }; -struct nfsd3_readlinkargs { - struct svc_fh fh; - char * buffer; -}; - struct nfsd3_linkargs { struct svc_fh ffh; struct svc_fh tfh; @@ -96,10 +90,8 @@ struct nfsd3_symlinkargs { struct nfsd3_readdirargs { struct svc_fh fh; __u64 cookie; - __u32 dircount; __u32 count; __be32 * verf; - __be32 * buffer; }; struct nfsd3_commitargs { @@ -110,13 +102,13 @@ struct nfsd3_commitargs { struct nfsd3_getaclargs { struct svc_fh fh; - int mask; + __u32 mask; }; struct posix_acl; struct nfsd3_setaclargs { struct svc_fh fh; - int mask; + __u32 mask; struct posix_acl *acl_access; struct posix_acl *acl_default; }; @@ -273,7 +265,7 @@ union nfsd3_xdrstore { #define NFS3_SVC_XDRSIZE sizeof(union nfsd3_xdrstore) -int nfs3svc_decode_fhandle(struct svc_rqst *, __be32 *); +int nfs3svc_decode_fhandleargs(struct svc_rqst *, __be32 *); int nfs3svc_decode_sattrargs(struct svc_rqst *, __be32 *); int nfs3svc_decode_diropargs(struct svc_rqst *, __be32 *); int nfs3svc_decode_accessargs(struct svc_rqst *, __be32 *); @@ -283,7 +275,6 @@ int nfs3svc_decode_createargs(struct svc_rqst *, __be32 *); int nfs3svc_decode_mkdirargs(struct svc_rqst *, __be32 *); int nfs3svc_decode_mknodargs(struct svc_rqst *, __be32 *); int nfs3svc_decode_renameargs(struct svc_rqst *, __be32 *); -int nfs3svc_decode_readlinkargs(struct svc_rqst *, __be32 *); int nfs3svc_decode_linkargs(struct svc_rqst *, __be32 *); int nfs3svc_decode_symlinkargs(struct svc_rqst *, __be32 *); int nfs3svc_decode_readdirargs(struct svc_rqst *, __be32 *); @@ -316,7 +307,6 @@ int nfs3svc_encode_entry_plus(void *, const char *name, /* Helper functions for NFSv3 ACL code */ __be32 *nfs3svc_encode_post_op_attr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp); -__be32 *nfs3svc_decode_fh(__be32 *p, struct svc_fh *fhp); - +bool svcxdr_decode_nfs_fh3(struct xdr_stream *xdr, struct svc_fh *fhp); #endif /* _LINUX_NFSD_XDR3_H */ diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index a60ff5ce1a37..c300885ae75d 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -568,7 +568,6 @@ struct nfsd4_copy { struct nfs_fh c_fh; nfs4_stateid stateid; }; -extern bool inter_copy_offload_enable; struct nfsd4_seek { /* request */ diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c index 64bc81363c6c..e1bd592ce700 100644 --- a/fs/nilfs2/file.c +++ b/fs/nilfs2/file.c @@ -141,6 +141,7 @@ const struct file_operations nilfs_file_operations = { /* .release = nilfs_release_file, */ .fsync = nilfs_sync_file, .splice_read = generic_file_splice_read, + .splice_write = iter_file_splice_write, }; const struct inode_operations nilfs_file_inode_operations = { diff --git a/fs/nilfs2/segbuf.c b/fs/nilfs2/segbuf.c index 1a8729eded8b..1e75417bfe6e 100644 --- a/fs/nilfs2/segbuf.c +++ b/fs/nilfs2/segbuf.c @@ -386,10 +386,6 @@ static struct bio *nilfs_alloc_seg_bio(struct the_nilfs *nilfs, sector_t start, struct bio *bio; bio = bio_alloc(GFP_NOIO, nr_vecs); - if (bio == NULL) { - while (!bio && (nr_vecs >>= 1)) - bio = bio_alloc(GFP_NOIO, nr_vecs); - } if (likely(bio)) { bio_set_dev(bio, nilfs->ns_bdev); bio->bi_iter.bi_sector = diff --git a/fs/nilfs2/the_nilfs.h b/fs/nilfs2/the_nilfs.h index b55cdeb4d169..987c8ab02aee 100644 --- a/fs/nilfs2/the_nilfs.h +++ b/fs/nilfs2/the_nilfs.h @@ -375,7 +375,7 @@ static inline int nilfs_flush_device(struct the_nilfs *nilfs) */ smp_wmb(); - err = blkdev_issue_flush(nilfs->ns_bdev, GFP_KERNEL); + err = blkdev_issue_flush(nilfs->ns_bdev); if (err != -EIO) err = 0; return err; diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 3e01d8f2ab90..dcab112e1f00 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -1285,26 +1285,23 @@ fput_and_out: return ret; } +#ifndef CONFIG_ARCH_SPLIT_ARG64 SYSCALL_DEFINE5(fanotify_mark, int, fanotify_fd, unsigned int, flags, __u64, mask, int, dfd, const char __user *, pathname) { return do_fanotify_mark(fanotify_fd, flags, mask, dfd, pathname); } +#endif -#ifdef CONFIG_COMPAT -COMPAT_SYSCALL_DEFINE6(fanotify_mark, +#if defined(CONFIG_ARCH_SPLIT_ARG64) || defined(CONFIG_COMPAT) +SYSCALL32_DEFINE6(fanotify_mark, int, fanotify_fd, unsigned int, flags, - __u32, mask0, __u32, mask1, int, dfd, + SC_ARG64(mask), int, dfd, const char __user *, pathname) { - return do_fanotify_mark(fanotify_fd, flags, -#ifdef __BIG_ENDIAN - ((__u64)mask0 << 32) | mask1, -#else - ((__u64)mask1 << 32) | mask0, -#endif - dfd, pathname); + return do_fanotify_mark(fanotify_fd, flags, SC_VAL64(__u64, mask), + dfd, pathname); } #endif diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 85979e2214b3..df6d709d2ae3 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -194,7 +194,7 @@ static int ocfs2_sync_file(struct file *file, loff_t start, loff_t end, needs_barrier = true; err = jbd2_complete_transaction(journal, commit_tid); if (needs_barrier) { - ret = blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL); + ret = blkdev_issue_flush(inode->i_sb->s_bdev); if (!err) err = ret; } diff --git a/fs/open.c b/fs/open.c index 1e06e443a565..ca5444733acd 100644 --- a/fs/open.c +++ b/fs/open.c @@ -1091,6 +1091,12 @@ inline int build_open_flags(const struct open_how *how, struct open_flags *op) lookup_flags |= LOOKUP_BENEATH; if (how->resolve & RESOLVE_IN_ROOT) lookup_flags |= LOOKUP_IN_ROOT; + if (how->resolve & RESOLVE_CACHED) { + /* Don't bother even trying for create/truncate/tmpfile open */ + if (flags & (O_TRUNC | O_CREAT | O_TMPFILE)) + return -EAGAIN; + lookup_flags |= LOOKUP_CACHED; + } op->lookup_flags = lookup_flags; return 0; diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index e5b616c93e11..0fed532efa68 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -84,6 +84,14 @@ int ovl_copy_xattr(struct super_block *sb, struct dentry *old, if (ovl_is_private_xattr(sb, name)) continue; + + error = security_inode_copy_up_xattr(name); + if (error < 0 && error != -EOPNOTSUPP) + break; + if (error == 1) { + error = 0; + continue; /* Discard */ + } retry: size = vfs_getxattr(old, name, value, value_size); if (size == -ERANGE) @@ -107,13 +115,6 @@ retry: goto retry; } - error = security_inode_copy_up_xattr(name); - if (error < 0 && error != -EOPNOTSUPP) - break; - if (error == 1) { - error = 0; - continue; /* Discard */ - } error = vfs_setxattr(new, name, value, size, 0); if (error) { if (error != -EOPNOTSUPP || ovl_must_copy_xattr(name)) diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index 28a075b5f5b2..d1efa3a5a503 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -992,8 +992,8 @@ static char *ovl_get_redirect(struct dentry *dentry, bool abs_redirect) buflen -= thislen; memcpy(&buf[buflen], name, thislen); - tmp = dget_dlock(d->d_parent); spin_unlock(&d->d_lock); + tmp = dget_parent(d); dput(d); d = tmp; diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index bd9dd38347ae..077d3ad343f6 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -398,8 +398,9 @@ static int ovl_fsync(struct file *file, loff_t start, loff_t end, int datasync) const struct cred *old_cred; int ret; - if (!ovl_should_sync(OVL_FS(file_inode(file)->i_sb))) - return 0; + ret = ovl_sync_status(OVL_FS(file_inode(file)->i_sb)); + if (ret <= 0) + return ret; ret = ovl_real_fdget_meta(file, &real, !datasync); if (ret) diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index d739e14c6814..cf41bcb664bc 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -352,7 +352,9 @@ int ovl_xattr_set(struct dentry *dentry, struct inode *inode, const char *name, goto out; if (!value && !upperdentry) { + old_cred = ovl_override_creds(dentry->d_sb); err = vfs_getxattr(realdentry, name, NULL, 0); + revert_creds(old_cred); if (err < 0) goto out_drop_write; } diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index b487e48c7fd4..cb4e2d60ecf9 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -324,6 +324,7 @@ int ovl_check_metacopy_xattr(struct ovl_fs *ofs, struct dentry *dentry); bool ovl_is_metacopy_dentry(struct dentry *dentry); char *ovl_get_redirect_xattr(struct ovl_fs *ofs, struct dentry *dentry, int padding); +int ovl_sync_status(struct ovl_fs *ofs); static inline bool ovl_is_impuredir(struct super_block *sb, struct dentry *dentry) diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h index fbd5e27ce66b..63efee554f69 100644 --- a/fs/overlayfs/ovl_entry.h +++ b/fs/overlayfs/ovl_entry.h @@ -81,6 +81,8 @@ struct ovl_fs { atomic_long_t last_ino; /* Whiteout dentry cache */ struct dentry *whiteout; + /* r/o snapshot of upperdir sb's only taken on volatile mounts */ + errseq_t errseq; }; static inline struct vfsmount *ovl_upper_mnt(struct ovl_fs *ofs) diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c index 01620ebae1bd..f404a78e6b60 100644 --- a/fs/overlayfs/readdir.c +++ b/fs/overlayfs/readdir.c @@ -865,7 +865,7 @@ struct file *ovl_dir_real_file(const struct file *file, bool want_upper) struct ovl_dir_file *od = file->private_data; struct dentry *dentry = file->f_path.dentry; - struct file *realfile = od->realfile; + struct file *old, *realfile = od->realfile; if (!OVL_TYPE_UPPER(ovl_path_type(dentry))) return want_upper ? NULL : realfile; @@ -874,29 +874,20 @@ struct file *ovl_dir_real_file(const struct file *file, bool want_upper) * Need to check if we started out being a lower dir, but got copied up */ if (!od->is_upper) { - struct inode *inode = file_inode(file); - realfile = READ_ONCE(od->upperfile); if (!realfile) { struct path upperpath; ovl_path_upper(dentry, &upperpath); realfile = ovl_dir_open_realfile(file, &upperpath); + if (IS_ERR(realfile)) + return realfile; - inode_lock(inode); - if (!od->upperfile) { - if (IS_ERR(realfile)) { - inode_unlock(inode); - return realfile; - } - smp_store_release(&od->upperfile, realfile); - } else { - /* somebody has beaten us to it */ - if (!IS_ERR(realfile)) - fput(realfile); - realfile = od->upperfile; + old = cmpxchg_release(&od->upperfile, NULL, realfile); + if (old) { + fput(realfile); + realfile = old; } - inode_unlock(inode); } } @@ -909,8 +900,9 @@ static int ovl_dir_fsync(struct file *file, loff_t start, loff_t end, struct file *realfile; int err; - if (!ovl_should_sync(OVL_FS(file->f_path.dentry->d_sb))) - return 0; + err = ovl_sync_status(OVL_FS(file->f_path.dentry->d_sb)); + if (err <= 0) + return err; realfile = ovl_dir_real_file(file, true); err = PTR_ERR_OR_ZERO(realfile); diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 2bd570cbe8a4..d58b8f2bf9d0 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -264,11 +264,20 @@ static int ovl_sync_fs(struct super_block *sb, int wait) struct super_block *upper_sb; int ret; - if (!ovl_upper_mnt(ofs)) - return 0; + ret = ovl_sync_status(ofs); + /* + * We have to always set the err, because the return value isn't + * checked in syncfs, and instead indirectly return an error via + * the sb's writeback errseq, which VFS inspects after this call. + */ + if (ret < 0) { + errseq_set(&sb->s_wb_err, -EIO); + return -EIO; + } + + if (!ret) + return ret; - if (!ovl_should_sync(ofs)) - return 0; /* * Not called for sync(2) call or an emergency sync (SB_I_SKIP_SYNC). * All the super blocks will be iterated, including upper_sb. @@ -1923,6 +1932,10 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) unsigned int numlower; int err; + err = -EIO; + if (WARN_ON(sb->s_user_ns != current_user_ns())) + goto out; + sb->s_d_op = &ovl_dentry_operations; err = -ENOMEM; @@ -1989,6 +2002,8 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) sb->s_op = &ovl_super_operations; if (ofs->config.upperdir) { + struct super_block *upper_sb; + if (!ofs->config.workdir) { pr_err("missing 'workdir'\n"); goto out_err; @@ -1998,6 +2013,16 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) if (err) goto out_err; + upper_sb = ovl_upper_mnt(ofs)->mnt_sb; + if (!ovl_should_sync(ofs)) { + ofs->errseq = errseq_sample(&upper_sb->s_wb_err); + if (errseq_check(&upper_sb->s_wb_err, ofs->errseq)) { + err = -EIO; + pr_err("Cannot mount volatile when upperdir has an unseen error. Sync upperdir fs to clear state.\n"); + goto out_err; + } + } + err = ovl_get_workdir(sb, ofs, &upperpath); if (err) goto out_err; @@ -2005,9 +2030,8 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) if (!ofs->workdir) sb->s_flags |= SB_RDONLY; - sb->s_stack_depth = ovl_upper_mnt(ofs)->mnt_sb->s_stack_depth; - sb->s_time_gran = ovl_upper_mnt(ofs)->mnt_sb->s_time_gran; - + sb->s_stack_depth = upper_sb->s_stack_depth; + sb->s_time_gran = upper_sb->s_time_gran; } oe = ovl_get_lowerstack(sb, splitlower, numlower, ofs, layers); err = PTR_ERR(oe); diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c index 6569031af3cd..9826b003f1d2 100644 --- a/fs/overlayfs/util.c +++ b/fs/overlayfs/util.c @@ -962,3 +962,30 @@ err_free: kfree(buf); return ERR_PTR(res); } + +/* + * ovl_sync_status() - Check fs sync status for volatile mounts + * + * Returns 1 if this is not a volatile mount and a real sync is required. + * + * Returns 0 if syncing can be skipped because mount is volatile, and no errors + * have occurred on the upperdir since the mount. + * + * Returns -errno if it is a volatile mount, and the error that occurred since + * the last mount. If the error code changes, it'll return the latest error + * code. + */ + +int ovl_sync_status(struct ovl_fs *ofs) +{ + struct vfsmount *mnt; + + if (ovl_should_sync(ofs)) + return 1; + + mnt = ovl_upper_mnt(ofs); + if (!mnt) + return 0; + + return errseq_check(&mnt->mnt_sb->s_wb_err, ofs->errseq); +} diff --git a/fs/pipe.c b/fs/pipe.c index c5989cfd564d..39c96845a72f 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -1206,6 +1206,7 @@ const struct file_operations pipefifo_fops = { .unlocked_ioctl = pipe_ioctl, .release = pipe_release, .fasync = pipe_fasync, + .splice_write = iter_file_splice_write, }; /* diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 317899222d7f..d2018f70d1fa 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -1770,6 +1770,12 @@ static int process_sysctl_arg(char *param, char *val, return 0; } + if (!val) + return -EINVAL; + len = strlen(val); + if (len == 0) + return -EINVAL; + /* * To set sysctl options, we use a temporary mount of proc, look up the * respective sys/ file and write to it. To avoid mounting it when no @@ -1811,7 +1817,6 @@ static int process_sysctl_arg(char *param, char *val, file, param, val); goto out; } - len = strlen(val); wret = kernel_write(file, val, len, &pos); if (wret < 0) { err = wret; diff --git a/fs/proc/self.c b/fs/proc/self.c index cc71ce3466dc..a4012154e109 100644 --- a/fs/proc/self.c +++ b/fs/proc/self.c @@ -20,7 +20,7 @@ static const char *proc_self_get_link(struct dentry *dentry, * Not currently supported. Once we can inherit all of struct pid, * we can allow this. */ - if (current->flags & PF_KTHREAD) + if (current->flags & PF_IO_WORKER) return ERR_PTR(-EOPNOTSUPP); if (!tgid) diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index ee5a235b3056..3cec6fbef725 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1035,6 +1035,25 @@ struct clear_refs_private { }; #ifdef CONFIG_MEM_SOFT_DIRTY + +#define is_cow_mapping(flags) (((flags) & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE) + +static inline bool pte_is_pinned(struct vm_area_struct *vma, unsigned long addr, pte_t pte) +{ + struct page *page; + + if (!pte_write(pte)) + return false; + if (!is_cow_mapping(vma->vm_flags)) + return false; + if (likely(!atomic_read(&vma->vm_mm->has_pinned))) + return false; + page = vm_normal_page(vma, addr, pte); + if (!page) + return false; + return page_maybe_dma_pinned(page); +} + static inline void clear_soft_dirty(struct vm_area_struct *vma, unsigned long addr, pte_t *pte) { @@ -1049,6 +1068,8 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma, if (pte_present(ptent)) { pte_t old_pte; + if (pte_is_pinned(vma, addr, ptent)) + return; old_pte = ptep_modify_prot_start(vma, addr, pte); ptent = pte_wrprotect(old_pte); ptent = pte_clear_soft_dirty(ptent); @@ -1189,7 +1210,6 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, struct mm_struct *mm; struct vm_area_struct *vma; enum clear_refs_types type; - struct mmu_gather tlb; int itype; int rv; @@ -1215,53 +1235,41 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, .type = type, }; + if (mmap_write_lock_killable(mm)) { + count = -EINTR; + goto out_mm; + } if (type == CLEAR_REFS_MM_HIWATER_RSS) { - if (mmap_write_lock_killable(mm)) { - count = -EINTR; - goto out_mm; - } - /* * Writing 5 to /proc/pid/clear_refs resets the peak * resident set size to this mm's current rss value. */ reset_mm_hiwater_rss(mm); - mmap_write_unlock(mm); - goto out_mm; + goto out_unlock; } - if (mmap_read_lock_killable(mm)) { - count = -EINTR; - goto out_mm; - } - tlb_gather_mmu(&tlb, mm, 0, -1); if (type == CLEAR_REFS_SOFT_DIRTY) { for (vma = mm->mmap; vma; vma = vma->vm_next) { if (!(vma->vm_flags & VM_SOFTDIRTY)) continue; - mmap_read_unlock(mm); - if (mmap_write_lock_killable(mm)) { - count = -EINTR; - goto out_mm; - } - for (vma = mm->mmap; vma; vma = vma->vm_next) { - vma->vm_flags &= ~VM_SOFTDIRTY; - vma_set_page_prot(vma); - } - mmap_write_downgrade(mm); - break; + vma->vm_flags &= ~VM_SOFTDIRTY; + vma_set_page_prot(vma); } + inc_tlb_flush_pending(mm); mmu_notifier_range_init(&range, MMU_NOTIFY_SOFT_DIRTY, 0, NULL, mm, 0, -1UL); mmu_notifier_invalidate_range_start(&range); } walk_page_range(mm, 0, mm->highest_vm_end, &clear_refs_walk_ops, &cp); - if (type == CLEAR_REFS_SOFT_DIRTY) + if (type == CLEAR_REFS_SOFT_DIRTY) { mmu_notifier_invalidate_range_end(&range); - tlb_finish_mmu(&tlb, 0, -1); - mmap_read_unlock(mm); + flush_tlb_mm(mm); + dec_tlb_flush_pending(mm); + } +out_unlock: + mmap_write_unlock(mm); out_mm: mmput(mm); } diff --git a/fs/proc/thread_self.c b/fs/proc/thread_self.c index a553273fbd41..d56681d86d28 100644 --- a/fs/proc/thread_self.c +++ b/fs/proc/thread_self.c @@ -17,6 +17,13 @@ static const char *proc_thread_self_get_link(struct dentry *dentry, pid_t pid = task_pid_nr_ns(current, ns); char *name; + /* + * Not currently supported. Once we can inherit all of struct pid, + * we can allow this. + */ + if (current->flags & PF_IO_WORKER) + return ERR_PTR(-EOPNOTSUPP); + if (!pid) return ERR_PTR(-ENOENT); name = kmalloc(10 + 6 + 10 + 1, dentry ? GFP_KERNEL : GFP_ATOMIC); diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index 32f64abc277c..d963ae7902f9 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -269,7 +269,7 @@ static int pstore_compress(const void *in, void *out, { int ret; - if (!IS_ENABLED(CONFIG_PSTORE_COMPRESSION)) + if (!IS_ENABLED(CONFIG_PSTORE_COMPRESS)) return -EINVAL; ret = crypto_comp_compress(tfm, in, inlen, out, &outlen); @@ -671,7 +671,7 @@ static void decompress_record(struct pstore_record *record) int unzipped_len; char *unzipped, *workspace; - if (!IS_ENABLED(CONFIG_PSTORE_COMPRESSION) || !record->compressed) + if (!IS_ENABLED(CONFIG_PSTORE_COMPRESS) || !record->compressed) return; /* Only PSTORE_TYPE_DMESG support compression. */ diff --git a/fs/read_write.c b/fs/read_write.c index 75f764b43418..9db7adf160d2 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -1188,6 +1188,7 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, { struct fd in, out; struct inode *in_inode, *out_inode; + struct pipe_inode_info *opipe; loff_t pos; loff_t out_pos; ssize_t retval; @@ -1228,9 +1229,6 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, in_inode = file_inode(in.file); out_inode = file_inode(out.file); out_pos = out.file->f_pos; - retval = rw_verify_area(WRITE, out.file, &out_pos, count); - if (retval < 0) - goto fput_out; if (!max) max = min(in_inode->i_sb->s_maxbytes, out_inode->i_sb->s_maxbytes); @@ -1253,9 +1251,18 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, if (in.file->f_flags & O_NONBLOCK) fl = SPLICE_F_NONBLOCK; #endif - file_start_write(out.file); - retval = do_splice_direct(in.file, &pos, out.file, &out_pos, count, fl); - file_end_write(out.file); + opipe = get_pipe_info(out.file, true); + if (!opipe) { + retval = rw_verify_area(WRITE, out.file, &out_pos, count); + if (retval < 0) + goto fput_out; + file_start_write(out.file); + retval = do_splice_direct(in.file, &pos, out.file, &out_pos, + count, fl); + file_end_write(out.file); + } else { + retval = splice_file_to_pipe(in.file, opipe, &pos, count, fl); + } if (retval > 0) { add_rchar(current, retval); diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c index 0b641ae694f1..1db0254bc38b 100644 --- a/fs/reiserfs/file.c +++ b/fs/reiserfs/file.c @@ -159,7 +159,7 @@ static int reiserfs_sync_file(struct file *filp, loff_t start, loff_t end, barrier_done = reiserfs_commit_for_inode(inode); reiserfs_write_unlock(inode->i_sb); if (barrier_done != 1 && reiserfs_barrier_flush(inode->i_sb)) - blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL); + blkdev_issue_flush(inode->i_sb->s_bdev); inode_unlock(inode); if (barrier_done < 0) return barrier_done; diff --git a/fs/select.c b/fs/select.c index ebfebdfe5c69..37aaa8317f3a 100644 --- a/fs/select.c +++ b/fs/select.c @@ -1011,14 +1011,17 @@ static int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds, fdcount = do_poll(head, &table, end_time); poll_freewait(&table); + if (!user_write_access_begin(ufds, nfds * sizeof(*ufds))) + goto out_fds; + for (walk = head; walk; walk = walk->next) { struct pollfd *fds = walk->entries; int j; - for (j = 0; j < walk->len; j++, ufds++) - if (__put_user(fds[j].revents, &ufds->revents)) - goto out_fds; + for (j = walk->len; j; fds++, ufds++, j--) + unsafe_put_user(fds->revents, &ufds->revents, Efault); } + user_write_access_end(); err = fdcount; out_fds: @@ -1030,6 +1033,11 @@ out_fds: } return err; + +Efault: + user_write_access_end(); + err = -EFAULT; + goto out_fds; } static long do_restart_poll(struct restart_block *restart_block) diff --git a/fs/splice.c b/fs/splice.c index 866d5c2367b2..5dbce4dcc1a7 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -662,12 +662,14 @@ iter_file_splice_write(struct pipe_inode_info *pipe, struct file *out, /* build the vector */ left = sd.total_len; - for (n = 0; !pipe_empty(head, tail) && left && n < nbufs; tail++, n++) { + for (n = 0; !pipe_empty(head, tail) && left && n < nbufs; tail++) { struct pipe_buffer *buf = &pipe->bufs[tail & mask]; size_t this_len = buf->len; - if (this_len > left) - this_len = left; + /* zero-length bvecs are not supported, skip them */ + if (!this_len) + continue; + this_len = min(this_len, left); ret = pipe_buf_confirm(pipe, buf); if (unlikely(ret)) { @@ -680,6 +682,7 @@ iter_file_splice_write(struct pipe_inode_info *pipe, struct file *out, array[n].bv_len = this_len; array[n].bv_offset = buf->offset; left -= this_len; + n++; } iov_iter_bvec(&from, WRITE, array, n, sd.total_len - left); @@ -771,11 +774,16 @@ static long do_splice_to(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { + unsigned int p_space; int ret; if (unlikely(!(in->f_mode & FMODE_READ))) return -EBADF; + /* Don't try to read more the pipe has space for. */ + p_space = pipe->max_usage - pipe_occupancy(pipe->head, pipe->tail); + len = min_t(size_t, len, p_space << PAGE_SHIFT); + ret = rw_verify_area(READ, in, ppos, len); if (unlikely(ret < 0)) return ret; @@ -856,15 +864,10 @@ ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd, WARN_ON_ONCE(!pipe_empty(pipe->head, pipe->tail)); while (len) { - unsigned int p_space; size_t read_len; loff_t pos = sd->pos, prev_pos = pos; - /* Don't try to read more the pipe has space for. */ - p_space = pipe->max_usage - - pipe_occupancy(pipe->head, pipe->tail); - read_len = min_t(size_t, len, p_space << PAGE_SHIFT); - ret = do_splice_to(in, &pos, pipe, read_len, flags); + ret = do_splice_to(in, &pos, pipe, len, flags); if (unlikely(ret <= 0)) goto out_release; @@ -1002,6 +1005,23 @@ static int splice_pipe_to_pipe(struct pipe_inode_info *ipipe, struct pipe_inode_info *opipe, size_t len, unsigned int flags); +long splice_file_to_pipe(struct file *in, + struct pipe_inode_info *opipe, + loff_t *offset, + size_t len, unsigned int flags) +{ + long ret; + + pipe_lock(opipe); + ret = wait_for_space(opipe, flags); + if (!ret) + ret = do_splice_to(in, offset, opipe, len, flags); + pipe_unlock(opipe); + if (ret > 0) + wakeup_pipe_readers(opipe); + return ret; +} + /* * Determine where to splice to/from. */ @@ -1081,20 +1101,7 @@ long do_splice(struct file *in, loff_t *off_in, struct file *out, if (out->f_flags & O_NONBLOCK) flags |= SPLICE_F_NONBLOCK; - pipe_lock(opipe); - ret = wait_for_space(opipe, flags); - if (!ret) { - unsigned int p_space; - - /* Don't try to read more the pipe has space for. */ - p_space = opipe->max_usage - pipe_occupancy(opipe->head, opipe->tail); - len = min_t(size_t, len, p_space << PAGE_SHIFT); - - ret = do_splice_to(in, &offset, opipe, len, flags); - } - pipe_unlock(opipe); - if (ret > 0) - wakeup_pipe_readers(opipe); + ret = splice_file_to_pipe(in, opipe, &offset, len, flags); if (!off_in) in->f_pos = offset; else diff --git a/fs/squashfs/block.c b/fs/squashfs/block.c index 8a19773b5a0b..45f44425d856 100644 --- a/fs/squashfs/block.c +++ b/fs/squashfs/block.c @@ -196,9 +196,15 @@ int squashfs_read_data(struct super_block *sb, u64 index, int length, length = SQUASHFS_COMPRESSED_SIZE(length); index += 2; - TRACE("Block @ 0x%llx, %scompressed size %d\n", index, + TRACE("Block @ 0x%llx, %scompressed size %d\n", index - 2, compressed ? "" : "un", length); } + if (length < 0 || length > output->length || + (index + length) > msblk->bytes_used) { + res = -EIO; + goto out; + } + if (next_index) *next_index = index + length; diff --git a/fs/squashfs/export.c b/fs/squashfs/export.c index ae2c87bb0fbe..eb02072d28dd 100644 --- a/fs/squashfs/export.c +++ b/fs/squashfs/export.c @@ -41,12 +41,17 @@ static long long squashfs_inode_lookup(struct super_block *sb, int ino_num) struct squashfs_sb_info *msblk = sb->s_fs_info; int blk = SQUASHFS_LOOKUP_BLOCK(ino_num - 1); int offset = SQUASHFS_LOOKUP_BLOCK_OFFSET(ino_num - 1); - u64 start = le64_to_cpu(msblk->inode_lookup_table[blk]); + u64 start; __le64 ino; int err; TRACE("Entered squashfs_inode_lookup, inode_number = %d\n", ino_num); + if (ino_num == 0 || (ino_num - 1) >= msblk->inodes) + return -EINVAL; + + start = le64_to_cpu(msblk->inode_lookup_table[blk]); + err = squashfs_read_metadata(sb, &ino, &start, &offset, sizeof(ino)); if (err < 0) return err; @@ -111,7 +116,10 @@ __le64 *squashfs_read_inode_lookup_table(struct super_block *sb, u64 lookup_table_start, u64 next_table, unsigned int inodes) { unsigned int length = SQUASHFS_LOOKUP_BLOCK_BYTES(inodes); + unsigned int indexes = SQUASHFS_LOOKUP_BLOCKS(inodes); + int n; __le64 *table; + u64 start, end; TRACE("In read_inode_lookup_table, length %d\n", length); @@ -121,20 +129,37 @@ __le64 *squashfs_read_inode_lookup_table(struct super_block *sb, if (inodes == 0) return ERR_PTR(-EINVAL); - /* length bytes should not extend into the next table - this check - * also traps instances where lookup_table_start is incorrectly larger - * than the next table start + /* + * The computed size of the lookup table (length bytes) should exactly + * match the table start and end points */ - if (lookup_table_start + length > next_table) + if (length != (next_table - lookup_table_start)) return ERR_PTR(-EINVAL); table = squashfs_read_table(sb, lookup_table_start, length); + if (IS_ERR(table)) + return table; /* - * table[0] points to the first inode lookup table metadata block, - * this should be less than lookup_table_start + * table0], table[1], ... table[indexes - 1] store the locations + * of the compressed inode lookup blocks. Each entry should be + * less than the next (i.e. table[0] < table[1]), and the difference + * between them should be SQUASHFS_METADATA_SIZE or less. + * table[indexes - 1] should be less than lookup_table_start, and + * again the difference should be SQUASHFS_METADATA_SIZE or less */ - if (!IS_ERR(table) && le64_to_cpu(table[0]) >= lookup_table_start) { + for (n = 0; n < (indexes - 1); n++) { + start = le64_to_cpu(table[n]); + end = le64_to_cpu(table[n + 1]); + + if (start >= end || (end - start) > SQUASHFS_METADATA_SIZE) { + kfree(table); + return ERR_PTR(-EINVAL); + } + } + + start = le64_to_cpu(table[indexes - 1]); + if (start >= lookup_table_start || (lookup_table_start - start) > SQUASHFS_METADATA_SIZE) { kfree(table); return ERR_PTR(-EINVAL); } diff --git a/fs/squashfs/id.c b/fs/squashfs/id.c index 6be5afe7287d..11581bf31af4 100644 --- a/fs/squashfs/id.c +++ b/fs/squashfs/id.c @@ -35,10 +35,15 @@ int squashfs_get_id(struct super_block *sb, unsigned int index, struct squashfs_sb_info *msblk = sb->s_fs_info; int block = SQUASHFS_ID_BLOCK(index); int offset = SQUASHFS_ID_BLOCK_OFFSET(index); - u64 start_block = le64_to_cpu(msblk->id_table[block]); + u64 start_block; __le32 disk_id; int err; + if (index >= msblk->ids) + return -EINVAL; + + start_block = le64_to_cpu(msblk->id_table[block]); + err = squashfs_read_metadata(sb, &disk_id, &start_block, &offset, sizeof(disk_id)); if (err < 0) @@ -56,7 +61,10 @@ __le64 *squashfs_read_id_index_table(struct super_block *sb, u64 id_table_start, u64 next_table, unsigned short no_ids) { unsigned int length = SQUASHFS_ID_BLOCK_BYTES(no_ids); + unsigned int indexes = SQUASHFS_ID_BLOCKS(no_ids); + int n; __le64 *table; + u64 start, end; TRACE("In read_id_index_table, length %d\n", length); @@ -67,20 +75,36 @@ __le64 *squashfs_read_id_index_table(struct super_block *sb, return ERR_PTR(-EINVAL); /* - * length bytes should not extend into the next table - this check - * also traps instances where id_table_start is incorrectly larger - * than the next table start + * The computed size of the index table (length bytes) should exactly + * match the table start and end points */ - if (id_table_start + length > next_table) + if (length != (next_table - id_table_start)) return ERR_PTR(-EINVAL); table = squashfs_read_table(sb, id_table_start, length); + if (IS_ERR(table)) + return table; /* - * table[0] points to the first id lookup table metadata block, this - * should be less than id_table_start + * table[0], table[1], ... table[indexes - 1] store the locations + * of the compressed id blocks. Each entry should be less than + * the next (i.e. table[0] < table[1]), and the difference between them + * should be SQUASHFS_METADATA_SIZE or less. table[indexes - 1] + * should be less than id_table_start, and again the difference + * should be SQUASHFS_METADATA_SIZE or less */ - if (!IS_ERR(table) && le64_to_cpu(table[0]) >= id_table_start) { + for (n = 0; n < (indexes - 1); n++) { + start = le64_to_cpu(table[n]); + end = le64_to_cpu(table[n + 1]); + + if (start >= end || (end - start) > SQUASHFS_METADATA_SIZE) { + kfree(table); + return ERR_PTR(-EINVAL); + } + } + + start = le64_to_cpu(table[indexes - 1]); + if (start >= id_table_start || (id_table_start - start) > SQUASHFS_METADATA_SIZE) { kfree(table); return ERR_PTR(-EINVAL); } diff --git a/fs/squashfs/squashfs_fs_sb.h b/fs/squashfs/squashfs_fs_sb.h index 34c21ffb6df3..166e98806265 100644 --- a/fs/squashfs/squashfs_fs_sb.h +++ b/fs/squashfs/squashfs_fs_sb.h @@ -64,5 +64,6 @@ struct squashfs_sb_info { unsigned int inodes; unsigned int fragments; int xattr_ids; + unsigned int ids; }; #endif diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c index d6c6593ec169..88cc94be1076 100644 --- a/fs/squashfs/super.c +++ b/fs/squashfs/super.c @@ -166,6 +166,7 @@ static int squashfs_fill_super(struct super_block *sb, struct fs_context *fc) msblk->directory_table = le64_to_cpu(sblk->directory_table_start); msblk->inodes = le32_to_cpu(sblk->inodes); msblk->fragments = le32_to_cpu(sblk->fragments); + msblk->ids = le16_to_cpu(sblk->no_ids); flags = le16_to_cpu(sblk->flags); TRACE("Found valid superblock on %pg\n", sb->s_bdev); @@ -177,7 +178,7 @@ static int squashfs_fill_super(struct super_block *sb, struct fs_context *fc) TRACE("Block size %d\n", msblk->block_size); TRACE("Number of inodes %d\n", msblk->inodes); TRACE("Number of fragments %d\n", msblk->fragments); - TRACE("Number of ids %d\n", le16_to_cpu(sblk->no_ids)); + TRACE("Number of ids %d\n", msblk->ids); TRACE("sblk->inode_table_start %llx\n", msblk->inode_table); TRACE("sblk->directory_table_start %llx\n", msblk->directory_table); TRACE("sblk->fragment_table_start %llx\n", @@ -236,8 +237,7 @@ static int squashfs_fill_super(struct super_block *sb, struct fs_context *fc) allocate_id_index_table: /* Allocate and read id index table */ msblk->id_table = squashfs_read_id_index_table(sb, - le64_to_cpu(sblk->id_table_start), next_table, - le16_to_cpu(sblk->no_ids)); + le64_to_cpu(sblk->id_table_start), next_table, msblk->ids); if (IS_ERR(msblk->id_table)) { errorf(fc, "unable to read id index table"); err = PTR_ERR(msblk->id_table); diff --git a/fs/squashfs/xattr.h b/fs/squashfs/xattr.h index 184129afd456..d8a270d3ac4c 100644 --- a/fs/squashfs/xattr.h +++ b/fs/squashfs/xattr.h @@ -17,8 +17,16 @@ extern int squashfs_xattr_lookup(struct super_block *, unsigned int, int *, static inline __le64 *squashfs_read_xattr_id_table(struct super_block *sb, u64 start, u64 *xattr_table_start, int *xattr_ids) { + struct squashfs_xattr_id_table *id_table; + + id_table = squashfs_read_table(sb, start, sizeof(*id_table)); + if (IS_ERR(id_table)) + return (__le64 *) id_table; + + *xattr_table_start = le64_to_cpu(id_table->xattr_table_start); + kfree(id_table); + ERROR("Xattrs in filesystem, these will be ignored\n"); - *xattr_table_start = start; return ERR_PTR(-ENOTSUPP); } diff --git a/fs/squashfs/xattr_id.c b/fs/squashfs/xattr_id.c index d99e08464554..ead66670b41a 100644 --- a/fs/squashfs/xattr_id.c +++ b/fs/squashfs/xattr_id.c @@ -31,10 +31,15 @@ int squashfs_xattr_lookup(struct super_block *sb, unsigned int index, struct squashfs_sb_info *msblk = sb->s_fs_info; int block = SQUASHFS_XATTR_BLOCK(index); int offset = SQUASHFS_XATTR_BLOCK_OFFSET(index); - u64 start_block = le64_to_cpu(msblk->xattr_id_table[block]); + u64 start_block; struct squashfs_xattr_id id; int err; + if (index >= msblk->xattr_ids) + return -EINVAL; + + start_block = le64_to_cpu(msblk->xattr_id_table[block]); + err = squashfs_read_metadata(sb, &id, &start_block, &offset, sizeof(id)); if (err < 0) @@ -50,13 +55,17 @@ int squashfs_xattr_lookup(struct super_block *sb, unsigned int index, /* * Read uncompressed xattr id lookup table indexes from disk into memory */ -__le64 *squashfs_read_xattr_id_table(struct super_block *sb, u64 start, +__le64 *squashfs_read_xattr_id_table(struct super_block *sb, u64 table_start, u64 *xattr_table_start, int *xattr_ids) { - unsigned int len; + struct squashfs_sb_info *msblk = sb->s_fs_info; + unsigned int len, indexes; struct squashfs_xattr_id_table *id_table; + __le64 *table; + u64 start, end; + int n; - id_table = squashfs_read_table(sb, start, sizeof(*id_table)); + id_table = squashfs_read_table(sb, table_start, sizeof(*id_table)); if (IS_ERR(id_table)) return (__le64 *) id_table; @@ -70,13 +79,52 @@ __le64 *squashfs_read_xattr_id_table(struct super_block *sb, u64 start, if (*xattr_ids == 0) return ERR_PTR(-EINVAL); - /* xattr_table should be less than start */ - if (*xattr_table_start >= start) + len = SQUASHFS_XATTR_BLOCK_BYTES(*xattr_ids); + indexes = SQUASHFS_XATTR_BLOCKS(*xattr_ids); + + /* + * The computed size of the index table (len bytes) should exactly + * match the table start and end points + */ + start = table_start + sizeof(*id_table); + end = msblk->bytes_used; + + if (len != (end - start)) return ERR_PTR(-EINVAL); - len = SQUASHFS_XATTR_BLOCK_BYTES(*xattr_ids); + table = squashfs_read_table(sb, start, len); + if (IS_ERR(table)) + return table; + + /* table[0], table[1], ... table[indexes - 1] store the locations + * of the compressed xattr id blocks. Each entry should be less than + * the next (i.e. table[0] < table[1]), and the difference between them + * should be SQUASHFS_METADATA_SIZE or less. table[indexes - 1] + * should be less than table_start, and again the difference + * shouls be SQUASHFS_METADATA_SIZE or less. + * + * Finally xattr_table_start should be less than table[0]. + */ + for (n = 0; n < (indexes - 1); n++) { + start = le64_to_cpu(table[n]); + end = le64_to_cpu(table[n + 1]); + + if (start >= end || (end - start) > SQUASHFS_METADATA_SIZE) { + kfree(table); + return ERR_PTR(-EINVAL); + } + } + + start = le64_to_cpu(table[indexes - 1]); + if (start >= table_start || (table_start - start) > SQUASHFS_METADATA_SIZE) { + kfree(table); + return ERR_PTR(-EINVAL); + } - TRACE("In read_xattr_index_table, length %d\n", len); + if (*xattr_table_start >= le64_to_cpu(table[0])) { + kfree(table); + return ERR_PTR(-EINVAL); + } - return squashfs_read_table(sb, start + sizeof(*id_table), len); + return table; } diff --git a/fs/statfs.c b/fs/statfs.c index 68cb07788750..0ba34c135593 100644 --- a/fs/statfs.c +++ b/fs/statfs.c @@ -255,7 +255,10 @@ SYSCALL_DEFINE2(ustat, unsigned, dev, struct ustat __user *, ubuf) memset(&tmp,0,sizeof(struct ustat)); tmp.f_tfree = sbuf.f_bfree; - tmp.f_tinode = sbuf.f_ffree; + if (IS_ENABLED(CONFIG_ARCH_32BIT_USTAT_F_TINODE)) + tmp.f_tinode = min_t(u64, sbuf.f_ffree, UINT_MAX); + else + tmp.f_tinode = sbuf.f_ffree; return copy_to_user(ubuf, &tmp, sizeof(struct ustat)) ? -EFAULT : 0; } diff --git a/fs/super.c b/fs/super.c index 2c6cdea2ab2d..5a1f384ffc74 100644 --- a/fs/super.c +++ b/fs/super.c @@ -865,7 +865,8 @@ int reconfigure_super(struct fs_context *fc) if (fc->sb_flags_mask & SB_RDONLY) { #ifdef CONFIG_BLOCK - if (!(fc->sb_flags & SB_RDONLY) && bdev_read_only(sb->s_bdev)) + if (!(fc->sb_flags & SB_RDONLY) && sb->s_bdev && + bdev_read_only(sb->s_bdev)) return -EACCES; #endif diff --git a/fs/ubifs/auth.c b/fs/ubifs/auth.c index 51a7c8c2c3f0..e564d5ff8781 100644 --- a/fs/ubifs/auth.c +++ b/fs/ubifs/auth.c @@ -327,7 +327,7 @@ int ubifs_init_authentication(struct ubifs_info *c) ubifs_err(c, "hmac %s is bigger than maximum allowed hmac size (%d > %d)", hmac_name, c->hmac_desc_len, UBIFS_HMAC_ARR_SZ); err = -EINVAL; - goto out_free_hash; + goto out_free_hmac; } err = crypto_shash_setkey(c->hmac_tfm, ukp->data, ukp->datalen); diff --git a/fs/ubifs/journal.c b/fs/ubifs/journal.c index 03410ae0813a..2857e64d673d 100644 --- a/fs/ubifs/journal.c +++ b/fs/ubifs/journal.c @@ -881,7 +881,7 @@ int ubifs_jnl_write_inode(struct ubifs_info *c, const struct inode *inode) struct inode *xino; struct ubifs_dent_node *xent, *pxent = NULL; - if (ui->xattr_cnt >= ubifs_xattr_max_cnt(c)) { + if (ui->xattr_cnt > ubifs_xattr_max_cnt(c)) { ubifs_err(c, "Cannot delete inode, it has too much xattrs!"); goto out_release; } diff --git a/fs/ubifs/replay.c b/fs/ubifs/replay.c index 79801c9a5b87..0f8a6a16421b 100644 --- a/fs/ubifs/replay.c +++ b/fs/ubifs/replay.c @@ -559,7 +559,9 @@ static int is_last_bud(struct ubifs_info *c, struct ubifs_bud *bud) } /* authenticate_sleb_hash is split out for stack usage */ -static int authenticate_sleb_hash(struct ubifs_info *c, struct shash_desc *log_hash, u8 *hash) +static int noinline_for_stack +authenticate_sleb_hash(struct ubifs_info *c, + struct shash_desc *log_hash, u8 *hash) { SHASH_DESC_ON_STACK(hash_desc, c->hash_tfm); diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 138b9426c6c1..ddb2ca636c93 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -838,8 +838,10 @@ static int alloc_wbufs(struct ubifs_info *c) c->jheads[i].wbuf.jhead = i; c->jheads[i].grouped = 1; c->jheads[i].log_hash = ubifs_hash_get_desc(c); - if (IS_ERR(c->jheads[i].log_hash)) + if (IS_ERR(c->jheads[i].log_hash)) { + err = PTR_ERR(c->jheads[i].log_hash); goto out; + } } /* diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c index a0b9b349efe6..842d5f14545d 100644 --- a/fs/ubifs/xattr.c +++ b/fs/ubifs/xattr.c @@ -498,7 +498,7 @@ int ubifs_purge_xattrs(struct inode *host) struct fscrypt_name nm = {0}; int err; - if (ubifs_inode(host)->xattr_cnt < ubifs_xattr_max_cnt(c)) + if (ubifs_inode(host)->xattr_cnt <= ubifs_xattr_max_cnt(c)) return 0; ubifs_warn(c, "inode %lu has too many xattrs, doing a non-atomic deletion", diff --git a/fs/udf/super.c b/fs/udf/super.c index 5bef3a68395d..d0df217f4712 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -705,6 +705,7 @@ static int udf_check_vsd(struct super_block *sb) struct buffer_head *bh = NULL; int nsr = 0; struct udf_sb_info *sbi; + loff_t session_offset; sbi = UDF_SB(sb); if (sb->s_blocksize < sizeof(struct volStructDesc)) @@ -712,7 +713,8 @@ static int udf_check_vsd(struct super_block *sb) else sectorsize = sb->s_blocksize; - sector += (((loff_t)sbi->s_session) << sb->s_blocksize_bits); + session_offset = (loff_t)sbi->s_session << sb->s_blocksize_bits; + sector += session_offset; udf_debug("Starting at sector %u (%lu byte sectors)\n", (unsigned int)(sector >> sb->s_blocksize_bits), @@ -757,8 +759,7 @@ static int udf_check_vsd(struct super_block *sb) if (nsr > 0) return 1; - else if (!bh && sector - (sbi->s_session << sb->s_blocksize_bits) == - VSD_FIRST_SECTOR_OFFSET) + else if (!bh && sector - session_offset == VSD_FIRST_SECTOR_OFFSET) return -1; else return 0; diff --git a/fs/verity/Makefile b/fs/verity/Makefile index 570e9136334d..435559a4fa9e 100644 --- a/fs/verity/Makefile +++ b/fs/verity/Makefile @@ -5,6 +5,7 @@ obj-$(CONFIG_FS_VERITY) += enable.o \ init.o \ measure.o \ open.o \ + read_metadata.o \ verify.o obj-$(CONFIG_FS_VERITY_BUILTIN_SIGNATURES) += signature.o diff --git a/fs/verity/fsverity_private.h b/fs/verity/fsverity_private.h index 6413d28664d6..a7920434bae5 100644 --- a/fs/verity/fsverity_private.h +++ b/fs/verity/fsverity_private.h @@ -122,12 +122,17 @@ int fsverity_init_merkle_tree_params(struct merkle_tree_params *params, const u8 *salt, size_t salt_size); struct fsverity_info *fsverity_create_info(const struct inode *inode, - void *desc, size_t desc_size); + struct fsverity_descriptor *desc, + size_t desc_size); void fsverity_set_info(struct inode *inode, struct fsverity_info *vi); void fsverity_free_info(struct fsverity_info *vi); +int fsverity_get_descriptor(struct inode *inode, + struct fsverity_descriptor **desc_ret, + size_t *desc_size_ret); + int __init fsverity_init_info_cache(void); void __init fsverity_exit_info_cache(void); @@ -135,15 +140,13 @@ void __init fsverity_exit_info_cache(void); #ifdef CONFIG_FS_VERITY_BUILTIN_SIGNATURES int fsverity_verify_signature(const struct fsverity_info *vi, - const struct fsverity_descriptor *desc, - size_t desc_size); + const u8 *signature, size_t sig_size); int __init fsverity_init_signature(void); #else /* !CONFIG_FS_VERITY_BUILTIN_SIGNATURES */ static inline int fsverity_verify_signature(const struct fsverity_info *vi, - const struct fsverity_descriptor *desc, - size_t desc_size) + const u8 *signature, size_t sig_size) { return 0; } diff --git a/fs/verity/open.c b/fs/verity/open.c index 228d0eca3e2e..60ff8af7219f 100644 --- a/fs/verity/open.c +++ b/fs/verity/open.c @@ -142,45 +142,17 @@ static int compute_file_digest(struct fsverity_hash_alg *hash_alg, } /* - * Validate the given fsverity_descriptor and create a new fsverity_info from - * it. The signature (if present) is also checked. + * Create a new fsverity_info from the given fsverity_descriptor (with optional + * appended signature), and check the signature if present. The + * fsverity_descriptor must have already undergone basic validation. */ struct fsverity_info *fsverity_create_info(const struct inode *inode, - void *_desc, size_t desc_size) + struct fsverity_descriptor *desc, + size_t desc_size) { - struct fsverity_descriptor *desc = _desc; struct fsverity_info *vi; int err; - if (desc_size < sizeof(*desc)) { - fsverity_err(inode, "Unrecognized descriptor size: %zu bytes", - desc_size); - return ERR_PTR(-EINVAL); - } - - if (desc->version != 1) { - fsverity_err(inode, "Unrecognized descriptor version: %u", - desc->version); - return ERR_PTR(-EINVAL); - } - - if (memchr_inv(desc->__reserved, 0, sizeof(desc->__reserved))) { - fsverity_err(inode, "Reserved bits set in descriptor"); - return ERR_PTR(-EINVAL); - } - - if (desc->salt_size > sizeof(desc->salt)) { - fsverity_err(inode, "Invalid salt_size: %u", desc->salt_size); - return ERR_PTR(-EINVAL); - } - - if (le64_to_cpu(desc->data_size) != inode->i_size) { - fsverity_err(inode, - "Wrong data_size: %llu (desc) != %lld (inode)", - le64_to_cpu(desc->data_size), inode->i_size); - return ERR_PTR(-EINVAL); - } - vi = kmem_cache_zalloc(fsverity_info_cachep, GFP_KERNEL); if (!vi) return ERR_PTR(-ENOMEM); @@ -209,7 +181,8 @@ struct fsverity_info *fsverity_create_info(const struct inode *inode, vi->tree_params.hash_alg->name, vi->tree_params.digest_size, vi->file_digest); - err = fsverity_verify_signature(vi, desc, desc_size); + err = fsverity_verify_signature(vi, desc->signature, + le32_to_cpu(desc->sig_size)); out: if (err) { fsverity_free_info(vi); @@ -245,15 +218,57 @@ void fsverity_free_info(struct fsverity_info *vi) kmem_cache_free(fsverity_info_cachep, vi); } -/* Ensure the inode has an ->i_verity_info */ -static int ensure_verity_info(struct inode *inode) +static bool validate_fsverity_descriptor(struct inode *inode, + const struct fsverity_descriptor *desc, + size_t desc_size) { - struct fsverity_info *vi = fsverity_get_info(inode); - struct fsverity_descriptor *desc; - int res; + if (desc_size < sizeof(*desc)) { + fsverity_err(inode, "Unrecognized descriptor size: %zu bytes", + desc_size); + return false; + } - if (vi) - return 0; + if (desc->version != 1) { + fsverity_err(inode, "Unrecognized descriptor version: %u", + desc->version); + return false; + } + + if (memchr_inv(desc->__reserved, 0, sizeof(desc->__reserved))) { + fsverity_err(inode, "Reserved bits set in descriptor"); + return false; + } + + if (desc->salt_size > sizeof(desc->salt)) { + fsverity_err(inode, "Invalid salt_size: %u", desc->salt_size); + return false; + } + + if (le64_to_cpu(desc->data_size) != inode->i_size) { + fsverity_err(inode, + "Wrong data_size: %llu (desc) != %lld (inode)", + le64_to_cpu(desc->data_size), inode->i_size); + return false; + } + + if (le32_to_cpu(desc->sig_size) > desc_size - sizeof(*desc)) { + fsverity_err(inode, "Signature overflows verity descriptor"); + return false; + } + + return true; +} + +/* + * Read the inode's fsverity_descriptor (with optional appended signature) from + * the filesystem, and do basic validation of it. + */ +int fsverity_get_descriptor(struct inode *inode, + struct fsverity_descriptor **desc_ret, + size_t *desc_size_ret) +{ + int res; + struct fsverity_descriptor *desc; res = inode->i_sb->s_vop->get_verity_descriptor(inode, NULL, 0); if (res < 0) { @@ -272,20 +287,46 @@ static int ensure_verity_info(struct inode *inode) res = inode->i_sb->s_vop->get_verity_descriptor(inode, desc, res); if (res < 0) { fsverity_err(inode, "Error %d reading verity descriptor", res); - goto out_free_desc; + kfree(desc); + return res; + } + + if (!validate_fsverity_descriptor(inode, desc, res)) { + kfree(desc); + return -EINVAL; } - vi = fsverity_create_info(inode, desc, res); + *desc_ret = desc; + *desc_size_ret = res; + return 0; +} + +/* Ensure the inode has an ->i_verity_info */ +static int ensure_verity_info(struct inode *inode) +{ + struct fsverity_info *vi = fsverity_get_info(inode); + struct fsverity_descriptor *desc; + size_t desc_size; + int err; + + if (vi) + return 0; + + err = fsverity_get_descriptor(inode, &desc, &desc_size); + if (err) + return err; + + vi = fsverity_create_info(inode, desc, desc_size); if (IS_ERR(vi)) { - res = PTR_ERR(vi); + err = PTR_ERR(vi); goto out_free_desc; } fsverity_set_info(inode, vi); - res = 0; + err = 0; out_free_desc: kfree(desc); - return res; + return err; } /** diff --git a/fs/verity/read_metadata.c b/fs/verity/read_metadata.c new file mode 100644 index 000000000000..7e2d0c7bdf0d --- /dev/null +++ b/fs/verity/read_metadata.c @@ -0,0 +1,195 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Ioctl to read verity metadata + * + * Copyright 2021 Google LLC + */ + +#include "fsverity_private.h" + +#include <linux/backing-dev.h> +#include <linux/highmem.h> +#include <linux/sched/signal.h> +#include <linux/uaccess.h> + +static int fsverity_read_merkle_tree(struct inode *inode, + const struct fsverity_info *vi, + void __user *buf, u64 offset, int length) +{ + const struct fsverity_operations *vops = inode->i_sb->s_vop; + u64 end_offset; + unsigned int offs_in_page; + pgoff_t index, last_index; + int retval = 0; + int err = 0; + + end_offset = min(offset + length, vi->tree_params.tree_size); + if (offset >= end_offset) + return 0; + offs_in_page = offset_in_page(offset); + last_index = (end_offset - 1) >> PAGE_SHIFT; + + /* + * Iterate through each Merkle tree page in the requested range and copy + * the requested portion to userspace. Note that the Merkle tree block + * size isn't important here, as we are returning a byte stream; i.e., + * we can just work with pages even if the tree block size != PAGE_SIZE. + */ + for (index = offset >> PAGE_SHIFT; index <= last_index; index++) { + unsigned long num_ra_pages = + min_t(unsigned long, last_index - index + 1, + inode->i_sb->s_bdi->io_pages); + unsigned int bytes_to_copy = min_t(u64, end_offset - offset, + PAGE_SIZE - offs_in_page); + struct page *page; + const void *virt; + + page = vops->read_merkle_tree_page(inode, index, num_ra_pages); + if (IS_ERR(page)) { + err = PTR_ERR(page); + fsverity_err(inode, + "Error %d reading Merkle tree page %lu", + err, index); + break; + } + + virt = kmap(page); + if (copy_to_user(buf, virt + offs_in_page, bytes_to_copy)) { + kunmap(page); + put_page(page); + err = -EFAULT; + break; + } + kunmap(page); + put_page(page); + + retval += bytes_to_copy; + buf += bytes_to_copy; + offset += bytes_to_copy; + + if (fatal_signal_pending(current)) { + err = -EINTR; + break; + } + cond_resched(); + offs_in_page = 0; + } + return retval ? retval : err; +} + +/* Copy the requested portion of the buffer to userspace. */ +static int fsverity_read_buffer(void __user *dst, u64 offset, int length, + const void *src, size_t src_length) +{ + if (offset >= src_length) + return 0; + src += offset; + src_length -= offset; + + length = min_t(size_t, length, src_length); + + if (copy_to_user(dst, src, length)) + return -EFAULT; + + return length; +} + +static int fsverity_read_descriptor(struct inode *inode, + void __user *buf, u64 offset, int length) +{ + struct fsverity_descriptor *desc; + size_t desc_size; + int res; + + res = fsverity_get_descriptor(inode, &desc, &desc_size); + if (res) + return res; + + /* don't include the signature */ + desc_size = offsetof(struct fsverity_descriptor, signature); + desc->sig_size = 0; + + res = fsverity_read_buffer(buf, offset, length, desc, desc_size); + + kfree(desc); + return res; +} + +static int fsverity_read_signature(struct inode *inode, + void __user *buf, u64 offset, int length) +{ + struct fsverity_descriptor *desc; + size_t desc_size; + int res; + + res = fsverity_get_descriptor(inode, &desc, &desc_size); + if (res) + return res; + + if (desc->sig_size == 0) { + res = -ENODATA; + goto out; + } + + /* + * Include only the signature. Note that fsverity_get_descriptor() + * already verified that sig_size is in-bounds. + */ + res = fsverity_read_buffer(buf, offset, length, desc->signature, + le32_to_cpu(desc->sig_size)); +out: + kfree(desc); + return res; +} + +/** + * fsverity_ioctl_read_metadata() - read verity metadata from a file + * @filp: file to read the metadata from + * @uarg: user pointer to fsverity_read_metadata_arg + * + * Return: length read on success, 0 on EOF, -errno on failure + */ +int fsverity_ioctl_read_metadata(struct file *filp, const void __user *uarg) +{ + struct inode *inode = file_inode(filp); + const struct fsverity_info *vi; + struct fsverity_read_metadata_arg arg; + int length; + void __user *buf; + + vi = fsverity_get_info(inode); + if (!vi) + return -ENODATA; /* not a verity file */ + /* + * Note that we don't have to explicitly check that the file is open for + * reading, since verity files can only be opened for reading. + */ + + if (copy_from_user(&arg, uarg, sizeof(arg))) + return -EFAULT; + + if (arg.__reserved) + return -EINVAL; + + /* offset + length must not overflow. */ + if (arg.offset + arg.length < arg.offset) + return -EINVAL; + + /* Ensure that the return value will fit in INT_MAX. */ + length = min_t(u64, arg.length, INT_MAX); + + buf = u64_to_user_ptr(arg.buf_ptr); + + switch (arg.metadata_type) { + case FS_VERITY_METADATA_TYPE_MERKLE_TREE: + return fsverity_read_merkle_tree(inode, vi, buf, arg.offset, + length); + case FS_VERITY_METADATA_TYPE_DESCRIPTOR: + return fsverity_read_descriptor(inode, buf, arg.offset, length); + case FS_VERITY_METADATA_TYPE_SIGNATURE: + return fsverity_read_signature(inode, buf, arg.offset, length); + default: + return -EINVAL; + } +} +EXPORT_SYMBOL_GPL(fsverity_ioctl_read_metadata); diff --git a/fs/verity/signature.c b/fs/verity/signature.c index 012468eda2a7..143a530a8008 100644 --- a/fs/verity/signature.c +++ b/fs/verity/signature.c @@ -29,21 +29,19 @@ static struct key *fsverity_keyring; /** * fsverity_verify_signature() - check a verity file's signature * @vi: the file's fsverity_info - * @desc: the file's fsverity_descriptor - * @desc_size: size of @desc + * @signature: the file's built-in signature + * @sig_size: size of signature in bytes, or 0 if no signature * - * If the file's fs-verity descriptor includes a signature of the file digest, - * verify it against the certificates in the fs-verity keyring. + * If the file includes a signature of its fs-verity file digest, verify it + * against the certificates in the fs-verity keyring. * * Return: 0 on success (signature valid or not required); -errno on failure */ int fsverity_verify_signature(const struct fsverity_info *vi, - const struct fsverity_descriptor *desc, - size_t desc_size) + const u8 *signature, size_t sig_size) { const struct inode *inode = vi->inode; const struct fsverity_hash_alg *hash_alg = vi->tree_params.hash_alg; - const u32 sig_size = le32_to_cpu(desc->sig_size); struct fsverity_formatted_digest *d; int err; @@ -56,11 +54,6 @@ int fsverity_verify_signature(const struct fsverity_info *vi, return 0; } - if (sig_size > desc_size - sizeof(*desc)) { - fsverity_err(inode, "Signature overflows verity descriptor"); - return -EBADMSG; - } - d = kzalloc(sizeof(*d) + hash_alg->digest_size, GFP_KERNEL); if (!d) return -ENOMEM; @@ -70,8 +63,7 @@ int fsverity_verify_signature(const struct fsverity_info *vi, memcpy(d->digest, vi->file_digest, hash_alg->digest_size); err = verify_pkcs7_signature(d, sizeof(*d) + hash_alg->digest_size, - desc->signature, sig_size, - fsverity_keyring, + signature, sig_size, fsverity_keyring, VERIFYING_UNSPECIFIED_SIGNATURE, NULL, NULL); kfree(d); diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index 7cb9f064ac64..0c623d3c1036 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -2474,6 +2474,47 @@ xfs_defer_agfl_block( xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_AGFL_FREE, &new->xefi_list); } +#ifdef DEBUG +/* + * Check if an AGF has a free extent record whose length is equal to + * args->minlen. + */ +STATIC int +xfs_exact_minlen_extent_available( + struct xfs_alloc_arg *args, + struct xfs_buf *agbp, + int *stat) +{ + struct xfs_btree_cur *cnt_cur; + xfs_agblock_t fbno; + xfs_extlen_t flen; + int error = 0; + + cnt_cur = xfs_allocbt_init_cursor(args->mp, args->tp, agbp, + args->agno, XFS_BTNUM_CNT); + error = xfs_alloc_lookup_ge(cnt_cur, 0, args->minlen, stat); + if (error) + goto out; + + if (*stat == 0) { + error = -EFSCORRUPTED; + goto out; + } + + error = xfs_alloc_get_rec(cnt_cur, &fbno, &flen, stat); + if (error) + goto out; + + if (*stat == 1 && flen != args->minlen) + *stat = 0; + +out: + xfs_btree_del_cursor(cnt_cur, error); + + return error; +} +#endif + /* * Decide whether to use this allocation group for this allocation. * If so, fix up the btree freelist's size. @@ -2545,6 +2586,15 @@ xfs_alloc_fix_freelist( if (!xfs_alloc_space_available(args, need, flags)) goto out_agbp_relse; +#ifdef DEBUG + if (args->alloc_minlen_only) { + int stat; + + error = xfs_exact_minlen_extent_available(args, agbp, &stat); + if (error || !stat) + goto out_agbp_relse; + } +#endif /* * Make the freelist shorter if it's too long. * diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h index 6c22b12176b8..a4427c5775c2 100644 --- a/fs/xfs/libxfs/xfs_alloc.h +++ b/fs/xfs/libxfs/xfs_alloc.h @@ -75,6 +75,9 @@ typedef struct xfs_alloc_arg { char wasfromfl; /* set if allocation is from freelist */ struct xfs_owner_info oinfo; /* owner of blocks being allocated */ enum xfs_ag_resv_type resv; /* block reservation to use */ +#ifdef DEBUG + bool alloc_minlen_only; /* allocate exact minlen extent */ +#endif } xfs_alloc_arg_t; /* diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c index fd8e6418a0d3..472b3039eabb 100644 --- a/fs/xfs/libxfs/xfs_attr.c +++ b/fs/xfs/libxfs/xfs_attr.c @@ -396,6 +396,7 @@ xfs_attr_set( struct xfs_trans_res tres; bool rsvd = (args->attr_filter & XFS_ATTR_ROOT); int error, local; + int rmt_blks = 0; unsigned int total; if (XFS_FORCED_SHUTDOWN(dp->i_mount)) @@ -442,34 +443,33 @@ xfs_attr_set( tres.tr_logcount = XFS_ATTRSET_LOG_COUNT; tres.tr_logflags = XFS_TRANS_PERM_LOG_RES; total = args->total; + + if (!local) + rmt_blks = xfs_attr3_rmt_blocks(mp, args->valuelen); } else { XFS_STATS_INC(mp, xs_attr_remove); tres = M_RES(mp)->tr_attrrm; total = XFS_ATTRRM_SPACE_RES(mp); + rmt_blks = xfs_attr3_rmt_blocks(mp, XFS_XATTR_SIZE_MAX); } /* * Root fork attributes can use reserved data blocks for this * operation if necessary */ - error = xfs_trans_alloc(mp, &tres, total, 0, - rsvd ? XFS_TRANS_RESERVE : 0, &args->trans); + error = xfs_trans_alloc_inode(dp, &tres, total, 0, rsvd, &args->trans); if (error) return error; - xfs_ilock(dp, XFS_ILOCK_EXCL); - xfs_trans_ijoin(args->trans, dp, 0); - if (args->value) { - unsigned int quota_flags = XFS_QMOPT_RES_REGBLKS; - - if (rsvd) - quota_flags |= XFS_QMOPT_FORCE_RES; - error = xfs_trans_reserve_quota_nblks(args->trans, dp, - args->total, 0, quota_flags); + if (args->value || xfs_inode_hasattr(dp)) { + error = xfs_iext_count_may_overflow(dp, XFS_ATTR_FORK, + XFS_IEXT_ATTR_MANIP_CNT(rmt_blks)); if (error) goto out_trans_cancel; + } + if (args->value) { error = xfs_has_attr(args); if (error == -EEXIST && (args->attr_flags & XATTR_CREATE)) goto out_trans_cancel; diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index bc446418e227..e0905ad171f0 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -1079,21 +1079,13 @@ xfs_bmap_add_attrfork( blks = XFS_ADDAFORK_SPACE_RES(mp); - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_addafork, blks, 0, - rsvd ? XFS_TRANS_RESERVE : 0, &tp); + error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_addafork, blks, 0, + rsvd, &tp); if (error) return error; - - xfs_ilock(ip, XFS_ILOCK_EXCL); - error = xfs_trans_reserve_quota_nblks(tp, ip, blks, 0, rsvd ? - XFS_QMOPT_RES_REGBLKS | XFS_QMOPT_FORCE_RES : - XFS_QMOPT_RES_REGBLKS); - if (error) - goto trans_cancel; if (XFS_IFORK_Q(ip)) goto trans_cancel; - xfs_trans_ijoin(tp, ip, 0); xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); error = xfs_bmap_set_attrforkoff(ip, size, &version); if (error) @@ -3463,34 +3455,16 @@ xfs_bmap_btalloc_accounting( args->len); } -STATIC int -xfs_bmap_btalloc( - struct xfs_bmalloca *ap) /* bmap alloc argument struct */ +static int +xfs_bmap_compute_alignments( + struct xfs_bmalloca *ap, + struct xfs_alloc_arg *args) { - xfs_mount_t *mp; /* mount point structure */ - xfs_alloctype_t atype = 0; /* type for allocation routines */ - xfs_extlen_t align = 0; /* minimum allocation alignment */ - xfs_agnumber_t fb_agno; /* ag number of ap->firstblock */ - xfs_agnumber_t ag; - xfs_alloc_arg_t args; - xfs_fileoff_t orig_offset; - xfs_extlen_t orig_length; - xfs_extlen_t blen; - xfs_extlen_t nextminlen = 0; - int nullfb; /* true if ap->firstblock isn't set */ - int isaligned; - int tryagain; - int error; - int stripe_align; - - ASSERT(ap->length); - orig_offset = ap->offset; - orig_length = ap->length; - - mp = ap->ip->i_mount; + struct xfs_mount *mp = args->mp; + xfs_extlen_t align = 0; /* minimum allocation alignment */ + int stripe_align = 0; /* stripe alignment for allocation is determined by mount parameters */ - stripe_align = 0; if (mp->m_swidth && (mp->m_flags & XFS_MOUNT_SWALLOC)) stripe_align = mp->m_swidth; else if (mp->m_dalign) @@ -3501,13 +3475,171 @@ xfs_bmap_btalloc( else if (ap->datatype & XFS_ALLOC_USERDATA) align = xfs_get_extsz_hint(ap->ip); if (align) { - error = xfs_bmap_extsize_align(mp, &ap->got, &ap->prev, - align, 0, ap->eof, 0, ap->conv, - &ap->offset, &ap->length); - ASSERT(!error); + if (xfs_bmap_extsize_align(mp, &ap->got, &ap->prev, align, 0, + ap->eof, 0, ap->conv, &ap->offset, + &ap->length)) + ASSERT(0); ASSERT(ap->length); } + /* apply extent size hints if obtained earlier */ + if (align) { + args->prod = align; + div_u64_rem(ap->offset, args->prod, &args->mod); + if (args->mod) + args->mod = args->prod - args->mod; + } else if (mp->m_sb.sb_blocksize >= PAGE_SIZE) { + args->prod = 1; + args->mod = 0; + } else { + args->prod = PAGE_SIZE >> mp->m_sb.sb_blocklog; + div_u64_rem(ap->offset, args->prod, &args->mod); + if (args->mod) + args->mod = args->prod - args->mod; + } + + return stripe_align; +} + +static void +xfs_bmap_process_allocated_extent( + struct xfs_bmalloca *ap, + struct xfs_alloc_arg *args, + xfs_fileoff_t orig_offset, + xfs_extlen_t orig_length) +{ + int nullfb; + + nullfb = ap->tp->t_firstblock == NULLFSBLOCK; + + /* + * check the allocation happened at the same or higher AG than + * the first block that was allocated. + */ + ASSERT(nullfb || + XFS_FSB_TO_AGNO(args->mp, ap->tp->t_firstblock) <= + XFS_FSB_TO_AGNO(args->mp, args->fsbno)); + + ap->blkno = args->fsbno; + if (nullfb) + ap->tp->t_firstblock = args->fsbno; + ap->length = args->len; + /* + * If the extent size hint is active, we tried to round the + * caller's allocation request offset down to extsz and the + * length up to another extsz boundary. If we found a free + * extent we mapped it in starting at this new offset. If the + * newly mapped space isn't long enough to cover any of the + * range of offsets that was originally requested, move the + * mapping up so that we can fill as much of the caller's + * original request as possible. Free space is apparently + * very fragmented so we're unlikely to be able to satisfy the + * hints anyway. + */ + if (ap->length <= orig_length) + ap->offset = orig_offset; + else if (ap->offset + ap->length < orig_offset + orig_length) + ap->offset = orig_offset + orig_length - ap->length; + xfs_bmap_btalloc_accounting(ap, args); +} + +#ifdef DEBUG +static int +xfs_bmap_exact_minlen_extent_alloc( + struct xfs_bmalloca *ap) +{ + struct xfs_mount *mp = ap->ip->i_mount; + struct xfs_alloc_arg args = { .tp = ap->tp, .mp = mp }; + xfs_fileoff_t orig_offset; + xfs_extlen_t orig_length; + int error; + + ASSERT(ap->length); + + if (ap->minlen != 1) { + ap->blkno = NULLFSBLOCK; + ap->length = 0; + return 0; + } + + orig_offset = ap->offset; + orig_length = ap->length; + + args.alloc_minlen_only = 1; + + xfs_bmap_compute_alignments(ap, &args); + + if (ap->tp->t_firstblock == NULLFSBLOCK) { + /* + * Unlike the longest extent available in an AG, we don't track + * the length of an AG's shortest extent. + * XFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENT is a debug only knob and + * hence we can afford to start traversing from the 0th AG since + * we need not be concerned about a drop in performance in + * "debug only" code paths. + */ + ap->blkno = XFS_AGB_TO_FSB(mp, 0, 0); + } else { + ap->blkno = ap->tp->t_firstblock; + } + + args.fsbno = ap->blkno; + args.oinfo = XFS_RMAP_OINFO_SKIP_UPDATE; + args.type = XFS_ALLOCTYPE_FIRST_AG; + args.total = args.minlen = args.maxlen = ap->minlen; + + args.alignment = 1; + args.minalignslop = 0; + + args.minleft = ap->minleft; + args.wasdel = ap->wasdel; + args.resv = XFS_AG_RESV_NONE; + args.datatype = ap->datatype; + + error = xfs_alloc_vextent(&args); + if (error) + return error; + + if (args.fsbno != NULLFSBLOCK) { + xfs_bmap_process_allocated_extent(ap, &args, orig_offset, + orig_length); + } else { + ap->blkno = NULLFSBLOCK; + ap->length = 0; + } + + return 0; +} +#else + +#define xfs_bmap_exact_minlen_extent_alloc(bma) (-EFSCORRUPTED) + +#endif + +STATIC int +xfs_bmap_btalloc( + struct xfs_bmalloca *ap) +{ + struct xfs_mount *mp = ap->ip->i_mount; + struct xfs_alloc_arg args = { .tp = ap->tp, .mp = mp }; + xfs_alloctype_t atype = 0; + xfs_agnumber_t fb_agno; /* ag number of ap->firstblock */ + xfs_agnumber_t ag; + xfs_fileoff_t orig_offset; + xfs_extlen_t orig_length; + xfs_extlen_t blen; + xfs_extlen_t nextminlen = 0; + int nullfb; /* true if ap->firstblock isn't set */ + int isaligned; + int tryagain; + int error; + int stripe_align; + + ASSERT(ap->length); + orig_offset = ap->offset; + orig_length = ap->length; + + stripe_align = xfs_bmap_compute_alignments(ap, &args); nullfb = ap->tp->t_firstblock == NULLFSBLOCK; fb_agno = nullfb ? NULLAGNUMBER : XFS_FSB_TO_AGNO(mp, @@ -3538,9 +3670,6 @@ xfs_bmap_btalloc( * Normal allocation, done through xfs_alloc_vextent. */ tryagain = isaligned = 0; - memset(&args, 0, sizeof(args)); - args.tp = ap->tp; - args.mp = mp; args.fsbno = ap->blkno; args.oinfo = XFS_RMAP_OINFO_SKIP_UPDATE; @@ -3571,21 +3700,7 @@ xfs_bmap_btalloc( args.total = ap->total; args.minlen = ap->minlen; } - /* apply extent size hints if obtained earlier */ - if (align) { - args.prod = align; - div_u64_rem(ap->offset, args.prod, &args.mod); - if (args.mod) - args.mod = args.prod - args.mod; - } else if (mp->m_sb.sb_blocksize >= PAGE_SIZE) { - args.prod = 1; - args.mod = 0; - } else { - args.prod = PAGE_SIZE >> mp->m_sb.sb_blocklog; - div_u64_rem(ap->offset, args.prod, &args.mod); - if (args.mod) - args.mod = args.prod - args.mod; - } + /* * If we are not low on available data blocks, and the underlying * logical volume manager is a stripe, and the file offset is zero then @@ -3687,37 +3802,10 @@ xfs_bmap_btalloc( return error; ap->tp->t_flags |= XFS_TRANS_LOWMODE; } + if (args.fsbno != NULLFSBLOCK) { - /* - * check the allocation happened at the same or higher AG than - * the first block that was allocated. - */ - ASSERT(ap->tp->t_firstblock == NULLFSBLOCK || - XFS_FSB_TO_AGNO(mp, ap->tp->t_firstblock) <= - XFS_FSB_TO_AGNO(mp, args.fsbno)); - - ap->blkno = args.fsbno; - if (ap->tp->t_firstblock == NULLFSBLOCK) - ap->tp->t_firstblock = args.fsbno; - ASSERT(nullfb || fb_agno <= args.agno); - ap->length = args.len; - /* - * If the extent size hint is active, we tried to round the - * caller's allocation request offset down to extsz and the - * length up to another extsz boundary. If we found a free - * extent we mapped it in starting at this new offset. If the - * newly mapped space isn't long enough to cover any of the - * range of offsets that was originally requested, move the - * mapping up so that we can fill as much of the caller's - * original request as possible. Free space is apparently - * very fragmented so we're unlikely to be able to satisfy the - * hints anyway. - */ - if (ap->length <= orig_length) - ap->offset = orig_offset; - else if (ap->offset + ap->length < orig_offset + orig_length) - ap->offset = orig_offset + orig_length - ap->length; - xfs_bmap_btalloc_accounting(ap, &args); + xfs_bmap_process_allocated_extent(ap, &args, orig_offset, + orig_length); } else { ap->blkno = NULLFSBLOCK; ap->length = 0; @@ -4001,8 +4089,7 @@ xfs_bmapi_reserve_delalloc( * blocks. This number gets adjusted later. We return if we haven't * allocated blocks already inside this loop. */ - error = xfs_trans_reserve_quota_nblks(NULL, ip, (long)alen, 0, - XFS_QMOPT_RES_REGBLKS); + error = xfs_quota_reserve_blkres(ip, alen); if (error) return error; @@ -4048,8 +4135,7 @@ out_unreserve_blocks: xfs_mod_fdblocks(mp, alen, false); out_unreserve_quota: if (XFS_IS_QUOTA_ON(mp)) - xfs_trans_unreserve_quota_nblks(NULL, ip, (long)alen, 0, - XFS_QMOPT_RES_REGBLKS); + xfs_quota_unreserve_blkres(ip, alen); return error; } @@ -4083,6 +4169,10 @@ xfs_bmap_alloc_userdata( return xfs_bmap_rtalloc(bma); } + if (unlikely(XFS_TEST_ERROR(false, mp, + XFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENT))) + return xfs_bmap_exact_minlen_extent_alloc(bma); + return xfs_bmap_btalloc(bma); } @@ -4119,10 +4209,15 @@ xfs_bmapi_allocate( else bma->minlen = 1; - if (bma->flags & XFS_BMAPI_METADATA) - error = xfs_bmap_btalloc(bma); - else + if (bma->flags & XFS_BMAPI_METADATA) { + if (unlikely(XFS_TEST_ERROR(false, mp, + XFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENT))) + error = xfs_bmap_exact_minlen_extent_alloc(bma); + else + error = xfs_bmap_btalloc(bma); + } else { error = xfs_bmap_alloc_userdata(bma); + } if (error || bma->blkno == NULLFSBLOCK) return error; @@ -4527,6 +4622,12 @@ xfs_bmapi_convert_delalloc( return error; xfs_ilock(ip, XFS_ILOCK_EXCL); + + error = xfs_iext_count_may_overflow(ip, whichfork, + XFS_IEXT_ADD_NOSPLIT_CNT); + if (error) + goto out_trans_cancel; + xfs_trans_ijoin(tp, ip, 0); if (!xfs_iext_lookup_extent(ip, ifp, offset_fsb, &bma.icur, &bma.got) || @@ -4826,9 +4927,8 @@ xfs_bmap_del_extent_delay( * sb counters as we might have to borrow some blocks for the * indirect block accounting. */ - error = xfs_trans_reserve_quota_nblks(NULL, ip, - -((long)del->br_blockcount), 0, - isrt ? XFS_QMOPT_RES_RTBLKS : XFS_QMOPT_RES_REGBLKS); + ASSERT(!isrt); + error = xfs_quota_unreserve_blkres(ip, del->br_blockcount); if (error) return error; ip->i_delayed_blks -= del->br_blockcount; @@ -5145,6 +5245,27 @@ xfs_bmap_del_extent_real( /* * Deleting the middle of the extent. */ + + /* + * For directories, -ENOSPC is returned since a directory entry + * remove operation must not fail due to low extent count + * availability. -ENOSPC will be handled by higher layers of XFS + * by letting the corresponding empty Data/Free blocks to linger + * until a future remove operation. Dabtree blocks would be + * swapped with the last block in the leaf space and then the + * new last block will be unmapped. + * + * The above logic also applies to the source directory entry of + * a rename operation. + */ + error = xfs_iext_count_may_overflow(ip, whichfork, 1); + if (error) { + ASSERT(S_ISDIR(VFS_I(ip)->i_mode) && + whichfork == XFS_DATA_FORK); + error = -ENOSPC; + goto done; + } + old = got; got.br_blockcount = del->br_startoff - got.br_startoff; diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c index c4d7a9241dc3..b56ff451adce 100644 --- a/fs/xfs/libxfs/xfs_btree.c +++ b/fs/xfs/libxfs/xfs_btree.c @@ -353,20 +353,17 @@ xfs_btree_free_block( */ void xfs_btree_del_cursor( - xfs_btree_cur_t *cur, /* btree cursor */ - int error) /* del because of error */ + struct xfs_btree_cur *cur, /* btree cursor */ + int error) /* del because of error */ { - int i; /* btree level */ + int i; /* btree level */ /* - * Clear the buffer pointers, and release the buffers. - * If we're doing this in the face of an error, we - * need to make sure to inspect all of the entries - * in the bc_bufs array for buffers to be unlocked. - * This is because some of the btree code works from - * level n down to 0, and if we get an error along - * the way we won't have initialized all the entries - * down to 0. + * Clear the buffer pointers and release the buffers. If we're doing + * this because of an error, inspect all of the entries in the bc_bufs + * array for buffers to be unlocked. This is because some of the btree + * code works from level n down to 0, and if we get an error along the + * way we won't have initialized all the entries down to 0. */ for (i = 0; i < cur->bc_nlevels; i++) { if (cur->bc_bufs[i]) @@ -374,17 +371,11 @@ xfs_btree_del_cursor( else if (!error) break; } - /* - * Can't free a bmap cursor without having dealt with the - * allocated indirect blocks' accounting. - */ - ASSERT(cur->bc_btnum != XFS_BTNUM_BMAP || - cur->bc_ino.allocated == 0); - /* - * Free the cursor. - */ + + ASSERT(cur->bc_btnum != XFS_BTNUM_BMAP || cur->bc_ino.allocated == 0 || + XFS_FORCED_SHUTDOWN(cur->bc_mp)); if (unlikely(cur->bc_flags & XFS_BTREE_STAGING)) - kmem_free((void *)cur->bc_ops); + kmem_free(cur->bc_ops); kmem_cache_free(xfs_btree_cur_zone, cur); } diff --git a/fs/xfs/libxfs/xfs_dir2.h b/fs/xfs/libxfs/xfs_dir2.h index e55378640b05..d03e6098ded9 100644 --- a/fs/xfs/libxfs/xfs_dir2.h +++ b/fs/xfs/libxfs/xfs_dir2.h @@ -47,8 +47,6 @@ extern int xfs_dir_lookup(struct xfs_trans *tp, struct xfs_inode *dp, extern int xfs_dir_removename(struct xfs_trans *tp, struct xfs_inode *dp, struct xfs_name *name, xfs_ino_t ino, xfs_extlen_t tot); -extern bool xfs_dir2_sf_replace_needblock(struct xfs_inode *dp, - xfs_ino_t inum); extern int xfs_dir_replace(struct xfs_trans *tp, struct xfs_inode *dp, struct xfs_name *name, xfs_ino_t inum, xfs_extlen_t tot); diff --git a/fs/xfs/libxfs/xfs_dir2_sf.c b/fs/xfs/libxfs/xfs_dir2_sf.c index 2463b5d73447..8c4f76bba88b 100644 --- a/fs/xfs/libxfs/xfs_dir2_sf.c +++ b/fs/xfs/libxfs/xfs_dir2_sf.c @@ -1018,7 +1018,7 @@ xfs_dir2_sf_removename( /* * Check whether the sf dir replace operation need more blocks. */ -bool +static bool xfs_dir2_sf_replace_needblock( struct xfs_inode *dp, xfs_ino_t inum) diff --git a/fs/xfs/libxfs/xfs_errortag.h b/fs/xfs/libxfs/xfs_errortag.h index 53b305dea381..6ca9084b6934 100644 --- a/fs/xfs/libxfs/xfs_errortag.h +++ b/fs/xfs/libxfs/xfs_errortag.h @@ -56,7 +56,9 @@ #define XFS_ERRTAG_FORCE_SUMMARY_RECALC 33 #define XFS_ERRTAG_IUNLINK_FALLBACK 34 #define XFS_ERRTAG_BUF_IOERROR 35 -#define XFS_ERRTAG_MAX 36 +#define XFS_ERRTAG_REDUCE_MAX_IEXTENTS 36 +#define XFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENT 37 +#define XFS_ERRTAG_MAX 38 /* * Random factors for above tags, 1 means always, 2 means 1/2 time, etc. @@ -97,5 +99,7 @@ #define XFS_RANDOM_FORCE_SUMMARY_RECALC 1 #define XFS_RANDOM_IUNLINK_FALLBACK (XFS_RANDOM_DEFAULT/10) #define XFS_RANDOM_BUF_IOERROR XFS_RANDOM_DEFAULT +#define XFS_RANDOM_REDUCE_MAX_IEXTENTS 1 +#define XFS_RANDOM_BMAP_ALLOC_MINLEN_EXTENT 1 #endif /* __XFS_ERRORTAG_H_ */ diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h index 2a2e3cfd94f0..6fad140d4c8e 100644 --- a/fs/xfs/libxfs/xfs_fs.h +++ b/fs/xfs/libxfs/xfs_fs.h @@ -250,6 +250,7 @@ typedef struct xfs_fsop_resblks { #define XFS_FSOP_GEOM_FLAGS_RMAPBT (1 << 19) /* reverse mapping btree */ #define XFS_FSOP_GEOM_FLAGS_REFLINK (1 << 20) /* files can share blocks */ #define XFS_FSOP_GEOM_FLAGS_BIGTIME (1 << 21) /* 64-bit nsec timestamps */ +#define XFS_FSOP_GEOM_FLAGS_INOBTCNT (1 << 22) /* inobt btree counter */ /* * Minimum and maximum sizes need for growth checks. diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c index 7575de5cecb1..e080d7e07643 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.c +++ b/fs/xfs/libxfs/xfs_inode_fork.c @@ -23,6 +23,8 @@ #include "xfs_da_btree.h" #include "xfs_dir2_priv.h" #include "xfs_attr_leaf.h" +#include "xfs_types.h" +#include "xfs_errortag.h" kmem_zone_t *xfs_ifork_zone; @@ -728,3 +730,28 @@ xfs_ifork_verify_local_attr( return 0; } + +int +xfs_iext_count_may_overflow( + struct xfs_inode *ip, + int whichfork, + int nr_to_add) +{ + struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); + uint64_t max_exts; + uint64_t nr_exts; + + if (whichfork == XFS_COW_FORK) + return 0; + + max_exts = (whichfork == XFS_ATTR_FORK) ? MAXAEXTNUM : MAXEXTNUM; + + if (XFS_TEST_ERROR(false, ip->i_mount, XFS_ERRTAG_REDUCE_MAX_IEXTENTS)) + max_exts = 10; + + nr_exts = ifp->if_nextents + nr_to_add; + if (nr_exts < ifp->if_nextents || nr_exts > max_exts) + return -EFBIG; + + return 0; +} diff --git a/fs/xfs/libxfs/xfs_inode_fork.h b/fs/xfs/libxfs/xfs_inode_fork.h index a4953e95c4f3..9e2137cd7372 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.h +++ b/fs/xfs/libxfs/xfs_inode_fork.h @@ -35,6 +35,67 @@ struct xfs_ifork { #define XFS_IFBROOT 0x04 /* i_broot points to the bmap b-tree root */ /* + * Worst-case increase in the fork extent count when we're adding a single + * extent to a fork and there's no possibility of splitting an existing mapping. + */ +#define XFS_IEXT_ADD_NOSPLIT_CNT (1) + +/* + * Punching out an extent from the middle of an existing extent can cause the + * extent count to increase by 1. + * i.e. | Old extent | Hole | Old extent | + */ +#define XFS_IEXT_PUNCH_HOLE_CNT (1) + +/* + * Directory entry addition can cause the following, + * 1. Data block can be added/removed. + * A new extent can cause extent count to increase by 1. + * 2. Free disk block can be added/removed. + * Same behaviour as described above for Data block. + * 3. Dabtree blocks. + * XFS_DA_NODE_MAXDEPTH blocks can be added. Each of these can be new + * extents. Hence extent count can increase by XFS_DA_NODE_MAXDEPTH. + */ +#define XFS_IEXT_DIR_MANIP_CNT(mp) \ + ((XFS_DA_NODE_MAXDEPTH + 1 + 1) * (mp)->m_dir_geo->fsbcount) + +/* + * Adding/removing an xattr can cause XFS_DA_NODE_MAXDEPTH extents to + * be added. One extra extent for dabtree in case a local attr is + * large enough to cause a double split. It can also cause extent + * count to increase proportional to the size of a remote xattr's + * value. + */ +#define XFS_IEXT_ATTR_MANIP_CNT(rmt_blks) \ + (XFS_DA_NODE_MAXDEPTH + max(1, rmt_blks)) + +/* + * A write to a sub-interval of an existing unwritten extent causes the original + * extent to be split into 3 extents + * i.e. | Unwritten | Real | Unwritten | + * Hence extent count can increase by 2. + */ +#define XFS_IEXT_WRITE_UNWRITTEN_CNT (2) + + +/* + * Moving an extent to data fork can cause a sub-interval of an existing extent + * to be unmapped. This will increase extent count by 1. Mapping in the new + * extent can increase the extent count by 1 again i.e. + * | Old extent | New extent | Old extent | + * Hence number of extents increases by 2. + */ +#define XFS_IEXT_REFLINK_END_COW_CNT (2) + +/* + * Removing an initial range of source/donor file's extent and adding a new + * extent (from donor/source file) in its place will cause extent count to + * increase by 1. + */ +#define XFS_IEXT_SWAP_RMAP_CNT (1) + +/* * Fork handling. */ @@ -172,5 +233,7 @@ extern void xfs_ifork_init_cow(struct xfs_inode *ip); int xfs_ifork_verify_local_data(struct xfs_inode *ip); int xfs_ifork_verify_local_attr(struct xfs_inode *ip); +int xfs_iext_count_may_overflow(struct xfs_inode *ip, int whichfork, + int nr_to_add); #endif /* __XFS_INODE_FORK_H__ */ diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c index bbda117e5d85..60e6d255e5e2 100644 --- a/fs/xfs/libxfs/xfs_sb.c +++ b/fs/xfs/libxfs/xfs_sb.c @@ -1138,6 +1138,8 @@ xfs_fs_geometry( geo->flags |= XFS_FSOP_GEOM_FLAGS_REFLINK; if (xfs_sb_version_hasbigtime(sbp)) geo->flags |= XFS_FSOP_GEOM_FLAGS_BIGTIME; + if (xfs_sb_version_hasinobtcounts(sbp)) + geo->flags |= XFS_FSOP_GEOM_FLAGS_INOBTCNT; if (xfs_sb_version_hassector(sbp)) geo->logsectsize = sbp->sb_logsectsize; else diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c index 8ea6d4aa3f55..53456f3de881 100644 --- a/fs/xfs/scrub/common.c +++ b/fs/xfs/scrub/common.c @@ -888,7 +888,7 @@ xchk_stop_reaping( struct xfs_scrub *sc) { sc->flags |= XCHK_REAPING_DISABLED; - xfs_stop_block_reaping(sc->mp); + xfs_blockgc_stop(sc->mp); } /* Restart background reaping of resources. */ @@ -896,6 +896,6 @@ void xchk_start_reaping( struct xfs_scrub *sc) { - xfs_start_block_reaping(sc->mp); + xfs_blockgc_start(sc->mp); sc->flags &= ~XCHK_REAPING_DISABLED; } diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c index 93e4d8ae6e92..2344757ede63 100644 --- a/fs/xfs/xfs_bmap_item.c +++ b/fs/xfs/xfs_bmap_item.c @@ -471,6 +471,7 @@ xfs_bui_item_recover( xfs_exntst_t state; unsigned int bui_type; int whichfork; + int iext_delta; int error = 0; if (!xfs_bui_validate(mp, buip)) { @@ -508,6 +509,15 @@ xfs_bui_item_recover( xfs_ilock(ip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, ip, 0); + if (bui_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); + 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, diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 7371a7f7c652..e7d68318e6a5 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -727,11 +727,9 @@ xfs_alloc_file_space( xfs_fileoff_t startoffset_fsb; xfs_fileoff_t endoffset_fsb; int nimaps; - int quota_flag; int rt; xfs_trans_t *tp; xfs_bmbt_irec_t imaps[1], *imapp; - uint qblocks, resblks, resrtextents; int error; trace_xfs_alloc_file_space(ip); @@ -761,6 +759,7 @@ xfs_alloc_file_space( */ while (allocatesize_fsb && !error) { xfs_fileoff_t s, e; + unsigned int dblocks, rblocks, resblks; /* * Determine space reservations for data/realtime. @@ -790,45 +789,31 @@ xfs_alloc_file_space( */ resblks = min_t(xfs_fileoff_t, (e - s), (MAXEXTLEN * nimaps)); if (unlikely(rt)) { - resrtextents = qblocks = resblks; - resrtextents /= mp->m_sb.sb_rextsize; - resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0); - quota_flag = XFS_QMOPT_RES_RTBLKS; + dblocks = XFS_DIOSTRAT_SPACE_RES(mp, 0); + rblocks = resblks; } else { - resrtextents = 0; - resblks = qblocks = XFS_DIOSTRAT_SPACE_RES(mp, resblks); - quota_flag = XFS_QMOPT_RES_REGBLKS; + dblocks = XFS_DIOSTRAT_SPACE_RES(mp, resblks); + rblocks = 0; } /* * Allocate and setup the transaction. */ - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, - resrtextents, 0, &tp); - - /* - * Check for running out of space - */ - if (error) { - /* - * Free the transaction structure. - */ - ASSERT(error == -ENOSPC || XFS_FORCED_SHUTDOWN(mp)); - break; - } - xfs_ilock(ip, XFS_ILOCK_EXCL); - error = xfs_trans_reserve_quota_nblks(tp, ip, qblocks, - 0, quota_flag); + error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_write, + dblocks, rblocks, false, &tp); if (error) - goto error1; + break; - xfs_trans_ijoin(tp, ip, 0); + error = xfs_iext_count_may_overflow(ip, XFS_DATA_FORK, + XFS_IEXT_ADD_NOSPLIT_CNT); + if (error) + goto error; error = xfs_bmapi_write(tp, ip, startoffset_fsb, allocatesize_fsb, alloc_type, 0, imapp, &nimaps); if (error) - goto error0; + goto error; /* * Complete the transaction @@ -851,10 +836,7 @@ xfs_alloc_file_space( return error; -error0: /* unlock inode, unreserve quota blocks, cancel trans */ - xfs_trans_unreserve_quota_nblks(tp, ip, (long)qblocks, 0, quota_flag); - -error1: /* Just cancel transaction */ +error: xfs_trans_cancel(tp); xfs_iunlock(ip, XFS_ILOCK_EXCL); return error; @@ -872,20 +854,16 @@ xfs_unmap_extent( uint resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0); int error; - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0, &tp); - if (error) { - ASSERT(error == -ENOSPC || XFS_FORCED_SHUTDOWN(mp)); + error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_write, resblks, 0, + false, &tp); + if (error) return error; - } - xfs_ilock(ip, XFS_ILOCK_EXCL); - error = xfs_trans_reserve_quota(tp, mp, ip->i_udquot, ip->i_gdquot, - ip->i_pdquot, resblks, 0, XFS_QMOPT_RES_REGBLKS); + error = xfs_iext_count_may_overflow(ip, XFS_DATA_FORK, + XFS_IEXT_PUNCH_HOLE_CNT); if (error) goto out_trans_cancel; - xfs_trans_ijoin(tp, ip, 0); - error = xfs_bunmapi(tp, ip, startoffset_fsb, len_fsb, 0, 2, done); if (error) goto out_trans_cancel; @@ -1163,6 +1141,11 @@ xfs_insert_file_space( xfs_ilock(ip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, ip, 0); + error = xfs_iext_count_may_overflow(ip, XFS_DATA_FORK, + XFS_IEXT_PUNCH_HOLE_CNT); + if (error) + goto out_trans_cancel; + /* * The extent shifting code works on extent granularity. So, if stop_fsb * is not the starting block of extent, we need to split the extent at @@ -1384,6 +1367,22 @@ xfs_swap_extent_rmap( irec.br_blockcount); trace_xfs_swap_extent_rmap_remap_piece(tip, &uirec); + if (xfs_bmap_is_real_extent(&uirec)) { + error = xfs_iext_count_may_overflow(ip, + XFS_DATA_FORK, + XFS_IEXT_SWAP_RMAP_CNT); + if (error) + goto out; + } + + if (xfs_bmap_is_real_extent(&irec)) { + error = xfs_iext_count_may_overflow(tip, + XFS_DATA_FORK, + XFS_IEXT_SWAP_RMAP_CNT); + if (error) + goto out; + } + /* Remove the mapping from the donor file. */ xfs_bmap_unmap_extent(tp, tip, &uirec); diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index f8400bbd6473..f6e5235df7c9 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -43,7 +43,7 @@ static kmem_zone_t *xfs_buf_zone; * pag_buf_lock * lru_lock * - * xfs_buftarg_wait_rele + * xfs_buftarg_drain_rele * lru_lock * b_lock (trylock due to inversion) * @@ -88,7 +88,7 @@ xfs_buf_vmap_len( * because the corresponding decrement is deferred to buffer release. Buffers * can undergo I/O multiple times in a hold-release cycle and per buffer I/O * tracking adds unnecessary overhead. This is used for sychronization purposes - * with unmount (see xfs_wait_buftarg()), so all we really need is a count of + * with unmount (see xfs_buftarg_drain()), so all we really need is a count of * in-flight buffers. * * Buffers that are never released (e.g., superblock, iclog buffers) must set @@ -1786,7 +1786,7 @@ __xfs_buf_mark_corrupt( * while freeing all the buffers only held by the LRU. */ static enum lru_status -xfs_buftarg_wait_rele( +xfs_buftarg_drain_rele( struct list_head *item, struct list_lru_one *lru, spinlock_t *lru_lock, @@ -1798,7 +1798,7 @@ xfs_buftarg_wait_rele( if (atomic_read(&bp->b_hold) > 1) { /* need to wait, so skip it this pass */ - trace_xfs_buf_wait_buftarg(bp, _RET_IP_); + trace_xfs_buf_drain_buftarg(bp, _RET_IP_); return LRU_SKIP; } if (!spin_trylock(&bp->b_lock)) @@ -1815,14 +1815,13 @@ xfs_buftarg_wait_rele( return LRU_REMOVED; } +/* + * Wait for outstanding I/O on the buftarg to complete. + */ void -xfs_wait_buftarg( +xfs_buftarg_wait( struct xfs_buftarg *btp) { - LIST_HEAD(dispose); - int loop = 0; - bool write_fail = false; - /* * First wait on the buftarg I/O count for all in-flight buffers to be * released. This is critical as new buffers do not make the LRU until @@ -1838,10 +1837,21 @@ xfs_wait_buftarg( while (percpu_counter_sum(&btp->bt_io_count)) delay(100); flush_workqueue(btp->bt_mount->m_buf_workqueue); +} + +void +xfs_buftarg_drain( + struct xfs_buftarg *btp) +{ + LIST_HEAD(dispose); + int loop = 0; + bool write_fail = false; + + xfs_buftarg_wait(btp); /* loop until there is nothing left on the lru list. */ while (list_lru_count(&btp->bt_lru)) { - list_lru_walk(&btp->bt_lru, xfs_buftarg_wait_rele, + list_lru_walk(&btp->bt_lru, xfs_buftarg_drain_rele, &dispose, LONG_MAX); while (!list_empty(&dispose)) { diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index 5d91a31298a4..459ca34f26f5 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -152,7 +152,7 @@ struct xfs_buf { struct list_head b_list; struct xfs_perag *b_pag; /* contains rbtree root */ struct xfs_mount *b_mount; - xfs_buftarg_t *b_target; /* buffer target (device) */ + struct xfs_buftarg *b_target; /* buffer target (device) */ void *b_addr; /* virtual address of buffer */ struct work_struct b_ioend_work; struct completion b_iowait; /* queue for I/O waiters */ @@ -344,11 +344,12 @@ xfs_buf_update_cksum(struct xfs_buf *bp, unsigned long cksum_offset) /* * Handling of buftargs. */ -extern xfs_buftarg_t *xfs_alloc_buftarg(struct xfs_mount *, - struct block_device *, struct dax_device *); +extern struct xfs_buftarg *xfs_alloc_buftarg(struct xfs_mount *, + struct block_device *, struct dax_device *); extern void xfs_free_buftarg(struct xfs_buftarg *); -extern void xfs_wait_buftarg(xfs_buftarg_t *); -extern int xfs_setsize_buftarg(xfs_buftarg_t *, unsigned int); +extern void xfs_buftarg_wait(struct xfs_buftarg *); +extern void xfs_buftarg_drain(struct xfs_buftarg *); +extern int xfs_setsize_buftarg(struct xfs_buftarg *, unsigned int); #define xfs_getsize_buftarg(buftarg) block_size((buftarg)->bt_bdev) #define xfs_readonly_buftarg(buftarg) bdev_read_only((buftarg)->bt_bdev) diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c index 1d95ed387d66..bd8379b98374 100644 --- a/fs/xfs/xfs_dquot.c +++ b/fs/xfs/xfs_dquot.c @@ -314,8 +314,14 @@ xfs_dquot_disk_alloc( return -ESRCH; } - /* Create the block mapping. */ xfs_trans_ijoin(tp, quotip, XFS_ILOCK_EXCL); + + error = xfs_iext_count_may_overflow(quotip, XFS_DATA_FORK, + XFS_IEXT_ADD_NOSPLIT_CNT); + if (error) + return error; + + /* Create the block mapping. */ error = xfs_bmapi_write(tp, quotip, dqp->q_fileoffset, XFS_DQUOT_CLUSTER_SIZE_FSB, XFS_BMAPI_METADATA, 0, &map, &nmaps); @@ -500,6 +506,42 @@ xfs_dquot_alloc( return dqp; } +/* Check the ondisk dquot's id and type match what the incore dquot expects. */ +static bool +xfs_dquot_check_type( + struct xfs_dquot *dqp, + struct xfs_disk_dquot *ddqp) +{ + uint8_t ddqp_type; + uint8_t dqp_type; + + ddqp_type = ddqp->d_type & XFS_DQTYPE_REC_MASK; + dqp_type = xfs_dquot_type(dqp); + + if (be32_to_cpu(ddqp->d_id) != dqp->q_id) + return false; + + /* + * V5 filesystems always expect an exact type match. V4 filesystems + * expect an exact match for user dquots and for non-root group and + * project dquots. + */ + if (xfs_sb_version_hascrc(&dqp->q_mount->m_sb) || + dqp_type == XFS_DQTYPE_USER || dqp->q_id != 0) + return ddqp_type == dqp_type; + + /* + * V4 filesystems support either group or project quotas, but not both + * at the same time. The non-user quota file can be switched between + * group and project quota uses depending on the mount options, which + * means that we can encounter the other type when we try to load quota + * defaults. Quotacheck will soon reset the the entire quota file + * (including the root dquot) anyway, but don't log scary corruption + * reports to dmesg. + */ + return ddqp_type == XFS_DQTYPE_GROUP || ddqp_type == XFS_DQTYPE_PROJ; +} + /* Copy the in-core quota fields in from the on-disk buffer. */ STATIC int xfs_dquot_from_disk( @@ -512,8 +554,7 @@ xfs_dquot_from_disk( * Ensure that we got the type and ID we were looking for. * Everything else was checked by the dquot buffer verifier. */ - if ((ddqp->d_type & XFS_DQTYPE_REC_MASK) != xfs_dquot_type(dqp) || - be32_to_cpu(ddqp->d_id) != dqp->q_id) { + if (!xfs_dquot_check_type(dqp, ddqp)) { xfs_alert_tag(bp->b_mount, XFS_PTAG_VERIFIER_ERROR, "Metadata corruption detected at %pS, quota %u", __this_address, dqp->q_id); diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c index 7f6e20899473..185b4915b7bf 100644 --- a/fs/xfs/xfs_error.c +++ b/fs/xfs/xfs_error.c @@ -54,6 +54,8 @@ static unsigned int xfs_errortag_random_default[] = { XFS_RANDOM_FORCE_SUMMARY_RECALC, XFS_RANDOM_IUNLINK_FALLBACK, XFS_RANDOM_BUF_IOERROR, + XFS_RANDOM_REDUCE_MAX_IEXTENTS, + XFS_RANDOM_BMAP_ALLOC_MINLEN_EXTENT, }; struct xfs_errortag_attr { @@ -164,6 +166,8 @@ XFS_ERRORTAG_ATTR_RW(force_repair, XFS_ERRTAG_FORCE_SCRUB_REPAIR); XFS_ERRORTAG_ATTR_RW(bad_summary, XFS_ERRTAG_FORCE_SUMMARY_RECALC); XFS_ERRORTAG_ATTR_RW(iunlink_fallback, XFS_ERRTAG_IUNLINK_FALLBACK); XFS_ERRORTAG_ATTR_RW(buf_ioerror, XFS_ERRTAG_BUF_IOERROR); +XFS_ERRORTAG_ATTR_RW(reduce_max_iextents, XFS_ERRTAG_REDUCE_MAX_IEXTENTS); +XFS_ERRORTAG_ATTR_RW(bmap_alloc_minlen_extent, XFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENT); static struct attribute *xfs_errortag_attrs[] = { XFS_ERRORTAG_ATTR_LIST(noerror), @@ -202,6 +206,8 @@ static struct attribute *xfs_errortag_attrs[] = { XFS_ERRORTAG_ATTR_LIST(bad_summary), XFS_ERRORTAG_ATTR_LIST(iunlink_fallback), XFS_ERRORTAG_ATTR_LIST(buf_ioerror), + XFS_ERRORTAG_ATTR_LIST(reduce_max_iextents), + XFS_ERRORTAG_ATTR_LIST(bmap_alloc_minlen_extent), NULL, }; diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 5b0f93f73837..68ca1b40d8c7 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -118,6 +118,54 @@ xfs_dir_fsync( return xfs_log_force_inode(ip); } +static xfs_lsn_t +xfs_fsync_lsn( + struct xfs_inode *ip, + bool datasync) +{ + if (!xfs_ipincount(ip)) + return 0; + if (datasync && !(ip->i_itemp->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP)) + return 0; + return ip->i_itemp->ili_last_lsn; +} + +/* + * All metadata updates are logged, which means that we just have to flush the + * log up to the latest LSN that touched the inode. + * + * If we have concurrent fsync/fdatasync() calls, we need them to all block on + * the log force before we clear the ili_fsync_fields field. This ensures that + * we don't get a racing sync operation that does not wait for the metadata to + * hit the journal before returning. If we race with clearing ili_fsync_fields, + * then all that will happen is the log force will do nothing as the lsn will + * already be on disk. We can't race with setting ili_fsync_fields because that + * is done under XFS_ILOCK_EXCL, and that can't happen because we hold the lock + * shared until after the ili_fsync_fields is cleared. + */ +static int +xfs_fsync_flush_log( + struct xfs_inode *ip, + bool datasync, + int *log_flushed) +{ + int error = 0; + xfs_lsn_t lsn; + + xfs_ilock(ip, XFS_ILOCK_SHARED); + lsn = xfs_fsync_lsn(ip, datasync); + if (lsn) { + error = xfs_log_force_lsn(ip->i_mount, lsn, XFS_LOG_SYNC, + log_flushed); + + spin_lock(&ip->i_itemp->ili_lock); + ip->i_itemp->ili_fsync_fields = 0; + spin_unlock(&ip->i_itemp->ili_lock); + } + xfs_iunlock(ip, XFS_ILOCK_SHARED); + return error; +} + STATIC int xfs_file_fsync( struct file *file, @@ -125,13 +173,10 @@ xfs_file_fsync( loff_t end, int datasync) { - struct inode *inode = file->f_mapping->host; - struct xfs_inode *ip = XFS_I(inode); - struct xfs_inode_log_item *iip = ip->i_itemp; + struct xfs_inode *ip = XFS_I(file->f_mapping->host); struct xfs_mount *mp = ip->i_mount; int error = 0; int log_flushed = 0; - xfs_lsn_t lsn = 0; trace_xfs_file_fsync(ip); @@ -156,32 +201,13 @@ xfs_file_fsync( xfs_blkdev_issue_flush(mp->m_ddev_targp); /* - * All metadata updates are logged, which means that we just have to - * flush the log up to the latest LSN that touched the inode. If we have - * concurrent fsync/fdatasync() calls, we need them to all block on the - * log force before we clear the ili_fsync_fields field. This ensures - * that we don't get a racing sync operation that does not wait for the - * metadata to hit the journal before returning. If we race with - * clearing the ili_fsync_fields, then all that will happen is the log - * force will do nothing as the lsn will already be on disk. We can't - * race with setting ili_fsync_fields because that is done under - * XFS_ILOCK_EXCL, and that can't happen because we hold the lock shared - * until after the ili_fsync_fields is cleared. + * Any inode that has dirty modifications in the log is pinned. The + * racy check here for a pinned inode while not catch modifications + * that happen concurrently to the fsync call, but fsync semantics + * only require to sync previously completed I/O. */ - xfs_ilock(ip, XFS_ILOCK_SHARED); - if (xfs_ipincount(ip)) { - if (!datasync || - (iip->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP)) - lsn = iip->ili_last_lsn; - } - - if (lsn) { - error = xfs_log_force_lsn(mp, lsn, XFS_LOG_SYNC, &log_flushed); - spin_lock(&iip->ili_lock); - iip->ili_fsync_fields = 0; - spin_unlock(&iip->ili_lock); - } - xfs_iunlock(ip, XFS_ILOCK_SHARED); + if (xfs_ipincount(ip)) + error = xfs_fsync_flush_log(ip, datasync, &log_flushed); /* * If we only have a single device, and the log force about was @@ -197,30 +223,42 @@ xfs_file_fsync( return error; } +static int +xfs_ilock_iocb( + struct kiocb *iocb, + unsigned int lock_mode) +{ + struct xfs_inode *ip = XFS_I(file_inode(iocb->ki_filp)); + + if (iocb->ki_flags & IOCB_NOWAIT) { + if (!xfs_ilock_nowait(ip, lock_mode)) + return -EAGAIN; + } else { + xfs_ilock(ip, lock_mode); + } + + return 0; +} + STATIC ssize_t -xfs_file_dio_aio_read( +xfs_file_dio_read( struct kiocb *iocb, struct iov_iter *to) { struct xfs_inode *ip = XFS_I(file_inode(iocb->ki_filp)); - size_t count = iov_iter_count(to); ssize_t ret; - trace_xfs_file_direct_read(ip, count, iocb->ki_pos); + trace_xfs_file_direct_read(iocb, to); - if (!count) + if (!iov_iter_count(to)) return 0; /* skip atime */ file_accessed(iocb->ki_filp); - if (iocb->ki_flags & IOCB_NOWAIT) { - if (!xfs_ilock_nowait(ip, XFS_IOLOCK_SHARED)) - return -EAGAIN; - } else { - xfs_ilock(ip, XFS_IOLOCK_SHARED); - } - ret = iomap_dio_rw(iocb, to, &xfs_read_iomap_ops, NULL, - is_sync_kiocb(iocb)); + ret = xfs_ilock_iocb(iocb, XFS_IOLOCK_SHARED); + if (ret) + return ret; + ret = iomap_dio_rw(iocb, to, &xfs_read_iomap_ops, NULL, 0); xfs_iunlock(ip, XFS_IOLOCK_SHARED); return ret; @@ -232,21 +270,16 @@ xfs_file_dax_read( struct iov_iter *to) { struct xfs_inode *ip = XFS_I(iocb->ki_filp->f_mapping->host); - size_t count = iov_iter_count(to); ssize_t ret = 0; - trace_xfs_file_dax_read(ip, count, iocb->ki_pos); + trace_xfs_file_dax_read(iocb, to); - if (!count) + if (!iov_iter_count(to)) return 0; /* skip atime */ - if (iocb->ki_flags & IOCB_NOWAIT) { - if (!xfs_ilock_nowait(ip, XFS_IOLOCK_SHARED)) - return -EAGAIN; - } else { - xfs_ilock(ip, XFS_IOLOCK_SHARED); - } - + ret = xfs_ilock_iocb(iocb, XFS_IOLOCK_SHARED); + if (ret) + return ret; ret = dax_iomap_rw(iocb, to, &xfs_read_iomap_ops); xfs_iunlock(ip, XFS_IOLOCK_SHARED); @@ -255,21 +288,18 @@ xfs_file_dax_read( } STATIC ssize_t -xfs_file_buffered_aio_read( +xfs_file_buffered_read( struct kiocb *iocb, struct iov_iter *to) { struct xfs_inode *ip = XFS_I(file_inode(iocb->ki_filp)); ssize_t ret; - trace_xfs_file_buffered_read(ip, iov_iter_count(to), iocb->ki_pos); + trace_xfs_file_buffered_read(iocb, to); - if (iocb->ki_flags & IOCB_NOWAIT) { - if (!xfs_ilock_nowait(ip, XFS_IOLOCK_SHARED)) - return -EAGAIN; - } else { - xfs_ilock(ip, XFS_IOLOCK_SHARED); - } + ret = xfs_ilock_iocb(iocb, XFS_IOLOCK_SHARED); + if (ret) + return ret; ret = generic_file_read_iter(iocb, to); xfs_iunlock(ip, XFS_IOLOCK_SHARED); @@ -293,9 +323,9 @@ xfs_file_read_iter( if (IS_DAX(inode)) ret = xfs_file_dax_read(iocb, to); else if (iocb->ki_flags & IOCB_DIRECT) - ret = xfs_file_dio_aio_read(iocb, to); + ret = xfs_file_dio_read(iocb, to); else - ret = xfs_file_buffered_aio_read(iocb, to); + ret = xfs_file_buffered_read(iocb, to); if (ret > 0) XFS_STATS_ADD(mp, xs_read_bytes, ret); @@ -310,7 +340,7 @@ xfs_file_read_iter( * if called for a direct write beyond i_size. */ STATIC ssize_t -xfs_file_aio_write_checks( +xfs_file_write_checks( struct kiocb *iocb, struct iov_iter *from, int *iolock) @@ -328,7 +358,14 @@ restart: if (error <= 0) return error; - error = xfs_break_layouts(inode, iolock, BREAK_WRITE); + if (iocb->ki_flags & IOCB_NOWAIT) { + error = break_layout(inode, false); + if (error == -EWOULDBLOCK) + error = -EAGAIN; + } else { + error = xfs_break_layouts(inode, iolock, BREAK_WRITE); + } + if (error) return error; @@ -339,7 +376,11 @@ restart: if (*iolock == XFS_IOLOCK_SHARED && !IS_NOSEC(inode)) { xfs_iunlock(ip, *iolock); *iolock = XFS_IOLOCK_EXCL; - xfs_ilock(ip, *iolock); + error = xfs_ilock_iocb(iocb, *iolock); + if (error) { + *iolock = 0; + return error; + } goto restart; } /* @@ -361,6 +402,10 @@ restart: isize = i_size_read(inode); if (iocb->ki_pos > isize) { spin_unlock(&ip->i_flags_lock); + + if (iocb->ki_flags & IOCB_NOWAIT) + return -EAGAIN; + if (!drained_dio) { if (*iolock == XFS_IOLOCK_SHARED) { xfs_iunlock(ip, *iolock); @@ -389,12 +434,6 @@ restart: } else spin_unlock(&ip->i_flags_lock); - /* - * Updating the timestamps will grab the ilock again from - * xfs_fs_dirty_inode, so we have to call it after dropping the - * lock above. Eventually we should look into a way to avoid - * the pointless lock roundtrip. - */ return file_modified(file); } @@ -480,122 +519,149 @@ static const struct iomap_dio_ops xfs_dio_write_ops = { }; /* - * xfs_file_dio_aio_write - handle direct IO writes - * - * Lock the inode appropriately to prepare for and issue a direct IO write. - * By separating it from the buffered write path we remove all the tricky to - * follow locking changes and looping. - * - * If there are cached pages or we're extending the file, we need IOLOCK_EXCL - * until we're sure the bytes at the new EOF have been zeroed and/or the cached - * pages are flushed out. - * - * In most cases the direct IO writes will be done holding IOLOCK_SHARED - * allowing them to be done in parallel with reads and other direct IO writes. - * However, if the IO is not aligned to filesystem blocks, the direct IO layer - * needs to do sub-block zeroing and that requires serialisation against other - * direct IOs to the same block. In this case we need to serialise the - * submission of the unaligned IOs so that we don't get racing block zeroing in - * the dio layer. To avoid the problem with aio, we also need to wait for - * outstanding IOs to complete so that unwritten extent conversion is completed - * before we try to map the overlapping block. This is currently implemented by - * hitting it with a big hammer (i.e. inode_dio_wait()). - * - * Returns with locks held indicated by @iolock and errors indicated by - * negative return values. + * Handle block aligned direct I/O writes */ -STATIC ssize_t -xfs_file_dio_aio_write( +static noinline ssize_t +xfs_file_dio_write_aligned( + struct xfs_inode *ip, struct kiocb *iocb, struct iov_iter *from) { - struct file *file = iocb->ki_filp; - struct address_space *mapping = file->f_mapping; - struct inode *inode = mapping->host; - struct xfs_inode *ip = XFS_I(inode); - struct xfs_mount *mp = ip->i_mount; - ssize_t ret = 0; - int unaligned_io = 0; - int iolock; - size_t count = iov_iter_count(from); - struct xfs_buftarg *target = xfs_inode_buftarg(ip); + int iolock = XFS_IOLOCK_SHARED; + ssize_t ret; - /* DIO must be aligned to device logical sector size */ - if ((iocb->ki_pos | count) & target->bt_logical_sectormask) - return -EINVAL; + ret = xfs_ilock_iocb(iocb, iolock); + if (ret) + return ret; + ret = xfs_file_write_checks(iocb, from, &iolock); + if (ret) + goto out_unlock; /* - * Don't take the exclusive iolock here unless the I/O is unaligned to - * the file system block size. We don't need to consider the EOF - * extension case here because xfs_file_aio_write_checks() will relock - * the inode as necessary for EOF zeroing cases and fill out the new - * inode size as appropriate. + * We don't need to hold the IOLOCK exclusively across the IO, so demote + * the iolock back to shared if we had to take the exclusive lock in + * xfs_file_write_checks() for other reasons. */ - if ((iocb->ki_pos & mp->m_blockmask) || - ((iocb->ki_pos + count) & mp->m_blockmask)) { - unaligned_io = 1; - - /* - * We can't properly handle unaligned direct I/O to reflink - * files yet, as we can't unshare a partial block. - */ - if (xfs_is_cow_inode(ip)) { - trace_xfs_reflink_bounce_dio_write(ip, iocb->ki_pos, count); - return -ENOTBLK; - } - iolock = XFS_IOLOCK_EXCL; - } else { + if (iolock == XFS_IOLOCK_EXCL) { + xfs_ilock_demote(ip, XFS_IOLOCK_EXCL); iolock = XFS_IOLOCK_SHARED; } + trace_xfs_file_direct_write(iocb, from); + ret = iomap_dio_rw(iocb, from, &xfs_direct_write_iomap_ops, + &xfs_dio_write_ops, 0); +out_unlock: + if (iolock) + xfs_iunlock(ip, iolock); + return ret; +} - if (iocb->ki_flags & IOCB_NOWAIT) { - /* unaligned dio always waits, bail */ - if (unaligned_io) - return -EAGAIN; - if (!xfs_ilock_nowait(ip, iolock)) +/* + * Handle block unaligned direct I/O writes + * + * In most cases direct I/O writes will be done holding IOLOCK_SHARED, allowing + * them to be done in parallel with reads and other direct I/O writes. However, + * if the I/O is not aligned to filesystem blocks, the direct I/O layer may need + * to do sub-block zeroing and that requires serialisation against other direct + * I/O to the same block. In this case we need to serialise the submission of + * the unaligned I/O so that we don't get racing block zeroing in the dio layer. + * In the case where sub-block zeroing is not required, we can do concurrent + * sub-block dios to the same block successfully. + * + * Optimistically submit the I/O using the shared lock first, but use the + * IOMAP_DIO_OVERWRITE_ONLY flag to tell the lower layers to return -EAGAIN + * if block allocation or partial block zeroing would be required. In that case + * we try again with the exclusive lock. + */ +static noinline ssize_t +xfs_file_dio_write_unaligned( + struct xfs_inode *ip, + struct kiocb *iocb, + struct iov_iter *from) +{ + size_t isize = i_size_read(VFS_I(ip)); + size_t count = iov_iter_count(from); + int iolock = XFS_IOLOCK_SHARED; + unsigned int flags = IOMAP_DIO_OVERWRITE_ONLY; + ssize_t ret; + + /* + * Extending writes need exclusivity because of the sub-block zeroing + * that the DIO code always does for partial tail blocks beyond EOF, so + * don't even bother trying the fast path in this case. + */ + if (iocb->ki_pos > isize || iocb->ki_pos + count >= isize) { +retry_exclusive: + if (iocb->ki_flags & IOCB_NOWAIT) return -EAGAIN; - } else { - xfs_ilock(ip, iolock); + iolock = XFS_IOLOCK_EXCL; + flags = IOMAP_DIO_FORCE_WAIT; } - ret = xfs_file_aio_write_checks(iocb, from, &iolock); + ret = xfs_ilock_iocb(iocb, iolock); if (ret) - goto out; - count = iov_iter_count(from); + return ret; /* - * If we are doing unaligned IO, we can't allow any other overlapping IO - * in-flight at the same time or we risk data corruption. Wait for all - * other IO to drain before we submit. If the IO is aligned, demote the - * iolock if we had to take the exclusive lock in - * xfs_file_aio_write_checks() for other reasons. + * We can't properly handle unaligned direct I/O to reflink files yet, + * as we can't unshare a partial block. */ - if (unaligned_io) { - inode_dio_wait(inode); - } else if (iolock == XFS_IOLOCK_EXCL) { - xfs_ilock_demote(ip, XFS_IOLOCK_EXCL); - iolock = XFS_IOLOCK_SHARED; + if (xfs_is_cow_inode(ip)) { + trace_xfs_reflink_bounce_dio_write(iocb, from); + ret = -ENOTBLK; + goto out_unlock; } - trace_xfs_file_direct_write(ip, count, iocb->ki_pos); + ret = xfs_file_write_checks(iocb, from, &iolock); + if (ret) + goto out_unlock; + /* - * If unaligned, this is the only IO in-flight. Wait on it before we - * release the iolock to prevent subsequent overlapping IO. + * If we are doing exclusive unaligned I/O, this must be the only I/O + * in-flight. Otherwise we risk data corruption due to unwritten extent + * conversions from the AIO end_io handler. Wait for all other I/O to + * drain first. */ + if (flags & IOMAP_DIO_FORCE_WAIT) + inode_dio_wait(VFS_I(ip)); + + trace_xfs_file_direct_write(iocb, from); ret = iomap_dio_rw(iocb, from, &xfs_direct_write_iomap_ops, - &xfs_dio_write_ops, - is_sync_kiocb(iocb) || unaligned_io); -out: - xfs_iunlock(ip, iolock); + &xfs_dio_write_ops, flags); /* - * No fallback to buffered IO after short writes for XFS, direct I/O - * will either complete fully or return an error. + * Retry unaligned I/O with exclusive blocking semantics if the DIO + * layer rejected it for mapping or locking reasons. If we are doing + * nonblocking user I/O, propagate the error. */ - ASSERT(ret < 0 || ret == count); + if (ret == -EAGAIN && !(iocb->ki_flags & IOCB_NOWAIT)) { + ASSERT(flags & IOMAP_DIO_OVERWRITE_ONLY); + xfs_iunlock(ip, iolock); + goto retry_exclusive; + } + +out_unlock: + if (iolock) + xfs_iunlock(ip, iolock); return ret; } +static ssize_t +xfs_file_dio_write( + struct kiocb *iocb, + struct iov_iter *from) +{ + struct xfs_inode *ip = XFS_I(file_inode(iocb->ki_filp)); + struct xfs_buftarg *target = xfs_inode_buftarg(ip); + size_t count = iov_iter_count(from); + + /* direct I/O must be aligned to device logical sector size */ + if ((iocb->ki_pos | count) & target->bt_logical_sectormask) + return -EINVAL; + if ((iocb->ki_pos | count) & ip->i_mount->m_blockmask) + return xfs_file_dio_write_unaligned(ip, iocb, from); + return xfs_file_dio_write_aligned(ip, iocb, from); +} + static noinline ssize_t xfs_file_dax_write( struct kiocb *iocb, @@ -605,31 +671,26 @@ xfs_file_dax_write( struct xfs_inode *ip = XFS_I(inode); int iolock = XFS_IOLOCK_EXCL; ssize_t ret, error = 0; - size_t count; loff_t pos; - if (iocb->ki_flags & IOCB_NOWAIT) { - if (!xfs_ilock_nowait(ip, iolock)) - return -EAGAIN; - } else { - xfs_ilock(ip, iolock); - } - - ret = xfs_file_aio_write_checks(iocb, from, &iolock); + ret = xfs_ilock_iocb(iocb, iolock); + if (ret) + return ret; + ret = xfs_file_write_checks(iocb, from, &iolock); if (ret) goto out; pos = iocb->ki_pos; - count = iov_iter_count(from); - trace_xfs_file_dax_write(ip, count, pos); + trace_xfs_file_dax_write(iocb, from); ret = dax_iomap_rw(iocb, from, &xfs_direct_write_iomap_ops); if (ret > 0 && iocb->ki_pos > i_size_read(inode)) { i_size_write(inode, iocb->ki_pos); error = xfs_setfilesize(ip, pos, ret); } out: - xfs_iunlock(ip, iolock); + if (iolock) + xfs_iunlock(ip, iolock); if (error) return error; @@ -643,7 +704,7 @@ out: } STATIC ssize_t -xfs_file_buffered_aio_write( +xfs_file_buffered_write( struct kiocb *iocb, struct iov_iter *from) { @@ -652,7 +713,7 @@ xfs_file_buffered_aio_write( struct inode *inode = mapping->host; struct xfs_inode *ip = XFS_I(inode); ssize_t ret; - int enospc = 0; + bool cleared_space = false; int iolock; if (iocb->ki_flags & IOCB_NOWAIT) @@ -662,14 +723,14 @@ write_retry: iolock = XFS_IOLOCK_EXCL; xfs_ilock(ip, iolock); - ret = xfs_file_aio_write_checks(iocb, from, &iolock); + ret = xfs_file_write_checks(iocb, from, &iolock); if (ret) goto out; /* We can write back this queue in page reclaim */ current->backing_dev_info = inode_to_bdi(inode); - trace_xfs_file_buffered_write(ip, iov_iter_count(from), iocb->ki_pos); + trace_xfs_file_buffered_write(iocb, from); ret = iomap_file_buffered_write(iocb, from, &xfs_buffered_write_iomap_ops); if (likely(ret >= 0)) @@ -682,27 +743,23 @@ write_retry: * metadata space. This reduces the chances that the eofblocks scan * waits on dirty mappings. Since xfs_flush_inodes() is serialized, this * also behaves as a filter to prevent too many eofblocks scans from - * running at the same time. + * running at the same time. Use a synchronous scan to increase the + * effectiveness of the scan. */ - if (ret == -EDQUOT && !enospc) { + if (ret == -EDQUOT && !cleared_space) { xfs_iunlock(ip, iolock); - enospc = xfs_inode_free_quota_eofblocks(ip); - if (enospc) - goto write_retry; - enospc = xfs_inode_free_quota_cowblocks(ip); - if (enospc) - goto write_retry; - iolock = 0; - } else if (ret == -ENOSPC && !enospc) { + xfs_blockgc_free_quota(ip, XFS_EOF_FLAGS_SYNC); + cleared_space = true; + goto write_retry; + } else if (ret == -ENOSPC && !cleared_space) { struct xfs_eofblocks eofb = {0}; - enospc = 1; + cleared_space = true; xfs_flush_inodes(ip->i_mount); xfs_iunlock(ip, iolock); eofb.eof_flags = XFS_EOF_FLAGS_SYNC; - xfs_icache_free_eofblocks(ip->i_mount, &eofb); - xfs_icache_free_cowblocks(ip->i_mount, &eofb); + xfs_blockgc_free_space(ip->i_mount, &eofb); goto write_retry; } @@ -749,12 +806,12 @@ xfs_file_write_iter( * CoW. In all other directio scenarios we do not * allow an operation to fall back to buffered mode. */ - ret = xfs_file_dio_aio_write(iocb, from); + ret = xfs_file_dio_write(iocb, from); if (ret != -ENOTBLK) return ret; } - return xfs_file_buffered_aio_write(iocb, from); + return xfs_file_buffered_write(iocb, from); } static void @@ -1319,17 +1376,19 @@ xfs_filemap_pfn_mkwrite( return __xfs_filemap_fault(vmf, PE_SIZE_PTE, true); } -static void +static vm_fault_t xfs_filemap_map_pages( struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff) { struct inode *inode = file_inode(vmf->vma->vm_file); + vm_fault_t ret; xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED); - filemap_map_pages(vmf, start_pgoff, end_pgoff); + ret = filemap_map_pages(vmf, start_pgoff, end_pgoff); xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED); + return ret; } static const struct vm_operations_struct xfs_file_vm_ops = { diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index 959ce91a3755..a2a407039227 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -25,17 +25,17 @@ */ static int xfs_growfs_data_private( - xfs_mount_t *mp, /* mount point for filesystem */ - xfs_growfs_data_t *in) /* growfs data input struct */ + struct xfs_mount *mp, /* mount point for filesystem */ + struct xfs_growfs_data *in) /* growfs data input struct */ { struct xfs_buf *bp; int error; xfs_agnumber_t nagcount; xfs_agnumber_t nagimax = 0; - xfs_rfsblock_t nb, nb_mod; - xfs_rfsblock_t new; + xfs_rfsblock_t nb, nb_div, nb_mod; + xfs_rfsblock_t delta; xfs_agnumber_t oagcount; - xfs_trans_t *tp; + struct xfs_trans *tp; struct aghdr_init_data id = {}; nb = in->newblocks; @@ -50,16 +50,16 @@ xfs_growfs_data_private( return error; xfs_buf_relse(bp); - new = nb; /* use new as a temporary here */ - nb_mod = do_div(new, mp->m_sb.sb_agblocks); - nagcount = new + (nb_mod != 0); + nb_div = nb; + nb_mod = do_div(nb_div, mp->m_sb.sb_agblocks); + nagcount = nb_div + (nb_mod != 0); if (nb_mod && nb_mod < XFS_MIN_AG_BLOCKS) { nagcount--; nb = (xfs_rfsblock_t)nagcount * mp->m_sb.sb_agblocks; if (nb < mp->m_sb.sb_dblocks) return -EINVAL; } - new = nb - mp->m_sb.sb_dblocks; + delta = nb - mp->m_sb.sb_dblocks; oagcount = mp->m_sb.sb_agcount; /* allocate the new per-ag structures */ @@ -89,7 +89,7 @@ xfs_growfs_data_private( INIT_LIST_HEAD(&id.buffer_list); for (id.agno = nagcount - 1; id.agno >= oagcount; - id.agno--, new -= id.agsize) { + id.agno--, delta -= id.agsize) { if (id.agno == nagcount - 1) id.agsize = nb - @@ -110,8 +110,8 @@ xfs_growfs_data_private( xfs_trans_agblocks_delta(tp, id.nfree); /* If there are new blocks in the old last AG, extend it. */ - if (new) { - error = xfs_ag_extend_space(mp, tp, &id, new); + if (delta) { + error = xfs_ag_extend_space(mp, tp, &id, delta); if (error) goto out_trans_cancel; } @@ -143,7 +143,7 @@ xfs_growfs_data_private( * If we expanded the last AG, free the per-AG reservation * so we can reinitialize it with the new size. */ - if (new) { + if (delta) { struct xfs_perag *pag; pag = xfs_perag_get(mp, id.agno); @@ -170,8 +170,8 @@ out_trans_cancel: static int xfs_growfs_log_private( - xfs_mount_t *mp, /* mount point for filesystem */ - xfs_growfs_log_t *in) /* growfs log input struct */ + struct xfs_mount *mp, /* mount point for filesystem */ + struct xfs_growfs_log *in) /* growfs log input struct */ { xfs_extlen_t nb; @@ -268,7 +268,7 @@ out_error: int xfs_growfs_log( xfs_mount_t *mp, - xfs_growfs_log_t *in) + struct xfs_growfs_log *in) { int error; diff --git a/fs/xfs/xfs_fsops.h b/fs/xfs/xfs_fsops.h index 92869f6ec8d3..2cffe51a31e8 100644 --- a/fs/xfs/xfs_fsops.h +++ b/fs/xfs/xfs_fsops.h @@ -6,8 +6,8 @@ #ifndef __XFS_FSOPS_H__ #define __XFS_FSOPS_H__ -extern int xfs_growfs_data(xfs_mount_t *mp, xfs_growfs_data_t *in); -extern int xfs_growfs_log(xfs_mount_t *mp, xfs_growfs_log_t *in); +extern int xfs_growfs_data(struct xfs_mount *mp, struct xfs_growfs_data *in); +extern int xfs_growfs_log(struct xfs_mount *mp, struct xfs_growfs_log *in); extern void xfs_fs_counts(xfs_mount_t *mp, xfs_fsop_counts_t *cnt); extern int xfs_reserve_blocks(xfs_mount_t *mp, uint64_t *inval, xfs_fsop_resblks_t *outval); diff --git a/fs/xfs/xfs_globals.c b/fs/xfs/xfs_globals.c index fa55ab8b8d80..f62fa652c2fd 100644 --- a/fs/xfs/xfs_globals.c +++ b/fs/xfs/xfs_globals.c @@ -8,8 +8,8 @@ /* * Tunable XFS parameters. xfs_params is required even when CONFIG_SYSCTL=n, * other XFS code uses these values. Times are measured in centisecs (i.e. - * 100ths of a second) with the exception of eofb_timer and cowb_timer, which - * are measured in seconds. + * 100ths of a second) with the exception of blockgc_timer, which is measured + * in seconds. */ xfs_param_t xfs_params = { /* MIN DFLT MAX */ @@ -28,8 +28,7 @@ xfs_param_t xfs_params = { .rotorstep = { 1, 1, 255 }, .inherit_nodfrg = { 0, 1, 1 }, .fstrm_timer = { 1, 30*100, 3600*100}, - .eofb_timer = { 1, 300, 3600*24}, - .cowb_timer = { 1, 1800, 3600*24}, + .blockgc_timer = { 1, 300, 3600*24}, }; struct xfs_globals xfs_globals = { diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index deb99300d171..1d7720a0c068 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -916,69 +916,6 @@ xfs_inode_walk( } /* - * Background scanning to trim post-EOF preallocated space. This is queued - * based on the 'speculative_prealloc_lifetime' tunable (5m by default). - */ -void -xfs_queue_eofblocks( - struct xfs_mount *mp) -{ - rcu_read_lock(); - if (radix_tree_tagged(&mp->m_perag_tree, XFS_ICI_EOFBLOCKS_TAG)) - queue_delayed_work(mp->m_eofblocks_workqueue, - &mp->m_eofblocks_work, - msecs_to_jiffies(xfs_eofb_secs * 1000)); - rcu_read_unlock(); -} - -void -xfs_eofblocks_worker( - struct work_struct *work) -{ - struct xfs_mount *mp = container_of(to_delayed_work(work), - struct xfs_mount, m_eofblocks_work); - - if (!sb_start_write_trylock(mp->m_super)) - return; - xfs_icache_free_eofblocks(mp, NULL); - sb_end_write(mp->m_super); - - xfs_queue_eofblocks(mp); -} - -/* - * Background scanning to trim preallocated CoW space. This is queued - * based on the 'speculative_cow_prealloc_lifetime' tunable (5m by default). - * (We'll just piggyback on the post-EOF prealloc space workqueue.) - */ -void -xfs_queue_cowblocks( - struct xfs_mount *mp) -{ - rcu_read_lock(); - if (radix_tree_tagged(&mp->m_perag_tree, XFS_ICI_COWBLOCKS_TAG)) - queue_delayed_work(mp->m_eofblocks_workqueue, - &mp->m_cowblocks_work, - msecs_to_jiffies(xfs_cowb_secs * 1000)); - rcu_read_unlock(); -} - -void -xfs_cowblocks_worker( - struct work_struct *work) -{ - struct xfs_mount *mp = container_of(to_delayed_work(work), - struct xfs_mount, m_cowblocks_work); - - if (!sb_start_write_trylock(mp->m_super)) - return; - xfs_icache_free_cowblocks(mp, NULL); - sb_end_write(mp->m_super); - - xfs_queue_cowblocks(mp); -} - -/* * Grab the inode for reclaim exclusively. * * We have found this inode via a lookup under RCU, so the inode may have @@ -1346,14 +1283,17 @@ xfs_reclaim_worker( STATIC int xfs_inode_free_eofblocks( struct xfs_inode *ip, - void *args) + void *args, + unsigned int *lockflags) { struct xfs_eofblocks *eofb = args; bool wait; - int ret; wait = eofb && (eofb->eof_flags & XFS_EOF_FLAGS_SYNC); + if (!xfs_iflags_test(ip, XFS_IEOFBLOCKS)) + return 0; + if (!xfs_can_free_eofblocks(ip, false)) { /* inode could be preallocated or append-only */ trace_xfs_inode_free_eofblocks_invalid(ip); @@ -1380,130 +1320,68 @@ xfs_inode_free_eofblocks( return -EAGAIN; return 0; } + *lockflags |= XFS_IOLOCK_EXCL; - ret = xfs_free_eofblocks(ip); - xfs_iunlock(ip, XFS_IOLOCK_EXCL); - - return ret; -} - -int -xfs_icache_free_eofblocks( - struct xfs_mount *mp, - struct xfs_eofblocks *eofb) -{ - return xfs_inode_walk(mp, 0, xfs_inode_free_eofblocks, eofb, - XFS_ICI_EOFBLOCKS_TAG); + return xfs_free_eofblocks(ip); } /* - * Run eofblocks scans on the quotas applicable to the inode. For inodes with - * multiple quotas, we don't know exactly which quota caused an allocation - * failure. We make a best effort by including each quota under low free space - * conditions (less than 1% free space) in the scan. + * Background scanning to trim preallocated space. This is queued based on the + * 'speculative_prealloc_lifetime' tunable (5m by default). */ -static int -__xfs_inode_free_quota_eofblocks( - struct xfs_inode *ip, - int (*execute)(struct xfs_mount *mp, - struct xfs_eofblocks *eofb)) -{ - int scan = 0; - struct xfs_eofblocks eofb = {0}; - struct xfs_dquot *dq; - - /* - * Run a sync scan to increase effectiveness and use the union filter to - * cover all applicable quotas in a single scan. - */ - eofb.eof_flags = XFS_EOF_FLAGS_UNION|XFS_EOF_FLAGS_SYNC; - - if (XFS_IS_UQUOTA_ENFORCED(ip->i_mount)) { - dq = xfs_inode_dquot(ip, XFS_DQTYPE_USER); - if (dq && xfs_dquot_lowsp(dq)) { - eofb.eof_uid = VFS_I(ip)->i_uid; - eofb.eof_flags |= XFS_EOF_FLAGS_UID; - scan = 1; - } - } - - if (XFS_IS_GQUOTA_ENFORCED(ip->i_mount)) { - dq = xfs_inode_dquot(ip, XFS_DQTYPE_GROUP); - if (dq && xfs_dquot_lowsp(dq)) { - eofb.eof_gid = VFS_I(ip)->i_gid; - eofb.eof_flags |= XFS_EOF_FLAGS_GID; - scan = 1; - } - } - - if (scan) - execute(ip->i_mount, &eofb); - - return scan; -} - -int -xfs_inode_free_quota_eofblocks( - struct xfs_inode *ip) -{ - return __xfs_inode_free_quota_eofblocks(ip, xfs_icache_free_eofblocks); -} - -static inline unsigned long -xfs_iflag_for_tag( - int tag) +static inline void +xfs_blockgc_queue( + struct xfs_perag *pag) { - switch (tag) { - case XFS_ICI_EOFBLOCKS_TAG: - return XFS_IEOFBLOCKS; - case XFS_ICI_COWBLOCKS_TAG: - return XFS_ICOWBLOCKS; - default: - ASSERT(0); - return 0; - } + rcu_read_lock(); + if (radix_tree_tagged(&pag->pag_ici_root, XFS_ICI_BLOCKGC_TAG)) + queue_delayed_work(pag->pag_mount->m_blockgc_workqueue, + &pag->pag_blockgc_work, + msecs_to_jiffies(xfs_blockgc_secs * 1000)); + rcu_read_unlock(); } static void -__xfs_inode_set_blocks_tag( - xfs_inode_t *ip, - void (*execute)(struct xfs_mount *mp), - void (*set_tp)(struct xfs_mount *mp, xfs_agnumber_t agno, - int error, unsigned long caller_ip), - int tag) +xfs_blockgc_set_iflag( + struct xfs_inode *ip, + unsigned long iflag) { - struct xfs_mount *mp = ip->i_mount; - struct xfs_perag *pag; - int tagged; + struct xfs_mount *mp = ip->i_mount; + struct xfs_perag *pag; + int tagged; + + ASSERT((iflag & ~(XFS_IEOFBLOCKS | XFS_ICOWBLOCKS)) == 0); /* * Don't bother locking the AG and looking up in the radix trees * if we already know that we have the tag set. */ - if (ip->i_flags & xfs_iflag_for_tag(tag)) + if (ip->i_flags & iflag) return; spin_lock(&ip->i_flags_lock); - ip->i_flags |= xfs_iflag_for_tag(tag); + ip->i_flags |= iflag; spin_unlock(&ip->i_flags_lock); pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino)); spin_lock(&pag->pag_ici_lock); - tagged = radix_tree_tagged(&pag->pag_ici_root, tag); + tagged = radix_tree_tagged(&pag->pag_ici_root, XFS_ICI_BLOCKGC_TAG); radix_tree_tag_set(&pag->pag_ici_root, - XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino), tag); + XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino), + XFS_ICI_BLOCKGC_TAG); if (!tagged) { - /* propagate the eofblocks tag up into the perag radix tree */ + /* propagate the blockgc tag up into the perag radix tree */ spin_lock(&ip->i_mount->m_perag_lock); radix_tree_tag_set(&ip->i_mount->m_perag_tree, XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino), - tag); + XFS_ICI_BLOCKGC_TAG); spin_unlock(&ip->i_mount->m_perag_lock); /* kick off background trimming */ - execute(ip->i_mount); + xfs_blockgc_queue(pag); - set_tp(ip->i_mount, pag->pag_agno, -1, _RET_IP_); + trace_xfs_perag_set_blockgc(ip->i_mount, pag->pag_agno, -1, + _RET_IP_); } spin_unlock(&pag->pag_ici_lock); @@ -1515,38 +1393,43 @@ xfs_inode_set_eofblocks_tag( xfs_inode_t *ip) { trace_xfs_inode_set_eofblocks_tag(ip); - return __xfs_inode_set_blocks_tag(ip, xfs_queue_eofblocks, - trace_xfs_perag_set_eofblocks, - XFS_ICI_EOFBLOCKS_TAG); + return xfs_blockgc_set_iflag(ip, XFS_IEOFBLOCKS); } static void -__xfs_inode_clear_blocks_tag( - xfs_inode_t *ip, - void (*clear_tp)(struct xfs_mount *mp, xfs_agnumber_t agno, - int error, unsigned long caller_ip), - int tag) +xfs_blockgc_clear_iflag( + struct xfs_inode *ip, + unsigned long iflag) { - struct xfs_mount *mp = ip->i_mount; - struct xfs_perag *pag; + struct xfs_mount *mp = ip->i_mount; + struct xfs_perag *pag; + bool clear_tag; + + ASSERT((iflag & ~(XFS_IEOFBLOCKS | XFS_ICOWBLOCKS)) == 0); spin_lock(&ip->i_flags_lock); - ip->i_flags &= ~xfs_iflag_for_tag(tag); + ip->i_flags &= ~iflag; + clear_tag = (ip->i_flags & (XFS_IEOFBLOCKS | XFS_ICOWBLOCKS)) == 0; spin_unlock(&ip->i_flags_lock); + if (!clear_tag) + return; + pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino)); spin_lock(&pag->pag_ici_lock); radix_tree_tag_clear(&pag->pag_ici_root, - XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino), tag); - if (!radix_tree_tagged(&pag->pag_ici_root, tag)) { - /* clear the eofblocks tag from the perag radix tree */ + XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino), + XFS_ICI_BLOCKGC_TAG); + if (!radix_tree_tagged(&pag->pag_ici_root, XFS_ICI_BLOCKGC_TAG)) { + /* clear the blockgc tag from the perag radix tree */ spin_lock(&ip->i_mount->m_perag_lock); radix_tree_tag_clear(&ip->i_mount->m_perag_tree, XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino), - tag); + XFS_ICI_BLOCKGC_TAG); spin_unlock(&ip->i_mount->m_perag_lock); - clear_tp(ip->i_mount, pag->pag_agno, -1, _RET_IP_); + trace_xfs_perag_clear_blockgc(ip->i_mount, pag->pag_agno, -1, + _RET_IP_); } spin_unlock(&pag->pag_ici_lock); @@ -1558,8 +1441,7 @@ xfs_inode_clear_eofblocks_tag( xfs_inode_t *ip) { trace_xfs_inode_clear_eofblocks_tag(ip); - return __xfs_inode_clear_blocks_tag(ip, - trace_xfs_perag_clear_eofblocks, XFS_ICI_EOFBLOCKS_TAG); + return xfs_blockgc_clear_iflag(ip, XFS_IEOFBLOCKS); } /* @@ -1609,20 +1491,42 @@ xfs_prep_free_cowblocks( STATIC int xfs_inode_free_cowblocks( struct xfs_inode *ip, - void *args) + void *args, + unsigned int *lockflags) { struct xfs_eofblocks *eofb = args; + bool wait; int ret = 0; + wait = eofb && (eofb->eof_flags & XFS_EOF_FLAGS_SYNC); + + if (!xfs_iflags_test(ip, XFS_ICOWBLOCKS)) + return 0; + if (!xfs_prep_free_cowblocks(ip)) return 0; if (!xfs_inode_matches_eofb(ip, eofb)) return 0; - /* Free the CoW blocks */ - xfs_ilock(ip, XFS_IOLOCK_EXCL); - xfs_ilock(ip, XFS_MMAPLOCK_EXCL); + /* + * If the caller is waiting, return -EAGAIN to keep the background + * scanner moving and revisit the inode in a subsequent pass. + */ + if (!(*lockflags & XFS_IOLOCK_EXCL) && + !xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL)) { + if (wait) + return -EAGAIN; + return 0; + } + *lockflags |= XFS_IOLOCK_EXCL; + + if (!xfs_ilock_nowait(ip, XFS_MMAPLOCK_EXCL)) { + if (wait) + return -EAGAIN; + return 0; + } + *lockflags |= XFS_MMAPLOCK_EXCL; /* * Check again, nobody else should be able to dirty blocks or change @@ -1630,37 +1534,15 @@ xfs_inode_free_cowblocks( */ if (xfs_prep_free_cowblocks(ip)) ret = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF, false); - - xfs_iunlock(ip, XFS_MMAPLOCK_EXCL); - xfs_iunlock(ip, XFS_IOLOCK_EXCL); - return ret; } -int -xfs_icache_free_cowblocks( - struct xfs_mount *mp, - struct xfs_eofblocks *eofb) -{ - return xfs_inode_walk(mp, 0, xfs_inode_free_cowblocks, eofb, - XFS_ICI_COWBLOCKS_TAG); -} - -int -xfs_inode_free_quota_cowblocks( - struct xfs_inode *ip) -{ - return __xfs_inode_free_quota_eofblocks(ip, xfs_icache_free_cowblocks); -} - void xfs_inode_set_cowblocks_tag( xfs_inode_t *ip) { trace_xfs_inode_set_cowblocks_tag(ip); - return __xfs_inode_set_blocks_tag(ip, xfs_queue_cowblocks, - trace_xfs_perag_set_cowblocks, - XFS_ICI_COWBLOCKS_TAG); + return xfs_blockgc_set_iflag(ip, XFS_ICOWBLOCKS); } void @@ -1668,24 +1550,158 @@ xfs_inode_clear_cowblocks_tag( xfs_inode_t *ip) { trace_xfs_inode_clear_cowblocks_tag(ip); - return __xfs_inode_clear_blocks_tag(ip, - trace_xfs_perag_clear_cowblocks, XFS_ICI_COWBLOCKS_TAG); + return xfs_blockgc_clear_iflag(ip, XFS_ICOWBLOCKS); } +#define for_each_perag_tag(mp, next_agno, pag, tag) \ + for ((next_agno) = 0, (pag) = xfs_perag_get_tag((mp), 0, (tag)); \ + (pag) != NULL; \ + (next_agno) = (pag)->pag_agno + 1, \ + xfs_perag_put(pag), \ + (pag) = xfs_perag_get_tag((mp), (next_agno), (tag))) + + /* Disable post-EOF and CoW block auto-reclamation. */ void -xfs_stop_block_reaping( +xfs_blockgc_stop( struct xfs_mount *mp) { - cancel_delayed_work_sync(&mp->m_eofblocks_work); - cancel_delayed_work_sync(&mp->m_cowblocks_work); + struct xfs_perag *pag; + xfs_agnumber_t agno; + + for_each_perag_tag(mp, agno, pag, XFS_ICI_BLOCKGC_TAG) + cancel_delayed_work_sync(&pag->pag_blockgc_work); } /* Enable post-EOF and CoW block auto-reclamation. */ void -xfs_start_block_reaping( +xfs_blockgc_start( struct xfs_mount *mp) { - xfs_queue_eofblocks(mp); - xfs_queue_cowblocks(mp); + struct xfs_perag *pag; + xfs_agnumber_t agno; + + for_each_perag_tag(mp, agno, pag, XFS_ICI_BLOCKGC_TAG) + xfs_blockgc_queue(pag); +} + +/* Scan one incore inode for block preallocations that we can remove. */ +static int +xfs_blockgc_scan_inode( + struct xfs_inode *ip, + void *args) +{ + unsigned int lockflags = 0; + int error; + + error = xfs_inode_free_eofblocks(ip, args, &lockflags); + if (error) + goto unlock; + + error = xfs_inode_free_cowblocks(ip, args, &lockflags); +unlock: + if (lockflags) + xfs_iunlock(ip, lockflags); + return error; +} + +/* Background worker that trims preallocated space. */ +void +xfs_blockgc_worker( + struct work_struct *work) +{ + struct xfs_perag *pag = container_of(to_delayed_work(work), + struct xfs_perag, pag_blockgc_work); + struct xfs_mount *mp = pag->pag_mount; + int error; + + if (!sb_start_write_trylock(mp->m_super)) + return; + error = xfs_inode_walk_ag(pag, 0, xfs_blockgc_scan_inode, NULL, + XFS_ICI_BLOCKGC_TAG); + if (error) + xfs_info(mp, "AG %u preallocation gc worker failed, err=%d", + pag->pag_agno, error); + sb_end_write(mp->m_super); + xfs_blockgc_queue(pag); +} + +/* + * Try to free space in the filesystem by purging eofblocks and cowblocks. + */ +int +xfs_blockgc_free_space( + struct xfs_mount *mp, + struct xfs_eofblocks *eofb) +{ + trace_xfs_blockgc_free_space(mp, eofb, _RET_IP_); + + return xfs_inode_walk(mp, 0, xfs_blockgc_scan_inode, eofb, + XFS_ICI_BLOCKGC_TAG); +} + +/* + * Run cow/eofblocks scans on the supplied dquots. We don't know exactly which + * quota caused an allocation failure, so we make a best effort by including + * each quota under low free space conditions (less than 1% free space) in the + * scan. + * + * Callers must not hold any inode's ILOCK. If requesting a synchronous scan + * (XFS_EOF_FLAGS_SYNC), the caller also must not hold any inode's IOLOCK or + * MMAPLOCK. + */ +int +xfs_blockgc_free_dquots( + struct xfs_mount *mp, + struct xfs_dquot *udqp, + struct xfs_dquot *gdqp, + struct xfs_dquot *pdqp, + unsigned int eof_flags) +{ + struct xfs_eofblocks eofb = {0}; + bool do_work = false; + + if (!udqp && !gdqp && !pdqp) + return 0; + + /* + * Run a scan to free blocks using the union filter to cover all + * applicable quotas in a single scan. + */ + eofb.eof_flags = XFS_EOF_FLAGS_UNION | eof_flags; + + if (XFS_IS_UQUOTA_ENFORCED(mp) && udqp && xfs_dquot_lowsp(udqp)) { + eofb.eof_uid = make_kuid(mp->m_super->s_user_ns, udqp->q_id); + eofb.eof_flags |= XFS_EOF_FLAGS_UID; + do_work = true; + } + + if (XFS_IS_UQUOTA_ENFORCED(mp) && gdqp && xfs_dquot_lowsp(gdqp)) { + eofb.eof_gid = make_kgid(mp->m_super->s_user_ns, gdqp->q_id); + eofb.eof_flags |= XFS_EOF_FLAGS_GID; + do_work = true; + } + + if (XFS_IS_PQUOTA_ENFORCED(mp) && pdqp && xfs_dquot_lowsp(pdqp)) { + eofb.eof_prid = pdqp->q_id; + eofb.eof_flags |= XFS_EOF_FLAGS_PRID; + do_work = true; + } + + if (!do_work) + return 0; + + return xfs_blockgc_free_space(mp, &eofb); +} + +/* Run cow/eofblocks scans on the quotas attached to the inode. */ +int +xfs_blockgc_free_quota( + struct xfs_inode *ip, + unsigned int eof_flags) +{ + return xfs_blockgc_free_dquots(ip->i_mount, + xfs_inode_dquot(ip, XFS_DQTYPE_USER), + xfs_inode_dquot(ip, XFS_DQTYPE_GROUP), + xfs_inode_dquot(ip, XFS_DQTYPE_PROJ), eof_flags); } diff --git a/fs/xfs/xfs_icache.h b/fs/xfs/xfs_icache.h index 3a4c8b382cd0..d1fddb152420 100644 --- a/fs/xfs/xfs_icache.h +++ b/fs/xfs/xfs_icache.h @@ -23,8 +23,8 @@ struct xfs_eofblocks { #define XFS_ICI_NO_TAG (-1) /* special flag for an untagged lookup in xfs_inode_walk */ #define XFS_ICI_RECLAIM_TAG 0 /* inode is to be reclaimed */ -#define XFS_ICI_EOFBLOCKS_TAG 1 /* inode has blocks beyond EOF */ -#define XFS_ICI_COWBLOCKS_TAG 2 /* inode can have cow blocks to gc */ +/* Inode has speculative preallocations (posteof or cow) to clean. */ +#define XFS_ICI_BLOCKGC_TAG 1 /* * Flags for xfs_iget() @@ -54,19 +54,19 @@ long xfs_reclaim_inodes_nr(struct xfs_mount *mp, int nr_to_scan); void xfs_inode_set_reclaim_tag(struct xfs_inode *ip); +int xfs_blockgc_free_dquots(struct xfs_mount *mp, struct xfs_dquot *udqp, + struct xfs_dquot *gdqp, struct xfs_dquot *pdqp, + unsigned int eof_flags); +int xfs_blockgc_free_quota(struct xfs_inode *ip, unsigned int eof_flags); +int xfs_blockgc_free_space(struct xfs_mount *mp, struct xfs_eofblocks *eofb); + void xfs_inode_set_eofblocks_tag(struct xfs_inode *ip); void xfs_inode_clear_eofblocks_tag(struct xfs_inode *ip); -int xfs_icache_free_eofblocks(struct xfs_mount *, struct xfs_eofblocks *); -int xfs_inode_free_quota_eofblocks(struct xfs_inode *ip); -void xfs_eofblocks_worker(struct work_struct *); -void xfs_queue_eofblocks(struct xfs_mount *); void xfs_inode_set_cowblocks_tag(struct xfs_inode *ip); void xfs_inode_clear_cowblocks_tag(struct xfs_inode *ip); -int xfs_icache_free_cowblocks(struct xfs_mount *, struct xfs_eofblocks *); -int xfs_inode_free_quota_cowblocks(struct xfs_inode *ip); -void xfs_cowblocks_worker(struct work_struct *); -void xfs_queue_cowblocks(struct xfs_mount *); + +void xfs_blockgc_worker(struct work_struct *work); int xfs_inode_walk(struct xfs_mount *mp, int iter_flags, int (*execute)(struct xfs_inode *ip, void *args), @@ -75,7 +75,7 @@ int xfs_inode_walk(struct xfs_mount *mp, int iter_flags, int xfs_icache_inode_is_allocated(struct xfs_mount *mp, struct xfs_trans *tp, xfs_ino_t ino, bool *inuse); -void xfs_stop_block_reaping(struct xfs_mount *mp); -void xfs_start_block_reaping(struct xfs_mount *mp); +void xfs_blockgc_stop(struct xfs_mount *mp); +void xfs_blockgc_start(struct xfs_mount *mp); #endif diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index b7352bc4c815..636ac13b1df2 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -775,6 +775,7 @@ xfs_init_new_inode( prid_t prid, struct xfs_inode **ipp) { + struct inode *dir = pip ? VFS_I(pip) : NULL; struct xfs_mount *mp = tp->t_mountp; struct xfs_inode *ip; unsigned int flags; @@ -804,18 +805,17 @@ xfs_init_new_inode( ASSERT(ip != NULL); inode = VFS_I(ip); - inode->i_mode = mode; set_nlink(inode, nlink); - inode->i_uid = current_fsuid(); inode->i_rdev = rdev; ip->i_d.di_projid = prid; - if (pip && XFS_INHERIT_GID(pip)) { - inode->i_gid = VFS_I(pip)->i_gid; - if ((VFS_I(pip)->i_mode & S_ISGID) && S_ISDIR(mode)) - inode->i_mode |= S_ISGID; + if (dir && !(dir->i_mode & S_ISGID) && + (mp->m_flags & XFS_MOUNT_GRPID)) { + inode->i_uid = current_fsuid(); + inode->i_gid = dir->i_gid; + inode->i_mode = mode; } else { - inode->i_gid = current_fsgid(); + inode_init_owner(inode, dir, mode); } /* @@ -1022,23 +1022,22 @@ xfs_create( * the case we'll drop the one we have and get a more * appropriate transaction later. */ - error = xfs_trans_alloc(mp, tres, resblks, 0, 0, &tp); + error = xfs_trans_alloc_icreate(mp, tres, udqp, gdqp, pdqp, resblks, + &tp); if (error == -ENOSPC) { /* flush outstanding delalloc blocks and retry */ xfs_flush_inodes(mp); - error = xfs_trans_alloc(mp, tres, resblks, 0, 0, &tp); + error = xfs_trans_alloc_icreate(mp, tres, udqp, gdqp, pdqp, + resblks, &tp); } if (error) - goto out_release_inode; + goto out_release_dquots; xfs_ilock(dp, XFS_ILOCK_EXCL | XFS_ILOCK_PARENT); unlock_dp_on_error = true; - /* - * Reserve disk quota and the inode. - */ - error = xfs_trans_reserve_quota(tp, mp, udqp, gdqp, - pdqp, resblks, 1, 0); + error = xfs_iext_count_may_overflow(dp, XFS_DATA_FORK, + XFS_IEXT_DIR_MANIP_CNT(mp)); if (error) goto out_trans_cancel; @@ -1116,7 +1115,7 @@ xfs_create( xfs_finish_inode_setup(ip); xfs_irele(ip); } - + out_release_dquots: xfs_qm_dqrele(udqp); xfs_qm_dqrele(gdqp); xfs_qm_dqrele(pdqp); @@ -1160,14 +1159,10 @@ xfs_create_tmpfile( resblks = XFS_IALLOC_SPACE_RES(mp); tres = &M_RES(mp)->tr_create_tmpfile; - error = xfs_trans_alloc(mp, tres, resblks, 0, 0, &tp); - if (error) - goto out_release_inode; - - error = xfs_trans_reserve_quota(tp, mp, udqp, gdqp, - pdqp, resblks, 1, 0); + error = xfs_trans_alloc_icreate(mp, tres, udqp, gdqp, pdqp, resblks, + &tp); if (error) - goto out_trans_cancel; + goto out_release_dquots; error = xfs_dir_ialloc(&tp, dp, mode, 0, 0, prid, &ip); if (error) @@ -1210,7 +1205,7 @@ xfs_create_tmpfile( xfs_finish_inode_setup(ip); xfs_irele(ip); } - + out_release_dquots: xfs_qm_dqrele(udqp); xfs_qm_dqrele(gdqp); xfs_qm_dqrele(pdqp); @@ -1258,6 +1253,11 @@ xfs_link( xfs_trans_ijoin(tp, sip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, tdp, XFS_ILOCK_EXCL); + error = xfs_iext_count_may_overflow(tdp, XFS_DATA_FORK, + XFS_IEXT_DIR_MANIP_CNT(mp)); + if (error) + goto error_return; + /* * If we are using project inheritance, we only allow hard link * creation in our tree when the project IDs are the same; else @@ -3017,7 +3017,7 @@ xfs_rename( struct xfs_trans *tp; struct xfs_inode *wip = NULL; /* whiteout inode */ struct xfs_inode *inodes[__XFS_SORT_INODES]; - struct xfs_buf *agibp; + int i; int num_inodes = __XFS_SORT_INODES; bool new_parent = (src_dp != target_dp); bool src_is_directory = S_ISDIR(VFS_I(src_ip)->i_mode); @@ -3106,6 +3106,35 @@ xfs_rename( /* * Check for expected errors before we dirty the transaction * so we can return an error without a transaction abort. + * + * Extent count overflow check: + * + * From the perspective of src_dp, a rename operation is essentially a + * directory entry remove operation. Hence the only place where we check + * for extent count overflow for src_dp is in + * xfs_bmap_del_extent_real(). xfs_bmap_del_extent_real() returns + * -ENOSPC when it detects a possible extent count overflow and in + * response, the higher layers of directory handling code do the + * following: + * 1. Data/Free blocks: XFS lets these blocks linger until a + * future remove operation removes them. + * 2. Dabtree blocks: XFS swaps the blocks with the last block in the + * Leaf space and unmaps the last block. + * + * For target_dp, there are two cases depending on whether the + * destination directory entry exists or not. + * + * When destination directory entry does not exist (i.e. target_ip == + * NULL), extent count overflow check is performed only when transaction + * has a non-zero sized space reservation associated with it. With a + * zero-sized space reservation, XFS allows a rename operation to + * continue only when the directory has sufficient free space in its + * data/leaf/free space blocks to hold the new entry. + * + * When destination directory entry exists (i.e. target_ip != NULL), all + * we need to do is change the inode number associated with the already + * existing entry. Hence there is no need to perform an extent count + * overflow check. */ if (target_ip == NULL) { /* @@ -3116,6 +3145,12 @@ xfs_rename( error = xfs_dir_canenter(tp, target_dp, target_name); if (error) goto out_trans_cancel; + } else { + error = xfs_iext_count_may_overflow(target_dp, + XFS_DATA_FORK, + XFS_IEXT_DIR_MANIP_CNT(mp)); + if (error) + goto out_trans_cancel; } } else { /* @@ -3131,6 +3166,30 @@ xfs_rename( } /* + * Lock the AGI buffers we need to handle bumping the nlink of the + * whiteout inode off the unlinked list and to handle dropping the + * nlink of the target inode. Per locking order rules, do this in + * increasing AG order and before directory block allocation tries to + * grab AGFs because we grab AGIs before AGFs. + * + * The (vfs) caller must ensure that if src is a directory then + * target_ip is either null or an empty directory. + */ + for (i = 0; i < num_inodes && inodes[i] != NULL; i++) { + if (inodes[i] == wip || + (inodes[i] == target_ip && + (VFS_I(target_ip)->i_nlink == 1 || src_is_directory))) { + struct xfs_buf *bp; + xfs_agnumber_t agno; + + agno = XFS_INO_TO_AGNO(mp, inodes[i]->i_ino); + error = xfs_read_agi(mp, tp, agno, &bp); + if (error) + goto out_trans_cancel; + } + } + + /* * Directory entry creation below may acquire the AGF. Remove * the whiteout from the unlinked list first to preserve correct * AGI/AGF locking order. This dirties the transaction so failures @@ -3182,22 +3241,6 @@ xfs_rename( * In case there is already an entry with the same * name at the destination directory, remove it first. */ - - /* - * Check whether the replace operation will need to allocate - * blocks. This happens when the shortform directory lacks - * space and we have to convert it to a block format directory. - * When more blocks are necessary, we must lock the AGI first - * to preserve locking order (AGI -> AGF). - */ - if (xfs_dir2_sf_replace_needblock(target_dp, src_ip->i_ino)) { - error = xfs_read_agi(mp, tp, - XFS_INO_TO_AGNO(mp, target_ip->i_ino), - &agibp); - if (error) - goto out_trans_cancel; - } - error = xfs_dir_replace(tp, target_dp, target_name, src_ip->i_ino, spaceres); if (error) @@ -3273,9 +3316,16 @@ xfs_rename( if (wip) { error = xfs_dir_replace(tp, src_dp, src_name, wip->i_ino, spaceres); - } else + } else { + /* + * NOTE: We don't need to check for extent count overflow here + * because the dir remove name code will leave the dir block in + * place if the extent count would overflow. + */ error = xfs_dir_removename(tp, src_dp, src_name, src_ip->i_ino, spaceres); + } + if (error) goto out_trans_cancel; diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 3fbd98f61ea5..248083ea0276 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -1275,24 +1275,23 @@ xfs_ioctl_setattr_prepare_dax( */ static struct xfs_trans * xfs_ioctl_setattr_get_trans( - struct xfs_inode *ip) + struct xfs_inode *ip, + struct xfs_dquot *pdqp) { struct xfs_mount *mp = ip->i_mount; struct xfs_trans *tp; int error = -EROFS; if (mp->m_flags & XFS_MOUNT_RDONLY) - goto out_unlock; + goto out_error; error = -EIO; if (XFS_FORCED_SHUTDOWN(mp)) - goto out_unlock; + goto out_error; - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ichange, 0, 0, 0, &tp); + error = xfs_trans_alloc_ichange(ip, NULL, NULL, pdqp, + capable(CAP_FOWNER), &tp); if (error) - goto out_unlock; - - xfs_ilock(ip, XFS_ILOCK_EXCL); - xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); + goto out_error; /* * CAP_FOWNER overrides the following restrictions: @@ -1312,7 +1311,7 @@ xfs_ioctl_setattr_get_trans( out_cancel: xfs_trans_cancel(tp); -out_unlock: +out_error: return ERR_PTR(error); } @@ -1436,13 +1435,13 @@ xfs_ioctl_setattr( struct xfs_trans *tp; struct xfs_dquot *pdqp = NULL; struct xfs_dquot *olddquot = NULL; - int code; + int error; trace_xfs_ioctl_setattr(ip); - code = xfs_ioctl_setattr_check_projid(ip, fa); - if (code) - return code; + error = xfs_ioctl_setattr_check_projid(ip, fa); + if (error) + return error; /* * If disk quotas is on, we make sure that the dquots do exist on disk, @@ -1453,44 +1452,36 @@ xfs_ioctl_setattr( * because the i_*dquot fields will get updated anyway. */ if (XFS_IS_QUOTA_ON(mp)) { - code = xfs_qm_vop_dqalloc(ip, VFS_I(ip)->i_uid, + error = xfs_qm_vop_dqalloc(ip, VFS_I(ip)->i_uid, VFS_I(ip)->i_gid, fa->fsx_projid, XFS_QMOPT_PQUOTA, NULL, NULL, &pdqp); - if (code) - return code; + if (error) + return error; } xfs_ioctl_setattr_prepare_dax(ip, fa); - tp = xfs_ioctl_setattr_get_trans(ip); + tp = xfs_ioctl_setattr_get_trans(ip, pdqp); if (IS_ERR(tp)) { - code = PTR_ERR(tp); + error = PTR_ERR(tp); goto error_free_dquots; } - if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_PQUOTA_ON(mp) && - ip->i_d.di_projid != fa->fsx_projid) { - code = xfs_qm_vop_chown_reserve(tp, ip, NULL, NULL, pdqp, - capable(CAP_FOWNER) ? XFS_QMOPT_FORCE_RES : 0); - if (code) /* out of quota */ - goto error_trans_cancel; - } - xfs_fill_fsxattr(ip, false, &old_fa); - code = vfs_ioc_fssetxattr_check(VFS_I(ip), &old_fa, fa); - if (code) + error = vfs_ioc_fssetxattr_check(VFS_I(ip), &old_fa, fa); + if (error) goto error_trans_cancel; - code = xfs_ioctl_setattr_check_extsize(ip, fa); - if (code) + error = xfs_ioctl_setattr_check_extsize(ip, fa); + if (error) goto error_trans_cancel; - code = xfs_ioctl_setattr_check_cowextsize(ip, fa); - if (code) + error = xfs_ioctl_setattr_check_cowextsize(ip, fa); + if (error) goto error_trans_cancel; - code = xfs_ioctl_setattr_xflags(tp, ip, fa); - if (code) + error = xfs_ioctl_setattr_xflags(tp, ip, fa); + if (error) goto error_trans_cancel; /* @@ -1530,7 +1521,7 @@ xfs_ioctl_setattr( else ip->i_d.di_cowextsize = 0; - code = xfs_trans_commit(tp); + error = xfs_trans_commit(tp); /* * Release any dquot(s) the inode had kept before chown. @@ -1538,13 +1529,13 @@ xfs_ioctl_setattr( xfs_qm_dqrele(olddquot); xfs_qm_dqrele(pdqp); - return code; + return error; error_trans_cancel: xfs_trans_cancel(tp); error_free_dquots: xfs_qm_dqrele(pdqp); - return code; + return error; } STATIC int @@ -1608,7 +1599,7 @@ xfs_ioc_setxflags( xfs_ioctl_setattr_prepare_dax(ip, &fa); - tp = xfs_ioctl_setattr_get_trans(ip); + tp = xfs_ioctl_setattr_get_trans(ip, NULL); if (IS_ERR(tp)) { error = PTR_ERR(tp); goto out_drop_write; @@ -2260,7 +2251,7 @@ xfs_file_ioctl( } case XFS_IOC_FSGROWFSDATA: { - xfs_growfs_data_t in; + struct xfs_growfs_data in; if (copy_from_user(&in, arg, sizeof(in))) return -EFAULT; @@ -2274,7 +2265,7 @@ xfs_file_ioctl( } case XFS_IOC_FSGROWFSLOG: { - xfs_growfs_log_t in; + struct xfs_growfs_log in; if (copy_from_user(&in, arg, sizeof(in))) return -EFAULT; @@ -2348,8 +2339,10 @@ xfs_file_ioctl( if (error) return error; + trace_xfs_ioc_free_eofblocks(mp, &keofb, _RET_IP_); + sb_start_write(mp->m_super); - error = xfs_icache_free_eofblocks(mp, &keofb); + error = xfs_blockgc_free_space(mp, &keofb); sb_end_write(mp->m_super); return error; } diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 7b9ff824e82d..e17ab7f42928 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -194,25 +194,21 @@ xfs_iomap_write_direct( struct xfs_trans *tp; xfs_filblks_t resaligned; int nimaps; - int quota_flag; - uint qblocks, resblks; - unsigned int resrtextents = 0; + unsigned int dblocks, rblocks; + bool force = false; int error; int bmapi_flags = XFS_BMAPI_PREALLOC; - uint tflags = 0; ASSERT(count_fsb > 0); resaligned = xfs_aligned_fsb_count(offset_fsb, count_fsb, xfs_get_extsz_hint(ip)); if (unlikely(XFS_IS_REALTIME_INODE(ip))) { - resrtextents = qblocks = resaligned; - resrtextents /= mp->m_sb.sb_rextsize; - resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0); - quota_flag = XFS_QMOPT_RES_RTBLKS; + dblocks = XFS_DIOSTRAT_SPACE_RES(mp, 0); + rblocks = resaligned; } else { - resblks = qblocks = XFS_DIOSTRAT_SPACE_RES(mp, resaligned); - quota_flag = XFS_QMOPT_RES_REGBLKS; + dblocks = XFS_DIOSTRAT_SPACE_RES(mp, resaligned); + rblocks = 0; } error = xfs_qm_dqattach(ip); @@ -235,23 +231,21 @@ xfs_iomap_write_direct( if (IS_DAX(VFS_I(ip))) { bmapi_flags = XFS_BMAPI_CONVERT | XFS_BMAPI_ZERO; if (imap->br_state == XFS_EXT_UNWRITTEN) { - tflags |= XFS_TRANS_RESERVE; - resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0) << 1; + force = true; + dblocks = XFS_DIOSTRAT_SPACE_RES(mp, 0) << 1; } } - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, resrtextents, - tflags, &tp); + + error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_write, dblocks, + rblocks, force, &tp); if (error) return error; - xfs_ilock(ip, XFS_ILOCK_EXCL); - - error = xfs_trans_reserve_quota_nblks(tp, ip, qblocks, 0, quota_flag); + error = xfs_iext_count_may_overflow(ip, XFS_DATA_FORK, + XFS_IEXT_ADD_NOSPLIT_CNT); if (error) goto out_trans_cancel; - xfs_trans_ijoin(tp, ip, 0); - /* * From this point onwards we overwrite the imap pointer that the * caller gave to us. @@ -260,7 +254,7 @@ xfs_iomap_write_direct( error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb, bmapi_flags, 0, imap, &nimaps); if (error) - goto out_res_cancel; + goto out_trans_cancel; /* * Complete the transaction @@ -284,8 +278,6 @@ out_unlock: xfs_iunlock(ip, XFS_ILOCK_EXCL); return error; -out_res_cancel: - xfs_trans_unreserve_quota_nblks(tp, ip, (long)qblocks, 0, quota_flag); out_trans_cancel: xfs_trans_cancel(tp); goto out_unlock; @@ -548,16 +540,13 @@ xfs_iomap_write_unwritten( * here as we might be asked to write out the same inode that we * complete here and might deadlock on the iolock. */ - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, - XFS_TRANS_RESERVE, &tp); + error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_write, resblks, + 0, true, &tp); if (error) return error; - xfs_ilock(ip, XFS_ILOCK_EXCL); - xfs_trans_ijoin(tp, ip, 0); - - error = xfs_trans_reserve_quota_nblks(tp, ip, resblks, 0, - XFS_QMOPT_RES_REGBLKS | XFS_QMOPT_FORCE_RES); + error = xfs_iext_count_may_overflow(ip, XFS_DATA_FORK, + XFS_IEXT_WRITE_UNWRITTEN_CNT); if (error) goto error_on_bmapi_transaction; @@ -784,15 +773,28 @@ xfs_direct_write_iomap_begin( goto allocate_blocks; /* - * NOWAIT IO needs to span the entire requested IO with a single map so - * that we avoid partial IO failures due to the rest of the IO range not - * covered by this map triggering an EAGAIN condition when it is - * subsequently mapped and aborting the IO. + * NOWAIT and OVERWRITE I/O needs to span the entire requested I/O with + * a single map so that we avoid partial IO failures due to the rest of + * the I/O range not covered by this map triggering an EAGAIN condition + * when it is subsequently mapped and aborting the I/O. */ - if ((flags & IOMAP_NOWAIT) && - !imap_spans_range(&imap, offset_fsb, end_fsb)) { + if (flags & (IOMAP_NOWAIT | IOMAP_OVERWRITE_ONLY)) { error = -EAGAIN; - goto out_unlock; + if (!imap_spans_range(&imap, offset_fsb, end_fsb)) + goto out_unlock; + } + + /* + * For overwrite only I/O, we cannot convert unwritten extents without + * requiring sub-block zeroing. This can only be done under an + * exclusive IOLOCK, hence return -EAGAIN if this is not a written + * extent to tell the caller to try again. + */ + if (flags & IOMAP_OVERWRITE_ONLY) { + error = -EAGAIN; + if (imap.br_state != XFS_EXT_NORM && + ((offset | length) & mp->m_blockmask)) + goto out_unlock; } xfs_iunlock(ip, lockmode); @@ -801,7 +803,7 @@ xfs_direct_write_iomap_begin( allocate_blocks: error = -EAGAIN; - if (flags & IOMAP_NOWAIT) + if (flags & (IOMAP_NOWAIT | IOMAP_OVERWRITE_ONLY)) goto out_unlock; /* @@ -842,7 +844,8 @@ out_found_cow: return xfs_bmbt_to_iomap(ip, iomap, &cmap, IOMAP_F_SHARED); out_unlock: - xfs_iunlock(ip, lockmode); + if (lockmode) + xfs_iunlock(ip, lockmode); return error; } @@ -870,6 +873,9 @@ xfs_buffered_write_iomap_begin( int allocfork = XFS_DATA_FORK; int error = 0; + if (XFS_FORCED_SHUTDOWN(mp)) + return -EIO; + /* we can't use delayed allocations when using extent size hints */ if (xfs_get_extsz_hint(ip)) return xfs_direct_write_iomap_begin(inode, offset, count, diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 67c8dc9de8aa..00369502fe25 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -700,13 +700,11 @@ xfs_setattr_nonsize( return error; } - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ichange, 0, 0, 0, &tp); + error = xfs_trans_alloc_ichange(ip, udqp, gdqp, NULL, + capable(CAP_FOWNER), &tp); if (error) goto out_dqrele; - xfs_ilock(ip, XFS_ILOCK_EXCL); - xfs_trans_ijoin(tp, ip, 0); - /* * Change file ownership. Must be the owner or privileged. */ @@ -723,21 +721,6 @@ xfs_setattr_nonsize( uid = (mask & ATTR_UID) ? iattr->ia_uid : iuid; /* - * Do a quota reservation only if uid/gid is actually - * going to change. - */ - if (XFS_IS_QUOTA_RUNNING(mp) && - ((XFS_IS_UQUOTA_ON(mp) && !uid_eq(iuid, uid)) || - (XFS_IS_GQUOTA_ON(mp) && !gid_eq(igid, gid)))) { - ASSERT(tp); - error = xfs_qm_vop_chown_reserve(tp, ip, udqp, gdqp, - NULL, capable(CAP_FOWNER) ? - XFS_QMOPT_FORCE_RES : 0); - if (error) /* out of quota */ - goto out_cancel; - } - - /* * CAP_FSETID overrides the following restrictions: * * The set-user-ID and set-group-ID bits of a file will be @@ -786,8 +769,6 @@ xfs_setattr_nonsize( xfs_trans_set_sync(tp); error = xfs_trans_commit(tp); - xfs_iunlock(ip, XFS_ILOCK_EXCL); - /* * Release any dquot(s) the inode had kept before chown. */ @@ -814,9 +795,6 @@ xfs_setattr_nonsize( return 0; -out_cancel: - xfs_trans_cancel(tp); - xfs_iunlock(ip, XFS_ILOCK_EXCL); out_dqrele: xfs_qm_dqrele(udqp); xfs_qm_dqrele(gdqp); @@ -846,7 +824,7 @@ xfs_setattr_size( ASSERT(xfs_isilocked(ip, XFS_MMAPLOCK_EXCL)); ASSERT(S_ISREG(inode->i_mode)); ASSERT((iattr->ia_valid & (ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET| - ATTR_MTIME_SET|ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0); + ATTR_MTIME_SET|ATTR_TIMES_SET)) == 0); oldsize = inode->i_size; newsize = iattr->ia_size; diff --git a/fs/xfs/xfs_iwalk.c b/fs/xfs/xfs_iwalk.c index eae3aff9bc97..c4a340f1f1e1 100644 --- a/fs/xfs/xfs_iwalk.c +++ b/fs/xfs/xfs_iwalk.c @@ -618,15 +618,12 @@ xfs_iwalk_threaded( { struct xfs_pwork_ctl pctl; xfs_agnumber_t agno = XFS_INO_TO_AGNO(mp, startino); - unsigned int nr_threads; int error; ASSERT(agno < mp->m_sb.sb_agcount); ASSERT(!(flags & ~XFS_IWALK_FLAGS_ALL)); - nr_threads = xfs_pwork_guess_datadev_parallelism(mp); - error = xfs_pwork_init(mp, &pctl, xfs_iwalk_ag_work, "xfs_iwalk", - nr_threads); + error = xfs_pwork_init(mp, &pctl, xfs_iwalk_ag_work, "xfs_iwalk"); if (error) return error; diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h index 5b7a1e201559..af6be9b9ccdf 100644 --- a/fs/xfs/xfs_linux.h +++ b/fs/xfs/xfs_linux.h @@ -98,8 +98,7 @@ typedef __u32 xfs_nlink_t; #define xfs_rotorstep xfs_params.rotorstep.val #define xfs_inherit_nodefrag xfs_params.inherit_nodfrg.val #define xfs_fstrm_centisecs xfs_params.fstrm_timer.val -#define xfs_eofb_secs xfs_params.eofb_timer.val -#define xfs_cowb_secs xfs_params.cowb_timer.val +#define xfs_blockgc_secs xfs_params.blockgc_timer.val #define current_cpu() (raw_smp_processor_id()) #define current_set_flags_nested(sp, f) \ diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index fa2d05e65ff1..06041834daa3 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -91,6 +91,9 @@ STATIC int xlog_iclogs_empty( struct xlog *log); +static int +xfs_log_cover(struct xfs_mount *); + static void xlog_grant_sub_space( struct xlog *log, @@ -347,6 +350,25 @@ xlog_tic_add_region(xlog_ticket_t *tic, uint len, uint type) tic->t_res_num++; } +bool +xfs_log_writable( + struct xfs_mount *mp) +{ + /* + * Never write to the log on norecovery mounts, if the block device is + * read-only, or if the filesystem is shutdown. Read-only mounts still + * allow internal writes for log recovery and unmount purposes, so don't + * restrict that case here. + */ + if (mp->m_flags & XFS_MOUNT_NORECOVERY) + return false; + if (xfs_readonly_buftarg(mp->m_log->l_targ)) + return false; + if (XFS_FORCED_SHUTDOWN(mp)) + return false; + return true; +} + /* * Replenish the byte reservation required by moving the grant write head. */ @@ -741,7 +763,7 @@ xfs_log_mount_finish( xfs_log_force(mp, XFS_LOG_SYNC); xfs_ail_push_all_sync(mp->m_ail); } - xfs_wait_buftarg(mp->m_ddev_targp); + xfs_buftarg_drain(mp->m_ddev_targp); if (readonly) mp->m_flags |= XFS_MOUNT_RDONLY; @@ -886,15 +908,8 @@ xfs_log_unmount_write( { struct xlog *log = mp->m_log; - /* - * Don't write out unmount record on norecovery mounts or ro devices. - * Or, if we are doing a forced umount (typically because of IO errors). - */ - if (mp->m_flags & XFS_MOUNT_NORECOVERY || - xfs_readonly_buftarg(log->l_targ)) { - ASSERT(mp->m_flags & XFS_MOUNT_RDONLY); + if (!xfs_log_writable(mp)) return; - } xfs_log_force(mp, XFS_LOG_SYNC); @@ -924,10 +939,9 @@ xfs_log_unmount_write( * To do this, we first need to shut down the background log work so it is not * trying to cover the log as we clean up. We then need to unpin all objects in * the log so we can then flush them out. Once they have completed their IO and - * run the callbacks removing themselves from the AIL, we can write the unmount - * record. + * run the callbacks removing themselves from the AIL, we can cover the log. */ -void +int xfs_log_quiesce( struct xfs_mount *mp) { @@ -936,16 +950,24 @@ xfs_log_quiesce( /* * The superblock buffer is uncached and while xfs_ail_push_all_sync() - * will push it, xfs_wait_buftarg() will not wait for it. Further, + * will push it, xfs_buftarg_wait() will not wait for it. Further, * xfs_buf_iowait() cannot be used because it was pushed with the * XBF_ASYNC flag set, so we need to use a lock/unlock pair to wait for * the IO to complete. */ xfs_ail_push_all_sync(mp->m_ail); - xfs_wait_buftarg(mp->m_ddev_targp); + xfs_buftarg_wait(mp->m_ddev_targp); xfs_buf_lock(mp->m_sb_bp); xfs_buf_unlock(mp->m_sb_bp); + return xfs_log_cover(mp); +} + +void +xfs_log_clean( + struct xfs_mount *mp) +{ + xfs_log_quiesce(mp); xfs_log_unmount_write(mp); } @@ -960,7 +982,9 @@ void xfs_log_unmount( struct xfs_mount *mp) { - xfs_log_quiesce(mp); + xfs_log_clean(mp); + + xfs_buftarg_drain(mp->m_ddev_targp); xfs_trans_ail_destroy(mp); @@ -1037,17 +1061,15 @@ xfs_log_space_wake( * there's no point in running a dummy transaction at this point because we * can't start trying to idle the log until both the CIL and AIL are empty. */ -static int -xfs_log_need_covered(xfs_mount_t *mp) +static bool +xfs_log_need_covered( + struct xfs_mount *mp) { - struct xlog *log = mp->m_log; - int needed = 0; - - if (!xfs_fs_writable(mp, SB_FREEZE_WRITE)) - return 0; + struct xlog *log = mp->m_log; + bool needed = false; if (!xlog_cil_empty(log)) - return 0; + return false; spin_lock(&log->l_icloglock); switch (log->l_covered_state) { @@ -1062,14 +1084,14 @@ xfs_log_need_covered(xfs_mount_t *mp) if (!xlog_iclogs_empty(log)) break; - needed = 1; + needed = true; if (log->l_covered_state == XLOG_STATE_COVER_NEED) log->l_covered_state = XLOG_STATE_COVER_DONE; else log->l_covered_state = XLOG_STATE_COVER_DONE2; break; default: - needed = 1; + needed = true; break; } spin_unlock(&log->l_icloglock); @@ -1077,6 +1099,60 @@ xfs_log_need_covered(xfs_mount_t *mp) } /* + * Explicitly cover the log. This is similar to background log covering but + * intended for usage in quiesce codepaths. The caller is responsible to ensure + * the log is idle and suitable for covering. The CIL, iclog buffers and AIL + * must all be empty. + */ +static int +xfs_log_cover( + struct xfs_mount *mp) +{ + int error = 0; + bool need_covered; + + ASSERT((xlog_cil_empty(mp->m_log) && xlog_iclogs_empty(mp->m_log) && + !xfs_ail_min_lsn(mp->m_log->l_ailp)) || + XFS_FORCED_SHUTDOWN(mp)); + + if (!xfs_log_writable(mp)) + return 0; + + /* + * xfs_log_need_covered() is not idempotent because it progresses the + * state machine if the log requires covering. Therefore, we must call + * this function once and use the result until we've issued an sb sync. + * Do so first to make that abundantly clear. + * + * Fall into the covering sequence if the log needs covering or the + * mount has lazy superblock accounting to sync to disk. The sb sync + * used for covering accumulates the in-core counters, so covering + * handles this for us. + */ + need_covered = xfs_log_need_covered(mp); + if (!need_covered && !xfs_sb_version_haslazysbcount(&mp->m_sb)) + return 0; + + /* + * To cover the log, commit the superblock twice (at most) in + * independent checkpoints. The first serves as a reference for the + * tail pointer. The sync transaction and AIL push empties the AIL and + * updates the in-core tail to the LSN of the first checkpoint. The + * second commit updates the on-disk tail with the in-core LSN, + * covering the log. Push the AIL one more time to leave it empty, as + * we found it. + */ + do { + error = xfs_sync_sb(mp, true); + if (error) + break; + xfs_ail_push_all_sync(mp->m_ail); + } while (xfs_log_need_covered(mp)); + + return error; +} + +/* * We may be holding the log iclog lock upon entering this routine. */ xfs_lsn_t @@ -1259,7 +1335,7 @@ xfs_log_worker( struct xfs_mount *mp = log->l_mp; /* dgc: errors ignored - not fatal and nowhere to report them */ - if (xfs_log_need_covered(mp)) { + if (xfs_fs_writable(mp, SB_FREEZE_WRITE) && xfs_log_need_covered(mp)) { /* * Dump a transaction into the log that contains no real change. * This is needed to stamp the current tail LSN into the log @@ -1416,8 +1492,9 @@ xlog_alloc_log( log->l_iclog->ic_prev = prev_iclog; /* re-write 1st prev ptr */ log->l_ioend_workqueue = alloc_workqueue("xfs-log/%s", - WQ_MEM_RECLAIM | WQ_FREEZABLE | WQ_HIGHPRI, 0, - mp->m_super->s_id); + XFS_WQFLAGS(WQ_FREEZABLE | WQ_MEM_RECLAIM | + WQ_HIGHPRI), + 0, mp->m_super->s_id); if (!log->l_ioend_workqueue) goto out_free_iclog; @@ -2538,12 +2615,15 @@ xlog_covered_state( int iclogs_changed) { /* - * We usually go to NEED. But we go to NEED2 if the changed indicates we - * are done writing the dummy record. If we are done with the second - * dummy recored (DONE2), then we go to IDLE. + * We go to NEED for any non-covering writes. We go to NEED2 if we just + * wrote the first covering record (DONE). We go to IDLE if we just + * wrote the second covering record (DONE2) and remain in IDLE until a + * non-covering write occurs. */ switch (prev_state) { case XLOG_STATE_COVER_IDLE: + if (iclogs_changed == 1) + return XLOG_STATE_COVER_IDLE; case XLOG_STATE_COVER_NEED: case XLOG_STATE_COVER_NEED2: break; diff --git a/fs/xfs/xfs_log.h b/fs/xfs/xfs_log.h index 58c3fcbec94a..044e02cb8921 100644 --- a/fs/xfs/xfs_log.h +++ b/fs/xfs/xfs_log.h @@ -127,6 +127,7 @@ int xfs_log_reserve(struct xfs_mount *mp, int xfs_log_regrant(struct xfs_mount *mp, struct xlog_ticket *tic); void xfs_log_unmount(struct xfs_mount *mp); int xfs_log_force_umount(struct xfs_mount *mp, int logerror); +bool xfs_log_writable(struct xfs_mount *mp); struct xlog_ticket *xfs_log_ticket_get(struct xlog_ticket *ticket); void xfs_log_ticket_put(struct xlog_ticket *ticket); @@ -137,7 +138,8 @@ void xlog_cil_process_committed(struct list_head *list); bool xfs_log_item_in_current_chkpt(struct xfs_log_item *lip); void xfs_log_work_queue(struct xfs_mount *mp); -void xfs_log_quiesce(struct xfs_mount *mp); +int xfs_log_quiesce(struct xfs_mount *mp); +void xfs_log_clean(struct xfs_mount *mp); bool xfs_log_check_lsn(struct xfs_mount *, xfs_lsn_t); bool xfs_log_in_recovery(struct xfs_mount *); diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 7110507a2b6b..52370d0a3f43 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -126,6 +126,7 @@ __xfs_free_perag( { struct xfs_perag *pag = container_of(head, struct xfs_perag, rcu_head); + ASSERT(!delayed_work_pending(&pag->pag_blockgc_work)); ASSERT(atomic_read(&pag->pag_ref) == 0); kmem_free(pag); } @@ -146,6 +147,7 @@ xfs_free_perag( spin_unlock(&mp->m_perag_lock); ASSERT(pag); ASSERT(atomic_read(&pag->pag_ref) == 0); + cancel_delayed_work_sync(&pag->pag_blockgc_work); xfs_iunlink_destroy(pag); xfs_buf_hash_destroy(pag); call_rcu(&pag->rcu_head, __xfs_free_perag); @@ -201,6 +203,7 @@ xfs_initialize_perag( pag->pag_agno = index; pag->pag_mount = mp; spin_lock_init(&pag->pag_ici_lock); + INIT_DELAYED_WORK(&pag->pag_blockgc_work, xfs_blockgc_worker); INIT_RADIX_TREE(&pag->pag_ici_root, GFP_ATOMIC); error = xfs_buf_hash_init(pag); @@ -946,7 +949,7 @@ xfs_mountfs( */ if ((mp->m_flags & (XFS_MOUNT_RDONLY|XFS_MOUNT_NORECOVERY)) == XFS_MOUNT_RDONLY) { - xfs_quiesce_attr(mp); + xfs_log_clean(mp); } /* @@ -1023,8 +1026,8 @@ xfs_mountfs( xfs_log_mount_cancel(mp); out_fail_wait: if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp) - xfs_wait_buftarg(mp->m_logdev_targp); - xfs_wait_buftarg(mp->m_ddev_targp); + xfs_buftarg_drain(mp->m_logdev_targp); + xfs_buftarg_drain(mp->m_ddev_targp); out_free_perag: xfs_free_perag(mp); out_free_dir: @@ -1054,7 +1057,7 @@ xfs_unmountfs( uint64_t resblks; int error; - xfs_stop_block_reaping(mp); + xfs_blockgc_stop(mp); xfs_fs_unreserve_ag_blocks(mp); xfs_qm_unmount_quotas(mp); xfs_rtunmount_inodes(mp); @@ -1124,12 +1127,6 @@ xfs_unmountfs( xfs_warn(mp, "Unable to free reserved block pool. " "Freespace may not be correct on next mount."); - error = xfs_log_sbcount(mp); - if (error) - xfs_warn(mp, "Unable to update superblock counters. " - "Freespace may not be correct on next mount."); - - xfs_log_unmount(mp); xfs_da_unmount(mp); xfs_uuid_unmount(mp); @@ -1165,32 +1162,6 @@ xfs_fs_writable( } /* - * xfs_log_sbcount - * - * Sync the superblock counters to disk. - * - * Note this code can be called during the process of freezing, so we use the - * transaction allocator that does not block when the transaction subsystem is - * in its frozen state. - */ -int -xfs_log_sbcount(xfs_mount_t *mp) -{ - /* allow this to proceed during the freeze sequence... */ - if (!xfs_fs_writable(mp, SB_FREEZE_COMPLETE)) - return 0; - - /* - * we don't need to do this if we are updating the superblock - * counters on every modification. - */ - if (!xfs_sb_version_haslazysbcount(&mp->m_sb)) - return 0; - - return xfs_sync_sb(mp, true); -} - -/* * Deltas for the block count can vary from 1 to very large, but lock contention * only occurs on frequent small block count updates such as in the delayed * allocation path for buffered writes (page a time updates). Hence we set diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index dfa429b77ee2..659ad95fe3e0 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -93,7 +93,7 @@ typedef struct xfs_mount { struct workqueue_struct *m_unwritten_workqueue; struct workqueue_struct *m_cil_workqueue; struct workqueue_struct *m_reclaim_workqueue; - struct workqueue_struct *m_eofblocks_workqueue; + struct workqueue_struct *m_blockgc_workqueue; struct workqueue_struct *m_sync_workqueue; int m_bsize; /* fs logical block size */ @@ -177,10 +177,6 @@ typedef struct xfs_mount { uint64_t m_resblks_avail;/* available reserved blocks */ uint64_t m_resblks_save; /* reserved blks @ remount,ro */ struct delayed_work m_reclaim_work; /* background inode reclaim */ - struct delayed_work m_eofblocks_work; /* background eof blocks - trimming */ - struct delayed_work m_cowblocks_work; /* background cow blocks - trimming */ struct xfs_kobj m_kobj; struct xfs_kobj m_error_kobj; struct xfs_kobj m_error_meta_kobj; @@ -369,6 +365,9 @@ typedef struct xfs_perag { /* Blocks reserved for the reverse mapping btree. */ struct xfs_ag_resv pag_rmapbt_resv; + /* background prealloc block trimming */ + struct delayed_work pag_blockgc_work; + /* reference count */ uint8_t pagf_refcount_level; @@ -399,7 +398,6 @@ int xfs_buf_hash_init(xfs_perag_t *pag); void xfs_buf_hash_destroy(xfs_perag_t *pag); extern void xfs_uuid_table_free(void); -extern int xfs_log_sbcount(xfs_mount_t *); extern uint64_t xfs_default_resblks(xfs_mount_t *mp); extern int xfs_mountfs(xfs_mount_t *mp); extern int xfs_initialize_perag(xfs_mount_t *mp, xfs_agnumber_t agcount, diff --git a/fs/xfs/xfs_mru_cache.c b/fs/xfs/xfs_mru_cache.c index a06661dac5be..34c3b16f834f 100644 --- a/fs/xfs/xfs_mru_cache.c +++ b/fs/xfs/xfs_mru_cache.c @@ -294,7 +294,7 @@ int xfs_mru_cache_init(void) { xfs_mru_reap_wq = alloc_workqueue("xfs_mru_cache", - WQ_MEM_RECLAIM|WQ_FREEZABLE, 1); + XFS_WQFLAGS(WQ_MEM_RECLAIM | WQ_FREEZABLE), 1); if (!xfs_mru_reap_wq) return -ENOMEM; return 0; diff --git a/fs/xfs/xfs_pwork.c b/fs/xfs/xfs_pwork.c index b03333f1c84a..c283b801cc5d 100644 --- a/fs/xfs/xfs_pwork.c +++ b/fs/xfs/xfs_pwork.c @@ -61,16 +61,18 @@ xfs_pwork_init( struct xfs_mount *mp, struct xfs_pwork_ctl *pctl, xfs_pwork_work_fn work_fn, - const char *tag, - unsigned int nr_threads) + const char *tag) { + unsigned int nr_threads = 0; + #ifdef DEBUG if (xfs_globals.pwork_threads >= 0) nr_threads = xfs_globals.pwork_threads; #endif trace_xfs_pwork_init(mp, nr_threads, current->pid); - pctl->wq = alloc_workqueue("%s-%d", WQ_FREEZABLE, nr_threads, tag, + pctl->wq = alloc_workqueue("%s-%d", + WQ_UNBOUND | WQ_SYSFS | WQ_FREEZABLE, nr_threads, tag, current->pid); if (!pctl->wq) return -ENOMEM; @@ -117,20 +119,3 @@ xfs_pwork_poll( atomic_read(&pctl->nr_work) == 0, HZ) == 0) touch_softlockup_watchdog(); } - -/* - * Return the amount of parallelism that the data device can handle, or 0 for - * no limit. - */ -unsigned int -xfs_pwork_guess_datadev_parallelism( - struct xfs_mount *mp) -{ - struct xfs_buftarg *btp = mp->m_ddev_targp; - - /* - * For now we'll go with the most conservative setting possible, - * which is two threads for an SSD and 1 thread everywhere else. - */ - return blk_queue_nonrot(btp->bt_bdev->bd_disk->queue) ? 2 : 1; -} diff --git a/fs/xfs/xfs_pwork.h b/fs/xfs/xfs_pwork.h index 8133124cf3bb..c0ef81fc85dd 100644 --- a/fs/xfs/xfs_pwork.h +++ b/fs/xfs/xfs_pwork.h @@ -51,11 +51,9 @@ xfs_pwork_want_abort( } int xfs_pwork_init(struct xfs_mount *mp, struct xfs_pwork_ctl *pctl, - xfs_pwork_work_fn work_fn, const char *tag, - unsigned int nr_threads); + xfs_pwork_work_fn work_fn, const char *tag); void xfs_pwork_queue(struct xfs_pwork_ctl *pctl, struct xfs_pwork *pwork); int xfs_pwork_destroy(struct xfs_pwork_ctl *pctl); void xfs_pwork_poll(struct xfs_pwork_ctl *pctl); -unsigned int xfs_pwork_guess_datadev_parallelism(struct xfs_mount *mp); #endif /* __XFS_PWORK_H__ */ diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index c134eb4aeaa8..742d1413e2d0 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -1786,105 +1786,35 @@ xfs_qm_vop_chown( xfs_trans_mod_dquot(tp, newdq, XFS_TRANS_DQ_ICOUNT, 1); /* - * Take an extra reference, because the inode is going to keep - * this dquot pointer even after the trans_commit. + * Back when we made quota reservations for the chown, we reserved the + * ondisk blocks + delalloc blocks with the new dquot. Now that we've + * switched the dquots, decrease the new dquot's block reservation + * (having already bumped up the real counter) so that we don't have + * any reservation to give back when we commit. */ - *IO_olddq = xfs_qm_dqhold(newdq); + xfs_trans_mod_dquot(tp, newdq, XFS_TRANS_DQ_RES_BLKS, + -ip->i_delayed_blks); - return prevdq; -} - -/* - * Quota reservations for setattr(AT_UID|AT_GID|AT_PROJID). - */ -int -xfs_qm_vop_chown_reserve( - struct xfs_trans *tp, - struct xfs_inode *ip, - struct xfs_dquot *udqp, - struct xfs_dquot *gdqp, - struct xfs_dquot *pdqp, - uint flags) -{ - struct xfs_mount *mp = ip->i_mount; - uint64_t delblks; - unsigned int blkflags; - struct xfs_dquot *udq_unres = NULL; - struct xfs_dquot *gdq_unres = NULL; - struct xfs_dquot *pdq_unres = NULL; - struct xfs_dquot *udq_delblks = NULL; - struct xfs_dquot *gdq_delblks = NULL; - struct xfs_dquot *pdq_delblks = NULL; - int error; - - - ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED)); - ASSERT(XFS_IS_QUOTA_RUNNING(mp)); - - delblks = ip->i_delayed_blks; - blkflags = XFS_IS_REALTIME_INODE(ip) ? - XFS_QMOPT_RES_RTBLKS : XFS_QMOPT_RES_REGBLKS; - - if (XFS_IS_UQUOTA_ON(mp) && udqp && - i_uid_read(VFS_I(ip)) != udqp->q_id) { - udq_delblks = udqp; - /* - * If there are delayed allocation blocks, then we have to - * unreserve those from the old dquot, and add them to the - * new dquot. - */ - if (delblks) { - ASSERT(ip->i_udquot); - udq_unres = ip->i_udquot; - } - } - if (XFS_IS_GQUOTA_ON(ip->i_mount) && gdqp && - i_gid_read(VFS_I(ip)) != gdqp->q_id) { - gdq_delblks = gdqp; - if (delblks) { - ASSERT(ip->i_gdquot); - gdq_unres = ip->i_gdquot; - } - } - - if (XFS_IS_PQUOTA_ON(ip->i_mount) && pdqp && - ip->i_d.di_projid != pdqp->q_id) { - pdq_delblks = pdqp; - if (delblks) { - ASSERT(ip->i_pdquot); - pdq_unres = ip->i_pdquot; - } - } - - error = xfs_trans_reserve_quota_bydquots(tp, ip->i_mount, - udq_delblks, gdq_delblks, pdq_delblks, - ip->i_d.di_nblocks, 1, flags | blkflags); - if (error) - return error; + /* + * Give the incore reservation for delalloc blocks back to the old + * dquot. We don't normally handle delalloc quota reservations + * transactionally, so just lock the dquot and subtract from the + * reservation. Dirty the transaction because it's too late to turn + * back now. + */ + tp->t_flags |= XFS_TRANS_DIRTY; + xfs_dqlock(prevdq); + ASSERT(prevdq->q_blk.reserved >= ip->i_delayed_blks); + prevdq->q_blk.reserved -= ip->i_delayed_blks; + xfs_dqunlock(prevdq); /* - * Do the delayed blks reservations/unreservations now. Since, these - * are done without the help of a transaction, if a reservation fails - * its previous reservations won't be automatically undone by trans - * code. So, we have to do it manually here. + * Take an extra reference, because the inode is going to keep + * this dquot pointer even after the trans_commit. */ - if (delblks) { - /* - * Do the reservations first. Unreservation can't fail. - */ - ASSERT(udq_delblks || gdq_delblks || pdq_delblks); - ASSERT(udq_unres || gdq_unres || pdq_unres); - error = xfs_trans_reserve_quota_bydquots(NULL, ip->i_mount, - udq_delblks, gdq_delblks, pdq_delblks, - (xfs_qcnt_t)delblks, 0, flags | blkflags); - if (error) - return error; - xfs_trans_reserve_quota_bydquots(NULL, ip->i_mount, - udq_unres, gdq_unres, pdq_unres, - -((xfs_qcnt_t)delblks), 0, blkflags); - } + *IO_olddq = xfs_qm_dqhold(newdq); - return 0; + return prevdq; } int diff --git a/fs/xfs/xfs_quota.h b/fs/xfs/xfs_quota.h index 5a62398940d0..d00d01302545 100644 --- a/fs/xfs/xfs_quota.h +++ b/fs/xfs/xfs_quota.h @@ -81,11 +81,14 @@ extern void xfs_trans_mod_dquot_byino(struct xfs_trans *, struct xfs_inode *, uint, int64_t); extern void xfs_trans_apply_dquot_deltas(struct xfs_trans *); extern void xfs_trans_unreserve_and_mod_dquots(struct xfs_trans *); -extern int xfs_trans_reserve_quota_nblks(struct xfs_trans *, - struct xfs_inode *, int64_t, long, uint); +int xfs_trans_reserve_quota_nblks(struct xfs_trans *tp, struct xfs_inode *ip, + int64_t dblocks, int64_t rblocks, bool force); extern int xfs_trans_reserve_quota_bydquots(struct xfs_trans *, struct xfs_mount *, struct xfs_dquot *, struct xfs_dquot *, struct xfs_dquot *, int64_t, long, uint); +int xfs_trans_reserve_quota_icreate(struct xfs_trans *tp, + struct xfs_dquot *udqp, struct xfs_dquot *gdqp, + struct xfs_dquot *pdqp, int64_t dblocks); extern int xfs_qm_vop_dqalloc(struct xfs_inode *, kuid_t, kgid_t, prid_t, uint, struct xfs_dquot **, struct xfs_dquot **, @@ -95,9 +98,6 @@ extern void xfs_qm_vop_create_dqattach(struct xfs_trans *, struct xfs_inode *, extern int xfs_qm_vop_rename_dqattach(struct xfs_inode **); extern struct xfs_dquot *xfs_qm_vop_chown(struct xfs_trans *, struct xfs_inode *, struct xfs_dquot **, struct xfs_dquot *); -extern int xfs_qm_vop_chown_reserve(struct xfs_trans *, struct xfs_inode *, - struct xfs_dquot *, struct xfs_dquot *, - struct xfs_dquot *, uint); extern int xfs_qm_dqattach(struct xfs_inode *); extern int xfs_qm_dqattach_locked(struct xfs_inode *ip, bool doalloc); extern void xfs_qm_dqdetach(struct xfs_inode *); @@ -108,6 +108,11 @@ extern void xfs_qm_mount_quotas(struct xfs_mount *); extern void xfs_qm_unmount(struct xfs_mount *); extern void xfs_qm_unmount_quotas(struct xfs_mount *); +static inline int +xfs_quota_reserve_blkres(struct xfs_inode *ip, int64_t blocks) +{ + return xfs_trans_reserve_quota_nblks(NULL, ip, blocks, 0, false); +} #else static inline int xfs_qm_vop_dqalloc(struct xfs_inode *ip, kuid_t kuid, kgid_t kgid, @@ -121,11 +126,12 @@ xfs_qm_vop_dqalloc(struct xfs_inode *ip, kuid_t kuid, kgid_t kgid, } #define xfs_trans_dup_dqinfo(tp, tp2) #define xfs_trans_free_dqinfo(tp) -#define xfs_trans_mod_dquot_byino(tp, ip, fields, delta) +#define xfs_trans_mod_dquot_byino(tp, ip, fields, delta) do { } while (0) #define xfs_trans_apply_dquot_deltas(tp) #define xfs_trans_unreserve_and_mod_dquots(tp) static inline int xfs_trans_reserve_quota_nblks(struct xfs_trans *tp, - struct xfs_inode *ip, int64_t nblks, long ninos, uint flags) + struct xfs_inode *ip, int64_t dblocks, int64_t rblocks, + bool force) { return 0; } @@ -136,26 +142,39 @@ static inline int xfs_trans_reserve_quota_bydquots(struct xfs_trans *tp, { return 0; } + +static inline int +xfs_quota_reserve_blkres(struct xfs_inode *ip, int64_t blocks) +{ + return 0; +} + +static inline int +xfs_trans_reserve_quota_icreate(struct xfs_trans *tp, struct xfs_dquot *udqp, + struct xfs_dquot *gdqp, struct xfs_dquot *pdqp, int64_t dblocks) +{ + return 0; +} + #define xfs_qm_vop_create_dqattach(tp, ip, u, g, p) #define xfs_qm_vop_rename_dqattach(it) (0) #define xfs_qm_vop_chown(tp, ip, old, new) (NULL) -#define xfs_qm_vop_chown_reserve(tp, ip, u, g, p, fl) (0) #define xfs_qm_dqattach(ip) (0) #define xfs_qm_dqattach_locked(ip, fl) (0) #define xfs_qm_dqdetach(ip) -#define xfs_qm_dqrele(d) -#define xfs_qm_statvfs(ip, s) +#define xfs_qm_dqrele(d) do { (d) = (d); } while(0) +#define xfs_qm_statvfs(ip, s) do { } while(0) #define xfs_qm_newmount(mp, a, b) (0) #define xfs_qm_mount_quotas(mp) #define xfs_qm_unmount(mp) #define xfs_qm_unmount_quotas(mp) #endif /* CONFIG_XFS_QUOTA */ -#define xfs_trans_unreserve_quota_nblks(tp, ip, nblks, ninos, flags) \ - xfs_trans_reserve_quota_nblks(tp, ip, -(nblks), -(ninos), flags) -#define xfs_trans_reserve_quota(tp, mp, ud, gd, pd, nb, ni, f) \ - xfs_trans_reserve_quota_bydquots(tp, mp, ud, gd, pd, nb, ni, \ - f | XFS_QMOPT_RES_REGBLKS) +static inline int +xfs_quota_unreserve_blkres(struct xfs_inode *ip, int64_t blocks) +{ + return xfs_quota_reserve_blkres(ip, -blocks); +} extern int xfs_mount_reset_sbqflags(struct xfs_mount *); diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index 6fa05fb78189..725c7d8e4438 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -376,16 +376,14 @@ xfs_reflink_allocate_cow( resblks = XFS_DIOSTRAT_SPACE_RES(mp, resaligned); xfs_iunlock(ip, *lockmode); - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0, &tp); - *lockmode = XFS_ILOCK_EXCL; - xfs_ilock(ip, *lockmode); + *lockmode = 0; + error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_write, resblks, 0, + false, &tp); if (error) return error; - error = xfs_qm_dqattach_locked(ip, false); - if (error) - goto out_trans_cancel; + *lockmode = XFS_ILOCK_EXCL; /* * Check for an overlapping extent again now that we dropped the ilock. @@ -398,20 +396,13 @@ xfs_reflink_allocate_cow( goto convert; } - error = xfs_trans_reserve_quota_nblks(tp, ip, resblks, 0, - XFS_QMOPT_RES_REGBLKS); - if (error) - goto out_trans_cancel; - - xfs_trans_ijoin(tp, ip, 0); - /* Allocate the entire reservation as unwritten blocks. */ nimaps = 1; error = xfs_bmapi_write(tp, ip, imap->br_startoff, imap->br_blockcount, XFS_BMAPI_COWFORK | XFS_BMAPI_PREALLOC, 0, cmap, &nimaps); if (error) - goto out_unreserve; + goto out_trans_cancel; xfs_inode_set_cowblocks_tag(ip); error = xfs_trans_commit(tp); @@ -436,9 +427,6 @@ convert: trace_xfs_reflink_convert_cow(ip, cmap); return xfs_reflink_convert_cow_locked(ip, offset_fsb, count_fsb); -out_unreserve: - xfs_trans_unreserve_quota_nblks(tp, ip, (long)resblks, 0, - XFS_QMOPT_RES_REGBLKS); out_trans_cancel: xfs_trans_cancel(tp); return error; @@ -508,9 +496,8 @@ xfs_reflink_cancel_cow_blocks( xfs_bmap_del_extent_cow(ip, &icur, &got, &del); /* Remove the quota reservation */ - error = xfs_trans_reserve_quota_nblks(NULL, ip, - -(long)del.br_blockcount, 0, - XFS_QMOPT_RES_REGBLKS); + error = xfs_quota_unreserve_blkres(ip, + del.br_blockcount); if (error) break; } else { @@ -628,6 +615,11 @@ xfs_reflink_end_cow_extent( xfs_ilock(ip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, ip, 0); + error = xfs_iext_count_may_overflow(ip, XFS_DATA_FORK, + XFS_IEXT_REFLINK_END_COW_CNT); + if (error) + goto out_cancel; + /* * In case of racing, overlapping AIO writes no COW extents might be * left by the time I/O completes for the loser of the race. In that @@ -997,22 +989,47 @@ xfs_reflink_remap_extent( struct xfs_mount *mp = ip->i_mount; struct xfs_trans *tp; xfs_off_t newlen; - int64_t qres, qdelta; + int64_t qdelta = 0; unsigned int resblks; + bool quota_reserved = true; bool smap_real; bool dmap_written = xfs_bmap_is_written_extent(dmap); + int iext_delta = 0; int nimaps; int error; - /* Start a rolling transaction to switch the mappings */ + /* + * Start a rolling transaction to switch the mappings. + * + * Adding a written extent to the extent map can cause a bmbt split, + * and removing a mapped extent from the extent can cause a bmbt split. + * The two operations cannot both cause a split since they operate on + * the same index in the bmap btree, so we only need a reservation for + * one bmbt split if either thing is happening. However, we haven't + * locked the inode yet, so we reserve assuming this is the case. + * + * The first allocation call tries to reserve enough space to handle + * mapping dmap into a sparse part of the file plus the bmbt split. We + * haven't locked the inode or read the existing mapping yet, so we do + * not know for sure that we need the space. This should succeed most + * of the time. + * + * If the first attempt fails, try again but reserving only enough + * space to handle a bmbt split. This is the hard minimum requirement, + * and we revisit quota reservations later when we know more about what + * we're remapping. + */ resblks = XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK); - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0, &tp); + error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_write, + resblks + dmap->br_blockcount, 0, false, &tp); + if (error == -EDQUOT || error == -ENOSPC) { + quota_reserved = false; + error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_write, + resblks, 0, false, &tp); + } if (error) goto out; - xfs_ilock(ip, XFS_ILOCK_EXCL); - xfs_trans_ijoin(tp, ip, 0); - /* * Read what's currently mapped in the destination file into smap. * If smap isn't a hole, we will have to remove it before we can add @@ -1060,15 +1077,9 @@ xfs_reflink_remap_extent( } /* - * Compute quota reservation if we think the quota block counter for + * Increase quota reservation if we think the quota block counter for * this file could increase. * - * Adding a written extent to the extent map can cause a bmbt split, - * and removing a mapped extent from the extent can cause a bmbt split. - * The two operations cannot both cause a split since they operate on - * the same index in the bmap btree, so we only need a reservation for - * one bmbt split if either thing is happening. - * * If we are mapping a written extent into the file, we need to have * enough quota block count reservation to handle the blocks in that * extent. We log only the delta to the quota block counts, so if the @@ -1081,19 +1092,29 @@ xfs_reflink_remap_extent( * count. This is suboptimal, but the VFS flushed the dest range * before we started. That should have removed all the delalloc * reservations, but we code defensively. + * + * xfs_trans_alloc_inode above already tried to grab an even larger + * quota reservation, and kicked off a blockgc scan if it couldn't. + * If we can't get a potentially smaller quota reservation now, we're + * done. */ - qres = qdelta = 0; - if (smap_real || dmap_written) - qres = XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK); - if (!smap_real && dmap_written) - qres += dmap->br_blockcount; - if (qres > 0) { - error = xfs_trans_reserve_quota_nblks(tp, ip, qres, 0, - XFS_QMOPT_RES_REGBLKS); + if (!quota_reserved && !smap_real && dmap_written) { + error = xfs_trans_reserve_quota_nblks(tp, ip, + dmap->br_blockcount, 0, false); if (error) goto out_cancel; } + if (smap_real) + ++iext_delta; + + if (dmap_written) + ++iext_delta; + + error = xfs_iext_count_may_overflow(ip, XFS_DATA_FORK, iext_delta); + if (error) + goto out_cancel; + if (smap_real) { /* * If the extent we're unmapping is backed by storage (written diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c index b4999fb01ff7..161b0e8992ba 100644 --- a/fs/xfs/xfs_rtalloc.c +++ b/fs/xfs/xfs_rtalloc.c @@ -804,6 +804,11 @@ xfs_growfs_rt_alloc( xfs_ilock(ip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); + error = xfs_iext_count_may_overflow(ip, XFS_DATA_FORK, + XFS_IEXT_ADD_NOSPLIT_CNT); + if (error) + goto out_trans_cancel; + /* * Allocate blocks to the bitmap file. */ diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 813be879a5e5..586d42342a79 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -35,6 +35,7 @@ #include "xfs_refcount_item.h" #include "xfs_bmap_item.h" #include "xfs_reflink.h" +#include "xfs_pwork.h" #include <linux/magic.h> #include <linux/fs_context.h> @@ -342,7 +343,7 @@ void xfs_blkdev_issue_flush( xfs_buftarg_t *buftarg) { - blkdev_issue_flush(buftarg->bt_bdev, GFP_NOFS); + blkdev_issue_flush(buftarg->bt_bdev); } STATIC void @@ -495,40 +496,44 @@ xfs_init_mount_workqueues( struct xfs_mount *mp) { mp->m_buf_workqueue = alloc_workqueue("xfs-buf/%s", - WQ_MEM_RECLAIM|WQ_FREEZABLE, 1, mp->m_super->s_id); + XFS_WQFLAGS(WQ_FREEZABLE | WQ_MEM_RECLAIM), + 1, mp->m_super->s_id); if (!mp->m_buf_workqueue) goto out; mp->m_unwritten_workqueue = alloc_workqueue("xfs-conv/%s", - WQ_MEM_RECLAIM|WQ_FREEZABLE, 0, mp->m_super->s_id); + XFS_WQFLAGS(WQ_FREEZABLE | WQ_MEM_RECLAIM), + 0, mp->m_super->s_id); if (!mp->m_unwritten_workqueue) goto out_destroy_buf; mp->m_cil_workqueue = alloc_workqueue("xfs-cil/%s", - WQ_MEM_RECLAIM | WQ_FREEZABLE | WQ_UNBOUND, + XFS_WQFLAGS(WQ_FREEZABLE | WQ_MEM_RECLAIM | WQ_UNBOUND), 0, mp->m_super->s_id); if (!mp->m_cil_workqueue) goto out_destroy_unwritten; mp->m_reclaim_workqueue = alloc_workqueue("xfs-reclaim/%s", - WQ_MEM_RECLAIM|WQ_FREEZABLE, 0, mp->m_super->s_id); + XFS_WQFLAGS(WQ_FREEZABLE | WQ_MEM_RECLAIM), + 0, mp->m_super->s_id); if (!mp->m_reclaim_workqueue) goto out_destroy_cil; - mp->m_eofblocks_workqueue = alloc_workqueue("xfs-eofblocks/%s", - WQ_MEM_RECLAIM|WQ_FREEZABLE, 0, mp->m_super->s_id); - if (!mp->m_eofblocks_workqueue) + mp->m_blockgc_workqueue = alloc_workqueue("xfs-blockgc/%s", + WQ_SYSFS | WQ_UNBOUND | WQ_FREEZABLE | WQ_MEM_RECLAIM, + 0, mp->m_super->s_id); + if (!mp->m_blockgc_workqueue) goto out_destroy_reclaim; - mp->m_sync_workqueue = alloc_workqueue("xfs-sync/%s", WQ_FREEZABLE, 0, - mp->m_super->s_id); + mp->m_sync_workqueue = alloc_workqueue("xfs-sync/%s", + XFS_WQFLAGS(WQ_FREEZABLE), 0, mp->m_super->s_id); if (!mp->m_sync_workqueue) goto out_destroy_eofb; return 0; out_destroy_eofb: - destroy_workqueue(mp->m_eofblocks_workqueue); + destroy_workqueue(mp->m_blockgc_workqueue); out_destroy_reclaim: destroy_workqueue(mp->m_reclaim_workqueue); out_destroy_cil: @@ -546,7 +551,7 @@ xfs_destroy_mount_workqueues( struct xfs_mount *mp) { destroy_workqueue(mp->m_sync_workqueue); - destroy_workqueue(mp->m_eofblocks_workqueue); + destroy_workqueue(mp->m_blockgc_workqueue); destroy_workqueue(mp->m_reclaim_workqueue); destroy_workqueue(mp->m_cil_workqueue); destroy_workqueue(mp->m_unwritten_workqueue); @@ -868,39 +873,6 @@ xfs_restore_resvblks(struct xfs_mount *mp) } /* - * Trigger writeback of all the dirty metadata in the file system. - * - * This ensures that the metadata is written to their location on disk rather - * than just existing in transactions in the log. This means after a quiesce - * there is no log replay required to write the inodes to disk - this is the - * primary difference between a sync and a quiesce. - * - * We cancel log work early here to ensure all transactions the log worker may - * run have finished before we clean up and log the superblock and write an - * unmount record. The unfreeze process is responsible for restarting the log - * worker correctly. - */ -void -xfs_quiesce_attr( - struct xfs_mount *mp) -{ - int error = 0; - - cancel_delayed_work_sync(&mp->m_log->l_work); - - /* force the log to unpin objects from the now complete transactions */ - xfs_log_force(mp, XFS_LOG_SYNC); - - - /* Push the superblock and write an unmount record */ - error = xfs_log_sbcount(mp); - if (error) - xfs_warn(mp, "xfs_attr_quiesce: failed to log sb changes. " - "Frozen image may not be consistent."); - xfs_log_quiesce(mp); -} - -/* * Second stage of a freeze. The data is already frozen so we only * need to take care of the metadata. Once that's done sync the superblock * to the log to dirty it in case of a crash while frozen. This ensures that we @@ -920,10 +892,9 @@ xfs_fs_freeze( * set a GFP_NOFS context here to avoid recursion deadlocks. */ flags = memalloc_nofs_save(); - xfs_stop_block_reaping(mp); + xfs_blockgc_stop(mp); xfs_save_resvblks(mp); - xfs_quiesce_attr(mp); - ret = xfs_sync_sb(mp, true); + ret = xfs_log_quiesce(mp); memalloc_nofs_restore(flags); return ret; } @@ -936,7 +907,7 @@ xfs_fs_unfreeze( xfs_restore_resvblks(mp); xfs_log_work_queue(mp); - xfs_start_block_reaping(mp); + xfs_blockgc_start(mp); return 0; } @@ -1720,7 +1691,7 @@ xfs_remount_rw( xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); return error; } - xfs_start_block_reaping(mp); + xfs_blockgc_start(mp); /* Create the per-AG metadata reservation pool .*/ error = xfs_fs_reserve_ag_blocks(mp); @@ -1740,10 +1711,10 @@ xfs_remount_ro( * Cancel background eofb scanning so it cannot race with the final * log force+buftarg wait and deadlock the remount. */ - xfs_stop_block_reaping(mp); + xfs_blockgc_stop(mp); /* Get rid of any leftover CoW reservations... */ - error = xfs_icache_free_cowblocks(mp, NULL); + error = xfs_blockgc_free_space(mp, NULL); if (error) { xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); return error; @@ -1765,7 +1736,7 @@ xfs_remount_ro( */ xfs_save_resvblks(mp); - xfs_quiesce_attr(mp); + xfs_log_clean(mp); mp->m_flags |= XFS_MOUNT_RDONLY; return 0; @@ -1872,8 +1843,6 @@ static int xfs_init_fs_context( mutex_init(&mp->m_growlock); INIT_WORK(&mp->m_flush_inodes_work, xfs_flush_inodes_worker); INIT_DELAYED_WORK(&mp->m_reclaim_work, xfs_reclaim_worker); - INIT_DELAYED_WORK(&mp->m_eofblocks_work, xfs_eofblocks_worker); - INIT_DELAYED_WORK(&mp->m_cowblocks_work, xfs_cowblocks_worker); mp->m_kobj.kobject.kset = xfs_kset; /* * We don't create the finobt per-ag space reservation until after log @@ -2119,11 +2088,12 @@ xfs_init_workqueues(void) * max_active value for this workqueue. */ xfs_alloc_wq = alloc_workqueue("xfsalloc", - WQ_MEM_RECLAIM|WQ_FREEZABLE, 0); + XFS_WQFLAGS(WQ_MEM_RECLAIM | WQ_FREEZABLE), 0); if (!xfs_alloc_wq) return -ENOMEM; - xfs_discard_wq = alloc_workqueue("xfsdiscard", WQ_UNBOUND, 0); + xfs_discard_wq = alloc_workqueue("xfsdiscard", XFS_WQFLAGS(WQ_UNBOUND), + 0); if (!xfs_discard_wq) goto out_free_alloc_wq; diff --git a/fs/xfs/xfs_super.h b/fs/xfs/xfs_super.h index b552cf6d3379..1ca484b8357f 100644 --- a/fs/xfs/xfs_super.h +++ b/fs/xfs/xfs_super.h @@ -75,6 +75,12 @@ extern void xfs_qm_exit(void); XFS_ASSERT_FATAL_STRING \ XFS_DBG_STRING /* DBG must be last */ +#ifdef DEBUG +# define XFS_WQFLAGS(wqflags) (WQ_SYSFS | (wqflags)) +#else +# define XFS_WQFLAGS(wqflags) (wqflags) +#endif + struct xfs_inode; struct xfs_mount; struct xfs_buftarg; diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c index 1f43fd7f3209..8565663b16cd 100644 --- a/fs/xfs/xfs_symlink.c +++ b/fs/xfs/xfs_symlink.c @@ -197,9 +197,10 @@ xfs_symlink( fs_blocks = xfs_symlink_blocks(mp, pathlen); resblks = XFS_SYMLINK_SPACE_RES(mp, link_name->len, fs_blocks); - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_symlink, resblks, 0, 0, &tp); + error = xfs_trans_alloc_icreate(mp, &M_RES(mp)->tr_symlink, udqp, gdqp, + pdqp, resblks, &tp); if (error) - goto out_release_inode; + goto out_release_dquots; xfs_ilock(dp, XFS_ILOCK_EXCL | XFS_ILOCK_PARENT); unlock_dp_on_error = true; @@ -212,11 +213,8 @@ xfs_symlink( goto out_trans_cancel; } - /* - * Reserve disk quota : blocks and inode. - */ - error = xfs_trans_reserve_quota(tp, mp, udqp, gdqp, - pdqp, resblks, 1, 0); + error = xfs_iext_count_may_overflow(dp, XFS_DATA_FORK, + XFS_IEXT_DIR_MANIP_CNT(mp)); if (error) goto out_trans_cancel; @@ -300,6 +298,7 @@ xfs_symlink( } ASSERT(pathlen == 0); } + i_size_write(VFS_I(ip), ip->i_d.di_size); /* * Create the directory entry for the symlink. @@ -342,7 +341,7 @@ out_release_inode: xfs_finish_inode_setup(ip); xfs_irele(ip); } - +out_release_dquots: xfs_qm_dqrele(udqp); xfs_qm_dqrele(gdqp); xfs_qm_dqrele(pdqp); diff --git a/fs/xfs/xfs_sysctl.c b/fs/xfs/xfs_sysctl.c index fac9de7ee6d0..145e06c47744 100644 --- a/fs/xfs/xfs_sysctl.c +++ b/fs/xfs/xfs_sysctl.c @@ -194,21 +194,12 @@ static struct ctl_table xfs_table[] = { }, { .procname = "speculative_prealloc_lifetime", - .data = &xfs_params.eofb_timer.val, + .data = &xfs_params.blockgc_timer.val, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &xfs_params.eofb_timer.min, - .extra2 = &xfs_params.eofb_timer.max, - }, - { - .procname = "speculative_cow_prealloc_lifetime", - .data = &xfs_params.cowb_timer.val, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &xfs_params.cowb_timer.min, - .extra2 = &xfs_params.cowb_timer.max, + .extra1 = &xfs_params.blockgc_timer.min, + .extra2 = &xfs_params.blockgc_timer.max, }, /* please keep this the last entry */ #ifdef CONFIG_PROC_FS diff --git a/fs/xfs/xfs_sysctl.h b/fs/xfs/xfs_sysctl.h index 8abf4640f1d5..7692e76ead33 100644 --- a/fs/xfs/xfs_sysctl.h +++ b/fs/xfs/xfs_sysctl.h @@ -35,8 +35,7 @@ typedef struct xfs_param { xfs_sysctl_val_t rotorstep; /* inode32 AG rotoring control knob */ xfs_sysctl_val_t inherit_nodfrg;/* Inherit the "nodefrag" inode flag. */ xfs_sysctl_val_t fstrm_timer; /* Filestream dir-AG assoc'n timeout. */ - xfs_sysctl_val_t eofb_timer; /* Interval between eofb scan wakeups */ - xfs_sysctl_val_t cowb_timer; /* Interval between cowb scan wakeups */ + xfs_sysctl_val_t blockgc_timer; /* Interval between blockgc scans */ } xfs_param_t; /* diff --git a/fs/xfs/xfs_trace.c b/fs/xfs/xfs_trace.c index 120398a37c2a..9b8d703dc9fd 100644 --- a/fs/xfs/xfs_trace.c +++ b/fs/xfs/xfs_trace.c @@ -29,6 +29,7 @@ #include "xfs_filestream.h" #include "xfs_fsmap.h" #include "xfs_btree_staging.h" +#include "xfs_icache.h" /* * We include this last to have the helpers above available for the trace diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index 5a263ae3d4f0..e74bbb648f83 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -37,6 +37,7 @@ struct xfs_trans_res; struct xfs_inobt_rec_incore; union xfs_btree_ptr; struct xfs_dqtrx; +struct xfs_eofblocks; #define XFS_ATTR_FILTER_FLAGS \ { XFS_ATTR_ROOT, "ROOT" }, \ @@ -154,10 +155,8 @@ DEFINE_PERAG_REF_EVENT(xfs_perag_get_tag); DEFINE_PERAG_REF_EVENT(xfs_perag_put); DEFINE_PERAG_REF_EVENT(xfs_perag_set_reclaim); DEFINE_PERAG_REF_EVENT(xfs_perag_clear_reclaim); -DEFINE_PERAG_REF_EVENT(xfs_perag_set_eofblocks); -DEFINE_PERAG_REF_EVENT(xfs_perag_clear_eofblocks); -DEFINE_PERAG_REF_EVENT(xfs_perag_set_cowblocks); -DEFINE_PERAG_REF_EVENT(xfs_perag_clear_cowblocks); +DEFINE_PERAG_REF_EVENT(xfs_perag_set_blockgc); +DEFINE_PERAG_REF_EVENT(xfs_perag_clear_blockgc); DECLARE_EVENT_CLASS(xfs_ag_class, TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno), @@ -358,7 +357,7 @@ DEFINE_BUF_EVENT(xfs_buf_get_uncached); DEFINE_BUF_EVENT(xfs_buf_item_relse); DEFINE_BUF_EVENT(xfs_buf_iodone_async); DEFINE_BUF_EVENT(xfs_buf_error_relse); -DEFINE_BUF_EVENT(xfs_buf_wait_buftarg); +DEFINE_BUF_EVENT(xfs_buf_drain_buftarg); DEFINE_BUF_EVENT(xfs_trans_read_buf_shut); /* not really buffer traces, but the buf provides useful information */ @@ -1287,8 +1286,8 @@ TRACE_EVENT(xfs_log_assign_tail_lsn, ) DECLARE_EVENT_CLASS(xfs_file_class, - TP_PROTO(struct xfs_inode *ip, size_t count, loff_t offset), - TP_ARGS(ip, count, offset), + TP_PROTO(struct kiocb *iocb, struct iov_iter *iter), + TP_ARGS(iocb, iter), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_ino_t, ino) @@ -1297,11 +1296,11 @@ DECLARE_EVENT_CLASS(xfs_file_class, __field(size_t, count) ), TP_fast_assign( - __entry->dev = VFS_I(ip)->i_sb->s_dev; - __entry->ino = ip->i_ino; - __entry->size = ip->i_d.di_size; - __entry->offset = offset; - __entry->count = count; + __entry->dev = file_inode(iocb->ki_filp)->i_sb->s_dev; + __entry->ino = XFS_I(file_inode(iocb->ki_filp))->i_ino; + __entry->size = XFS_I(file_inode(iocb->ki_filp))->i_d.di_size; + __entry->offset = iocb->ki_pos; + __entry->count = iov_iter_count(iter); ), TP_printk("dev %d:%d ino 0x%llx size 0x%llx offset 0x%llx count 0x%zx", MAJOR(__entry->dev), MINOR(__entry->dev), @@ -1313,14 +1312,16 @@ DECLARE_EVENT_CLASS(xfs_file_class, #define DEFINE_RW_EVENT(name) \ DEFINE_EVENT(xfs_file_class, name, \ - TP_PROTO(struct xfs_inode *ip, size_t count, loff_t offset), \ - TP_ARGS(ip, count, offset)) + TP_PROTO(struct kiocb *iocb, struct iov_iter *iter), \ + TP_ARGS(iocb, iter)) DEFINE_RW_EVENT(xfs_file_buffered_read); DEFINE_RW_EVENT(xfs_file_direct_read); DEFINE_RW_EVENT(xfs_file_dax_read); DEFINE_RW_EVENT(xfs_file_buffered_write); DEFINE_RW_EVENT(xfs_file_direct_write); DEFINE_RW_EVENT(xfs_file_dax_write); +DEFINE_RW_EVENT(xfs_reflink_bounce_dio_write); + DECLARE_EVENT_CLASS(xfs_imap_class, TP_PROTO(struct xfs_inode *ip, xfs_off_t offset, ssize_t count, @@ -3294,8 +3295,6 @@ DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_found); DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_enospc); DEFINE_INODE_IREC_EVENT(xfs_reflink_convert_cow); -DEFINE_SIMPLE_IO_EVENT(xfs_reflink_bounce_dio_write); - DEFINE_SIMPLE_IO_EVENT(xfs_reflink_cancel_cow_range); DEFINE_SIMPLE_IO_EVENT(xfs_reflink_end_cow); DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_remap); @@ -3888,6 +3887,47 @@ DEFINE_EVENT(xfs_timestamp_range_class, name, \ DEFINE_TIMESTAMP_RANGE_EVENT(xfs_inode_timestamp_range); DEFINE_TIMESTAMP_RANGE_EVENT(xfs_quota_expiry_range); +DECLARE_EVENT_CLASS(xfs_eofblocks_class, + TP_PROTO(struct xfs_mount *mp, struct xfs_eofblocks *eofb, + unsigned long caller_ip), + TP_ARGS(mp, eofb, caller_ip), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(__u32, flags) + __field(uint32_t, uid) + __field(uint32_t, gid) + __field(prid_t, prid) + __field(__u64, min_file_size) + __field(unsigned long, caller_ip) + ), + TP_fast_assign( + __entry->dev = mp->m_super->s_dev; + __entry->flags = eofb ? eofb->eof_flags : 0; + __entry->uid = eofb ? from_kuid(mp->m_super->s_user_ns, + eofb->eof_uid) : 0; + __entry->gid = eofb ? from_kgid(mp->m_super->s_user_ns, + eofb->eof_gid) : 0; + __entry->prid = eofb ? eofb->eof_prid : 0; + __entry->min_file_size = eofb ? eofb->eof_min_file_size : 0; + __entry->caller_ip = caller_ip; + ), + TP_printk("dev %d:%d flags 0x%x uid %u gid %u prid %u minsize %llu caller %pS", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->flags, + __entry->uid, + __entry->gid, + __entry->prid, + __entry->min_file_size, + (char *)__entry->caller_ip) +); +#define DEFINE_EOFBLOCKS_EVENT(name) \ +DEFINE_EVENT(xfs_eofblocks_class, name, \ + TP_PROTO(struct xfs_mount *mp, struct xfs_eofblocks *eofb, \ + unsigned long caller_ip), \ + TP_ARGS(mp, eofb, caller_ip)) +DEFINE_EOFBLOCKS_EVENT(xfs_ioc_free_eofblocks); +DEFINE_EOFBLOCKS_EVENT(xfs_blockgc_free_space); + #endif /* _TRACE_XFS_H */ #undef TRACE_INCLUDE_PATH diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c index e72730f85af1..44f72c09c203 100644 --- a/fs/xfs/xfs_trans.c +++ b/fs/xfs/xfs_trans.c @@ -20,6 +20,10 @@ #include "xfs_trace.h" #include "xfs_error.h" #include "xfs_defer.h" +#include "xfs_inode.h" +#include "xfs_dquot_item.h" +#include "xfs_dquot.h" +#include "xfs_icache.h" kmem_zone_t *xfs_trans_zone; @@ -285,6 +289,17 @@ xfs_trans_alloc( tp->t_firstblock = NULLFSBLOCK; error = xfs_trans_reserve(tp, resp, blocks, rtextents); + if (error == -ENOSPC) { + /* + * We weren't able to reserve enough space for the transaction. + * Flush the other speculative space allocations to free space. + * Do not perform a synchronous scan because callers can hold + * other locks. + */ + error = xfs_blockgc_free_space(mp, NULL); + if (!error) + error = xfs_trans_reserve(tp, resp, blocks, rtextents); + } if (error) { xfs_trans_cancel(tp); return error; @@ -1024,3 +1039,183 @@ xfs_trans_roll( tres.tr_logflags = XFS_TRANS_PERM_LOG_RES; return xfs_trans_reserve(*tpp, &tres, 0, 0); } + +/* + * Allocate an transaction, lock and join the inode to it, and reserve quota. + * + * The caller must ensure that the on-disk dquots attached to this inode have + * already been allocated and initialized. The caller is responsible for + * releasing ILOCK_EXCL if a new transaction is returned. + */ +int +xfs_trans_alloc_inode( + struct xfs_inode *ip, + struct xfs_trans_res *resv, + unsigned int dblocks, + unsigned int rblocks, + bool force, + struct xfs_trans **tpp) +{ + struct xfs_trans *tp; + struct xfs_mount *mp = ip->i_mount; + bool retried = false; + int error; + +retry: + error = xfs_trans_alloc(mp, resv, dblocks, + rblocks / mp->m_sb.sb_rextsize, + force ? XFS_TRANS_RESERVE : 0, &tp); + if (error) + return error; + + xfs_ilock(ip, XFS_ILOCK_EXCL); + xfs_trans_ijoin(tp, ip, 0); + + error = xfs_qm_dqattach_locked(ip, false); + if (error) { + /* Caller should have allocated the dquots! */ + ASSERT(error != -ENOENT); + goto out_cancel; + } + + error = xfs_trans_reserve_quota_nblks(tp, ip, dblocks, rblocks, force); + if ((error == -EDQUOT || error == -ENOSPC) && !retried) { + xfs_trans_cancel(tp); + xfs_iunlock(ip, XFS_ILOCK_EXCL); + xfs_blockgc_free_quota(ip, 0); + retried = true; + goto retry; + } + if (error) + goto out_cancel; + + *tpp = tp; + return 0; + +out_cancel: + xfs_trans_cancel(tp); + xfs_iunlock(ip, XFS_ILOCK_EXCL); + return error; +} + +/* + * Allocate an transaction in preparation for inode creation by reserving quota + * against the given dquots. Callers are not required to hold any inode locks. + */ +int +xfs_trans_alloc_icreate( + struct xfs_mount *mp, + struct xfs_trans_res *resv, + struct xfs_dquot *udqp, + struct xfs_dquot *gdqp, + struct xfs_dquot *pdqp, + unsigned int dblocks, + struct xfs_trans **tpp) +{ + struct xfs_trans *tp; + bool retried = false; + int error; + +retry: + error = xfs_trans_alloc(mp, resv, dblocks, 0, 0, &tp); + if (error) + return error; + + error = xfs_trans_reserve_quota_icreate(tp, udqp, gdqp, pdqp, dblocks); + if ((error == -EDQUOT || error == -ENOSPC) && !retried) { + xfs_trans_cancel(tp); + xfs_blockgc_free_dquots(mp, udqp, gdqp, pdqp, 0); + retried = true; + goto retry; + } + if (error) { + xfs_trans_cancel(tp); + return error; + } + + *tpp = tp; + return 0; +} + +/* + * Allocate an transaction, lock and join the inode to it, and reserve quota + * in preparation for inode attribute changes that include uid, gid, or prid + * changes. + * + * The caller must ensure that the on-disk dquots attached to this inode have + * already been allocated and initialized. The ILOCK will be dropped when the + * transaction is committed or cancelled. + */ +int +xfs_trans_alloc_ichange( + struct xfs_inode *ip, + struct xfs_dquot *new_udqp, + struct xfs_dquot *new_gdqp, + struct xfs_dquot *new_pdqp, + bool force, + struct xfs_trans **tpp) +{ + struct xfs_trans *tp; + struct xfs_mount *mp = ip->i_mount; + struct xfs_dquot *udqp; + struct xfs_dquot *gdqp; + struct xfs_dquot *pdqp; + bool retried = false; + int error; + +retry: + error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ichange, 0, 0, 0, &tp); + if (error) + return error; + + xfs_ilock(ip, XFS_ILOCK_EXCL); + xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); + + error = xfs_qm_dqattach_locked(ip, false); + if (error) { + /* Caller should have allocated the dquots! */ + ASSERT(error != -ENOENT); + goto out_cancel; + } + + /* + * For each quota type, skip quota reservations if the inode's dquots + * now match the ones that came from the caller, or the caller didn't + * pass one in. The inode's dquots can change if we drop the ILOCK to + * perform a blockgc scan, so we must preserve the caller's arguments. + */ + udqp = (new_udqp != ip->i_udquot) ? new_udqp : NULL; + gdqp = (new_gdqp != ip->i_gdquot) ? new_gdqp : NULL; + pdqp = (new_pdqp != ip->i_pdquot) ? new_pdqp : NULL; + if (udqp || gdqp || pdqp) { + unsigned int qflags = XFS_QMOPT_RES_REGBLKS; + + if (force) + qflags |= XFS_QMOPT_FORCE_RES; + + /* + * Reserve enough quota to handle blocks on disk and reserved + * for a delayed allocation. We'll actually transfer the + * delalloc reservation between dquots at chown time, even + * though that part is only semi-transactional. + */ + error = xfs_trans_reserve_quota_bydquots(tp, mp, udqp, gdqp, + pdqp, ip->i_d.di_nblocks + ip->i_delayed_blks, + 1, qflags); + if ((error == -EDQUOT || error == -ENOSPC) && !retried) { + xfs_trans_cancel(tp); + xfs_blockgc_free_dquots(mp, udqp, gdqp, pdqp, 0); + retried = true; + goto retry; + } + if (error) + goto out_cancel; + } + + *tpp = tp; + return 0; + +out_cancel: + xfs_trans_cancel(tp); + return error; +} diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h index 084658946cc8..8b03fbfe9a1b 100644 --- a/fs/xfs/xfs_trans.h +++ b/fs/xfs/xfs_trans.h @@ -268,4 +268,17 @@ xfs_trans_item_relog( return lip->li_ops->iop_relog(lip, tp); } +struct xfs_dquot; + +int xfs_trans_alloc_inode(struct xfs_inode *ip, struct xfs_trans_res *resv, + unsigned int dblocks, unsigned int rblocks, bool force, + struct xfs_trans **tpp); +int xfs_trans_alloc_icreate(struct xfs_mount *mp, struct xfs_trans_res *resv, + struct xfs_dquot *udqp, struct xfs_dquot *gdqp, + struct xfs_dquot *pdqp, unsigned int dblocks, + struct xfs_trans **tpp); +int xfs_trans_alloc_ichange(struct xfs_inode *ip, struct xfs_dquot *udqp, + struct xfs_dquot *gdqp, struct xfs_dquot *pdqp, bool force, + struct xfs_trans **tpp); + #endif /* __XFS_TRANS_H__ */ diff --git a/fs/xfs/xfs_trans_dquot.c b/fs/xfs/xfs_trans_dquot.c index 28b8ac701919..48e09ea30ee5 100644 --- a/fs/xfs/xfs_trans_dquot.c +++ b/fs/xfs/xfs_trans_dquot.c @@ -16,6 +16,7 @@ #include "xfs_quota.h" #include "xfs_qm.h" #include "xfs_trace.h" +#include "xfs_error.h" STATIC void xfs_trans_alloc_dqinfo(xfs_trans_t *); @@ -691,9 +692,11 @@ xfs_trans_dqresv( nblks); xfs_trans_mod_dquot(tp, dqp, XFS_TRANS_DQ_RES_INOS, ninos); } - ASSERT(dqp->q_blk.reserved >= dqp->q_blk.count); - ASSERT(dqp->q_rtb.reserved >= dqp->q_rtb.count); - ASSERT(dqp->q_ino.reserved >= dqp->q_ino.count); + + if (XFS_IS_CORRUPT(mp, dqp->q_blk.reserved < dqp->q_blk.count) || + XFS_IS_CORRUPT(mp, dqp->q_rtb.reserved < dqp->q_rtb.count) || + XFS_IS_CORRUPT(mp, dqp->q_ino.reserved < dqp->q_ino.count)) + goto error_corrupt; xfs_dqunlock(dqp); return 0; @@ -703,6 +706,10 @@ error_return: if (xfs_dquot_type(dqp) == XFS_DQTYPE_PROJ) return -ENOSPC; return -EDQUOT; +error_corrupt: + xfs_dqunlock(dqp); + xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); + return -EFSCORRUPTED; } @@ -780,28 +787,60 @@ int xfs_trans_reserve_quota_nblks( struct xfs_trans *tp, struct xfs_inode *ip, - int64_t nblks, - long ninos, - uint flags) + int64_t dblocks, + int64_t rblocks, + bool force) { struct xfs_mount *mp = ip->i_mount; + unsigned int qflags = 0; + int error; if (!XFS_IS_QUOTA_RUNNING(mp) || !XFS_IS_QUOTA_ON(mp)) return 0; ASSERT(!xfs_is_quota_inode(&mp->m_sb, ip->i_ino)); - ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); - ASSERT((flags & ~(XFS_QMOPT_FORCE_RES)) == XFS_TRANS_DQ_RES_RTBLKS || - (flags & ~(XFS_QMOPT_FORCE_RES)) == XFS_TRANS_DQ_RES_BLKS); - /* - * Reserve nblks against these dquots, with trans as the mediator. - */ - return xfs_trans_reserve_quota_bydquots(tp, mp, - ip->i_udquot, ip->i_gdquot, - ip->i_pdquot, - nblks, ninos, flags); + if (force) + qflags |= XFS_QMOPT_FORCE_RES; + + /* Reserve data device quota against the inode's dquots. */ + error = xfs_trans_reserve_quota_bydquots(tp, mp, ip->i_udquot, + ip->i_gdquot, ip->i_pdquot, dblocks, 0, + XFS_QMOPT_RES_REGBLKS | qflags); + if (error) + return error; + + /* Do the same but for realtime blocks. */ + error = xfs_trans_reserve_quota_bydquots(tp, mp, ip->i_udquot, + ip->i_gdquot, ip->i_pdquot, rblocks, 0, + XFS_QMOPT_RES_RTBLKS | qflags); + if (error) { + xfs_trans_reserve_quota_bydquots(tp, mp, ip->i_udquot, + ip->i_gdquot, ip->i_pdquot, -dblocks, 0, + XFS_QMOPT_RES_REGBLKS); + return error; + } + + return 0; +} + +/* Change the quota reservations for an inode creation activity. */ +int +xfs_trans_reserve_quota_icreate( + struct xfs_trans *tp, + struct xfs_dquot *udqp, + struct xfs_dquot *gdqp, + struct xfs_dquot *pdqp, + int64_t dblocks) +{ + struct xfs_mount *mp = tp->t_mountp; + + if (!XFS_IS_QUOTA_RUNNING(mp) || !XFS_IS_QUOTA_ON(mp)) + return 0; + + return xfs_trans_reserve_quota_bydquots(tp, mp, udqp, gdqp, pdqp, + dblocks, 1, XFS_QMOPT_RES_REGBLKS); } /* diff --git a/fs/zonefs/Kconfig b/fs/zonefs/Kconfig index ef2697b78820..827278f937fe 100644 --- a/fs/zonefs/Kconfig +++ b/fs/zonefs/Kconfig @@ -3,6 +3,7 @@ config ZONEFS_FS depends on BLOCK depends on BLK_DEV_ZONED select FS_IOMAP + select CRC32 help zonefs is a simple file system which exposes zones of a zoned block device (e.g. host-managed or host-aware SMR disk drives) as files. diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index bec47f2d074b..a29653c0196b 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -541,7 +541,7 @@ static int zonefs_file_fsync(struct file *file, loff_t start, loff_t end, if (ZONEFS_I(inode)->i_ztype == ZONEFS_ZTYPE_CNV) ret = file_write_and_wait_range(file, start, end); if (!ret) - ret = blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL); + ret = blkdev_issue_flush(inode->i_sb->s_bdev); if (ret) zonefs_io_error(inode, true); @@ -678,7 +678,7 @@ static ssize_t zonefs_file_dio_append(struct kiocb *iocb, struct iov_iter *from) if (!nr_pages) return 0; - bio = bio_alloc_bioset(GFP_NOFS, nr_pages, &fs_bio_set); + bio = bio_alloc(GFP_NOFS, nr_pages); if (!bio) return -ENOMEM; @@ -780,7 +780,7 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from) ret = zonefs_file_dio_append(iocb, from); else ret = iomap_dio_rw(iocb, from, &zonefs_iomap_ops, - &zonefs_write_dio_ops, sync); + &zonefs_write_dio_ops, 0); if (zi->i_ztype == ZONEFS_ZTYPE_SEQ && (ret > 0 || ret == -EIOCBQUEUED)) { if (ret > 0) @@ -917,7 +917,7 @@ static ssize_t zonefs_file_read_iter(struct kiocb *iocb, struct iov_iter *to) } file_accessed(iocb->ki_filp); ret = iomap_dio_rw(iocb, to, &zonefs_iomap_ops, - &zonefs_read_dio_ops, is_sync_kiocb(iocb)); + &zonefs_read_dio_ops, 0); } else { ret = generic_file_read_iter(iocb, to); if (ret == -EIO) @@ -1581,12 +1581,11 @@ static int zonefs_fill_super(struct super_block *sb, void *data, int silent) sb->s_time_gran = 1; /* - * The block size is set to the device physical sector size to ensure - * that write operations on 512e devices (512B logical block and 4KB - * physical block) are always aligned to the device physical blocks, - * as mandated by the ZBC/ZAC specifications. + * The block size is set to the device zone write granularity to ensure + * that write operations are always aligned according to the device + * interface constraints. */ - sb_set_blocksize(sb, bdev_physical_block_size(sb->s_bdev)); + sb_set_blocksize(sb, bdev_zone_write_granularity(sb->s_bdev)); sbi->s_zone_sectors_shift = ilog2(bdev_zone_sectors(sb->s_bdev)); sbi->s_uid = GLOBAL_ROOT_UID; sbi->s_gid = GLOBAL_ROOT_GID; |